Computer Aided Diagnostic System for the Classification of Skin Cancer Using Dermoscopic Images

2013 ◽

Vol 2013 ◽

pp. 1-22 ◽

Cited By ~ 97

Author(s):

Ammara Masood ◽

Adel Ali Al-Jumaily

Keyword(s):

Skin Cancer ◽

State Of The Art ◽

Comparative Assessment ◽

Future Research ◽

Feature Extraction And Selection ◽

Diagnostic Models ◽

Computer Aided ◽

Aided Diagnosis ◽

Diagnostic Support

Image-based computer aided diagnosis systems have significant potential for screening and early detection of malignant melanoma. We review the state of the art in these systems and examine current practices, problems, and prospects of image acquisition, pre-processing, segmentation, feature extraction and selection, and classification of dermoscopic images. This paper reports statistics and results from the most important implementations reported to date. We compared the performance of several classifiers specifically developed for skin lesion diagnosis and discussed the corresponding findings. Whenever available, indication of various conditions that affect the technique’s performance is reported. We suggest a framework for comparative assessment of skin cancer diagnostic models and review the results based on these models. The deficiencies in some of the existing studies are highlighted and suggestions for future research are provided.

Download Full-text

Comparison of Deep Learning Algorithms for Semantic Segmentation of Ultrasound Thyroid Nodules

Current Directions in Biomedical Engineering ◽

10.1515/cdbme-2021-2224 ◽

2021 ◽

Vol 7 (2) ◽

pp. 879-882

Author(s):

Elmer Jeto Gomes Ataide ◽

Shubham Agrawal ◽

Aishwarya Jauhari ◽

Axel Boese ◽

Alfredol Illanes ◽

...

Keyword(s):

Deep Learning ◽

Risk Stratification ◽

Thyroid Nodules ◽

Performance Metrics ◽

Diagnostic System ◽

Diagnostic Tools ◽

Observer Variability ◽

Dice Coefficient ◽

Computer Aided

Abstract Ultrasound (US) imaging is used as a preliminary diagnostic tool for the detection, risk-stratification and classification of thyroid nodules. In order to perform the risk stratification of nodules in US images physicians first need to effectively detect the nodules. This process is affected due to the presence of inter-observer and intra-observer variability and subjectivity. Computer Aided Diagnostic tools prove to be a step in the right direction towards reducing the issue of subjectivity and observer variability. Several segmentation techniques have been proposed, from these Deep Learning techniques have yielded promising results. This work presents a comparison between four state of the art (SOTA) Deep Learning segmentation algorithms (UNet, SUMNet, ResUNet and Attention UNet). Each network was trained on the same dataset and the results are compared using performance metrics such as accuracy, dice coefficient and Intersection over Union (IoU) to determine the most effective in terms of thyroid nodule segmentation in US images. It was found that ResUNet performed the best with an accuracy, dice coefficient and IoU of 89.2%, 0.857, 0.767. The aim is to use the trained algorithm in the development of a Computer Aided Diagnostic system for the detection, riskstratification and classification of thyroid nodules using US images to reduce subjectivity and observer variability

Download Full-text

BI-RADS Breast Tumor Classification Through Image Mining

10.5753/kdmile.2019.8791 ◽

2019 ◽

Author(s):

Valesca J. S. Da Silva ◽

Mateus M. R. Da Silva ◽

Marcelino P. S. Silva ◽

Joana R. C. Nogueira

Keyword(s):

Breast Cancer ◽

Image Processing ◽

Breast Tumor ◽

Diagnostic System ◽

Tumor Classification ◽

Image Mining ◽

Computer Aided ◽

Breast Tumor Classification

In this article, a computer aided diagnostic system for BI-RADS classification of breast cancer is proposed. The approach involves image processing capabilities to extract features from tumors in mammography and image mining to classify them as BI-RADS 2, BI-RADS 3, BI-RADS 4C or BI-RADS 5. Images from the BCDR repository were used for the experiments. The results showed the efficacy of the proposed method, which classified tumors with considerable accuracy in four BI-RADS categories.

Download Full-text

Observer Variation in Clinical Diagnosis - A Computer-Aided Assessment of its Magnitude and Importance in 552 Patients with Abdominal Pain

Methods of Information in Medicine ◽

10.1055/s-0038-1636102 ◽

1973 ◽

Vol 12 (02) ◽

pp. 108-113 ◽

Cited By ~ 20

Author(s):

P. W. Gill ◽

D. J. Leaper ◽

P. J. Guillou ◽

J. R. Staniland ◽

J. C. Horhocks ◽

...

Keyword(s):

Abdominal Pain ◽

Clinical Diagnosis ◽

Error Rate ◽

Diagnostic System ◽

Diagnostic Error ◽

Observer Variation ◽

History Taking ◽

Computer Aided ◽

Computer Based ◽

Initial Survey

This report describes an evaluation of »observer variation« in history taking and examination of patients with abdominal pain. After an initial survey in which the degree of observer variation amongst the present authors fully confirmed previous rather gloomy forecasts, a system of »agreed definitions« was produced, and further studies showed a rapid and considerable fall in the degree of observer variation between the data recorded by the same authors. Finally, experience with a computer-based diagnostic system using the same system of agreed definitions showed the maximum diagnostic error rate due to faulty acquisition of data to be low (4.7°/o in a series of 552 cases). It is suggested as a result of these studies that — at least in respect of abdominal pain — errors in data acquisition by the clinician need not be the prime cause of faulty diagnoses.

Download Full-text

Breast Cancer Detection and Classification using Traditional Computer Vision Techniques: A Comprehensive Review

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405616666200406110547 ◽

2020 ◽

Vol 16 ◽

Cited By ~ 3

Author(s):

Saliha Zahoor ◽

Ikram Ullah Lali ◽

Muhammad Attique Khan ◽

Kashif Javed ◽

Waqar Mehmood

Keyword(s):

Breast Cancer ◽

Computer Aided Diagnosis ◽

Diagnose Breast Cancer ◽

Initial Stage ◽

Computer Aided ◽

Diagnosis And Classification ◽

And Performance ◽

Tools And Techniques ◽

Aided Diagnosis

: Breast Cancer is a common dangerous disease for women. In the world, many women died due to Breast cancer. However, in the initial stage, the diagnosis of breast cancer can save women's life. To diagnose cancer in the breast tissues there are several techniques and methods. The image processing, machine learning and deep learning methods and techniques are presented in this paper to diagnose the breast cancer. This work will be helpful to adopt better choices and reliable methods to diagnose breast cancer in an initial stage to survive the women's life. To detect the breast masses, microcalcifications, malignant cells the different techniques are used in the Computer-Aided Diagnosis (CAD) systems phases like preprocessing, segmentation, feature extraction, and classification. We have been reported a detailed analysis of different techniques or methods with their usage and performance measurement. From the reported results, it is concluded that for the survival of women’s life it is essential to improve the methods or techniques to diagnose breast cancer at an initial stage by improving the results of the Computer-Aided Diagnosis systems. Furthermore, segmentation and classification phases are challenging for researchers for the diagnosis of breast cancer accurately. Therefore, more advanced tools and techniques are still essential for the accurate diagnosis and classification of breast cancer.

Download Full-text