Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos

Abstract

Purpose: Real-time surgical tool tracking is a core component of the future intelligent operating room (OR), because it is highly instrumental to analyze and understand the surgical activities. Current methods for surgical tool tracking in videos need to be trained on data in which the spatial positions of the tools are manually annotated. Generating such training data is difficult and time-consuming. Instead, we propose to use solely binary presence annotations to train a tool tracker for laparoscopic videos. Methods: The proposed approach is composed of a CNN + Convolutional LSTM (ConvLSTM) neural network trained end-to-end, but weakly supervised on tool binary presence labels only. We use the ConvLSTM to model the temporal dependencies in the motion of the surgical tools and leverage its spatio-temporal ability to smooth the class peak activations in the localization heat maps (Lh-maps). Results: We build a baseline tracker on top of the CNN model and demonstrate that our approach based on the ConvLSTM outperforms the baseline in tool presence detection, spatial localization, and motion tracking by over 5.0%, 13.9%, and 12.6%, respectively. Conclusions: In this paper, we demonstrate that binary presence labels are sufficient for training a deep learning tracking model using our proposed method. We also show that the ConvLSTM can leverage the spatio-temporal coherence of consecutive image frames across a surgical video to improve tool presence detection, spatial localization, and motion tracking. keywords: Surgical workflow analysis, tool tracking, weak supervision, spatio-temporal coherence, ConvLSTM, endoscopic videos

14 pages, 3 figures, 3 tables, Supplementary video: https://youtu.be/vnMwlS5tvHE and https://youtu.be/SNhd1yzOe50

References in corpus (1)

• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net

Cited by in corpus (22)

• Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos
• CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions
• CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
• Image Compositing for Segmentation of Surgical Tools without Manual Annotations
• CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
• A Kinematic Bottleneck Approach For Pose Regression of Flexible Surgical Instruments directly from Images
• Preserving Privacy in Surgical Video Analysis Using Artificial Intelligence: A Deep Learning Classifier to Identify Out-of-Body Scenes in Endoscopic Videos
• On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis
• SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos
• A Neural Network based Framework for Effective Laparoscopic Video Quality Assessment
• Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognition
• Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets
• Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures
• Surgical Text-to-Image Generation
• Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets
• FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack
• Adaptive transfer learning for surgical tool presence detection in laparoscopic videos through gradual freezing fine-tuning
• Unsupervised Surgical Instrument Segmentation via Anchor Generation and Semantic Diffusion
• Multimodal Semantic Scene Graphs for Holistic Modeling of Surgical Procedures
• Automatic Tip Detection of Surgical Instruments in Biportal Endoscopic Spine Surgery
• Weakly-Supervised Cell Tracking via Backward-and-Forward Propagation
• A Novel Deep ML Architecture by Integrating Visual Simultaneous Localization and Mapping (vSLAM) into Mask R-CNN for Real-time Surgical Video Analysis