Miniatura

Fitxers

UTF-82025 Guzman SPIE.pdf (3.13 MB)

Tipus de document

Objecte de conferència

Versió

Versió acceptada

Data de publicació

2025-04-10

Tots els drets reservats

Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/220790

From hand-crafted radiomics to deep learning: evaluating breast cancer classification methods in mammograms

Títol de la revista

Autors

Director/Tutor

ISSN de la revista

Títol del volum

Recurs relacionat

https://doi.org/10.1117/12.3046672

Resum

This study evaluates the performance of some machine learning (ML) and deep learning (DL) models for breast cancer tumor classification in mammography (MG) images, by training them on the BCDR dataset. The study compares the use of radiomics-based features in ML models, including Random Forest, Support Vector Machines, and XGBoost, with two deep learning approaches using Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Radiomics features were extracted from segmented regions of interest (ROIs) and used to train the ML models, performing hyperparameter tuning and cross-validation to optimize the results. CNN and ViT models were trained using the MG location present in the ROI segmentations, to explore the impact of tumor region localization assistance on classification performance. To examine and verify the performance of the ML models and the ViT, the area under the receiver operating characteristic curve (AUC-ROC) and the training execution time of all experiments (performed on the same device) were used. The results indicate that, while all methods achieve good performance on the training dataset (mean AUCROC scores around 0.9), they exhibit substantial performance drops when tested on external data. Among the evaluated models, ViT achieves the highest overall AUC-ROC in both internal (0.93) and external (0.68) validation, surpassing CNNs and radiomics-based ML models. However, ViT also incurs the highest computational cost, highlighting a trade-off between accuracy and training time. These findings underscore the need for multicenter, multi-vendor data to improve model generalization and reliability, as well as for continued refinement of advanced architectures, such as transformers, to optimize breast cancer lesion classification in clinical settings.

Matèries

Aprenentatge automàtic, Mamografia, Càncer de mama, Xarxes neuronals convolucionals

Matèries (anglès)

Machine learning, Mammography, Breast cancer, Convolutional neural networks

Citació

Alejandro Guzman, Noah Márquez, Oliver Díaz, "From hand-crafted radiomics to deep learning: evaluating breast cancer classification methods in mammograms," Proc. SPIE 13411, Medical Imaging 2025: Imaging Informatics, 134110U (10 April 2025); https://doi.org/10.1117/12.3046672

Col·leccions

Comunicacions a congressos (Matemàtiques i Informàtica)

Citació

GUZMAN REQUENA, Alejandro, MÁRQUEZ VARA, Noah, DÍAZ, Oliver. From hand-crafted radiomics to deep learning: evaluating breast cancer classification methods in mammograms. _Comunicació a: Proc. SPIE 13411_. Medical Imaging 2025: Imaging Informatics; 134110U (10 April 2025). [consulta: 24 de gener de 2026]. [Disponible a: https://hdl.handle.net/2445/220790]

Exportar metadades

JSON - METS

Compartir registre