Computer-Aided Diagnosis of Thyroid Malignancy Using an Artificial Immune System Classification Algorithm

被引：10

作者：

Delibasis, Konstantinos K. ^{[1
]}

Asvestas, Pantelis A. ^{[2
]}

Matsopoulos, George K. ^{[1
]}

Zoulias, Emmanouil ^{[1
]}

Tseleni-Balafouta, Sofia ^{[3
]}

机构：

[1] Natl Tech Univ Athens, Athens 15780, Greece

[2] Technol Educ Inst Athens, Dept Med Instruments Technol, Fac Technol Applicat, Athens 12210, Greece

[3] Univ Athens, Sch Med, Dept Pathol A, Athens 10561, Greece

来源：

IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE | 2009年 / 13卷 / 05期

关键词：

Artificial immune systems (AIS); classification; feature selection; fine needle aspiration (FNA); thyroid malignancy; NEEDLE-ASPIRATION BIOPSY; DECISION-SUPPORT; RECOGNITION;

D O I：

10.1109/TITB.2008.926990

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The diagnosis of thyroid malignancy by fine needle aspiration (FNA) examination has been proven to show wide variations of sensitivity and specificity. This paper proposes the utilization of a computer-aided diagnosis system based on a supervised classification algorithm from the artificial immune systems to assist the task of thyroid malignancy diagnosis. The core of the proposed algorithm is the so-called BoxCells, which are defined as parallelepipeds in the feature space. Properly defined operators act on the BoxCells in order to convert them into individual, elementary classifiers. The proposed algorithm is applied on FNA data from 2016 subjects with verified diagnosis and has exhibited average specificity higher than 99%, 90% sensitivity, and 98.5% accuracy. Furthermore, 24% of the cases that are characterized as "suspicious" by FNA and are histologically proven nonmalignancies have been classified correctly.

引用

页码：680 / 686

页数：7

共 27 条

[1] [Anonymous], 1999, INT EDIT PRENTICE HA
[2] BERSINI H, P 1 INT C ART IMM SY, P107
[3] The immune system as a model for pattern recognition and classification
Carter, JH
[J]. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2000, 7 (01) : 28 - 41
[4] Accuracy of fine needle aspiration biopsy of thyroid nodules in detecting malignancy in childhood:: Comparison with conventional clinical, laboratory, and imaging approaches
Corrias, A
Einaudi, S
Chiorboli, E
Weber, G
Crinó, A
Andreo, M
Cesaretti, G
de Sanctis, L
Messina, MF
Segni, M
Cicchetti, M
Vigone, M
Pasquino, AM
Spera, S
de Luca, F
Mussa, GC
Bona, G
[J]. JOURNAL OF CLINICAL ENDOCRINOLOGY & METABOLISM, 2001, 86 (10) : 4644 - 4648
[5] Learning and optimization using the clonal selection principle
de Castro, LN
Von Zuben, FJ
[J]. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2002, 6 (03) : 239 - 251
[6] DECASTRO LN, P IEEE C EV COMP CEC, V1, P699
[7] An introduction to ROC analysis
Fawcett, Tom
[J]. PATTERN RECOGNITION LETTERS, 2006, 27 (08) : 861 - 874
[8] Forrest S., 1994, Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy (Cat. No.94CH3444-7), P202, DOI 10.1109/RISP.1994.296580
[9] FINE-NEEDLE ASPIRATION BIOPSY OF THE THYROID - AN APPRAISAL
GHARIB, H
GOELLNER, JR
[J]. ANNALS OF INTERNAL MEDICINE, 1993, 118 (04) : 282 - 289
[10] GOLDBERG D, 1989, GENETIC ALGORITHMS O

← 1 2 3 →