Prediction of genomic biomarkers in breast cancer from images of routine histopathology tissue slides of solid tumors using deep learning models

Arregui Hernández, Ernesto Santiago

Publicación:
Prediction of genomic biomarkers in breast cancer from images of routine histopathology tissue slides of solid tumors using deep learning models

dc.contributor.author	Arregui Hernández, Ernesto Santiago
dc.contributor.director	Pérez Martín, Jorge
dc.contributor.director	Carrilero Mardones, Mikel
dc.date.accessioned	2025-07-08T13:15:44Z
dc.date.available	2025-07-08T13:15:44Z
dc.date.issued	2025-06
dc.description.abstract	The increasing demand for biomarker testing in oncology highlights the need for scalable and cost-effective alternatives to molecular profiling. This master's thesis investigates whether deep learning (DL) models can predict clinically relevant genomic biomarkers directly from routine histopathology whole-slide images, focusing on PIK3CA gene mutation in breast cancer. The study applies a radiogenomics pipeline that includes tile extraction, stain normalization, and the use of multiple DL architectures. A subset of the TCGA-BRCA dataset was used, selecting diagnostic slides labelled for PIK3CA mutation status. Tiles were extracted and normalized using the Macenko method, then fed into models including VGG-19, ResNet-18, ResNet-50, and Swin Transformer. Two configurations were explored: cross-validation (C-V) ensemble models and single-model training with C-V tuned hyperparameters. Aggregation strategies and thresholding techniques were systematically evaluated to assess their impact on model performance. Performance metrics were computed on an unseen test set composed of subcohorts from medical centers not included in the training phase. A C-V ensemble model using a ResNet-18 pretrained on ImageNet and Macenko stain normalization achieved the best AUROC (0.733), with a sensitivity of 0.817, specificity of 0.451, and an F1 score of 0.757, raising the question of whether predicting PIK3CA mutation status from histopathology alone may ultimately be feasible.	en
dc.identifier.citation	Arregui Hernández, Ernesto Santiago. Trabajo fin de Máster: "Prediction of genomic biomarkers in breast cancer from images of routine histopathology tissue slides of solid tumors using deep learning models". Universidad Nacional de Educación a Distancia (UNED), 2025
dc.identifier.uri	https://hdl.handle.net/20.500.14468/29300
dc.language.iso	en
dc.publisher	Universidad Nacional de Educación a Distancia (UNED). E.T.S. de Ingeniería Informática
dc.relation.center	E.T.S. de Ingeniería Informática
dc.relation.degree	Máster universitario en Ingeniería y Ciencia de Datos
dc.relation.department	Inteligencia Artificial
dc.rights	info:eu-repo/semantics/openAccess
dc.rights.uri	Atribución-NoComercial-SinDerivadas 4.0 Internacional
dc.subject	1203.04 Inteligencia artificial
dc.subject.keywords	breast cancer	en
dc.subject.keywords	deep learning	en
dc.subject.keywords	histopathology	en
dc.subject.keywords	radiogenomics	en
dc.subject.keywords	whole-slide images	en
dc.title	Prediction of genomic biomarkers in breast cancer from images of routine histopathology tissue slides of solid tumors using deep learning models	en
dc.type	tesis de maestría	es
dc.type	master thesis	en
dspace.entity.type	Publication