Training and teaching of vagus nerve stimulation surgery: Worldwide survey and future perspectives

ObjectiveVagus nerve stimulation (VNS) therapy has been used for more than two decades to treat drug resistant epilepsy and depression and most recently received FDA approval for stroke rehabilitation. Expanding indications will renew the interest in the technique and increase the number of surgeons to be trained. The aim of this study was to survey surgeons with substantial expertise on optimal teaching and training approaches.MethodsAnonymous forms comprising 16 questions were sent by e-mail to surgeons with substantial expertise. Statistical analyses were used to compare the answers of the most experienced surgeons (>5 years) with the less experienced ones (<5 years).ResultsFully-completed forms were collected from 57 experts from 20 countries. The placement of the helical coils was deemed to be the most difficult step by 36 (63.2%) experts, and the use of optical magnification during this step was deemed necessary by 39 (68.4%) experts. Vocal cord palsy should be largely avoidable with proper surgical technique according to 44 (77.2%) experts. The teaching tool considered the most useful was mentoring (38, 66.7%). The future of VNS surgery teaching was deemed to be in anatomical workshops (29, 50.9%) and surgical simulation (26, 45.6%). Overall, answers did not vary significantly according to experience.ConclusionsVNS surgery should be mastered by actively participating in dedicated practical training courses and by individual mentoring during actual surgery, which is still the best way to learn. This study highlights the need for a formal training course and possible specific accreditation.     

Anomaly segmentation in retinal images with poisson-blending data augmentation

Diabetic retinopathy (DR) is one of the most important complications of diabetes. Accurate segmentation of DR lesions is of great importance for the early diagnosis of DR. However, simultaneous segmentation of multi-type DR lesions is technically challenging because of 1) the lack of pixel-level annotations and 2) the large diversity between different types of DR lesions. In this study, first, we propose a novel Poisson-blending data augmentation (PBDA) algorithm to generate synthetic images, which can be easily utilized to expand the existing training data for lesion segmentation. We perform extensive experiments to recognize the important attributes in the PBDA algorithm. We show that position constraints are of great importance and that the synthesis density of one type of lesion has a joint influence on the segmentation of other types of lesions. Second, we propose a convolutional neural network architecture, named DSR-U-Net++ (i.e., DC-SC residual U-Net++), for the simultaneous segmentation of multi-type DR lesions. Ablation studies showed that the mean area under precision recall curve (AUPR) for all four types of lesions increased by >5% with PBDA. The proposed DSR-U-Net++ with PBDA outperformed the state-of-the-art methods by 1.7%-9.9% on the Indian Diabetic Retinopathy Image Dataset (IDRiD) and 67.3% on the e-ophtha dataset with respect to mean AUPR. The developed method would be an efficient tool to generate large-scale task-specific training data for other medical anomaly segmentation tasks.