Dynamic Learning Rate in Deep CNN Model for Metastasis Detection and Classification of Histopathology Images
importance 6/10
ai assisted
AI in cancer detection digital pathology stage: research
Problem
Detecting and classifying breast cancer metastasis in histopathology whole slide images is difficult and needs computer-aided second opinions.
Why it matters
Accurate metastasis grading guides breast cancer treatment and early intervention.
What the AI did
A deep CNN trained on patches from whole slide images classifies tissue as benign or malignant, with learning-rate tuning to improve accuracy.
Results
not stated in source
Impact
Proposed CAD approach; clinical impact not demonstrated in abstract.
Record
| Venue | Computational and Mathematical Methods in Medicine |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Anil Johny, K. N. Madhusoodanan |
| Citations | 30 (OpenAlex, at import time) |
| References | 60 |
| Model or method | deep convolutional neural network (DCNN) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1155/2021/5557168 |
| Open access | hybrid |
| Keywords | histopathology, breast cancer, metastasis, deep CNN, learning rate, CAD |
Importance rating
6
significant — thousands to millions affected
Breast cancer metastasis grading via WSI is called the gold standard guiding treatment and early detection; no scale stated, but clinical significance is implied.