| 1. |
- Alvén, Jennifer, 1989, et al.
(författare)
-
A Deep Learning Approach to MR-less Spatial Normalization for Tau PET Images
- 2019
-
Ingår i: Medical Image Computing and Computer Assisted Intervention : MICCAI 2019 - 22nd International Conference, Proceedings - MICCAI 2019 - 22nd International Conference, Proceedings. - Cham : Springer International Publishing. - 1611-3349 .- 0302-9743. - 9783030322441 - 9783030322458 ; 11765 LNCS, s. 355-363
-
Konferensbidrag (refereegranskat)abstract
- The procedure of aligning a positron emission tomography (PET) image with a common coordinate system, spatial normalization, typically demands a corresponding structural magnetic resonance (MR) image. However, MR imaging is not always available or feasible for the subject, which calls for enabling spatial normalization without MR, MR-less spatial normalization. In this work, we propose a template-free approach to MR-less spatial normalization for [18F]flortaucipir tau PET images. We use a deep neural network that estimates an aligning transformation from the PET input image, and outputs the spatially normalized image as well as the parameterized transformation. In order to do so, the proposed network iteratively estimates a set of rigid and affine transformations by means of convolutional neural network regressors as well as spatial transformer layers. The network is trained and validated on 199 tau PET volumes with corresponding ground truth transformations, and tested on two different datasets. The proposed method shows competitive performance in terms of registration accuracy as well as speed, and compares favourably to previously published results.
|
|
| 2. |
- Hering, Alessa, et al.
(författare)
-
Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning
- 2023
-
Ingår i: IEEE Transactions on Medical Imaging. - : Institute of Electrical and Electronics Engineers (IEEE). - 0278-0062 .- 1558-254X. ; 42:3, s. 697-712
-
Tidskriftsartikel (refereegranskat)abstract
- Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https:// learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.
|
|
