Dual energy X-ray absorptiometry (DXA) is widely used modality for measuring bone mineral density (BMD). DXA is used to measure the quantitative areal BMD of bone, but has the disadvantage of not reflecting the bone architecture. To compensate for this disadvantage, trabecular bone score (TBS), a qualitative parameter of trabecular microarchitecture, is used. Meanwhile, there have been recent attempts to diagnose osteoporosis using the Hounsfield unit (HU) from CT and MR-based proton density fat fraction (PDFF) measurements. In our study, we aimed to find out the correlation between HU/PDFF and BMD/TBS, and whether osteoporosis can be diagnosed through HU/PDFF. Our study revealed that the HU value showed a moderate to good positive correlation with BMD and TBS. PDFF showed a fair negative correlation with BMD and TBS. In diagnosing osteopenia and osteoporosis, the HU value showed good performance, whereas the PDFF showed fair performance. In conclusion, both HU values and PDFF can play a role in predicting BMD and TBS. Both HU values and PDFF can be used to predict osteoporosis; further, CT is expected to show better results.

Background/Objectives: This study investigated the diagnostic capabilities of two AI-based tools, M4CXR (research-only version) and ChatGPT-4o, in chest X-ray interpretation. M4CXR is a specialized cloud-based system using advanced large language models (LLMs) for generating comprehensive radiology reports, while ChatGPT, built on the GPT-4 architecture, offers potential in settings with limited radiological expertise. Methods: This study evaluated 826 anonymized chest X-ray images from Inha University Hospital. Two experienced radiologists independently assessed the performance of M4CXR and ChatGPT across multiple diagnostic parameters. The evaluation focused on diagnostic accuracy, false findings, location accuracy, count accuracy, and the presence of hallucinations. Interobserver agreement was quantified using Cohen’s kappa coefficient. Results: M4CXR consistently demonstrated superior performance compared to ChatGPT across all evaluation metrics. For diagnostic accuracy, M4CXR achieved approximately 60–62% acceptability ratings compared to ChatGPT’s 42–45%. Both systems showed high interobserver agreement rates, with M4CXR generally displaying stronger consistency. Notably, M4CXR showed better performance in anatomical localization (76–77.5% accuracy) compared to ChatGPT (36–36.5%) and demonstrated fewer instances of hallucination. Conclusions: The findings highlight the complementary potential of these AI technologies in medical diagnostics. While M4CXR shows stronger performance in specialized radiological analysis, the integration of both systems could potentially optimize diagnostic workflows. This study emphasizes the role of AI in augmenting human expertise rather than replacing it, suggesting that a combined approach leveraging both AI capabilities and clinical judgment could enhance patient care outcomes.

Background: Knee osteoarthritis (OA) is a prevalent degenerative joint disease significantly impacting global health. Early and accurate diagnosis is crucial for effective management, but traditional methods often rely on subjective assessments. This study evaluates the efficacy of a deep learning model implemented through a no-code AI platform for diagnosing and grading knee OA from plain radiographs. Methods: We utilized the Osteoarthritis Initiative (OAI) dataset, comprising knee X-ray data from 1526 patients. The data were split into training (47.0%), validation (26.5%), and test (26.5%) sets. We employed a ResNet101 model on the DEEP:PHI no-code AI platform for image analysis. The model was trained to classify knee OA into five grades (0–4) based on the Kellgren–Lawrence scale. Results: Our AI model demonstrated high accuracy in distinguishing between different OA grades, with particular strength in early-stage detection. The model achieved optimal performance at 20 epochs, suggesting efficient learning dynamics. Grad-CAM visualizations were used to enhance the interpretability of the model’s decision-making process. Conclusions: This study demonstrates the potential of AI, implemented through a no-code platform, to accurately diagnose and grade knee OA from radiographs. The use of a no-code AI platform such as DEEP:PHI represents a step towards democratizing AI in healthcare, enabling the rapid development and deployment of sophisticated medical AI applications without extensive coding expertise. This approach could significantly enhance the early detection and management of knee OA, potentially improving patient outcomes and streamlining clinical workflows.

Background: The morphology of musculoskeletal dedifferentiated liposarcoma was previously reported as well-defined non-lipomatous masses juxtaposed with fatty tumors. Purpose: To establish a new spectrum of magnetic resonance imaging (MRI) findings for dedifferentiated liposarcoma according to the quantity and distribution of the non-fatty component in the tumor. Material and Methods: This study consisted of a retrospective review of MRI of 14 patients with a total of 18 histopathologically proven dedifferentiated liposarcoma lesions in the musculoskeletal area. Tumors were classified into four categories (I–IV) according to MR features: I = a well-defined fatty mass and juxtaposed well-defined non-fatty mass; II = a non-fatty component within a predominant fatty mass; III = a focal fatty component within a large non-fatty mass; and IV = a non-fatty mass. Tumor size and depth were also analyzed. Results: The MR categorizations of the tumors were as follows: Category I, n = 3; Category II, n = 1; Category III, n = 7; and Category IV, n = 7. The mean tumor size was 11.9 cm (range = 5.0–22.2 cm). Most of the tumors showed a predominant non-fatty area and were deeply located at the intra- or intermuscular space. Conclusion: Dedifferentiated liposarcoma lesions showed a diverse spectrum of MRI findings. Although the presence of a non-fatty region within or adjacent to a well-defined fatty mass can suggest dedifferentiated liposarcoma, non-fatty masses without a fatty component were frequent on MRI.