Publications by authors named "Gilmer Valdes"

41 Publications

A situational awareness Bayesian network approach for accurate and credible personalized adaptive radiotherapy outcomes prediction in lung cancer patients.

Phys Med 2021 Jun 4;87:11-23. Epub 2021 Jun 4.

Department of Radiation Oncology, The University of Michigan, Ann Arbor, MI, USA.

Purpose: A situational awareness Bayesian network (SA-BN) approach is developed to improve physicians' trust in the prediction of radiation outcomes and evaluate its performance for personalized adaptive radiotherapy (pART).

Methods: 118 non-small-cell lung cancer patients with their biophysical features were employed for discovery (n = 68) and validation (n = 50) of radiation outcomes prediction modeling. Patients' important characteristics identified by radiation experts to predict individual's tumor local control (LC) or radiation pneumonitis with grade ≥ 2 (RP2) were incorporated as expert knowledge (EK). Besides generating an EK-based naïve BN (EK-NBN), an SA-BN was developed by incorporating the EK features into pure data-driven BN (PD-BN) methods to improve the credibility of LC or / and RP2 prediction. After using area under the free-response receiver operating characteristics curve (AU-FROC) to assess the joint prediction of these outcomes, their prediction performances were compared with a regression approach based on the expert yielded estimates (EYE) penalty and its variants.

Results: In addition to improving the credibility of radiation outcomes prediction, the SA-BN approach outperformed the EYE penalty and its variants in terms of the joint prediction of LC and RP2. The value of AU-FROC improves from 0.70 (95% CI: 0.54-0.76) using EK-NBN, to 0.75 (0.65-0.82) using a variant of EYE penalty, to 0.83 (0.75-0.93) using PD-BN and 0.83 (0.77-0.90) using SA-BN; with similar trends in the validation cohort.

Conclusions: The SA-BN approach can provide an accurate and credible human-machine interface to gain physicians' trust in clinical decision-making, which has the potential to be an important component of pART.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejmp.2021.05.032DOI Listing
June 2021

Salvage high dose rate brachytherapy for recurrent prostate cancer after definitive radiation.

Pract Radiat Oncol 2021 May 30. Epub 2021 May 30.

Department of Radiation Oncology, University of California, San Francisco; San Francisco, CA. Electronic address:

Purpose: Salvage high-dose-rate brachytherapy (sHDRBT) for locally recurrent prostate cancer after definitive radiation is associated with biochemical control in approximately half of patients at 3-5 years. Given potential toxicity, patient selection is critical. We present our institutional experience with sHDRBT and validate a recursive partitioning machines model for biochemical control.

Materials And Methods: We performed a retrospective analysis of 129 patients who underwent whole-gland sHDRBT between 1998-2016. We evaluated clinical factors associated with biochemical control as well as toxicity.

Results: At diagnosis the median PSA was 7.77 ng/mL. Majority of patients had T1-2 (73%) and Gleason 6-7 (82%) disease. 71% received external beam RT alone, while 22% received permanent prostate implants. The median disease free interval (DFI) was 56 months, and median pre-salvage PSA was 4.95ng/mL. At sHDRBT, 46% had T3 disease and 51% had Gleason 8-10 disease. At a median of 68 months following sHDRBT, 3 and 5-year disease free survival were 85% (95% CI 79-91%) and 71% (95% CI 62-79%), respectively. Median PSA nadir was 0.18 ng/mL, achieved a median of 10 months after sHDRBT. Patients with ≥35%+ cores and a DFI <4.1 years had worse biochemical control (19% vs. 50%, p = 0.02). Local failure (with or without regional/distant failure) was seen in 11% of patients (14/129). 14 patients (11%) developed acute urinary obstruction requiring Foley placement and 19 patients (15%) developed strictures requiring dilation.

Conclusions: sHDRBT is a reasonable option for patients with locally recurrent prostate cancer following definitive RT. Those with <35%+ cores or an initial DFI of ≥4.1 years may be more likely to achieve long-term disease control following sHDRBT.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.prro.2021.04.007DOI Listing
May 2021

Artificial intelligence and machine learning for medical imaging: A technology review.

Phys Med 2021 Mar 9;83:242-256. Epub 2021 May 9.

Molecular Imaging, Radiation and Oncology (MIRO) Laboratory, UCLouvain, Belgium.

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejmp.2021.04.016DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8184621PMC
March 2021

Artificial intelligence for prediction of measurement-based patient-specific quality assurance is ready for prime time.

Med Phys 2021 Apr 2. Epub 2021 Apr 2.

Department of Radiation Oncology, Duke University, Durham, NC, 27710, USA.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.14870DOI Listing
April 2021

Integration of AI and Machine Learning in Radiotherapy QA.

Front Artif Intell 2020 29;3:577620. Epub 2020 Sep 29.

Department of Radiation Oncology, University of California, San Francisco, San Francisco, CA, United States.

The use of machine learning and other sophisticated models to aid in prediction and decision making has become widely popular across a breadth of disciplines. Within the greater diagnostic radiology, radiation oncology, and medical physics communities promising work is being performed in tissue classification and cancer staging, outcome prediction, automated segmentation, treatment planning, and quality assurance as well as other areas. In this article, machine learning approaches are explored, highlighting specific applications in machine and patient-specific quality assurance (QA). Machine learning can analyze multiple elements of a delivery system on its performance over time including the multileaf collimator (MLC), imaging system, mechanical and dosimetric parameters. Virtual Intensity-Modulated Radiation Therapy (IMRT) QA can predict passing rates using different measurement techniques, different treatment planning systems, and different treatment delivery machines across multiple institutions. Prediction of QA passing rates and other metrics can have profound implications on the current IMRT process. Here we cover general concepts of machine learning in dosimetry and various methods used in virtual IMRT QA, as well as their clinical applications.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/frai.2020.577620DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7861232PMC
September 2020

Targeted transfer learning to improve performance in small medical physics datasets.

Med Phys 2020 Dec 25;47(12):6246-6256. Epub 2020 Oct 25.

Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, 94158, USA.

Purpose: To perform an in-depth evaluation of current state of the art techniques in training neural networks to identify appropriate approaches in small datasets.

Method: In total, 112,120 frontal-view X-ray images from the NIH ChestXray14 dataset were used in our analysis. Two tasks were studied: unbalanced multi-label classification of 14 diseases, and binary classification of pneumonia vs non-pneumonia. All datasets were randomly split into training, validation, and testing (70%, 10%, and 20%). Two popular convolution neural networks (CNNs), DensNet121 and ResNet50, were trained using PyTorch. We performed several experiments to test: (a) whether transfer learning using pretrained networks on ImageNet are of value to medical imaging/physics tasks (e.g., predicting toxicity from radiographic images after training on images from the internet), (b) whether using pretrained networks trained on problems that are similar to the target task helps transfer learning (e.g., using X-ray pretrained networks for X-ray target tasks), (c) whether freeze deep layers or change all weights provides an optimal transfer learning strategy, (d) the best strategy for the learning rate policy, and (e) what quantity of data is needed in order to appropriately deploy these various strategies (N = 50 to N = 77 880).

Results: In the multi-label problem, DensNet121 needed at least 1600 patients to be comparable to, and 10 000 to outperform, radiomics-based logistic regression. In classifying pneumonia vs non-pneumonia, both CNN and radiomics-based methods performed poorly when N < 2000. For small datasets ( < 2000), however, a significant boost in performance (>15% increase on AUC) comes from a good selection of the transfer learning dataset, dropout, cycling learning rate, and freezing and unfreezing of deep layers as training progresses. In contrast, if sufficient data are available (>35 000), little or no tweaking is needed to obtain impressive performance. While transfer learning using X-ray images from other anatomical sites improves performance, we also observed a similar boost by using pretrained networks from ImageNet. Having source images from the same anatomical site, however, outperforms every other methodology, by up to 15%. In this case, DL models can be trained with as little as N = 50.

Conclusions: While training DL models in small datasets (N < 2000) is challenging, no tweaking is necessary for bigger datasets (N > 35 000). Using transfer learning with images from the same anatomical site can yield remarkable performance in new tasks with as few as N = 50. Surprisingly, we did not find any advantage for using images from other anatomical sites over networks that have been trained using ImageNet. This indicates that features learned may not be as general as currently believed, and performance decays rapidly even by just changing the anatomical site of the images.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.14507DOI Listing
December 2020

Machine learning for radiation outcome modeling and prediction.

Med Phys 2020 Jun;47(5):e178-e184

Department of Radiation Oncology, University of California, San Francisco, CA, 94158, USA.

Aims: This review paper intends to summarize the application of machine learning to radiotherapy outcome modeling based on structured and un-structured radiation oncology datasets.

Materials And Methods: The most appropriate machine learning approaches for structured datasets in terms of accuracy and interpretability are identified. For un-structured datasets, deep learning algorithms are explored and a critical view of the use of these approaches in radiation oncology is also provided.

Conclusions: We discuss the challenges in radiotherapy outcome prediction, and suggest to improve radiation outcome modeling by developing appropriate machine learning approaches where both accuracy and interpretability are taken into account.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.13570DOI Listing
June 2020

Expert-augmented machine learning.

Proc Natl Acad Sci U S A 2020 03 18;117(9):4571-4577. Epub 2020 Feb 18.

Department of Radiation Oncology, University of California, San Francisco, CA 94143.

Machine learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption is limited by the level of trust afforded by given models. Human vs. machine performance is commonly compared empirically to decide whether a certain task should be performed by a computer or an expert. In reality, the optimal learning strategy may involve combining the complementary strengths of humans and machines. Here, we present expert-augmented machine learning (EAML), an automated method that guides the extraction of expert knowledge and its integration into machine-learned models. We used a large dataset of intensive-care patient data to derive 126 decision rules that predict hospital mortality. Using an online platform, we asked 15 clinicians to assess the relative risk of the subpopulation defined by each rule compared to the total sample. We compared the clinician-assessed risk to the empirical risk and found that, while clinicians agreed with the data in most cases, there were notable exceptions where they overestimated or underestimated the true risk. Studying the rules with greatest disagreement, we identified problems with the training data, including one miscoded variable and one hidden confounder. Filtering the rules based on the extent of disagreement between clinician-assessed risk and empirical risk, we improved performance on out-of-sample data and were able to train with less data. EAML provides a platform for automated creation of problem-specific priors, which help build robust and dependable machine-learning models in critical applications.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1073/pnas.1906831117DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7060733PMC
March 2020

Integrated models incorporating radiologic and radiomic features predict meningioma grade, local failure, and overall survival.

Neurooncol Adv 2019 May-Dec;1(1):vdz011. Epub 2019 Aug 28.

Department of Radiation Oncology, University of California San Francisco, California.

Background: We investigated prognostic models based on clinical, radiologic, and radiomic feature to preoperatively identify meningiomas at risk for poor outcomes.

Methods: Retrospective review was performed for 303 patients who underwent resection of 314 meningiomas (57% World Health Organization grade I, 35% grade II, and 8% grade III) at two independent institutions, which comprised primary and external datasets. For each patient in the primary dataset, 16 radiologic and 172 radiomic features were extracted from preoperative magnetic resonance images, and prognostic features for grade, local failure (LF) or overall survival (OS) were identified using the Kaplan-Meier method, log-rank tests and recursive partitioning analysis. Regressions and random forests were used to generate and test prognostic models, which were validated using the external dataset.

Results: Multivariate analysis revealed that apparent diffusion coefficient hypointensity (HR 5.56, 95% CI 2.01-16.7, = .002) was associated with high grade meningioma, and low sphericity was associated both with increased LF (HR 2.0, 95% CI 1.1-3.5, = .02) and worse OS (HR 2.94, 95% CI 1.47-5.56, = .002). Both radiologic and radiomic predictors of adverse meningioma outcomes were significantly associated with molecular markers of aggressive meningioma biology, such as somatic mutation burden, DNA methylation status, and expression. Integrated prognostic models combining clinical, radiologic, and radiomic features demonstrated improved accuracy for meningioma grade, LF, and OS (area under the curve 0.78, 0.75, and 0.78, respectively) compared to models based on clinical features alone.

Conclusions: Preoperative radiologic and radiomic features such as apparent diffusion coefficient and sphericity can predict tumor grade, LF, and OS in patients with meningioma.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/noajnl/vdz011DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6777505PMC
August 2019

Building more accurate decision trees with the additive tree.

Proc Natl Acad Sci U S A 2019 10 16;116(40):19887-19893. Epub 2019 Sep 16.

Department of Radiation Oncology, University of California, San Francisco, CA 94115;

The expansion of machine learning to high-stakes application domains such as medicine, finance, and criminal justice, where making informed decisions requires clear understanding of the model, has increased the interest in interpretable machine learning. The widely used Classification and Regression Trees (CART) have played a major role in health sciences, due to their simple and intuitive explanation of predictions. Ensemble methods like gradient boosting can improve the accuracy of decision trees, but at the expense of the interpretability of the generated model. Additive models, such as those produced by gradient boosting, and full interaction models, such as CART, have been investigated largely in isolation. We show that these models exist along a spectrum, revealing previously unseen connections between these approaches. This paper introduces a rigorous formalization for the additive tree, an empirically validated learning technique for creating a single decision tree, and shows that this method can produce models equivalent to CART or gradient boosted stumps at the extremes by varying a single parameter. Although the additive tree is designed primarily to provide both the model interpretability and predictive performance needed for high-stakes applications like medicine, it also can produce decision trees represented by hybrid models between CART and boosted stumps that can outperform either of these approaches.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1073/pnas.1816748116DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6778203PMC
October 2019

In Reply to Gensheimer and Trister.

Int J Radiat Oncol Biol Phys 2018 12;102(5):1594-1596

Department of Computer and Information Science, University of Pennsylvania, Philadelphia, Pennsylvania.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijrobp.2018.08.009DOI Listing
December 2018

Predicting radiation pneumonitis in locally advanced stage II-III non-small cell lung cancer using machine learning.

Radiother Oncol 2019 04 23;133:106-112. Epub 2019 Jan 23.

Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, United States.

Background And Purpose: Radiation pneumonitis (RP) is a radiotherapy dose-limiting toxicity for locally advanced non-small cell lung cancer (LA-NSCLC). Prior studies have proposed relevant dosimetric constraints to limit this toxicity. Using machine learning algorithms, we performed analyses of contributing factors in the development of RP to uncover previously unidentified criteria and elucidate the relative importance of individual factors.

Materials And Methods: We evaluated 32 clinical features per patient in a cohort of 203 stage II-III LA-NSCLC patients treated with definitive chemoradiation to a median dose of 66.6 Gy in 1.8 Gy daily fractions at our institution from 2008 to 2016. Of this cohort, 17.7% of patients developed grade ≥2 RP. Univariate analysis was performed using trained decision stumps to individually analyze statistically significant predictors of RP and perform feature selection. Applying Random Forest, we performed multivariate analysis to assess the combined performance of important predictors of RP.

Results: On univariate analysis, lung V20, lung mean, lung V10 and lung V5 were found to be significant RP predictors with the greatest balance of specificity and sensitivity. On multivariate analysis, Random Forest (AUC = 0.66, p = 0.0005) identified esophagus max (20.5%), lung V20 (16.4%), lung mean (15.7%) and pack-year (14.9%) as the most common primary differentiators of RP.

Conclusions: We highlight Random Forest as an accurate machine learning method to identify known and new predictors of symptomatic RP. Furthermore, this analysis confirms the importance of lung V20, lung mean and pack-year as predictors of RP while also introducing esophagus max as an important RP predictor.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.radonc.2019.01.003DOI Listing
April 2019

Optimizing beam models for dosimetric accuracy over a wide range of treatments.

Phys Med 2019 Feb 24;58:47-53. Epub 2019 Jan 24.

Department of Radiation Oncology, University of California San Francisco, 1600 Divisadero Street, Suite H1031, San Francisco, CA 94115, United States.

This work presents a systematic approach for testing a dose calculation algorithm over a variety of conditions designed to span the possible range of clinical treatment plans. Using this method, a TrueBeam STx machine with high definition multi-leaf collimators (MLCs) was commissioned in the RayStation treatment planning system (TPS). The initial model parameters values were determined by comparing TPS calculations with standard measured depth dose and profile curves. The MLC leaf offset calibration was determined by comparing measured and calculated field edges utilizing a wide range of MLC retracted and over-travel positions. The radial fluence was adjusted using profiles through both the center and corners of the largest field size, and through measurements of small fields that were located at highly off-axis positions. The flattening filter source was adjusted to improve the TPS agreement for the output of MLC-defined fields with much larger jaw openings. The MLC leaf transmission and leaf end parameters were adjusted to optimize the TPS agreement for highly modulated intensity-modulated radiotherapy (IMRT) plans. The final model was validated for simple open fields, multiple field configurations, the TG 119 C-shape target test, and a battery of clinical IMRT and volumetric-modulated arc therapy (VMAT) plans. The commissioning process detected potential dosimetric errors of over 10% and resulted in a final model that provided in general 3% dosimetric accuracy. This study demonstrates the importance of using a variety of conditions to adjust a beam model and provides an effective framework for achieving high dosimetric accuracy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ejmp.2019.01.011DOI Listing
February 2019

The application of artificial intelligence in the IMRT planning process for head and neck cancer.

Oral Oncol 2018 12 31;87:111-116. Epub 2018 Oct 31.

Department of Radiation Oncology, University of California, San Francisco, CA 94115, USA. Electronic address:

Artificial intelligence (AI) is beginning to transform IMRT treatment planning for head and neck patients. However, the complexity and novelty of AI algorithms make them susceptible to misuse by researchers and clinicians. Understanding nuances of new technologies could serve to mitigate potential clinical implementation pitfalls. This article is intended to facilitate integration of AI into the radiotherapy clinic by providing an overview of AI algorithms, including support vector machines (SVMs), random forests (RF), gradient boosting (GB), and several variations of deep learning. This document describes current AI algorithms that have been applied to head and neck IMRT planning and identifies rapidly growing branches of AI in industry that have potential applications to head and neck cancer patients receiving IMRT. AI algorithms have great clinical potential if used correctly but can also cause harm if misused, so it is important to raise the level of AI competence within radiation oncology so that the benefits can be realized in a controlled and safe manner.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.oraloncology.2018.10.026DOI Listing
December 2018

Preoperative and postoperative prediction of long-term meningioma outcomes.

PLoS One 2018 20;13(9):e0204161. Epub 2018 Sep 20.

Department of Radiation Oncology, University of California San Francisco, San Francisco, United States of America.

Background: Meningiomas are stratified according to tumor grade and extent of resection, often in isolation of other clinical variables. Here, we use machine learning (ML) to integrate demographic, clinical, radiographic and pathologic data to develop predictive models for meningioma outcomes.

Methods And Findings: We developed a comprehensive database containing information from 235 patients who underwent surgery for 257 meningiomas at a single institution from 1990 to 2015. The median follow-up was 4.3 years, and resection specimens were re-evaluated according to current diagnostic criteria, revealing 128 WHO grade I, 104 grade II and 25 grade III meningiomas. A series of ML algorithms were trained and tuned by nested resampling to create models based on preoperative features, conventional postoperative features, or both. We compared different algorithms' accuracy as well as the unique insights they offered into the data. Machine learning models restricted to preoperative information, such as patient demographics and radiographic features, had similar accuracy for predicting local failure (AUC = 0.74) or overall survival (AUC = 0.68) as models based on meningioma grade and extent of resection (AUC = 0.73 and AUC = 0.72, respectively). Integrated models incorporating all available demographic, clinical, radiographic and pathologic data provided the most accurate estimates (AUC = 0.78 and AUC = 0.74, respectively). From these models, we developed decision trees and nomograms to estimate the risks of local failure or overall survival for meningioma patients.

Conclusions: Clinical information has been historically underutilized in the prediction of meningioma outcomes. Predictive models trained on preoperative clinical data perform comparably to conventional models trained on meningioma grade and extent of resection. Combination of all available information can help stratify meningioma patients more accurately.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0204161PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6147484PMC
March 2019

A Deep Look Into the Future of Quantitative Imaging in Oncology: A Statement of Working Principles and Proposal for Change.

Int J Radiat Oncol Biol Phys 2018 11 28;102(4):1074-1082. Epub 2018 Aug 28.

The D-Lab, Grow Research Institute for Oncology, Maastricht University, Maastricht, The Netherlands.

The adoption of enterprise digital imaging, along with the development of quantitative imaging methods and the re-emergence of statistical learning, has opened the opportunity for more personalized cancer treatments through transformative data science research. In the last 5 years, accumulating evidence has indicated that noninvasive advanced imaging analytics (i.e., radiomics) can reveal key components of tumor phenotype for multiple lesions at multiple time points over the course of treatment. Many groups using homegrown software have extracted engineered and deep quantitative features on 3-dimensional medical images for better spatial and longitudinal understanding of tumor biology and for the prediction of diverse outcomes. These developments could augment patient stratification and prognostication, buttressing emerging targeted therapeutic approaches. Unfortunately, the rapid growth in popularity of this immature scientific discipline has resulted in many early publications that miss key information or use underpowered patient data sets, without production of generalizable results. Quantitative imaging research is complex, and key principles should be followed to realize its full potential. The fields of quantitative imaging and radiomics in particular require a renewed focus on optimal study design and reporting practices, standardization, interpretability, data sharing, and clinical trials. Standardization of image acquisition, feature calculation, and statistical analysis (i.e., machine learning) are required for the field to move forward. A new data-sharing paradigm enacted among open and diverse participants (medical institutions, vendors and associations) should be embraced for faster development and comprehensive clinical validation of imaging biomarkers. In this review and critique of the field, we propose working principles and fundamental changes to the current scientific approach, with the goal of high-impact research and development of actionable prediction models that will yield more meaningful applications of precision cancer medicine.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijrobp.2018.08.032DOI Listing
November 2018

Machine learning and modeling: Data, validation, communication challenges.

Med Phys 2018 Oct 24;45(10):e834-e840. Epub 2018 Aug 24.

Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, USA.

With the era of big data, the utilization of machine learning algorithms in radiation oncology is rapidly growing with applications including: treatment response modeling, treatment planning, contouring, organ segmentation, image-guidance, motion tracking, quality assurance, and more. Despite this interest, practical clinical implementation of machine learning as part of the day-to-day clinical operations is still lagging. The aim of this white paper is to further promote progress in this new field of machine learning in radiation oncology by highlighting its untapped advantages and potentials for clinical advancement, while also presenting current challenges and open questions for future research. The targeted audience of this paper includes newcomers as well as practitioners in the field of medical physics/radiation oncology. The paper also provides general recommendations to avoid common pitfalls when applying these powerful data analytic tools to medical physics and radiation oncology problems and suggests some guidelines for transparent and informative reporting of machine learning results.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.12811DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6181755PMC
October 2018

An unsupervised convolutional neural network-based algorithm for deformable image registration.

Phys Med Biol 2018 09 17;63(18):185017. Epub 2018 Sep 17.

Department of Radiation Oncology, University of California, San Francisco, CA, United States of America.

The purpose of the work is to develop a deep unsupervised learning strategy for cone-beam CT (CBCT) to CT deformable image registration (DIR). This technique uses a deep convolutional inverse graphics network (DCIGN) based DIR algorithm implemented on 2 Nvidia 1080 Ti graphics processing units. The model is comprised of an encoding and decoding stage. The fully-convolutional encoding stage learns hierarchical features and simultaneously forms an information bottleneck, while the decoding stage restores the original dimensionality of the input image. Activations from the encoding stage are used as the input channels to a sparse DIR algorithm. DCIGN was trained using a distributive learning-based convolutional neural network architecture and used 285 head and neck patients to train, validate, and test the algorithm. The accuracy of the DCIGN algorithm was evaluated on 100 synthetic cases and 12 hold out test patient cases. The results indicate that DCIGN performed better than rigid registration, intensity corrected Demons, and landmark-guided deformable image registration for all evaluation metrics. DCIGN required ~14 h to train, and ~3.5 s to make a prediction on a 512  ×  512  ×  120 voxel image. In conclusion, DCIGN is able to maintain high accuracy in the presence of CBCT noise contamination, while simultaneously preserving high computational efficiency.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6560/aada66DOI Listing
September 2018

Clinical Applications of Quantitative 3-Dimensional MRI Analysis for Pediatric Embryonal Brain Tumors.

Int J Radiat Oncol Biol Phys 2018 11 8;102(4):744-756. Epub 2018 Jun 8.

Department of Radiation Oncology, University of California, San Francisco, San Francisco, California; Department of Neurological Surgery, University of California, San Francisco, San Francisco, California. Electronic address:

Purpose: To investigate the prognostic utility of quantitative 3-dimensional magnetic resonance imaging radiomic analysis for primary pediatric embryonal brain tumors.

Methods And Materials: Thirty-four pediatric patients with embryonal brain tumor with concurrent preoperative T1-weighted postcontrast (T1PG) and T2-weighted fluid-attenuated inversion recovery (FLAIR) magnetic resonance images were identified from an institutional database. The median follow-up period was 5.2 years. Radiomic features were extracted from axial T1PG and FLAIR contours using MATLAB, and 15 features were selected for analysis based on qualitative radiographic features with prognostic significance for pediatric embryonal brain tumors. Logistic regression, linear regression, receiver operating characteristic curves, the Harrell C index, and the Somer D index were used to test the relationships between radiomic features and demographic variables, as well as clinical outcomes.

Results: Pediatric embryonal brain tumors in older patients had an increased normalized mean tumor intensity (P = .05, T1PG), decreased tumor volume (P = .02, T1PG), and increased markers of heterogeneity (P ≤ .01, T1PG and FLAIR) relative to those in younger patients. We identified 10 quantitative radiomic features that delineated medulloblastoma, pineoblastoma, and supratentorial primitive neuroectodermal tumor, including size and heterogeneity (P ≤ .05, T1PG and FLAIR). Decreased markers of tumor heterogeneity were predictive of neuraxis metastases and trended toward significance (P = .1, FLAIR). Tumors with an increased size (area under the curve = 0.7, FLAIR) and decreased heterogeneity (area under the curve = 0.7, FLAIR) at diagnosis were more likely to recur.

Conclusions: Quantitative radiomic features are associated with pediatric embryonal brain tumor patient age, histology, neuraxis metastases, and recurrence. These data suggest that quantitative 3-dimensional magnetic resonance imaging radiomic analysis has the potential to identify radiomic risk features for pediatric patients with embryonal brain tumors.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijrobp.2018.05.077DOI Listing
November 2018

Exploratory analysis using machine learning to predict for chest wall pain in patients with stage I non-small-cell lung cancer treated with stereotactic body radiation therapy.

J Appl Clin Med Phys 2018 Sep 10;19(5):539-546. Epub 2018 Jul 10.

Department of Radiation Oncology, University of Maryland, School of Medicine, Baltimore, MD, USA.

Background And Purpose: Chest wall toxicity is observed after stereotactic body radiation therapy (SBRT) for peripherally located lung tumors. We utilize machine learning algorithms to identify toxicity predictors to develop dose-volume constraints.

Materials And Methods: Twenty-five patient, tumor, and dosimetric features were recorded for 197 consecutive patients with Stage I NSCLC treated with SBRT, 11 of whom (5.6%) developed CTCAEv4 grade ≥2 chest wall pain. Decision tree modeling was used to determine chest wall syndrome (CWS) thresholds for individual features. Significant features were determined using independent multivariate methods. These methods incorporate out-of-bag estimation using Random forests (RF) and bootstrapping (100 iterations) using decision trees.

Results: Univariate analysis identified rib dose to 1 cc < 4000 cGy (P = 0.01), chest wall dose to 30 cc < 1900 cGy (P = 0.035), rib Dmax < 5100 cGy (P = 0.05) and lung dose to 1000 cc < 70 cGy (P = 0.039) to be statistically significant thresholds for avoiding CWS. Subsequent multivariate analysis confirmed the importance of rib dose to 1 cc, chest wall dose to 30 cc, and rib Dmax. Using learning-curve experiments, the dataset proved to be self-consistent and provides a realistic model for CWS analysis.

Conclusions: Using machine learning algorithms in this first of its kind study, we identify robust features and cutoffs predictive for the rare clinical event of CWS. Additional data in planned subsequent multicenter studies will help increase the accuracy of multivariate analysis.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/acm2.12415DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6123157PMC
September 2018

Artificial intelligence in radiation oncology: A specialty-wide disruptive transformation?

Radiother Oncol 2018 12 12;129(3):421-426. Epub 2018 Jun 12.

Oregon Health & Science University, Portland, USA.

Artificial intelligence (AI) is emerging as a technology with the power to transform established industries, and with applications from automated manufacturing to advertising and facial recognition to fully autonomous transportation. Advances in each of these domains have led some to call AI the "fourth" industrial revolution [1]. In healthcare, AI is emerging as both a productive and disruptive force across many disciplines. This is perhaps most evident in Diagnostic Radiology and Pathology, specialties largely built around the processing and complex interpretation of medical images, where the role of AI is increasingly seen as both a boon and a threat. In Radiation Oncology as well, AI seems poised to reshape the specialty in significant ways, though the impact of AI has been relatively limited at present, and may rightly seem more distant to many, given the predominantly interpersonal and complex interventional nature of the specialty. In this overview, we will explore the current state and anticipated future impact of AI on Radiation Oncology, in detail, focusing on key topics from multiple stakeholder perspectives, as well as the role our specialty may play in helping to shape the future of AI within the larger spectrum of medicine.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.radonc.2018.05.030DOI Listing
December 2018

Machine learning algorithms for outcome prediction in (chemo)radiotherapy: An empirical comparison of classifiers.

Med Phys 2018 Jul 13;45(7):3449-3459. Epub 2018 Jun 13.

The D-lab: Decision Support for Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Universiteitssingel 40, 6229 ER, Maastricht, The Netherlands.

Purpose: Machine learning classification algorithms (classifiers) for prediction of treatment response are becoming more popular in radiotherapy literature. General Machine learning literature provides evidence in favor of some classifier families (random forest, support vector machine, gradient boosting) in terms of classification performance. The purpose of this study is to compare such classifiers specifically for (chemo)radiotherapy datasets and to estimate their average discriminative performance for radiation treatment outcome prediction.

Methods: We collected 12 datasets (3496 patients) from prior studies on post-(chemo)radiotherapy toxicity, survival, or tumor control with clinical, dosimetric, or blood biomarker features from multiple institutions and for different tumor sites, that is, (non-)small-cell lung cancer, head and neck cancer, and meningioma. Six common classification algorithms with built-in feature selection (decision tree, random forest, neural network, support vector machine, elastic net logistic regression, LogitBoost) were applied on each dataset using the popular open-source R package caret. The R code and documentation for the analysis are available online (https://github.com/timodeist/classifier_selection_code). All classifiers were run on each dataset in a 100-repeated nested fivefold cross-validation with hyperparameter tuning. Performance metrics (AUC, calibration slope and intercept, accuracy, Cohen's kappa, and Brier score) were computed. We ranked classifiers by AUC to determine which classifier is likely to also perform well in future studies. We simulated the benefit for potential investigators to select a certain classifier for a new dataset based on our study (pre-selection based on other datasets) or estimating the best classifier for a dataset (set-specific selection based on information from the new dataset) compared with uninformed classifier selection (random selection).

Results: Random forest (best in 6/12 datasets) and elastic net logistic regression (best in 4/12 datasets) showed the overall best discrimination, but there was no single best classifier across datasets. Both classifiers had a median AUC rank of 2. Preselection and set-specific selection yielded a significant average AUC improvement of 0.02 and 0.02 over random selection with an average AUC rank improvement of 0.42 and 0.66, respectively.

Conclusion: Random forest and elastic net logistic regression yield higher discriminative performance in (chemo)radiotherapy outcome and toxicity prediction than other studied classifiers. Thus, one of these two classifiers should be the first choice for investigators when building classification models or to benchmark one's own modeling results against. Our results also show that an informed preselection of classifiers based on existing datasets can improve discrimination over random selection.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.12967DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6095141PMC
July 2018

Machine Learning in Radiation Oncology: Opportunities, Requirements, and Needs.

Front Oncol 2018 17;8:110. Epub 2018 Apr 17.

Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, United States.

Machine learning (ML) has the potential to revolutionize the field of radiation oncology, but there is much work to be done. In this article, we approach the radiotherapy process from a workflow perspective, identifying specific areas where a data-centric approach using ML could improve the quality and efficiency of patient care. We highlight areas where ML has already been used, and identify areas where we should invest additional resources. We believe that this article can serve as a guide for both clinicians and researchers to start discussing issues that must be addressed in a timely manner.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fonc.2018.00110DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5913324PMC
April 2018

Salvage HDR Brachytherapy: Multiple Hypothesis Testing Versus Machine Learning Analysis.

Int J Radiat Oncol Biol Phys 2018 07 13;101(3):694-703. Epub 2018 Mar 13.

Radiation Oncology Department, University of California San Francisco, San Francisco, California.

Purpose: Salvage high-dose-rate brachytherapy (sHDRB) is a treatment option for recurrences after prior radiation therapy. However, only approximately 50% of patients benefit, with the majority of second recurrences after salvage brachytherapy occurring distantly. Therefore, identification of characteristics that can help select patients who may benefit most from sHDRB is critical. Machine learning may be used to identify characteristics that predict outcome following sHDRB. We aimed to use machine learning to identify patient characteristics associated with biochemical failure (BF) following prostate sHDRB.

Methods And Materials: We analyzed data for 52 patients treated with sHDRB for locally recurrent prostate cancer after previous definitive radiation therapy between 1998 and 2009. Following pathologic confirmation of locally recurrent disease without evidence of metastatic disease, 36 Gy in 6 fractions was administered to the prostate and seminal vesicles. BF following sHDRB was defined using the Phoenix definition. Sixteen different clinical risk features were collected, and machine learning analysis was executed to identify subpopulations at higher risk of BF. Decision tree-based algorithms including classification and regression trees, MediBoost, and random forests were constructed.

Results: Patients were followed up for a minimum of 5 years after sHDRB. Those with a fraction of positive cores ≥0.35 and a disease-free interval <4.12 years after their initial radiation treatment experienced a higher failure rate after sHDRB of 0.75 versus 0.38 for the rest of the population.

Conclusions: Using machine learning, we have identified that patients with a fraction of positive cores ≥0.35 and a disease-free interval <4.1 years might be associated with a high risk of BF following sHDRB.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijrobp.2018.03.001DOI Listing
July 2018

Deep nets vs expert designed features in medical physics: An IMRT QA case study.

Med Phys 2018 Jun 18;45(6):2672-2680. Epub 2018 Apr 18.

Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA.

Purpose: The purpose of this study was to compare the performance of Deep Neural Networks against a technique designed by domain experts in the prediction of gamma passing rates for Intensity Modulated Radiation Therapy Quality Assurance (IMRT QA).

Method: A total of 498 IMRT plans across all treatment sites were planned in Eclipse version 11 and delivered using a dynamic sliding window technique on Clinac iX or TrueBeam Linacs. Measurements were performed using a commercial 2D diode array, and passing rates for 3%/3 mm local dose/distance-to-agreement (DTA) were recorded. Separately, fluence maps calculated for each plan were used as inputs to a convolution neural network (CNN). The CNNs were trained to predict IMRT QA gamma passing rates using TensorFlow and Keras. A set of model architectures, inspired by the convolutional blocks of the VGG-16 ImageNet model, were constructed and implemented. Synthetic data, created by rotating and translating the fluence maps during training, was created to boost the performance of the CNNs. Dropout, batch normalization, and data augmentation were utilized to help train the model. The performance of the CNNs was compared to a generalized Poisson regression model, previously developed for this application, which used 78 expert designed features.

Results: Deep Neural Networks without domain knowledge achieved comparable performance to a baseline system designed by domain experts in the prediction of 3%/3 mm Local gamma passing rates. An ensemble of neural nets resulted in a mean absolute error (MAE) of 0.70 ± 0.05 and the domain expert model resulted in a 0.74 ± 0.06.

Conclusions: Convolutional neural networks (CNNs) with transfer learning can predict IMRT QA passing rates by automatically designing features from the fluence maps without human expert supervision. Predictions from CNNs are comparable to a system carefully designed by physicist experts.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.12890DOI Listing
June 2018

Comment on 'Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study'.

Phys Med Biol 2018 03 15;63(6):068001. Epub 2018 Mar 15.

Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, United States of America.

The application of machine learning (ML) presents tremendous opportunities for the field of oncology, thus we read 'Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study' with great interest. In this article, the authors used state of the art techniques: a pre-trained convolutional neural network (VGG-16 CNN), transfer learning, data augmentation, drop out and early stopping, all of which are directly responsible for the success and the excitement that these algorithms have created in other fields. We believe that the use of these techniques can offer tremendous opportunities in the field of Medical Physics and as such we would like to praise the authors for their pioneering application to the field of Radiation Oncology. That being said, given that the field of Medical Physics has unique characteristics that differentiate us from those fields where these techniques have been applied successfully, we would like to raise some points for future discussion and follow up studies that could help the community understand the limitations and nuances of deep learning techniques.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6560/aaae23DOI Listing
March 2018