Computer-assisted real-time automatic prostate segmentation during TaTME: a single-center feasibility study.

BACKGROUND: Urethral injuries (UIs) are significant complications pertaining to transanal total mesorectal excision (TaTME). It is important for surgeons to identify the prostate during TaTME to prevent UI occurrence; intraoperative image navigation could be considered useful in this regard. This study aims at developing a deep learning model for real-time automatic prostate segmentation based on intraoperative video during TaTME. The proposed model's performance has been evaluated. METHODS: This was a single-institution retrospective feasibility study. Semantic segmentation of the prostate area was performed using a convolutional neural network (CNN)-based approach. DeepLab v3 plus was utilized as the CNN model for the semantic segmentation task. The Dice coefficient (DC), which is calculated based on the overlapping area between the ground truth and predicted area, was utilized as an evaluation metric for the proposed model. RESULTS: Five hundred prostate images were randomly extracted from 17 TaTME videos, and the prostate area was manually annotated on each image. Fivefold cross-validation tests were performed, and as observed, the average DC value equaled 0.71 ± 0.04, the maximum value being 0.77. Additionally, the model operated at 11 fps, which provides acceptable real-time performance. CONCLUSIONS: To the best of the authors' knowledge, this is the first effort toward realization of computer-assisted TaTME, and results obtained in this study suggest that the proposed deep learning model can be utilized for real-time automatic prostate segmentation. In future endeavors, the accuracy and performance of the proposed model will be improved to enable its use in practical applications, and its capability to reduce UI risks during TaTME will be verified.

Malignant peripheral nerve sheath tumour of the oesophagus: a case report.

BACKGROUND: Malignant peripheral nerve sheath tumour (MPNST) is a very rare disease, and its pathogenesis is unknown. There are few reports of MPNST of the oesophagus. We report a case of an MPNST that was diagnosed and resected. CASE PRESENTATION: A 30-year-old female presented with dysphagia. She had been aware of the dysphagia approximately 6 months before presentation. The chest X-ray showed shadows in the right mediastinum. Barium fluoroscopy revealed a semicircular raised lesion in the lower oesophagus. Upper gastrointestinal endoscopy revealed a type 1 oesophageal tumour centred on the posterior wall 26-35 cm from the incisors. The surface was ulcerated, and the tumour was exposed. The affected area showed no iodine uptake. The EUS showed an isoechoic mass. The CT scan showed a mass of 71 × 61 × 55 mm in the beginning of the lower oesophagus with low density mass and swelling of the right recurrent nerve lymph node to 12 mm. On FDG-PET, the tumour showed an SUVmax of 11.05, and no abnormal accumulation was found in lymph nodes or other organs. The MRI showed a hyperintense mass on the T2WI, which had prolonged contrast enhancement, and no findings of invasion into surrounding tissue were found. The patient underwent right thoracotomy and open thoracic oesophagectomy. The affected lymph node was tumour negative by rapid pathological diagnosis during the operation. Histologically, spindle cells with different-sized nuclei were mixed throughout the tissue. Some regions showed nuclear polymorphism or a storiform pattern, and locally, there were approximately 7 mitoses/10 HPFs. The margin was relatively clear, but spindle-shaped tumour cells infiltrated the surrounding interstitium and basal myoepithelium, and the patient was diagnosed with MPNST. In this case, the postoperative course was good, and 16 months after the operation, the patient is currently under observation at the outpatient stage without recurrence. CONCLUSIONS: MPNST in the oesophagus is a relatively rare disease. Diagnosis before treatment is sometimes difficult, but the prognosis is good if radical resection is possible.