RESUMO
STUDY DESIGN: Cross-sectional database study. OBJECTIVE: The purpose of this study was to develop a successful, reproducible, and reliable convolutional neural network (CNN) model capable of segmentation and classification for grading intervertebral disc degeneration (IVDD), as well as quantify the network's impact on doctors' clinical decision-making. METHODS: 5685 discs from 1137 patients were graded separately by four experienced doctors according to the Pfirrmann classification. A ground truth (GT) was established for each disc in accordance with the decision of the majority of doctors. The U-net model is used for segmentation. 1815 discs from 363 patients were used to train and test the U-net. The Inception V3 model is employed for classification. All discs were separated into two distinct sets: 90% in a training set and 10% in a test set. The performance metrics of these models were measured. Reliability tests were performed. The impact of CNN assistance on doctors was assessed. RESULTS: Segmentation accuracy was .9597 with a .8717 Jaccard Index and a .9314 Sorensen Dice coefficient. Classification accuracy is .9346, and the F1 score is .9355. The intraclass correlation coefficient (ICC) and kappa values between CNN and GT were .95-.97. With CNN's assistance, the success rates of doctors increased by 7.9% to 22%. CONCLUSIONS: The fully automated network outperformed doctors markedly in terms of accuracy and reliability. The results of CNN were comparable to those of other recent studies in the literature. It was determined that CNN's assistance had a substantial positive effect on the doctor's decision.
RESUMO
BACKGROUND: To describe the severity and types of blast-related extremity injuries and the presence of accompanying vascular injuries (VI) and amputation, and to identify the associated factors affecting the treatment management and clinical course. METHODS: The study included 101 patients with extremity injuries caused by a bomb explosion. The radiographs and computed tomography angiographies of the patients were evaluated in terms of injury patterns, presence of penetrating fragments and fractures, and localization (upper or lower extremity) and type (open or closed) of injury. The Gustilo-Anderson classification was used for open fractures. According to their severity, open fractures classified as types 1 and 2 were included in Group 1 and those classified as type 3A, 3B and 3C in Group 2. RESULTS: As a result of blast exposure, 101 (57.7%) patients had extremity injuries, of which 76 (75.2%) presented with at least one fracture. Of the total of 103 fractures, nine (8.8%) were closed and 94 (91.2%) were open. Thirty-eight (40.4%) of the open fractures were located in the upper extremities, and 56 (59.6%) in the lower extremities and pelvis. Open fractures were most frequently localized in the femur (n = 20; 21.2%), followed by the tibia (n = 18; 19.1%). The majority of patients with open fractures were in Group 1 (71.4%). The duration of hospital stay was longer in Group 2 (12.1 ± 5.8 vs. 6.3 ± 6.7 days, p < 0.0001, respectively). Mortality among patients in Group 2 (45.0%) was significantly higher than in Group 1 (8.0%) (p < 0.0001). Similarly, the injury severity score (ISS) was higher in Group 2 (median 20 vs. 9, p < 0.0001). VI was present in 13 (12.9%) of all patients, and amputation in seven (7.9%). CONCLUSION: The presence of severe open fractures, VI, and high ISS score can be considered as important factors that increase morbidity and mortality. In extremity traumas, through the secondary blast mechanism, contaminated-fragmented tissue injuries occur. Therefore, we believe that it will be beneficial to apply damage control surgery in places with low socioeconomic level and poor hygienic conditions.
