Differential Diagnosis and Molecular Stratification of Gastrointestinal Stromal Tumors on CT Images Using a Radiomics Approach.

Treatment planning of gastrointestinal stromal tumors (GISTs) includes distinguishing GISTs from other intra-abdominal tumors and GISTs' molecular analysis. The aim of this study was to evaluate radiomics for distinguishing GISTs from other intra-abdominal tumors, and in GISTs, predict the c-KIT, PDGFRA, BRAF mutational status, and mitotic index (MI). Patients diagnosed at the Erasmus MC between 2004 and 2017, with GIST or non-GIST intra-abdominal tumors and a contrast-enhanced venous-phase CT, were retrospectively included. Tumors were segmented, from which 564 image features were extracted. Prediction models were constructed using a combination of machine learning approaches. The evaluation was performed in a 100 × random-split cross-validation. Model performance was compared to that of three radiologists. One hundred twenty-five GISTs and 122 non-GISTs were included. The GIST vs. non-GIST radiomics model had a mean area under the curve (AUC) of 0.77. Three radiologists had an AUC of 0.69, 0.76, and 0.84, respectively. The radiomics model had an AUC of 0.52 for c-KIT, 0.56 for c-KIT exon 11, and 0.52 for the MI. The numbers of PDGFRA, BRAF, and other c-KIT mutations were too low for analysis. Our radiomics model was able to distinguish GISTs from non-GISTs with a performance similar to three radiologists, but less observer dependent. Therefore, it may aid in the early diagnosis of GIST, facilitating rapid referral to specialized treatment centers. As the model was not able to predict any genetic or molecular features, it cannot aid in treatment planning yet.

Distinguishing pure histopathological growth patterns of colorectal liver metastases on CT using deep learning and radiomics: a pilot study.

Histopathological growth patterns (HGPs) are independent prognosticators for colorectal liver metastases (CRLM). Currently, HGPs are determined postoperatively. In this study, we evaluated radiomics for preoperative prediction of HGPs on computed tomography (CT), and its robustness to segmentation and acquisition variations. Patients with pure HGPs [i.e. 100% desmoplastic (dHGP) or 100% replacement (rHGP)] and a CT-scan who were surgically treated at the Erasmus MC between 2003-2015 were included retrospectively. Each lesion was segmented by three clinicians and a convolutional neural network (CNN). A prediction model was created using 564 radiomics features and a combination of machine learning approaches by training on the clinician's and testing on the unseen CNN segmentations. The intra-class correlation coefficient (ICC) was used to select features robust to segmentation variations; ComBat was used to harmonize for acquisition variations. Evaluation was performed through a 100 × random-split cross-validation. The study included 93 CRLM in 76 patients (48% dHGP; 52% rHGP). Despite substantial differences between the segmentations of the three clinicians and the CNN, the radiomics model had a mean area under the curve of 0.69. ICC-based feature selection or ComBat yielded no improvement. Concluding, the combination of a CNN for segmentation and radiomics for classification has potential for automatically distinguishing dHGPs from rHGP, and is robust to segmentation and acquisition variations. Pending further optimization, including extension to mixed HGPs, our model may serve as a preoperative addition to postoperative HGP assessment, enabling further exploitation of HGPs as a biomarker.

The Prognostic Role of ß-Catenin Mutations in Desmoid-type Fibromatosis Undergoing Resection Only: A Meta-analysis of Individual Patient Data.

OBJECTIVE: This meta-analysis (PROSPERO CRD42018100653) uses individual patient data (IPD) to assess the association between recurrence and CTNNB1 mutation status in surgically treated adult desmoid-type fibromatosis (DTF) patients. SUMMARY OF BACKGROUND DATA: The majority of sporadic DTF tumors harbor a CTNNB1 (ß-catenin) mutation: T41A, S45F, and S45P or are wild-type (WT). Results are conflicting regarding the recurrence risk after surgery for these mutation types. METHODS: A systematic literature search was performed on June 6th, 2018. IPD from eligible studies was used to analyze differences in recurrence according to CTNNB1 mutation status using Cox proportional hazards analysis. Predictive factors included: sex, age, mutation type, tumor site, tumor size, resection margin status, and cohort. The PRISMA-IPD guideline was used. RESULTS: Seven studies, describing retrospective cohorts were included and the IPD of 329 patients were used of whom 154 (46.8%) had a T41A mutation, 66 (20.1%) a S45F mutation, and 24 (7.3%) a S45P mutation, whereas 85 (25.8%) patients had a WT CTNNB1. Eighty-three patients (25.2%) experienced recurrence. Multivariable analysis, adjusting for sex, age, and tumor site yielded a P-value of 0.011 for CTNNB1 mutation. Additional adjustment for tumor size yielded a P-value of 0.082 with hazard ratio's of 0.83 [95% confidence interval (CI) 0.48-1.42), 0.37 (95% CI 0.12-1.14), and 0.44 (95% CI 0.21-0.92) for T41A, S45P and WT DTF tumors compared to S45F DTF tumors. The effect modification between tumor size and mutation type suggests that tumor size is an important mediator for recurrence. CONCLUSIONS: Primary sporadic DTFs harboring a CTNNB1 S45F mutation have a higher risk of recurrence after surgery compared to T41A, S45P, and WT DTF, but this association seems to be mediated by tumor size.