Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsies
The scalable recurrence graph network (SRGNet) is introduced in this paper to improve the accuracy of predicting five-year survival outcomes in rectal cancer patients by analyzing RhoB texture dynamics in biopsies. RhoB, a key biomarker assessed via immunohistochemistry, is crucial in predicting res...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-03-01
|
| Series: | APL Machine Learning |
| Online Access: | http://dx.doi.org/10.1063/5.0243636 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849739080814821376 |
|---|---|
| author | Tuan D. Pham |
| author_facet | Tuan D. Pham |
| author_sort | Tuan D. Pham |
| collection | DOAJ |
| description | The scalable recurrence graph network (SRGNet) is introduced in this paper to improve the accuracy of predicting five-year survival outcomes in rectal cancer patients by analyzing RhoB texture dynamics in biopsies. RhoB, a key biomarker assessed via immunohistochemistry, is crucial in predicting responses to radiotherapy (RT), but variability in staining techniques and tumor heterogeneity often complicate these assessments. SRGNet integrates spatial statistics, nonlinear dynamics, graph theory, and graph convolutional networks to address these challenges. In testing, SRGNet outperformed 10 pre-trained convolutional neural networks, achieving 88% accuracy in biopsies from RT patients, with 67% accuracy for predicting survival under five years and 100% accuracy for survival over five years, along with 100% precision, an F1 score of 0.80, and an AUC of 0.73. For non-RT patients, SRGNet attained 91% accuracy, 100% precision for survival over five years, an F1 score of 0.86, and an AUC of 0.82. These results demonstrate SRGNet’s potential to enhance the precision and reliability of survival predictions in rectal cancer patients, overcoming challenges of RhoB expression variability and tumor heterogeneity. |
| format | Article |
| id | doaj-art-530def4e87814855b088658043a4d7b7 |
| institution | DOAJ |
| issn | 2770-9019 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Machine Learning |
| spelling | doaj-art-530def4e87814855b088658043a4d7b72025-08-20T03:06:24ZengAIP Publishing LLCAPL Machine Learning2770-90192025-03-0131016105016105-1310.1063/5.0243636Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsiesTuan D. Pham0Barts and The London School of Medicine and Dentistry, Queen Mary University of London, Turner Street, London E1 2AD, United KingdomThe scalable recurrence graph network (SRGNet) is introduced in this paper to improve the accuracy of predicting five-year survival outcomes in rectal cancer patients by analyzing RhoB texture dynamics in biopsies. RhoB, a key biomarker assessed via immunohistochemistry, is crucial in predicting responses to radiotherapy (RT), but variability in staining techniques and tumor heterogeneity often complicate these assessments. SRGNet integrates spatial statistics, nonlinear dynamics, graph theory, and graph convolutional networks to address these challenges. In testing, SRGNet outperformed 10 pre-trained convolutional neural networks, achieving 88% accuracy in biopsies from RT patients, with 67% accuracy for predicting survival under five years and 100% accuracy for survival over five years, along with 100% precision, an F1 score of 0.80, and an AUC of 0.73. For non-RT patients, SRGNet attained 91% accuracy, 100% precision for survival over five years, an F1 score of 0.86, and an AUC of 0.82. These results demonstrate SRGNet’s potential to enhance the precision and reliability of survival predictions in rectal cancer patients, overcoming challenges of RhoB expression variability and tumor heterogeneity.http://dx.doi.org/10.1063/5.0243636 |
| spellingShingle | Tuan D. Pham Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsies APL Machine Learning |
| title | Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsies |
| title_full | Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsies |
| title_fullStr | Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsies |
| title_full_unstemmed | Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsies |
| title_short | Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsies |
| title_sort | scalable recurrence graph network for stratifying rhob texture dynamics in rectal cancer biopsies |
| url | http://dx.doi.org/10.1063/5.0243636 |
| work_keys_str_mv | AT tuandpham scalablerecurrencegraphnetworkforstratifyingrhobtexturedynamicsinrectalcancerbiopsies |