Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer
Abstract Objective This study aimed to develop and evaluate an automatic model using artificial intelligence (AI) for quantifying vascular involvement and classifying tumor resectability stage in patients with pancreatic ductal adenocarcinoma (PDAC), primarily to support radiologists in referral cen...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-02-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-023-00419-9 |
| _version_ | 1797275940568432640 |
|---|---|
| author | Jacqueline I. Bereska Boris V. Janssen C. Yung Nio Marnix P. M. Kop Geert Kazemier Olivier R. Busch Femke Struik Henk A. Marquering Jaap Stoker Marc G. Besselink Inez M. Verpalen for the Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) consortium |
| author_facet | Jacqueline I. Bereska Boris V. Janssen C. Yung Nio Marnix P. M. Kop Geert Kazemier Olivier R. Busch Femke Struik Henk A. Marquering Jaap Stoker Marc G. Besselink Inez M. Verpalen for the Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) consortium |
| author_sort | Jacqueline I. Bereska |
| collection | DOAJ |
| description | Abstract Objective This study aimed to develop and evaluate an automatic model using artificial intelligence (AI) for quantifying vascular involvement and classifying tumor resectability stage in patients with pancreatic ductal adenocarcinoma (PDAC), primarily to support radiologists in referral centers. Resectability of PDAC is determined by the degree of vascular involvement on computed tomography scans (CTs), which is associated with considerable inter-observer variability. Methods We developed a semisupervised machine learning segmentation model to segment the PDAC and surrounding vasculature using 613 CTs of 467 patients with pancreatic tumors and 50 control patients. After segmenting the relevant structures, our model quantifies vascular involvement by measuring the degree of the vessel wall that is in contact with the tumor using AI-segmented CTs. Based on these measurements, the model classifies the resectability stage using the Dutch Pancreatic Cancer Group criteria as either resectable, borderline resectable, or locally advanced (LA). Results We evaluated the performance of the model using a test set containing 60 CTs from 60 patients, consisting of 20 resectable, 20 borderline resectable, and 20 locally advanced cases, by comparing the automated analysis obtained from the model to expert visual vascular involvement assessments. The model concurred with the radiologists on 227/300 (76%) vessels for determining vascular involvement. The model’s resectability classification agreed with the radiologists on 17/20 (85%) resectable, 16/20 (80%) for borderline resectable, and 15/20 (75%) for locally advanced cases. Conclusions This study demonstrates that an AI model may allow automatic quantification of vascular involvement and classification of resectability for PDAC. Relevance statement This AI model enables automated vascular involvement quantification and resectability classification for pancreatic cancer, aiding radiologists in treatment decisions, and potentially improving patient outcomes. Key points • High inter-observer variability exists in determining vascular involvement and resectability for PDAC. • Artificial intelligence accurately quantifies vascular involvement and classifies resectability for PDAC. • Artificial intelligence can aid radiologists by automating vascular involvement and resectability assessments. Graphical Abstract |
| first_indexed | 2024-03-07T15:21:15Z |
| format | Article |
| id | doaj.art-bc69e5a6ed964550a326bec8491c1902 |
| institution | Directory Open Access Journal |
| issn | 2509-9280 |
| language | English |
| last_indexed | 2024-03-07T15:21:15Z |
| publishDate | 2024-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj.art-bc69e5a6ed964550a326bec8491c19022024-03-05T17:38:15ZengSpringerOpenEuropean Radiology Experimental2509-92802024-02-018111010.1186/s41747-023-00419-9Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancerJacqueline I. Bereska0Boris V. Janssen1C. Yung Nio2Marnix P. M. Kop3Geert Kazemier4Olivier R. Busch5Femke Struik6Henk A. Marquering7Jaap Stoker8Marc G. Besselink9Inez M. Verpalen10for the Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) consortiumDepartment of Radiology and Nuclear Medicine, Amsterdam UMC, Location University of AmsterdamCancer Center AmsterdamDepartment of Radiology and Nuclear Medicine, Amsterdam UMC, Location University of AmsterdamDepartment of Radiology and Nuclear Medicine, Amsterdam UMC, Location University of AmsterdamCancer Center AmsterdamCancer Center AmsterdamDepartment of Radiology and Nuclear Medicine, Amsterdam UMC, Location University of AmsterdamDepartment of Radiology and Nuclear Medicine, Amsterdam UMC, Location University of AmsterdamDepartment of Radiology and Nuclear Medicine, Amsterdam UMC, Location University of AmsterdamCancer Center AmsterdamDepartment of Radiology and Nuclear Medicine, Amsterdam UMC, Location University of AmsterdamAbstract Objective This study aimed to develop and evaluate an automatic model using artificial intelligence (AI) for quantifying vascular involvement and classifying tumor resectability stage in patients with pancreatic ductal adenocarcinoma (PDAC), primarily to support radiologists in referral centers. Resectability of PDAC is determined by the degree of vascular involvement on computed tomography scans (CTs), which is associated with considerable inter-observer variability. Methods We developed a semisupervised machine learning segmentation model to segment the PDAC and surrounding vasculature using 613 CTs of 467 patients with pancreatic tumors and 50 control patients. After segmenting the relevant structures, our model quantifies vascular involvement by measuring the degree of the vessel wall that is in contact with the tumor using AI-segmented CTs. Based on these measurements, the model classifies the resectability stage using the Dutch Pancreatic Cancer Group criteria as either resectable, borderline resectable, or locally advanced (LA). Results We evaluated the performance of the model using a test set containing 60 CTs from 60 patients, consisting of 20 resectable, 20 borderline resectable, and 20 locally advanced cases, by comparing the automated analysis obtained from the model to expert visual vascular involvement assessments. The model concurred with the radiologists on 227/300 (76%) vessels for determining vascular involvement. The model’s resectability classification agreed with the radiologists on 17/20 (85%) resectable, 16/20 (80%) for borderline resectable, and 15/20 (75%) for locally advanced cases. Conclusions This study demonstrates that an AI model may allow automatic quantification of vascular involvement and classification of resectability for PDAC. Relevance statement This AI model enables automated vascular involvement quantification and resectability classification for pancreatic cancer, aiding radiologists in treatment decisions, and potentially improving patient outcomes. Key points • High inter-observer variability exists in determining vascular involvement and resectability for PDAC. • Artificial intelligence accurately quantifies vascular involvement and classifies resectability for PDAC. • Artificial intelligence can aid radiologists by automating vascular involvement and resectability assessments. Graphical Abstracthttps://doi.org/10.1186/s41747-023-00419-9Artificial intelligenceCarcinoma (pancreatic ductal)Pancreatic neoplasmsTomography (x-ray computed)Unsupervised machine learning |
| spellingShingle | Jacqueline I. Bereska Boris V. Janssen C. Yung Nio Marnix P. M. Kop Geert Kazemier Olivier R. Busch Femke Struik Henk A. Marquering Jaap Stoker Marc G. Besselink Inez M. Verpalen for the Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) consortium Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer European Radiology Experimental Artificial intelligence Carcinoma (pancreatic ductal) Pancreatic neoplasms Tomography (x-ray computed) Unsupervised machine learning |
| title | Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer |
| title_full | Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer |
| title_fullStr | Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer |
| title_full_unstemmed | Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer |
| title_short | Artificial intelligence for assessment of vascular involvement and tumor resectability on CT in patients with pancreatic cancer |
| title_sort | artificial intelligence for assessment of vascular involvement and tumor resectability on ct in patients with pancreatic cancer |
| topic | Artificial intelligence Carcinoma (pancreatic ductal) Pancreatic neoplasms Tomography (x-ray computed) Unsupervised machine learning |
| url | https://doi.org/10.1186/s41747-023-00419-9 |
| work_keys_str_mv | AT jacquelineibereska artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT borisvjanssen artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT cyungnio artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT marnixpmkop artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT geertkazemier artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT olivierrbusch artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT femkestruik artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT henkamarquering artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT jaapstoker artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT marcgbesselink artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT inezmverpalen artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer AT forthepancreatobiliaryandhepaticartificialintelligenceresearchphairconsortium artificialintelligenceforassessmentofvascularinvolvementandtumorresectabilityonctinpatientswithpancreaticcancer |