Developing an MRI-based radiomics model to effectively and accurately predict the predominant histopathologic growth patterns (HGPs) of colorectal liver metastases (CRLMs). Materials and Methods: In this study, 182 resected and histopathological proven CRLMs of chemotherapy-naive patients from two institutions, including 123 replacement CRLMs and 59 desmoplastic CRLMs, were retrospectively analyzed. Radiomics analysis was performed on two regions of interest (ROI), the tumor zone and the tumor-liver interface (TLI) zone. Decision tree (DT) algorithm was used for radiomics modeling on each MR sequence, and fused radiomics model was constructed by combining the radiomics signature of each sequence. The clinical and combination models were developed through multivariate logistic regression method. The performance of the developed models was assessed by receiver operating characteristic (ROC) curves with indicators of area under curve (AUC), accuracy, sensitivity, and specificity. A nomogram was constructed to evaluate the discrimination, calibration, and usefulness. Results: The fused radiomics tumor and radiomics TLI models showed better performance than any single sequence and clinical model. In addition, the radiomics TLI model exhibited better performance than radiomics tumor model (AUC of 0.912 vs. 0.879) in internal validation cohort. The combination model showed good discrimination, and the AUC of nomogram was 0.971, 0.909, and 0.905 in the training, internal validation, and external validation cohorts, respectively. Han et al. Radiomics in CRLM's HGP Prediction Conclusion: MRI-based radiomics method has high potential in predicting the predominant HGPs of CRLM. Preoperative non-invasive identification of predominant HGPs could further explore the ability of HGPs as a potential biomarker for clinical treatment strategy, reflecting different biological pathways.

Purpose The purpose of this study was to develop and validate a deep learning (DL)‐based radiomics model to predict the response to chemotherapy in colorectal liver metastases (CRLM). Methods In this retrospective study, we enrolled 192 patients diagnosed with CRLM who received first‐line chemotherapy and were followed by response assessment. Tumor response was identified according to the Response Evaluation Criteria in Solid Tumors (RECIST). Contrast‐enhanced multidetector computed tomography (MDCT) images were fed as inputs of the ResNet10‐based DL radiomics model, and the possibility of response was predicted as the output. The final combined DL radiomics model was constructed by integrating the response‐related clinical factors and the developed DL radiomics signature. A time‐independent validation cohort (n = 48) was extracted from the 192 patients to evaluate the DL model with area under the receiver operating characteristic curve (AUC), specificity, and sensitivity. Meanwhile, a traditional radiomics model was constructed using least absolute shrinkage and selection operator (lasso) as comparisons with the DL‐based model. Results According to RECIST criteria, 131 patients were identified as responders with complete response, partial response, and stable disease, while 61 patients were nonresponders with progression disease. The selected predictive clinical factor turned out to be the carcinoembryonic antigen (CEA) level with AUC of 0.489 (95% confidence interval [CI], 0.380–0.599) and 0.558 (95% CI, 0.374–0.741) in the training and validation cohorts, respectively. The DL‐based model provided better performance than the traditional classifier‐based radiomics model with significantly higher AUC (training: 0.903 [95% CI, 0.851–0.955] vs 0.745 [95% CI, 0.659–0.831]; validation: 0.820 [95% CI, 0.681–0.959] vs 0.598 [95% CI, 0.422–0.774]). The combination of DL‐based model with the CEA level provided slightly increased performance with AUC of 0.935 [95% CI, 0.897–0.973] in the training cohort and 0.830 [95% CI, 0.688‐0.973] in the validation cohort. Conclusions The developed DL‐based radiomics model could improve the efficiency to predict the response to chemotherapy in CRLM, which may assist in subsequent personalized treatment decision‐making in CRLM management.

No abstract

No abstract

This is an open access article under the terms of the Creat ive Commo ns Attri bution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.