연속 초음파영상에서의 바늘 검출을 위한 3D와 연속 영상문맥을 활용한 D-Attention Unet 모델 개발 및 평가
Development and Evaluation of D-Attention Unet Model Using 3D and Continuous Visual Context for Needle Detection in Continuous Ultrasound Images
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Needle detection in ultrasound images is sometimes difficult due to obstruction of fat tissues. Accurate needle detection using continuous ultrasound (CUS) images is a vital stage of treatment planning for tissue biopsy and brachytherapy. The main goal of the study is classified into two categories. First, new detection model, i.e. DAttention Unet, is developed by combining the context information of 3D medical data and CUS images. Second, the D-Attention Unet model was compared with other models to verify its usefulness for needle detection in continuous ultrasound images. The continuous needle images taken with ultrasonic waves were converted into still images for dataset to evaluate the performance of the D-Attention Unet. The dataset was used for training and testing. Based on the results, the proposed D-Attention Unet model showed the better performance than other 3 models (Unet, D-Unet and Attention Unet), with Dice Similarity Coefficient (DSC), Recall and Precision at 71.9%, 70.6% and 73.7%, respectively. In conclusion, the D-Attention Unet model provides accurate needle detection for US-guided biopsy or brachytherapy, facilitating the clinical workflow. Especially, this kind of research is enthusiastically being performed on how to add image processing techniques to learning techniques. Thus, the proposed method is applied in this manner, it will be more effective technique than before.
Abstract
Needle detection in ultrasound images is sometimes difficult due to obstruction of fat tissues. Accurate needle detection using continuous ultrasound (CUS) images is a vital stage of treatment planning for tissue biopsy and brachytherapy. The main goal of the study is classified into two categories. First, new detection model, i.e. DAttention Unet, is developed by combining the context information of 3D medical data and CUS images. Second, the D-Attention Unet model was compared with other models to verify its usefulness for needle detection in continuous ultrasound images. The continuous needle images taken with ultrasonic waves were converted into still images for dataset to evaluate the performance of the D-Attention Unet. The dataset was used for training and testing. Based on the results, the proposed D-Attention Unet model showed the better performance than other 3 models (Unet, D-Unet and Attention Unet), with Dice Similarity Coefficient (DSC), Recall and Precision at 71.9%, 70.6% and 73.7%, respectively. In conclusion, the D-Attention Unet model provides accurate needle detection for US-guided biopsy or brachytherapy, facilitating the clinical workflow. Especially, this kind of research is enthusiastically being performed on how to add image processing techniques to learning techniques. Thus, the proposed method is applied in this manner, it will be more effective technique than before.
참고문헌 (23)
- Kamilaris, "Deep learning in agriculture : A survey", Computers and electronics in agriculture, 147, pp.70~90 (2018)
- Dinggang S, "Deep learning in medical image analysis", Annual review of biomedical engineering, 19, pp.221~248 (2017)
- Zhao ZQ, "Object detection with deep learning : A review", IEEE transactions on neural networks and learning systems, 30(11), pp.3212~3232 (2019)
- Rajpurkar P, "Chexnet : Radiologist-level pneumonia detection on chest x-rays with deep learning", ~ (2017)
- Krizhevsky A, "Imagenet classification with deep convolutional neural networks", Advances in Neural Information Processing Systems, 25, pp.1097~1005 (2012)
- Falk T, "Unet: deep learning for cell counting, detection, and morphometry", Nature methods, 16, pp.67~70 (2019)
- Ronneberger O, "Unet: Convolutional networks for biomedical image segmentation", International Conference on Medical image computing and computer-assisted intervention, pp.234~241 (2015)
- Weng Y, "Nas-unet : Neural architecture search for medical image segmentation", IEEE Access, 7, pp.44247~44257 (2019)
- Dubost F, "GP-Unet: Lesion detection from weak labels with a 3D regression network", International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.214~221 (2017)
- Denil M, "Predicting parameters in deep learning", Advances in neural information processing systems, 26, pp.2148~2156 (2013)
- Torralba A, "Contextbased vision system for place and object recognition", ICCV, 3, pp.273~280 (2003)
- Mottaghi R, "The Role of Context for Object Detection and Semantic Segmentation in the Wild", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.891~898 (2014)
- Zhou Y, "D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation", IEEE, 2019, ~
- Jin Q, "DUNet : A deformable network for retinal vessel segmentation", Knowledge-Based Systems, 178, pp.149~162 (2019)
- Oktay O, "Attention Unet: Learning where to look for the pancreas", MIDL, ~ (2018)
- Dong Y, "Attention Res-Unet : an efficient shadow detection algorithm", Journal of ZheJiang University(Engineering Science), 53(2), pp.373~381 (2019)
- Sinha, Ashish, "Multi-scale guided attention for medical image segmentation", arXiv, ~ (2019)
- Ding M, "A real-time biopsy needle segmentation technique using Hough Transform", Medical physics, 30(8), pp.2222~2233 (2003)
- Mehrtash A, "Automatic needle segmentation and localization in MRI with 3-D convolutional neural networks : application to MRI-targeted prostate biopsy", IEEE transactions on medical imaging, 38(4), pp.1026~1036 (2018)
- Zhang Y, "Multi-Needle Detection in 3D Ultrasound Images Using Unsupervised Order-Graph Regularized Sparse Dictionary Learning", IEEE Transactions on Medical Imaging, 39(7), pp.2302~2315 (2020)
- Lee SJ, "Basic Study on the Effect of Number of Hidden Layers on Performance of Estimation Model of Compressive Strength of Concrete Using Deep Learning Algorithms", J Korea Inst Build Constr, 18(1), pp.130~141 (2018)
- Yun JR, "Object Recognition in 360° Streaming Video", The Korean Society of Computer Information Conference, 27(2), pp.317~318 (2019)
- Bruzzone L, "Automatic analysis of the difference image for unsupervised change detection", IEEE Transactions on Geoscience and Remote sensing, 38(3), pp.1171~1182 (2000)