Pan-mediastinal neoplasm diagnosis via nationwide federated learning: a multicentre cohort study.

BACKGROUND: Mediastinal neoplasms are typical thoracic diseases with increasing incidence in the general global population and can lead to poor prognosis. In clinical practice, the mediastinum's complex anatomic structures and intertype confusion among different mediastinal neoplasm pathologies severely hinder accurate diagnosis. To solve these difficulties, we organised a multicentre national collaboration on the basis of privacy-secured federated learning and developed CAIMEN, an efficient chest CT-based artificial intelligence (AI) mediastinal neoplasm diagnosis system. METHODS: In this multicentre cohort study, 7825 mediastinal neoplasm cases and 796 normal controls were collected from 24 centres in China to develop CAIMEN. We further enhanced CAIMEN with several novel algorithms in a multiview, knowledge-transferred, multilevel decision-making pattern. CAIMEN was tested by internal (929 cases at 15 centres), external (1216 cases at five centres and a real-world cohort of 11 162 cases), and human-AI (60 positive cases from four centres and radiologists from 15 institutions) test sets to evaluate its detection, segmentation, and classification performance. FINDINGS: In the external test experiments, the area under the receiver operating characteristic curve for detecting mediastinal neoplasms of CAIMEN was 0·973 (95% CI 0·969-0·977). In the real-world cohort, CAIMEN detected 13 false-negative cases confirmed by radiologists. The dice score for segmenting mediastinal neoplasms of CAIMEN was 0·765 (0·738-0·792). The mediastinal neoplasm classification top-1 and top-3 accuracy of CAIMEN were 0·523 (0·497-0·554) and 0·799 (0·778-0·822), respectively. In the human-AI test experiments, CAIMEN outperformed clinicians with top-1 and top-3 accuracy of 0·500 (0·383-0·633) and 0·800 (0·700-0·900), respectively. Meanwhile, with assistance from the computer aided diagnosis software based on CAIMEN, the 46 clinicians improved their average top-1 accuracy by 19·1% (0·345-0·411) and top-3 accuracy by 13·0% (0·545-0·616). INTERPRETATION: For mediastinal neoplasms, CAIMEN can produce high diagnostic accuracy and assist the diagnosis of human experts, showing its potential for clinical practice. FUNDING: National Key R&D Program of China, National Natural Science Foundation of China, and Beijing Natural Science Foundation.

How to optimize the treatment strategy for patients of pulmonary sequestration with an elevated risk of fatal hemorrhage during operation: case discussion.

Video-assisted thoracoscopic surgery (VATS) lobectomy, especially uniportal VATS, is increasingly used for pulmonary sequestration (PS). However, there are few descriptions of safe handling of the aberrant artery with atherosclerosis, especially the diameter of arteries exceeds than 2.0 cm, under uniportal VATS approach. Here we report a 56-year-old man who was diagnosed with pulmonary sequestration following trauma. The patient had a long history of cough with purulent sputum. One month before the trauma, he had copious expectoration with foul smell again. A contrast CT scan revealed a 7.5 cm mass in his right lower lobe. The mass was supplied by a thick aberrant atherosclerotic artery (over than 2 cm in diameter), which stemmed from the thoracic aorta with multiple calcifications on both. After adequate preoperative evaluation, we performed a right lower lobectomy under uniportal VATS approach. No surgical-associated complications occurred, and the patient was discharged on the 5th days after the operation. We organized an iMDT (international multidisciplinary team) to discuss the reasonability and optimal treatment pattern for this patient. We found that fully assess the quality of the aberrant arteries of PS following blocking and cutting off in an appropriate way are crucial to avoid the happening of fatal bleeding during the operation.

Clinical application of enhanced recovery after surgery (ERAS) in pectus excavatum patients following Nuss procedure.

BACKGROUND: Evaluate the effect of enhanced recovery after surgery (ERAS) protocol on postoperative recovery quality of pectus excavatum patients with Nuss procedure. METHODS: A retrospective study was performed on patients undergoing Nuss procedure from the Department of Thoracic Surgery of The Cancer Hospital of China Medical University between September 2016 and September 2019. Patients were divided into 2 groups by perioperative management: the traditional procedure group (T group) and the ERAS strategy group (E group). The outcome measures were postoperative drainage time, postoperative hospital time, and postoperative complications measured by the Clavien-Dindo method. RESULTS: Of the 168 patients from this time period, 148 met the inclusion criteria (75 in Group T and 73 in Group E). All operations involved in this study were completed successfully. There was no statistical difference between the 2 groups with respect to baseline demographics (P>0.05). In Group E, postoperative drainage time (2.53±0.72 vs. 3.45±2.07 days) and postoperative hospitalization time (4.96±1.48 vs. 7.71±7.78 days) were statistically significantly better than those in Group T (P<0.05). There was no difference in overall postoperative complications as measured by Clavien-Dindo score. CONCLUSIONS: The measures of no indwelling urinary catheter (IDUC), laryngeal mask anesthesia, and indwelling tubule drainage can improve postoperative recovery quality of pectus excavatum patients following Nuss procedure.