Breast Cancer Detection with Topological Deep Learning
Nuwagira, B.; Rodriguez, A.; Li, Q.; Coskunuzer, B.
Show abstract
In this paper, we investigate the integration of topological data analysis (TDA) techniques with deep learning (DL) models to improve breast cancer diagnosis from ultrasound images. By leveraging persistent homology, a TDA method that captures global structural patterns, we enrich the local spatial features typically learned by DL models. We in-corporate topological features into various pre-trained architectures, including CNNs and vision transformers (VTs), aiming to enhance screening accuracy for breast cancer, which remains the most common cancer among women. Experiments on publicly available ultrasound datasets demonstrate that combining CNNs and VTs with topological features consistently yields statistically significant performance improvements. Notably, this approach also helps to address challenges faced by DL models, such as interpretability and reliance on large labeled datasets. Further-more, we generalize the Alexander duality theorem to cubical persistence, showing that persistent homology remains invariant under sublevel and superlevel filtrations for image data. This advancement reduces computational costs, making TDA methods more practical for image analysis.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Single-Cell Multi-Modal GAN (scMMGAN) reveals spatial patterns in single-cell data from triple negative breast cancer 94%
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 92%
- Tokenized and Continuous Embedding Compressions of Protein Sequence and Structure 92%
Similar papers in this journal
- Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement 96%
- Deep Learning Classification of Lipid Droplets in Quantitative Phase Images 95%
- Enhancing Breast Ultrasound Segmentation through Fine-tuning and Optimization Techniques: Sharp Attention UNet 95%
Similar papers in this journal
- Collective Intelligent Strategy for Improved Segmentation of COVID-19 from CT 95%
- A Deep Attention-Based Encoder for the Prediction of Type 2 Diabetes Longitudinal Outcomes from Routinely Collected Health Care Data 91%
- Supervised contrastive learning enhances MHC-II peptide binding affinity prediction 90%
Similar papers in this journal
- SN-FPN: Self-attention Nested Feature Pyramid Network for Digital Pathology Image Segmentation 95%
- The tempest in a cubic millimeter: Image-based refinements necessitate the reconstruction of 3D microvasculature from a large series of damaged alternately-stained histological sections 95%
- Cell segmentation without annotation by unsupervised domain adaptation based on cooperative self-learning 94%
Similar papers in this journal
- ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning 94%
- A novel interpretable deep transfer learning combining diverse learnable parameters for improved T2D prediction based on single-cell gene regulatory networks 94%
- Aggregation of Cohorts for Histopathological Diagnosis with Deep Morphological Analysis 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.