Bilateral View Hypercomplex Breast Classification

Kalbe Digital Lab

Overview

Breast cancer classification using 2-views (bilateral) that compose a mammography exam, owing to the correlations contained in mammography views, which present crucial information for identifying tumors.
Reference: https://arxiv.org/abs/2204.05798

Dataset

The model is trained using CBIS INBReast Dataset

  • Target: Lesions (masses, calcifications, asymmetries, and distortions)
  • Task: Classification
  • Modality: Grayscale

Model Architecture

Parameterized Hypercomplex ResNets-18 Variants (PHYResNet).

model-architecture

Demo

Please select the example below or upload 2 pairs of mammography exam result.