Prediction of histopathologic growth patterns of colorectal liver metastases with a noninvasive imaging method
Annals of Surgical Oncology Nov 23, 2019
Cheng J, Wei J, Tong T, et al. - In colorectal liver metastases (CRLMs), histopathologic growth patterns (HGPs) were investigated with a noninvasive radiomics model. Researchers performed a retrospective study including patients with chemotherapy-naive CRLMs who underwent abdominal contrast-enhanced multidetector CT (MDCT) followed by partial hepatectomy between January 2007 and January 2019 from two institutions. They reviewed hematoxylin- and eosin-stained histopathologic sections of CRLMs, with HGPs defined according to international consensus. Based on patients’ sources, division of lesions into training and validation datasets was done. To extract radiomic features, pre- and post-contrast (arterial and portal venous) phase MDCT images were used, with review focusing on the segmented tumor–liver interface zones of CRLMs. Assessment of a total of 126 CRLMs with histopathologic-demonstrated desmoplastic (n = 68) or replacement (n = 58) HGPs was done. In distinguishing between replacement and desmoplastic HGPs, the best predictive performance was achieved with the 3 phases fused radiomics signature. Good discrimination was noted with the clinical-radiomics combined model (C-indices of 0.941 and 0.833 in the training and external validation cohorts, respectively).
Go to Original
Only Doctors with an M3 India account can read this article. Sign up for free or login with your existing account.
4 reasons why Doctors love M3 India
-
Exclusive Write-ups & Webinars by KOLs
-
Daily Quiz by specialty
-
Paid Market Research Surveys
-
Case discussions, News & Journals' summaries