{
  "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 location of surgical tools in the field of view and the direction of lighting, both of which are tightly related to the region of interest. We propose methods for evaluating the severity of these biases based on measurements of model consistency under real or simulated exposure to these shortcuts, and augmentation-based methods for mitigating them. We show that our tool bias mitigations based on pasting tool images in random locations improve the models’ prediction consistency under tool movements by 9 percentage points in the most inconsistent cases, and by 4 percentage points on average. Our lighting bias mitigations based on simulated lighting adjustments help reduce fraction of pixels originally predicted as belonging to the dangerous zone that may flip to safe under light changes from 5% to 1.5%, without compromising segmentation quality. Author summary: Artificial intelligence is increasingly used to support surgeons, for example by highlighting which tissue is safe to cut and which is dangerous during gallbladder removal (laparoscopic cholecystectomy), one of the most common abdominal operations. These systems can, however, learn the wrong lesson. We found that AI models for this task come to rely on where the surgeon places the instruments and where the camera light is pointed, rather than on the anatomy itself. Experienced surgeons tend to position their tools and lighting in predictable places, so the model takes a shortcut. The danger is that a less experienced surgeon, who handles equipment differently, could receive misleading guidance. This flaw is hard to detect because the pattern runs through all of the data, so ordinary testing does not reveal it. We developed a way to measure how strongly a model leans on these shortcuts, and a simple training method that breaks them by inserting instruments and extra lighting at random positions. Our approach makes predictions substantially more consistent without sacrificing accuracy, a step toward surgical AI that offers trustworthy guidance to surgeons at every level of experience.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Science, University of Toronto, Toronto, Ontario, Canada",
    "Vector Institute for Artificial Intelligence, Toronto, Ontario, Canada",
    "University Health Network, Toronto, Ontario, Canada"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Sergey Protserov"
    },
    {
      "affs": [
        1
      ],
      "name": "Anastasiia Repalo"
    },
    {
      "affs": [
        2
      ],
      "name": "Pouria Mashouri"
    },
    {
      "name": "Jaryd Hunter"
    },
    {
      "name": "Caterina Masino"
    },
    {
      "name": "Amin Madani"
    },
    {
      "name": "Michael Brudno"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f85rbpxgcax25.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pdig.0001421",
  "fulltext_url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001421",
  "id": "f85rbpxgcax25",
  "issns": [
    "2767-3170"
  ],
  "landing_url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001421",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2746|Surgical Simulation and Training"
    ],
    [
      "plos",
      "/Biology and life sciences/Bioengineering/Biotechnology/Medical devices and equipment"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Computer vision"
    ],
    [
      "plos",
      "/Engineering and technology/Bioengineering/Biotechnology/Medical devices and equipment"
    ],
    [
      "plos",
      "/Medicine and health sciences/Health care/Health care providers/Physicians/Surgeons"
    ],
    [
      "plos",
      "/Medicine and health sciences/Medical devices and equipment"
    ],
    [
      "plos",
      "/Medicine and health sciences/Surgical and invasive medical procedures"
    ],
    [
      "plos",
      "/Medicine and health sciences/Surgical and invasive medical procedures/Digestive system procedures/Cholecystectomy/Laparoscopic cholecystectomy"
    ],
    [
      "plos",
      "/Medicine and health sciences/Surgical and invasive medical procedures/Laparoscopy"
    ],
    [
      "plos",
      "/Medicine and health sciences/Surgical and invasive medical procedures/Laparoscopy/Laparoscopic cholecystectomy"
    ],
    [
      "plos",
      "/People and places/Population groupings/Professions/Medical personnel/Physicians/Surgeons"
    ]
  ],
  "openalex": "W7220960826",
  "pdf_url": "https://journals.plos.org/digitalhealth/article/file?id=10.1371/journal.pdig.0001421&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-08",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/f85rbpxgcax25.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:30Z",
      "native_id": "10.1371/journal.pdig.0001421",
      "source": "plos",
      "url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001421"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:biotechnology",
      "subfield": "systems-synthetic"
    },
    {
      "field": "medicine",
      "origin": "plos:surgical and invasive medical procedures",
      "subfield": "surgery"
    }
  ],
  "title": "Analysis and mitigation of equipment-induced shortcuts in AI models for laparoscopic cholecystectomy",
  "title_text": "Analysis and mitigation of equipment-induced shortcuts in AI models for laparoscopic cholecystectomy",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:30Z",
  "url": "https://research.draconitic.com/paper/f85rbpxgcax25",
  "venue": "PLOS Digital Health",
  "versions": []
}