An Open Medical Platform to Share Source Code and Various Pre-Trained Weights for Models to Use in Deep Learning Research.

Deep learning-based applications have great potential to enhance the quality of medical services. The power of deep learning depends on open databases and innovation. Radiologists can act as important mediators between deep learning and medicine by simultaneously playing pioneering and gatekeeping roles. The application of deep learning technology in medicine is sometimes restricted by ethical or legal issues, including patient privacy and confidentiality, data ownership, and limitations in patient agreement. In this paper, we present an open platform, MI2RLNet, for sharing source code and various pre-trained weights for models to use in downstream tasks, including education, application, and transfer learning, to encourage deep learning research in radiology. In addition, we describe how to use this open platform in the GitHub environment. Our source code and models may contribute to further deep learning research in radiology, which may facilitate applications in medicine and healthcare, especially in medical imaging, in the near future. All code is available at https://github.com/mi2rl/MI2RLNet.

Video recognition of simple mastoidectomy using convolutional neural networks: Detection and segmentation of surgical tools and anatomical regions.

A simple mastoidectomy is used to remove inflammation of the mastoid cavity and to create a route to the skull base and middle ear. However, due to the complexity and difficulty of the simple mastoidectomy, implementing robot vision for assisted surgery is a challenge. To overcome this issue using a convolutional neural network architecture in a surgical environment, each surgical instrument and anatomical region must be distinguishable in real time. To meet this condition, we used the latest instance segmentation architecture, YOLACT. In this study, a data set comprising 5,319 extracted frames from 70 simple mastoidectomy surgery videos were used. Six surgical tools and five anatomic regions were identified for the training. The YOLACT-based model in the surgical environment was trained and evaluated for real-time object detection and semantic segmentation. Detection accuracies of surgical tools and anatomic regions were 91.2% and 56.5% in mean average precision, respectively. Additionally, the dice similarity coefficient metric for segmentation of the five anatomic regions was 48.2%. The mean frames per second of this model was 32.3, which is sufficient for real-time robotic applications.

Rho-kinase/AMPK axis regulates hepatic lipogenesis during overnutrition.

Obesity is a major risk factor for developing nonalcoholic fatty liver disease (NAFLD). NAFLD is the most common form of chronic liver disease and is closely associated with insulin resistance, ultimately leading to cirrhosis and hepatocellular carcinoma. However, knowledge of the intracellular regulators of obesity-linked fatty liver disease remains incomplete. Here we showed that hepatic Rho-kinase 1 (ROCK1) drives obesity-induced steatosis in mice through stimulation of de novo lipogenesis. Mice lacking ROCK1 in the liver were resistant to diet-induced obesity owing to increased energy expenditure and thermogenic gene expression. Constitutive expression of hepatic ROCK1 was sufficient to promote adiposity, insulin resistance, and hepatic lipid accumulation in mice fed a high-fat diet. Correspondingly, liver-specific ROCK1 deletion prevented the development of severe hepatic steatosis and reduced hyperglycemia in obese diabetic (ob/ob) mice. Of pathophysiological significance, hepatic ROCK1 was markedly upregulated in humans with fatty liver disease and correlated with risk factors clustering around NAFLD and insulin resistance. Mechanistically, we found that hepatic ROCK1 suppresses AMPK activity and a ROCK1/AMPK pathway is necessary to mediate cannabinoid-induced lipogenesis in the liver. Furthermore, treatment with metformin, the most widely used antidiabetes drug, reduced hepatic lipid accumulation by inactivating ROCK1, resulting in activation of AMPK downstream signaling. Taken together, our findings establish a ROCK1/AMPK signaling axis that regulates de novo lipogenesis, providing a unique target for treating obesity-related metabolic disorders such as NAFLD.