| 1. |
- Platten, Michael
(author)
-
Quantitative MRI Biomarkers of Neurodegeneration in Multiple Sclerosis
- 2022
-
Doctoral thesis (other academic/artistic)abstract
- Background: Multiple sclerosis (MS) is a chronic neuroinflammatory and neurodegenerative disease that targets myelin in the brain and spinal cord. The corpus callosum connects the cerebral hemispheres and is composed of heavily myelinated axons. Atrophy of the corpus callosum has been explored as a more sensitive marker of disease status and neurodegeneration relative to other neuroanatomical structures. However, development of more accurate, precise and less labor demanding tools for characterizing callosal atrophy would increase its potential as a proxy marker of MS evolution.Purpose: The primary objective of this thesis was to evaluate and develop quantitative methods for measuring neurodegeneration in MS with a focus on the corpus callosum. This was achieved through the comparison of the accuracy and precision of manual delineation, conventional volumetric methods, and machine learning approaches.Study I: In a prospective study, 9 MS patients underwent scan/re-scanning with and without repositioning to measure the precision and accuracy of manual versus volumetric cross-sectional and longitudinal FreeSurfer analyses. While the longitudinal stream of FreeSurfer revealed the highest precision, the overall limitations on accuracy warrants caution.Study II: In a prospective study, 553 MS patients with 704 2D T2-weighted MRI acquisitions were used to train and validate a machine learning algorithm for segmenting a marker of neurodegeneration. The algorithm quickly produced highly accurate segmentations of the corpus callosum and brain (Dice Coefficient: 89% and 98%, respectively). The algorithm had numerically higher correlations to neurologic disability as compared to FreeSurfer.Study III: Analogous to Study II, in a prospective study, 631 MS patients with 3D T1-weighted and T2-weighted FLAIR acquisitions were used to train and validate a machine learning algorithm for segmenting the mid-sagittal normalized corpus callosum area. The algorithm performed better with T1-weighted scans and less atrophied patients. Scanner parameters had no significant effect on the T1-weighted output. The algorithm produced segmentations in less than a minute per scan, with similar correlations to neurologic disability, as compared to FreeSurfer.Study IV: In a prospective study, 92 MS patients acquired both 3 and 7 Tesla brain MRI scans to reveal the lobe-specific lesion volumes’ association to corpus callosum atrophy, where lesion burden was found to be greatest in the frontal and parietal lobes. In addition, the posterior portions of the corpus callosum provided the strongest fit linear regression models, with a combination of white matter lesions and intracortical lesions predicting atrophy.Conclusions: Creating and evaluating novel tools for measuring neurodegeneration over time is important both for monitoring disease progression and to evaluate therapeutic responses with current drugs. As novel therapeutic strategies appear, it may also help in assessing neuroregenerative approaches.
|
|
| 2. |
- Wang, Chunliang, 1980-
(author)
-
Computer Assisted Coronary CT Angiography Analysis : Disease-centered Software Development
- 2009
-
Licentiate thesis (other academic/artistic)abstract
- The substantial advances of coronary CTA have resulted in a boost of use of this new technique in the last several years, which brings a big challenge to radiologists by the increasing number of exams and the large amount of data for each patient. The main goal of this study was to develop a computer tool to facilitate coronary CTA analysis by combining knowledge of medicine and image processing.Firstly, a competing fuzzy connectedness tree algorithm was developed to segment the coronary arteries and extract centerlines for each branch. The new algorithm, which is an extension of the “virtual contrast injection” method, preserves the low density soft tissue around the coronary, which reduces the possibility of introducing false positive stenoses during segmentation.Secondly, this algorithm was implemented in open source software in which multiple visualization techniques were integrated into an intuitive user interface to facilitate user interaction and provide good over¬views of the processing results. Considerable efforts were put on optimizing the computa¬tional speed of the algorithm to meet the clinical requirements.Thirdly, an automatic seeding method, that can automatically remove rib cage and recognize the aortic root, was introduced into the interactive segmentation workflow to further minimize the requirement of user interactivity during post-processing. The automatic procedure is carried out right after the images are received, which saves users time after they open the data. Vessel enhance¬ment and quantitative 2D vessel contour analysis are also included in this new version of the software. In our preliminary experience, visually accurate segmentation results of major branches have been achieved in 74 cases (42 cases reported in paper II and 32 cases in paper III) using our software with limited user interaction. On 128 branches of 32 patients, the average overlap between the centerline created in our software and the manually created reference standard was 96.0%. The average distance between them was 0.38 mm, lower than the mean voxel size. The automatic procedure ran for 3-5 min as a single-thread application in the background. Interactive processing took 3 min in average with the latest version of software. In conclusion, the presented software provides fast and automatic coron¬ary artery segmentation and visualization. The accuracy of the centerline tracking was found to be acceptable when compared to manually created centerlines.
|
|
| 3. |
- Astaraki, Mehdi, PhD Student, 1984-
(author)
-
Advanced Machine Learning Methods for Oncological Image Analysis
- 2022
-
Doctoral thesis (other academic/artistic)abstract
- Cancer is a major public health problem, accounting for an estimated 10 million deaths worldwide in 2020 alone. Rapid advances in the field of image acquisition and hardware development over the past three decades have resulted in the development of modern medical imaging modalities that can capture high-resolution anatomical, physiological, functional, and metabolic quantitative information from cancerous organs. Therefore, the applications of medical imaging have become increasingly crucial in the clinical routines of oncology, providing screening, diagnosis, treatment monitoring, and non/minimally-invasive evaluation of disease prognosis. The essential need for medical images, however, has resulted in the acquisition of a tremendous number of imaging scans. Considering the growing role of medical imaging data on one side and the challenges of manually examining such an abundance of data on the other side, the development of computerized tools to automatically or semi-automatically examine the image data has attracted considerable interest. Hence, a variety of machine learning tools have been developed for oncological image analysis, aiming to assist clinicians with repetitive tasks in their workflow.This thesis aims to contribute to the field of oncological image analysis by proposing new ways of quantifying tumor characteristics from medical image data. Specifically, this thesis consists of six studies, the first two of which focus on introducing novel methods for tumor segmentation. The last four studies aim to develop quantitative imaging biomarkers for cancer diagnosis and prognosis.The main objective of Study I is to develop a deep learning pipeline capable of capturing the appearance of lung pathologies, including lung tumors, and integrating this pipeline into the segmentation networks to leverage the segmentation accuracy. The proposed pipeline was tested on several comprehensive datasets, and the numerical quantifications show the superiority of the proposed prior-aware DL framework compared to the state of the art. Study II aims to address a crucial challenge faced by supervised segmentation models: dependency on the large-scale labeled dataset. In this study, an unsupervised segmentation approach is proposed based on the concept of image inpainting to segment lung and head-neck tumors in images from single and multiple modalities. The proposed autoinpainting pipeline shows great potential in synthesizing high-quality tumor-free images and outperforms a family of well-established unsupervised models in terms of segmentation accuracy.Studies III and IV aim to automatically discriminate the benign from the malignant pulmonary nodules by analyzing the low-dose computed tomography (LDCT) scans. In Study III, a dual-pathway deep classification framework is proposed to simultaneously take into account the local intra-nodule heterogeneities and the global contextual information. Study IV seeks to compare the discriminative power of a series of carefully selected conventional radiomics methods, end-to-end Deep Learning (DL) models, and deep features-based radiomics analysis on the same dataset. The numerical analyses show the potential of fusing the learned deep features into radiomic features for boosting the classification power.Study V focuses on the early assessment of lung tumor response to the applied treatments by proposing a novel feature set that can be interpreted physiologically. This feature set was employed to quantify the changes in the tumor characteristics from longitudinal PET-CT scans in order to predict the overall survival status of the patients two years after the last session of treatments. The discriminative power of the introduced imaging biomarkers was compared against the conventional radiomics, and the quantitative evaluations verified the superiority of the proposed feature set. Whereas Study V focuses on a binary survival prediction task, Study VI addresses the prediction of survival rate in patients diagnosed with lung and head-neck cancer by investigating the potential of spherical convolutional neural networks and comparing their performance against other types of features, including radiomics. While comparable results were achieved in intra-dataset analyses, the proposed spherical-based features show more predictive power in inter-dataset analyses.In summary, the six studies incorporate different imaging modalities and a wide range of image processing and machine-learning techniques in the methods developed for the quantitative assessment of tumor characteristics and contribute to the essential procedures of cancer diagnosis and prognosis.
|
|
| 4. |
- Brusini, Irene
(author)
-
Methods for the analysis and characterization of brain morphology from MRI images
- 2022
-
Doctoral thesis (other academic/artistic)abstract
- Brain magnetic resonance imaging (MRI) is an imaging modality that produces detailed images of the brain without using any ionizing radiation. From a structural MRI scan, it is possible to extract morphological properties of different brain regions, such as their volume and shape. These measures can both allow a better understanding of how the brain changes due to multiple factors (e.g., environmental and pathological) and contribute to the identification of new imaging biomarkers of neurological and psychiatric diseases. The overall goal of the present thesis is to advance the knowledge on how brain MRI image processing can be effectively used to analyze and characterize brain structure.The first two works presented in this thesis are animal studies that primarily aim to use MRI data for analyzing differences between groups of interest. In Paper I, MRI scans from wild and domestic rabbits were processed to identify structural brain differences between these two groups. Domestication was found to significantly reshape brain structure in terms of both regional gray matter volume and white matter integrity. In Paper II, rat brain MRI scans were used to train a brain age prediction model. This model was then tested on both controls and a group of rats that underwent long-term environmental enrichment and dietary restriction. This healthy lifestyle intervention was shown to significantly affect the predicted brain age trajectories by slowing the rats' aging process compared to controls. Furthermore, brain age predicted on young adult rats was found to have a significant effect on survival.Papers III to V are human studies that propose deep learning-based methods for segmenting brain structures that can be severely affected by neurodegeneration. In particular, Papers III and IV focus on U-Net-based 2D segmentation of the corpus callosum (CC) in multiple sclerosis (MS) patients. In both studies, good segmentation accuracy was obtained and a significant correlation was found between CC area and the patient's level of cognitive and physical disability. Additionally, in Paper IV, shape analysis of the segmented CC revealed a significant association between disability and both CC thickness and bending angle. Conversely, in Paper V, a novel method for automatic segmentation of the hippocampus is proposed, which consists of embedding a statistical shape prior as context information into a U-Net-based framework. The inclusion of shape information was shown to significantly improve segmentation accuracy when testing the method on a new unseen cohort (i.e., different from the one used for training). Furthermore, good performance was observed across three different diagnostic groups (healthy controls, subjects with mild cognitive impairment and Alzheimer's patients) that were characterized by different levels of hippocampal atrophy.In summary, the studies presented in this thesis support the great value of MRI image analysis for the advancement of neuroscientific knowledge, and their contribution is mostly two-fold. First, by applying well-established processing methods on datasets that had not yet been explored in the literature, it was possible to characterize specific brain changes and disentangle relevant problems of a clinical or biological nature. Second, a technical contribution is provided by modifying and extending already-existing brain image processing methods to achieve good performance on new datasets.
|
|
