Artificial intelligence for surgical safety during laparoscopic gastrectomy for gastric cancer: Indication of anatomical landmarks related to postoperative pancreatic fistula using deep learning.

BACKGROUND: Postoperative pancreatic fistula (POPF) is a critical complication of laparoscopic gastrectomy (LG). However, there are no widely recognized anatomical landmarks to prevent POPF during LG. This study aimed to identify anatomical landmarks related to POPF occurrence during LG for gastric cancer and to develop an artificial intelligence (AI) navigation system for indicating these landmarks. METHODS: Dimpling lines (DLs)-depressions formed between the pancreas and surrounding organs-were defined as anatomical landmarks related to POPF. The DLs for the mesogastrium, intestine, and transverse mesocolon were named DMP, DIP, and DTP, respectively. We included 50 LG cases to develop the AI system (45/50 were used for training and 5/50 for adjusting the hyperparameters of the employed system). Regarding the validation of the AI system, DLs were assessed by an external evaluation committee using a Likert scale, and the pancreas was assessed using the Dice coefficient, with 10 prospectively registered cases. RESULTS: Six expert surgeons confirmed the efficacy of DLs as anatomical landmarks related to POPF in LG. An AI system was developed using a semantic segmentation model that indicated DLs in real-time when this system was synchronized during surgery. Additionally, the distribution of scores for DMP was significantly higher than that of the other DLs (p < 0.001), indicating the relatively high accuracy of this landmark. In addition, the Dice coefficient of the pancreas was 0.70. CONCLUSIONS: The DLs may be used as anatomical landmarks related to POPF occurrence. The developed AI navigation system can help visualize the DLs in real-time during LG.

Development of a cross-artificial intelligence system for identifying intraoperative anatomical landmarks and surgical phases during laparoscopic cholecystectomy.

BACKGROUND: Attention to anatomical landmarks in the appropriate surgical phase is important to prevent bile duct injury (BDI) during laparoscopic cholecystectomy (LC). Therefore, we created a cross-AI system that works with two different AI algorithms simultaneously, landmark detection and phase recognition. We assessed whether landmark detection was activated in the appropriate phase by phase recognition during LC and the potential contribution of the cross-AI system in preventing BDI through a clinical feasibility study (J-SUMMIT-C-02). METHODS: A prototype was designed to display landmarks during the preparation phase and Calot's triangle dissection. A prospective clinical feasibility study using the cross-AI system was performed in 20 LC cases. The primary endpoint of this study was the appropriateness of the detection timing of landmarks, which was assessed by an external evaluation committee (EEC). The secondary endpoint was the correctness of landmark detection and the contribution of cross-AI in preventing BDI, which were assessed based on the annotation and 4-point rubric questionnaire. RESULTS: Cross-AI-detected landmarks in 92% of the phases where the EEC considered landmarks necessary. In the questionnaire, each landmark detected by AI had high accuracy, especially the landmarks of the common bile duct and cystic duct, which were assessed at 3.78 and 3.67, respectively. In addition, the contribution to preventing BDI was relatively high at 3.65. CONCLUSIONS: The cross-AI system provided landmark detection at appropriate situations. The surgeons who previewed the model suggested that the landmark information provided by the cross-AI system may be effective in preventing BDI. Therefore, it is suggested that our system could help prevent BDI in practice. Trial registration University Hospital Medical Information Network Research Center Clinical Trial Registration System (UMIN000045731).

Monoallelic BUB1B mutations and defective mitotic-spindle checkpoint in seven families with premature chromatid separation (PCS) syndrome.

Cancer-prone syndrome of premature chromatid separation (PCS syndrome) with mosaic variegated aneuploidy (MVA) is a rare autosomal recessive disorder characterized by growth retardation, microcephaly, childhood cancer, premature chromatid separation of all chromosomes, and mosaicism for various trisomies and monosomies. Biallelic BUB1B mutations were recently reported in five of eight families with MVA syndrome (probably identical to the PCS syndrome). We here describe molecular analysis of BUB1B (encoding BubR1) in seven Japanese families with the PCS syndrome. Monoallelic BUB1B mutations were found in all seven families studied: a single-base deletion (1833delT) in four families; and a splice site mutation, a nonsense mutation, and a missense mutation in one family each. Transcripts derived from the patients with the 1833delT mutation and the splice site mutation were significantly reduced, probably due to nonsense-mediated mRNA decay. No mutation was found in the second alleles in the seven families studied, but RT-PCR of BUB1B and Western blot analysis of BubR1 indicated a modest decrease of their transcripts. BubR1 in the cells from two patients showed both reduced protein expression and diminished kinetochore localization. Their expression level of p55cdc, a specific activator of anaphase-promoting complex, was normal but its kinetochore association was abolished. Microcell-mediated transfer of chromosome 15 (containing BUB1B) into the cells restored normal BubR1 levels, kinetochore localization of p55cdc, and the normal responses to colcemid treatment. These findings indicate the involvement of BubR1 in p55cdc-mediated mitotic checkpoint signaling, and suggest that >50% decrease in expression (or activity) of BubR1 is involved in the PCS syndrome.

NBS1 localizes to gamma-H2AX foci through interaction with the FHA/BRCT domain.

DNA double-strand breaks represent the most potentially serious damage to a genome; hence, many repair proteins are recruited to nuclear damage sites by as yet poorly characterized sensor mechanisms. Here, we show that NBS1, the gene product defective in Nijmegen breakage syndrome (NBS), physically interacts with histone, rather than damaged DNA, by direct binding to gamma-H2AX. We also demonstrate that NBS1 binding can occur in the absence of interaction with hMRE11 or BRCA1. Furthermore, this NBS1 physical interaction was reduced when anti-gamma-H2AX antibody was introduced into normal cells and was also delayed in AT cells, which lack the kinase activity for phosphorylation of H2AX. NBS1 has no DNA binding region but carries a combination of the fork-head associated (FHA) and the BRCA1 C-terminal domains (BRCT). We show that the FHA/BRCT domain of NBS1 is essential for this physical interaction, since NBS1 lacking this domain failed to bind to gamma-H2AX in cells, and a recombinant FHA/BRCT domain alone can bind to recombinant gamma-H2AX. Consequently, the FHA/BRCT domain is likely to have a crucial role for both binding to histone and for relocalization of hMRE11/hRAD50 nuclease complex to the vicinity of DNA damage.