Silva, Alvin C.

Abstract Purpose: With increasing incidence of renal mass, it is important to make a pretreatment differentiation between benign renal mass and malignant tumor. We aimed to develop a deep learning model that distinguishes benign renal tumors from renal cell carcinoma (RCC) by applying a residual convolutional neural network (ResNet) on routine MR imaging. Experimental Design: Preoperative MR images (T2-weighted and T1-postcontrast sequences) of 1,162 renal lesions definitely diagnosed on pathology or imaging in a multicenter cohort were divided into training, validation, and test sets (70:20:10 split). An ensemble model based on ResNet was built combining clinical variables and T1C and T2WI MR images using a bagging classifier to predict renal tumor pathology. Final model performance was compared with expert interpretation and the most optimized radiomics model. Results: Among the 1,162 renal lesions, 655 were malignant and 507 were benign. Compared with a baseline zero rule algorithm, the ensemble deep learning model had a statistically significant higher test accuracy (0.70 vs. 0.56, P = 0.004). Compared with all experts averaged, the ensemble deep learning model had higher test accuracy (0.70 vs. 0.60, P = 0.053), sensitivity (0.92 vs. 0.80, P = 0.017), and specificity (0.41 vs. 0.35, P = 0.450). Compared with the radiomics model, the ensemble deep learning model had higher test accuracy (0.70 vs. 0.62, P = 0.081), sensitivity (0.92 vs. 0.79, P = 0.012), and specificity (0.41 vs. 0.39, P = 0.770). Conclusions: Deep learning can noninvasively distinguish benign renal tumors from RCC using conventional MR imaging in a multi-institutional dataset with good accuracy, sensitivity, and specificity comparable with experts and radiomics.

Spontaneous portosystemic shunts (SPSSs) have been associated with worse clinical outcomes in the pre–liver transplantation (LT) setting, but little is known about their post‐LT impacts. Our aim was to compare LT candidates with and without SPSSs and assess the impact of SPSSs on patient mortality and graft survival in the post‐LT setting. Patients 18 years or older with abdominal imaging done prior to LT were included. Exclusion criteria were the presence of pre‐LT surgical shunts, LT indications other than cirrhosis, and combined solid organ transplantations. SPSSs were classified as absent, small, or large according to their maximum diameter (8 mm). Multiple variables that could influence the post‐LT course were extracted for analysis. Patient and graft survival were estimated using the Kaplan‐Meier method and were compared between groups using a log‐rank test. The project received institutional review board approval. We extracted data from 326 patients. After comparing patients without SPSS or with small or large SPSSs, no statistical difference was found for overall patient survival: no SPSS (n = 8/63), reference; small SPSS (n = 18/150), hazard ratio (HR), 1.05 (95% confidence interval [CI], 0.45‐2.46); and large SPSS (n = 6/113), HR, 0.60 (95% CI, 0.20‐1.78); P = 0.20. Also, no difference was found for graft survival: no SPSS (n = 11/63), reference; small SPSS (n = 21/150), HR, 0.80 (95% CI, 0.38‐1.70); large SPSS (n = 11/113), HR, 0.59 (95% CI, 0.25‐1.40); P = 0.48. Similarly, no statistical significance was found for these variables when comparing if the graft used was procured from a donation after circulatory death donor versus a donation after brain death donor. In conclusion, the previously described association between SPSSs and worse clinical outcomes in pre‐LT patients seems not to persist once patients undergo LT. This study suggests that no steps to correct SPSS intraoperatively are necessary.

e15626 Background: FGFR2 fusions are found in 10-15% of intrahepatic cholangiocarcinomas. Individuals with FGFR2 fusions have a better prognosis and more indolent natural history. More recently FGFR2 fusions have been described as a predictive marker for tyrosine kinase inhibitors targeting the FGFR2 pathway. Texture analysis from CT imaging has been used in the past to estimate degree of fibrosis and angiogenesis in various tumors types; however, texture analysis has not been used in the past to detect FGFR2 rearrangements. Methods: This is a retrospective study of 33 patients with intrahepatic cholangiocarcinoma who were previously tested for FGFR2 fusions with either a FISH break apart assay or with clinically available next generation sequencing assays. All patients had a contrast enhanced CT performed. To address physiological and pathological variations, matched-size regions of interest (ROIs) over areas of non-necrotic tumor and unaffected liver during the portal venous phase were drawn. The paired ROIs for each patient were then processed via an imaging analytic pipeline for (1) ROI normalization, (2) texture panel creation, and (3) machine learning predictive model development. Results: Fifteen patients with FGFR2 fusions and 18 patients without FGFR2 fusions were included in the study. Using the developed predictive model, accurate FGFR2 fusion classification in 90% of cases was achieved (sensitivity = 87%, specificity = 94%). Conclusions: Utilizing advanced analytics with machine learning techniques, multi-textural data obtained from conventional CT images has the capability to detect genetic aberrations in intrahepatic cholangiocarcinoma, including FGFR2 gene fusions. Radiogenomic evaluation has several attractive benefits including the cost effective and expeditious detection of actionable mutations such as FGFR2 fusions as well as avoidance of invasive procedures such as percutaneous core biopsies. [Table: see text]

AbstractSarcopenia, or loss of skeletal muscle mass, is associated with increased mortality and morbidity in liver transplant (LT) candidates. Six‐minute walk distance (6MWD) and health‐related quality of life (HRQOL) as assessed by short form 36 scores (SF‐36) also impact clinical outcomes in these patients. This study explored the relationship between the sarcopenia, 6MWD, and HRQOL in LT candidates. Sarcopenia was evaluated based on skeletal muscle mass index (SMI) quantified from abdominal computed tomography. Patients were followed until death, removal from the wait list or the end of the study period. Two hundred and thirteen patients listed for LT were included. The mean SMI, 6MWD and mean gait speed were 54.3 ± 9.7, 370.5 m and 1 m/s, respectively. Sarcopenia was noted in 22.2% of LT candidates. There was no correlation between sarcopenia, 6MWD, and SF‐36 scores. The 6MWD, but not sarcopenia, was an independent predictor of mortality (hazard ratio = 2.1 [0.9–4.7]). In summary, sarcopenia did not emerge as a significant predictor of waitlist mortality and also failed to correlate with either functional capacity or HRQOL in LT candidates. In patients with ESLD awaiting LT, 6MWD appears to be a more useful prognostic indicator than the presence of sarcopenia.