The Society of Surgical Oncology, inc.
The American Society of Breast Surgeons.
Annals of Surgical Oncology

Log in | Register

Prediction of Histopathologic Growth Patterns of Colorectal Liver Metastases with a Noninvasive Imaging Method

Jin Cheng MD, Jingwei Wei PhD, Tong Tong MD, Weiqi Sheng MD, Yinli Zhang MD, Yuqi Han PhD, Dongsheng Gu PhD, Nan Hong MD, Yingjiang Ye MD, Jie Tian PhD, Yi Wang MD
Hepatobiliary Tumors
Volume 26, Issue 13 / December , 2019



To predict histopathologic growth patterns (HGPs) in colorectal liver metastases (CRLMs) with a noninvasive radiomics model.


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 were included in this retrospective study. Hematoxylin- and eosin-stained histopathologic sections of CRLMs were reviewed, with HGPs defined according to international consensus. Lesions were divided into training and validation datasets based on patients’ sources. Radiomic features were extracted from pre- and post-contrast (arterial and portal venous) phase MDCT images, with review focusing on the segmented tumor–liver interface zones of CRLMs. Minimum redundancy maximum relevance and decision tree methods were used for radiomics modeling. Multivariable logistic regression analyses and ROC curves were used to assess the predictive performance of these models in predicting HGP types.


A total of 126 CRLMs with histopathologic-demonstrated desmoplastic (n = 68) or replacement (n = 58) HGPs were assessed. The radiomics signature consisted of 20 features of each phase selected. The 3 phases fused radiomics signature demonstrated the best predictive performance in distinguishing between replacement and desmoplastic HGPs (AUCs of 0.926 and 0.939 in the training and external validation cohorts, respectively). The clinical-radiomics combined model showed good discrimination (C-indices of 0.941 and 0.833 in the training and external validation cohorts, respectively).


A radiomics model derived from MDCT images may effectively predict the HGP of CRLMs, thus providing a basis for prognostic stratification and therapeutic decision-making.

Add a comment

0 comment(s)



Join the conversation!

Follow the journal on Twitter and Facebook

Help to expand the reach of the journal to support the research and practice needs of surgical oncologists and their patients.