| 1. |
- Alvén, Jennifer, 1989, et al.
(författare)
-
Shape-aware label fusion for multi-atlas frameworks
- 2019
-
Ingår i: Pattern Recognition Letters. - : Elsevier BV. - 0167-8655. ; 124, s. 109-117
-
Tidskriftsartikel (refereegranskat)abstract
- Despite of having no explicit shape model, multi-atlas approaches to image segmentation have proved to be a top-performer for several diverse datasets and imaging modalities. In this paper, we show how one can directly incorporate shape regularization into the multi-atlas framework. Unlike traditional multi-atlas methods, our proposed approach does not rely on label fusion on the voxel level. Instead, each registered atlas is viewed as an estimate of the position of a shape model. We evaluate and compare our method on two public benchmarks: (i) the VISCERAL Grand Challenge on multi-organ segmentation of whole-body CT images and (ii) the Hammers brain atlas of MR images for segmenting the hippocampus and the amygdala. For this wide spectrum of both easy and hard segmentation tasks, our experimental quantitative results are on par or better than state-of-the-art. More importantly, we obtain qualitatively better segmentation boundaries, for instance, preserving topology and fine structures.
|
|
| 2. |
- Alvén, Jennifer, 1989, et al.
(författare)
-
Shape-aware multi-atlas segmentation
- 2016
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 1051-4651. ; 0, s. 1101-1106
-
Konferensbidrag (refereegranskat)abstract
- Despite of having no explicit shape model, multi-atlas approaches to image segmentation have proved to be a top-performer for several diverse datasets and imaging modalities. In this paper, we show how one can directly incorporate shape regularization into the multi-atlas framework. Unlike traditional methods, our proposed approach does not rely on label fusion on the voxel level. Instead, each registered atlas is viewed as an estimate of the position of a shape model. We evaluate and compare our method on two public benchmarks: (i) the VISCERAL Grand Challenge on multi-organ segmentation of whole-body CT images and (ii) the Hammers brain atlas of MR images for segmenting the hippocampus and the amygdala. For this wide spectrum of both easy and hard segmentation tasks, our experimental quantitative results are on par or better than state-of-the-art. More importantly, we obtain qualitatively better segmentation boundaries, for instance, preserving fine structures.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Fejne, Frida, 1986, et al.
(författare)
-
Multiatlas Segmentation Using Robust Feature-Based Registration
- 2017
-
Ingår i: , Cloud-Based Benchmarking of Medical Image Analysis. - Cham : Springer International Publishing. - 9783319496429 ; , s. 203-218
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a pipeline which uses a multiatlas approach for multiorgan segmentation in whole-body CT images. In order to obtain accurate registrations between the target and the atlas images, we develop an adapted feature-based method which uses organ-specific features. These features are learnt during an offline preprocessing step, and thus, the algorithm still benefits from the speed of feature-based registration methods. These feature sets are then used to obtain pairwise non-rigid transformations using RANSAC followed by a thin-plate spline refinement or NiftyReg. The fusion of the transferred atlas labels is performed using a random forest classifier, and finally, the segmentation is obtained using graph cuts with a Potts model as interaction term. Our pipeline was evaluated on 20 organs in 10 whole-body CT images at the VISCERAL Anatomy Challenge, in conjunction with the International Symposium on Biomedical Imaging, Brooklyn, New York, in April 2015. It performed best on majority of the organs, with respect to the Dice index.
|
|
| 6. |
- Hellner, Qarin, et al.
(författare)
-
Effects of tillage and liming on macropore networks derived from X-ray tomography images of a silty clay soil
- 2018
-
Ingår i: Soil Use and Management. - : Wiley. - 0266-0032 .- 1475-2743. ; 34, s. 197-205
-
Tidskriftsartikel (refereegranskat)abstract
- Soil structure influences water infiltration, aeration and root growth and, thereby, also the conditions for sustainable crop production. Our objective was to quantify the effects of different soil management methods and land uses on the topsoil structure of a silty clay soil. We sampled 32 intact soil columns (18 cm high, 12.7 cm diameter) from an experimental silty clay field with four treatments: conventional tillage (CT), conventional tillage followed by liming (CTL), reduced tillage (RT) and unfertilized fallow (UF). The columns were analysed using 3-D X-ray tomography. The samples were taken in autumn after harvest, 7 yr after quick lime was applied to the CTL plots. Despite a relatively large number of replicates per treatment (8, 8, 8 and 6 (two UF samples were excluded), respectively), there were no significant differences between any of the investigated macropore network properties related to tilled treatments. The UF treatment, in contrast, exhibited more vertically oriented macropores, which were also better connected compared to the other treatments. This confirms previous findings that tillage may disrupt the vertical continuity of macropore clusters. The impact of liming on soil pore network properties may have been limited to pores smaller than the resolution in our X-ray images. It is also possible that the effects of lime on soil structure were limited to a few years which means that any effect would have diminished by the time of this study. These matters should be further investigated in follow-up studies to understand better the potential of lime amendments to clay soil.
|
|
| 7. |
- Kaboteh, Reza, et al.
(författare)
-
Convolutional neural network based quantification of choline uptake in PET/CT studies is associated with overall survival in patients with prostate cancer
- 2017
-
Ingår i: European Journal of Nuclear Medicine and Molecular Imaging. - 1619-7070 .- 1619-7089. ; 44:supplement 2
-
Tidskriftsartikel (refereegranskat)abstract
- Aim : To develop a convolutional neural network (CNN) based automated method for quantification of 18F-choline uptake in the prostate gland in PET/CT studies and to study the association between this measure, clinical data and overall survival in patients with prostate cancer. Methods : A CNN was trained to segment the prostate gland in CT images using manual segmentations performed by a radiologist in a group of 100 patients, who had undergone 18F-FDG PET/CT. After the training process, the CNN automatically segmented the prostate gland in the CT images and SUV values in the corresponding PET images were automatically analyzed in a separate validation group consisting of 45 patients with biopsy-proven hormone-naïve prostate cancer. All patients had undergone an 18F-choline PET/CT as part of a previous research project. Voxels localized in the prostate gland and having a SUV >2.65 were defined as abnormal, as proposed by Reske S et al. (2006). Automated calculation of the following five PET measurements was performed: maximal SUV within the prostate gland - SUVmax; average SUV for voxels with SUV >2.65 - SUVmean; volume of voxels with SUV >2.65 - VOL; fraction of VOL related to the whole volume of the prostate gland - FRAC; product SUVmean x FRAC defined as Total Lesion Uptake - TLU. The association between the automated PET measurements, age, PSA, Gleason score and overall survival (OS) was evaluated using a univariate Cox proportional hazards regression model. Kaplan-Meier analysis was used to estimate the survival difference (log-rank test). Results : TLU and FRAC were significantly associated with OS in the Cox analysis while the other three PET measurements; age, PSA and Gleason score were not. Kaplan-Meier analysis showed that patients with SUVmax <5.3, SUVmean <3.5 and TLU <1 showed significantly longer survival times than patients with values higher than these thresholds. No significant differences were found when patients were stratified based on the other two PET measurements, PSA or Gleason score. Conclusion : Measurements reflecting 18F-choline PET uptake in the prostate gland obtained using a completely automated method were significantly associated with OS in patients with hormone-naïve prostate cancer. This type of objective quantification of PET/CT studies could be of value also for other PET tracers and other cancers in the future.
|
|
| 8. |
- Kahl, Fredrik, 1972, et al.
(författare)
-
Good Features for Reliable Registration in Multi-Atlas Segmentation
- 2015
-
Ingår i: CEUR Workshop Proceedings. - 1613-0073. ; 1390:January, s. 12-17
-
Konferensbidrag (refereegranskat)abstract
- This work presents a method for multi-organ segmentation in whole-body CT images based on a multi-atlas approach. A robust and efficient feature-based registration technique is developed which uses sparse organ specific features that are learnt based on their ability to register different organ types accurately. The best fitted feature points are used in RANSAC to estimate an affine transformation, followed by a thin plate spline refinement. This yields an accurate and reliable nonrigid transformation for each organ, which is independent of initialization and hence does not suffer from the local minima problem. Further, this is accomplished at a fraction of the time required by intensity-based methods. The technique is embedded into a standard multi-atlas framework using label transfer and fusion, followed by a random forest classifier which produces the data term for the final graph cut segmentation. For a majority of the classes our approach outperforms the competitors at the VISCERAL Anatomy Grand Challenge on segmentation at ISBI 2015.
|
|
| 9. |
- Lind, Erica, et al.
(författare)
-
Automated quantification of reference levels in liver and mediastinum (blood pool) for the Deauville therapy response classification using FDG-PET/CT in lymphoma patients
- 2017
-
Ingår i: European Journal of Nuclear Medicine and Molecular Imaging. - 1619-7070 .- 1619-7089. ; 44:supplement 2
-
Tidskriftsartikel (refereegranskat)abstract
- Aim : To develop and validate a convolutional neural network (CNN) based method for automated quantification of reference levels in liver and mediastinum (blood pool) for the Deauville therapy response classification using FDG-PET/CT in lymphoma patients. Methods : CNNs were trained to segment the liver and the mediastinum, defined as the thoracic part of the aorta, in CT images from 81 consecutive lymphoma patients, who had undergone FDG-PET/CT examinations. Trained image readers segmented the liver and aorta manually in each of the CT images and these segmentations together with the CT images were used to train the CNN. After the training process, the CNN method was applied to a separate validation group consisting of six consecutive lymphoma patients (17-82 years, 3 female). First, the liver and mediastinum were automatically segmented in the CT images. Second, voxels in the corresponding FDG-PET images, which were localized in the liver and mediastinum, were selected and the median standard uptake value (SUV) was calculated. The CNN based analysis was compared to corresponding manual segmentations by two experienced radiologists. The Dice index was used to analyse the overlap between the segmentations by the CNN and the two radiologists. A Dice index of 1.00 indicates perfect matching. Results : The mean Dice indices for the comparison between CNN based liver segmentations and those of the two radiologists in the validation group were 0.95 and 0.95. A corresponding comparison between the two radiologists also resulted in a Dice index of 0.95. The mean liver volumes were 1,752ml, 1,757ml and 1,768ml for the CNN and two radiologists, respectively. The median SUV for the liver was on average 1.8 and the differences between median SUV based on CNN and manual segmentations were less or equal to 0.1. The mean Dice indices for the mediastinum were 0.80, 0.83 (CNN vs radiologists) and 0.86 (comparing the two radiologists). The mean mediastinum (aorta) volumes were 147ml, 140ml and 125ml for the CNN and two radiologists, respectively. The median SUV for the mediastinum was on average 1.4 and the differences between median SUV based on CNN and manual segmentations were less or equal to 0.14. Conclusion : A CNN based method for automated quantification of reference levels in liver and mediastinum show good agreement with results obtained by experienced radiologists, who manually segmented the CT images. This is a first and promising step towards a completely objective treatment response evaluation in patients with lymphoma based on FDG-PET/CT.
|
|
| 10. |
- Lindgren Belal, Sarah, et al.
(författare)
-
Deep learning for segmentation of 49 selected bones in CT scans: First step in automated PET/CT-based 3D quantification of skeletal metastases
- 2019
-
Ingår i: European Journal of Radiology. - : Elsevier BV. - 0720-048X .- 1872-7727. ; 113, s. 89-95
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: The aim of this study was to develop a deep learning-based method for segmentation of bones in CT scans and test its accuracy compared to manual delineation, as a first step in the creation of an automated PET/CT-based method for quantifying skeletal tumour burden. Methods: Convolutional neural networks (CNNs) were trained to segment 49 bones using manual segmentations from 100 CT scans. After training, the CNN-based segmentation method was tested on 46 patients with prostate cancer, who had undergone 18 F-choline-PET/CT and 18 F-NaF PET/CT less than three weeks apart. Bone volumes were calculated from the segmentations. The network's performance was compared with manual segmentations of five bones made by an experienced physician. Accuracy of the spatial overlap between automated CNN-based and manual segmentations of these five bones was assessed using the Sørensen-Dice index (SDI). Reproducibility was evaluated applying the Bland-Altman method. Results: The median (SD) volumes of the five selected bones were by CNN and manual segmentation: Th7 41 (3.8) and 36 (5.1), L3 76 (13) and 75 (9.2), sacrum 284 (40) and 283 (26), 7th rib 33 (3.9) and 31 (4.8), sternum 80 (11) and 72 (9.2), respectively. Median SDIs were 0.86 (Th7), 0.85 (L3), 0.88 (sacrum), 0.84 (7th rib) and 0.83 (sternum). The intraobserver volume difference was less with CNN-based than manual approach: Th7 2% and 14%, L3 7% and 8%, sacrum 1% and 3%, 7th rib 1% and 6%, sternum 3% and 5%, respectively. The average volume difference measured as ratio volume difference/mean volume between the two CNN-based segmentations was 5–6% for the vertebral column and ribs and ≤3% for other bones. Conclusion: The new deep learning-based method for automated segmentation of bones in CT scans provided highly accurate bone volumes in a fast and automated way and, thus, appears to be a valuable first step in the development of a clinical useful processing procedure providing reliable skeletal segmentation as a key part of quantification of skeletal metastases.
|
|
