Publications by authors named "Daniela Lozano"

3 Publications

  • Page 1 of 1

Synthetic pulmonary perfusion images from 4DCT for functional avoidance using deep learning.

Phys Med Biol 2021 08 23;66(17). Epub 2021 Aug 23.

Beaumont Artificial Intelligence Research Laboratory, Beaumont Health, Royal Oak, MI, United States of America.

To develop and evaluate the performance of a deep learning model to generate synthetic pulmonary perfusion images from clinical 4DCT images for patients undergoing radiotherapy for lung cancer.. A clinical data set of 58 pre- and post-radiotherapyTc-labeled MAA-SPECT perfusion studies (32 patients) each with contemporaneous 4DCT studies was collected. Using the inhale and exhale phases of the 4DCT, a 3D-residual network was trained to create synthetic perfusion images utilizing the MAA-SPECT as ground truth. The training process was repeated for a 50-imaging study, five-fold validation with twenty model instances trained per fold. The highest performing model instance from each fold was selected for inference upon the eight-study test set. A manual lung segmentation was used to compute correlation metrics constrained to the voxels within the lungs. From the pre-treatment test cases ( = 5), 50th percentile contours of well-perfused lung were generated from both the clinical and synthetic perfusion images and the agreement was quantified.. Across the hold-out test set, our deep learning model predicted perfusion with a Spearman correlation coefficient of 0.70 (IQR: 0.61-0.76) and a Pearson correlation coefficient of 0.66 (IQR: 0.49-0.73). The agreement of the functional avoidance contour pairs was Dice of 0.803 (IQR: 0.750-0.810) and average surface distance of 5.92 mm (IQR: 5.68-7.55).. We demonstrate that from 4DCT alone, a deep learning model can generate synthetic perfusion images with potential application in functional avoidance treatment planning.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6560/ac16ecDOI Listing
August 2021

Genetic diversity among multidrug-resistant Mycobacterium tuberculosis strains in Mexico.

Infect Genet Evol 2013 Mar 16;14:434-43. Epub 2013 Jan 16.

Instituto de Diagnóstico y Referencia Epidemiológicos, Secretaría de Salud, Mexico City, Mexico.

Tuberculosis is an important public health problem in Mexico. However, limited information about the genetic diversity of Mycobacterium tuberculosis strains circulating in the country is available. In this work, 109 multidrug-resistant (MDR) M. tuberculosis isolates collected in 23 different states of Mexico in 2003 were retrospectively characterized by spoligotyping and MIRU-VNTRs. All isolates, except for a single cluster containing two strains (subcluster E1), were split when information from the 12-loci MIRUs and spoligo-pattern was simultaneously analyzed. The discriminative power of 12-loci MIRU-VNTR and spoligotyping, by the Hunter-Gaston index, were 0.9998 and 0.9011, respectively. These findings suggest that almost all cases were epidemiologically unrelated. Instead, the genetic variations observed among these strains are suggestive of emergence of acquired drug-resistance during the course of treatment. The results suggest a high degree of genetic variability and a high frequency of SIT53 (T1 family) spoligotype among the MDR M. tuberculosis isolates included in the study.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.meegid.2012.12.024DOI Listing
March 2013

Rapid hepatitis C virus divergence among chronically infected individuals.

J Clin Microbiol 2013 Feb 5;51(2):629-32. Epub 2012 Dec 5.

Facultad de Medicina, Universidad Nacional Autónoma de México, Mexico City, Mexico.

Here, we analyze the viral divergence among hepatitis C virus (HCV) chronic cases infected with genotype 1. The intrahost viral evolution was assessed by deep sequencing using the 454 Genome Sequencer platform. The results showed a rapid nucleotide sequence divergence. This notorious short-term viral evolution is of the utmost importance for the study of HCV transmission, because direct links between related samples were virtually lost. Thus, rapid divergence of HCV significantly affects genetic relatedness studies and outbreak investigations.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1128/JCM.03042-12DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3553878PMC
February 2013
-->