Deep Neural Networks Can Accurately Detect Blood Loss and Hemorrhage Control Task Success From Video

Abstract

BACKGROUND: Deep neural networks (DNNs) have not been proven to detect blood loss (BL) or predict surgeon performance from video. OBJECTIVE: To train a DNN using video from cadaveric training exercises of surgeons controlling simulated internal carotid hemorrhage to predict clinically relevant outcomes. METHODS: Video was input as a series of images; deep learning networks were developed, which predicted BL and task success from images alone (automated model) and images plus human-labeled instrument annotations (semiautomated model). These models were compared against 2 reference models, which used average BL across all trials as its prediction (control 1) and a linear regression with time to hemostasis (a metric with known association with BL) as input (control 2). The root-mean-square error (RMSE) and correlation coefficients were used to compare the models; lower RMSE indicates superior performance. RESULTS: One hundred forty-three trials were used (123 for training and 20 for testing). Deep learning models outperformed controls (control 1: RMSE 489 mL, control 2: RMSE 431 mL, R 2 = 0.35) at BL prediction. The automated model predicted BL with an RMSE of 358 mL (R2 = 0.4) and correctly classified outcome in 85% of trials. The RMSE and classification performance of the semiautomated model improved to 260 mL and 90%, respectively. CONCLUSION: BL and task outcome classification are important components of an automated assessment of surgical performance. DNNs can predict BL and outcome of hemorrhage control from video alone; their performance is improved with surgical instrument presence data. The generalizability of DNNs trained on hemorrhage control tasks should be investigated.

Automated Capture of Intraoperative Adverse Events Using Artificial Intelligence: A Systematic Review and Meta-Analysis

“…A flow-chart of the article selection process is shown in Figure 1 . The 13 studies included in this review were published from 2016 to 2022 [ 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 ], with the majority published during or after 2020. Table 1 shows an overview of the methodologies used, adverse events analyzed, AI algorithms, type of validation, outcomes, and comparative metrics from the 13 included articles.…”

Pilot Analysis of Surgeon Instrument Utilization Signatures Based on Shannon Entropy and Deep Learning for Surgeon Performance Assessment in a Cadaveric Carotid Artery Injury Control Simulation

“…For CV detection of surgical tools, the SOCAL data set images, composed of individual frames from an operative video down sampled to 1 frame per second, were divided into training and testing subsets, as previously described, to generate an approximately 80/20 split. 14,24 All frames from a single trial were all assigned to the same set, and the associated annotations contained surgical instrument bounding box coordinates. A "you only look once" (YOLOv4) algorithm, forked from the AlexeyAB-Darknet GitHub repository, was trained on 27 223 training set images from 124 SOCAL trials with the following parameters: batch size of 8, a network width and height of 608, learning rate of 0.001, and pretrained starting weights from the Microsoft COCO data set.…”

“…In this study, we evaluate the ability of ShEn and DL to predict surgical outcomes from a validated and high-fidelity cadaveric simulation of carotid artery lacerations. 11,14,[24][25][26] This work demonstrates a novel surgical APM to quantify patterns in instrument usage, and we display its performance using DL instrument detections.…”

Letter: Deep Neural Networks Can Accurately Detect Blood Loss and Hemorrhage Control Task Success from Video

“…2-4 Nevertheless, they have received limited attention in neurosurgery. Although Kugener et al have explored RNN in deep learning–based video analysis pipelines, 1 these architectures may be applicable to other fields of neurosurgery, including sequential data for time series analyses. 5 In this letter, we expound on the current state and future potential of time series–based model architectures for machine learning analyses in the field of neurosurgery.…”