Using radiomic features of lumbar spine CT images to differentiate osteoporosis from normal bone density.

OBJECTIVE: This study aimed to develop a predictive model to detect osteoporosis using radiomic features from lumbar spine computed tomography (CT) images. METHODS: A total of 133 patients were included in this retrospective study, 41 men and 92 women, with a mean age of 65.45 ± 9.82 years (range: 31-94 years); 53 had normal bone mineral density, 32 osteopenia, and 48 osteoporosis. For each patient, the L1-L4 vertebrae on the CT images were automatically segmented using SenseCare and defined as regions of interest (ROIs). In total, 1,197 radiomic features were extracted from these ROIs using PyRadiomics. The most significant features were selected using logistic regression and Pearson correlation coefficient matrices. Using these features, we constructed three linear classification models based on the random forest (RF), support vector machine (SVM), and K-nearest neighbor (KNN) algorithms, respectively. The training and test sets were repeatedly selected using fivefold cross-validation. The model performance was evaluated using the area under the receiver operator characteristic curve (AUC) and confusion matrix. RESULTS: The classification model based on RF had the highest performance, with an AUC of 0.994 (95% confidence interval [CI]: 0.979-1.00) for differentiating normal BMD and osteoporosis, 0.866 (95% CI: 0.779-0.954) for osteopenia versus osteoporosis, and 0.940 (95% CI: 0.891-0.989) for normal BMD versus osteopenia. CONCLUSIONS: The excellent performance of this radiomic model indicates that lumbar spine CT images can effectively be used to identify osteoporosis and as a tool for opportunistic osteoporosis screening.

[Assessment of normal and abnormal tongue tissues with MR diffusion-weighted imaging].

PURPOSE: The aim of this study was to evaluate the MR-DWI findings of the normal and abnormal tongue tissues, and to determine the potential role of apparent diffusion coefficient (ADC) value obtained from different b values in the accurately diagnosing lesions arising from the tongue. METHODS: MR-DWI was performed in 15 healthy volunteers and 79 patients with tongue lesions, respectively. All the tongue lesions were pathologically proved (19 benign lesions and 60 malignant tumors). Two ADC values from b values (500 and 1000 s/mm²) in the 15 volunteers and 79 lesions were used for comparison. The diversities of ADC values between the normal and abnormal tongues, and the benign lesions and malignant tumors of tongues were statistically analyzed. The data was subjected to SPSS10.0 software package for t test. RESULTS: (1)There was significant difference between the volunteer's tongue and the abnormal tongues(P<0.01), and between the benign lesions and the malignant tumors of tongues (P<0.05). (2)The mean ADC value of the benign lesions of tongues was significantly higher than that of the surrounding tongue tissues and volunteer's tongues (P<0.05). (3)The mean ADC value of the malignant tumors of tongues was higher than that of the volunteer's tongues, but no difference was found between the malignant tumors and its surrounding tongue tissues. CONCLUSION: MR-DWI might be considered as a valuable imaging index for the discrimination of normal tongue from abnormal tongue.

Rapid prototyped PGA/PLA scaffolds in the reconstruction of mandibular condyle bone defects.

BACKGROUND: Craniomaxillofacial bone defects are currently reconstructed by using computer-aided design and manufacturing (CAD/CAM) processes. We have developed a novel digital medical support system that enables us to custom-make scaffolds to repair craniomaxillofacial bone defects using three-dimensional computed tomographic (CT) images and a rapid-prototyping method. METHODS: We created positive molds using CT data, CAD/CAM and a rapid prototyping method using 3D printing. Custom-made poly (glycolic acid) (PGA) and polymers poly (lactic acid) (PLA) scaffolds were prefabricated by a positive-negative mold interchange technique. A laser scanning system was used to evaluate the accuracy of the PGA/PLA scaffold. Bone marrow stem cells were incubated with the scaffold to assess biocompatibility. RESULTS: The mean error was <0.3 mm and confidence was >or=95% when the error was <1 mm. Results from in vitro cell culture demonstrated that the PGA/PLA scaffold had excellent cellular compatibility. CONCLUSIONS: This pilot study suggests that custom-made PGA/PLA scaffolds infiltrated with bone marrow stem cells may be effective for future treatment of craniomaxillofacial bone injuries.

Computer-assisted orthopedic diagnosis and preoperative planning system based on the integrated electronic patient record.

Computer-assisted orthopedic diagnosis and preoperative planning have been recognized as efficient tools to improve the accuracy of clinic diagnosis and surgical procedure. In orthopedic clinic, such practices are heavily relied on the patient-specific medical image data.