breakhis

🔬 Detecção Histopatológica de Câncer a partir de imagens disponibilizadas pelos datasets PatchCamelyon (PCam) e Breast Cancer Histopathological Dataset (BreakHis) e a partir de dados tabulares (Breast Cancer Wisconsin Diagnostic Dataset).

A curated repository for the BreakHis Breast Cancer Histopathological Database, including folder structure, magnification levels, and class information for binary and multiclass classification tasks.

Ensemble model (EfficientNetB0 + ResNet50 + DenseNet121) for breast cancer binary classification on BreakHis dataset - 90.99% accuracy

Binary classification of breast cancer histopathology images (Benign vs Malignant) using an improved CNN on the BreakHis dataset - 88.24% test accuracy.

Exploratory analysis and visualization of a breast cancer histopathology image dataset, including binary and multiclass classification structures across multiple magnification levels.