Menu
Home
Contact us
Stats
Categories
Calendar
Toggle Wiki
Wiki Home
Last Changes
Rankings
List pages
Orphan pages
Sandbox
Print
Toggle Image Galleries
Galleries
Rankings
Toggle Articles
Articles home
List articles
Rankings
Toggle Blogs
List blogs
Rankings
Toggle Forums
List forums
Rankings
Toggle File Galleries
List galleries
Rankings
Toggle Maps
Mapfiles
Toggle Surveys
List surveys
Stats
ITHEA Classification Structure > I. Computing Methodologies  > I.5 PATTERN RECOGNITION  > I.5.1 Models 
PERFORMANCE OF COMPUTER-AIDED DIAGNOSIS TECHNIQUES IN INTERPRETATION OF ...
By: Anatoli Nachev, Mairead Hogan, Borislav Stoyanov (4205 reads)
Rating: (1.00/10)

Abstract: This study explores and compares predictive abilities of six types of neural networks used as tools for computer-aided breast cancer diagnosis, namely, multilayer perceptron, cascade-correlation neural network, and four ART-based neural networks. Our experimental dataset consists of 803 patterns of 39 BI-RADS, mammographic, sonographic, and other descriptors. Using such a combination of features is not traditional in the field and we find it is better than traditional ones. The study also focuses on exploring how various feature selection techniques influence predictive abilities of the models. We found that certain feature subsets show themselves as top candidates for all the models, but each model performs differently with them. We estimated models performance by ROC analysis and metrics, such as max accuracy, area under the ROC curve, area under the convex hull, partial area under the ROC curve with sensitivity above 90%, and specificity at 98% sensitivity. We paid particular attention to the metrics with higher specificity as it reduces false positive predictions, which would allow decreasing unnecessary benign breast biopsies while minimizing the number of delayed breast cancer diagnoses. In order to validate our experiments we used 5-fold cross validation. In conclusion, out results show that among the neural networks considered here, best overall performer is the Default ARTMAP neural network.

Keywords: data mining, neural networks, heterogeneous data; breast cancer diagnosis, computer aided diagnosis.

ACM Classification Keywords: I.5.1- Computing Methodologies - Pattern Recognition – Models - Neural Nets

Link:

PERFORMANCE OF COMPUTER-AIDED DIAGNOSIS TECHNIQUES IN INTERPRETATION OF BREAST LESION DATA

Anatoli Nachev, Mairead Hogan, Borislav Stoyanov

http://foibg.com/ibs_isc/ibs-23/ibs-23-p23.pdf

Print
I.5.1 Models
article: POLLEN GRAINS RECOGNITION USING STRUCTURAL APPROACH AND NEURAL NETWORKS · Bankruptcy risk forecasting under uncertainty with application of fuzzy · CONVOLUTION NETWORKS AS A METHOD OF REALISATION OF CUSTOMS RISK-MANAGEMENT · АППРОКСИМАЦИЯ ФУНКЦИИ ЯРКОСТИ ОБЪЕКТА ПОЛУТОНОВОГО ИЗОБРАЖЕНИЯ · SELF-MODIFICATED PREDICATE NETWORKS · ON A METHOD OF MULTI-ALGORITHMIC CLASSIFICATION · PROCESSING SETS OF CLASSES’ LOGICAL REGULARITIES · ADAPTIVE FUZZY PROBABILISTIC CLUSTERING OF INCOMPLETE DATA · THE INVERSE MASLOV METHOD AND ANT TACTICS FOR EXHAUSTIVE SEARCH DECREASING · JOINT STUDY OF VISUAL PERCEPTION MECHANISM AND COMPUTER VISION SYSTEMS THAT ... · Online Handwritten Mathematical Expressions Recognition System Using Fussy ... · Automated Building Extraction System Applied On High Resolution Satellite ... · SPREADING THE MOORE - PENROSE PSEUDO INVERSE ON MATRICES EUCLIDEAN SPACES: ... · CONSTRUCTION OF CLASS LEVEL DESCRIPTION FOR EFFICIENT RECOGNITION OF ... · INFORMATION TECHNOLOGY OF PROCESSING INFORMATION OF THE CUSTOMS CONTROL · MODEL FOR ASTRONOMICAL DATING OF THE CHRONICLE OF HYDATIUS: ... · MATRIX “FEATURE VECTORS” IN GROUPING INFORMATION PROBLEM: LINEAR ... · EFFICIENT SIMULATION FOR PROLOG IMPLEMENTATION OF IMAGE RECOGNITION PROBLEM · VECTORS AND MATRIXES IN GROUPING INFORMATION PROBLEM · CROP STATE AND AREA ESTIMATION IN UKRAINE BASED ON REMOTE AND INSITU ... · THE INVERSE METHOD FOR SOLVING ARTIFICIAL INTELLIGENCE PROBLEMS IN ... · RECURRENT PROCEDURE IN SOLVING THE GROUPING INFORMATION PROBLEM IN APPLIED... · ‘FEATURE VECTORS’ IN GROUPING INFORMATION PROBLEM IN APPLIED MATHEMATICS: .. · ADAPTIVE CLUSTERING OF INCOMPLETE DATA USING NEURO-FUZZY KOHONEN NETWORK · INTELLIGENT ANALYSIS OF MARKETING DATA · FUZZY SETS AS A MEAN FOR UNCERTAINTY HANDLING: MATH, APPLIED MATH, HEURISTICS · PERFORMANCE OF COMPUTER-AIDED DIAGNOSIS TECHNIQUES IN INTERPRETATION OF ... · FUZZY SETS: MATH, APPLIED MATH, HEURISTICS? PROBLEMS AND INTERPRETATIONS · ОНЛАЙН РАСПОЗНАВАНИЕ РУКОПИСНЫХ МАТЕМАТИЧ� · РАСПОЗНАВАНИЕ ЗДАНИЙ НА СПУТНИКОВЫХ СНИМКА · СЛОЖНЫЕ ЗАДАЧИ РАСПОЗНАВАНИЯ ОБРАЗОВ И ВОЗМОЖНОСТИ ИХ РЕШЕНИЯ · THE USAGE OF NEURAL NETWORKS FOR THE MEDICAL DIAGNOSIS · SYNTHESIS OF CORRECTOR FAMILY WITH HIGH RECOGNITION ABILITY* · FLOOD RISK ASSESSMENT BASED ON GEOSPATIAL DATA · FUZZY ARTMAP NEURAL NETWORKS FOR COMPUTER AIDED DIAGNOSIS · STRUCTURAL MODEL OF HALFTONE IMAGE AND IMAGE SEGMENTATION EXPERIMENTS · HIGH-PERFORMANCE INTELLIGENT COMPUTATIONS ... · INTELLIGENCE ALGORITHMS FOR INCREASING NAVIGATION SYSTEMS ACCURACY · ADAPTIVE GUSTAFSON-KESSEL FUZZY CLUSTERING ALGORITHM BASED ON ... · UNCERTAINTY AND FUZZY SETS: CLASSIFYING THE SITUATION · LOGIC BASED PATTERN RECOGNITION - ONTOLOGY CONTENT (1) 1 · EVALUATING MISCLASSIFICATION PROBABILITY USING EMPIRICAL RISK1 · FUZZY SETS: ABSTRACTION AXIOM, STATISTICAL INTERPRETATION, OBSERVATIONS ... · AN APPROACH TO COLLABORATIVE FILTERING BY ARTMAP NEURAL NETWORKS ·
Login
[ register | I forgot my password ]
World Clock
Powered by Tikiwiki Powered by PHP Powered by Smarty Powered by ADOdb Made with CSS Powered by RDF powered by The PHP Layers Menu System
RSS Wiki RSS Blogs rss Articles RSS Image Galleries RSS File Galleries RSS Forums RSS Maps rss Calendars
[ Execution time: 0.08 secs ]   [ Memory usage: 7.60MB ]   [ GZIP Disabled ]   [ Server load: 0.67 ]
Powered by Tikiwiki CMS/Groupware