Analysis and Mitigation of Equipment-induced Shortcuts in AI Models for Laparoscopic Cholecystectomy
Protserov, S.; Repalo, A.; Mashouri, P.; Hunter, J.; Masino, C.; Madani, A.; Brudno, M.
Show abstract
Machine learning models have seen a lot of success in medical image segmentation domain. However, one of the challenges that they face are confounders or shortcuts: spurious correlations or biases in the training data that affect the resulting models. One example of such confounders for surgical machine learning is the setup of surgical equipment, including tools and lighting. Using the task of identification of safe and dangerous zones of dissection in laparoscopic cholecystectomy images and videos as a use-case, we inspect two equipment-induced biases: the presence of surgical tools in the field of view and the position of lighting. We propose methods for evaluating the severity of these biases and augmentation-based methods for mitigating them. We show that our tool bias mitigations improve the models consistency under tool movements by 9 percentage points in the most inconsistent cases, and by 4 percentage points on average. Our lighting bias mitigations help reduce fraction of true dangerous zone pixels that may be predicted as safe under light changes from 5% to 1.5%, without compromising segmentation quality.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- The tempest in a cubic millimeter: Image-based refinements necessitate the reconstruction of 3D microvasculature from a large series of damaged alternately-stained histological sections 95%
- SN-FPN: Self-attention Nested Feature Pyramid Network for Digital Pathology Image Segmentation 94%
- Cell segmentation without annotation by unsupervised domain adaptation based on cooperative self-learning 93%
Similar papers in this journal
- A human-in-the-loop explanation framework for morphologically transparent AI predictions from whole-slide images 93%
- A Deep Learning Based Smartphone Application for Early Detection of Nasopharyngeal Carcinoma Using Endoscopic Images 92%
- Evaluating large language model workflows in clinical decision support: referral, triage, and diagnosis 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.