lishen/end2end-all-conv
Deep Learning to Improve Breast Cancer Detection on Screening Mammography
Implements end-to-end whole-image classification using an all-convolutional architecture that converts patch-level classifiers (ResNet50, VGG16) into full mammogram predictors by appending convolutional and heatmap layers. Achieves 0.88-0.96 AUC across DDSM and INbreast datasets through two-stage training with patch sampling, patch classification, and whole-image fine-tuning. Provides pre-trained models and transfer learning utilities enabling rapid adaptation to custom mammography datasets via feature-wise centering and data augmentation.
389 stars. No commits in the last 6 months.
Stars
389
Forks
137
Language
Jupyter Notebook
License
—
Category
Last pushed
Feb 24, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lishen/end2end-all-conv"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
nyukat/breast_cancer_classifier
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
LidiaGarrucho/MAMA-MIA
The MAMA-MIA Dataset: A Multi-Center Breast Cancer DCE-MRI Public Dataset with Expert Segmentations
nyukat/GMIC
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly...
cbailes/awesome-ai-cancer
Awesome artificial intelligence in cancer diagnostics and oncology
Adamouization/Breast-Cancer-Detection-Mammogram-Deep-Learning
Master's dissertation for breast cancer detection in mammograms using deep learning techniques...