Search results
(1 - 3 of 3)
- Title
- DEEP LEARNING FOR IMAGE PROCESSING WITH APPLICATIONS TO MEDICAL IMAGING
- Creator
- Zarshenas, Amin
- Date
- 2019
- Description
-
Deep Learning is a subfield of machine learning concerned with algorithms that learn hierarchical data representations. Deep learning has...
Show moreDeep Learning is a subfield of machine learning concerned with algorithms that learn hierarchical data representations. Deep learning has proven extremely successful in many computer vision tasks including object detection and recognition. In this thesis, we aim to develop and design deep-learning models to better perform image processing and tackle three important problems: natural image denoising, computed tomography (CT) dose reduction, and bone suppression in chest radiography (“chest x-ray”: CXR). As the first contribution of this thesis, we aimed to answer to probably the most critical design questions, under the task of natural image denoising. To this end, we defined a class of deep learning models, called neural network convolution (NNC). We investigated several design modules for designing NNC for image processing. Based on our analysis, we design a deep residual NNC (R-NNC) for this task. One of the important challenges in image denoising regards to a scenario in which the images have varying noise levels. Our analysis showed that training a single R-NNC on images at multiple noise levels results in a network that cannot handle very high noise levels; and sometimes, it blurs the high-frequency information on less noisy areas. To address this problem, we designed and developed two new deep-learning structures, namely, noise-specific NNC (NS-NNC) and a DeepFloat model, for the task of image denoising at varying noise levels. Our models achieved the highest denoising performance comparing to the state-of-the-art techniques.As the second contribution of the thesis, we aimed to tackle the task of CT dose reduction by means of our NNC. Studies have shown that high dose of CT scans can increase the risk of radiation-induced cancer in patients dramatically; therefore, it is very important to reduce the radiation dose as much as possible. For this problem, we introduced a mixture of anatomy-specific (AS) NNC experts. The basic idea is to train multiple NNC models for different anatomic segments with different characteristics, and merge the predictions based on the segmentations. Our phantom and clinical analysis showed that more than 90% dose reduction would be achieved using our AS NNC model.We exploited our findings from image denoising and CT dose reduction, to tackle the challenging task of bone suppression in CXRs. Most lung nodules that are missed by radiologists as well as by computer-aided detection systems overlap with bones in CXRs. Our purpose was to develop an imaging system to virtually separate ribs and clavicles from lung nodules and soft-tissue in CXRs. To achieve this, we developed a mixture of anatomy-specific, orientation-frequency-specific (ASOFS) expert deep NNC model. While our model was able to decompose the CXRs, to achieve an even higher bone suppression performance, we employed our deep R-NNC for the bone suppression application. Our model was able to create bone and soft-tissue images from single CXRs, without requiring specialized equipment or increasing the radiation dose.
Show less
- Title
- AI IN MEDICINE: ENABLING INTELLIGENT IMAGING, PROGNOSIS, AND MINIMALLY INVASIVE SURGERY
- Creator
- Getty, Neil
- Date
- 2022
- Description
-
While an extremely rich research field, compared to other applications of AI such as natural language processing (NLP) and image processing...
Show moreWhile an extremely rich research field, compared to other applications of AI such as natural language processing (NLP) and image processing/generation, AI in medicine has been much slower to be applied in real-world clinical settings. Often the stakes of failure are more dire, the access of private and proprietary data more costly, and the burden of proof required by expert clinicians is much higher. Beyond these barriers, the often typical data-driven approach towards validation is interrupted by a need for expertise to analyze results. Whereas the results of a trained Imagenet or machine translation model are easily verified by a computational researcher, analysis in medicine can be much more multi-disciplinary demanding. AI in medicine is motivated by a great demand for progress in health-care, but an even greater responsibility for high accuracy, model transparency, and expert validation.This thesis develops machine and deep learning techniques for medical image enhancement, patient outcome prognosis, and minimally invasive robotic surgery awareness and augmentation. Each of the works presented were undertaken in di- rect collaboration with medical domain experts, and the efforts could not have been completed without them. Pursuing medical image enhancement we worked with radiologists, neuroscientists and a neurosurgeon. In patient outcome prognosis we worked with clinical neuropsychologists and a cardiovascular surgeon. For robotic surgery we worked with surgical residents and a surgeon expert in minimally invasive surgery. Each of these collaborations guided priorities for problem and model design, analysis, and long-term objectives that ground this thesis as a concerted effort towards clinically actionable medical AI. The contributions of this thesis focus on three specific medical domains. (1) Deep learning for medical brain scans: developed processing pipelines and deep learn- ing models for image annotation, registration, segmentation and diagnosis in both traumatic brain injury (TBI) and brain tumor cohorts. A major focus of these works is on the efficacy of low-data methods, and techniques for validation of results without any ground truth annotations. (2) Outcome prognosis for TBI and risk prediction for Cardiovascular Disease (CVD): we developed feature extraction pipelines and models for TBI and CVD patient clinical outcome prognosis and risk assessment. We design risk prediction models for CVD patients using traditional Cox modeling, machine learning, and deep learning techniques. In this works we conduct exhaustive data and model ablation study, with a focus on feature saliency analysis, model transparency, and usage of multi-modal data. (3) AI for enhanced and automated robotic surgery: we developed computer vision and deep learning techniques for understanding and augmenting minimally invasive robotic surgery scenes. We’ve developed models to recognize surgical actions from vision and kinematic data. Beyond model and techniques, we also curated novel datasets and prediction benchmarks from simulated and real endoscopic surgeries. We show the potential for self-supervised techniques in surgery, as well as multi-input and multi-task models.
Show less
- Title
- LOCAL VISCOELASTIC PROPERTIES OF SOFT ANISOTROPIC FIBROUS TISSUE
- Creator
- Gallo, Nicolas Remy
- Date
- 2020
- Description
-
The current aging population, with more than 80 million "baby boomers", will present a steep medical challenge for our society in a...
Show moreThe current aging population, with more than 80 million "baby boomers", will present a steep medical challenge for our society in a foreseeable future. Half of the adults over 85 years old are predicted to be diagnosed with Alzheimer's disease by 2050. With healthcare cost reaching over 700 billion dollars in the United States, early detection of Alzheimer's disease (AD) and other co-existing neurodegenerative diseases is crucial to improve the recovery odds in patients and to decrease individual care cost. This work seeks to tackle this problem by proposing a novel computational framework toward improving the measurement of shear visco-elastic properties of brain white matter (WM), which vary with age. These measurements practically represent the effective (average) response of many cells and are typically obtained by using rheology or elastography. Although the former is direct, the latter requires the solution of an inverse problem based on a priori mechanical tissue model. The mechanical anisotropy of WM has previously not been fully explored although many inconsistencies have been reported in brain MRE experiments. To account for these inconsistencies a transversely isotropic constitutive model for the brain WM is proposed to interpret prior experiments involving 7 young and 4 older healthy men. By employing a novel inversion scheme, we report the local variation of the effective transverse and axial shear moduli in two well aligned WM structures (corpus callosum: CC; and cortical spinal tract: CST) for both the young and old cohort of healthy subjects part of the study. This work reports statistically significant changes in local regional variation of the transverse modulus across the CC for the young cohort. In the older cohort, the trend was similar yet not statistically significant. A novel candidate biomarker, the shear anisotropy metric, defined as the ratio of the transverse and axial shear moduli, found statistically significant local regional variation across the CC but not in the CST. Healthy aging was observed to decrease both transverse and axial in both CC and CST, although the variation was significant only for the CC. Finally, in an effort to understand the cause of effective transverse mechanical properties variation in WM with aging, the connection between effective and intrinsic contribution of WM cellular constituents is established. The intrinsic mechanical contributions of axons and glial matrix are separated by fitting the estimates of the effective shear moduli to a microscopic composite fiber model of myelinated axons embedded in the glial matrix. This work provides a method to establish a baseline for healthy brain mechanical properties thus promising to increase the specificity of MRE toward early diagnosis of neurodegenerative diseases. Additional oscillating disc rheology experiments with decellularized porcine myocardium, and the fabrication of a stable heterogeneous phantom matching the mechanical, diffusional and electrical properties of the WM provide foundational knowledge for due development and validation of MRE methodologies employed in other tissues.
Show less