Analytical, Diagnostic and Therapeutic Techniques and Equipment Commons^™

Machine Learning As A Tool For Early Detection: A Focus On Late-Stage Colorectal Cancer Across Socioeconomic Spectrums, Hadiza Galadima, Rexford Anson-Dwamena, Ashley Johnson, Ghalib Bello, Georges Adunlin, James Blando

Community & Environmental Health Faculty Publications

Purpose: To assess the efficacy of various machine learning (ML) algorithms in predicting late-stage colorectal cancer (CRC) diagnoses against the backdrop of socio-economic and regional healthcare disparities. Methods: An innovative theoretical framework was developed to integrate individual- and census tract-level social determinants of health (SDOH) with sociodemographic factors. A comparative analysis of the ML models was conducted using key performance metrics such as AUC-ROC to evaluate their predictive accuracy. Spatio-temporal analysis was used to identify disparities in late-stage CRC diagnosis probabilities. Results: Gradient boosting emerged as the superior model, with the top predictors for late-stage CRC diagnosis being anatomic site, …

Evaluation Of Cold Atmospheric Plasma For The Decontamination Of Flexible Endoscopes, R. C. Hervé, Michael G. Kong, Sudhir Bhatt, Hai-Lan Chen, E. E. Comoy, J-P. Deslys, T. J. Secker, C. W. Keevil

Bioelectrics Publications

Background: Despite adherence to standard protocols, residues including live microorganisms may remain on the various surfaces of reprocessed flexible endoscopes. Prions are infectious proteins notoriously difficult to eliminate.

Aim: We tested the potential of cold atmospheric plasma (CAP) for the decontamination of flexible endoscope various surfaces, measuring total proteins and prion-residual infectivity as an indicator of efficacy.

Methods: New PTFE endoscope channels and metal test surfaces spiked with test soil or prion-infected tissues were treated using different CAP-generating prototypes. Surfaces were then examined for the presence of residues using very sensitive fluorescence epi-microscopy. Prion residual infectivity was determined using the …

Identifying The Serious Clinical Outcomes Of Adverse Reactions To Drugs By A Multi-Task Deep Learning Framework, Haochen Zhao, Peng Ni, Qichang Zhao, Xiao Liang, Di Ai, Shannon Erhardt, Jun Wang, Yaohang Li, Jiianxin Wang

Computer Science Faculty Publications

Adverse Drug Reactions (ADRs) have a direct impact on human health. As continuous pharmacovigilance and drug monitoring prove to be costly and time-consuming, computational methods have emerged as promising alternatives. However, most existing computational methods primarily focus on predicting whether or not the drug is associated with an adverse reaction and do not consider the core issue of drug benefit-risk assessment-whether the treatment outcome is serious when adverse drug reactions occur. To this end, we categorize serious clinical outcomes caused by adverse reactions to drugs into seven distinct classes and present a deep learning framework, so-called GCAP, for predicting the …

A Comparison Of Chief Complaints, Specific Diagnoses, And Demographics Of Pediatric Urgent Care Visits Before And During The Covid-19 Pandemic: A Retrospective Study, Zaharoula A. Viennas, Julie Martin, Benjamin Klick, Tammy Speerhas, Turaj Vazifedan, Danielle Millspaugh, Jennifer Ferris, Margret Bedle, Lauren Paluch, Theresa Guins

Nursing Faculty Publications

There was an increased incidence of pediatric patients who presented with injuries caused by falls not related to sports or other recreational activities, as well as for animal bites, during the early pandemic period of April 2020. Education of parents and caregivers of young children is warranted to raise awareness of the even greater potential for falls and animal bites when children are confined at home for longer than typical periods of time, as occurred with the stay-at-home government orders during the initial period of the COVID-19 pandemic.

A Clinical Study Of Venereal And Non Venereal Genital Dermatoses In Women, Lakkireddygari Sujana, Savitha L. Beergouder, Alekhya Rallapalli, Prasanthi Chidipudi, Sujatha Alla

Engineering Management & Systems Engineering Faculty Publications

Background: Any genital lesion or related symptoms are erroneously considered to be sexually transmitted as it is the most covered regions of the body and seems truly to be a forgotten pelvic organ it is the significant and important group of dermatological conditions may be associated with considerable morbidity, discomfort, and embarrassment. The most common conditions seen in a Dermatology Clinic are vulvar dermatoses, which comprise of lichen sclerosis, lichen planus, vulvar eczema, and psoriasis. Other conditions such as vulvar pain syndromes, vulvar disorders associated with systemic diseases, and blistering diseases are also seen.

Materials and Methods: This was a …

Neuromotor Changes In Participants With A Concussion History Can Be Detected With A Custom Smartphone App, Christopher K. Rhea, Masahiro Yamada, Nikita A. Kuznetsov, Jason T. Jakiela, Chanel T. Lojacono, Scott E. Ross, F. J. Haran, Jason M. Bailie, W. Geoffrey Wright

Rehabilitation Sciences Faculty Publications

Neuromotor dysfunction after a concussion is common, but balance tests used to assess neuromotor dysfunction are typically subjective. Current objective balance tests are either cost- or space-prohibitive, or utilize a static balance protocol, which may mask neuromotor dysfunction due to the simplicity of the task. To address this gap, our team developed an Android-based smartphone app (portable and cost-effective) that uses the sensors in the device (objective) to record movement profiles during a stepping-in-place task (dynamic movement). The purpose of this study was to examine the extent to which our custom smartphone app and protocol could discriminate neuromotor behavior between …

The Enlightening Role Of Explainable Artificial Intelligence In Chronic Wound Classification, Salih Sarp, Murat Kuzlu, Emmanuel Wilson, Umit Cali, Ozgur Guler

Engineering Technology Faculty Publications

Artificial Intelligence (AI) has been among the most emerging research and industrial application fields, especially in the healthcare domain, but operated as a black-box model with a limited understanding of its inner working over the past decades. AI algorithms are, in large part, built on weights calculated as a result of large matrix multiplications. It is typically hard to interpret and debug the computationally intensive processes. Explainable Artificial Intelligence (XAI) aims to solve black-box and hard-to-debug approaches through the use of various techniques and tools. In this study, XAI techniques are applied to chronic wound classification. The proposed model classifies …

Simultaneous Wound Border Segmentation And Tissue Classification Using A Conditional Generative Adversarial Network, Salih Sarp, Murat Kuzlu, Manisa Pipattanasomporn, Ozgur Guler

Engineering Technology Faculty Publications

Generative adversarial network (GAN) applications on medical image synthesis have the potential to assist caregivers in deciding a proper chronic wound treatment plan by understanding the border segmentation and the wound tissue classification visually. This study proposes a hybrid wound border segmentation and tissue classification method utilising conditional GAN, which can mimic real data without expert knowledge. We trained the network on chronic wound datasets with different sizes. The performance of the GAN algorithm is evaluated through the mean squared error, Dice coefficient metrics and visual inspection of generated images. This study also analyses the optimum number of training images …

The Influence Of Sonographer Experience On Skeletal Muscle Image Acquisition And Analysis, Joshua C. Carr, Gena R. Gerstner, Caleb C. Voskuil, Joel E. Harden, Dustin Dunnick, Kristin M. Badillo, Jason I. Pagan, Kylie K. Harmon, Ryan M. Girts, Jonathan P. Beausejour, Matt S. Stock

Human Movement Studies & Special Education Faculty Publications

The amount of experience with ultrasonography may influence measurement outcomes while images are acquired or analyzed. The purpose of this study was to identify the interrater reliability of ultrasound image acquisition and image analysis between experienced and novice sonographers and image analysts, respectively. Following a brief hands-on training session (2 h), the experienced and novice sonographers and analysts independently performed image acquisition and analyses on the biceps brachii, vastus lateralis, and medial gastrocnemius in a sample of healthy participants (n = 17). Test–retest reliability statistics were computed for muscle thickness (transverse and sagittal planes), muscle cross-sectional area, echo intensity and …

Tri-Molybdenum Phosphide (Mo3P) And Multi-Walled Carbon Nanotube Junctions For Volatile Organic Compounds (Vocs) Detection, Baleeswaraiah Muchharla, Praveen Malali, Brenna Daniel, Alireza Kondori, Mohammad Asadi, Wei Cao, Hani E. Elsayed-Ali, Mickaël Castro, Mehran Elahi, Adetayo Adedeji, Kishor Kumar Sadasivuni, Muni Raj Mauya, Kapil Kumar, Abdennaceur Karoui, Bijandra Kumar

Electrical & Computer Engineering Faculty Publications

Detection and analysis of volatile organic compounds’ (VOCs) biomarkers lead to improvement in healthcare diagnosis and other applications such as chemical threat detection and food quality control. Here, we report on tri-molybdenum phosphide (Mo₃P) and multi- walled carbon nanotube (MWCNT) junction-based vapor quantum resistive sensors (vQRSs), which exhibit more than one order of magni- tude higher sensitivity and superior selectivity for biomarkers in comparison to pristine MWCNT junctions based vQRSs. Transmission electron microscope/scanning tunneling electron microscope with energy dispersive x-ray spectroscopy, x-ray diffraction, and x-ray photo- electron spectroscopy studies reveal the crystallinity and the presence of Mo and …

Visual Estimates Of Blood Loss By Medical Laypeople: Effects Of Blood Loss Volume, Victim Gender, And Perspective, Rachel Phillips, Marc Friberg, Mattias Lantz Cronqvist, Carl-Oscar Jonson, Erik Prytz

Psychology Faculty Publications

A severe hemorrhage can result in death within minutes, before professional first responders have time to arrive. Thus, intervention by bystanders, who may lack medical training, may be necessary to save a victim's life in situations with bleeding injuries. Proper intervention requires that bystanders accurately assess the severity of the injury and respond appropriately. As many bystanders lack tools and training, they are limited in terms of the information they can use in their evaluative process. In hemorrhage situations, visible blood loss may serve as a dominant cue to action. Therefore, understanding how medically untrained bystanders (i.e., laypeople) perceive hemorrhage …

Single-Molecule Analysis Of Subtelomeres And Telomeres In Alternative Lengthening Of Telomeres (Alt) Cells, Heba Z. Abid, Jennifer Mccaffrey, Kaitlin Raseley, Eleanor Young, Katy Lassahn, Dharma Varapula, Harold Riethman, Ming Xiao

School of Medical Diagnostics & Translational Sciences Faculty Publications

BACKGROUND: Telomeric DNA is typically comprised of G-rich tandem repeat motifs and maintained by telomerase (Greider CW, Blackburn EH; Cell 51:887-898; 1987). In eukaryotes lacking telomerase, a variety of DNA repair and DNA recombination based pathways for telomere maintenance have evolved in organisms normally dependent upon telomerase for telomere elongation (Webb CJ, Wu Y, Zakian VA; Cold Spring Harb Perspect Biol 5:a012666; 2013); collectively called Alternative Lengthening of Telomeres (ALT) pathways. By measuring (TTAGGG) n tract lengths from the same large DNA molecules that were optically mapped, we simultaneously analyzed telomere length dynamics and subtelomere-linked structural changes at a large …

The Impact Of Delayed Treatment Of Uncomplicated P. Falciparum Malaria On Progression To Severe Malaria: A Systematic Review And A Pooled Multicentre Individual-Patient Meta-Analysis, Andria Mousa, Abdullah Al-Taiar, Nicholas M. Anstey, Cyril Badaut, Bridget E. Barber, Quique Bassat, Joseph D. Challenger, Aubrey J. Cunnington, Dibyadyuti Datta, Chris Drakeley, Azra C. Ghani, Victor R. Gordeuk, Matthew J. Grigg, Pierre Hugo, Chandy C. John, Alfredo Mayor, Florence Migot-Nabias, Robert O. Opoka, Geoffrey Pasvoi, Claire Rees, Hugh Reyburn, Eleanor M. Riley, Binal N. Shah, Antonio Sitoe, Colin J. Sutherland, Philip E. Thuma, Stefan A. Unger, Firmine Viwami, Michael Walther, Christopher J.M. Whitty, Timothy William, Lucy C. Okell

Community & Environmental Health Faculty Publications

BACKGROUND: Delay in receiving treatment for uncomplicated malaria (UM) is often reported to increase the risk of developing severe malaria (SM), but access to treatment remains low in most high-burden areas. Understanding the contribution of treatment delay on progression to severe disease is critical to determine how quickly patients need to receive treatment and to quantify the impact of widely implemented treatment interventions, such as 'test-and-treat' policies administered by community health workers (CHWs). We conducted a pooled individual-participant meta-analysis to estimate the association between treatment delay and presenting with SM.

METHODS AND FINDINGS: A search using Ovid MEDLINE and Embase …

Saliva Microrna Biomarkers Of Cumulative Concussion, Steven D. Hicks, Robert P. Olympia, Cayce Onks, Raymond Y. Kim, Kevin J. Zhen, Gregory Fedorchak, Samantha Devita, Aakanksha Rangnekar, Matthew Heller, Hallie Zwibel, Chuck Monteith, Zofia Gagnon, Callan D. Mcloughlin, Jason Randall, Miguel Madeira, Thomas R. Campbell, Elise Fengler, Michael N. Dretsch, Christopher Neville, Frank A. Middleton

Rehabilitation Sciences Faculty Publications

Recurrent concussions increase risk for persistent post-concussion symptoms, and may lead to chronic neurocognitive deficits. Little is known about the molecular pathways that contribute to persistent concussion symptoms. We hypothesized that salivary measurement of microribonucleic acids (miRNAs), a class of epitranscriptional molecules implicated in concussion pathophysiology, would provide insights about the molecular cascade resulting from recurrent concussions. This hypothesis was tested in a case-control study involving 13 former professional football athletes with a history of recurrent concussion, and 18 age/sex-matched peers. Molecules of interest were further validated in a cross-sectional study of 310 younger individuals with a history of no …

Can Nanotechnology Be The Leading Method In Detecting And Treating Cerebral Tumors?, Daniel D. Singh, Zuri Jules-Culver

OUR Journal: ODU Undergraduate Research Journal

Nanotechnology refers to the manipulation or design of materials and structures with desired features in the 1nm–1000 nm size range. The blood brain barrier (BBB) is a major obstacle that drugs must overcome in order to reach tumor cells. The role of this barrier is to transport essential nutrients while protecting and regulating the internal environment. Nanoparticles have been shown to transport drugs through this barrier and accumulate in tumor cells. This is significant since nanoparticles are drug carriers allowing chemotherapeutic drugs to accumulate in target areas (Sun et al., 2017). This is possible because they are able to be …

Serological Proteomic Screening And Evaluation Of A Recombinant Egg Antigen For The Diagnosis Of Low-Intensity Schistosoma Mansoni Infections In Endemic Area In Brazil, Vanessa Silva-Moraes, Lisa Marie Shollenberger, William Castro-Borges, Ana Lucia Teles Rabello, Donald A. Harn, Lia Carolina Soares Medeiros, Wander De Jesus Jeremias, Liliane Maria Vidal Siqueira, Caroline Stephane Salviano Pereira, Maria Luysa Camargos Pedrosa, Nathalie Bonatti Franco Almeida, Aureo Almeida, Jose Roberto Lambertucci, Nidia Francisca De Figueiredo Carneiro, Paulo Marcos Zech Coelho, Refaella Fortini Queiroz Grenfell

Biological Sciences Faculty Publications

Background

Despite decades of use of control programs, schistosomiasis remains a global public health problem. To further reduce prevalence and intensity of infection, or to achieve the goal of elimination in low-endemic areas, there needs to be better diagnostic tools to detect low-intensity infections in low-endemic areas in Brazil. The rationale for development of new diagnostic tools is that the current standard test Kato-Katz (KK) is not sensitive enough to detect low-intensity infections in low-endemic areas. In order to develop new diagnostic tools, we employed a proteomics approach to identify biomarkers associated with schistosome-specific immune responses in hopes of developing …

Diagnosis Of Schistosoma Mansoni Infections: What Are The Choices In Brazilian Low-Endemic Areas?, Vanessa Silva-Moraes, Lisa M. Shollenberger, Liliane Maria Vidal Siqueira, William Castro-Borges, Donald A. Harn, Rafaella Fortini Queiroz E. Grenfell, Ana Lucia Teles Rabello, Paulo Marcos Zech Coelho

Biological Sciences Faculty Publications

The population of Brazil is currently characterised by many individuals harbouring low-intensity Schistosoma mansoni infections. The Kato-Katz technique is the diagnostic method recommended by the World Health Organization (WHO) to assess these infections, but this method is not sensitive enough in the context of low egg excretion. In this regard, potential alternatives are being employed to overcome the limits of the Kato-Katz technique. In the present review, we evaluated the performance of parasitological and immunological approaches adopted in Brazilian areas. Currently, the diagnostic choices involve a combination of strategies, including the utilisation of antibody methods to screen individuals and then …

Feature-Guided Deep Radiomics For Glioblastoma Patient Survival Prediction, Zeina A. Shboul, Mahbubul Alam, Lasitha Vidyaratne, Linmin Pei, Mohamed I. Elbakary, Khan M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Glioblastoma is recognized as World Health Organization (WHO) grade IV glioma with an aggressive growth pattern. The current clinical practice in diagnosis and prognosis of Glioblastoma using MRI involves multiple steps including manual tumor sizing. Accurate identification and segmentation of multiple abnormal tissues within tumor volume in MRI is essential for precise survival prediction. Manual tumor and abnormal tissue detection and sizing are tedious, and subject to inter-observer variability. Consequently, this work proposes a fully automated MRI-based glioblastoma and abnormal tissue segmentation, and survival prediction framework. The framework includes radiomics feature-guided deep neural network methods for tumor tissue segmentation; followed …

The Role Of Neighborhood Characteristics In Late Stage Melanoma Diagnosis Among Hispanic Men In California, Texas, And Florida, 1996-2012, Valerie M. Harvey, Clinton W. Enos, Jarvis T. Chen, Hadiza Galadima, Karl Eschbach

Community & Environmental Health Faculty Publications

Background. Hispanics diagnosed with cutaneous melanoma are more likely to present at advanced stages but the reasons for this are unknown. We identify census tracts at high risk for late stage melanoma diagnosis (LSMD) and examine the contextual predictors of LSMD in California, Texas, and Florida. Methods. We conducted a cross-sectional study using geocoded state cancer registry data. Using hierarchical multilevel logistic regression models we estimated ORs and 95% confidence intervals for the impact of socioeconomic, Hispanic ethnic concentration, index of dissimilarity, and health resource availability measures on LSMD. Results. We identified 12,493 cases. In California, late …

Race, Ethnicity, Psychosocial Factors, And Telomere Length In A Multicenter Setting, Shannon M. Lynch, M. K. Peek, Nandita Mitra, Krithika Ravichandran, Charles Branas, Elaine Spangler, Wenting Zhou, Electra D. Paskett, Sarah Gehlert, Cecilia Degraffinreid, Timothy R. Rebbeck, Harold Riethman

School of Medical Diagnostics & Translational Sciences Faculty Publications

Background

Leukocyte telomere length(LTL) has been associated with age, self-reported race/ethnicity, gender, education, and psychosocial factors, including perceived stress, and depression. However, inconsistencies in associations of LTL with disease and other phenotypes exist across studies. Population characteristics, including race/ethnicity, laboratory methods, and statistical approaches in LTL have not been comprehensively studied and could explain inconsistent LTL associations.

Methods

LTL was measured using Southern Blot in 1510 participants from a multi-ethnic, multi-center study combining data from 3 centers with different population characteristics and laboratory processing methods. Main associations between LTL and psychosocial factors and LTL and race/ethnicity were evaluated and then …

Erosive Hand Osteoarthritis Is Associated With Subclinical Atherosclerosis And Endothelial Dysfunction, Athanasios Koutroumpas, Athanasios Giannoukas, Elias Zintzaras, Ekaterini Exarchou, Aris Baliakos, Konstantinos Makaritsis, Lazaros I. Sakkas

Biological Sciences Faculty Publications

Chronic inflammatory disorders have been associated with accelerated atherosclerosis and increased cardiovascular (CV) risk. Recent evidence suggests that erosive hand osteoarthritis (EOA) has considerable inflammation; therefore, we examined the presence of subclinical atherosclerosis and endothelial dysfunction in EOA. Twenty-four patients with EOA and 24 age- and sex-matched healthy individuals without clinical OA were included in the study. No subject had a history of CV disease. Intima-media thickness (IMT) and atheromatous plaques in the common carotid and common femoral arteries were measured by Doppler ultrasonography. The endothelium-dependent, flow-mediated dilatation (FMD) and endothelium-independent, sublingual glyceryl trinitrate (NTG)-induced dilatation (NMD) of the brachial …

Bcc Skin Cancer Diagnosis Based On Texture Analysis Techniques, Shao-Hui Chuang, Xiaoyan Sun, Wen-Yu Chang, Gwo-Shing Chen, Adam Huang, Jiang Li, Frederic D. Mckenzie

Electrical & Computer Engineering Faculty Publications

In this paper, we present a texture analysis based method for diagnosing the Basal Cell Carcinoma (BCC) skin cancer using optical images taken from the suspicious skin regions. We first extracted the Run Length Matrix and Haralick texture features from the images and used a feature selection algorithm to identify the most effective feature set for the diagnosis. We then utilized a Multi-Layer Perceptron (MLP) classifier to classify the images to BCC or normal cases. Experiments showed that detecting BCC cancer based on optical images is feasible. The best sensitivity and specificity we achieved on our data set were 94% …

Adjacent Slice Prostate Cancer Prediction To Inform Maldi Imaging Biomarker Analysis, Shao-Hui Chuang, Xiaoyan Sun, Lisa Cazares, Julius Nyalwidhe, Dean Troyer, O. John Semmes, Jiang Li, Frederic D. Mckenzie, Nico Karssemeijer (Ed.), Ronald M. Summers (Ed.)

Electrical & Computer Engineering Faculty Publications

Prostate cancer is the second most common type of cancer among men in US [1]. Traditionally, prostate cancer diagnosis is made by the analysis of prostate-specific antigen (PSA) levels and histopathological images of biopsy samples under microscopes. Proteomic biomarkers can improve upon these methods. MALDI molecular spectra imaging is used to visualize protein/peptide concentrations across biopsy samples to search for biomarker candidates. Unfortunately, traditional processing methods require histopathological examination on one slice of a biopsy sample while the adjacent slice is subjected to the tissue destroying desorption and ionization processes of MALDI. The highest confidence tumor regions gained from the …

Validating Pareto Optimal Operation Parameters Of Polyp Detection Algorithms For Ct Colonography, Jiang Li, Adam Huang, Nicholas Petrick, Jianhua Yao, Ronald M. Summers, Maryellen L. Giger (Ed.), Nico Karssemeijer (Ed.)

Electrical & Computer Engineering Faculty Publications

We evaluated a Pareto front-based multi-objective evolutionary algorithm for optimizing our CT colonography (CTC) computer-aided detection (CAD) system. The system identifies colonic polyps based on curvature and volumetric based features, where a set of thresholds for these features was optimized by the evolutionary algorithm. We utilized a two-fold cross-validation (CV) method to test if the optimized thresholds can be generalized to new data sets. We performed the CV method on 133 patients; each patient had a prone and a supine scan. There were 103 colonoscopically confirmed polyps resulting in 188 positive detections in CTC reading from either the prone or …

Using Pareto Fronts To Evaluate Polyp Detection Algorithms For Ct Colonography, Adam Huang, Jiang Li, Ronald M. Summers, Nicholas Petrick, Amy K. Hara

Electrical & Computer Engineering Faculty Publications

We evaluate and improve an existing curvature-based region growing algorithm for colonic polyp detection for our CT colonography (CTC) computer-aided detection (CAD) system by using Pareto fronts. The performance of a polyp detection algorithm involves two conflicting objectives, minimizing both false negative (FN) and false positive (FP) detection rates. This problem does not produce a single optimal solution but a set of solutions known as a Pareto front. Any solution in a Pareto front can only outperform other solutions in one of the two competing objectives. Using evolutionary algorithms to find the Pareto fronts for multi-objective optimization problems has been …

Wavelet Analysis In Virtual Colonoscopy, Sharon Greenblum, Jiang Li, Adam Huang, Ronald M. Summers, Armando Manduca (Ed.), Amir A. Amini (Ed.)

Electrical & Computer Engineering Faculty Publications

The computed tomographic colonography (CTC) computer aided detection (CAD) program is a new method in development to detect colon polyps in virtual colonoscopy. While high sensitivity is consistently achieved, additional features are desired to increase specificity. In this paper, a wavelet analysis was applied to CTCCAD outputs in an attempt to filter out false positive detections. 52 CTCCAD detection images were obtained using a screen capture application. 26 of these images were real polyps, confirmed by optical colonoscopy and 26 were false positive detections. A discrete wavelet transform of each image was computed with the MATLAB wavelet toolbox using the …

Automatic Colonic Polyp Detection Using Multiobjective Evolutionary Techniques, Jiang Li, Adam Huang, Jianhua Yao, Ingmar Bitter, Nicholas Petrick, Ronald M. Summers, Perry J. Pickhardt, J. Richard Choi

Electrical & Computer Engineering Faculty Publications

Colonie polyps appear like elliptical protrusions on the inner wall of the colon. Curvature based features for colonie polyp detection have proved to be successful in several computer-aided diagnostic CT colonography (CTC) systems. Some simple thresholds are set for those features for creating initial polyp candidates, sophisticated classification scheme are then applied on these polyp candidates to reduce false positives. There are two objective functions, the number of missed polyps and false positive rate, that need to be minimized when setting those thresholds. These two objectives conflict and it is usually difficult to optimize them both by a gradient search. …