Scribd Logo
Upload

Welcome to Scribd!

  • Using Machine Learning Algorithms For Improved Diagnosis in Skincare Using IMAGE Processing

    Uploaded by

    Mansi Mittal
    13 views9 pages
    This document proposes using machine learning algorithms and image processing to improve diagnosis of skin conditions. Existing methods that use individual patient photos can be inaccurate. The proposed system would have pathologists upload microscope images of skin slides to a database. An algorithm would then analyze the images to accurately detect diseases. This could help doctors diagnose patients around the world more effectively. The methodology would involve collecting a large dataset of skin images, organizing them taxonomically, preprocessing images, and using machine learning algorithms like disease partitioning and training algorithms to classify individual conditions.

    Original Description:

    Original Title

    MINI_PRESENTATION.pptx

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document proposes using machine learning algorithms and image processing to improve diagnosis of skin conditions. Existing methods that use individual patient photos can be inaccurate. The proposed system would have pathologists upload microscope images of skin slides to a database. An algorithm would then analyze the images to accurately detect diseases. This could help doctors diagnose patients around the world more effectively. The methodology would involve collecting a large dataset of skin images, organizing them taxonomically, preprocessing images, and using machine learning algorithms like disease partitioning and training algorithms to classify individual conditions.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pptx, pdf, or txt
    13 views9 pages

    Using Machine Learning Algorithms For Improved Diagnosis in Skincare Using IMAGE Processing

    Uploaded by

    Mansi Mittal
    This document proposes using machine learning algorithms and image processing to improve diagnosis of skin conditions. Existing methods that use individual patient photos can be inaccurate. The proposed system would have pathologists upload microscope images of skin slides to a database. An algorithm would then analyze the images to accurately detect diseases. This could help doctors diagnose patients around the world more effectively. The methodology would involve collecting a large dataset of skin images, organizing them taxonomically, preprocessing images, and using machine learning algorithms like disease partitioning and training algorithms to classify individual conditions.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pptx, pdf, or txt
    of 9

    Using Machine Learning Algorithms for improved

    diagnosis in skincare using IMAGE


    PROCESSING.
    Contents
    Literature Review

    Proposed Work

    Methodology

    References
    Literature Review
    After going through a few research papers, in which Machine learning
    and Healthcare were combined, most of them worked with pictures of
    the affected area, and then working on it. These pictures might vary
    from patient to patient and won’t give a very accurate result, thus
    making the work of a physician difficult.
    In a paper published from the Stanford University, the pictures of skin
    were uploaded, and then when a new picture was uploaded, the
    algorithm was processed and then the diseases was detected, but
    this gives less accurate result.
    Thus, digital pathology is a better technique for more accurate result.
    Proposed Work
    With the rise in whole slide scanner technology, large numbers of tissue
    slides are being scanned and represented and archived digitally. While
    digital pathology has substantial implications for telepathology, second
    opinions, and education there are also huge research opportunities in
    image computing with this new source of data. It is well known that there
    is fundamental prognostic data embedded in pathology images. The
    ability to mine “sub-visual” image features from digital pathology slide
    images, features that may not be visually discernible by a pathologist,
    offers the opportunity for better quantitative modeling of disease
    appearance and hence possibly improved prediction of disease
    aggressiveness and patient outcome
    The system that exists today, relies on the help of individual doctors
    (General Physicians and specialised doctors) to examine the
    condition of the patient with any kind of disease.
    With the help of this, the pathologist will click a picture of the slide
    through the microscope and can upload, this picture.
    After uploading the picture will be added to the database, the
    algorithm will work on it and give the most accurate result.
    The proposed system is able to successfully detect the disease
    present in the image. It can be used to help people from all over the
    world and can be used in doing some productive work.
    Methodology
    Datasets: The efficiency of a Machine learning model depends on
    the size of the data set. So, to achieve acceptable efficiency, a large
    data set is required. The data used in this project are images.

    Taxonomy: Our taxonomy represents individual diseases arranged


    in bottom up approach which becomes easier to get recognized by both
    machine learning programmers and medical practitioners.

    Data Preparation Phase/ Image Processing: Blurry


    images and far-away images will be removed from the test and
    validation sets, filters will be applied to photos so as to make them more
    clear.
    Sample Selection : This is when some of the images are
    randomly selected while some of them are removed on the basis of their
    resolution(image quality).

    Machine Learning Algorithms: Various algorithms like


    Disease partitioning algorithm,Training algorithm , Inference algorithm
    etc in which various diseases will be divided.
    References
    Okuboyejo, Damilola A, et al. ―Automating Skin Disease Diagnosis Using Image
    Classification.‖ Proceedings of WCECS 2013, October 23 - 25, 2013, San Francisco, USA,
    IAENG Open Access Publication, 24 Oct. 2013,

    Ajith, Archana, et al. ―Dermatological Disease Detection Using Image Processing and
    Artificial Neural Network.‖ Dermatological Disease Detection Using Image Processing and
    Artificial Neural Network - IEEE Conference Publication, 15 June 2015

    Ambad, Pravin S., and A. S. Shirat. ―A Image Analysis System to Detect Skin Diseases.‖
    Index of /Iosr-Jvlsi/Papers/vol6-issue5/Version-1, 1 Oct. 2016,

    Gound, R. S., et al. ―Number 16 (ISBN: 973-93-80898-01-6).‖ IJCA - Number 16 (ISBN: 973-
    93- 80898-01-6), 16 Jan. 2018

    Mrs. S.Kalaiarasi, Harsh Kumar, Sourav Patra- Dermatological Disease Detection using Image
    Processing and Neural Networks, S.Kalaiarasi et al, International Journal of Computer Science
    and Mobile Applications, Vol.6 Issue. 4, April- 2018, pg. 109-118

    You might also like