Impact of an AI-Based laparoscopic cholecystectomy coaching program on the surgical performance: a randomized controlled trial.

BACKGROUND: Laparoscopic cholecystectomy (LC) is the gold standard for treating symptomatic gallstones but carries inherent risks like bile duct injury (BDI). While critical view of safety (CVS) is advocated to mitigate BDI, its real-world adoption is limited. Additionally, significant variations in surgeon performance impede procedural standardization, highlighting the need for a feasible, innovative, and effective training approach. The aim of this study is to develop an Artificial Intelligence (AI)-assisted coaching program for LC to enhance surgical education and improve surgeon's performance. MATERIALS AND METHODS: We conducted a multi-center, randomized controlled trial from May 2022 to August 2023 to assess the impact of an AI-based coaching program, SmartCoach, on novice performing LC. Surgeons and patients meeting specific inclusion criteria were randomly assigned to either a coaching group with AI-enhanced feedback or a self-learning group. The primary outcome was assessed using the Laparoscopic Cholecystectomy Rating Form (LCRF), with secondary outcomes including surgical safety, efficiency, and adverse events. Statistical analyses were performed using SPSS, with significance set at P-value less than 0.05. RESULTS: Between May 2022 and August 2023, 22 surgeons were initially enrolled from 10 hospitals, with 18 completing the study. No demographic differences were noted between coaching and self-learning groups. In terms of surgical performance (LCRF scores), the coaching group showed significant improvement over time (31 to 40, P=0.008), outperforming the self-learning group by study end (40 vs 38, P=0.032). Significant improvements in CVS achievement were also noted in the coaching group (11% to 78%, P=0.021). Overall, the coaching program was well-received, outpacing traditional educational methods in both understanding and execution of CVS and participants in the intervention group expressed strongly satisfaction with the program. CONCLUSIONS: The AI-assisted surgical coaching program effectively improved surgical performance and safety for novice surgeons in LC procedures. The model holds significant promise for advancing surgical education.

Efficient Medical Image Segmentation Based on Knowledge Distillation.

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational complexity and massive storage, which is impractical in the real-world scenario. To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network. This architecture empowers the lightweight network to get a significant improvement on segmentation capability while retaining its runtime efficiency. We further devise a novel distillation module tailored for medical image segmentation to transfer semantic region information from teacher to student network. It forces the student network to mimic the extent of difference of representations calculated from different tissue regions. This module avoids the ambiguous boundary problem encountered when dealing with medical imaging but instead encodes the internal information of each semantic region for transferring. Benefited from our module, the lightweight network could receive an improvement of up to 32.6% in our experiment while maintaining its portability in the inference phase. The entire structure has been verified on two widely accepted public CT datasets LiTS17 and KiTS19. We demonstrate that a lightweight network distilled by our method has non-negligible value in the scenario which requires relatively high operating speed and low storage usage.

Development of deep learning-based detecting systems for pathologic myopia using retinal fundus images.

Globally, cases of myopia have reached epidemic levels. High myopia and pathological myopia (PM) are the leading cause of visual impairment and blindness in China, demanding a large volume of myopia screening tasks to control the rapid growing myopic prevalence. It is desirable to develop the automatically intelligent system to facilitate these time- and labor- consuming tasks. In this study, we designed a series of deep learning systems to detect PM and myopic macular lesions according to a recent international photographic classification system (META-PM) classification based on color fundus images. Notably, our systems recorded robust performance both in the test and external validation dataset. The performance was comparable to the general ophthalmologist and retinal specialist. With the extensive adoption of this technology, effective mass screening for myopic population will become feasible on a national scale.