ABSTRACT
Objective@#To investigate the value of texture analysis based on MR ADC map of prostate in differentiating between low-grade and high-grade prostate cancer (PCa).@*Methods@#PCa confirmed by pathology after radical prostatectomy were analyzed retrospectively, all patients underwent multiparametric MRI before radical prostatectomy, including T1WI,T2WI and DWI. On the ADC map, ROI was drawn manually to encompass the whole tumor by ITK-SNAP software. The python-based pyradiomics package was used to extract 105 texture features. The intraclass correlation coefficient was used to evaluate the repeatability of the texture features. The independent sample t test or Mann-Whitney U test was used to exclude features that had no significant difference between low grade and high grade PCa. Lasso regression model and 5 fold cross validation method were used to obtain texture feature combination of the highest performance and develop a classification modelfor discriminating low from high grade PCa. ROC curve was used to evaluate the diagnostic efficiency of the model.@*Result@#Ninety patients with PCa confirmed by pathology after radical prostatectomywere analyzed retrospectively,including 36 patients with low-level PCa (GS≤3+4) and 54 patients with high-level PCa (GS≥4+3). The area under curve of the model was 0.841, with sensitivity 69.6% and specificity 91.2%, which was significantly higher than single texture feature or traditional mean ADC value.@*Conclusion@#Texture analysis based on MRI-ADC map of prostate could be used to discriminate low grade PCa from high grade PCa.
ABSTRACT
Objective@#To develop a convolution neural network (CNN) model to classify multi-sequence MR images of the prostate.@*Methods@#ResNet18 convolution neural network (CNN) model was developed to classify multi-sequence MR images of the prostate. A deep residual network was used to improve training accuracy and test accuracy. The dataset used in this experiment included 19 146 7-sequence prostate MR images (transverse T1WI, transverse T2WI, coronal T2WI, sagittal T2WI, transverse DWI, transverse ADC, transverse PWI), from which a total of 2 800 7-sequence MR images was selected as a training set. Three hundred and eighty eight 7-sequence MR images were selected as test sets. Accuracy was used to evaluate the effectiveness of ResNet18 CNN model.@*Results@#The classification accuracy of the model for transverse DWI, sagittal T2WI, transverse ADC, transverse T1WI, and transverse T2WI was as high as 100.0% (44/44,52/52), and the accuracy for transverse PWI was also as high as 96.7% (116/120). The accuracy for coronal T2WI was 77.5% (31/40). 0.8% (1/120) of transverse PWI was incorrectly assigned to transverse T2WI, and 2.5% (3/120) incorrectly assigned to sagittal T2WI. 15.0% (6/40) of coronal T2WI was incorrectly assigned to transverse T2WI, and 7.5% (3/40) to sagittal T2WI.@*Conclusion@#The experimental results show the effectiveness of our deep learning method regarding accuracy in the prostate multi-sequence MR images detection.
ABSTRACT
Objective To investigate the value of texture analysis based on MR ADC map of prostate in differentiating between low?grade and high?grade prostate cancer (PCa). Methods PCa confirmed by pathology after radical prostatectomy were analyzed retrospectively, all patients underwent multiparametric MRI before radical prostatectomy, including T1WI,T2WI and DWI. On the ADC map, ROI was drawn manually to encompass the whole tumor by ITK?SNAP software. The python?based pyradiomics package was used to extract 105 texture features. The intraclass correlation coefficient was used to evaluate the repeatability of the texture features. The independent sample t test or Mann?Whitney U test was used to exclude features that had no significant difference between low grade and high grade PCa. Lasso regression model and 5 fold cross validation method were used to obtain texture feature combination of the highest performance and develop a classification modelfor discriminating low from high grade PCa. ROC curve was used to evaluate the diagnostic efficiency of the model. Result Ninety patients with PCa confirmed by pathology after radical prostatectomywere analyzed retrospectively,including 36 patients with low?level PCa (GS≤3+4) and 54 patients with high?level PCa (GS≥4+3). The area under curve of the model was 0.841, with sensitivity 69.6% and specificity 91.2%, which was significantly higher than single texture feature or traditional mean ADC value. Conclusion Texture analysis based on MRI?ADC map of prostate could be used to discriminate low grade PCa from high grade PCa.
ABSTRACT
Objective To develop a convolution neural network (CNN) model to classify multi?sequence MR images of the prostate. Methods ResNet18 convolution neural network (CNN) model was developed to classify multi?sequence MR images of the prostate. A deep residual network was used to improve training accuracy and test accuracy. The dataset used in this experiment included 19 146 7?sequence prostate MR images (transverse T1WI, transverse T2WI, coronal T2WI, sagittal T2WI, transverse DWI, transverse ADC, transverse PWI), from which a total of 2 800 7?sequence MR images was selected as a training set. Three hundred and eighty eight 7?sequence MR images were selected as test sets. Accuracy was used to evaluate the effectiveness of ResNet18 CNN model. Results The classification accuracy of the model for transverse DWI, sagittal T2WI, transverse ADC, transverse T1WI, and transverse T2WI was as high as 100.0% (44/44,52/52), and the accuracy for transverse PWI was also as high as 96.7% (116/120). The accuracy for coronal T2WI was 77.5% (31/40). 0.8% (1/120) of transverse PWI was incorrectly assigned to transverse T2WI, and 2.5% (3/120) incorrectly assigned to sagittal T2WI. 15.0% (6/40) of coronal T2WI was incorrectly assigned to transverse T2WI, and 7.5% (3/40) to sagittal T2WI. Conclusion The experimental results show the effectiveness of our deep learning method regarding accuracy in the prostate multi?sequence MR images detection.