RESUMO
PURPOSE: This study aims to evaluate the effectiveness of advanced deep learning models, specifically YOLOv8 and EfficientNetV2, in detecting meniscal tears on magnetic resonance imaging (MRI) using a relatively small data set. METHOD: Our data set consisted of MRI studies from 642 knees-two orthopaedic surgeons labelled and annotated the MR images. The training pipeline included MRI scans of these knees. It was divided into two stages: initially, a deep learning algorithm called YOLO was employed to identify the meniscus location, and subsequently, the EfficientNetV2 deep learning architecture was utilized to detect meniscal tears. A concise report indicating the location and detection of a torn meniscus is provided at the end. RESULT: The YOLOv8 model achieved mean average precision at 50% threshold (mAP@50) scores of 0.98 in the sagittal view and 0.985 in the coronal view. Similarly, the EfficientNetV2 model obtained area under the curve scores of 0.97 and 0.98 in the sagittal and coronal views, respectively. These outstanding results demonstrate exceptional performance in meniscus localization and tear detection. CONCLUSION: Despite a relatively small data set, state-of-the-art models like YOLOv8 and EfficientNetV2 yielded promising results. This artificial intelligence system enhances meniscal injury diagnosis by generating instant structured reports, facilitating faster image interpretation and reducing physician workload. LEVEL OF EVIDENCE: Level III.
RESUMO
PURPOSE: End-stage ankle arthrosis causes severe pain and limited movement. Tibiotalocalcaneal arthrodesis with arthroscopy-assisted hindfoot nailing can be used to achieve a high union rate and low complication rate. We aimed to examine the early- and mid-term results of patients treated with this technique from various perspectives and to evaluate them by comparing them with the current literature. METHODS: Data were collected from 25 patients who met the established criteria and underwent TTCA with arthroscopic-assisted hindfoot nailing. In addition to the demographic data of the patients, their clinical and pain scores were evaluated using the American Orthopedic Foot and Ankle Society (AOFAS) and visual analogue scale (VAS). Additionally, the union time and complication data during the follow-up period were examined. RESULTS: When the AOFAS and VAS scores of the 25 patients were examined, a significant improvement was observed in the preoperative period and early postoperative period comparisons (p < .001). No significant change was observed between the comparison of the postoperative 12th month and last postoperative control clinical scores. While the union rate of the patients was observed to be 92%, the average union time was 13.1 ± 3.5 weeks. During follow-up, peri-implant fracture, deep infection, and non-union were observed in one patient each (12%). CONCLUSION: The early- and mid-term postoperative results of patients treated with TTCA surgery with posterior approach arthroscopic-assisted hindfoot nailing show that this technique may be an option with low complication and high union rates for the appropriate group of patients planned for ankle arthrodesis.
Assuntos
Articulação do Tornozelo , Artrodese , Artroscopia , Pinos Ortopédicos , Humanos , Artrodese/métodos , Artrodese/instrumentação , Masculino , Feminino , Pessoa de Meia-Idade , Articulação do Tornozelo/cirurgia , Articulação do Tornozelo/diagnóstico por imagem , Artroscopia/métodos , Idoso , Adulto , Estudos Retrospectivos , Osteoartrite/cirurgiaRESUMO
OBJECTIVE: This study aims to determine whether the number of pregnancies contributes to the development of chronic lower back pain, worsening the lumbar disc degeneration and altering the normal lumbar sagittal balance. MATERIAL METHOD: There are 134 ladies participated in this study. They are divided into two groups based on their number of pregnancies (parity). All patients with chronic back pain were assessed using a visual analog scale for pain and the Oswestry Disability Index for their functional status assessment. Degenerative signs in lumbar MRI, which are Modic changes and the presence of Schmorl's node, were evaluated. Besides that, the sagittal balance of the lumbar spine was also measured via an erect lumbar plain radiograph. RESULTS: Patients with parities < 5 were included in Group 1, and those with parities ≥ 5 in Group 2. The mean visual analog scale score of Group 2 was significantly higher than that of Group 1 (8.42 ± 1.34 vs.6.50 ± 1.61). The mean Oswestry Disability Index score in Group 2 was significantly higher than that of Group 1 (29.87 ± 6.75 vs.18.41 ± 7.97). This relationship between the groups in terms of Modic change was statistically significant. The relationship between the groups regarding the presence of Schmorl's nodes was also statistically significant. The difference between the groups in terms of sagittal balance parameters was not statistically significant. CONCLUSION: Chronic lower back pain is significantly worse and associated with more disability in patients with more than five previous pregnancies. MRI degenerative changes are also significantly higher in these grand multipara groups.