Browsing by Subject "segmentation"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Automated Computer-Based Enumeration of Acellular Capillaries for Assessment of Diabetic Retinopathy
    (SPIE, 2020-02) Tuceryan, Mihran; Hemmady, Anish N.; Schebler, Craig; Alex, Alpha; Bhatwadekar, Ashay D.; Computer and Information Science, School of Science
    Diabetic retinopathy (DR) is the most common complications of diabetes; if untreated the DR can lead to a vision loss. The treatment options for DR are limited and the development of newer therapies are of considerable interest. Drug screening for the retinopathy treatment is undertaken using animal models in which the quantification of acellular capillaries (capillary without any cells) is used as a marker to assess the severity of retinopathy and the treatment response. The traditional approach to quantitate acellular capillaries is through manual counting. The purpose of this investigation was to develop an automated technique for the quantitation of acellular capillaries using computer-based image processing algorithms. We developed a custom procedure using the Python, the medial axis transform (MAT) and the connected component algorithm. The program was tested on the retinas of wild-type and diabetic mice and the results were compared to single blind manual counts by two independent investigators. The program successfully identified and enumerated acellular capillaries. The acellular capillary counts were comparable to the traditional manual counting. In conclusion, we developed an automated computer-based program, which can be effectively used for future pharmacological development of treatments for DR. This algorithm will enhance consistency in retinopathy assessment and reduce the time for analysis, thus, contributing substantially towards the development of future pharmacological agents for the treatment of DR.
  • Thumbnail Image
    Item
    Automatic segmentation of intravital fluorescence microscopy images by K-means clustering of FLIM phasors
    (OSA, 2019-08) Zhang, Yide; Hato, Takashi; Dagher, Pierre C.; Nichols, Evan L.; Smith, Cody J.; Dunn, Kenneth W.; Howard, Scott S.; Medicine, School of Medicine
    Fluorescence lifetime imaging microscopy (FLIM) provides additional contrast for fluorophores with overlapping emission spectra. The phasor approach to FLIM greatly reduces the complexity of FLIM analysis and enables a useful image segmentation technique by selecting adjacent phasor points and labeling their corresponding pixels with different colors. This phasor labeling process, however, is empirical and could lead to biased results. In this Letter, we present a novel and unbiased approach to automate the phasor labeling process using an unsupervised machine learning technique, i.e., K-means clustering. In addition, we provide an open-source, user-friendly program that enables users to easily employ the proposed approach. We demonstrate successful image segmentation on 2D and 3D FLIM images of fixed cells and living animals acquired with two different FLIM systems. Finally, we evaluate how different parameters affect the segmentation result and provide a guideline for users to achieve optimal performance.
  • Thumbnail Image
    Item
    Energy Efficiency of Quantized Neural Networks in Medical Imaging
    (2022-04) Sinha, Priyanshu; Tummala, Sai Sreya; Purkayastha, Saptarshi; Gichoya, Judy W.; BioHealth Informatics, School of Informatics and Computing
    The main goal of this paper is to compare the energy efficiency of quantized neural networks to perform medical image analysis on different processors and neural network architectures. Deep neural networks have demonstrated outstanding performance in medical image analysis but require high computation and power usage. In our work, we review the power usage and temperature of processors when running Resnet and Unet architectures to perform image classification and segmentation respectively. We compare Edge TPU, Jetson Nano, Apple M1, Nvidia Quadro P6000 and Nvidia A6000 to infer using full-precision FP32 and quantized INT8 models. The results will be useful for designers and implementers of medical imaging AI on hand-held or edge computing devices.
  • Thumbnail Image
    Item
    Microtargeting y segmentación electoral: Estudio de los votantes de VOX (Barómetro del CIS, enero de 2021)
    (2021) Mallorquí-Ruscalleda, Enric
    A partir de los datos más recientes de enero de 2021 que contamos del Centro de Investigaciones Sociológicas (CIS), en este informe se estudia y valora, primero, la evolución en el número de votantes del partido VOX y, segundo, los cambios en las características personales de los votantes, especialmente, las variables sociológicas y de opinión. Todo ello con la finalidad de intentar llegar a la conclusión de cuál debería ser el target de una potencial campaña electoral del partido político VOX.