Artificial intelligence–Driven patient selection for preoperative portal vein embolization for patients with colorectal cancer liver metastases Journal Article


Authors: Kuhn, T. N.; Engelhardt, W. D.; Kahl, V. H.; Alkukhun, A.; Gross, M.; Iseke, S.; Onofrey, J.; Covey, A.; Camacho, J. C.; Kawaguchi, Y.; Hasegawa, K.; Odisio, B. C.; Vauthey, J. N.; Antoch, G.; Chapiro, J.; Madoff, D. C.
Article Title: Artificial intelligence–Driven patient selection for preoperative portal vein embolization for patients with colorectal cancer liver metastases
Abstract: Purpose: To develop a machine learning algorithm to improve hepatic resection selection for patients with metastatic colorectal cancer (CRC) by predicting post–portal vein embolization (PVE) outcomes. Materials and Methods: This multicenter retrospective study (2000–2020) included 200 consecutive patients with CRC liver metastases planned for PVE before surgery. Data on radiomic features and laboratory values were collected. Patient-specific eigenvalues for each liver shape were calculated using a statistical shape model approach. After semiautomatic segmentation and review by a board-certified radiologist, the data were split 70%/30% for training and testing. Three machine learning algorithms predicting the total liver volume (TLV) after PVE, sufficient future liver remnant (FLR%), and kinetic growth rate (KGR%) were trained, with performance assessed using accuracy, sensitivity, specificity, area under the curve (AUC), or root mean squared error. Significance between the internal and external test sets was assessed by the Student t-test. One institution was kept separate as an external testing set. Results: A total of 114 (76 men; mean age, 56 years [SD± 12]) and 37 (19 men; mean age, 50 years ± [SD± 11]) patients met the inclusion criteria for the internal validation and external validation, respectively. Prediction accuracy and AUC for sufficient FLR% or liver growth potential (KGR%> 0%) were high in the internal testing set—85.81% (SD ± 1.01) and 0.91 (SD ± 0.01) or 87.44% (SD ± 0.10) and 0.66 (SD ± 0.03), respectively. Similar results occurred in the external testing set—79.66% (SD ± 0.60) and 0.88 (SD ± 0.00) or 72.06% (SD ± 0.30) and 0.69 (SD ± 0.01), respectively. TLV prediction showed discrepancy rates of 12.56% (SD ±4.20%; P = .86) internally and 13.57% (SD ± 3.76%; P = .91) externally. Conclusions: Machine learning–based models incorporating radiomics and laboratory test results may help predict the FLR%, KGR%, and TLV as metrics for successful PVE. © 2024 SIR
Keywords: adult; controlled study; middle aged; cancer surgery; human cell; major clinical study; bevacizumab; cisplatin; fluorouracil; cancer combination chemotherapy; patient selection; treatment planning; capecitabine; gemcitabine; cancer patient; preoperative care; follow up; antineoplastic agent; diagnostic accuracy; sensitivity and specificity; computer assisted tomography; multiple cycle treatment; cyclophosphamide; validation study; retrospective study; cetuximab; irinotecan; panitumumab; postoperative complication; alkaline phosphatase; bilirubin; liver failure; prothrombin time; liver; medical information; laboratory test; artificial intelligence; folinic acid; hepatectomy; oxaliplatin; floxuridine; false positive result; statistical model; bilirubin blood level; nuclear magnetic resonance; predictive value; liver weight; receiver operating characteristic; platelet count; image segmentation; external validity; internal validity; metastatic colorectal cancer; diagnostic test accuracy study; clinical outcome; multicenter study (topic); feature extraction; machine learning; learning algorithm; gimeracil plus oteracil potassium plus tegafur; gelatin sponge; colorectal liver metastasis; predictive model; human; male; female; article; future liver remnant; feature selection; digestive tract parameters; radiomics; artificial embolization; vinorelbine tartrate; hepatic portal vein; enbucrilate; alkaline phosphatase level; kinetic growth rate; liver shape
Journal Title: Journal of Vascular and Interventional Radiology
Volume: 36
Issue: 3
ISSN: 1051-0443
Publisher: Elsevier Science, Inc.  
Date Published: 2025-03-01
Start Page: 477
End Page: 488
Language: English
DOI: 10.1016/j.jvir.2024.11.025
PUBMED: 39638087
PROVIDER: scopus
DOI/URL:
Notes: Article -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Anne Covey
    166 Covey