RESUMO
Objective: To assess the performance of a novel deep learning (DL)-based artificial intelligence (AI) system in classifying computed tomography (CT) scans of pneumonia patients into different groups, as well as to present an effective clinically relevant machine learning (ML) system based on medical image identification and clinical feature interpretation to assist radiologists in triage and diagnosis. Methods: The 3,463 CT images of pneumonia used in this multi-center retrospective study were divided into four categories: bacterial pneumonia (n = 507), fungal pneumonia (n = 126), common viral pneumonia (n = 777), and COVID-19 (n = 2,053). We used DL methods based on images to distinguish pulmonary infections. A machine learning (ML) model for risk interpretation was developed using key imaging (learned from the DL methods) and clinical features. The algorithms were evaluated using the areas under the receiver operating characteristic curves (AUCs). Results: The median AUC of DL models for differentiating pulmonary infection was 99.5% (COVID-19), 98.6% (viral pneumonia), 98.4% (bacterial pneumonia), 99.1% (fungal pneumonia), respectively. By combining chest CT results and clinical symptoms, the ML model performed well, with an AUC of 99.7% for SARS-CoV-2, 99.4% for common virus, 98.9% for bacteria, and 99.6% for fungus. Regarding clinical features interpreting, the model revealed distinctive CT characteristics associated with specific pneumonia: in COVID-19, ground-glass opacity (GGO) [92.5%; odds ratio (OR), 1.76; 95% confidence interval (CI): 1.71-1.86]; larger lesions in the right upper lung (75.0%; OR, 1.12; 95% CI: 1.03-1.25) with viral pneumonia; older age (57.0 years ± 14.2, OR, 1.84; 95% CI: 1.73-1.99) with bacterial pneumonia; and consolidation (95.8%, OR, 1.29; 95% CI: 1.05-1.40) with fungal pneumonia. Conclusion: For classifying common types of pneumonia and assessing the influential factors for triage, our AI system has shown promising results. Our ultimate goal is to assist clinicians in making quick and accurate diagnoses, resulting in the potential for early therapeutic intervention.
RESUMO
OBJECTIVE: To study the feasibility and clinical efficacy of a minimally invasive sinus tarsi approach in the treatment of Sanders II calcaneus fractures. METHODS: From August of 2015 to July of 2016, 13 patients(totally 13 feet) with Sanders II intra-articular calcaneus fractures were treated via the minimally invasive sinus tarsi approach. The Böhler angle, Gissane angle and the length, width and height of calcaneus were compared between pre-operation and post-operation. The AOFAS ankle and foot scoring system of the orthopaedic ankle foot Association was used to evaluate the efficacy. RESULTS: All the patients were followed up, and the duration ranged from 6 to 15 months, with an average of 9.5 months. No incision complications occurred. The Böhler angle was increased from preoperative (18.82±5.11)° to postoperative(26.63±4.45)°(t=-4.16, P=0.000). The Gissane angle was increased from preoperative(111.07±15.36)° to postoperative (124.56±8.71)° (t=-2.75, P=0.011). The length, width, height of calcaneus were absolutely improved from preoperative(69.82±5.95) mm, (42.07±3.68) mm, (41.20±3.90) mm to preoperatively(72.61±5.46) mm, (39.10±4.02) mm, (44.03±3.33) mm. According to the AOFAS, 8 patients got an excellent result, 4 good and 1 poor, and the postoperative mean score was 88.2±5.9. CONCLUSIONS: The limited open sinus tarsi approach could be used successfully to treat displaced Sanders II fractures with less injury and effectively restored the surface of subtalar joint, however the method is not fit for the patients with comminuted fracture in lateral wall and great change in the length, width, height, varus and valgus of calcaneus.