Machine learning combined with radiomics and deep learning features extracted from CT images: a novel AI model to distinguish benign from malignant ovarian tumors.

BACKGROUND: To develop an artificial intelligence (AI) model with radiomics and deep learning (DL) features extracted from CT images to distinguish benign from malignant ovarian tumors. METHODS: We enrolled 149 patients with pathologically confirmed ovarian tumors. A total of 185 tumors were included and divided into training and testing sets in a 7:3 ratio. All tumors were manually segmented from preoperative contrast-enhanced CT images. CT image features were extracted using radiomics and DL. Five models with different combinations of feature sets were built. Benign and malignant tumors were classified using machine learning (ML) classifiers. The model performance was compared with five radiologists on the testing set. RESULTS:  Among the five models, the best performing model is the ensemble model with a combination of radiomics, DL, and clinical feature sets. The model achieved an accuracy of 82%, specificity of 89% and sensitivity of 68%. Compared with junior radiologists averaged results, the model had a higher accuracy (82% vs 66%) and specificity (89% vs 65%) with comparable sensitivity (68% vs 67%). With the assistance of the model, the junior radiologists achieved a higher average accuracy (81% vs 66%), specificity (80% vs 65%), and sensitivity (82% vs 67%), approaching to the performance of senior radiologists. CONCLUSIONS:  We developed a CT-based AI model that can differentiate benign and malignant ovarian tumors with high accuracy and specificity. This model significantly improved the performance of less-experienced radiologists in ovarian tumor assessment, and may potentially guide gynecologists to provide better therapeutic strategies for these patients.

Spontaneous bilateral perirenal hemorrhage following prolonged fever: an uncommon presentation of polyarteritis nodosa.

A 68-year-old man presented with a spontaneous bilateral perirenal hemorrhage following a 2-month fever of unknown origin. A renal biopsy for a pathologic diagnosis seemed very risky because of the patient's bilateral perirenal hemorrhage. Therefore, we diagnosed polyarteritis nodosa using an abdominal computed tomography scan, a renal angiogram, and American College of Rheumatology criteria. The patient's multiple symptoms then responded well to the prescribed immunosuppressive regimen. This case is an uncommon presentation of polyarteritis nodosa with fever of unknown origin before a spontaneous bilateral perirenal hemorrhage.

Reverse epidemiology of hypertension-mortality associations in hemodialysis patients: a long-term population-based study.

BACKGROUND: Although hypertension (HTN) is a predictor of mortality, recent data have questioned the link between baseline HTN and mortality in incident hemodialysis (HD) patients. We used Taiwan's National Health Insurance claim data (NHRI-NHIRD-99182) to investigate the association. METHODS: In 1999, this longitudinal cohort study enrolled 5752 new HD patients. Follow-up began from the initiation of HD until death, the end of HD, or the end of 2008. A Kaplan-Meier survival analysis was done. Cox proportional hazard analysis was used to identify the risk factors for mortality. RESULTS: The prevalence of baseline HTN was 75.47%. Patients with HTN had a higher prevalence of diabetic mellitus (DM) and cardiovascular diseases. The 1-, 5-, and 9-year cumulative survival rates were 95.5, 63.7 and 41.8% in patients with HTN, and 95.5, 71.0, and 52.0% in those without HTN (log-rank test: P <0.001). Multivariate analysis showed that patients with baseline HTN may have a higher survival rate (hazard ratio (HR) 0.901, 95% confidence interval (CI): 0.819-0.992). After stratification by age and DM, only elderly (≥65) patients without DM had a significantly higher survival rate (HR 0.769, 95% CI: 0.637-0.927). HTN predicts lower mortality with increasing age in patients with congestive heart failure (CHF) or coronary artery disease (CAD). CONCLUSIONS: There is a reverse (counterintuitive) association between baseline HTN and mortality in elderly HD patients without DM and a clear tendency for a reverse association with increasing age in patients with CHF or CAD. Further study of the association between HTN and mortality in older HD patients may be warranted.