A5048449561- Spectroscopy Techniques in Biomedical and Chemical Research
- Spectroscopy and Chemometric Analyses
- Diabetic Foot Ulcer Assessment and Management
- Infrared Thermography in Medicine
- Thermography and Photoacoustic Techniques
- Optical Imaging and Spectroscopy Techniques
- Artificial Intelligence in Healthcare
- AI in cancer detection
- Metabolomics and Mass Spectrometry Studies
- Thermoregulation and physiological responses
Autonomous University of San Luis Potosí
2017-2025
Type 2 diabetes mellitus (DM2) is one of the most widely prevalent diseases worldwide and currently screened by invasive techniques based on enzymatic assays that measure plasma glucose concentration in a laboratory setting. A promising plan action for screening DM2 to identify molecular signatures non-invasive fashion. This work describes application portable Raman spectroscopy coupled with several supervised machine-learning techniques, discern between diabetic patients healthy controls...
Infrared thermography is a technique that can detect anomalies in temperature patterns which indicate some breast pathologies including cancer. One limitation of the method absence standardised interpretation procedures. Deep learning models have been used for pattern recognition and classification objects adopted as an adjunct methodology medical imaging diagnosis. In this paper, use deep convolutional neural network (CNN) with transfer proposed to automatically classify thermograms into...
In agriculture, machine learning (ML) and deep (DL) have increased significantly in the last few years. The use of ML DL for image classification plant disease has generated significant interest due to their cost, automatization, scalability, early detection. However, high-quality datasets are required train robust classifier models this work, we created an dataset 649 orange leaves divided into two groups: control (n = 379) huanglongbing (HLB) 270). images were acquired with several...
Infrared thermography can be used for pre-screening of breast cancer but the results this technique depend on experience human expert. We propose an automated analysis approach to assess capabilities deep neural networks classify thermograms. The dataset consisted 173 images and we compared seven learning architectures. VGG-16 convolutional network outperformed with a sensitivity 100%, specificity 82.35% balanced accuracy 91.18%. Such indicate that in thermal pre-screening.
In this article, we investigated the feasibility of using Raman spectroscopy and multivariate analysis method to noninvasively screen for prediabetes diabetes in vivo. measurements were performed on skin from 56 patients with diabetes, 19 prediabetic 32 healthy volunteers. These spectra collected along reference values provided by standard glycated hemoglobin (HbA1c) assay. A multiclass principal component support vector machine (PCA-SVM) model was created labeled validated through a...
We show the spectra of advanced glycation products in response to recent comments made by Bratchenko et al.Our results suggest that information retrieved Raman spectroscopy is relevant screening diabetic patients, however, comparison carried out our paper, between ANN and SVM, was not fair, because erroneous PCA selection procedure different sources variation present analysis.
This work describes the application of portable Raman spectroscopy coupled with Artificial Neural Networks (ANN), to discern between diabetic patients and healthy controls, a high degree accuracy (Acc=89.7±6.6%). technique is relatively low-cost, simple comfortable for patient, yielding rapid diagnosis. These features make our method promising screening tool identifying type 2 diabetes mellitus (dM2) in non-invasive automated fashion.
This letter aims to reply Bratchenko and Bratchenko's comment on our paper "Feasibility of Raman spectroscopy as a potential in vivo tool screen for pre-diabetes diabetes." Our analyzed the feasibility using measurements combined with machine learning techniques diabetic prediabetic patients. We argued that this approach yields high overall accuracy (94.3%) while retaining good capacity distinguish between (area under receiver-operating curve [AUC] = 0.86) control classes (AUC 0.97) moderate...