arXiv subjects

Pietro Mascagni

Publications and source records attributed to Pietro Mascagni.

40 records · Page 3Linked to original sources

arXiv2021

Intraoperative time out to promote the implementation of the critical view of safety in laparoscopic cholecystectomy: a video-based assessment of 343 procedures

Background: The critical view of safety (CVS) is poorly adopted in surgical practices although it is ubiquitously recommended to prevent major bile duct injuries during laparoscopic cholecystectomy (LC). This study aims to determine whether performing a short intraoperative time out can improve CVS implementation. Methods: Surgeons performing LCs at an academic centre were invited to perform a 5-second long time out to verify CVS before dividing the cystic duct (5-second rule). The primary endpoint was to compare the rate of CVS achievement between LCs performed in the year before and the year after the 5-second rule. The CVS achievement rate was computed using the mediated video-based assessment of two independent reviewers. Clinical outcomes, LC workflows, and postoperative reports were also compared. Results: Three hundred and forty-three (171 before and 172 after the 5-second rule) of the 381 LCs performed over the 2-year study were analysed. After the implementation of the 5-second rule, the rate of CVS achievement increased significantly (15.9 vs 44.1 %; P<0.001) as well as the rate of bailout procedures (8.2 vs 15.7 %; P=0.045), the median time to clip the cystic duct or artery (17:26 [interquartile range: 16:46] vs 23:12 [17:16] minutes; P=0.007), and the rate of postoperative CVS reporting (1.3 vs 28.8 %; P<0.001). Morbidity was comparable (1.75 vs 2.33 % before and after the 5-second rule respectively; P=0.685). Conclusion: Performing a short intraoperative time out improves CVS implementation during LC. Systematic intraoperative cognitive aids should be studied to sustain the uptake of guidelines.

q-bio.TO↗

arXiv2021

Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures

Purpose: Automatic segmentation and classification of surgical activity is crucial for providing advanced support in computer-assisted interventions and autonomous functionalities in robot-assisted surgeries. Prior works have focused on recognizing either coarse activities, such as phases, or fine-grained activities, such as gestures. This work aims at jointly recognizing two complementary levels of granularity directly from videos, namely phases and steps. Method: We introduce two correlated surgical activities, phases and steps, for the laparoscopic gastric bypass procedure. We propose a Multi-task Multi-Stage Temporal Convolutional Network (MTMS-TCN) along with a multi-task Convolutional Neural Network (CNN) training setup to jointly predict the phases and steps and benefit from their complementarity to better evaluate the execution of the procedure. We evaluate the proposed method on a large video dataset consisting of 40 surgical procedures (Bypass40). Results: We present experimental results from several baseline models for both phase and step recognition on the Bypass40 dataset. The proposed MTMS-TCN method outperforms in both phase and step recognition by 1-2% in accuracy, precision and recall, compared to single-task methods. Furthermore, for step recognition, MTMS-TCN achieves a superior performance of 3-6% compared to LSTM based models in accuracy, precision, and recall. Conclusion: In this work, we present a multi-task multi-stage temporal convolutional network for surgical activity recognition, which shows improved results compared to single-task models on the Bypass40 gastric bypass dataset with multi-level annotations. The proposed method shows that the joint modeling of phases and steps is beneficial to improve the overall recognition of each type of activity.

cs.CV↗

arXiv2020

Artificial Intelligence in Surgery: Neural Networks and Deep Learning

Deep neural networks power most recent successes of artificial intelligence, spanning from self-driving cars to computer aided diagnosis in radiology and pathology. The high-stake data intensive process of surgery could highly benefit from such computational methods. However, surgeons and computer scientists should partner to develop and assess deep learning applications of value to patients and healthcare systems. This chapter and the accompanying hands-on material were designed for surgeons willing to understand the intuitions behind neural networks, become familiar with deep learning concepts and tasks, grasp what implementing a deep learning model in surgery means, and finally appreciate the specific challenges and limitations of deep neural networks in surgery. For the associated hands-on material, please see https://github.com/CAMMA-public/ai4surgery.

cs.NE↗

arXiv2020

Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets

Recognition of surgical activity is an essential component to develop context-aware decision support for the operating room. In this work, we tackle the recognition of fine-grained activities, modeled as action triplets representing the tool activity. To this end, we introduce a new laparoscopic dataset, CholecT40, consisting of 40 videos from the public dataset Cholec80 in which all frames have been annotated using 128 triplet classes. Furthermore, we present an approach to recognize these triplets directly from the video data. It relies on a module called Class Activation Guide (CAG), which uses the instrument activation maps to guide the verb and target recognition. To model the recognition of multiple triplets in the same frame, we also propose a trainable 3D Interaction Space, which captures the associations between the triplet components. Finally, we demonstrate the significance of these contributions via several ablation studies and comparisons to baselines on CholecT40.

eess.IV↗