Prof. Scott E. Umbaugh Profile

Prof. Scott E. Umbaugh

Emeritus Distinguished Research Professor at Southern Illinois Univ Edwardsville

SPIE Involvement:

Author

Publications (24)

Proceedings Article | 30 September 2024 Presentation + Paper

Land cover classification of satellite images using deep learning

Md Sami Ul Hoque, Al Mahmud, Roshan Silwal, Hanieh Ajami, Mahdi Kargar Nigjeh, Scott Umbaugh

Proceedings Volume 13137, 131370L (2024) https://doi.org/10.1117/12.3028330

KEYWORDS: Data modeling, Image classification, Deep learning, Performance modeling, Image segmentation, Matrices, Satellite imaging, Agriculture, Image processing, Environmental monitoring, Environmental management, Computer vision technology

Read Abstract +

Proceedings Article | 30 September 2024 Presentation + Paper

Comparative analysis of deep learning models for brain tumor classification in MRI images using enhanced preprocessing techniques

Mahdi Kargar Nigjeh, Hanieh Ajami, Al Mahmud, Md Sami Ul Hoque, Scott Umbaugh

Proceedings Volume 13137, 1313706 (2024) https://doi.org/10.1117/12.3028318

KEYWORDS: Tumors, Brain, Neuroimaging, Magnetic resonance imaging, Image classification, Deep learning, Tunable filters, Digital filtering, Data modeling, Education and training

Read Abstract +

This research introduces a novel approach to automate the classification of brain tumors in MRI images by leveraging three prominent deep learning models: VGG16, ResNet18, and DenseNet. The study harnesses datasets from Figshare, the SARTAJ, and Br35H, comprising 7023 human brain MRI images categorized into glioma, meningioma, no tumor, and pituitary classes. Data augmentation techniques are performed to improve the learning process, optimizing the models for discerning intricate patterns within the diverse tumor categories.

In contrast to conventional methods, the proposed methodology incorporates an advanced image enhancement algorithm. This algorithm involves a multi-step preprocessing approach, including applying a Kuwahara filter, a median filter, and a homomorphic sharpening filter. The primary purpose is to enhance the visibility of tumor structures in MRI images, effectively highlighting relevant features while mitigating unwanted details and noise.

This study adopts a comparative analysis strategy, independently employing VGG16, ResNet18, and DenseNet pretrained models to classify brain tumors. By evaluating and contrasting the performance of these models, we aim to identify the most adequate one in terms of accuracy and efficiency. Our findings demonstrate that implementing this methodology with deep learning architectures results in an outstanding classification accuracy of up to 95%.

This research brings significant progress to automated brain tumor classification by providing detailed insights into the strengths and limitations of various deep-learning models used in medical imaging. The results serve as a practical guide for future research, which could lead to the development of more accurate diagnostic tools. Specifically, the findings can help create targeted tools for diagnosing glioma, meningioma, no tumor, and pituitary classes, which could bring advancements in medical imaging technology, leading to more efficient neurology diagnostics.

Proceedings Article | 30 September 2024 Presentation + Paper

BetaVAEClassifier versus PCAEClassifier: investigating variational autoencoder and classification for accurate identification of white lesions in multiple sclerosis brain MRIs

Hanieh Ajami, Al Mahmud, Mahdi Kargar Nigjeh, Md Sami Ul Hoque, Heena Chakradhar, Scott Umbaugh

Proceedings Volume 13137, 1313703 (2024) https://doi.org/10.1117/12.3027808

KEYWORDS: Multiple sclerosis, Education and training, Data modeling, Machine learning, Performance modeling, Magnetic resonance imaging, Image classification, Nanooptomechanical systems, Deep learning, Brain

Read Abstract +

Multiple sclerosis is one of the critical autoimmune diseases that require early detection. The central nervous system (CNS) is demyelinated by multiple sclerosis (MS), which causes lesions in both the grey and white matter (GM and WM). However, the lesions in the WM are most frequently seen on routinely obtained clinical scans. Magnetic resonance imaging (MRI) is used to identify these lesions. As part of the clinical diagnostic process, the variation in lesion charge obtained in the various MRI sequences is an important criterion indicating disease progression in terms of volume and localization as well as providing information on the efficacy of therapy. Manual segmentation, while still being used, is not ideal due to its reliance on expert knowledge, time-consuming nature, and susceptibility to variations among different experts. To address these challenges, demonstrating a tremendous deal of promise to support the diagnostic procedure of professionals, deep learning is one such subject that focuses on developing sophisticated algorithms to automate diagnosis. This research compares two different deep learning techniques (PCAEClassifier, BetaVAEClassifier) for automatically analyzing brain MRI scans from multiple sclerosis (MS) patients. The goal is to identify these WMLs and classify them into two classes, the class that contains the MRIs with white matter lesions, and the other class is for MRIs that do not have these lesions, ultimately helping diagnose and assess this disease. The performance of each model was then evaluated using the metrics of accuracy, precision, recall, and F-score. It is evident that the choice of hyperparameters significantly impacts the model's performance. For the BetaVAEClassifier, the model's performance varied significantly with different beta values. With a beta (β) of 20, the model achieved an accuracy of 87.61%, maintaining a balanced performance with precision, recall, and F1-score hovering around 87%. Similarly, for the PCAEClassifier, the model's performance varied with different sparsity parameters (S). With S equal to 20, the model achieved the highest accuracy of 88.82%, accompanied by precision, recall, and F1-score of 90.38%, 86.40%, and 88.34%, respectively. These models' sensitivity to hyperparameters highlights the intricate balance required in model configuration, especially in tasks where precision and recall are crucial, such as anomaly detection. Particularly in medical diagnostics like multiple sclerosis (MS) classification, where accurately distinguishing between affected and unaffected individuals is paramount, the performance of these models holds significant promise. Leveraging their capabilities for anomaly detection in medical imaging, particularly in the context of MS classification, could lead to earlier and more accurate diagnoses, enabling timely intervention and improved patient outcomes.

Proceedings Article | 30 September 2024 Presentation + Paper

Comparative evaluation of two algorithmic methods to enhance autonomous vehicle vision through de-raining imagery techniques

Hanieh Ajami, Mahdi Kargar Nigjeh, Mahsa Kargar Nigjeh, Scott Umbaugh

Proceedings Volume 13137, 131370G (2024) https://doi.org/10.1117/12.3027823

KEYWORDS: Rain, Image processing, Algorithm development, Unmanned vehicles, Image enhancement, Detection and tracking algorithms, Image quality, Image sharpness, Image filtering, Tunable filters

Read Abstract +

Proceedings Article | 30 September 2024 Presentation + Paper

Automated retinal disorders classification: leveraging digital image enhancement techniques and deep learning on OCT images

Mahdi Kargar Nigjeh, Mahsa Kargar Nigjeh, Scott Umbaugh

Proceedings Volume 13137, 131370K (2024) https://doi.org/10.1117/12.3028346

KEYWORDS: Image enhancement, Optical coherence tomography, Deep learning, Education and training, Retinal diseases, Artificial intelligence, Image classification, Eye models, Data modeling, Image processing

Read Abstract +

Proceedings Article | 30 September 2024 Presentation + Paper

Comparison of performance of two deep learning models for classification of skin lesions using image resampling technique for data augmentation

Al Mahmud, Hanieh Ajami, Md Sami Ul Hoque, Roshan Silwal, Mahdi Kargar Nigjeh, Scott Umbaugh

Proceedings Volume 13137, 1313705 (2024) https://doi.org/10.1117/12.3027916

KEYWORDS: Deep learning, Skin, Performance modeling, Image classification, Image processing

Read Abstract +

Proceedings Article | 30 September 2024 Presentation + Paper

Comparative analysis of white matter lesion segmentation in multiple sclerosis patients' MRIs: evaluating the results of FCNN architecture and CVIPtools software on compressed image data

Hanieh Ajami, Heena Chakradhar, Mahdi Kargar Nigjeh, Al Mahmud, Md Sami Ul Hoque, Scott Umbaugh

Proceedings Volume 13137, 1313704 (2024) https://doi.org/10.1117/12.3027815

KEYWORDS: Image compression, Deep learning, Multiple sclerosis, Machine learning, Magnetic resonance imaging, Data modeling, Image classification, Image segmentation, Medical imaging, Education and training

Read Abstract +

Proceedings Article | 4 October 2023 Paper

Automated classification of white matter lesions in multiple sclerosis patients' MRI images using gray level enhancement and deep learning

Mahsa Kargar Nigjeh, Hanieh Ajami, Scott Umbaugh

Proceedings Volume 12674, 1267411 (2023) https://doi.org/10.1117/12.2688269

KEYWORDS: Multiple sclerosis, Magnetic resonance imaging, Education and training, Image classification, Deep learning, White matter, RGB color model, Classification systems, Neuroimaging, Data modeling

Read Abstract +

Proceedings Article | 4 October 2023 Paper

Unsupervised white matter lesion identification in multiple sclerosis (MS) using MRI segmentation and pattern classification: a novel approach with CVIPtools

Hanieh Ajami, Mahsa Kargar Nigjeh, Scott Umbaugh

Proceedings Volume 12674, 1267410 (2023) https://doi.org/10.1117/12.2688268

KEYWORDS: Digital image processing, Multiple sclerosis, Magnetic resonance imaging, Image segmentation, Image classification, White matter, Feature extraction, Brain, Image processing algorithms and systems, Image processing, Algorithm development

Read Abstract +

Proceedings Article | 12 April 2021 Presentation + Paper

Automatic mask creation of thermographic gait images using CVIPtools ATAT

Charles Stacey, Scott Umbaugh, Dominic Marino, Joseph Sackman

Proceedings Volume 11743, 1174305 (2021) https://doi.org/10.1117/12.2585646

KEYWORDS: Gait analysis, Image segmentation, Algorithm development, Machine vision, Image processing, Computer vision technology, Analytical research

Read Abstract +

Proceedings Article | 12 April 2021 Poster + Presentation + Paper

Machine learning with a convolutional neural network for segmentation of ophthalmological images

Hridoy Biswas, Scott Umbaugh

Proceedings Volume 11731, 117310C (2021) https://doi.org/10.1117/12.2587516

KEYWORDS: Image segmentation, Machine learning, Blood vessels, Convolutional neural networks, Convolution, Computer programming, Sensors, Retina, Neural networks, Eye

Read Abstract +

Proceedings Article | 12 April 2021 Presentation + Paper

Comparison of K-means and K-means++ for image compression with thermographic images

Hridoy Biswas, Scott Umbaugh, Dominic Marino, Joseph Sackman

Proceedings Volume 11743, 117430U (2021) https://doi.org/10.1117/12.2587264

KEYWORDS: Image compression, Image processing algorithms and systems, Cancer, Signal to noise ratio, Image segmentation, Algorithm development, Visualization, Machine learning, MATLAB, Image analysis

Read Abstract +

Proceedings Article | 23 April 2020 Presentation + Paper

Identification of bone cancer in canine thermograms

Naveena Gorre, Scott Umbaugh, Dominic Marino, Joseph Sackman

Proceedings Volume 11409, 1140903 (2020) https://doi.org/10.1117/12.2554490

KEYWORDS: Cancer, Bone, Algorithm development, Image classification, Image processing, Databases, Feature extraction, Distance measurement, Machine vision, Computer vision technology

Read Abstract +

Proceedings Article | 2 May 2019 Presentation + Paper

Detection of syrinx in thermographic images of canines with Chiari malformation using MATLAB CVIP toolbox GUI

A. Karlapalem, J. Cuellar , S. Umbaugh, D. Marino, J. Sackman

Proceedings Volume 11004, 1100405 (2019) https://doi.org/10.1117/12.2519112

KEYWORDS: MATLAB, Feature extraction, Image classification, Software development, Image segmentation, Image processing, Cameras, Algorithm development, Distance measurement, Machine vision

Read Abstract +

Proceedings Article | 19 September 2017 Paper

Veterinary software application for comparison of thermograms for pathology evaluation

Gita Pant, Scott Umbaugh, Rohini Dahal, Norsang Lama, Dominic Marino, Joseph Sackman

Proceedings Volume 10396, 103962B (2017) https://doi.org/10.1117/12.2273077

KEYWORDS: Pathology, Feature extraction, Thermography, Medical imaging, Machine vision, Computer vision technology, Digital image processing, Image classification, Software development, Image processing

Read Abstract +

Proceedings Article | 5 May 2017 Paper

Thermography based prescreening software tool for veterinary clinics

Rohini Dahal, Scott Umbaugh, Deependra Mishra, Norsang Lama, Mehrdad Alvandipour, David Umbaugh, Dominic Marino, Joseph Sackman

Proceedings Volume 10214, 102141A (2017) https://doi.org/10.1117/12.2260758

KEYWORDS: Algorithm development, Databases, Cameras, Imaging systems, Thermography, Image classification, Pathology, Image fusion, Infrared imaging, Feature extraction, Software development, Bone, Cancer, Computed tomography

Read Abstract +

Proceedings Article | 5 May 2017 Paper

Thermographic image analysis for classification of ACL rupture disease, bone cancer, and feline hyperthyroid, with Gabor filters

Mehrdad Alvandipour, Scott Umbaugh, Deependra Mishra, Rohini Dahal, Norsang Lama, Dominic Marino, Joseph Sackman

Proceedings Volume 10214, 102140B (2017) https://doi.org/10.1117/12.2261753

KEYWORDS: Image classification, Pathology, Image analysis, Bone, Cancer, Image filtering, Optical filters, Medical imaging, Thermography, Linear filtering, Feature extraction

Read Abstract +

Proceedings Article | 27 September 2016 Presentation + Paper

An effective hair detection algorithm for dermoscopic melanoma images of skin lesions

Damayanti Chakraborti, Ravneet Kaur, Scott Umbaugh, Robert LeAnder

Proceedings Volume 9971, 997104 (2016) https://doi.org/10.1117/12.2236565

KEYWORDS: Skin, Melanoma, Detection and tracking algorithms, Edge detection, Image segmentation, Digital filtering, Algorithm development, Image filtering, Sensors, Image processing algorithms and systems

Read Abstract +

Proceedings Article | 27 September 2016 Paper

Image processing and pattern recognition with CVIPtools MATLAB toolbox: automatic creation of masks for veterinary thermographic images

Deependra Mishra, Scott Umbaugh, Norsang Lama, Rohini Dahal, Dominic Marino, Joseph Sackman

Proceedings Volume 9971, 99713G (2016) https://doi.org/10.1117/12.2238183

KEYWORDS: Image processing, MATLAB, Machine vision, Computer vision technology, Pattern recognition, Image processing, Algorithm development, Image filtering, Image segmentation, Optical filters, Digital filtering

Read Abstract +

Proceedings Article | 27 September 2016 Paper

Thermography based diagnosis of ruptured anterior cruciate ligament (ACL) in canines

Norsang Lama, Scott Umbaugh, Deependra Mishra, Rohini Dahal, Dominic Marino, Joseph Sackman

Proceedings Volume 9971, 99712N (2016) https://doi.org/10.1117/12.2237462

KEYWORDS: Feature extraction, Image classification, Diagnostics, Thermography, Computed tomography, Injuries, Medicine, Cameras, Binary data, Distance measurement

Read Abstract +

Proceedings Article | 23 September 2014 Paper

Thermographic image analysis as a pre-screening tool for the detection of canine bone cancer

Samrat Subedi, Scott Umbaugh, Jiyuan Fu, Dominic Marino, Catherine Loughin, Joseph Sackman

Proceedings Volume 9217, 92171D (2014) https://doi.org/10.1117/12.2061233

KEYWORDS: Cancer, Bone, Image classification, Feature extraction, Thermography, Cameras, Image analysis, Magnetic resonance imaging, Injuries, Analytical research

Read Abstract +

Proceedings Article | 9 March 2010 Paper

New algorithm for detecting smaller retinal blood vessels in fundus images

Robert LeAnder, Praveen Bidari, Tauseef Mohammed, Moumita Das, Scott Umbaugh

Proceedings Volume 7624, 76243B (2010) https://doi.org/10.1117/12.844996

KEYWORDS: Image segmentation, Blood vessels, Hough transforms, Image processing algorithms and systems, Signal to noise ratio, Databases, Algorithm development, Binary data, Image filtering, Spatial filters

Read Abstract +

Proceedings Article | 27 March 2008 Paper

Comparison of two algorithms in the automatic segmentation of blood vessels in fundus images

Robert LeAnder, Myneni Sushma Chowdary, Swapnasri Mokkapati, Scott Umbaugh

Proceedings Volume 6915, 69153H (2008) https://doi.org/10.1117/12.770786

KEYWORDS: Image segmentation, Signal to noise ratio, Blood vessels, Image processing algorithms and systems, Detection and tracking algorithms, Binary data, Image filtering, Edge detection, Databases, Hough transforms

Read Abstract +

Effective timing and treatment are critical to saving the sight of patients with diabetes. Lack of screening, as well as a shortage of ophthalmologists, help contribute to approximately 8,000 cases per year of people who lose their sight to diabetic retinopathy, the leading cause of new cases of blindness [1] [2]. Timely treatment for diabetic retinopathy prevents severe vision loss in over 50% of eyes tested [1]. Fundus images can provide information for detecting and monitoring eye-related diseases, like diabetic retinopathy, which if detected early, may help prevent vision loss. Damaged blood vessels can indicate the presence of diabetic retinopathy [9]. So, early detection of damaged vessels in retinal images can provide valuable information about the presence of disease, thereby helping to prevent vision loss. Purpose: The purpose of this study was to compare the effectiveness of two blood vessel segmentation algorithms. Methods: Fifteen fundus images from the STARE database were used to develop two algorithms using the CVIPtools software environment. Another set of fifteen images were derived from the first fifteen and contained ophthalmologists' hand-drawn tracings over the retinal vessels. The ophthalmologists' tracings were used as the "gold standard" for perfect segmentation and compared with the segmented images that were output by the two algorithms. Comparisons between the segmented and the hand-drawn images were made using Pratt's Figure of Merit (FOM), Signal-to-Noise Ratio (SNR) and Root Mean Square (RMS) Error. Results: Algorithm 2 has an FOM that is 10% higher than Algorithm 1. Algorithm 2 has a 6%-higher SNR than Algorithm 1. Algorithm 2 has only 1.3% more RMS error than Algorithm 1. Conclusions: Algorithm 1 extracted most of the blood vessels with some missing intersections and bifurcations. Algorithm 2 extracted all the major blood vessels, but eradicated some vessels as well. Algorithm 2 outperformed Algorithm 1 in terms of visual clarity, FOM and SNR. The performances of these algorithms show that they have an appreciable amount of potential in helping ophthalmologists detect the severity of eye-related diseases and prevent vision loss.

Proceedings Article | 30 March 2007 Paper

Automatic differentiation of melanoma and Clark nevus skin lesions

R. LeAnder, A. Kasture, A. Pandey, S. Umbaugh

Proceedings Volume 6514, 65142V (2007) https://doi.org/10.1117/12.709986

KEYWORDS: Melanoma, Tumors, Image segmentation, Skin, Image classification, Photography, Image processing, Image filtering, Feature extraction, Skin cancer

Read Abstract +

Skin cancer is the most common form of cancer in the United States. Although melanoma accounts for just 11% of all types of skin cancer, it is responsible for most of the deaths, claiming more than 7910 lives annually. Melanoma is visually difficult for clinicians to differentiate from Clark nevus lesions which are benign. The application of pattern recognition techniques to these lesions may be useful as an educational tool for teaching physicians to differentiate lesions, as well as for contributing information about the essential optical characteristics that identify them. Purpose: This study sought to find the most effective features to extract from melanoma, melanoma in situ and Clark nevus lesions, and to find the most effective pattern-classification criteria and algorithms for differentiating those lesions, using the Computer Vision and Image Processing Tools (CVIPtools) software package. Methods: Due to changes in ambient lighting during the photographic process, color differences between images can occur. These differences were minimized by capturing dermoscopic images instead of photographic images. Differences in skin color between patients were minimized via image color normalization, by converting original color images to relative-color images. Relative-color images also helped minimize changes in color that occur due to changes in the photographic and digitization processes. Tumors in the relative-color images were segmented and morphologically filtered. Filtered, relative-color, tumor features were then extracted and various pattern-classification schemes were applied. Results: Experimentation resulted in four useful pattern classification methods, the best of which was an overall classification rate of 100% for melanoma and melanoma in situ (grouped) and 60% for Clark nevus. Conclusion: Melanoma and melanoma in situ have feature parameters and feature values that are similar enough to be considered one class of tumor that significantly differs from Clark nevus. Consequently, grouping melanoma and melanoma in situ together achieves the best results in classifying and automatically differentiating melanoma from Clark nevus lesions.

Showing 5 of 24 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years