Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551039
Pertenecen a esta colección Tesis y Trabajos de grado de las Maestrías correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- Face detection and feature extraction for classification tasks on thermal images of Covid-19 patients(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2025-06) Ramírez Treviño, Luis Javier; Tamez Peña, José Gerardo; emimmayorquin; Santos Díaz, Alejandro; Martínez Ledesma, Juan Emmanuel; School of Engineering and Sciences; Campus MonterreyThis thesis presents a methodology for diagnosing COVID-19 patients using computer vision, infrared thermography, and machine learning. The study focuses on the analysis of thermal images, which offer a non-invasive and contactless alternative to traditional imaging methods like computed tomography (CT) and radiography. The research leverages a database of thermal images from 252 patients, including both COVID-19 positive and negative cases, to explore the potential of infrared thermography in detecting respiratory diseases. The proposed methodology involves two main approaches: one using a Convolutional Neural Network (CNN) to extract features from the full thermal image, and another incorporating a face detection step to focus on facial features. Three face detection algorithms—Haar Cascades, Local Binary Patterns (LBP), and CNNs (specifically YOLOv5)—were evaluated, with achieved accuracies of 93%, 98%, and 100%, respectively. Feature extraction was performed using the VGG-16 CNN architecture, pre-trained on the ImageNet dataset, followed by classification using traditional machine learning models such as Logistic Regression, AdaBoost, Support Vector Machines (SVM), Random Forest, and Gradient Boosting. The methodology was tested on two classification tasks: gender classification and COVID-19 symptom classification. For gender classification, the full-body approach achieved accuracies ranging from 0.933 to 0.996, while the face-only approach yielded slightly lower accuracies (0.868 to 0.923). For symptom classification, the full-body approach achieved accuracies between 0.607 and 0.650, outperforming previous work using radiomic features on the same dataset. The face-only approach for symptom classification resulted in accuracies ranging from 0.544 to 0.612, still demonstrating improvement over prior results. The study concludes that the proposed methodology is effective for classification tasks on thermal images, particularly for gender classification. While the results for symptom classification are not yet reliable enough for standalone diagnostic use, the high sensitivity scores suggest potential as a screening tool. The research highlights the promise of infrared thermography combined with machine learning for medical applications, especially in scenarios where traditional imaging methods are impractical or pose risks due to radiation exposure. Future work could explore data augmentation, additional patient data, and applications in other medical domains.
- lmproved Diagnosis of Breast Cancer via NLP Analysis of Radiological Reports(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11) Sosa Silva, Patricia Angelli; Tamez Peña, José Gerardo; emimmayorquin; Martínez Ledezma, Emmanuel; Avendaño Davalos, Betzabeth; School of Engineering and Sciences; Campus Monterrey; Santos Díaz, AlejandroToe main objective of this thesis was to evaluate the use of natural language processing (NLP) techniques and machine learning models to improve the specificity of breast cancer diagnosis and reduce false-positive rates using a dataset of radiological reports from Mexican hospitals. Toe methodology involved text preprocessing, feature extraction using NLP techniques and classification using machine learning models for the radiological reports. The preprocessing consisted of lemmatization, stop-word removal, and tokenization. Various NLP techniques were then applied, including bag-of-words, TF-IDF, Word2Vec embeddings, and ClinicalBERT embeddings. These were used as input features for classical machine learning models (Logistic Regression, Random Forest, Extreme Grading Boosting, Naive Bayes, k-Nearest Neighbors, Support Vector Machine and their ensemble) as well as a deep learning LSTM model. The models were trained, calibrated, and evaluated using metrics: AUC, accuracy, precision, recall, specificity and Fl-score. The key findings showed that the ensemble model with Bag-of-words and SVM using TF-IDF vectorized reports achieved the best performance, with an AUC of 0.79, specificity of 0.27 and AUC of 0.80 and specificity of 0.26, respectively. Thess model was able to identify all true positive cases while reducing the number of unnecessary biopsies by 19.49% and 15.08%, respectively. Feature importance analysis revealed that terms like "speculated", "irregular", and "4a category" were critica! for breast cancer classification. In contrast, the deep learning LSTM model performed poorly, with an AUC of only 0.52 and specificity of O. These results demonstrate the potential of NLP and machine learning techniques to enhance the reliability of breast cancer diagnosis and management, reducing the burden of unnecessary medica! procedures on patients and the healthcare system. The theoretical implications include the importance of effective feature engineering and the limitations of deep learning models for this specific task.
- Automated radiology report generation using radiomics and natural language processing techniques(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-01) Bosques Palomo, Beatriz Alejandra; Tamez Peña, José Gerardo; emipsanchez; Santos Díaz, Alejandro; Avendaño Avalos, Daly Betzabeth; Helguera, Maria; Escuela de Ingeniería y Ciencias; Campus MonterreyThis thesis addresses the significant challenges in breast cancer diagnosis in developing countries, where delayed follow-ups due to resource constraints can impede timely and accurate detection, affecting patient outcomes. A novel approach using radiomic features integrated with transformer models to automate mammography report generation, specifically focusing on report conclusions is proposed. The primary goal is to assess if these AI-driven models can replicate the diagnostic accuracy of expert radiologists in assigning BI-RADS categories and recommending follow-ups or biopsies. The study begins with meticulous image preprocessing, including a customized histogram matching scheme to standardize input data and reduce variability among images from different vendors. Radiomic features were then extracted and validated through a classification task obtaining an AUC of 0.81, proving their efficacy as inputs for the transformer architecture. The transformer models utilized both radiomic features and deep learning features extracted via a pretrained CNN. This approach allowed for a direct comparison of model performance between the hand-crafted radiomic inputs and the more complex deep learning features against expert evaluations. Results showed that the models reached high agreement with radiologists’ evaluations, with kappa values reaching up to 0.93 for the simpler BI-RADS categorization task (1 & 5) using deep learning features. However, performance declined in more complex cases, with kappa values dropping to 0.23 for radiomic features across all BI-RADS categories (1, 2, 3, 4 & 5), indicating only fair agreement. In contrast, deep learning features maintained a moderate agreement with a kappa of 0.41. Despite these promising results, the study acknowledges certain limitations, including the inability to fine-tune feature extraction due to the hand-crafted nature of radiomic features, as well as the potential subjectivity in the data, given that radiologist evaluations are susceptible to human error. Nonetheless, this research lays crucial groundwork for future AI advancements in radiological diagnostics, aiming to enhance the efficiency, accuracy, and comprehensiveness of medical image analysis in resource-limited settings.
- ECG-based heartbeat classification for arrhythmia detection: a step-by-step AI exploratory process(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-12) Silva Mendez, Adrian; TAMEZ PEÑA, JOSE GERARDO; 67337; Tamez Peña, José Gerardo; emipsanchez; Gutiérrez Ruiz, Dania; Santos Díaz, Alejandro; Martínez Ledesma, Juan Emmanuel; School of Engineering and Sciences; Campus MonterreyThis document presents the thesis of “ECG-based heartbeat classification for arrhythmia detection: A step-by-step AI Exploratory Process” for the degree of Master in Computer Science at Tecnológico de Monterrey. One of the biggest causes of death around the world (including third and first world countries) are Cardiovascular Diseases. Arrhythmia is one of those diseases in which the heart beats at an inconsistent and abnormal rhythm due to a malfunction in the electrical system of the heart. The detection, diagnosis, and classification are very challenging tasks for doctors as time is a crucial factor on the table. If it is not done in time, the patient’s life can be at risk. This proposal explores different Data Pre-processing and Feature Generation techniques to create an efficient and accurate binary classification model capable of distinguishing normal from abnormal heartbeats with an Accuracy and Sensitivity ranging in the 80-90% with a 10% increase when compared to a RAW feature vector. One of the most important ideas discussed throughout this thesis includes decomposing the ECG signal in Frequency and Time domains usingDual Tree Complex Wavelet Transform to create a Feature Vector. Another important highlight of this thesis is database manipulation, including the exclusion and the correct distribution of subjects across the training and testing sets. The approach aims to test the feature vectors by training different Supervised Learning Models including K Nearest Neighbours, Random Forest, and X-Gradient Boosting. We will be using the MIT-BIH Arrhythmia Database for the experimentation process.
- Risk of breast cancer in the mexican population: a radiomics approach(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-05-01) Lafarga Osuna, Yareth; Tamez Peña, José Gerardo; puemcuervo, emipsanchez; Santos Díaz, Alejandro; Martínez Ledezma, Juan Emmanuel; Castañeda, Benjamin; School of Engineering and Sciences; Campus MonterreyBreast cancer is a significant global health concern, especially among women, with rising incidence rates in specific populations. Low screening rates contribute to this alarming trend, emphasizing the need to improve breast cancer risk prediction and enhance screening outcomes. This thesis explores the potential of image-based models and machine learning techniques to address limitations in traditional risk assessment models and leverage the rich information available in mammography images. A larger dataset, including diverse cases with breast cancer diagnoses, is recommended to improve accuracy and generalizability. In addition, extracting additional image-based features to characterize breast anatomy could provide valuable insights. The outcomes of this research can contribute to personalized medicine approaches and improve breast cancer risk prediction, leading to early detection, timely interventions, and improved patient outcomes. This study showed successful segmentation and extraction of 78 features per image (first and second order), and the methodology's performance with a machine learning Cox model achieved an AUC of 0.76. Furthermore, the Kaplan-Meier curve significantly differed between the low-risk and high-risk groups. The advantage of using a Cox model is its ability to identify the most discriminative features, which in this case were three features associated with the physiological characteristics of the patients. This thesis provides a roadmap for further investigation, emphasizing the importance of larger datasets, technique refinement, and exploration of population-specific characteristics to develop more effective breast cancer screening and prevention strategies.