Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model.

OBJECTIVE: To develop and evaluate a deep learning model based on chest CT that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images, and explore the feasibility and effectiveness of the model based on the lumbar 1 vertebral body alone. MATERIALS AND METHODS: The chest CT images of 1048 health check subjects from January 2021 to June were retrospectively collected as the internal dataset (the segmentation model: 548 for training, 100 for tuning and 400 for test. The classification model: 530 for training, 100 for validation and 418 for test set). The subjects were divided into three categories according to the quantitative CT measurements, namely, normal, osteopenia and osteoporosis. First, a deep learning-based segmentation model was constructed, and the dice similarity coefficient(DSC) was used to compare the consistency between the model and manual labelling. Then, two classification models were established, namely, (i) model 1 (fusion feature construction of lumbar vertebral bodies 1 and 2) and (ii) model 2 (feature construction of lumbar 1 alone). Receiver operating characteristic curves were used to evaluate the diagnostic efficacy of the models, and the Delong test was used to compare the areas under the curve. RESULTS: When the number of images in the training set was 300, the DSC value was 0.951 ± 0.030 in the test set. The results showed that the model 1 diagnosing normal, osteopenia and osteoporosis achieved an AUC of 0.990, 0.952 and 0.980; the model 2 diagnosing normal, osteopenia and osteoporosis achieved an AUC of 0.983, 0.940 and 0.978. The Delong test showed that there was no significant difference in area under the curve (AUC) values between the osteopenia group and osteoporosis group (P = 0.210, 0.546), while the AUC value of normal model 2 was higher than that of model 1 (0.990 vs. 0.983, P = 0.033). CONCLUSION: This study proposed a chest CT deep learning model that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images. We further constructed the comparable model based on the lumbar 1 vertebra alone which can shorten the scan length, reduce the radiation dose received by patients, and reduce the training cost of technologists.

Measurement of myocardial extracellular volume fraction in patients with heart failure with preserved ejection fraction using dual-energy computed tomography.

OBJECTIVES: To measure the myocardial extracellular volume (ECV) in patients with heart failure with preserved ejection fraction (HFpEF) using dual-energy computed tomography with late iodine enhancement (LIE-DECT) and to evaluate the relationship between ECV and risk of HFpEF and cardiac structure and function. METHODS: A total of 112 consecutive patients with HFpEF and 80 consecutive subjects without heart disease (control group) who underwent LIE-DECT were included. All patients were divided into ischaemic and non-ischaemic groups according to the LIE patterns detected using iodine maps. The ischaemic scar burden was calculated in the ischaemic HFpEF group. Iodine maps and haematocrit were used to measure ECV in the non-ischaemic HFpEF group and remote ECV of the non-scarred myocardium in the ischaemic HFpEF group, respectively. Cardiac structural and functional variables were collected. RESULTS: ECV in patients with non-ischaemic HFpEF (n = 77) and remote ECV in patients with ischaemic HFpEF (n = 35) were significantly higher than those in control subjects (p < 0.001). Multivariate logistic regression analysis revealed that after adjusting for age, sex, body mass index, smoking, and drinking, a higher ECV/remote ECV was still associated with non-ischaemic HFpEF and ischaemic HFpEF (p < 0.001). A positive correlation was established between ECV and cardiac structural and functional variables (p < 0.05) in all participants. Subgroup analysis showed that ECV/remote ECV and ischaemic scar burden positively correlated with heart failure classification in the HFpEF subgroup (p < 0.05). CONCLUSION: ECV/remote ECV elevation was significantly associated with non-ischaemic and ischaemic HFpEF. Remote ECV and LIE may have synergistic effects in the risk assessment of ischaemic HFpEF. KEY POINTS: • ECV/remote ECV elevation is associated not only with non-ischaemic HFpEF but also with ischaemic HFpEF. • ECV/remote ECV and ischaemic scar burden are correlated with cardiac structure and function.

Inter- and intraobserver agreement of ADC measurements of lung cancer in free breathing, breath-hold and respiratory triggered diffusion-weighted MRI.

OBJECTIVE: To prospectively evaluate the inter- and intraobserver agreement of apparent diffusion coefficient (ADC) measurements in free breathing, breath-hold, and respiratory triggered diffusion-weighted imaging (DWI) of lung cancer. METHODS: Twenty-two patients with lung cancer (tumor size >2cm) underwent DWIs (3.0T) in three imaging methods. Lesion ADCs were measured twice by both of the two independent observers and compared. RESULTS: No statistical significance was found among methods, though respiratory-triggered DWI tended to have higher ADCs than breath-hold DWI. Great inter- and intraobserver agreement was shown. CONCLUSION: ADCs had good inter- and intraobserver agreement in all three DWI methods.

A massive renal epithelioid angiomyolipoma with multiple metastatic lymph nodes.

A 47-year-old man presented with dull pain in the left upper abdomen for 1 year. Computed tomograph (CT) examination revealed a very large heterogeneously enhancing mass in the left kidney, measuring up to 28 cm. The mass was accompanied by several enlarged lymph nodes in the peri-aortic region. Radical nephrectomy was performed and pathologic evaluation revealed sheets of epithelioid cells and piecemeal necrosis consistent with malignant epithelioid angiomyolipoma (EAML) with regional lymph node metastases. The tumor cells were strongly positive for human melanosome-associated protein (HMB-45) on immunohistochemical staining. There was neither metastasis nor recurrence 2 years postoperatively. EAML is a rare tumor of mesenchymal tissue with potential for aggressive behavior. If this neoplasm is suspected based on CT features, EAML should be confirmed by pathology and immunohistochemistry.