Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In Current medical imaging

BACKGROUND : The incidence rate of renal disease is high which can cause end-stage renal disease. Ultrasound is a commonly used imaging method, including conventional ultrasound, color ultrasound, elastography etc. Machine learning is a potential method which has been widely used in clinical.

OBJECTIVE : To compare the diagnostic performance of different ultrasonic image measurement parameters for kidney diseases, and to compare different machine learning methods with human-reading method.

METHODS : 94 patients with pathologically diagnosed renal diseases and 109 normal controls were included in this study. The patients were examined by conventional ultrasound, color ultrasound and shear wave elasticity respectively. Ultrasonic data were analyzed by Support vector machine (SVM), random forest(RF), K-nearest neighbor (KNN) and artificial neural network (ANN), respectively, and compared with the human-reading method.

RESULTS : Only ultrasound elastography data have diagnostic value for renal diseases. The accuracy of SVM, RF, KNN and ANN methods are 80.98%,80.32%,78.03%and79.67% respectively, while the accuracy of human-reading is 78.33%. In the data of machine learning ultrasound elastography, the elastic hardness parameters of renal cortex are most important.

CONCLUSION : Ultrasound elastography is of highest diagnostic value in machine learning for nephropathy,the diagnostic efficiency of machine learning method is slightly higher than that of human-reading method, and the diagnostic ability of SVM method is higher than other methods.

Li Guanghan, Liu Jian, Wu Jingping, Tian Yan, Ma Liyong, Liu Yuejun, Zhang Bo, Mou Shan, Zheng Min


Renal disease, diagnosis, elastography, machine learning, support vector machine., ultrasound image