Antoine Netter

Background: Laparoscopic surgery for endometriosis presents unique challenges due to the complexity of and variability in lesion appearances within the abdominal cavity. This study investigates the application of deep learning models for object detection in laparoscopic videos, aiming to assist surgeons in accurately identifying and localizing endometriosis lesions and related anatomical structures. A custom dataset was curated, comprising of 199 video sequences and 205,725 frames. Of these, 17,560 frames were meticulously annotated by medical professionals. The dataset includes object detection annotations for 10 object classes relevant to endometriosis, alongside segmentation masks for some classes. Methods: To address the object detection task, we evaluated the performance of two deep learning models—FasterRCNN and YOLOv9—under both stratified and non-stratified training scenarios. Results: The experimental results demonstrated that stratified training significantly reduced the risk of data leakage and improved model generalization. The best-performing FasterRCNN object detection model achieved a high average test precision of 0.9811 ± 0.0084, recall of 0.7083 ± 0.0807, and mAP50 (mean average precision at 50% overlap) of 0.8185 ± 0.0562 across all presented classes. Despite these successes, the study also highlights the challenges posed by the weak annotations and class imbalances in the dataset, which impacted overall model performances. Conclusions: In conclusion, this study provides valuable insights into the application of deep learning for enhancing laparoscopic surgical precision in endometriosis treatment. The findings underscore the importance of robust dataset curation and advanced training strategies in developing reliable AI-assisted tools for surgical interventions. The latter could potentially improve the guidance of surgical interventions and prevent blind spots occurring in difficult to reach abdominal regions. Future work will focus on refining the dataset and exploring more sophisticated model architectures to further improve detection accuracy.

Laparoscopic surgery for endometriosis presents unique challenges due to the complexity and variability of lesion appearances within the abdominal cavity. This study investigates the application of deep learning models for object detection in laparoscopic videos, aiming to assist surgeons in accurately identifying and localising endometriosis lesions and related anatomical structures. A custom dataset was curated, comprising 332 video sequences and 354,906 frames. Of these, 17,560 frames were meticulously annotated by medical professionals. The dataset includes object-detection annotations for 10 object classes relevant to endometriosis, alongside segmentation masks for some classes. To address the object detection task, we evaluated the performance of three deep learning models - FasterRCNN, MaskRCNN, and YOLOv9 - under both stratified and non-stratified training scenarios. Experimental results demonstrated that stratified training significantly reduced the risk of data leakage and improved model generalization. The best-performing object detection model achieved high precision and recall across most classes. Despite these successes, the study also highlights the challenges posed by the weak annotations and class imbalances in the dataset, which impacted overall models performances. In conclusion, this study provides valuable insights into the application of deep learning for enhancing laparoscopic surgical precision in endometriosis treatment. The findings underscore the importance of robust dataset curation and advanced training strategies in developing reliable AI-assisted tools for surgical interventions. Future work will focus on refining the dataset and exploring more sophisticated model architectures to further improve detection accuracy.

The diagnosis of endometriomas in patients with endometriosis is of primary importance because it influences the management and prognosis of infertility and pain. Imaging techniques are evolving constantly. This study aimed to systematically assess the diagnostic accuracy of transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI) in detecting endometrioma using the surgical visualisation of lesions with or without histopathological confirmation as reference standards in patients of reproductive age with suspected endometriosis. PubMed, Embase, Web of Science, Cumulative Index to Nursing and Allied Health Literature and ClinicalTrials.gov databases were searched from their inception to 12 October 2022, using a manual search for additional articles. Two authors independently performed title, abstract and full-text screening of the identified records, extracted study details and quantitative data and assessed the quality of the studies using the 'Quality Assessment of Diagnostic Accuracy Study 2' tool. Bivariate random-effects models were used to determine the pooled sensitivity and specificity, compare the two imaging modalities and evaluate the sources of heterogeneity. Sixteen prospective studies (10 assessing TVUS, 4 assessing MRI and 2 assessing both TVUS and MRI) were included, representing 1976 participants. Pooled TVUS and MRI sensitivities for endometrioma were 0.89 (95% confidence interval 'CI', 0.86-0.92) and 0.94 (95% CI, 0.74-0.99), respectively (indirect comparison p-value of 0.47). Pooled TVUS and MRI specificities for endometrioma were 0.95 (95% CI, 0.92-0.97) and 0.94 (95% CI, 0.89-0.97), respectively (indirect comparison p-value of 0.51). These studies had a high or unclear risk of bias. A direct comparison (all participants undergoing TVUS and MRI) of the modalities was available in only two studies. TVUS and MRI have high accuracy for diagnosing endometriomas; however, high-quality studies comparing the two modalities are lacking.