CholecTriplet2021: A benchmark challenge for surgical action triplet recognition.

Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of combination delivers more comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. The challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and the assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. A total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms from the competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery.

Evaluating the Relationship Between Metabolic Syndrome and Liver Biopsy-Proven Non-Alcoholic Steatohepatitis in China: A Multicenter Cross-Sectional Study Design.

INTRODUCTION: Non-alcoholic steatohepatitis (NASH) is a serious form of non-alcoholic fatty liver disease (NAFLD) that can progress to advanced fibrosis, cirrhosis, and hepatocellular carcinoma. Differentiating between non-alcoholic fatty liver (NAFL) and NASH/advanced fibrosis is an important step in the management of NAFLD. Metabolic syndrome (MS) and its components are important risk factors for NAFLD, and NASH is thought to be the hepatic injury of MS. The prevalence of NASH among NAFLD patients with MS is thought to be high. In China, NAFLD is a relatively new public health concern, and the current prevalence of NASH among Chinese liver biopsy-proven NAFLD patients with and without MS is not known. METHODS: This multicenter, cross-sectional study will investigate the prevalence of NASH in approximately 480 Chinese NAFLD patients. Patients will be eligible for enrollment if they have biopsy-proven NAFLD and if their liver biopsies are available for rereading. For our analysis, patients will be stratified according to the presence/absence of MS, and the prevalence of NASH in the subgroups will be compared. Other possible tests that could indicate a risk of NASH, including transient elastography, ultrasonography, cytokeratin-18, liver function tests, and others, will be studied in an effort to derive a practical, noninvasive predictive model for NASH. DISCUSSION: Patients with NAFL who have MS may also have a very high risk of developing NASH. The present study will inform about the risk of NASH in Chinese liver biopsy-proven NAFLD patients with and without MS. TRIAL REGISTRATION: This study registered at http://www.chictr.org.cn (registration number: ChiCTR-OOC-16007902). FUNDING: Sanofi (China) Investment Co., Ltd.