Background Misdiagnosis of malignant musculoskeletal tumors may lead to the delay of intervention, resulting in amputation or death. Purpose To improve the diagnostic efficacy of musculoskeletal tumors by developing deep learning (DL) models based on contrast‐enhanced magnetic resonance imaging and to quantify the improvement in diagnostic performance obtained by using these models. Study type Retrospective. Population Three hundreds and four musculoskeletal tumors, including 212 malignant and 92 benign lesions, were randomized into the training (n = 180), validation (n = 62) and testing cohort (n = 62). Field strength/sequence A 3 T/T1‐weighted (T1‐w), T2‐weighted (T2‐w), diffusion‐weighted imaging (DWI), and contrast‐enhanced T1‐weighted (CET1‐w) images. Assessment Three DL models based, respectively, on the sagittal, coronal, and axial MR images were constructed to predict the malignancy of tumors. Blinded to the prediction results, a group of specialists made independent initial diagnoses for each patient by reading all image sequences. One month after the initial diagnoses, the same group of doctors made another round of diagnoses knowing the malignancy of each tumor predicted by the three models. The reference standard was the pathological diagnosis of malignancy. Statistical tests Sensitivity, specificity, and accuracy (all with 95% confidential intervals [CI]) corresponding to each diagnostic test were computed. Chi‐square tests were used to assess the differences in those parameters with and without DL models. A P value < 0.05 was considered statistically significant. Results The developed models significantly improved the diagnostic sensitivities of two oncologists by 0.15 (95% CI: 0.06–0.24) and 0.36 (95% CI: 0.24–0.28), one radiologist by 0.12 (95% CI: 0.04–0.20), and three of the four orthopedists, respectively, by 0.12 (95% CI: 0.04–0.20), 0.29 (95% CI: 0.18–0.40), and 0.23 (95% CI: 0.13–0.33), without impairing any of their diagnostic specificities (all P > 0.128). Data conclusion The DL models developed can significantly improve the performance of doctors with different training and experience in diagnosing musculoskeletal tumors. Evidence Level 3 Technical Efficacy Stage 2

Background A defective nutrient foramen in the fovea capitis femoris was hypothesized to reflect the blood circulation pattern of the femoral head, leading to insufficient blood supply and causing osteonecrosis of the femoral head. Methods Normal and necrotic femoral head specimens were collected. The necrotic femoral head group was divided into a non-traumatic and traumatic subgroup. 3D scanning was applied to read the number, the diameter, and the total cross-sectional area of the nutrient foramina in the fovea capitis femoris. Chi-squared tests and independent t-tests were used to detect any differences in the categorical and continuous demographic variables. Logistic regression models were used to estimate the odds ratio (OR) for non-traumatic and traumatic osteonecrosis in different characteristic comparisons. Results A total of 249 femoral head specimens were collected, including 100 normal femoral heads and 149 necrotic femoral heads. The necrotic femoral head group revealed a significantly higher percentage of no nutrient foramen (p < 0.001), a smaller total area of nutrient foramina (p < 0.001), a smaller mean area of nutrient foramina (p = 0.014), a lower maximum diameter of the nutrient foramen (p < 0.001), and a lower minimum diameter of the nutrient foramen (p < 0.001) than the normal femoral head group. The logistic regression model demonstrated an increasing number of nutrient foramina (crude OR, 0.51; p < 0.001), a larger total area of nutrient foramina (crude OR, 0.58; p < 0.001), a larger mean area of nutrient foramina (crude OR, 0.52; p = 0.023), a greater maximum diameter of the nutrient foramen (crude OR, 0.26; p < 0.001), and greater minimum diameter of the nutrient foramen (crude OR, 0.20; p < 0.001) significantly associated with reduced odds of osteonecrosis of the femoral head (ONFH). The necrotic femoral head group was further divided into 118 non-traumatic and 31 traumatic necrotic subgroups, and no significant difference was observed in any characteristics between them. Conclusions Characteristics of the nutrient foramen in the fovea capitis femoris showed a significant defect of necrotic than normal femoral heads, and significantly reduced odds were associated with the higher abundance of the nutrient foramen in ONFH. Therefore, the condition of the nutrient foramen might be the indicator of ONFH.

Bone tumors X-ray image segmentation is crucial for many medical image processing applications such as X-ray image enhancement, lesion diagnosis, etc. In this paper, we propose a new topological structure of u-net, named merged u-net, for bone tumors X-ray image segmentation. We attach a topdown merged branch to the vanilla encoder-decoder network, enhancing the hierarchical feature aggregation. In the merged path, a multi-feature aggregation block, named merged gate, is proposed for better localization of lesion area. According to the attention matrix, the proposed merged gate can generate a reconstructed feature that contains both low-level information and high-level information. Then we incorporate the reconstructed feature with the small scare feature cued with a local feature fusion method, achieving multi-scare feature aggregation. Additionally, we propose a new X-ray image dataset for bone tumors segmentation, which consists of 88 benign images and 217 malignant images, provided with corresponding segmentation masks. Experimental results demonstrate that the proposed merged u-net outperforms other u-net based medical segmentation methods on the proposed X-ray image dataset.