딥러닝을 활용한 3차원 초음파 파노라마 영상 복원
3D Ultrasound Panoramic Image Reconstruction using Deep Learning
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Clinical ultrasound (US) is a widely used imaging modality with various clinical applications. However, cap- turing a large field of view often requires specialized transducers which have limitations for specific clinical scenarios. Panoramic imaging offers an alternative approach by sequentially aligning image sections acquired from freehand sweeps using a standard transducer. To reconstruct a 3D volume from these 2D sections, an external device can be employed to track the transducer’s motion accurately. However, the presence of optical or electrical interferences in a clinical setting often leads to incorrect measurements from such sensors. In this paper, we propose a deep learn- ing (DL) framework that enables the prediction of scan trajectories using only US data, eliminating the need for an external tracking device. Our approach incorporates diverse data types, including correlation volume, optical flow, B-mode images, and rawer data (IQ data). We develop a DL network capable of effectively handling these data types and introduce an attention technique to emphasize crucial local areas for precise trajectory prediction. Through exten- sive experimentation, we demonstrate the superiority of our proposed method over other DL-based approaches in terms of long trajectory prediction performance. Our findings highlight the potential of employing DL techniques for trajectory estimation in clinical ultrasound, offering a promising alternative for panoramic imaging.
Abstract
Clinical ultrasound (US) is a widely used imaging modality with various clinical applications. However, cap- turing a large field of view often requires specialized transducers which have limitations for specific clinical scenarios. Panoramic imaging offers an alternative approach by sequentially aligning image sections acquired from freehand sweeps using a standard transducer. To reconstruct a 3D volume from these 2D sections, an external device can be employed to track the transducer’s motion accurately. However, the presence of optical or electrical interferences in a clinical setting often leads to incorrect measurements from such sensors. In this paper, we propose a deep learn- ing (DL) framework that enables the prediction of scan trajectories using only US data, eliminating the need for an external tracking device. Our approach incorporates diverse data types, including correlation volume, optical flow, B-mode images, and rawer data (IQ data). We develop a DL network capable of effectively handling these data types and introduce an attention technique to emphasize crucial local areas for precise trajectory prediction. Through exten- sive experimentation, we demonstrate the superiority of our proposed method over other DL-based approaches in terms of long trajectory prediction performance. Our findings highlight the potential of employing DL techniques for trajectory estimation in clinical ultrasound, offering a promising alternative for panoramic imaging.
참고문헌 (12)
- Mi J, "Comparative effectiveness of MRI, 4D-CT and ultrasonography in patients with secondary hyperparathyroidism", Therapeutics and Clinical Risk Management, 19, pp.369~381 (2023)
- Chen JF, "Determination of scan-plane motion using speckle decorrelation: Theoretical considerations and initial test", International Journal of Imaging Systems and Technology, 8(1), pp.38~44 (1997)
- Tuthill TA, "Automated three-dimensional US frame positioning computed from elevational speckle decorrelation", Radiology, 209(2), pp.575~582 (1998)
- Mondillo S, "Speckletracking echocardiography: a new technique for assessing myocardial function", Journal of Ultrasound in Medicine, 30(1), pp.71~83 (2011)
- Ronneberger O, "U-net: Convolutional networks for biomedical image segmentation", Medical Image Computing and Computer-Assisted Intervention–MICCAI, 2015, pp.234~241 (2015)
- Esteva A, "Dermatologist-level classification of skin cancer with deep neural networks", Nature, 542, pp.115~118 (2017)
- Gulshan V, "Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs", JAMA, 316(22), pp.2402~2410 (2016)
- Prevost R, "3D freehand ultrasound without external tracking using deep learning", Medical image analysis, 48, pp.187~202 (2018)
- Guo H, "Sensorless freehand 3D ultrasound reconstruction via deep contextual learning", Medical Image Computing and Computer Assisted Intervention–MICCAI, 2020, pp.463~472 (2020)
- Teed Z, "Raft: Recurrent all-pairs field transforms for optical flow", Computer Vision–ECCV, 2020, pp.402~419 (2020)
- He K, "Deep residual learning for image recognition", IEEE conference on computer vision and pattern recognition (CVPR), pp.770~778 (2016)
- Woo SH, "Cbam: Convolutional block attention module", European conference on computer vision (ECCV), pp.3~19 (2018)