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.

A cross-study analysis of drug response prediction in cancer cell lines.

To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross-validation within a single study to assess model accuracy. While an essential first step, cross-validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly available cell line-based data sets: National Cancer Institute 60, ancer Therapeutics Response Portal (CTRP), Genomics of Drug Sensitivity in Cancer, Cancer Cell Line Encyclopedia and Genentech Cell Line Screening Initiative (gCSI). Based on observed experimental variability across studies, we explore estimates of prediction upper bounds. We report performance results of a variety of machine learning models, with a multitasking deep neural network achieving the best cross-study generalizability. By multiple measures, models trained on CTRP yield the most accurate predictions on the remaining testing data, and gCSI is the most predictable among the cell line data sets included in this study. With these experiments and further simulations on partial data, two lessons emerge: (1) differences in viability assays can limit model generalizability across studies and (2) drug diversity, more than tumor diversity, is crucial for raising model generalizability in preclinical screening.

Four distinct isolates of Helminthosporium victoriae virus 190S identified from Bipolaris maydis.

Helminthosporium victoriae virus 190S (HvV190S) is the type species of the genus Victorivirus under the family Totiviridae. To date, HvV190S has never been found in places outside of the USA and has Helminthosporium victoriae as its only know natural host fungus in the field. Here, we report the identification of 4 double-stranded RNA (dsRNA) viruses from Bipolaris maydis in Hubei province of China. Interestingly, the genomes of the 4 viruses show 81.2 %-85.5 % nucleotide sequence identities to HvV190S. Their capsid protein (CP) and RNA-dependent RNA polymerase (RdRp) share 95.5-97.9 % and 94.6-96.6 % amino acid sequence identities to corresponding proteins of HvV190S. Therefore, the 4 viruses, which show 81.8-87.3 % pairwise genome sequence identities, should be considered as distinct isolates of HvV190S. Our finding suggests that HvV190S is widely distributed in the world and may infect fungal species other than H. victoriae.