Independent validation of CT radiomics models in colorectal liver metastases: predicting local tumour progression after ablation.

OBJECTIVES: Independent internal and external validation of three previously published CT-based radiomics models to predict local tumor progression (LTP) after thermal ablation of colorectal liver metastases (CRLM). MATERIALS AND METHODS: Patients with CRLM treated with thermal ablation were collected from two institutions to collect a new independent internal and external validation cohort. Ablation zones (AZ) were delineated on portal venous phase CT 2-8 weeks post-ablation. Radiomics features were extracted from the AZ and a 10 mm peri-ablational rim (PAR) of liver parenchyma around the AZ. Three previously published prediction models (clinical, radiomics, combined) were tested without retraining. LTP was defined as new tumor foci appearing next to the AZ up to 24 months post-ablation. RESULTS: The internal cohort included 39 patients with 68 CRLM and the external cohort 52 patients with 78 CRLM. 34/146 CRLM developed LTP after a median follow-up of 24 months (range 5-139). The median time to LTP was 8 months (range 2-22). The combined clinical-radiomics model yielded a c-statistic of 0.47 (95%CI 0.30-0.64) in the internal cohort and 0.50 (95%CI 0.38-0.62) in the external cohort, compared to 0.78 (95%CI 0.65-0.87) in the previously published original cohort. The radiomics model yielded c-statistics of 0.46 (95%CI 0.29-0.63) and 0.39 (95%CI 0.28-0.52), and the clinical model 0.51 (95%CI 0.34-0.68) and 0.51 (95%CI 0.39-0.63) in the internal and external cohort, respectively. CONCLUSION: The previously published results for prediction of LTP after thermal ablation of CRLM using clinical and radiomics models were not reproducible in independent internal and external validation. CLINICAL RELEVANCE STATEMENT: Local tumour progression after thermal ablation of CRLM cannot yet be predicted with the use of CT radiomics of the ablation zone and peri-ablational rim. These results underline the importance of validation of radiomics results to test for reproducibility in independent cohorts. KEY POINTS: • Previous research suggests CT radiomics models have the potential to predict local tumour progression after thermal ablation in colorectal liver metastases, but independent validation is lacking. • In internal and external validation, the previously published models were not able to predict local tumour progression after ablation. • Radiomics prediction models should be investigated in independent validation cohorts to check for reproducibility.

Deep infiltrating endometriosis of the bowel: MR imaging as a method to predict muscular invasion.

PURPOSE: To evaluate magnetic resonance (MR) imaging morphologic- and signal intensity abnormalities of deep infiltrating endometriosis (DIE) of the bowel wall and to assess its value in predicting depth and extent of bowel wall infiltration. MATERIALS AND METHODS: This single-center study was performed in a tertiary referral center for endometriosis. All patients (n = 28) who underwent segmental bowel resection (2004-2010) were retrospectively studied. MR images were analyzed by two experienced readers independently (number of lesions, location, size, signal intensity, and depth of bowel wall infiltration) and this was correlated with histopathology. RESULTS: The sensitivity, specificity, positive and negative predictive values, and accuracy for diagnosis of endometriosis infiltrating the muscular layer of the bowel were 100%, 75%, 96%, 100%, and 96%, respectively. The inter-rater agreement was 0.84. "Fan shaped" configurations with hypointensity on T2- and T1-weighted imaging were characteristic for thickening of indigenous smooth muscle and smooth muscle hyperplasia at histopathology, as a consequence of infiltration by endometriosis. Thickening of the (sub)mucosa corresponded to edema with or without infiltration of endometriosis. CONCLUSION: MR imaging at 1.5 Tesla is useful to predict muscular infiltration of the bowel in endometriosis, whereas it is of limited value in diagnosis of (sub)mucosal infiltration.

Appearance of abdominal wall endometriosis on MR imaging.

OBJECTIVE: Abdominal wall endometriosis (AWE) is defined as endometrial tissue that is superficial to the peritoneum. AWE is often difficult to diagnose, mimicking a broad spectrum of diseases. The aim of this study was to describe the appearance of AWE on magnetic resonance (MR) imaging. METHODS: We present ten patients with AWE (12 lesions) in which MR imaging was used for diagnosis. MR imaging included T2-weighted imaging and T1-weighted imaging with fat suppression. To assess the value of diffusion-weighted imaging (DWI) in endometriosis, four patients underwent additional DWI. The apparent diffusion coefficient (ADC) was calculated using b values of 50, 400, 800 and 1,200 s/mm(2). RESULTS: In most cases, the lesion was located ventral or dorsal to the aponeurosis of the rectus oblique muscle (n = 6) or in the rectus abdominis (n = 5). MR of AWE lesions showed isointense or slightly hyperintense signal compared with muscle on T2-weighted images and showed isointense or slightly hyperintense signal compared with muscle on T1-weighted images with foci of high signal intensity, indicative of haemorrhage. The mean ADC value of AWE was 0.93 x 10(-3)/mm(2)/s. CONCLUSION: MR imaging seems to be useful in determining the location and depth of infiltration in surrounding tissue preoperatively.