Multi-centre deep learning for placenta segmentation in obstetric ultrasound with multi-observer and cross-country generalization.

The placenta is crucial to fetal well-being and it plays a significant role in the pathogenesis of hypertensive pregnancy disorders. Moreover, a timely diagnosis of placenta previa may save lives. Ultrasound is the primary imaging modality in pregnancy, but high-quality imaging depends on the access to equipment and staff, which is not possible in all settings. Convolutional neural networks may help standardize the acquisition of images for fetal diagnostics. Our aim was to develop a deep learning based model for classification and segmentation of the placenta in ultrasound images. We trained a model based on manual annotations of 7,500 ultrasound images to identify and segment the placenta. The model's performance was compared to annotations made by 25 clinicians (experts, trainees, midwives). The overall image classification accuracy was 81%. The average intersection over union score (IoU) reached 0.78. The model's accuracy was lower than experts' and trainees', but it outperformed all clinicians at delineating the placenta, IoU = 0.75 vs 0.69, 0.66, 0.59. The model was cross validated on 100 2nd trimester images from Barcelona, yielding an accuracy of 76%, IoU 0.68. In conclusion, we developed a model for automatic classification and segmentation of the placenta with consistent performance across different patient populations. It may be used for automated detection of placenta previa and enable future deep learning research in placental dysfunction.

Expertise in colonoscopy intubation does not predict diagnostic accuracy: a simulation-based study.

Background and study aims Studies have linked cecal intubation rate with adenoma detection rate; however, the direct association between technical performance during colonoscopy intubation and withdrawal has never been explored. Thus, it remains unclear whether gentle and efficient intubation predicts superior mucosal inspection. The aim of this study was to investigate the correlation between performance during intubation and withdrawal in a simulation-based setup. Methods Twenty-four physicians with various experience in colonoscopy performed twice on the Endoscopy Training System (ETS). Intubation skills were evaluated by assessing tasks on the ETS related to intubation (scope manipulation and loop management) and use of a computerized assessment tool called the 3D-Colonoscopy Progression Score (3D-CoPS). Diagnostic accuracy was defined by the number of polyps found during the ETS task of mucosal inspection. Pearson's correlations were calculated to explore associations between intubation skill and diagnostic accuracy. Results The correlation analysis between 3D-CoPS and number of polyps found during mucosal inspection revealed a weak and insignificant correlation (0.157, P  = 0.3). Likewise, an insignificant correlation was seen between ETS intubation and number of polyps found (0.149, P  = 0.32). Conclusions We found no evidence to support that technical performance during intubation is correlated with mucosal inspection performance in a simulation-based setting.