Objective: Development of a fully automated computer application for detection and classification of clustered microcalcifications using neural nets. Material and Methods: Mammographic films with clustered microcalcifications of known histology were digitized. All clusters were rated by two radiologists on a 3 point scale: benign, indeterminate and malignant. Automated detected clustered microcalcifications were clustered. Features derived from those clusters were used as input to 2 artificial neural nets: one was trained to identify the indeterminate clusters, whereas the second ANN classified the remaining clusters in benign or malignant ones. Performance evaluation followed the patient-based receiver operator characteristic analysis. Results: For identification of patients with indeterminate clusters a an Az-value of 0.8741 could be achieved. For the remaining patients their clusters could be classified as benign or malignant at an Az-value of 0.8749, a sensitivity of 0.977 and specificity of 0.471. Conclusions: A fully automated computer system for detection and classification of clustered microcalcifications was developed. The system is able to identify patients with indeterminate clusters, where additional investigations are recommended, and produces a reliable estimation of the biologic dignity for the remaining ones.
%0 Journal Article
%1 sor2000
%A Sorantin, E.
%A Schmidt, F.
%A Mayer, H.
%A Becker, M.
%A Szepesvári, Cs.
%A Graif, E.
%A Winkler, P.
%D 2000
%J Journal of Computing and Information Technology
%K application, clinical decision health image informatics, networks, neural processing, support
%N 2
%T Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets
%U http://cit.srce.hr/index.php/CIT/article/view/1415
%V 8
%X Objective: Development of a fully automated computer application for detection and classification of clustered microcalcifications using neural nets. Material and Methods: Mammographic films with clustered microcalcifications of known histology were digitized. All clusters were rated by two radiologists on a 3 point scale: benign, indeterminate and malignant. Automated detected clustered microcalcifications were clustered. Features derived from those clusters were used as input to 2 artificial neural nets: one was trained to identify the indeterminate clusters, whereas the second ANN classified the remaining clusters in benign or malignant ones. Performance evaluation followed the patient-based receiver operator characteristic analysis. Results: For identification of patients with indeterminate clusters a an Az-value of 0.8741 could be achieved. For the remaining patients their clusters could be classified as benign or malignant at an Az-value of 0.8749, a sensitivity of 0.977 and specificity of 0.471. Conclusions: A fully automated computer system for detection and classification of clustered microcalcifications was developed. The system is able to identify patients with indeterminate clusters, where additional investigations are recommended, and produces a reliable estimation of the biologic dignity for the remaining ones.
@article{sor2000,
abstract = {Objective: Development of a fully automated computer application for detection and classification of clustered microcalcifications using neural nets. Material and Methods: Mammographic films with clustered microcalcifications of known histology were digitized. All clusters were rated by two radiologists on a 3 point scale: benign, indeterminate and malignant. Automated detected clustered microcalcifications were clustered. Features derived from those clusters were used as input to 2 artificial neural nets: one was trained to identify the indeterminate clusters, whereas the second ANN classified the remaining clusters in benign or malignant ones. Performance evaluation followed the patient-based receiver operator characteristic analysis. Results: For identification of patients with indeterminate clusters a an Az-value of 0.8741 could be achieved. For the remaining patients their clusters could be classified as benign or malignant at an Az-value of 0.8749, a sensitivity of 0.977 and specificity of 0.471. Conclusions: A fully automated computer system for detection and classification of clustered microcalcifications was developed. The system is able to identify patients with indeterminate clusters, where additional investigations are recommended, and produces a reliable estimation of the biologic dignity for the remaining ones.},
added-at = {2020-03-17T03:03:01.000+0100},
author = {Sorantin, E. and Schmidt, F. and Mayer, H. and Becker, M. and Szepesv{\'a}ri, {Cs}. and Graif, E. and Winkler, P.},
bdsk-url-1 = {http://cit.srce.hr/index.php/CIT/article/view/1415},
biburl = {https://www.bibsonomy.org/bibtex/2da16017ea881510dd6f5467ef204a1e7/csaba},
date-added = {2010-09-02 10:15:27 -0600},
date-modified = {2010-09-02 13:09:59 -0600},
interhash = {9ac5d48b9f37a7e11ed5830a0cc38e20},
intrahash = {da16017ea881510dd6f5467ef204a1e7},
journal = {Journal of Computing and Information Technology},
keywords = {application, clinical decision health image informatics, networks, neural processing, support},
number = 2,
pdf = {papers/JCIT2000.pdf},
timestamp = {2020-03-17T03:03:01.000+0100},
title = {Computer Aided Diagnosis of Clustered Microcalcifications Using Artificial Neural Nets},
url = {http://cit.srce.hr/index.php/CIT/article/view/1415},
volume = 8,
year = 2000
}