Deep Learning-based mitosis detection in breast cancer histologic samples
Michel Halmes, Hippolyte Heuberger, Sylvain Berlemont
TL;DR
This paper presents a deep learning approach for mitosis detection in breast cancer histology images, utilizing a two-stage Faster RCNN model with DenseNet backbone, achieving competitive F1-score in a challenge setting.
Contribution
It introduces a novel application of Faster RCNN with DenseNet backbone specifically for mitosis detection in breast cancer histology images.
Findings
F1-score of 0.6645 on the challenge leaderboard
Effective use of two-stage object detection model for histology images
Demonstrates potential for automated cancer cell detection
Abstract
This is the submission for mitosis detection in the context of the MIDOG 2021 challenge. It is based on the two-stage objection model Faster RCNN as well as DenseNet as a backbone for the neural network architecture. It achieves a F1-score of 0.6645 on the Preliminary Test Phase Leaderboard.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAI in cancer detection · Radiomics and Machine Learning in Medical Imaging · Digital Imaging for Blood Diseases
Methods*Communicated@Fast*How Do I Communicate to Expedia? · Batch Normalization · Concatenated Skip Connection · 1x1 Convolution · Dropout · Softmax · Max Pooling · Convolution · Dense Connections · Kaiming Initialization