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.

Refracture of the cemented vertebrae after percutaneous vertebroplasty: risk factors and imaging findings.

BACKGROUND: To determine the related imaging findings and risk factors to refracture of the cemented vertebrae after percutaneous vertebroplasty (PVP) treatment. METHODS: Patients who were treated with PVP for single vertebral compression fractures (VCFs) and met this study's inclusion criteria were retrospectively reviewed from January 2012 to January 2019. The follow-up period was at least 2 years. Forty-eight patients with refracture of the cemented vertebrae and 45 non-refractured patients were included. The following variates were reviewed: age, sex, fracture location, bone mineral density (BMD), intravertebral cleft (IVC), kyphotic angle (KA), wedge angle, endplate cortical disruption, cement volume, surgical approach, non-PMMA-endplate-contact (NPEC), cement leakage, other vertebral fractures, reduction rate (RR), and reduction angle (RA). Multiple logistic regression modeling was used to identify the independent risk factors of refracture. RESULTS: Refracture was found in 48 (51.6%) patients. Four risk factors, including IVC (P = 0.005), endplate cortical disruption (P = 0.037), larger RR (P = 0.007), and NPEC (P = 0.006) were found to be significant independent risk factors for refracture. CONCLUSIONS: Patients with IVC or larger RR, NPEC, or endplate cortical disruption have a high risk of refracture in the cemented vertebrae after PVP.

Diagnostic performance of whole-lesion apparent diffusion coefficient histogram analysis metrics for differentiating benign and malignant breast lesions: a systematic review and diagnostic meta-analysis.

BACKGROUND: Although whole-lesion apparent diffusion coefficient (ADC) histogram has been increasingly used for breast lesions, it has not been routinely used in clinical practice as an emergent promising imaging tool. PURPOSE: To evaluate the performance of whole-lesion ADC histogram analysis metrics for differentiating benign and malignant breast lesions. MATERIAL AND METHODS: A systematic PubMed/EMBASE/Cochrane electronic database search was performed for original diagnostic studies from 1 January 1970 to 2 January 2019. Summary estimates of diagnostic accuracy were generated and meta-regression was performed to explore sources of heterogeneity according to study and magnetic resonance imaging characteristics. RESULTS: Five original articles involving 493 patients were included in the meta-analysis. The pooled sensitivity and specificity of whole-lesion ADC histogram analysis were 0.85 (95% confidence interval [CI] = 0.81-0.89) and 0.79 (95% CI = 0.72-0.84) for distinguishing benign and malignant breast lesions, respectively. The area under the curve (AUC) was 0.9178. No publication bias was detected (P = 0.51). In subgroup analysis, the summary sensitivity and specificity of 50th percentile ADC value were 0.81 (95% CI = 0.71-0.88) and 0.86 (95% CI = 0.74-0.94), respectively. Meta-regression analysis indicated no covariates were sources of heterogeneity (P > 0.05). CONCLUSION: Whole-lesion ADC histogram analysis demonstrated good diagnostic performance for differentiating between benign and malignant breast lesions, with 50th percentile ADC value showing higher diagnostic accuracy than other histogram parameters. Given the limited number of studies included in the analysis, the findings from our meta-analysis will need further confirmation in future research.