| 1. |
-
Annual Report 2008
- 2009. - 250
-
Samlingsverk (redaktörskap) (övrigt vetenskapligt/konstnärligt)
|
|
| 2. |
|
|
| 3. |
- Bengtsson Bernander, Karl
(författare)
-
Equivariant Neural Networks for Biomedical Image Analysis
- 2024
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- While artificial intelligence and deep learning have revolutionized many fields in the last decade, one of the key drivers has been access to data. This is especially true in biomedical image analysis where expert annotated data is hard to come by. The combination of Convolutional Neural Networks (CNNs) with data augmentation has proven successful in increasing the amount of training data at the cost of overfitting. In this thesis, equivariant neural networks have been used to extend the equivariant properties of CNNs to more transformations than translations. The networks have been trained and evaluated on biomedical image datasets, including bright-field microscopy images of cytological samples indicating oral cancer, and transmission electron microscopy images of virus samples. By designing the networks to be equivariant to e.g. rotations, it is shown that the need for data augmentation is reduced, that less overfitting occurs, and that convergence during training is faster. Furthermore, equivariant neural networks are more data efficient than CNNs, as demonstrated by scaling laws. These benefits are not present in all problem settings and which benefits will occur is somewhat unpredictable. We have identified that the results to some extent depend on architectures, hyperparameters and datasets. Further research may broaden the performed studies to explain how the results occur with new theory.
|
|
| 4. |
- Bengtsson Bernander, Karl, et al.
(författare)
-
Replacing data augmentation with rotation-equivariant CNNs in image-based classification of oral cancer
- 2021
-
Ingår i: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. - Cham : Springer International Publishing. - 9783030934194 - 9783030934200 ; , s. 24-33
-
Konferensbidrag (refereegranskat)abstract
- We present how replacing convolutional neural networks with a rotation-equivariant counterpart can be used to reduce the amount of training images needed for classification of whether a cell is cancerous or not. Our hypothesis is that data augmentation schemes by rotation can be replaced, thereby increasing weight sharing and reducing overfitting. The dataset at hand consists of single cell images. We have balanced a subset of almost 9.000 images from healthy patients and patients diagnosed with cancer. Results show that classification accuracy is improved and overfitting reduced if compared to an ordinary convolutional neural network. The results are encouraging and thereby an advancing step towards making screening of patients widely used for the application of oral cancer.
|
|
| 5. |
|
|
| 6. |
- Blache, Ludovic, et al.
(författare)
-
SoftCut: : A Virtual Planning Tool for Soft Tissue Resection on CT Images
- 2018
-
Ingår i: Medical Image Understanding and Analysis. - Cham : Springer. - 9783319959207 ; , s. 299-310
-
Konferensbidrag (refereegranskat)abstract
- With the increasing use of three-dimensional (3D) models and Computer Aided Design (CAD) in the medical domain, virtual surgical planning is now frequently used. Most of the current solutions focus on bone surgical operations. However, for head and neck oncologic resection, soft tissue ablation and reconstruction are common operations. In this paper, we propose a method to provide a fast and efficient estimation of shape and dimensions of soft tissue resections. Our approach takes advantage of a simple sketch-based interface which allows the user to paint the contour of the resection on a patient specific 3D model reconstructed from a computed tomography (CT) scan. The volume is then virtually cut and carved following this pattern. From the outline of the resection defined on the skin surface as a closed curve, we can identify which areas of the skin are inside or outside this shape. We then use distance transforms to identify the soft tissue voxels which are closer from the inside of this shape. Thus, we can propagate the shape of the resection inside the soft tissue layers of the volume. We demonstrate the usefulness of the method on patient specific CT data.
|
|
| 7. |
|
|
| 8. |
- Malmberg, Filip, et al.
(författare)
-
Relaxed Image Foresting Transforms for Interactive Volume Image Segmentation
- 2010
-
Ingår i: MEDICAL IMAGING 2010. - : SPIE. - 9780819480248 ; 7623
-
Konferensbidrag (refereegranskat)abstract
- The image Foresting (IFT) is a framework for image partitioning, commonly used for interactive segmentation. Given an image where a subset of the image elements (seed-points) have been assigned correct segmentation labels, the IFT completes the labeling by computing minimal cost paths from all image elements to the seed-points. Each image element is then given the same label as the closest seed-point. Here, we propose the relaxed IFT (RIFT). This modified version of the IFT features an additional parameter to control the smoothness of the segmentation boundary. The RIFT yields more intuitive segmentation results in the presence of noise and weak edges, while maintaining a low computational complexity. We show an application of the method to the refinement of manual segmentations of a thoracolumbar muscle in magnetic resonance images. The performed study shows that the refined segmentations are qualitatively similar to the manual segmentations, while intra-user variations are reduced by more than 50%.
|
|
| 9. |
- Nedelcu, Robert, et al.
(författare)
-
Accuracy and precision of 3 intraoral scanners and accuracy of conventional impressions : A novel in vivo analysis method
- 2018
-
Ingår i: Journal of Dentistry. - : ELSEVIER SCI LTD. - 0300-5712 .- 1879-176X. ; 69, s. 110-118
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: To evaluate a novel methodology using industrial scanners as a reference, and assess in vivo accuracy of 3 intraoral scanners (IOS) and conventional impressions. Further, to evaluate IOS precision in vivo.Methods: Four reference-bodies were bonded to the buccal surfaces of upper premolars and incisors in five subjects. After three reference-scans, ATOS Core 80 (ATOS), subjects were scanned three times with three IOS systems: 3M True Definition (3M), CEREC Omnicam (OMNI) and Trios 3 (TRIOS). One conventional impression (IMPR) was taken, 3M Impregum Penta Soft, and poured models were digitized with laboratory scanner 3shape D1000 (D1000). Best-fit alignment of reference-bodies and 3D Compare Analysis was performed. Precision of ATOS and D1000 was assessed for quantitative evaluation and comparison. Accuracy of IOS and IMPR were analyzed using ATOS as reference. Precision of IOS was evaluated through intra-system comparison.Results: Precision of ATOS reference scanner (mean 0.6 mu m) and D1000 (mean 0.5 mu m) was high. Pairwise multiple comparisons of reference-bodies located in different tooth positions displayed a statistically significant difference of accuracy between two scanner-groups: 3M and TRIOS, over OMNI (p value range 0.0001 to 0.0006). IMPR did not show any statistically significant difference to IOS. However, deviations of IOS and IMPR were within a similar magnitude. No statistical difference was found for IOS precision.Conclusion: The methodology can be used for assessing accuracy of IOS and IMPR in vivo in up to five units bilaterally from midline. 3M and TRIOS had a higher accuracy than OMNI. IMPR overlapped both groups. Clinical significance: Intraoral scanners can be used as a replacement for conventional impressions when restoring up to ten units without extended edentulous spans.
|
|
| 10. |
|
|
