238 results match your criteria Artificial Intelligence[Journal]


CapsCovNet: A Modified Capsule Network to Diagnose COVID-19 From Multimodal Medical Imaging.

IEEE Trans Artif Intell 2021 Dec 16;2(6):608-617. Epub 2021 Aug 16.

Department of Electrical and Computer EngineeringConcordia University Montreal QC H3G 2W1 Canada.

Since the end of 2019, novel coronavirus disease (COVID-19) has brought about a plethora of unforeseen changes to the world as we know it. Despite our ceaseless fight against it, COVID-19 has claimed millions of lives, and the death toll exacerbated due to its extremely contagious and fast-spreading nature. To control the spread of this highly contagious disease, a rapid and accurate diagnosis can play a very crucial part. Read More

View Article and Full-Text PDF
December 2021

Automated COVID-19 Grading With Convolutional Neural Networks in Computed Tomography Scans: A Systematic Comparison.

IEEE Trans Artif Intell 2022 Apr 8;3(2):129-138. Epub 2021 Oct 8.

Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands.

Amidst the ongoing pandemic, the assessment of computed tomography (CT) images for COVID-19 presence can exceed the workload capacity of radiologists. Several studies addressed this issue by automating COVID-19 classification and grading from CT images with convolutional neural networks (CNNs). Many of these studies reported initial results of algorithms that were assembled from commonly used components. Read More

View Article and Full-Text PDF

Improving Our Understanding of Indolent Lesions: A New Role for AI.

Authors:
Steven C Horii

Radiol Artif Intell 2022 Mar 2;4(2):e210312. Epub 2022 Feb 2.

Department of Radiology, University of Pennsylvania Perelman School of Medicine, 3400 Spruce St, Philadelphia, PA 19104-4385.

View Article and Full-Text PDF

Utilization of Artificial Intelligence-based Intracranial Hemorrhage Detection on Emergent Noncontrast CT Images in Clinical Workflow.

Radiol Artif Intell 2022 Mar 9;4(2):e210168. Epub 2022 Feb 9.

Department of Diagnostic and Interventional Neuroradiology, Clinic of Radiology and Nuclear Medicine (M.S., A.B., M.N.P., K.A.B.), and Department of Radiology and Nuclear Medicine (T.W., A.S.), University Hospital of Basel, Petersgraben 4, 4031 Basel, Switzerland; and Department of Neurologic Sciences, University of Vermont Medical Center, Burlington, Vt (M.S.).

Authors implemented an artificial intelligence (AI)-based detection tool for intracranial hemorrhage (ICH) on noncontrast CT images into an emergent workflow, evaluated its diagnostic performance, and assessed clinical workflow metrics compared with pre-AI implementation. The finalized radiology report constituted the ground truth for the analysis, and CT examinations ( = 4450) before and after implementation were retrieved using various keywords for ICH. Diagnostic performance was assessed, and mean values with their respective 95% CIs were reported to compare workflow metrics (report turnaround time, communication time of a finding, consultation time of another specialty, and turnaround time in the emergency department). Read More

View Article and Full-Text PDF

Automated Deep Learning Analysis for Quality Improvement of CT Pulmonary Angiography.

Radiol Artif Intell 2022 Mar 23;4(2):e210162. Epub 2022 Feb 23.

Department of Radiology, University of California San Diego School of Medicine, 9300 Campus Point Dr, MC 0841, La Jolla, CA 92037-0841 (L.D.H., T.A., S.J.K., A.H.); and Naval Hospital Camp Pendleton, Oceanside, Calif (K.H.).

CT pulmonary angiography (CTPA) is the first-line imaging test for evaluation of acute pulmonary emboli. However, diagnostic quality is heterogeneous across institutions and is frequently limited by suboptimal pulmonary artery (PA) contrast enhancement. In this retrospective study, a deep learning algorithm for measuring enhancement of the central PAs was developed and assessed for feasibility of its use in quality improvement of CTPA. Read More

View Article and Full-Text PDF

Prospective Evaluation of Prostate and Organs at Risk Segmentation Software for MRI-based Prostate Radiation Therapy.

Radiol Artif Intell 2022 Mar 26;4(2):e210151. Epub 2022 Jan 26.

Departments of Imaging Physics (J.W.S.), Radiation Physics (R.J.K.), Radiation Oncology (C.T., H.M., S.J.F.), Diagnostic Radiology (A.M.V.), and Biostatistics (H.D.T.), The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, TX 77030.

The segmentation of the prostate and surrounding organs at risk (OARs) is a necessary workflow step for performing dose-volume histogram analyses of prostate radiation therapy procedures. Low-dose-rate prostate brachytherapy (LDRPBT) is a curative prostate radiation therapy treatment that delivers a single fraction of radiation over a period of days. Prior studies have demonstrated the feasibility of fully convolutional networks to segment the prostate and surrounding OARs for LDRPBT dose-volume histogram analyses. Read More

View Article and Full-Text PDF

Deployed Deep Learning Kidney Segmentation for Polycystic Kidney Disease MRI.

Radiol Artif Intell 2022 Mar 16;4(2):e210205. Epub 2022 Feb 16.

Departments of Radiology (A.G., G.S., S.R., S.J., H.D., R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York, NY 10021.

This study develops, validates, and deploys deep learning for automated total kidney volume (TKV) measurement (a marker of disease severity) on T2-weighted MRI studies of autosomal dominant polycystic kidney disease (ADPKD). The model was based on the U-Net architecture with an EfficientNet encoder, developed using 213 abdominal MRI studies in 129 patients with ADPKD. Patients were randomly divided into 70% training, 15% validation, and 15% test sets for model development. Read More

View Article and Full-Text PDF

Evaluating the Performance of a Convolutional Neural Network Algorithm for Measuring Thoracic Aortic Diameters in a Heterogeneous Population.

Radiol Artif Intell 2022 Mar 23;4(2):e210196. Epub 2022 Feb 23.

Division of Cardiothoracic Imaging, Nuclear Medicine and Molecular Imaging, Department of Radiology and Imaging Sciences, Emory University Hospital, 1364 Clifton Rd NE, Atlanta, GA 30322 (C.B.M., M.v.A., A.E.S., S.J.L., C.N.D.C.); Department of Biomedical Sciences for Health, Università degli Studi di Milano, Milan, Italy (C.B.M., F. Secchi, F. Sardanelli); Digital Health Imaging Decision Support, Siemens Healthineers, Princeton, NJ (P.H.); Computed Tomography, Siemens Healthineers, Malvern, Pa (G.S.K.F.); and Unit of Radiology, Istituto di Ricovero e Cura a Carattere Scientifico Policlinico San Donato, San Donato Milanese, Italy (F. Secchi, F. Sardanelli).

The purpose of this work was to assess the performance of a convolutional neural network (CNN) for automatic thoracic aortic measurements in a heterogeneous population. From June 2018 to May 2019, this study retrospectively analyzed 250 chest CT scans with or without contrast enhancement and electrocardiographic gating from a heterogeneous population with or without aortic pathologic findings. Aortic diameters at nine locations and maximum aortic diameter were measured manually and with an algorithm (Artificial Intelligence Rad Companion Chest CT prototype, Siemens Healthineers) by using a CNN. Read More

View Article and Full-Text PDF

Automatic Localization and Brand Detection of Cervical Spine Hardware on Radiographs Using Weakly Supervised Machine Learning.

Radiol Artif Intell 2022 Mar 19;4(2):e210099. Epub 2022 Jan 19.

Department of Computer Science, Shiv Nadar University, Greater Noida, Uttar Pradesh, India (R.D.); Department of Chemical Engineering and Applied Chemistry (D.M.) and Department of Computer Science (M.G.), University of Toronto, Toronto, Canada; and Departments of Radiology (H.M.P., S.B., J.G., T.Y., H.T.) and Biomedical Informatics (I.B.), Emory University, Atlanta, Ga.

Purpose: To develop an end-to-end pipeline to localize and identify cervical spine hardware brands on routine cervical spine radiographs.

Materials And Methods: In this single-center retrospective study, patients who received cervical spine implants between 2014 and 2018 were identified. Information on the implant model was retrieved from the surgical notes. Read More

View Article and Full-Text PDF

Assessing Methods and Tools to Improve Reporting, Increase Transparency, and Reduce Failures in Machine Learning Applications in Health Care.

Radiol Artif Intell 2022 Mar 26;4(2):e210127. Epub 2022 Jan 26.

College of Engineering & Computer Science, Florida Atlantic University, 777 Glades Rd, EE441, Boca Raton, FL 33431-0991.

Artificial intelligence applications for health care have come a long way. Despite the remarkable progress, there are several examples of unfulfilled promises and outright failures. There is still a struggle to translate successful research into successful real-world applications. Read More

View Article and Full-Text PDF

Overview of Noninterpretive Artificial Intelligence Models for Safety, Quality, Workflow, and Education Applications in Radiology Practice.

Radiol Artif Intell 2022 Mar 2;4(2):e210114. Epub 2022 Feb 2.

Department of Medicine, Medical College of Georgia, Augusta, Ga (Y.T.); Department of Radiology and Imaging Sciences (V.M., W.W., H.Z., M.H., E.K., N.S., J.G., H.T.), School of Medicine (N.B.), and Department of Biomedical Informatics (I.B.), Emory University, 1364 E Clifton Rd NE, Atlanta, GA 30322; and Southend University Hospital NHS Foundation Trust, Westcliff-on-Sea, UK (A.P.).

Artificial intelligence has become a ubiquitous term in radiology over the past several years, and much attention has been given to applications that aid radiologists in the detection of abnormalities and diagnosis of diseases. However, there are many potential applications related to radiologic image quality, safety, and workflow improvements that present equal, if not greater, value propositions to radiology practices, insurance companies, and hospital systems. This review focuses on six major categories for artificial intelligence applications: study selection and protocoling, image acquisition, worklist prioritization, study reporting, business applications, and resident education. Read More

View Article and Full-Text PDF

Development and Validation of Artificial Intelligence-based Method for Diagnosis of Mitral Regurgitation from Chest Radiographs.

Radiol Artif Intell 2022 Mar 2;4(2):e210221. Epub 2022 Mar 2.

Department of Diagnostic and Interventional Radiology (D.U., A.Y., S.L.W., T.M., A.S., Y.M.) and Department of Cardiovascular Medicine (S.E., S.I., M.Y.), Graduate School of Medicine, Osaka City University, 1-4-3 Asahi-machi, Abeno-ku, Osaka 545-8585, Japan; and the Central Clinical Laboratory, Osaka City University Hospital, Osaka, Japan (K.A.).

Purpose: To develop an artificial intelligence-based model to detect mitral regurgitation on chest radiographs.

Materials And Methods: This retrospective study included echocardiographs and associated chest radiographs consecutively collected at a single institution between July 2016 and May 2019. Associated radiographs were those obtained within 30 days of echocardiography. Read More

View Article and Full-Text PDF

Quantification of the Thoracic Aorta and Detection of Aneurysm at CT: Development and Validation of a Fully Automatic Methodology.

Radiol Artif Intell 2022 Mar 23;4(2):e210076. Epub 2022 Feb 23.

Massachusetts General Hospital and Brigham and Women's Hospital Center for Clinical Data Science, 100 Cambridge St, Boston, MA 02114 (F.B.C.M., C.L., J.S., S.D., M.Y., V.B.); Department of Cardiovascular Imaging, Massachusetts General Hospital, Boston, Mass (A.T., S.H., B.G.); and Nuance Communications, Montreal, Quebec, Canada (R.B.).

Purpose: To develop and validate a deep learning-based system that predicts the largest ascending and descending aortic diameters at chest CT through automatic thoracic aortic segmentation and identifies aneurysms in each segment.

Materials And Methods: In this retrospective study conducted from July 2019 to February 2021, a U-Net and a postprocessing algorithm for thoracic aortic segmentation and measurement were developed by using a dataset (dataset A) that included 315 CT studies split into training, hyperparameter-tuning, and testing sets. The U-Net and postprocessing algorithm were associated with a Digital Imaging and Communications in Medicine series filter and visualization interface and were further validated by using a dataset (dataset B) that included 1400 routine CT studies. Read More

View Article and Full-Text PDF

Reader Perceptions and Impact of AI on CT Assessment of Air Trapping.

Radiol Artif Intell 2022 Mar 10;4(2):e210160. Epub 2021 Nov 10.

Department of Radiology, University of California, San Diego, 9452 Medical Center Dr, 4th Floor, La Jolla, CA 92037 (T.A.R., S.J.K., K.E.J., A.C.Y., S.S.B., L.D.H., A.H.); and Department of Mathematics and Statistics, San Diego State University, San Diego, Calif (K.A.H.).

Quantitative imaging measurements can be facilitated by artificial intelligence (AI) algorithms, but how they might impact decision-making and be perceived by radiologists remains uncertain. After creation of a dedicated inspiratory-expiratory CT examination and concurrent deployment of a quantitative AI algorithm for assessing air trapping, five cardiothoracic radiologists retrospectively evaluated severity of air trapping on 17 examination studies. Air trapping severity of each lobe was evaluated in three stages: qualitatively (visually); semiquantitatively, allowing manual region-of-interest measurements; and quantitatively, using results from an AI algorithm. Read More

View Article and Full-Text PDF

Development and Validation of an AI-driven Mammographic Breast Density Classification Tool Based on Radiologist Consensus.

Radiol Artif Intell 2022 Mar 16;4(2):e210199. Epub 2022 Mar 16.

Department of Biomedical Sciences for Health (V.M., A.C., D.C., C.B.M., F.S.) and Postgraduate School in Radiodiagnostics (A.A.A., S.C., G.D.P., G.G., G.M., G.P.), Università degli Studi di Milano, Milan, Italy; DeepTrace Technologies, Milan, Italy (M.I., C.S.); Unit of Diagnostic Imaging and Stereotactic Radiosurgery, C.D.I. Centro Diagnostico Italiano, Milan, Italy (M.A., D.F., S.P.); Bracco Imaging, Milan, Italy (M.A.); Department of Science, Technology and Society, University School for Advanced Studies IUSS Pavia, Palazzo del Broletto, Piazza della Vittoria 15, 27100 Pavia, Italy (C.S.); Unit of Radiology, IRCCS Policlinico San Donato, San Donato Milanese, Italy (S.S., F.S.); Institute of Biomedical Imaging and Physiology, Consiglio Nazionale delle Ricerche, Segrate, Italy (I.C.); and Department of Physics, Università degli Studi di Milano-Bicocca, Milan, Italy (I.C.).

Mammographic breast density (BD) is commonly visually assessed using the Breast Imaging Reporting and Data System (BI-RADS) four-category scale. To overcome inter- and intraobserver variability of visual assessment, the authors retrospectively developed and externally validated a software for BD classification based on convolutional neural networks from mammograms obtained between 2017 and 2020. The tool was trained using the majority BD category determined by seven board-certified radiologists who independently visually assessed 760 mediolateral oblique (MLO) images in 380 women (mean age, 57 years ± 6 [SD]) from center 1; this process mimicked training from a consensus of several human readers. Read More

View Article and Full-Text PDF

Clinical Assessment of Deep Learning-based Super-Resolution for 3D Volumetric Brain MRI.

Radiol Artif Intell 2022 Mar 12;4(2):e210059. Epub 2022 Jan 12.

Department of Radiology & Biomedical Imaging, University of California, San Francisco, 505 Parnassus Ave, L-352, San Francisco, CA 94143 (J.D.R., T.G., M.J.B., D.M.W., J.E.V.M.); Subtle Medical, Menlo Park, Calif (A.S., T.Z., L.W., E.G.); and Department of Radiology, Stanford University, Stanford, Calif (G.Z.).

Artificial intelligence (AI)-based image enhancement has the potential to reduce scan times while improving signal-to-noise ratio (SNR) and maintaining spatial resolution. This study prospectively evaluated AI-based image enhancement in 32 consecutive patients undergoing clinical brain MRI. Standard-of-care (SOC) three-dimensional (3D) T1 precontrast, 3D T2 fluid-attenuated inversion recovery, and 3D T1 postcontrast sequences were performed along with 45% faster versions of these sequences using half the number of phase-encoding steps. Read More

View Article and Full-Text PDF

Deep Learning-based Automatic Lung Segmentation on Multiresolution CT Scans from Healthy and Fibrotic Lungs in Mice.

Radiol Artif Intell 2022 Mar 12;4(2):e210095. Epub 2022 Jan 12.

Clinical Cooperation Unit Radiation Oncology, German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, 69120 Heidelberg, Germany (F.S., P.S., M.M., C.Z., C.S., K.R., N.B., A.K., J.D., A.A., M.K.); Department of Radiation Oncology (F.S., P.S., M.M., C.Z., C.S., K.R., N.B., A.K., J.D., A.A., M.K.) and National Center for Tumor Diseases (NCT) (F.S., P.S., M.M., C.Z., C.S., K.R., N.B., J.D., A.A., M.K.), Heidelberg University Hospital (UKHD), Heidelberg, Germany; German Cancer Consortium (DKTK) Core Center Heidelberg, Heidelberg, Germany (F.S., P.S., M.M., C.Z., C.S., K.R., J.D., A.A., M.K.); National Center for Radiation Oncology (NCRO), Heidelberg Institute for Radiation Oncology (HIRO), Heidelberg, Germany (F.S., P.S., M.M., C.Z., C.S., K.R., N.B., A.K., J.D., A.A., M.K.); Heidelberg Ion-Beam Therapy Center (HIT), Heidelberg, Germany (F.S., P.S., M.M., C.Z., C.S., K.R., N.B., J.D., A.A., M.K.); Department of Clinical Pathology, Suez Canal University, Ismailia, Egypt (M.M.); Department of Radiation Oncology, Nanfang Hospital, Southern Medical University, Guangzhou, China (C.Z.); and The D-Laboratory and the M-Laboratory, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, the Netherlands (H.W., L.D., P.L.).

Purpose: To develop a model to accurately segment mouse lungs with varying levels of fibrosis and investigate its applicability to mouse images with different resolutions.

Materials And Methods: In this experimental retrospective study, a U-Net was trained to automatically segment lungs on mouse CT images. The model was trained ( = 1200), validated ( = 300), and tested ( = 154) on longitudinally acquired and semiautomatically segmented CT images, which included both healthy and irradiated mice (group A). Read More

View Article and Full-Text PDF

Imaging AI in Practice: Introducing the Special Issue.

Radiol Artif Intell 2022 Mar 23;4(2):e220039. Epub 2022 Mar 23.

Department of Radiology and Biomedical Imaging, Center for Intelligent Imaging, University of California, San Francisco, 505 Parnassus Ave, Box 0628, San Francisco, CA 94143 (J.M.); Department of Radiology, University of Cincinnati, Cincinnati, Ohio (A.V.); and Department of Thoracic Imaging, University of Texas MD Anderson Cancer Center, Houston, Tex (C.C.W.).

View Article and Full-Text PDF

Automated Identification and Measurement Extraction of Pancreatic Cystic Lesions from Free-Text Radiology Reports Using Natural Language Processing.

Radiol Artif Intell 2022 Mar 22;4(2):e210092. Epub 2021 Dec 22.

Departments of Biomedical Data Science (R.Y., D.L.R.) and Radiology (K.B., P.Y.C.C., J.H.D., M.N.F., D.G., L.N.M., A.S., A.L.W., D.L.R., T.S.D.), Stanford University School of Medicine, 300 Pasteur Dr, Stanford, CA 94305.

Purpose: To automatically identify a cohort of patients with pancreatic cystic lesions (PCLs) and extract PCL measurements from historical CT and MRI reports using natural language processing (NLP) and a question answering system.

Materials And Methods: Institutional review board approval was obtained for this retrospective Health Insurance Portability and Accountability Act-compliant study, and the requirement to obtain informed consent was waived. A cohort of free-text CT and MRI reports generated between January 1991 and July 2019 that covered the pancreatic region were identified. Read More

View Article and Full-Text PDF

Artificial Intelligence in "Code Stroke"-A Paradigm Shift: Do Radiologists Need to Change Their Practice?

Radiol Artif Intell 2022 Mar 19;4(2):e210204. Epub 2022 Jan 19.

Department of Radiology, University of Cincinnati Medical Center, 234 Goodman St, Cincinnati, OH 45267-0525 (A.V.); and Department of Diagnostic Imaging and Radiology, University of Cagliari, Cagliari, Italy (L.S.).

View Article and Full-Text PDF

Automatic Brand Identification of Orthopedic Implants from Radiographs: Ready for the Next Step?

Radiol Artif Intell 2022 Mar 2;4(2):e220008. Epub 2022 Mar 2.

Department of Radiology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht 3508, the Netherlands (M.H.); and Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, the Netherlands (N.L.).

View Article and Full-Text PDF

A Survey on Multi-View Clustering.

IEEE Trans Artif Intell 2021 Apr 5;2(2):146-168. Epub 2021 Apr 5.

Department of Computer Science, University of Connecticut, Storrs, CT 06269 USA.

Clustering is a machine learning paradigm of dividing sample subjects into a number of groups such that subjects in the same groups are more similar to those in other groups. With advances in information acquisition technologies, samples can frequently be viewed from different angles or in different modalities, generating multi-view data. Multi-view clustering, that clusters subjects into subgroups using multi-view data, has attracted more and more attentions. Read More

View Article and Full-Text PDF

Simpson's Paradox in COVID-19 Case Fatality Rates: A Mediation Analysis of Age-Related Causal Effects.

IEEE Trans Artif Intell 2021 Feb 14;2(1):18-27. Epub 2021 Apr 14.

Max Planck Institute for Intelligent Systems 72076 Tübingen Germany.

We point out an instantiation of Simpson's paradox in COVID-19 case fatality rates (cfrs): comparing a large-scale study from China (February 17) with early reports from Italy (March 9), we find that cfrs are lower in Italy for every age group, but higher overall. This phenomenon is explained by a stark difference in case demographic between the two countries. Using this as a motivating example, we introduce basic concepts from mediation analysis and show how these can be used to quantify different direct and indirect effects when assuming a coarse-grained causal graph involving country, age, and case fatality. Read More

View Article and Full-Text PDF
February 2021

Isophotes, Scale Space, and Invariants in Lung CT for COPD Diagnosis.

Radiol Artif Intell 2022 Jan 19;4(1):e210301. Epub 2022 Jan 19.

Department of Radiology, University of Chicago Medical Center, 5841 S Maryland Ave, Chicago, IL 60637.

View Article and Full-Text PDF
January 2022

CNN-based Deformable Registration Facilitates Fast and Accurate Air Trapping Measurements at Inspiratory and Expiratory CT.

Radiol Artif Intell 2022 Jan 10;4(1):e210211. Epub 2021 Nov 10.

Department of Radiology, University of California San Diego, 9500 Gilman Dr, San Diego, CA 92093 (K.A.H., N.Y., T.R., A.H.); and Department of Mathematics and Statistics, San Diego State University, San Diego, Calif (K.A.H., J.T.).

Purpose: To develop a convolutional neural network (CNN)-based deformable lung registration algorithm to reduce computation time and assess its potential for lobar air trapping quantification.

Materials And Methods: In this retrospective study, a CNN algorithm was developed to perform deformable registration of lung CT (LungReg) using data on 9118 patients from the COPDGene Study (data collected between 2007 and 2012). Loss function constraints included cross-correlation, displacement field regularization, lobar segmentation overlap, and the Jacobian determinant. Read More

View Article and Full-Text PDF
January 2022

Improved Detection of Chronic Obstructive Pulmonary Disease at Chest CT Using the Mean Curvature of Isophotes.

Radiol Artif Intell 2022 Jan 15;4(1):e210105. Epub 2021 Dec 15.

Department of Diagnostic Radiology (P.S., S.B., A.S., R.F., C.R.), Research Institute (R.F., C.R., D.H.E., R.J.D.), Meakins-Christie Laboratories, Research Institute (D.H.E., R.J.D.), Centre for Innovative Medicine, Research Institute (R.J.D.), and Montreal Chest Institute (R.J.D.), McGill University Health Centre, 1001 Décarie Blvd, Montréal, QC, Canada H4A 3J1; Department of Pathology (P.S.), Medical Physics Unit, Department of Oncology (P.S.), School of Computer Science (P.S., K.S.), Department of Epidemiology, Biostatistics and Occupational Health (S.B.), Segal Cancer Centre and Lady Davis Institute for Medical Research, Jewish General Hospital (R.F.), and Department of Medicine (D.H.E., R.J.D.), McGill University, Montreal, Quebec, Canada; Institut de Chirurgie Guidée par l'Image, IHU Strasbourg, Strasbourg, France (B.G.); Bernhardt-Walther Laboratory, Department of Psychology, University of Toronto, Toronto, Ontario, Canada (M.R.); and Lakeshore General Hospital, Pointe-Claire, Quebec, Canada (R.J.D.).

Purpose: To determine if the mean curvature of isophotes (MCI), a standard computer vision technique, can be used to improve detection of chronic obstructive pulmonary disease (COPD) at chest CT.

Materials And Methods: In this retrospective study, chest CT scans were obtained in 243 patients with COPD and 31 controls (among all 274: 151 women [mean age, 70 years; range, 44-90 years] and 123 men [mean age, 71 years; range, 29-90 years]) from two community practices between 2006 and 2019. A convolutional neural network (CNN) architecture was trained on either CT images or CT images transformed through the MCI algorithm. Read More

View Article and Full-Text PDF
January 2022

Automatic Diagnosis Labeling of Cardiovascular MRI by Using Semisupervised Natural Language Processing of Text Reports.

Radiol Artif Intell 2022 Jan 24;4(1):e210085. Epub 2021 Nov 24.

National Heart and Lung Institute, Imperial College London, Hammersmith Hospital, Du Cane Road, Second Floor B Block, London W12 0HS, England (S.Z., C.P., K.V., J.H., D.F., N.P., G.D.C.); Imperial College Healthcare National Health Service Trust, London, England (J.H., D.F., N.P., G.D.C., N.L.); and Department of Bioengineering, Imperial College London, London, England (A.B., N.L.).

Purpose: To assess whether the semisupervised natural language processing (NLP) of text from clinical radiology reports could provide useful automated diagnosis categorization for ground truth labeling to overcome manual labeling bottlenecks in the machine learning pipeline.

Materials And Methods: In this retrospective study, 1503 text cardiac MRI reports from 2016 to 2019 were manually annotated for five diagnoses by clinicians: normal, dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy, myocardial infarction (MI), and myocarditis. A semisupervised method that uses bidirectional encoder representations from transformers (BERT) pretrained on 1. Read More

View Article and Full-Text PDF
January 2022

A Fully Automated Deep Learning Pipeline for Multi-Vertebral Level Quantification and Characterization of Muscle and Adipose Tissue on Chest CT Scans.

Radiol Artif Intell 2022 Jan 5;4(1):e210080. Epub 2022 Jan 5.

Massachusetts General Hospital and Brigham and Women's Hospital Center for Clinical Data Science (C.P.B., J.K.C., K.P.A.); Martinos Center for Biomedical Imaging, Department of Radiology (C.P.B, K.P.A.); Division of Thoracic Imaging and Intervention (T.D.B., M.M.W., J.P.M., F.J.F.), Department of Radiology, Massachusetts General Hospital; and Department of Radiology, Brigham and Women's Hospital, (K.P.A.), 55 Fruit St, Boston, MA 02114; Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Radiology, Berlin, Germany (T.D.B.); Department of Radiology, Berlin Institute of Health, Berlin, Germany (T.D.B.); Department of Radiology, Ludwig Maximilian University, Munich, Germany (M.M.W.); Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, Calif (K.M.); Mallinckrodt Institute of Radiology, School of Medicine, Washington University, St Louis, Mo (C.J.); and Departments of Medicine and Radiology, University of Chicago, Chicago, Ill (J.H.C.).

Body composition on chest CT scans encompasses a set of important imaging biomarkers. This study developed and validated a fully automated analysis pipeline for multi-vertebral level assessment of muscle and adipose tissue on routine chest CT scans. This study retrospectively trained two convolutional neural networks on 629 chest CT scans from 629 patients (55% women; mean age, 67 years ± 10 [standard deviation]) obtained between 2014 and 2017 prior to lobectomy for primary lung cancer at three institutions. Read More

View Article and Full-Text PDF
January 2022

Classification of Multiple Diseases on Body CT Scans Using Weakly Supervised Deep Learning.

Radiol Artif Intell 2022 Jan 1;4(1):e210026. Epub 2021 Dec 1.

Center for Virtual Imaging Trials, Carl E. Ravin Advanced Imaging Laboratories, Department of Radiology and Department of Electrical and Computer Engineering, Duke University, 2424 Erwin Rd, Studio 302, Durham, NC 27705 (F.I.T., R.H., M.A.M., W.F., E.S., J.Y.L.); Department of Radiology, Duke University, Durham, NC (V.M.D.); and Department of Medical Imaging, University of Arizona, Tucson, Ariz (G.D.R.).

Purpose: To design multidisease classifiers for body CT scans for three different organ systems using automatically extracted labels from radiology text reports.

Materials And Methods: This retrospective study included a total of 12 092 patients (mean age, 57 years ± 18 [standard deviation]; 6172 women) for model development and testing. Rule-based algorithms were used to extract 19 225 disease labels from 13 667 body CT scans performed between 2012 and 2017. Read More

View Article and Full-Text PDF
January 2022