Juan Carlos Torres-Galván

Dr. Juan Carlos Torres-Galván

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 September 2018 in Biomedical Optics Express
Verified
Journal Article
Open access
PDF file
Edgar GuevaraEdgar Guevara
Edgar Guevara
JTJuan Carlos Torres-Galván
Juan Carlos Torres-Galván
MRMiguel G. Ramírez-Elías
Miguel G. Ramírez-Elías
CLClaudia Luevano-Contreras
Claudia Luevano-Contreras
FGFrancisco Gonzalez
Francisco Gonzalez
Type 2 diabetes mellitus (DM2) is one of the most widely prevalent diseases worldwide and is currently screened by invasive techniques based on enzymatic assays that measure plasma glucose concentration in a laboratory setting. A promising plan of action for screening DM2 is to identify molecular signatures in a non-invasive fashion. This work describes the application of portable Raman spectroscopy coupled with several supervised machine-learning techniques, to discern between diabetic patients and healthy controls (Ctrl), with a high degree of accuracy. Using artificial neural networks (ANN), we accurately discriminated between DM2 and Ctrl groups with 88.9–90.9% accuracy, depending on the sampling site. In order to compare the ANN performance to more traditional methods used in spectroscopy, principal component analysis (PCA) was carried out. A subset of features from PCA was used to generate a support vector machine (SVM) model, albeit with decreased accuracy (76.0–82.5%). The 10-fold cross-validation model was performed to validate both classifiers. This technique is relatively low-cost, harmless, simple and comfortable for the patient, yielding rapid diagnosis. Furthermore, the performance of the ANN-based method was better than the typical performance of the invasive measurement of capillary blood glucose. These characteristics make our method a promising screening tool for identifying DM2 in a non-invasive and automated fashion.

6 May 2021 in Quantitative InfraRed Thermography Journal
Verified
Journal Article
Closed access
JTJuan Carlos Torres-Galván
Juan Carlos Torres-Galván
Edgar GuevaraEdgar Guevara
Edgar Guevara
EKEleazar Samuel Kolosovas-Machuca
Eleazar Samuel Kolosovas-Machuca
AOAntonio Oceguera-Villanueva
Antonio Oceguera-Villanueva
JFJorge L. Flores
Jorge L. Flores
FGFrancisco Gonzalez
Francisco Gonzalez
Infrared thermography is a technique that can detect anomalies in temperature patterns which can indicate some breast pathologies including breast cancer. One limitation of the method is the absence of standardised thermography interpretation procedures. Deep learning models have been used for pattern recognition and classification of objects and have been adopted as an adjunct methodology in medical imaging diagnosis. In this paper, the use of a deep convolutional neural network (CNN) with transfer learning is proposed to automatically classify thermograms into two classes (normal and abnormal). A population of 311 female subjects was considered analysing two approaches to test the CNN’s performance: one with a balanced class distribution and the second study in a typical screening cohort, with a low prevalence of abnormal thermograms. Results showed that the transfer-learned ResNet-101 model had a sensitivity of 92.3% and a specificity of 53.8%, while with an unbalanced distribution the values were 84.6% and 65.3%, respectively. These results suggest that the model presented in this work can classify abnormal thermograms with high sensitivity which validates the use of infrared thermography as an adjunct method for breast cancer screening.

1 May 2019
Verified
Conference Paper
Closed access
JTJuan Carlos Torres-Galván
Juan Carlos Torres-Galván
EGEdgar Guevara
Edgar Guevara
FGFrancisco Javier Gonzalez
Francisco Javier Gonzalez
Infrared thermography can be used for pre-screening of breast cancer but the results of this technique depend on the experience of the human expert. We propose an automated analysis approach to assess the capabilities of deep neural networks to classify breast thermograms. The dataset consisted of 173 images and we compared seven deep learning architectures. VGG-16 convolutional neural network outperformed with a sensitivity of 100%, specificity of 82.35% and balanced accuracy of 91.18%. Such results indicate that deep neural networks can be used in the analysis of thermal images for breast cancer pre-screening.

21 June 2022 in Journal of Biophotonics
Verified
Journal Article
Closed access
Edgar GuevaraEdgar Guevara
Edgar Guevara
JTJuan Carlos Torres-Galván
Juan Carlos Torres-Galván
FGFrancisco Gonzalez
Francisco Gonzalez
CLClaudia Luevano‐Contreras
Claudia Luevano‐Contreras
CCClaudio Cayetano Castillo‐Martínez
Claudio Cayetano Castillo‐Martínez
M. G. Ramírez-ElíasM. G. Ramírez-Elías
M. G. Ramírez-Elías

6 August 2019 in Biomedical Optics Express
Verified
Journal Article
Closed access
Edgar GuevaraEdgar Guevara
Edgar Guevara
JTJuan Carlos Torres-Galván
Juan Carlos Torres-Galván
MRMiguel G. Ramírez-Elías
Miguel G. Ramírez-Elías
CLClaudia Luevano-Contreras
Claudia Luevano-Contreras
FGFrancisco Gonzalez
Francisco Gonzalez
We show the spectra of advanced glycation products in response to recent comments made by Bratchenko et al. Our results suggest that information retrieved by Raman spectroscopy is relevant to screening diabetic patients, however, the comparison carried out in our paper, between ANN and SVM, was not fair, because of the erroneous PCA selection procedure and different sources of variation present in the analysis. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

23 April 2025 in Data
Verified
Journal Article
Open access
PDF file
JTJuan Carlos Torres-Galván
Juan Carlos Torres-Galván
PHPaul Hernández-Herrera
Paul Hernández-Herrera
JOJuan Antonio Obispo
Juan Antonio Obispo
XCXocoyotzin Guadalupe Ávila Cruz
Xocoyotzin Guadalupe Ávila Cruz
LILiliana Montserrat Camacho Ibarra
Liliana Montserrat Camacho Ibarra
M. G. Ramírez-ElíasM. G. Ramírez-Elías
M. G. Ramírez-Elías
In agriculture, machine learning (ML) and deep learning (DL) have increased significantly in the last few years. The use of ML and DL for image classification in plant disease has generated significant interest due to their cost, automatization, scalability, and early detection. However, high-quality image datasets are required to train robust classifier models for plant disease detection. In this work, we have created an image dataset of 649 orange leaves divided into two groups: control (n = 379) and huanglongbing (HLB) disease (n = 270). The images were acquired with several smartphone cameras of high resolution and processed to remove the background. The dataset enriches the information on characteristics and symptoms of citrus leaves with HLB and healthy leaves. This enhancement makes the dataset potentially valuable for disease identification through leaf segmentation and abnormality detection, particularly when applying ML and DL models.