عنوان انگلیسی مقاله:
Accurate and robust deep learning-based segmentation of the prostate clinical target volume in ultrasound images
ترجمه فارسی عنوان مقاله:
تقسیم بندی دقیق و قوی بر اساس یادگیری عمیق از حجم هدف بالینی پروستات در تصاویر سونوگرافی
Sciencedirect - Elsevier - Medical Image Analysis, 57 (2019) 186-196: doi:10:1016/j:media:2019:07:005
Davood Karimi a , ∗, Qi Zeng a , Prateek Mathur a , Apeksha Avinash a , Sara Mahdavi b , Ingrid Spadinger b , Purang Abolmaesumi a , Septimiu E. Salcudean a
The goal of this work was to develop a method for accurate and robust automatic segmentation of the prostate clinical target volume in transrectal ultrasound (TRUS) images for brachytherapy. These images can be difficult to segment because of weak or insufficient landmarks or strong artifacts. We devise a method, based on convolutional neural networks (CNNs), that produces accurate segmentations on easy and difficult images alike. We propose two strategies to achieve improved segmentation accuracy on diffi- cult images. First, for CNN training we adopt an adaptive sampling strategy, whereby the training process is encouraged to pay more attention to images that are difficult to segment. Secondly, we train a CNN ensemble and use the disagreement among this ensemble to identify uncertain segmentations and to estimate a segmentation uncertainty map. We improve uncertain segmentations by utilizing the prior shape information in the form of a statistical shape model. Our method achieves Hausdorffdistance of 2.7 ±2.3 mm and Dice score of 93.9 ±3.5%. Comparisons with several competing methods show that our method achieves significantly better results and reduces the likelihood of committing large segmentation errors. Furthermore, our experiments show that our approach to estimating segmentation uncertainty is better than or on par with recent methods for estimation of prediction uncertainty in deep learning mod- els. Our study demonstrates that estimation of model uncertainty and use of prior shape information can significantly improve the performance of CNN-based medical image segmentation methods, especially on difficult images.
Keywords: Image segmentation | Model uncertainty | Shape models | Clustering | Deep learning