Prediction of biochemical prostate cancer recurrence from any Gleason score using robust tissue structure and clinically available information
Abstract Biopsy information and protein Prostate-Specific Antigen (PSA) levels are the most robust information available to oncologists worldwide to diagnose and decide therapies for prostate cancer patients. However, prostate cancer presents a high risk of recurrence, and the technologies used to e...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-02-01
|
| Series: | Discover Oncology |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s12672-025-01896-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861819387674624 |
|---|---|
| author | Laura E. Marin Daniel I. Zavaleta-Guzman Jessyca I. Gutierrez-Garcia Daniel Racoceanu Fanny L. Casado |
| author_facet | Laura E. Marin Daniel I. Zavaleta-Guzman Jessyca I. Gutierrez-Garcia Daniel Racoceanu Fanny L. Casado |
| author_sort | Laura E. Marin |
| collection | DOAJ |
| description | Abstract Biopsy information and protein Prostate-Specific Antigen (PSA) levels are the most robust information available to oncologists worldwide to diagnose and decide therapies for prostate cancer patients. However, prostate cancer presents a high risk of recurrence, and the technologies used to evaluate it demand more complex resources. This paper aims to predict Biochemical Recurrence (BCR) based on Whole Slide Images (WSI) of biopsies, Gleason scores, and PSA levels. A U-net model was used to segment phenotypic features and trained on images from the Prostate Cancer Grade Assessment (PANDA) database to segment tumorous regions from pre-processed and scored WSI of biopsies. Then, the model was tested on data from publicly available repositories achieving an Intersection over Union of 87%. Tissue features, Gleason scores, and PSA levels provided high accuracy and precision in classifying patients according to their risk of presenting recurrence, for any Gleason score sampled. The trained classifier model demonstrated a 79.2% relative accuracy, and a precision of 69.7% for patients experiencing recurrences before 24 months. Our results provide a robust, cost-efficient approach using already available information to predict the risk of BCR. |
| format | Article |
| id | doaj-art-8af6e045cf18492f888871a561059f8e |
| institution | Kabale University |
| issn | 2730-6011 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Springer |
| record_format | Article |
| series | Discover Oncology |
| spelling | doaj-art-8af6e045cf18492f888871a561059f8e2025-02-09T12:43:32ZengSpringerDiscover Oncology2730-60112025-02-0116111610.1007/s12672-025-01896-7Prediction of biochemical prostate cancer recurrence from any Gleason score using robust tissue structure and clinically available informationLaura E. Marin0Daniel I. Zavaleta-Guzman1Jessyca I. Gutierrez-Garcia2Daniel Racoceanu3Fanny L. Casado4Institute of Omics Sciences and Applied Biotechnology, Pontificia Universidad Catolica del PeruInstitute of Omics Sciences and Applied Biotechnology, Pontificia Universidad Catolica del PeruInstitute of Omics Sciences and Applied Biotechnology, Pontificia Universidad Catolica del PeruSorbonne University, Paris Brain Institute, CNRS, Inria, Inserm, AP-HPInstitute of Omics Sciences and Applied Biotechnology, Pontificia Universidad Catolica del PeruAbstract Biopsy information and protein Prostate-Specific Antigen (PSA) levels are the most robust information available to oncologists worldwide to diagnose and decide therapies for prostate cancer patients. However, prostate cancer presents a high risk of recurrence, and the technologies used to evaluate it demand more complex resources. This paper aims to predict Biochemical Recurrence (BCR) based on Whole Slide Images (WSI) of biopsies, Gleason scores, and PSA levels. A U-net model was used to segment phenotypic features and trained on images from the Prostate Cancer Grade Assessment (PANDA) database to segment tumorous regions from pre-processed and scored WSI of biopsies. Then, the model was tested on data from publicly available repositories achieving an Intersection over Union of 87%. Tissue features, Gleason scores, and PSA levels provided high accuracy and precision in classifying patients according to their risk of presenting recurrence, for any Gleason score sampled. The trained classifier model demonstrated a 79.2% relative accuracy, and a precision of 69.7% for patients experiencing recurrences before 24 months. Our results provide a robust, cost-efficient approach using already available information to predict the risk of BCR.https://doi.org/10.1007/s12672-025-01896-7Prostate cancerBiochemical recurrenceU-Net architectureGleason scoreWhole slide histopathology imageHematoxylin and Eosin staining |
| spellingShingle | Laura E. Marin Daniel I. Zavaleta-Guzman Jessyca I. Gutierrez-Garcia Daniel Racoceanu Fanny L. Casado Prediction of biochemical prostate cancer recurrence from any Gleason score using robust tissue structure and clinically available information Discover Oncology Prostate cancer Biochemical recurrence U-Net architecture Gleason score Whole slide histopathology image Hematoxylin and Eosin staining |
| title | Prediction of biochemical prostate cancer recurrence from any Gleason score using robust tissue structure and clinically available information |
| title_full | Prediction of biochemical prostate cancer recurrence from any Gleason score using robust tissue structure and clinically available information |
| title_fullStr | Prediction of biochemical prostate cancer recurrence from any Gleason score using robust tissue structure and clinically available information |
| title_full_unstemmed | Prediction of biochemical prostate cancer recurrence from any Gleason score using robust tissue structure and clinically available information |
| title_short | Prediction of biochemical prostate cancer recurrence from any Gleason score using robust tissue structure and clinically available information |
| title_sort | prediction of biochemical prostate cancer recurrence from any gleason score using robust tissue structure and clinically available information |
| topic | Prostate cancer Biochemical recurrence U-Net architecture Gleason score Whole slide histopathology image Hematoxylin and Eosin staining |
| url | https://doi.org/10.1007/s12672-025-01896-7 |
| work_keys_str_mv | AT lauraemarin predictionofbiochemicalprostatecancerrecurrencefromanygleasonscoreusingrobusttissuestructureandclinicallyavailableinformation AT danielizavaletaguzman predictionofbiochemicalprostatecancerrecurrencefromanygleasonscoreusingrobusttissuestructureandclinicallyavailableinformation AT jessycaigutierrezgarcia predictionofbiochemicalprostatecancerrecurrencefromanygleasonscoreusingrobusttissuestructureandclinicallyavailableinformation AT danielracoceanu predictionofbiochemicalprostatecancerrecurrencefromanygleasonscoreusingrobusttissuestructureandclinicallyavailableinformation AT fannylcasado predictionofbiochemicalprostatecancerrecurrencefromanygleasonscoreusingrobusttissuestructureandclinicallyavailableinformation |