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.
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.
Background
To investigate the association between computed tomography (CT)-detected extramural venous invasion (EMVI)-related genes and immunotherapy resistance and immune escape in patients with gastric cancer (GC).
Methods
Thirteen patients with pathologically proven locally advanced GC who had undergone preoperative abdominal contrast-enhanced CT and radical resection surgery were included in this study. Transcriptome sequencing was multidetector performed on the cancerous tissue obtained during surgery, and EMVI-related genes (P value for association < 0.001) were selected. A single-sample gene set enrichment analysis algorithm was also used to divide all GC samples (n = 377) in The Cancer Genome Atlas (TCGA) database into high and low EMVI-immune related groups based on immune-related differential genes. Cluster analysis was used to classify EMVI-immune-related genotypes, and survival among patients was validated in TCGA and Gene Expression Omnibus (GEO) cohorts. The EMVI scores were calculated using principal component analysis (PCA), and GC samples were divided into high and low EMVI score groups. Microsatellite instability (MSI) status, tumor mutation burden (TMB), response rate to immune checkpoint inhibitors (ICIs), immune escape were compared between the high and low EMVI score groups. Hub gene of the model in pan-cancer analysis was also performed.
Results
There were 17 EMVI-immune-related genes used for cluster analysis. PCA identified 8 genes (PCH17, SEMA6B, GJA4, CD34, ACVRL1, SOX17, CXCL12, DYSF) that were used to calculate EMVI scores. High EMVI score groups had lower MSI, TMB and response rate of ICIs, status but higher immune escape status. Among the 8 genes used for EMVI scores, CXCL12 and SOX17 were at the core of the protein–protein interaction (PPI) network and had a higher priority in pan-cancer analysis. Immunohistochemical analysis showed that the expression of CXCL12 and SOX17 was significantly higher in CT-detected EMVI-positive samples than in EMVI-negative samples (P < 0.0001).
Conclusion
A CT-detected EMVI gene signature could be a potential negative biomarker for ICIs treatment, as the signature is negatively correlated with TMB, and MSI, resulting in poorer prognosis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.