| 1. |
- Abramian, David, 1992-, et al.
(författare)
-
REFACING: RECONSTRUCTING ANONYMIZED FACIAL FEATURES USING GANS
- 2019
-
Ingår i: 2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019). - : IEEE. - 9781538636411 ; , s. 1104-1108
-
Konferensbidrag (refereegranskat)abstract
- Anonymization of medical images is necessary for protecting the identity of the test subjects, and is therefore an essential step in data sharing. However, recent developments in deep learning may raise the bar on the amount of distortion that needs to be applied to guarantee anonymity. To test such possibilities, we have applied the novel CycleGAN unsupervised image-to-image translation framework on sagittal slices of T1 MR images, in order to reconstruct, facial features from anonymized data. We applied the CycleGAN framework on both face-blurred and face-removed images. Our results show that face blurring may not provide adequate protection against malicious attempts at identifying the subjects, while face removal provides more robust anonymization, but is still partially reversible.
|
|
| 2. |
- Arvidsson, Ida, et al.
(författare)
-
Comparison of different augmentation techniques for improved generalization performance for gleason grading
- 2019
-
Ingår i: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). - 9781538636411 ; , s. 923-927
-
Konferensbidrag (refereegranskat)abstract
- The fact that deep learning based algorithms used for digital pathology tend to overfit to the site of the training data is well-known. Since an algorithm that does not generalize is not very useful, we have in this work studied how different data augmentation techniques can reduce this problem but also how data from different sites can be normalized to each other. For both of these approaches we have used cycle generative adversarial networks (GAN); either to generate more examples to train on or to transform images from one site to another. Furthermore, we have investigated to what extent standard augmentation techniques improve the generalization performance. We performed experiments on four datasets with slides from prostate biopsies, stained with HE, detailed annotated with Gleason grades. We obtained results similar to previous studies, with accuracies of 77% for Gleason grading for images from the same site as the training data and 59% for images from other sites. However, we also found out that the use of traditional augmentation techniques gave better performance compared to when using cycle GANs, either to augment the training data or to normalize the test data.
|
|
| 3. |
- Guigui, N., et al.
(författare)
-
Network Regularization in Imaging Genetics Improves Prediction Performances and Model Interpretability on Alzheimer’s Disease
- 2019
-
Ingår i: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). - : IEEE. - 9781538636411 ; , s. 1403-1406
-
Konferensbidrag (refereegranskat)abstract
- Imaging genetics is a growing popular research avenue which aims to find genetic variants associated with quantitative phenotypes that characterize a disease. In this work, we combine structural MRI with genetic data structured by prior knowledge of interactions in a Canonical Correlation Analysis (CCA) model with graph regularization. This results in improved prediction performance and yields a more interpretable model.
|
|
| 4. |
- Suveer, Amit, et al.
(författare)
-
Super-resolution Reconstruction of Transmission Electron Microscopy Images using Deep Learning
- 2019
-
Ingår i: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). - : IEEE. - 9781538636411 ; , s. 548-551
-
Konferensbidrag (refereegranskat)abstract
- Deep learning techniques have shown promising outcomes in single image super-resolution (SR) reconstruction from noisy and blurry low resolution data. The SR reconstruction can cater the fundamental. limitations of transmission electron microscopy (TEM) imaging to potentially attain a balance among the trade-offs like imaging-speed, spatial/temporal resolution, and dose/exposure-time, which is often difficult to achieve simultaneously otherwise. In this work, we present a convolutional neural network (CNN) model, utilizing both local and global skip connections, aiming for 4 x SR reconstruction of TEM images. We used exact image pairs of a calibration grid to generate our training and independent testing datasets. The results are compared and discussed using models trained on synthetic (downsampled) and real data from the calibration grid. We also compare the variants of the proposed network with well-known classical interpolations techniques. Finally, we investigate the domain adaptation capacity of the CNN-based model by testing it on TEM images of a cilia sample, having different image characteristics as compared to the calibration-grid.
|
|
| 5. |
- Tarun, Anjali, et al.
(författare)
-
Graph spectral analysis of voxel-wise brain graphs from diffusion-weighted mri
- 2019
-
Ingår i: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). - : IEEE. - 9781538636411 ; , s. 159-163
-
Konferensbidrag (refereegranskat)abstract
- Non-invasive characterization of brain structure has been made possible by the introduction of magnetic resonance imaging (MRI). Graph modeling of structural connectivity has been useful, but is often limited to defining nodes as regions from a brain atlas. Here, we propose two methods for encoding structural connectivity in a huge brain graph at the voxel-level resolution (i.e., 850'000 voxels) based on diffusion tensor imaging (DTI) and the orientation density functions (ODF), respectively. The eigendecomposition of the brain graph's Laplacian operator is then showing highly-resolved eigenmodes that reflect distributed structural features which are in good correspondence with major white matter tracks. To investigate the intrinsic dimensionality of eigenspace across subjects, we used a Procrustes validation that characterizes inter-subject variability. We found that the ODF approach using 3-neighborhood captures the most in-formation from the diffusion-weighted MRI. The proposed methods open a wide range of possibilities for new research avenues, especially in the field of graph signal processing applied to functional brain imaging.
|
|
