An Automatic Computer-Aided Detection System for Meniscal Tears on Magnetic Resonance Images

被引：15

作者：

Ramakrishna, Bharath ^{[2
,3
]}

Liu, Weimin ^{[2
]}

Saiprasad, Ganesh ^{[2
]}

Safdar, Nabile ^{[3
]}

Chang, Chein-I ^{[2
,4
,5
]}

Siddiqui, Khan ^{[6
]}

Kim, W. ^{[6
,7
]}

Siegel, Eliot ^{[3
,6
]}

Chai, Jyh-Wen ^{[1
,8
]}

Chen, Clayton Chi-Chang ^{[9
,10
]}

Lee, San-Kan ^{[8
]}

机构：

[1] China Med Univ, Coll Med, Dept Radiol, Taichung 404, Taiwan

[2] Univ Maryland, Dept Comp Sci & Elect Engn, Remote Sensing Signal & Image Proc Lab, Baltimore, MD 21250 USA

[3] Univ Maryland, Sch Med, Baltimore, MD 21201 USA

[4] Natl Chung Hsing Univ, Dept Elect Engn & Environm Restorat, Taichung 402, Taiwan

[5] Natl Chung Hsing Univ, Disaster Reduct Res Ctr, Taichung 402, Taiwan

[6] VA Maryland Hlth Care Syst, Baltimore, MD 21201 USA

[7] Hosp Univ Penn, Philadelphia, PA 19104 USA

[8] Taichung Vet Gen Hosp, Dept Radiol, Taichung 40705, Taiwan

[9] Cent Taiwan Univ Sci & Technol, Dept Radiol Technol, Taichung 406, Taiwan

[10] Taichung Vet Gen Hosp, Dept Radiol, Taichung 407, Taiwan

来源：

IEEE TRANSACTIONS ON MEDICAL IMAGING | 2009年 / 28卷 / 08期

关键词：

Computer aided diagnosis (CAD); magnetic resonance imaging (MRI); meniscal tears; orthopedics; shape analysis; ARTICULAR-CARTILAGE; KNEE; SEGMENTATION; DIAGNOSIS; ACCURACY; SURFACE;

D O I：

10.1109/TMI.2009.2014864

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Knee-related injuries including meniscal tears are common in both young athletes and the aging population, and require accurate diagnosis and surgical intervention when appropriate. With proper techniques and radiologists' experienced skills, confidence in detection of meniscal tears can be quite high. This paper develops a novel computer-aided detection ( CAD) diagnostic system for automatic detection of meniscal tears in the knee. Evaluation of this CAD system using an archived database of images from 40 individuals with suspected knee injuries indicates that the sensitivity and specificity of the proposed CAD system are 83.87% and 75.19%, respectively, compared to the mean sensitivity and specificity of 77.41% and 81.39%, respectively, obtained by experienced radiologists in routine diagnosis without using the CAD. The experimental results suggest that the developed CAD system has great potential and promise in automatic detection of both simple and complex meniscal tears of the knee.

引用

页码：1308 / 1316

页数：9

共 21 条

[1] MENISCAL TEARS OF THE KNEE - ACCURACY OF MR IMAGING [J].

CRUES, JV ;

MINK, J ;

LEVY, TL ;

LOTYSCH, M ;

STOLLER, DW .

RADIOLOGY, 1987, 164 (02) :445-448

[2] MR DIAGNOSIS OF MENISCAL TEARS OF THE KNEE - IMPORTANCE OF HIGH SIGNAL IN THE MENISCUS THAT EXTENDS TO THE SURFACE [J].

DESMET, AA ;

NORRIS, MA ;

YANDOW, DR ;

QUINTANA, FA ;

GRAF, BK ;

KEENE, JS .

AMERICAN JOURNAL OF ROENTGENOLOGY, 1993, 161 (01) :101-107

[3] ACCURACY OF DIAGNOSES FROM MAGNETIC-RESONANCE-IMAGING OF THE KNEE - A MULTICENTER ANALYSIS OF 1014 PATIENTS [J].

FISCHER, SP ;

FOX, JM ;

DELPIZZO, W ;

FRIEDMAN, MJ ;

SNYDER, SJ ;

FERKEL, RD .

JOURNAL OF BONE AND JOINT SURGERY-AMERICAN VOLUME, 1991, 73A (01) :2-10

[4]

Fox Michael G, 2007, Magn Reson Imaging Clin N Am, V15, P103, DOI 10.1016/j.mric.2007.02.004

[5] Segmentation of the bones in MRIs of the knee using phase, magnitude, and shape information [J].

Fripp, Jurgen ;

Bourgeat, Pierrick ;

Crozier, Stuart ;

Ourselin, Sebastien .

ACADEMIC RADIOLOGY, 2007, 14 (10) :1201-1208

[6]

Hata Y, 2001, LECT NOTES COMPUT SC, V2206, P55

[7]

Li K, 2005, LECT NOTES COMPUT SC, V3565, P406

[8] MR-IMAGING OF THE KNEE - EXPANDED CLASSIFICATION AND PITFALLS TO INTERPRETATION OF MENISCAL TEARS [J].

MESGARZADEH, M ;

MOYER, R ;

LEDER, DS ;

REVESZ, G ;

RUSSONIELLO, A ;

BONAKDARPOUR, A ;

TEHRANZADEH, J ;

GUTTMANN, D .

RADIOGRAPHICS, 1993, 13 (03) :489-500

[9]

RAMAKRISHNA B, 2008, SPIE MED IMAG

[10]

RAMAKRISHNA B, IEEE T MED IMA UNPUB

← 1 2 3 →