Multiple Instance Bagging and Risk Histogram for Survival Time Analysis Based on Whole Slide Images of Brain Cancer Patients
This study tackles the challenges in computer-aided prognosis for glioblastoma multiforme, a highly aggressive brain cancer, using only whole slide images (WSIs) as input. Unlike traditional methods that rely on random selection or region-of-interest (ROI) extraction to choose meaningful subsets of...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/15/12/750 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study tackles the challenges in computer-aided prognosis for glioblastoma multiforme, a highly aggressive brain cancer, using only whole slide images (WSIs) as input. Unlike traditional methods that rely on random selection or region-of-interest (ROI) extraction to choose meaningful subsets of patches representing the whole slide, we propose a multiple instance bagging approach. This method utilizes all patches extracted from the whole slide, employing different subsets in each training epoch, thereby leveraging information from the entire slide while keeping the training computationally feasible. Additionally, we developed a two-stage framework based on the ResNet-CBAM model which estimates not just the usual survival risk, but also predicts the actual survival time. Using risk scores of patches estimated from the risk estimation stage, a risk histogram can be constructed and used as input to train a survival time prediction model. A censor hinge loss based on root mean square error was also developed to handle censored data when training the regression model. Tests using the Cancer Genome Atlas Program’s glioblastoma public database yielded a concordance index of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>73.16</mn><mo>±</mo><mn>2.15</mn><mo>%</mo></mrow></semantics></math></inline-formula>, surpassing existing models. Log-rank testing on predicted high- and low-risk groups using the Kaplan–Meier method revealed a p-value of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3.88</mn><mo>×</mo><msup><mn>10</mn><mrow><mo>−</mo><mn>9</mn></mrow></msup></mrow></semantics></math></inline-formula>, well below the usual threshold of 0.005, indicating the model’s ability to significantly differentiate between the two groups. We also implemented a heatmap visualization method that provides interpretable risk assessments at the patch level, potentially aiding clinicians in identifying high-risk regions within WSIs. Notably, these results were achieved using 98% fewer parameters compared to state-of-the-art models. |
|---|---|
| ISSN: | 2078-2489 |