Synapse - Computed tomography-based radiomics with machine learning outperforms radiologist assessment in estimating colorectal liver metastases pathologic response after chemotherapy

Computed tomography-based radiomics with machine learning outperforms radiologist assessment in estimating colorectal liver metastases pathologic response after chemotherapy Journal Article

Authors:	Karagkounis, G.; Horvat, N.; Danilova, S.; Chhabra, S.; Narayan, R. R.; Barekzai, A. B.; Kleshchelski, A.; Joanne, C.; Gonen, M.; Balachandran, V.; Soares, K. C.; Wei, A. C.; Kingham, T. P.; Jarnagin, W. R.; Shia, J.; Chakraborty, J.; D’Angelica, M. I.
Article Title:	Computed tomography-based radiomics with machine learning outperforms radiologist assessment in estimating colorectal liver metastases pathologic response after chemotherapy
Abstract:	Objectives: This study was designed to assess computed tomography (CT)-based radiomics of colorectal liver metastases (CRLM), extracted from posttreatment scans in estimating pathologic treatment response to neoadjuvant therapy, and to compare treatment response estimates between CT-based radiomics and radiological response assessment by using RECIST 1.1 and CT morphologic criteria. Methods: Patients who underwent resection for CRLM from January 2003–December 2012 at a single institution were included. Patients who did not receive preoperative systemic chemotherapy, or without adequate imaging, were excluded. Imaging characteristics were evaluated based on RECIST 1.1 and CT morphologic criteria. A machine-learning model was designed with radiomic features extracted from manually segmented posttreatment CT tumoral and peritumoral regions to identify pathologic responders (≥ 50% response) versus nonresponders. Statistical analysis was performed at the tumor level. Results: Eighty-five patients (median age, 62 years; 55 women) with 95 tumors were included. None of the subjectively evaluated imaging characteristics were associated with pathologic response (p > 0.05). Inter-reader agreement was substantial for RECIST categorical response assessment (K = 0.70) and moderate for CT morphological group response (K = 0.50). In the validation cohort, the machine learning model built with radiomic features obtained an area under the curve (AUC) of 0.87 and outperformed subjective RECIST assessment (AUC = 0.53, p = 0.01) and morphologic assessment (AUC = 0.56, p = 0.02). Conclusions: Radiologist assessment of oligometastatic CRLM after neoadjuvant therapy using RECIST 1.1 and CT morphologic criteria was not associated with pathologic response. In contrast, a machine-learning model based on radiomic features extracted from tumoral and peritumoral regions had high diagnostic performance in assessing responders versus nonresponders. © Society of Surgical Oncology 2024.
Keywords:	adult; treatment response; aged; middle aged; cancer surgery; retrospective studies; major clinical study; histopathology; bevacizumab; fluorouracil; cancer combination chemotherapy; monotherapy; liver neoplasms; capecitabine; cancer patient; neoadjuvant therapy; follow up; follow-up studies; antineoplastic agent; sensitivity and specificity; colorectal cancer; computer assisted tomography; multiple cycle treatment; antineoplastic combined chemotherapy protocols; cohort analysis; tomography, x-ray computed; pathology; validation study; diagnostic imaging; retrospective study; age; irinotecan; colorectal neoplasms; radiologist; add on therapy; colorectal tumor; liver tumor; intermethod comparison; iohexol; hepatectomy; neoadjuvant chemotherapy; drug therapy; gender; oxaliplatin; cancer morphology; predictive value; receiver operating characteristic; pathological response; liver metastases; image segmentation; diagnostic test accuracy study; texture analysis; metastasis resection; feature extraction; machine learning; data extraction; pathologic response; response evaluation criteria in solid tumors; radiologists; capecitabine plus oxaliplatin; colorectal liver metastasis; humans; prognosis; human; male; female; article; x-ray computed tomography; radiomics; performance indicator
Journal Title:	Annals of Surgical Oncology
Volume:	31
Issue:	13
ISSN:	1068-9265
Publisher:	Springer
Date Published:	2024-12-01
Start Page:	9196
End Page:	9204
Language:	English
DOI:	10.1245/s10434-024-15373-y
PUBMED:	39369120
PROVIDER:	scopus
PMCID:	PMC11936377
DOI/URL:	https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205713551&doi=10.1245%2fs10434-024-15373-y&partnerID=40&md5=fe18799c34a61ff007f9627334c7f8b1
Notes:	Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- MSK corresponding author is Michael D'Angelica -- Source: Scopus