| 1. |
- Ravikumar, Sadhana, et al.
(författare)
-
Improved Segmentation of Deep Sulci in Cortical Gray Matter Using a Deep Learning Framework Incorporating Laplace’s Equation
- 2023
-
Ingår i: Information Processing in Medical Imaging - 28th International Conference, IPMI 2023, Proceedings. - 1611-3349 .- 0302-9743. - 9783031340475 ; 13939 LNCS, s. 692-704
-
Konferensbidrag (refereegranskat)abstract
- When developing tools for automated cortical segmentation, the ability to produce topologically correct segmentations is important in order to compute geometrically valid morphometry measures. In practice, accurate cortical segmentation is challenged by image artifacts and the highly convoluted anatomy of the cortex itself. To address this, we propose a novel deep learning-based cortical segmentation method in which prior knowledge about the geometry of the cortex is incorporated into the network during the training process. We design a loss function which uses the theory of Laplace’s equation applied to the cortex to locally penalize unresolved boundaries between tightly folded sulci. Using an ex vivo MRI dataset of human medial temporal lobe specimens, we demonstrate that our approach outperforms baseline segmentation networks, both quantitatively and qualitatively.
|
|
| 2. |
- Sadaghiani, Shokufeh, et al.
(författare)
-
Associations of phosphorylated tau pathology with whole-hemisphere ex vivo morphometry in 7 tesla MRI
- 2023
-
Ingår i: Alzheimer's and Dementia. - : Wiley. - 1552-5260 .- 1552-5279. ; 19:6, s. 2355-2364
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction: Neurodegenerative disorders are associated with different pathologies that often co-occur but cannot be measured specifically with in vivo methods. Methods: Thirty-three brain hemispheres from donors with an Alzheimer's disease (AD) spectrum diagnosis underwent T2-weighted magnetic resonance imaging (MRI). Gray matter thickness was paired with histopathology from the closest anatomic region in the contralateral hemisphere. Results: Partial Spearman correlation of phosphorylated tau and cortical thickness with TAR DNA-binding protein 43 (TDP-43) and α-synuclein scores, age, sex, and postmortem interval as covariates showed significant relationships in entorhinal and primary visual cortices, temporal pole, and insular and posterior cingulate gyri. Linear models including Braak stages, TDP-43 and α-synuclein scores, age, sex, and postmortem interval showed significant correlation between Braak stage and thickness in the parahippocampal gyrus, entorhinal cortex, and Broadman area 35. Conclusion: We demonstrated an association of measures of AD pathology with tissue loss in several AD regions despite a limited range of pathology in these cases. Highlights: Neurodegenerative disorders are associated with co-occurring pathologies that cannot be measured specifically with in vivo methods. Identification of the topographic patterns of these pathologies in structural magnetic resonance imaging (MRI) may provide probabilistic biomarkers. We demonstrated the correlation of the specific patterns of tissue loss from ex vivo brain MRI with underlying pathologies detected in postmortem brain hemispheres in patients with Alzheimer's disease (AD) spectrum disorders. The results provide insight into the interpretation of in vivo structural MRI studies in patients with AD spectrum disorders.
|
|
| 3. |
- Xie, Long, et al.
(författare)
-
Deep label fusion : A generalizable hybrid multi-atlas and deep convolutional neural network for medical image segmentation
- 2023
-
Ingår i: Medical Image Analysis. - : Elsevier BV. - 1361-8415. ; 83
-
Tidskriftsartikel (refereegranskat)abstract
- Deep convolutional neural networks (DCNN) achieve very high accuracy in segmenting various anatomical structures in medical images but often suffer from relatively poor generalizability. Multi-atlas segmentation (MAS), while less accurate than DCNN in many applications, tends to generalize well to unseen datasets with different characteristics from the training dataset. Several groups have attempted to integrate the power of DCNN to learn complex data representations and the robustness of MAS to changes in image characteristics. However, these studies primarily focused on replacing individual components of MAS with DCNN models and reported marginal improvements in accuracy. In this study we describe and evaluate a 3D end-to-end hybrid MAS and DCNN segmentation pipeline, called Deep Label Fusion (DLF). The DLF pipeline consists of two main components with learnable weights, including a weighted voting subnet that mimics the MAS algorithm and a fine-tuning subnet that corrects residual segmentation errors to improve final segmentation accuracy. We evaluate DLF on five datasets that represent a diversity of anatomical structures (medial temporal lobe subregions and lumbar vertebrae) and imaging modalities (multi-modality, multi-field-strength MRI and Computational Tomography). These experiments show that DLF achieves comparable segmentation accuracy to nnU-Net (Isensee et al., 2020), the state-of-the-art DCNN pipeline, when evaluated on a dataset with similar characteristics to the training datasets, while outperforming nnU-Net on tasks that involve generalization to datasets with different characteristics (different MRI field strength or different patient population). DLF is also shown to consistently improve upon conventional MAS methods. In addition, a modality augmentation strategy tailored for multimodal imaging is proposed and demonstrated to be beneficial in improving the segmentation accuracy of learning-based methods, including DLF and DCNN, in missing data scenarios in test time as well as increasing the interpretability of the contribution of each individual modality.
|
|
