Background: Computer-aided methods have been widely applied to diagnose lesions detected on breast MRI, but fullyautomatic diagnosis using deep learning is rarely reported. Purpose: To evaluate the diagnostic accuracy of mass lesions using region of interest (ROI)-based, radiomics and deeplearning methods, by taking peritumor tissues into consideration. Study Type: Retrospective. Population: In all, 133 patients with histologically confirmed 91 malignant and 62 benign mass lesions for training (74 patients with 48 malignant and 26 benign lesions for testing). Field Strength/Sequence: 3T, using the volume imaging for breast assessment (VIBRANT) dynamic contrast-enhanced (DCE) sequence. Assessment: 3D tumor segmentation was done automatically by using fuzzy-C-means algorithm with connectedcomponent labeling. A total of 99 texture and histogram parameters were calculated for each case, and 15 were selected using random forest to build a radiomics model. Deep learning was implemented using ResNet50, evaluated with 10-fold crossvalidation. The tumor alone, smallest bounding box, and 1.2, 1.5, 2.0 times enlarged boxes were used as inputs. Statistical Tests: The malignancy probability was calculated using each model, and the threshold of 0.5 was used to make a diagnosis. Results: In the training dataset, the diagnostic accuracy was 76% using three ROI-based parameters, 84% using the radiomics model, and 86% using ROI + radiomics model. In deep learning using the per-slice basis, the area under the receiver operating characteristic (ROC) was comparable for tumor alone, smallest and 1.2 times box (AUC = 0.97-0.99), which were significantly higher than 1.5 and 2.0 times box (AUC = 0.86 and 0.71, respectively). For per-lesion diagnosis, the highest accuracy of 91% was achieved when using the smallest bounding box, and that decreased to 84% for tumor alone and 1.2 times box, and further to 73% for 1.5 times box and 69% for 2.0 times box. In the independent testing dataset, the perlesion diagnostic accuracy was also the highest when using the smallest bounding box, 89%. Data Conclusion: Deep learning using ResNet50 achieved a high diagnostic accuracy. Using the smallest bounding box containing proximal peritumor tissue as input had higher accuracy compared to using tumor alone or larger boxes. Level of Evidence: 3 Technical Efficacy: Stage 2

Summary Background Interventional treatment for overt hepatic encephalopathy (OHE), includes non‐absorbable disaccharides, neomycin, rifaximin, L‐ornithine‐L‐aspartate and branched chain amino acids (BCAA). However, the optimum regimen remains inconclusive. Aim To compare interventions in terms of patients’ adverse events and major clinical outcomes. Methods Literature search of PubMed, Embase, Scopus, and Cochrane Library studies published up to July 31 2014. RCTs of above interventions in OHE patients were included. Network meta‐analysis combined direct and indirect evidence to estimate odds ratios (ORs) and mean difference (MD) between treatments and the probabilities of ranking for treatment based on clinical outcomes. Results Twenty eligible RCTs were included. When compared with observation, only L‐ornithine‐L‐aspartate (OR 3.71, P < 0.001) and BCAA (OR 3.37, P < 0.001) improved clinical efficacy significantly. However, when L‐ornithine‐L‐aspartate was compared with BCAA, non‐absorbable disaccharides and neomycin, there was a trend suggesting that L‐ornithine‐L‐aspartate may be the most effective intervention with respect to clinical improvement (OR 1.10), rifaximin (OR 1.31), non‐absorbable disaccharides (OR 2.75), neomycin (OR 2.22). In addition, L‐ornithine‐L‐aspartate (MD −20.18, 95% CI −40.12 to −0.27) provided a significant reduction in blood ammonia concentration compared with observation. Neomycin appeared to be associated with more adverse events in comparison with non‐absorbable disaccharides (OR 10.15), rifaximin (OR 17.31), L‐ornithine‐L‐aspartate (OR 3.16) or BCAA (OR 7.69). Conclusions L‐ornithine‐L‐aspartate treatment may show a trend in superiority for clinical efficacy among standard interventions for OHE. Rifaximin shows the greatest reduction in blood ammonia concentration, and treatment with neomycin demonstrates a higher probability in causing adverse effects among the five compared interventions.

Objectives: To apply deep learning algorithms using a conventional convolutional neural network (CNN) and a recurrent CNN to differentiate three breast cancer molecular subtypes on MRI.Methods: A total of 244 patients were analyzed, 99 in Training Dataset scanned at 1.5T, 83 in Testing-1 and 62 in Testing-2 scanned at 3T. Patients were classified into 3 subtypes based on hormonal receptor (HR) and HER2 receptor: (HR+/HER2−), HER2+ and triple negative (TN). Only images acquired in the DCE sequence were used in the analysis. The smallest bounding box covering tumor ROI was used as the input for deep learning to develop the model in the Training dataset, by using a conventional CNN and the convolutional long short term memory (CLSTM). Then, transfer learning was applied to re-tune the model using Testing-1(2) and evaluated in Testing-2(1). Results:In the Training dataset, the mean accuracy evaluated using 10-fold cross-validation was higher by using CLSTM (0.91) than CNN (0.79). When the developed model was applied to the independent Testing datasets, the accuracy was 0.4-0.5. With transfer learning by re-tuning parameters in Testing-1, the mean accuracy reached 0.91 by CNN and 0.83 by CLSTM, and improved accuracy in Testing-2 from 0.47 to 0.78 by CNN and from 0.39 to 0.74 by CLSTM. Overall, transfer learning could improve the classification accuracy by greater than 30%.

AimsRecovery after peripheral nerve injury (PNI) is often difficult, and there is no optimal treatment. Schwann cells (SCs) are important for peripheral nerve regeneration, so SC‐targeting treatments have gained importance. Adipose‐derived stem cells (ADSCs) and their exosomes can promote peripheral nerve repair, but their interactions with SCs are unclear.MethodsPurified SCs from sciatic nerve injury sites were harvested, and apoptosis and proliferation of SCs at post‐PNI 24 hours were analyzed. The effects of coculture with ADSCs and different concentrations of ADSC‐derived exosomes (ADSC‐Exo) were studied through in vitro experiments by flow cytometry, CCK8 assay, immunofluorescence staining, and histological analysis. The expression of the apoptosis‐related genes Bcl‐2 and Bax was also analyzed by qRT‐PCR.ResultsADSC‐Exo reduced the apoptosis of SCs after PNI by upregulating the anti‐apoptotic Bcl‐2 mRNA expression and downregulating the pro‐apoptotic Bax mRNA expression. Further, it also improved the proliferation rate of SCs. This effect was confirmed by the morphological and histological findings in PNI model rats.ConclusionOur results present a novel exosome‐mediated mechanism for ADSC‐SC cross talk that reduces the apoptosis and promotes the proliferation of SCs and may have therapeutic potential in the future.