| 11. |
|
|
| 12. |
- Astaraki, Mehdi, PhD Student, 1984-, et al.
(författare)
-
Prior-aware autoencoders for lung pathology segmentation
- 2022
-
Ingår i: Medical Image Analysis. - : Elsevier BV. - 1361-8415 .- 1361-8423. ; 80, s. 102491-
-
Tidskriftsartikel (refereegranskat)abstract
- Segmentation of lung pathology in Computed Tomography (CT) images is of great importance for lung disease screening. However, the presence of different types of lung pathologies with a wide range of heterogeneities in size, shape, location, and texture, on one side, and their visual similarity with respect to surrounding tissues, on the other side, make it challenging to perform reliable automatic lesion seg-mentation. To leverage segmentation performance, we propose a deep learning framework comprising a Normal Appearance Autoencoder (NAA) model to learn the distribution of healthy lung regions and re-construct pathology-free images from the corresponding pathological inputs by replacing the pathological regions with the characteristics of healthy tissues. Detected regions that represent prior information re-garding the shape and location of pathologies are then integrated into a segmentation network to guide the attention of the model into more meaningful delineations. The proposed pipeline was tested on three types of lung pathologies, including pulmonary nodules, Non-Small Cell Lung Cancer (NSCLC), and Covid-19 lesion on five comprehensive datasets. The results show the superiority of the proposed prior model, which outperformed the baseline segmentation models in all the cases with significant margins. On av-erage, adding the prior model improved the Dice coefficient for the segmentation of lung nodules by 0.038, NSCLCs by 0.101, and Covid-19 lesions by 0.041. We conclude that the proposed NAA model pro-duces reliable prior knowledge regarding the lung pathologies, and integrating such knowledge into a prior segmentation network leads to more accurate delineations.
|
|
| 13. |
|
|
| 14. |
- Bendazzoli, Simone, et al.
(författare)
-
Automatic rat brain segmentation from MRI using statistical shape models and random forest
- 2019
-
Ingår i: MEDICAL IMAGING 2019. - : SPIE-INT SOC OPTICAL ENGINEERING. - 9781510625464 - 9781510625457
-
Konferensbidrag (refereegranskat)abstract
- In MRI neuroimaging, the shimming procedure is used before image acquisition to correct for inhomogeneity of the static magnetic field within the brain. To correctly adjust the field, the brain's location and edges must first be identified from quickly-acquired low resolution data. This process is currently carried out manually by an operator, which can be time-consuming and not always accurate. In this work, we implement a quick and automatic technique for brain segmentation to be potentially used during the shimming. Our method is based on two main steps. First, a random forest classifier is used to get a preliminary segmentation from an input MRI image. Subsequently, a statistical shape model of the brain, which was previously generated from ground-truth segmentations, is fitted to the output of the classifier to obtain a model-based segmentation mask. In this way, a-priori knowledge on the brain's shape is included in the segmentation pipeline. The proposed methodology was tested on low resolution images of rat brains and further validated on rabbit brain images of higher resolution. Our results suggest that the present method is promising for the desired purpose in terms of time efficiency, segmentation accuracy and repeatability. Moreover, the use of shape modeling was shown to be particularly useful when handling low-resolution data, which could lead to erroneous classifications when using only machine learning-based methods.
|
|
| 15. |
|
|
| 16. |
- Bendazzoli, Simone, et al.
(författare)
-
Lung vessel connectivity map as anatomical prior knowledge for deep learning-based lung lobe segmentation
- 2024
-
Ingår i: Journal of Medical Imaging. - : SPIE-Intl Soc Optical Eng. - 2329-4302 .- 2329-4310. ; 11:4
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose Our study investigates the potential benefits of incorporating prior anatomical knowledge into a deep learning (DL) method designed for the automated segmentation of lung lobes in chest CT scans. Approach We introduce an automated DL-based approach that leverages anatomical information from the lung's vascular system to guide and enhance the segmentation process. This involves utilizing a lung vessel connectivity (LVC) map, which encodes relevant lung vessel anatomical data. Our study explores the performance of three different neural network architectures within the nnU-Net framework: a standalone U-Net, a multitasking U-Net, and a cascade U-Net. Results Experimental findings suggest that the inclusion of LVC information in the DL model can lead to improved segmentation accuracy, particularly, in the challenging boundary regions of expiration chest CT volumes. Furthermore, our study demonstrates the potential for LVC to enhance the model's generalization capabilities. Finally, the method's robustness is evaluated through the segmentation of lung lobes in 10 cases of COVID-19, demonstrating its applicability in the presence of pulmonary diseases. Conclusions Incorporating prior anatomical information, such as LVC, into the DL model shows promise for enhancing segmentation performance, particularly in the boundary regions. However, the extent of this improvement has limitations, prompting further exploration of its practical applicability.
|
|
| 17. |
- Bilic, Patrick, et al.
(författare)
-
The Liver Tumor Segmentation Benchmark (LiTS)
- 2023
-
Ingår i: Medical Image Analysis. - : Elsevier BV. - 1361-8415 .- 1361-8423. ; 84, s. 102680-
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.
|
|
| 18. |
|
|
| 19. |
- Brusini, Irene, et al.
(författare)
-
Changes in brain architecture are consistent with altered fear processing in domestic rabbits
- 2018
-
Ingår i: Proceedings of the National Academy of Sciences of the United States of America. - : National Academy of Sciences. - 0027-8424 .- 1091-6490. ; 115:28, s. 7380-7385
-
Tidskriftsartikel (refereegranskat)abstract
- The most characteristic feature of domestic animals is their change in behavior associated with selection for tameness. Here we show, using high-resolution brain magnetic resonance imaging in wild and domestic rabbits, that domestication reduced amygdala volume and enlarged medial prefrontal cortex volume, supporting that areas driving fear have lost volume while areas modulating negative affect have gained volume during domestication. In contrast to the localized gray matter alterations, white matter anisotropy was reduced in the corona radiata, corpus callosum, and the subcortical white matter. This suggests a compromised white matter structural integrity in projection and association fibers affecting both afferent and efferent neural flow, consistent with reduced neural processing. We propose that compared with their wild ancestors, domestic rabbits are less fearful and have an attenuated flight response because of these changes in brain architecture.
|
|
| 20. |
- Brusini, Irene, et al.
(författare)
-
Fully automatic estimation of the waist of the nerve fiber layer at the optic nerve head angularly resolved
- 2021
-
Ingår i: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. - : SPIE-Intl Soc Optical Eng. ; , s. 1D1-1D8
-
Konferensbidrag (refereegranskat)abstract
- The present project aims at developing a fully automatic software for estimation of the waist of the nerve fiber layer in the Optic Nerve Head (ONH) angularly resolved in the frontal plane as a tool for morphometric monitoring of glaucoma. The waist of the nerve fiber layer is here defined as Pigment epithelium central limit –Inner limit of the retina – Minimal Distance, (PIMD). 3D representations of the ONH were collected with high resolution OCT in young not glaucomatous eyes and glaucomatous eyes. An improved tool for manual annotation was developed in Python. This tool was found user friendly and to provide sufficiently precise manual annotation. PIMD was automatically estimated with a software consisting of one AI model for detection of the inner limit of the retina and another AI model for localization of the Optic nerve head Pigment epithelium Central limit (OPCL). In the current project, the AI model for OPCL localization was retrained with new data manually annotated with the improved tool for manual annotation both in not glaucomatous eyes and in glaucomatous eyes. Finally, automatic annotations were compared to 3 annotations made by 3 independent annotators in an independent subset of both the not glaucomatous and the glaucomatous eyes. It was found that the fully automatic estimation of PIMD-angle overlapped the 3 manual annotators with small variation among the manual annotators. Considering interobserver variation, the improved tool for manual annotation provided less variation than our original annotation tool in not glaucomatous eyes suggesting that variation in glaucomatous eyes is due to variable pathological anatomy, difficult to annotate without error. The small relative variation in relation to the substantial overall loss of PIMD in the glaucomatous eyes compared to the not glaucomatous eyes suggests that our software for fully automatic estimation of PIMD-angle can now be implemented clinically for monitoring of glaucoma progression.
|
|
