DIPO: Differentiable Parallel Operation Blocks for Surgical Neural Architecture Search
- 28 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5540-5550
Abstract
Deep learning has been used across a large number of computer vision tasks, however designing the network architectures for each task is time consuming. Neural Architecture Search (NAS) promises to automatically build neural networks, optimised for the given task and dataset. However, most NAS methods are constrained to a specific macro-architecture design which makes it hard to apply to different tasks (classification, detection, segmentation). Following the work in Differentiable NAS (DNAS), we present a simple and efficient NAS method, Differentiable Parallel Operation (DIPO), that constructs a local search space in the form of a DIPO block, and can easily be applied to any convolutional network by injecting it in-place of the convolutions. The DIPO block's internal architecture and parameters are automatically optimised end-to-end for each task. We demonstrate the flexibility of our approach by applying DIPO to 4 model architectures (U-Net, HRNET, KAPAO and YOLOX) across different surgical tasks (surgical scene segmentation, surgical instrument detection, and surgical instrument pose estimation) and evaluated across 5 datasets. Results show significant improvements in surgical scene segmentation (+10.5% in CholecSeg8K, +13.2% in CaDIS), instrument detection (+1.5% in ROBUST-MIS, +5.3% in RoboKP), and instrument pose estimation (+9.8% in RoboKP).Keywords
Funding Information
- Wellcome / EPSRC Centre for Interventional and Surgical Sciences (203145/Z/16/Z)
- Department of Science, Innovation and Technology
- Royal Academy of Engineering
- Chair in Emerging Technologies programme
- Engineering and Physical Sciences Research Council (EP/P027938/1, EP/R004080/1, EP/P012841/1)
This publication has 33 references indexed in Scilit:
- Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-person Human Pose Estimation2022
- An Improved YOLOX for Detection in Urine Sediment Images2022
- BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation2021
- Scalable Joint Detection and Segmentation of Surgical Instruments with Weak Supervision2021
- Automated COVID-19 Detection from Chest X-Ray Images: A High-Resolution Network (HRNet) ApproachSN Computer Science, 2021
- Semi-supervised Learning for Instrument Detection with a Class Imbalanced Dataset2020
- Searching for Efficient Architecture for Instrument Segmentation in Robotic Surgery2020
- AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation2020
- Neural Architecture Search2019
- Microsoft COCO: Common Objects in Context2014