IU Indianapolis ScholarWorks :: Browsing by Subject "Image processing"

Browsing by Subject "Image processing"

Now showing 1 - 10 of 16

AI in Medical Imaging Informatics: Current Challenges and Future Directions
(IEEE, 2020-07) Panayides, Andreas S.; Amini, Amir; Filipovic, Nenad D.; Sharma, Ashish; Tsaftaris, Sotirios A.; Young, Alistair; Foran, David; Do, Nhan; Golemati, Spyretta; Kurc, Tahsin; Huang, Kun; Nikita, Konstantina S.; Veasey, Ben P.; Zervakis, Michalis; Saltz, Joel H.; Pattichis, Constantinos S.; Biostatistics & Health Data Science, School of Medicine
This paper reviews state-of-the-art research solutions across the spectrum of medical imaging informatics, discusses clinical translation, and provides future directions for advancing clinical practice. More specifically, it summarizes advances in medical imaging acquisition technologies for different modalities, highlighting the necessity for efficient medical data management strategies in the context of AI in big healthcare data analytics. It then provides a synopsis of contemporary and emerging algorithmic methods for disease classification and organ/ tissue segmentation, focusing on AI and deep learning architectures that have already become the de facto approach. The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. Concluding, integrative analytics approaches driven by associate research branches highlighted in this study promise to revolutionize imaging informatics as known today across the healthcare continuum for both radiology and digital pathology applications. The latter, is projected to enable informed, more accurate diagnosis, timely prognosis, and effective treatment planning, underpinning precision medicine.
Analysis of Latent Space Representations for Object Detection
(2024-08) Dale, Ashley Susan; Christopher, Lauren; King, Brian; Salama, Paul; Rizkalla, Maher
Deep Neural Networks (DNNs) successfully perform object detection tasks, and the Con- volutional Neural Network (CNN) backbone is a commonly used feature extractor before secondary tasks such as detection, classification, or segmentation. In a DNN model, the relationship between the features learned by the model from the training data and the features leveraged by the model during test and deployment has motivated the area of feature interpretability studies. The work presented here applies equally to white-box and black-box models and to any DNN architecture. The metrics developed do not require any information beyond the feature vector generated by the feature extraction backbone. These methods are therefore the first methods capable of estimating black-box model robustness in terms of latent space complexity and the first methods capable of examining feature representations in the latent space of black box models. This work contributes the following four novel methodologies and results. First, a method for quantifying the invariance and/or equivariance of a model using the training data shows that the representation of a feature in the model impacts model performance. Second, a method for quantifying an observed domain gap in a dataset using the latent feature vectors of an object detection model is paired with pixel-level augmentation techniques to close the gap between real and synthetic data. This results in an improvement in the model’s F1 score on a test set of outliers from 0.5 to 0.9. Third, a method for visualizing and quantifying similarities of the latent manifolds of two black-box models is used to correlate similar feature representation with increase success in the transferability of gradient-based attacks. Finally, a method for examining the global complexity of decision boundaries in black-box models is presented, where more complex decision boundaries are shown to correlate with increased model robustness to gradient-based and random attacks.
Automated image classification via unsupervised feature learning by K-means
(2015-07-09) Karimy Dehkordy, Hossein; Dundar, Mehmet Murat; Song, Fengguang; Xia, Yuni
Research on image classification has grown rapidly in the field of machine learning. Many methods have already been implemented for image classification. Among all these methods, best results have been reported by neural network-based techniques. One of the most important steps in automated image classification is feature extraction. Feature extraction includes two parts: feature construction and feature selection. Many methods for feature extraction exist, but the best ones are related to deep-learning approaches such as network-in-network or deep convolutional network algorithms. Deep learning tries to focus on the level of abstraction and find higher levels of abstraction from the previous level by having multiple layers of hidden layers. The two main problems with using deep-learning approaches are the speed and the number of parameters that should be configured. Small changes or poor selection of parameters can alter the results completely or even make them worse. Tuning these parameters is usually impossible for normal users who do not have super computers because one should run the algorithm and try to tune the parameters according to the results obtained. Thus, this process can be very time consuming. This thesis attempts to address the speed and configuration issues found with traditional deep-network approaches. Some of the traditional methods of unsupervised learning are used to build an automated image-classification approach that takes less time both to configure and to run.
Computational analysis of pathological images enables a better diagnosis of TFE3 Xp11.2 translocation renal cell carcinoma
(Nature Research, 2020) Cheng, Jun; Han, Zhi; Mehra, Rohit; Shao, Wei; Cheng, Michael; Feng, Qianjin; Ni, Dong; Huang, Kun; Cheng, Liang; Zhang, Jie; Medicine, School of Medicine
TFE3 Xp11.2 translocation renal cell carcinoma (TFE3-RCC) generally progresses more aggressively compared with other RCC subtypes, but it is challenging to diagnose TFE3-RCC by traditional visual inspection of pathological images. In this study, we collect hematoxylin and eosin- stained histopathology whole-slide images of 74 TFE3-RCC cases (the largest cohort to date) and 74 clear cell RCC cases (ccRCC, the most common RCC subtype) with matched gender and tumor grade. An automatic computational pipeline is implemented to extract image features. Comparative study identifies 52 image features with significant differences between TFE3-RCC and ccRCC. Machine learning models are built to distinguish TFE3-RCC from ccRCC. Tests of the classification models on an external validation set reveal high accuracy with areas under ROC curve ranging from 0.842 to 0.894. Our results suggest that automatically derived image features can capture subtle morphological differences between TFE3-RCC and ccRCC and contribute to a potential guideline for TFE3-RCC diagnosis.
DeepSynth: Three-dimensional nuclear segmentation of biological images using neural networks trained with synthetic data
(Nature Research, 2019-12-04) Dunn, Kenneth W.; Fu, Chichen; Ho, David Joon; Lee, Soonam; Han, Shuo; Salama, Paul; Delp, Edward J.; Medicine, School of Medicine
The scale of biological microscopy has increased dramatically over the past ten years, with the development of new modalities supporting collection of high-resolution fluorescence image volumes spanning hundreds of microns if not millimeters. The size and complexity of these volumes is such that quantitative analysis requires automated methods of image processing to identify and characterize individual cells. For many workflows, this process starts with segmentation of nuclei that, due to their ubiquity, ease-of-labeling and relatively simple structure, make them appealing targets for automated detection of individual cells. However, in the context of large, three-dimensional image volumes, nuclei present many challenges to automated segmentation, such that conventional approaches are seldom effective and/or robust. Techniques based upon deep-learning have shown great promise, but enthusiasm for applying these techniques is tempered by the need to generate training data, an arduous task, particularly in three dimensions. Here we present results of a new technique of nuclear segmentation using neural networks trained on synthetic data. Comparisons with results obtained using commonly-used image processing packages demonstrate that DeepSynth provides the superior results associated with deep-learning techniques without the need for manual annotation.
Detection of Stroke, Blood Vessel Landmarks, and Leptomeningeal Anastomoses in Mouse Brain Imaging
(2022-12) Zhang, Leqi; Christopher, Lauren A.; King, Brian; Salama, Paul
Collateral connections in the brain, also known as Leptomeningeal Anastomoses, are connections between blood vessels originating from different arteries. Despite limited knowledge, they are suggested as an important contributor to cerebral stroke recovery that allows additional blood flow through the affected area. However, few databases and algorithms exist for this specific task of locating them. In this paper, a MATLAB program is developed to find these connections and detect strokes to replace manual labeling by professionals. The limited data available for this study are 23 2D microscopy images of mice cerebral vascular structures highlighted by dyes. In the images, strokes are shown to diminish the pixel count of vessels below 80\% compared to the healthy brain. Stroke classification error is greatly reduced by narrowing the scope from comparing the entire hemisphere to one smaller region. A novel way of finding collateral connections is utilizing connected components. Connected components organize all adjacent pixels into a group. All collateral connections can be found on the border of two neighboring arterial flow regions, and belong to the same group of connected components with the arterial source from each side. Along with finding collateral connections, a newly created coordinate system allows regions to be defined relative to the brain landmarks, based on the brain's center, orientation, and scale. The method newly proposed in this paper combines stroke detection, brain coordinate system extraction, and collateral connection detection in stroke-affected mouse brains using only image processing techniques. This allows a simpler, more explainable result on limited data than other techniques such as supervised machine learning. In addition, the new method does not require ground truth and high image count for training. This automated process was successfully interpreted by medical experts, which allows for further research into automating collateral connection detection in 3D.
Determination of Internal Elevation Fluctuation from CCTV Footage of Sanitary Sewers Using Deep Learning
(MDPI, 2021) Ji, Hyon Wook; Yoo, Sung Soo; Koo, Dan Daehyun; Kang, Jeong-Hee; Engineering Technology, School of Engineering and Technology
The slope of sewer pipes is a major factor for transporting sewage at designed flow rates. However, the gradient inside the sewer pipe changes locally for various reasons after construction. This causes flow disturbances requiring investigation and appropriate maintenance. This study extracted the internal elevation fluctuation from closed-circuit television investigation footage, which is required for sanitary sewers. The principle that a change in water level in sewer pipes indirectly indicates a change in elevation was applied. The sewage area was detected using a convolutional neural network, a type of deep learning technique, and the water level was calculated using the geometric principles of circles and proportions. The training accuracy was 98%, and the water level accuracy compared to random sampling was 90.4%. Lateral connections, joints, and outliers were removed, and a smoothing method was applied to reduce data fluctuations. Because the target sewer pipes are 2.5 m concrete reinforced pipes, the joint elevation was determined every 2.5 m so that the internal slope of the sewer pipe would consist of 2.5 m linear slopes. The investigative method proposed in this study is effective with high economic feasibility and sufficient accuracy compared to the existing sensor-based methods of internal gradient investigation.
High-throughput segmentation of unmyelinated axons by deep learning
(Springer Nature, 2022-01-24) Plebani, Emanuele; Biscola, Natalia P.; Havton, Leif A.; Rajwa, Bartek; Shemonti, Abida Sanjana; Jaffey, Deborah; Powley, Terry; Keast, Janet R.; Lu, Kun‑Han; Dundar, M. Murat; Computer and Information Science, School of Science
Axonal characterizations of connectomes in healthy and disease phenotypes are surprisingly incomplete and biased because unmyelinated axons, the most prevalent type of fibers in the nervous system, have largely been ignored as their quantitative assessment quickly becomes unmanageable as the number of axons increases. Herein, we introduce the first prototype of a high-throughput processing pipeline for automated segmentation of unmyelinated fibers. Our team has used transmission electron microscopy images of vagus and pelvic nerves in rats. All unmyelinated axons in these images are individually annotated and used as labeled data to train and validate a deep instance segmentation network. We investigate the effect of different training strategies on the overall segmentation accuracy of the network. We extensively validate the segmentation algorithm as a stand-alone segmentation tool as well as in an expert-in-the-loop hybrid segmentation setting with preliminary, albeit remarkably encouraging results. Our algorithm achieves an instance-level F1 score of between 0.7 and 0.9 on various test images in the stand-alone mode and reduces expert annotation labor by 80% in the hybrid setting. We hope that this new high-throughput segmentation pipeline will enable quick and accurate characterization of unmyelinated fibers at scale and become instrumental in significantly advancing our understanding of connectomes in both the peripheral and the central nervous systems.
Hydrodynamic delivery for the study, treatment and prevention of acute kidney injury
(2014-07-07) Corridon, Peter R.; Atkinson, Simon; Basile, David P.; Bacallao, Robert L.; Dunn, Kenneth William; Gattone II, Vincent H.
Advancements in human genomics have simultaneously enhanced our basic understanding of the human body and ability to combat debilitating diseases. Historically, research has shown that there have been many hindrances to realizing this medicinal revolution. One hindrance, with particular regard to the kidney, has been our inability to effectively and routinely delivery genes to various loci, without inducing significant injury. However, we have recently developed a method using hydrodynamic fluid delivery that has shown substantial promise in addressing aforesaid issues. We optimized our approach and designed a method that utilizes retrograde renal vein injections to facilitate widespread and persistent plasmid and adenoviral based transgene expression in rat kidneys. Exogenous gene expression extended throughout the cortex and medulla, lasting over 1 month within comparable expression profiles, in various renal cell types without considerably impacting normal organ function. As a proof of its utility we by attempted to prevent ischemic acute kidney injury (AKI), which is a leading cause of morbidity and mortality across among global populations, by altering the mitochondrial proteome. Specifically, our hydrodynamic delivery process facilitated an upregulated expression of mitochondrial enzymes that have been suggested to provide mediation from renal ischemic injury. Remarkably, this protein upregulation significantly enhanced mitochondrial membrane potential activity, comparable to that observed from ischemic preconditioning, and provided protection against moderate ischemia-reperfusion injury, based on serum creatinine and histology analyses. Strikingly, we also determined that hydrodynamic delivery of isotonic fluid alone, given as long as 24 hours after AKI is induced, is similarly capable of blunting the extent of injury. Altogether, these results indicate the development of novel and exciting platform for the future study and management of renal injury.
Longitudinal diffusion changes in prodromal and early HD: Evidence of white-matter tract deterioration
(Wiley, 2017-03) Shaffer, Joseph J.; Ghayoor, Ali; Long, Jeffrey D.; Kim, Regina Eun-Young; Lourens, Spencer; O’Donnell, Lauren J.; Westin, Carl-Fredrik; Rathi, Yogesh; Magnotta, Vincent; Paulsen, Jane S.; Johnson, Hans J.; Biostatistics, School of Public Health
INTRODUCTION: Huntington's disease (HD) is a genetic neurodegenerative disorder that primarily affects striatal neurons. Striatal volume loss is present years before clinical diagnosis; however, white matter degradation may also occur prior to diagnosis. Diffusion-weighted imaging (DWI) can measure microstructural changes associated with degeneration that precede macrostructural changes. DWI derived measures enhance understanding of degeneration in prodromal HD (pre-HD). METHODS: As part of the PREDICT-HD study, N = 191 pre-HD individuals and 70 healthy controls underwent two or more (baseline and 1-5 year follow-up) DWI, with n = 649 total sessions. Images were processed using cutting-edge DWI analysis methods for large multicenter studies. Diffusion tensor imaging (DTI) metrics were computed in selected tracts connecting the primary motor, primary somato-sensory, and premotor areas of the cortex with the subcortical caudate and putamen. Pre-HD participants were divided into three CAG-Age Product (CAP) score groups reflecting clinical diagnosis probability (low, medium, or high probabilities). Baseline and longitudinal group differences were examined using linear mixed models. RESULTS: Cross-sectional and longitudinal differences in DTI measures were present in all three CAP groups compared with controls. The high CAP group was most affected. CONCLUSIONS: This is the largest longitudinal DWI study of pre-HD to date. Findings showed DTI differences, consistent with white matter degeneration, were present up to a decade before predicted HD diagnosis. Our findings indicate a unique role for disrupted connectivity between the premotor area and the putamen, which may be closely tied to the onset of motor symptoms in HD. Hum Brain Mapp 38:1460-1477, 2017. © 2017 Wiley Periodicals, Inc.

Browsing by Subject "Image processing"

Results Per Page

Sort Options