SWOT Analysis of Vision Transformers (ViTs) for Automated Diagnosis of Endometriosis from Laparoscopic Videos: Feasibility and Ethical Challenges

Endometriosis diagnosis via laparoscopy remains challenging due to subtle lesion appearances and inter-observer variability. While artificial intelligence shows promise for surgical video analysis, the potential of Vision Transformers (ViTs) specifically for endometriosis detection remains unexplored. This study applied a SWOT framework to evaluate ViTs for automated endometriosis diagnosis in laparoscopic videos. Analysis of ۱۰ studies from PubMed, IEEE Xplore, and Scopus identified key findings: Strengths included (۱) global attention for lesion detection, (۲) outperforming CNNs/RNNs in surgical tasks (۹۱-۹۷% accuracy), and (۳) multimodal data integration. Weaknesses were (۱) dependence on unavailable annotated datasets, (۲) high computational needs, (۳) limited local feature sensitivity, and (۴) annotation variability issues. Opportunities involved (۱) self-supervised learning from unlabeled videos and (۲) explainable attention maps. Threats comprised (۱) performance variability across surgical settings, (۲) lacking regulatory standards, and (۳) data privacy concerns. Crucially, no studies directly tested ViTs for endometriosis diagnosis despite their potential. For clinical implementation, three requirements emerged: (۱) collaborative dataset creation, (۲) optimized hybrid architectures, and (۳) ethical guidelines for surgical AI. This structured analysis provides a roadmap for developing ViT-based diagnostic tools while addressing current limitations in data, technology, and clinical integration.

کلیدواژه ها:

Vision Transformers (ViTs) ، Endometriosis ، Laparoscopic Surgery ، SWOT Analysis ، Ethical AI