Biomedical | Open Access Articles | Digital Commons Network™

Advancing Electrical Stimulation: Full-Head Mri Segmentation For Abnormal Brain Anatomy With Tdcs, Andrew Birnbaum

Dissertations and Theses

Evaluating the effectiveness of transcranial direct current stimulation (tDCS) is essential for guiding its integration into therapeutic and performance-enhancement applications. In our laboratory, we investigate the efficacy of tDCS across multiple experimental models, including both animal and human studies. I have contributed significantly to the execution and analysis of these experiments, which include studies in rats and healthy human participants aimed at evaluating whether electrical stimulation of the motor cortex can enhance motor learning. These studies assess improvements in fine motor performance resulting from tDCS. In stroke patients, I contribute to our investigation of tDCS as a rehabilitative intervention, particularly …

Go to article

Advancing Brain Tumor Segmentation With Spectral–Spatial Graph Neural Networks, Sina Mohammadi, Mohamed Allali

Engineering Faculty Articles and Research

In the field of brain tumor segmentation, accurately capturing the complexities of tumor sub-regions poses significant challenges. Traditional segmentation methods usually fail to accurately segment tumor subregions. This research introduces a novel solution employing Graph Neural Networks (GNNs), enriched with spectral and spatial insight. In the supervoxel creation phase, we explored methods like VCCS, SLIC, Watershed, Meanshift, and Felzenszwalb–Huttenlocher, evaluating their performance based on homogeneity, moment of inertia, and uniformity in shape and size. After creating supervoxels, we represented 3D MRI images as a graph structure. In this study, we combined Spatial and Spectral GNNs to capture both local and …

Go to article

Adversarial Training Based Domain Adaptation Of Skin Cancer Images, Syed Qasim Gilani, Muhammad Umair, Maryam Naqvi, Oge Marques, Hee-Cheol Kim

Electrical & Computer Engineering Faculty Publications

Skin lesion datasets used in the research are highly imbalanced; Generative Adversarial Networks can generate synthetic skin lesion images to solve the class imbalance problem, but it can result in bias and domain shift. Domain shifts in skin lesion datasets can also occur if different instruments or imaging resolutions are used to capture skin lesion images. The deep learning models may not perform well in the presence of bias and domain shift in skin lesion datasets. This work presents a domain adaptation algorithm-based methodology for mitigating the effects of domain shift and bias in skin lesion datasets. Six experiments were …

Go to article

Qu-Brats: Miccai Brats 2020 Challenge On Quantifying Uncertainty In Brain Tumor Segmentation - Analysis Of Ranking Scores And Benchmarking Results, Raghav Mehta, Angelos Filos, Ujjwal Baid, Chiharu Sako, Richard Mckinley, Michael Rebsamen, Katrin Dätwyler, Raphael Meier, Piotr Radojewski, Gowtham Krishnan Murugesan, Sahil Nalawade, Chandan Ganesh, Ben Wagner, Fang F. Yu, Baowei Fei, Ananth J. Madhuranthakam, Joseph A. Maldjian, Laura Daza, Catalina Gómez, Pablo Arbeláez, Chengliang Dai, Shuo Wang, Hadrien Reynaud, Yuan-Han Mo, Elsa Angelini, Yike Guo, Wenjia Bai, Subhashis Banerjee, Lin-Min Pei, Murat Ak, Sarahi Rosas-González, Ilyess Zemmoura, Clovis Tauber, Minh H. Vu, Tufve Nyholm, Tommy Löfstedt, Laura Mora Ballestar, Veronica Vilaplana, Hugh Mchugh, Gonzalo Maso Talou, Alan Wang, Jay Patel, Ken Chang, Katharina Hoebel, Mishka Gidwani, Nishanth Arun, Sharut Gupta, Mehak Aggarwal, Praveer Singh, Elizabeth R. Gerstner, Jayashree Kalpathy-Cramer, Nicholas Boutry, Alexis Huard, Lasitha Vidyaratne, Md. Monibor Rahman, Khan M. Iftekharuddin, Joseph Chazalon, Elodie Puybareau, Guillaume Tochon, Jun Ma, Mariano Cabezas, Xavier Llado, Arnau Oliver, Liliana Valencia, Sergi Valverde, Mehdi Amian, Mohammadreza Soltaninejad, Andriy Myronenko, Ali Hatamizadeh, Xue Feng, Quan Dou, Nicholas Tustison, Craig Meyer, Nisarg A. Shah, Sanjay Talbar, Marc-André Weber, Abhishek Mahajan, Andras Jakab, Roland Wiest, Hassan M. Fathallah-Shaykh, Arash Nazeri, Mikhail Milchenko1, Daniel Marcus, Aikaterini Kotrotsou, Rivka Colen, John Freymann, Justin Kirby, Christos Davatzikos, Bjoern Menze, Spyridon Bakas, Yarin Gal, Tal Arbel

Electrical & Computer Engineering Faculty Publications

Deep learning (DL) models have provided the state-of-the-art performance in a wide variety of medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder the translation of DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties, could enable clinical review of the most uncertain regions, thereby building trust and paving the way towards clinical translation. Recently, a number of uncertainty estimation methods have been introduced for DL medical image segmentation tasks. …

Go to article

Biological Semantic Segmentation On Ct Medical Images For Kidney Tumor Detection Using Nnu-Net Framework, Andres Bergsneider

Master's Theses

Healthcare systems are constantly challenged with bottlenecks due to human-reliant operations, such as analyzing medical images. High precision and repeatability is necessary when performing a diagnostics on patients with tumors. Throughout the years an increasing number of advancements have been made using various machine learning algorithms for the detection of tumors helping to fast track diagnosis and treatment decisions. “Black Box” systems such as the complex deep learning networks discussed in this paper rely heavily on hyperparameter optimization in order to obtain the most ideal performance. This requires a signiﬁcant time investment in the tuning of such networks to acquire …

Go to article

Fly-In Visualization Of Tubular Objects: Theory And Application In Virtual Colonoscopy., Mostafa Mohamed

Electronic Theses and Dissertations

In this dissertation, visualization for tubular objects, i.e., projecting 2D images from 3D inner surfaces of tubular objects, is investigated. Given surface points on 3D objects, an approach that most accurately and effectively projects 2D images from the 3D surface with minimal loss of information is desired. A new visualization method for tubular surfaces is proposed, denoted by "Fly-In". The approach uses a virtual camera ring that moves along the inner surface's centerline, obtaining projections of the surrounding views, forming small 3D topological rings within the tube rendered as a 2D rectangular image. A new visualization loss measure is also …

Go to article

Deformable Contour Models For Digitizing A Printed Brainstem Atlas, Nirmal J. Patel

Electrical & Computer Engineering Theses & Dissertations

The brainstem is a part of the brain that is connected to the cerebrum and the spinal cord. Ten out of twelve pairs of cranial nerves emerge from the brainstem. The cranial nerves transmit information between the brain and various parts of the body. Due to its anatomical and physiological relevance, a descriptive digital brainstem is important for neurosurgery planning and simulation. For both of these neurosurgical applications, the complexity of the brainstem requires a digital atlas approach to segmentation that maps intensities to tissues rather than less descriptive voxel or surface-based approaches. However, a descriptive brainstem atlas with adequate …

Go to article

An Iris Authentication System Based On Artificial Neural Networks, Brenden Velu

Electrical Engineering

An iris authentication system verifies the authenticity of a person based on their iris features. The iris features are extracted through wavelet transform of the isolated iris from modified iris images. A level 5 wavelet decomposition is performed on the images, and the resulting low-frequency wavelet coefficients represent the inputs to the artificial neural network. The artificial neural network reads these features as inputs, and classifies each set of inputs according to their target identity. This authentication system currently classifies up to 10 people. The irises used for classification represent ideal situations with minimum eyelash and eyelid interference.

Go to article

Multi-Surface Simplex Spine Segmentation For Spine Surgery Simulation And Planning, Rabia Haq

Computational Modeling & Simulation Engineering Theses & Dissertations

This research proposes to develop a knowledge-based multi-surface simplex deformable model for segmentation of healthy as well as pathological lumbar spine data. It aims to provide a more accurate and robust segmentation scheme for identification of intervertebral disc pathologies to assist with spine surgery planning. A robust technique that combines multi-surface and shape statistics-aware variants of the deformable simplex model is presented. Statistical shape variation within the dataset has been captured by application of principal component analysis and incorporated during the segmentation process to refine results. In the case where shape statistics hinder detection of the pathological region, user-assistance is …

Go to article

Psychophysical Similarity Based Feature Selection For Nodule Retrieval In Ct, Ravi K. Samala

Open Access Theses & Dissertations

The emerging paradigms in cancer research indicate the need for a multi-perspective and multi-modal screening approach for early lung cancer diagnosis to increase the probability of clinical resection. Currently no standalone screening methodology is proved to suffice for a clinical diagnosis. Computed tomography has been proved to present abnormality at an early stage with less impact on survival rate in population studies. Nevertheless, because of its non-invasive characteristic, it can be used for diagnosis, prognosis and visualization of tumor. Studies have shown that Computer aided diagnosis (CAD) as a second reader can perform in a similar capacity as a radiologist. …

Go to article

Biomedical Commons^™

Full-Text Articles in Biomedical

Advancing Electrical Stimulation: Full-Head Mri Segmentation For Abnormal Brain Anatomy With Tdcs, Andrew Birnbaum

Dissertations and Theses

Advancing Brain Tumor Segmentation With Spectral–Spatial Graph Neural Networks, Sina Mohammadi, Mohamed Allali

Engineering Faculty Articles and Research

Adversarial Training Based Domain Adaptation Of Skin Cancer Images, Syed Qasim Gilani, Muhammad Umair, Maryam Naqvi, Oge Marques, Hee-Cheol Kim

Electrical & Computer Engineering Faculty Publications

Electrical & Computer Engineering Faculty Publications

Biological Semantic Segmentation On Ct Medical Images For Kidney Tumor Detection Using Nnu-Net Framework, Andres Bergsneider

Master's Theses

Fly-In Visualization Of Tubular Objects: Theory And Application In Virtual Colonoscopy., Mostafa Mohamed

Electronic Theses and Dissertations

Deformable Contour Models For Digitizing A Printed Brainstem Atlas, Nirmal J. Patel

Electrical & Computer Engineering Theses & Dissertations

An Iris Authentication System Based On Artificial Neural Networks, Brenden Velu

Electrical Engineering

Multi-Surface Simplex Spine Segmentation For Spine Surgery Simulation And Planning, Rabia Haq

Computational Modeling & Simulation Engineering Theses & Dissertations

Psychophysical Similarity Based Feature Selection For Nodule Retrieval In Ct, Ravi K. Samala

Open Access Theses & Dissertations