AI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump
Introduction: Perihilar cholangiocarcinoma (PHCC) is a rare malignancy with limited survival prediction accuracy. Artificial intelligence (AI) and digital pathology advancements have shown promise in predicting outcomes in cancer. We aimed to improve prognosis prediction for PHCC by combining AI-bas...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2153353923001591 |
| _version_ | 1797448102277283840 |
|---|---|
| author | Dieter P. Hoyer Saskia Ting Nina Rogacka Sven Koitka René Hosch Nils Flaschel Johannes Haubold Eugen Malamutmann Björn-Ole Stüben Jürgen Treckmann Felix Nensa Giulia Baldini |
| author_facet | Dieter P. Hoyer Saskia Ting Nina Rogacka Sven Koitka René Hosch Nils Flaschel Johannes Haubold Eugen Malamutmann Björn-Ole Stüben Jürgen Treckmann Felix Nensa Giulia Baldini |
| author_sort | Dieter P. Hoyer |
| collection | DOAJ |
| description | Introduction: Perihilar cholangiocarcinoma (PHCC) is a rare malignancy with limited survival prediction accuracy. Artificial intelligence (AI) and digital pathology advancements have shown promise in predicting outcomes in cancer. We aimed to improve prognosis prediction for PHCC by combining AI-based histopathological slide analysis with clinical factors. Methods: We retrospectively analyzed 317 surgically treated PHCC patients (January 2009–December 2018) at the University Hospital of Essen. Clinical data, surgical details, pathology, and outcomes were collected. Convolutional neural networks (CNN) analyzed whole-slide images. Survival models incorporated clinical and histological features. Results: Among 142 eligible patients, independent survival predictors were tumor grade (G), tumor size (T), and intraoperative transfusion requirement. The CNN-based model combining clinical and histopathological features demonstrates proof of concept in prognosis prediction, limited by histopathological complexity and feature extraction challenges. However, the CNN-based model generated heatmaps assisting pathologists in identifying areas of interest. Conclusion: AI-based digital pathology showed potential in PHCC prognosis prediction, though refinement is necessary for clinical relevance. Future research should focus on enhancing AI models and exploring novel approaches to improve PHCC patient prognosis prediction. |
| first_indexed | 2024-03-09T14:05:31Z |
| format | Article |
| id | doaj.art-1fba50fd11954cf6bc0d7d706821aaef |
| institution | Directory Open Access Journal |
| issn | 2153-3539 |
| language | English |
| last_indexed | 2024-03-09T14:05:31Z |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-1fba50fd11954cf6bc0d7d706821aaef2023-11-30T05:06:34ZengElsevierJournal of Pathology Informatics2153-35392024-12-0115100345AI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jumpDieter P. Hoyer0Saskia Ting1Nina Rogacka2Sven Koitka3René Hosch4Nils Flaschel5Johannes Haubold6Eugen Malamutmann7Björn-Ole Stüben8Jürgen Treckmann9Felix Nensa10Giulia Baldini11University Hospital Essen, Department of General, Visceral and Transplantation Surgery, Essen, GermanyUniversity Hospital Essen, Institute for Pathology and Neuropathology, Essen, Germany; Institute of Pathology Nordhessen, Kassel, GermanyUniversity Hospital Essen, Department of General, Visceral and Transplantation Surgery, Essen, GermanyUniversity Hospital Essen, Institute of Interventional and Diagnostic Radiology and Neuroradiology, Essen, Germany; University Hospital Essen, Institute for Artificial Intelligence in Medicine, Essen, GermanyUniversity Hospital Essen, Institute of Interventional and Diagnostic Radiology and Neuroradiology, Essen, Germany; University Hospital Essen, Institute for Artificial Intelligence in Medicine, Essen, GermanyUniversity Hospital Essen, Institute of Interventional and Diagnostic Radiology and Neuroradiology, Essen, Germany; University Hospital Essen, Institute for Artificial Intelligence in Medicine, Essen, GermanyUniversity Hospital Essen, Institute of Interventional and Diagnostic Radiology and Neuroradiology, Essen, Germany; University Hospital Essen, Institute for Artificial Intelligence in Medicine, Essen, GermanyUniversity Hospital Essen, Department of General, Visceral and Transplantation Surgery, Essen, GermanyUniversity Hospital Essen, Department of General, Visceral and Transplantation Surgery, Essen, GermanyUniversity Hospital Essen, Department of General, Visceral and Transplantation Surgery, Essen, GermanyUniversity Hospital Essen, Institute of Interventional and Diagnostic Radiology and Neuroradiology, Essen, Germany; University Hospital Essen, Institute for Artificial Intelligence in Medicine, Essen, GermanyUniversity Hospital Essen, Institute of Interventional and Diagnostic Radiology and Neuroradiology, Essen, Germany; University Hospital Essen, Institute for Artificial Intelligence in Medicine, Essen, Germany; Corresponding author at: Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen, Germany.Introduction: Perihilar cholangiocarcinoma (PHCC) is a rare malignancy with limited survival prediction accuracy. Artificial intelligence (AI) and digital pathology advancements have shown promise in predicting outcomes in cancer. We aimed to improve prognosis prediction for PHCC by combining AI-based histopathological slide analysis with clinical factors. Methods: We retrospectively analyzed 317 surgically treated PHCC patients (January 2009–December 2018) at the University Hospital of Essen. Clinical data, surgical details, pathology, and outcomes were collected. Convolutional neural networks (CNN) analyzed whole-slide images. Survival models incorporated clinical and histological features. Results: Among 142 eligible patients, independent survival predictors were tumor grade (G), tumor size (T), and intraoperative transfusion requirement. The CNN-based model combining clinical and histopathological features demonstrates proof of concept in prognosis prediction, limited by histopathological complexity and feature extraction challenges. However, the CNN-based model generated heatmaps assisting pathologists in identifying areas of interest. Conclusion: AI-based digital pathology showed potential in PHCC prognosis prediction, though refinement is necessary for clinical relevance. Future research should focus on enhancing AI models and exploring novel approaches to improve PHCC patient prognosis prediction.http://www.sciencedirect.com/science/article/pii/S2153353923001591KlatskinCholangiocarcinomaSurvival analysisSegmentationDigital pathologyArtificial intelligence |
| spellingShingle | Dieter P. Hoyer Saskia Ting Nina Rogacka Sven Koitka René Hosch Nils Flaschel Johannes Haubold Eugen Malamutmann Björn-Ole Stüben Jürgen Treckmann Felix Nensa Giulia Baldini AI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump Journal of Pathology Informatics Klatskin Cholangiocarcinoma Survival analysis Segmentation Digital pathology Artificial intelligence |
| title | AI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump |
| title_full | AI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump |
| title_fullStr | AI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump |
| title_full_unstemmed | AI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump |
| title_short | AI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump |
| title_sort | ai based digital histopathology for perihilar cholangiocarcinoma a step not a jump |
| topic | Klatskin Cholangiocarcinoma Survival analysis Segmentation Digital pathology Artificial intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S2153353923001591 |
| work_keys_str_mv | AT dieterphoyer aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT saskiating aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT ninarogacka aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT svenkoitka aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT renehosch aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT nilsflaschel aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT johanneshaubold aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT eugenmalamutmann aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT bjornolestuben aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT jurgentreckmann aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT felixnensa aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump AT giuliabaldini aibaseddigitalhistopathologyforperihilarcholangiocarcinomaastepnotajump |