Classiwng Cells for Cancer Diagnosis Using Neural

نویسنده

  • Ciamac Moallemi
چکیده

A S U C C E S S F U L COMPUTERbased system for diagnosing bladder cancer must accurately classify various objects in an image of cells from a urine sample. Typically, an object falls into one of two classes: Well or Not-well. The Well class contains the cells that will actually be useful for diagnosing bladder cancer. The Notwell class includes everything else, such as intercellular “garbage” and cells that would not aid in the diagnosis. In a sense, this classification filters out objects that are not needed. Yet, errors in this classification are undesirable. If a Well object is classified as Not-well, valuable information could be lost. Therefore, the classifier must be accurate if it is to be used clinically. There have been previous attempts to solve this classification problem. Wong et al. used a “selective mapping algorithm,” which used a tree classifier to classify objects by using thresholds for certain extracted features1 For example, the system deemed an object Not-well if its area was above or below a certain value. Similar tests were applied to other features. This system achieved a total misclassification rate of 23.2 percent. Systems prior to this also had error ra tes2 Furthermore, the time required by these systems for automated analysis clearly makes them impractical. THE WORK REPORTED HERE NETTED THE 15-YEAR-OLD AUTHOR Fl lTH PLACE AND A $1 5,000 SCHOLARSHIP IN THE ~ O T H ANNUAL WESTINGHOUSE SCIENCE TALENT SEARCH FOR HIGH-SCHOOL STUDENTS.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Diagnosis of Breast Cancer using a Combination of Genetic Algorithm and Artificial Neural Network in Medical Infrared Thermal Imaging

Introduction This study is an effort to diagnose breast cancer by processing the quantitative and qualitative information obtained from medical infrared imaging. The medical infrared imaging is free from any harmful radiation and it is one of the best advantages of the proposed method. By analyzing this information, the best diagnostic parameters among the available parameters are selected and ...

متن کامل

Diagnosis of brain tumor using PNN neural networks

Cells grow and then need a very neat method to create new cells that work properly to maintain the health of the body. When the ability to control the growth of the cells is lost, they are unconsidered and often divided without order. Exemplified cells form a tissue mass called the tumor. In fact, brain tumors are abnormal and uncontrolled cell proliferations. Segmentation methods are used in b...

متن کامل

Prediction of Breast Tumor Malignancy Using Neural Network and Whale Optimization Algorithms (WOA)

Introduction: Breast cancer is the most prevalent cause of cancer mortality among women. Early diagnosis of breast cancer gives patients greater survival time. The present study aims to provide an algorithm for more accurate prediction and more effective decision-making in the treatment of patients with breast cancer. Methods: The present study was applied, descriptive-analytical, based on the ...

متن کامل

Diagnosis and treatment of the Cancer Tumor Cells (CTCs); Capturing and Diagnosing Kits

Objective(s): In the developed countries, one of the leading causes of death is cancer. Cancer cells with their unique and destructive characteristics impose high costs on communities. Methods: In this study, we will review the latest cancer researches an...

متن کامل

Non-melanoma skin cancer diagnosis with a convolutional neural network

Background: The most common types of non-melanoma skin cancer are basal cell carcinoma (BCC), and squamous cell carcinoma (SCC). AKIEC -Actinic keratoses (Solar keratoses) and intraepithelial carcinoma (Bowen’s disease)- are common non-invasive precursors of SCC, which may progress to invasive SCC, if left untreated. Due to the importance of early detection in cancer treatment, this study aimed...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004