Deep learning-based framework for slide-based histopathological image analysis
importance 7/10
ai assisted
AI in cancer detection digital pathology stage: research
Problem
Whole-slide histopathology image analysis lacked a general slide-based framework, with existing methods being task-dependent.
Why it matters
Automated pathology analysis supports cancer classification, survival analysis, and subtyping from tissue images.
What the AI did
The authors proposed HipoMap, a slide-based WSI representation framework coupled with convolutional neural networks applicable to any slide-based problem.
Results
not stated in source
Impact
The evidence supports a proposed framework only; no benchmark or validation results are stated.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Sai Kosaraju, Jeongyeon Park, Hyun Jung Lee, Jung Wook Yang, Mingon Kang |
| Citations | 44 (OpenAlex, at import time) |
| References | 55 |
| Model or method | HipoMap with convolutional neural networks |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-022-23166-0 |
| Open access | gold |
| Keywords | digital pathology, whole-slide images, deep learning, HipoMap, CNN, cancer classification |
Importance rating
7
significant — thousands to millions affected
Supports cancer classification, survival analysis, and subtyping from pathology images; cancer diagnosis affects millions, but abstract gives no scale figures, only application domains.