METHODS: We retrospectively collected CT scan data from 276 patients with pathologically confirmed primary bone tumors from 4 medical centers in Guangdong Province between January, 2010 and August, 2021. A convolutional neural network (CNN) was employed as the deep learning architecture. The optimal baseline deep learning model (R-Net) was determined through transfer learning, and an optimized model (S-Net) was obtained through algorithmic improvements. Multivariate logistic regression analysis was used to screen the clinical features such as sex, age, mineralization location, and pathological fractures, which were then connected with the imaging features to construct the deep learning fusion model (SC-Net). The diagnostic performance of the SC-Net model and machine learning models were compared with radiologists' diagnoses, and their classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) and F1 score. RESULTS: In the external test set, the fusion model (SC-Net) achieved the best performance with an AUC of 0.901 (95% CI: 0.803-1.00), an accuracy of 83.7% (95% CI: 69.3%-93.2%) and an F1 score of 0.857, and outperformed the S-Net model with an AUC of 0.818 (95% CI: 0.694-0.942), an accuracy of 76.7% (95% CI: 61.4%-88.2%), and an F1 score of 0.828. The overall classification performance of the fusion model (SC-Net) exceeded that of radiologists' diagnoses. CONCLUSIONS The deep learning fusion model based on multi-center CT images and clinical features is capable of accurate classification of osseous and chondroid matrix mineralization and may potentially improve the accuracy of clinical diagnoses of osteogenic versus chondrogenic primary bone tumors.
Humans ; Deep Learning ; Bone Neoplasms/diagnostic imaging* ; Retrospective Studies ; Tomography, X-Ray Computed/methods* ; Neural Networks, Computer ; Male ; Female ; ROC Curve ; Algorithms

Objective: To investigate the clinical, imaging, histological, and molecular features and the differential diagnosis of radiation-associated sarcomas of bone and soft tissue. Methods: Forty-six cases of radiation-associated sarcomas of the bone and soft tissue in Beijing Jishuitan Hospital from January 2010 to January 2022 were retrospectively analyzed; and the imaging, histological features and immunophenotype were examined. Results: There were 33 females and 13 males, aged from 18 to 74 years, with a mean of 52 years. The most common site of radiation-associated sarcomas were the limbs and spine (15 cases), followed by the chest (9 cases). The primary diseases included epithelial tumors (15 breast cancer, 6 cervical cancer, and 5 bowel cancer), hematolymphoid tumors, bone and soft tissue tumors and infectious lesions. The latent period of radiation-associated sarcomas ranged from 2-22 years, with an average of 11.6 years. Histopathologically, the morphology was divergent from the primary tumor. The most common malignant tumor type was undifferentiated sarcoma (22 cases), followed by osteosarcoma (16 cases). The immunophenotype of radiation-related sarcoma was almost the same as the corresponding soft tissue sarcoma. Conclusions: Radiation-induced sarcoma has a wide range of primary tumor types and its imaging, morphology and immunohistochemical features are similar to those of the primary sarcoma of bone and soft tissue. Clinical correlation is often recommended for the differential diagnosis.
Male ; Female ; Humans ; Retrospective Studies ; Sarcoma/pathology* ; Osteosarcoma/diagnostic imaging* ; Soft Tissue Neoplasms/pathology* ; Bone Neoplasms/pathology*

Bone Neoplasms/diagnostic imaging* ; Hemangioendothelioma/surgery* ; Hemangioendothelioma, Epithelioid/surgery* ; Humans ; Precancerous Conditions

Bone and Bones/diagnostic imaging* ; Breast/diagnostic imaging* ; Breast Neoplasms/diagnostic imaging* ; Female ; Humans

Bone Neoplasms/therapy* ; Humans ; Temporal Bone/diagnostic imaging*

The diagnosis of bone metastasis of prostate cancer (PC) is of great significance to the treatment and prognosis of patients with PC.Bone scan is the most commonly used in the early diagnosis of bone metastasis, but its specificity is low and there is a high false positive.In recent years, with the in-depth study of the application of CT, MRI, emission computed tomography (ECT), positron emission computed tomography/computed tomography (PET/CT) and deep learning algorithm-convolutional neural networks (CNN) in the diagnosis of bone metastasis, the combined application of various auxiliary parameters in the diagnosis of bone metastasis has significantly been improved. The therapeutic effect of PC patients with bone metastasis can also be evaluated, which is expected to achieve the treatment of bone metastasis as well as diagnosis. By systematically expounding the research progress of the above-mentioned techniques in the diagnosis of bone metastasis, it can provide clinicians with new methods for the diagnosis of bone metastasis and improve the diagnostic efficiency for bone metastasis.
Bone Marrow Diseases ; Bone Neoplasms/diagnostic imaging* ; Humans ; Magnetic Resonance Imaging ; Male ; Positron Emission Tomography Computed Tomography ; Prostatic Neoplasms/diagnostic imaging*

BACKGROUND: Hibernoma is a rare benign tumor of adults that is composed of multivacuolated adipocytes resembling brown fat cells. Hibernoma typically occurs in soft tissue, and intraosseous examples are very rare. Intraosseous hibernomas can radiologically mimic metastatic carcinoma and other tumorous conditions. METHODS: To collect the intraosseous hibernomas, we searched the pathologic database and reviewed the hematoxylin and eosin (H&E)–stained slides of bone biopsy samples performed to differentiate radiologically abnormal bone lesions from 2006 to 2016. A total of six intraosseous hibernoma cases were collected, and clinical and radiological information was verified from electronic medical records. H&E slide review and immunohistochemical staining for CD68, pan-cytokeratin, and S-100 protein were performed. RESULTS: Magnetic resonance imaging of intraosseous hibernomas showed low signal intensity with slightly hyperintense foci on T1 and intermediate to high signal intensity on T2 weighted images. Intraosseous hibernomas appeared as heterogeneous sclerotic lesions with trabecular thickening on computed tomography scans and revealed mild hypermetabolism on positron emission tomography scans. Histopathologically, the bone marrow space was replaced by sheets of multivacuolated, foamy adipocytes resembling brown fat cells, without destruction of bone trabeculae. In immunohistochemical analysis, the tumor cells were negative for CD68 and pan-cytokeratin and positive for S-100 protein. CONCLUSIONS: Intraosseous hibernoma is very rare. This tumor can be overlooked due to its rarity and resemblance to bone marrow fat. Pathologists need to be aware of this entity to avoid misdiagnosis of this rare lesion.
Adipocytes ; Adipocytes, Brown ; Adult ; Biopsy ; Bone Marrow ; Bone Neoplasms ; Diagnostic Errors ; Electronic Health Records ; Eosine Yellowish-(YS) ; Hematoxylin ; Humans ; Immunohistochemistry ; Lipoma* ; Magnetic Resonance Imaging ; Pathology ; Positron-Emission Tomography ; S100 Proteins

INTRODUCTIONA subungual exostosis (SE) is a bony overgrowth that is permanently attached to the tip of the distal phalanx. Its pathology differs from osteocartilaginous exostoses in that it mainly involves the overgrowth of normal bone, which may present beneath the toenail or on the sides of the toe. This retrospective study aimed to report the results of surgical treatment when the diagnosis of SE was delayed; the condition was initially considered to be another pathology affecting a different nail or the terminal toe.

METHODSA total of 17 patients (12 female, five male) were included in the study. All surgical resections were performed by the same surgeon using the same surgical technique, with the patient under digital anaesthesia. The patients were evaluated pre- and postoperatively (on Weeks 1 and 6, the first year, and the last follow-up visit) using the American Orthopaedic Foot and Ankle Society questionnaire and the Visual Analogue Scale score.

RESULTSThe patients underwent surgery for SE removal between December 2009 and October 2012. Their mean age was 21.3 ± 4.4 (range 14-29) years and the mean follow-up period was 27.1 ± 7.8 (range 18-45) months. Clinical or radiological recurrence was not observed in any of the patients during the follow-up period. Four patients had superficial infections, which were treated using appropriate antibiotic therapies.

CONCLUSIONAs SE is an uncommon benign lesion, its diagnosis may be delayed. Radiography may be useful in obtaining a differential diagnosis.

Adolescent ; Adult ; Bone Neoplasms ; diagnostic imaging ; surgery ; Cartilage ; diagnostic imaging ; surgery ; Diagnosis, Differential ; Exostoses ; diagnostic imaging ; surgery ; Female ; Humans ; Male ; Middle Aged ; Nail Diseases ; diagnostic imaging ; surgery ; Nails ; surgery ; Orthopedics ; methods ; Pain Measurement ; Postoperative Period ; Recurrence ; Retrospective Studies ; Surveys and Questionnaires ; Young Adult

Adult ; Bone Neoplasms ; diagnosis ; diagnostic imaging ; pathology ; Diagnosis, Differential ; Diaphyses ; diagnostic imaging ; pathology ; Humans ; Knee Joint ; diagnostic imaging ; pathology ; Lipoma ; diagnosis ; diagnostic imaging ; pathology ; Magnetic Resonance Imaging ; Male ; Radiography ; Tibia ; diagnostic imaging ; pathology

Bone Neoplasms ; diagnostic imaging ; pathology ; Female ; Humans ; Middle Aged ; Osteoma ; diagnostic imaging ; pathology ; Palate ; diagnostic imaging ; pathology ; Radiography