Physical Sciences and Mathematics Commons^™

Skin Lesion Segmentation In Dermoscopic Images With Noisy Data, Norsang Lama, Jason Hagerty, Anand Nambisan, Ronald Joe Stanley, William Van Stoecker

Electrical and Computer Engineering Faculty Research & Creative Works

We Propose a Deep Learning Approach to Segment the Skin Lesion in Dermoscopic Images. the Proposed Network Architecture Uses a Pretrained Efficient Net Model in the Encoder and Squeeze-And-Excitation Residual Structures in the Decoder. We Applied This Approach on the Publicly Available International Skin Imaging Collaboration (ISIC) 2017 Challenge Skin Lesion Segmentation Dataset. This Benchmark Dataset Has Been Widely Used in Previous Studies. We Observed Many Inaccurate or Noisy Ground Truth Labels. to Reduce Noisy Data, We Manually Sorted All Ground Truth Labels into Three Categories — Good, Mildly Noisy, and Noisy Labels. Furthermore, We Investigated the Effect of Such …

Chimeranet: U-Net For Hair Detection In Dermoscopic Skin Lesion Images, Norsang Lama, Reda Kasmi, Jason R. Hagerty, R. Joe Stanley, Reagan Harris Young, Jessica Miinch, Januka Nepal, Anand Nambisan, William V. Stoecker

Electrical and Computer Engineering Faculty Research & Creative Works

Hair and ruler mark structures in dermoscopic images are an obstacle preventing accurate image segmentation and detection of critical network features. Recognition and removal of hairs from images can be challenging, especially for hairs that are thin, overlapping, faded, or of similar color as skin or overlaid on a textured lesion. This paper proposes a novel deep learning (DL) technique to detect hair and ruler marks in skin lesion images. Our proposed ChimeraNet is an encoder-decoder architecture that employs pretrained EfficientNet in the encoder and squeeze-and-excitation residual (SERes) structures in the decoder. We applied this approach at multiple image sizes …

In Situ Nmr Parameter Monitoring Systems And Methods For Measuring Ph And Temperature, Ming Huang, Lingyu Chi, Rex E. Gerald Ii, Jie Huang, Annalise R. Pfaff, Klaus Woelk

Electrical and Computer Engineering Faculty Research & Creative Works

Devices and methods are provided for measuring temperatures and pHs of a sample in situ using NMR spectroscopy, and for sealing one or more ends of a capillary tube after a reference material has been added to the capillary tube, which is used in an in situ NMR temperature measurement device. A method for measuring a pH of a sample in situ using NMR spectroscopy includes providing an in situ NMR pH measurement device. This device includes a sample housing member configured to house a target sample, at least one pH sensor configured to exhibit an NMR spectral change due …

Capillary-Tube Package Devices For The Quantitative Performance Evaluation Of Nuclear Magnetic Resonance Spectrometers And Pulse Sequences, Lingyu Chi, Ming Huang, Annalise R. Pfaff, Jie Huang, Rex E. Gerald Ii, Klaus Woelk

Electrical and Computer Engineering Faculty Research & Creative Works

With the increased sensitivity of modern nuclear magnetic resonance (NMR) spectrometers, the minimum amount needed for chemical-shift referencing of NMR spectra has decreased to a point where a few microliters can be sufficient to observe a reference signal. The reduction in the amount of required reference material is the basis for the NMR Capillary-tube Package (CapPack) platform that utilizes capillary tubes with inner diameters smaller than 150 µm as NMR-tube inserts for external reference standards. It is shown how commercially available electrophoresis capillary tubes with outer diameters of 360 µm are filled with reference liquids or solutions and then permanently …

Nmr Studies Of Loaded Microspheres, Ming Huang, Sisi Chen, Rex E. Gerald Ii, Jie Huang, Klaus Woelk

Electrical and Computer Engineering Faculty Research & Creative Works

Porous-wall hollow glass microspheres (PWHGMs) are a novel form of glass materials that consist of 1-μm-thick porous silica shells, 20-100 μm in diameter, with a hollow cavity in the center. Utilizing the central cavity for material storage and the porous walls for controlled release is a unique combination that renders PWHGMs a superior vehicle for targeted drug delivery. In this study, NMR spectroscopy was used to characterize PWHGMs for the first time. A vacuum-based loading system was developed to load PWHGMs with various compounds followed by a washing procedure that uses solvents immiscible with the target material. Immiscible binary model …

Fuzzy Color Clustering For Melanoma Diagnosis In Dermoscopy Images, Haidar A. Almubarak, R. Joe Stanley, William V. Stoecker, Randy Hays Moss

Electrical and Computer Engineering Faculty Research & Creative Works

A fuzzy logic-based color histogram analysis technique is presented for discriminating benign skin lesions from malignant melanomas in dermoscopy images. The approach extends previous research for utilizing a fuzzy set for skin lesion color for a specified class of skin lesions, using alpha-cut and support set cardinality for quantifying a fuzzy ratio skin lesion color feature. Skin lesion discrimination results are reported for the fuzzy clustering ratio over different regions of the lesion over a data set of 517 dermoscopy images consisting of 175 invasive melanomas and 342 benign lesions. Experimental results show that the fuzzy clustering ratio applied over …

Enhancements In Localized Classification For Uterine Cervical Cancer Digital Histology Image Assessment, Peng Guo, Haidar A. Almubarak, Koyel Banerjee, R. Joe Stanley, L. Rodney Long, Sameer K. Antani, George R. Thoma, Rosemary E. Zuna, Shelliane R. Frazier, Randy Hays Moss, William V. Stoecker

Electrical and Computer Engineering Faculty Research & Creative Works

Background: In previous research, we introduced an automated, localized, fusion-based approach for classifying uterine cervix squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN) based on digitized histology image analysis. As part of the CIN assessment process, acellular and atypical cell concentration features were computed from vertical segment partitions of the epithelium region to quantize the relative distribution of nuclei.

Methods: Feature data was extracted from 610 individual segments from 61 images for epithelium classification into categories of Normal, CIN1, CIN2, and CIN3. The classification results were compared against CIN labels obtained from two pathologists …

Real-Time Supervised Detection Of Pink Areas In Dermoscopic Images Of Melanoma: Importance Of Color Shades, Texture And Location, Ravneet Kaur, P. P. Albano, Justin G. Cole, Jason R. Hagerty, Robert W. Leander, Randy Hays Moss, William V. Stoecker

Electrical and Computer Engineering Faculty Research & Creative Works

Background/Purpose: Early detection of malignant melanoma is an important public health challenge. In the USA, dermatologists are seeing more melanomas at an early stage, before classic melanoma features have become apparent. Pink color is a feature of these early melanomas. If rapid and accurate automatic detection of pink color in these melanomas could be accomplished, there could be significant public health benefits.

Methods: Detection of three shades of pink (light pink, dark pink, and orange pink) was accomplished using color analysis techniques in five color planes (red, green, blue, hue, and saturation). Color shade analysis was performed using a logistic …

Microwave Reflectometry As A Novel Diagnostic Tool For Detection Of Skin Cancers, Pratik Mehta, Kundan Chand, Deepak Narayanswamy, Daryl G. Beetner, R. Zoughi, William V. Stoecker

Electrical and Computer Engineering Faculty Research & Creative Works

More than 1 000 000 people are diagnosed with skin cancer each year in the United States, and more than 10 000 people die from the disease. Methods such as visual inspection and dermoscopy are available for early detection of skin cancers, but improvement in accuracy is needed. This paper investigates the use of microwave reflectometry as a potential diagnostic tool for detection of skin cancers. Open-ended coaxial probes were used to measure microwave properties of skin. The influences of measurement parameters such as probe application pressure, power level, and variation in reflection properties of skin with location and hydration …

Microwave Reflectometry As A Novel Diagnostic Method For Detection Of Skin Cancers, Kundan Chand, Pratik Mehta, Daryl G. Beetner, R. Zoughi, William V. Stoecker

Electrical and Computer Engineering Faculty Research & Creative Works

More than one million people are diagnosed with skin cancer each year in the United States and more than ten thousand people die from the disease. Currently, there are some methods for early detection of skin cancers, like visual inspection, but improvements are needed. This paper presents a method involving microwave reflectometry as a diagnostic tool for detection of skin cancers. The results of measurements and simulations for normal and wet skin have been shown to distinguish among skin samples with different properties. Microwave measurements from lesions have also been presented which are used to distinguish between cancerous and benign …