Ik Yang

Purpose: Convolutional neural networks (CNNs) have been studied for detecting bone metastases on bone scans; however, the application of ConvNeXt and transformer models has not yet been explored. This study aims to evaluate the performance of various deep learning models, including the ConvNeXt and transformer models, in diagnosing metastatic lesions from bone scans. Materials and Methods: We retrospectively analyzed bone scans from patients with cancer obtained at 2 institutions: the training and validation sets (n=4626) were from Hospital 1 and the test set (n=1428) was from Hospital 2. The deep learning models evaluated included ResNet18, the Data-Efficient Image Transformer (DeiT), the Vision Transformer (ViT Large 16), the Swin Transformer (Swin Base), and ConvNeXt Large. Gradient-weighted class activation mapping (Grad-CAM) was used for visualization. Results: Both the validation set and the test set demonstrated that the ConvNeXt large model (0.969 and 0.885, respectively) exhibited the best performance, followed by the Swin Base model (0.965 and 0.840, respectively), both of which significantly outperformed ResNet (0.892 and 0.725, respectively). Subgroup analyses revealed that all the models demonstrated greater diagnostic accuracy for patients with polymetastasis compared with those with oligometastasis. Grad-CAM visualization revealed that the ConvNeXt Large model focused more on identifying local lesions, whereas the Swin Base model focused on global areas such as the axial skeleton and pelvis. Conclusions: Compared with traditional CNN and transformer models, the ConvNeXt model demonstrated superior diagnostic performance in detecting bone metastases from bone scans, especially in cases of polymetastasis, suggesting its potential in medical image analysis.

Cho YT, et al. Clin Orthop Surg. 2025 Dec;17(6):1025-1034. https://doi.org/10.4055/cios25074

This study aimed to establish a low-risk zone to avoid neurovascular injury during a temporary extra-articular calcaneo-tibial pin fixation in an unstable ankle or subtalar joint. A line from the calcaneal tuberosity center to the lateral end of the posterior malleolus at the ankle joint level defines the lateral border of this zone. Another line from the calcaneal tuberosity center to the midpoint of the anterior distal tibial articular surface at the joint level defines its medial border. This region was assumed to have a low neurovascular injury risk upon pin insertion. Fifty ankles from 50 patients who had undergone magnetic resonance imaging (MRI) for ankle disorders were assessed. T1-weighted oblique axial MRI slices were oriented to the pin trajectory. The mean distances between the sural nerve and the lateral border of the low-risk zone and between the posterior tibial neurovascular structures and the medial border of the low-risk zone were 15.0 ± 2.5 (range 9.1 to 21.1) and 12.8 ± 2.6 (6.3 to 20.8) mm, respectively. No neurovascular structures were identified within the low-risk zone. These findings demonstrated that an unstable ankle or subtalar joint can be temporarily fixated with an extra-articular calcaneo-tibial pin at a defined zone with a low neurovascular injury risk.

김종희, et al. J Korean Soc Radiol. 2021 Aug;82:e116. https://doi.org/10.3348/jksr.2021.0011

양익, et al. J Korean Soc Radiol. 2020 Aug;81:e68. https://doi.org/10.3348/jksr.2020.0088

Perineurioma is an unusual benign peripheral nerve sheath tumor that includes intraneural, soft tissue (conventional), reticular and sclerosing types. Sclerosing perineurioma is a recently described distinctive variant occurring nearly exclusively on the hands of young adults, in which it presents as a small, painless, dermal or subcutaneous mass. The only report of imaging findings in sclerosing perineurioma was by Miyake et al., who described the MR findings in 2006. However, there have been no reports of the ultrasound features. We report a 22-year-old man with sclerosing perineurioma and describe the lesion’s ultrasound and MR features.

Angiomyxolipoma (vascular myxolipoma) is a very rare variant of lipoma. This tumor is characterized by mature adipose tissue mixed with myxoid stroma and vascular vessels. To date, nine cases have been reported, all of them occurring in adults. Herein, we report a unique case of a 9-year-old boy presenting with a solitary painful mass on the right medial thigh and illustrate the imaging characteristics of this rare tumor.