Related Experiment Video
Updated: Aug 1, 2025
10:25
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
Published on: November 11, 2022
9.0K
A Deep Learning Approach for Histology-Based Nucleus Segmentation and Tumor Microenvironment Characterization.
Ruichen Rong1, Hudanyun Sheng1, Kevin W Jin1
1Quantitative Biomedical Research Center, Peter O'Donnell Jr. School of Public Health, UT Southwestern Medical Center, Dallas, Texas.
Summary
Histology-based Detection using Yolo (HD-Yolo) accelerates nucleus segmentation and tumor microenvironment quantification in whole-slide images (WSIs). This AI method improves accuracy and speed for digital pathology, outperforming existing approaches in cancer research.
Area of Science:
- Digital Pathology
- Computational Biology
- Cancer Research
Background:
- Manual pathology slide examination is subjective and time-consuming.
- Whole-slide imaging (WSI) generates massive datasets for high-resolution analysis.
- Deep learning enhances efficiency and accuracy in pathology image analysis.
Purpose of the Study:
- To develop a computationally efficient method for nucleus segmentation and tumor microenvironment (TME) quantification in WSIs.
- To accelerate digital pathology workflows for disease diagnosis and research.
- To improve the prognostic significance of nucleus features in cancer.
Main Methods:
- Introduced Histology-based Detection using Yolo (HD-Yolo), a novel deep learning approach.
- Applied HD-Yolo for nucleus segmentation and TME quantification on WSI data.
- Validated performance across lung, liver, and breast cancer tissue types.
Main Results:
- HD-Yolo significantly accelerates nucleus segmentation and TME quantification compared to existing methods.
- Achieved superior nucleus detection and classification accuracy.
- Demonstrated enhanced prognostic significance of nucleus features in breast cancer compared to IHC markers.
Conclusions:
- HD-Yolo offers a faster and more accurate solution for WSI analysis in digital pathology.
- The method provides valuable insights into tumor biology and prognostic factors.
- HD-Yolo has potential applications in routine clinical procedures and biomedical research.
