Deep learning-based diagnosis of osteoblastic bone metastases and bone islands in computed tomograph images: a multicenter diagnostic study.

OBJECTIVE: To develop and validate a deep learning (DL) model based on CT for differentiating bone islands and osteoblastic bone metastases. MATERIALS AND METHODS: The patients with sclerosing bone lesions (SBLs) were retrospectively included in three hospitals. The images from site 1 were randomly assigned to the training (70%) and intrinsic verification (10%) datasets for developing the two-dimensional (2D) DL model (single-slice input) and "2.5-dimensional" (2.5D) DL model (three-slice input) and to the internal validation dataset (20%) for evaluating the performance of both models. The diagnostic performance was evaluated using the internal validation set from site 1 and additional external validation datasets from site 2 and site 3. And statistically analyze the performance of 2D and 2.5D DL models. RESULTS: In total, 1918 SBLs in 728 patients in site 1, 122 SBLs in 71 patients in site 2, and 71 SBLs in 47 patients in site 3 were used to develop and test the 2D and 2.5D DL models. The best performance was obtained using the 2.5D DL model, which achieved an AUC of 0.996 (95% confidence interval [CI], 0.995-0.996), 0.958 (95% CI, 0.958-0.960), and 0.952 (95% CI, 0.951-0.953) and accuracies of 0.950, 0.902, and 0.863 for the internal validation set, the external validation set from site 2 and site 3, respectively. CONCLUSION: A DL model based on a three-slice CT image input (2.5D DL model) can improve the prediction of osteoblastic bone metastases, which can facilitate clinical decision-making. KEY POINTS: • This study investigated the value of deep learning models in identifying bone islands and osteoblastic bone metastases. • Three-slice CT image input (2.5D DL model) outweighed the 2D model in the classification of sclerosing bone lesions. • The 2.5D deep learning model showed excellent performance using the internal (AUC, 0.996) and two external (AUC, 0.958; AUC, 0.952) validation sets.

Deep learning-based artificial intelligence model for classification of vertebral compression fractures: A multicenter diagnostic study.

Objective: To develop and validate an artificial intelligence diagnostic system based on X-ray imaging data for diagnosing vertebral compression fractures (VCFs). Methods: In total, 1904 patients who underwent X-ray at four independent hospitals were retrospectively (n=1847) and prospectively (n=57) enrolled. The participants were separated into a development cohort, a prospective test cohort and three external test cohorts. The proposed model used a transfer learning method based on the ResNet-18 architecture. The diagnostic performance of the model was evaluated using receiver operating characteristic curve (ROC) analysis and validated using a prospective validation set and three external sets. The performance of the model was compared with three degrees of musculoskeletal expertise: expert, competent, and trainee. Results: The diagnostic accuracy for identifying compression fractures was 0.850 in the testing set, 0.829 in the prospective set, and ranged from 0.757 to 0.832 in the three external validation sets. In the human and deep learning (DL) collaboration dataset, the area under the ROC curves(AUCs) in acute, chronic, and pathological compression fractures were as follows: 0.780, 0.809, 0.734 for the DL model; 0.573, 0.618, 0.541 for the trainee radiologist; 0.701, 0.782, 0.665 for the competent radiologist; 0.707,0.732, 0.667 for the expert radiologist; 0.722, 0.744, 0.610 for the DL and trainee; 0.767, 0.779, 0.729 for the DL and competent; 0.801, 0.825, 0.751 for the DL and expert radiologist. Conclusions: Our study offers a high-accuracy multi-class deep learning model which could assist community-based hospitals in improving the diagnostic accuracy of VCFs.

Diagnostic Performance of Diffusion-Weighted Imaging for Differentiating Malignant From Benign Intraductal Papillary Mucinous Neoplasms of the Pancreas: A Systematic Review and Meta-Analysis.

OBJECTIVES: To assess the diagnostic accuracy of diffusion-weighted imaging (DWI) in predicting the malignant potential in patients with intraductal papillary mucinous neoplasms (IPMNs) of the pancreas. METHODS: A systematic search of articles investigating the diagnostic performance of DWI for prediction of malignant potential in IPMNs was conducted from PubMed, Embase, and Web of Science from January 1997 to 10 February 2020. QUADAS-2 tool was used to evaluate the study quality. Pooled sensitivity, specificity, diagnostic odds ratio (DOR), positive likelihood ratios (PLR), negative likelihood ratios (NLR), and their 95% confidence intervals (CIs) were calculated. The summary receiver operating characteristic (SROC) curve was then plotted, and meta-regression was also performed to explore the heterogeneity. RESULTS: Five articles with 307 patients were included. The pooled sensitivity and specificity of DWI were 0.74 (95% CI: 0.65, 0.82) and 0.94 (95% CI: 0.78, 0.99), in evaluating the malignant potential of IPMNs. The PLR was 13.5 (95% CI: 3.1, 58.7), the NLR was 0.27 (95% CI: 0.20, 0.37), and DOR was 50.0 (95% CI: 11.0, 224.0). The area under the curve (AUC) of SROC curve was 0.84 (95% CI: 0.80, 0.87). The meta-regression showed that the slice thickness of DWI (p = 0.02) and DWI parameter (p= 0.01) were significant factors affecting the heterogeneity. CONCLUSIONS: DWI is an effective modality for the differential diagnosis between benign and malignant IPMNs. The slice thickness of DWI and DWI parameter were the main factors influencing diagnostic specificity.

Regional Homogeneity and Multivariate Pattern Analysis of Cervical Spondylosis Neck Pain and the Modulation Effect of Treatment.

Objects: We investigated brain functional alteration in patients with chronic cervical spondylosis neck pain (CSNP) compared to healthy controls (HCs) and the effect of intervention. Methods: 104 CSNP patients and 96 matched HCs were recruited. Patients received 4 weeks of treatment. Resting-state fMRI and Northwick Park Neck Pain Questionnaire (NPQ) were collected before and after treatment. Resting state regional homogeneity (rs-ReHo) and multivariate pattern analysis (MVPA) were applied to (1) investigate rs-ReHo differences between CSNP patients and controls and the effect of longitudinal treatment and (2) classify CSNP patients from HCs and predict clinical outcomes before treatment using MVPA. Results: We found that (1) CSNP patients showed decreased rs-ReHo in the left sensorimotor cortex and right temporo-parietal junction (rTPJ), and rs-ReHo at the rTPJ significantly increased after treatment; (2) rs-ReHo at rTPJ was associated with NPQ at baseline, and pre- and post-treatment rs-ReHo changes at rTPJ were associated with NPQ changes in CSNP patients; and (3) MVPA could discriminate CSNP patients from HCs with 72% accuracy and predict clinical outcomes with a mean absolute error of 19.6%. Conclusion: CSNP patients are associated with dysfunction of the rTPJ and sensorimotor area. Significance: rTPJ plays on important role in the pathophysiology and development of CSNP.

[MRI pain matrix regional homogeneity in cervical spondylosis of neck type treated with acupuncture at multiple acupoints].

OBJECTIVE: To observe the impacts on pain matrix (PM) brain area in the patients of cervical spondylosis of neck type treated with acupuncture at single point and the multiple points. METHODS: Forty-nine patients of cervical spondylosis of neck type were randomized into a single-point group (25 cases) and a multiple-point group (24 cases), and treated with acupuncture at Bailao (EX-HN 15) singly or Bailao (EX-HN 15) and Hegu (LI 4) in combination correspondingly. At the same time, 19 healthy people were selected as a control group. The resting state functional magnetic resonance imaging (fMRI) was conducted in each group before and after treatment. The changes in the regional homogeneity (ReHo) of brain area PM were analyzed in terms of the different therapeutic programs. The relevant analysis was on the scores of the Northwick Park neck pain questionnaire (NPQ) and short form 36 questionnaire (SF-36) for life quality. RESULTS: Compared with the control group, ReHo value was increased in supplementary motor area (SMA) of PM in the patients, of cervical spondylosis of neck type. In the single-point group, after treatment, ReHo value was reduced in the bilateral medial superior frontal gyri of patients. In the multiple-point group, ReHo values were reduced in the left medial superior frontal gyrus and right SMA in PM area after treatment. In the single-point group, ReHo value in each brain area of PM was not significantly correlated with NPQ and SF-36 scores. In the multiple-point group, the changes of ReHo value in superior frontal gyrus were positively correlated with those of NPQ scores. CONCLUSION: Considering the clinical efficacy of acupunctrue for cervical spondylosis of neck type, the overall result in the multiple-point group is better than that in the single-point group. It is deduced that the advantages of the therapeutic program in the multiple-point group is relevant with the cooperative integration of the stimulation at multiple points in cerebral analgesic center.