Search

Aim: To test the diagnostic performance of a deep learning-based system for the detection of clinically significant pulmonary nodules/masses on chest radiographs.Materials and Methods: Using a retrospective study of 100 patients (47 with clinically significant pulmonary nodules/masses and 53 control subjects without pulmonary nodules), two radiologists verified clinically significantly pulmonary nodules/masses according to chest computed tomography (CT) findings. A computer-aided diagnosis (CAD) software using a deep-learning approach was used to detect pulmonary nodules/masses to determine the diagnostic performance in four algorithms (heat map, abnormal probability, nodule probability, and mass probability).Results: A total of 100 cases were included in the analysis. Among the four algorithms, mass algorithm could achieve a 76.6% sensitivity (36/47, 11 false negative) and 88.68% specificity (47/53, six false-positive) in the detection of pulmonary nodules/masses at the optimal probability score cut-off of 0.2884. Compared to the other three algorithms, mass probability algorithm had best predictive ability for pulmonary nodule/mass detection at the optimal probability score cut-off of 0.2884 (AUCMass: 0.916 versus AUCHeat map: 0.682, p<0.001; AUCMass: 0.916 versus AUCAbnormal: 0.810, p=0.002; AUCMass: 0.916 versus AUCNodule: 0.813, p=0.014).Conclusion: In conclusion, the deep-learning based computer-aided diagnosis system will likely play a vital role in the early detection and diagnosis of pulmonary nodules/masses on chest radiographs. In future applications, these algorithms could support triage workflow via double reading to improve sensitivity and specificity during the diagnostic process. [ABSTRACT FROM AUTHOR]

LIANG C.-H., YANG C.-Y., LU K.-C., CHU P., CHEN C.-H., CHANG Y.-S., O'BRIEN A.P., BLOOMER M. & CHOU K.-R. (2011) Factors affecting peritoneal dialysis selection in Taiwanese patients with chronic kidney disease. International Nursing Review 58, 463-469 Background: Taiwan has the highest incidence and prevalence of end-stage renal disease (ESRD) in the world with 55 499 ESRD patients on long-term dialysis. Nevertheless, 90.96% of these patients are managed on maintenance haemodialysis (HD), with only 9.03% enrolled in a peritoneal dialysis (PD) programme. Aim: The study aim was to identify the factors affecting Taiwanese patient's selection of PD in preference to HD for chronic kidney disease. Methods: A cross-sectional research design was utilized with 130 chronic renal failure (CRF) patients purposively selected from outpatient nephrology clinics at four separate Taiwan hospitals. Logistic regression was used to identify the main factors affecting the patient's choice of dialysis type. Results: Single-factor logistic regression found significant differences in opinion related to age, education level, occupation type, disease characteristics, lifestyle modifications, self-care ability, know-how of dialysis modality, security considerations and findings related to the decisions made by medical personnel ( P < 0.05). Moreover, multinomial logistic regression after adjustment for interfering variables found that self-care ability and dialysis modality know-how were the two main factors affecting the person's selection of dialysis type. Conclusions: Self-care ability and the person's knowledge of the different types of dialysis modality and how they function were the major determinants for selection of dialysis type in Taiwan based on the results from this study. The results indicate that the education of CRF patients about the types of dialysis available is essential to enable them to understand the benefits or limitations of both types of dialysis. [ABSTRACT FROM AUTHOR]