Evaluation of Transformer-Based Models for Molecular Subtype Classification of Invasive Ductal Breast Carcinoma Using Mammography
Saved in:
| Title: | Evaluation of Transformer-Based Models for Molecular Subtype Classification of Invasive Ductal Breast Carcinoma Using Mammography |
|---|---|
| Authors: | Blandón Tórrez, David |
| Contributors: | Díaz, Oliver |
| Source: | Treballs Finals de Grau (TFG)-Enginyeria Informàtica |
| Publisher Information: | 2025. |
| Publication Year: | 2025 |
| Subject Terms: | Sistemes classificadors (Intel·ligència artificial), Programari, Breast cancer, Deep learning (Machine learning), Bachelor's theses, Treballs de fi de grau, Computer software, Mamografia, Learning classifier systems, Càncer de mama, Aprenentatge profund, Mammography |
| Description: | Breast cancer remains the most prevalent malignancy and a leading cause of mortality in women worldwide. Early and accurate molecular characterization is critical for prognosis and treatment selection. Molecular subtyping, traditionally guided by invasive tissue biopsies and immunohistochemical analysis, enables personalized therapies but is costly, time-consuming, and not universally feasible. Non-invasive alternatives leveraging medical imaging, particularly mammography, have gained research interest for molecular classification. This study evaluates the potential of Transformer-based DL models to classify molecular subtypes of invasive ductal carcinoma using mammographic images exclusively from the public CMMD (The Chinese Mammography Database) dataset. A systematical analysis was conducted to compare three state-of-the-art Transformer architectures, Vision Transformer (ViT), Swin Transformer (Swin), and Multi-Axis Vision Transformer (MaxViT), against a traditional CNN model, ResNet-101. The experimental methodology addresses key challenges such as class imbalance through weighted loss functions, oversampling, data augmentation, and robust cross-validation strategies. Results demonstrate that transformer-based models consistently outperform the CNN baseline. ViT achieved the highest average AUC ( $0.635 \pm 0.016$ ) and balanced accuracy $(0.385 \pm 0.042)$ on test sets, compared to ResNet-101 (AUC: $0.563 \pm 0.03$; balanced accuracy: $0.322 \pm 0.062$ ). Statistical analysis confirmed significant performance differences ( $\mathrm{p} Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2025, Director: Oliver Díaz |
| Document Type: | Bachelor thesis |
| File Description: | application/pdf |
| Language: | English |
| Access URL: | https://hdl.handle.net/2445/223419 |
| Rights: | URL: http://www.gnu.org/licenses/gpl-3.0.ca.html |
| Accession Number: | edsair.od.......963..b898aa2ac69483e0e6e9d23900fd1a34 |
| Database: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | Breast cancer remains the most prevalent malignancy and a leading cause of mortality in women worldwide. Early and accurate molecular characterization is critical for prognosis and treatment selection. Molecular subtyping, traditionally guided by invasive tissue biopsies and immunohistochemical analysis, enables personalized therapies but is costly, time-consuming, and not universally feasible. Non-invasive alternatives leveraging medical imaging, particularly mammography, have gained research interest for molecular classification. This study evaluates the potential of Transformer-based DL models to classify molecular subtypes of invasive ductal carcinoma using mammographic images exclusively from the public CMMD (The Chinese Mammography Database) dataset. A systematical analysis was conducted to compare three state-of-the-art Transformer architectures, Vision Transformer (ViT), Swin Transformer (Swin), and Multi-Axis Vision Transformer (MaxViT), against a traditional CNN model, ResNet-101. The experimental methodology addresses key challenges such as class imbalance through weighted loss functions, oversampling, data augmentation, and robust cross-validation strategies. Results demonstrate that transformer-based models consistently outperform the CNN baseline. ViT achieved the highest average AUC ( $0.635 \pm 0.016$ ) and balanced accuracy $(0.385 \pm 0.042)$ on test sets, compared to ResNet-101 (AUC: $0.563 \pm 0.03$; balanced accuracy: $0.322 \pm 0.062$ ). Statistical analysis confirmed significant performance differences ( $\mathrm{p}<br />Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2025, Director: Oliver Díaz |
|---|