Preview

Medical Visualization

Advanced search

Diagnostic Value of 1st and 2nd Generation Computer Aided Detection Systems for Mammography: a Comparative Assessment

https://doi.org/10.24835/1607-0763-2017-1-90-102

Abstract

Aim: to compare the diagnostic efficacy of generation I and II computer aided detection (CAD) systems for mammography of our own design using the large set of unselect ed mammography images obtained in a routine clinical practice settings.

 

Material and methods. Both CADs were tested on the set of 1532 mammography images of 356 women with confirmed breast cancer (BC). We assessed their value in the detection of suspicious areas with various characteristics located on the different density background. Size of BC lesions varied from 4 to 35 mm (mean – 13,4 ± 6,3 mm). We excluded BC representing only with microcalcification clusters from this analysis, because this task is solved using the separate universal module compatible with both CADs.

Results. For I and II generation CADs we obtained the following results: detection of small nodular BCs (≤10 mm) – 41 of 52 (78.85%) and 48 of 52 (92.31%; p > 0.05), respectively; detection of BCs visible as asymmetric areas – 18 of 18 (100%) and 13 of 18 (72.2%; p > 0.05), respectively; detection of only partially visible masses – 15 of 18 (83.3%) and 17 of 18 (94.4%; p > 0.05); detection of lesions poorly visible or invisible on standard mammography images due to the high density background (C-D types according to the ACR 2013 classification) – 9 of 16 (56.3%) and 7 of 16 (70.0%; p = 0.046). Total detection rate was 88.76% (316 of 356 cases) – for CAD I and 90.73% (323 of 356 cases; р > 0.05) – for CAD II. Mean false positive marks rate was 1.8 and 1.3 per image, respectively, – for ACR А-В images and 2.6 and 1.8 per image, respectively – for ACR C-D images (p < 0.05).

Conclusion. Generally the diagnostic value of CAD II is not inferior that of CAD I in all analyzed situations, except the poorly visible or invisible lesions on the dense breast background. Moreover, CAD II is probably superior CAD I in the detection of spiculated small masses. The rate of false positive marks was significantly higher for CAD I.

About the Authors

D. V. Pasynkov
Oncology Dispenser of Mari El Republic
Russian Federation

cand. of med. sci., head of radiology department, Oncology Dispenser of Mari El Republic, Yoshkar-Ola

22 Osipenko str., Yoshkar-Ola 424037, Russia. Phone: +7-9023-29-76-51



I. A. Egoshin
Mari State University
Russian Federation
postgraduate student, department of applied mathematics and informatics, Mari State University, Yoshkar-Ola


A. A. Kolchev
Kazan Federal University
Russian Federation

cand. of physmath. sci., associate professor of radio astronomy department, Kazan Federal University, Kazan



I. V. Kliouchkin
Kazan State Medical University
Russian Federation

doct. of med. sci., professor of general surgery department, Kazan State Medical University, Kazan



O. V. Busygina
Oncology Dispenser of Mari El Republic
Russian Federation

radiologist, radiology department, Oncology Dispenser of Mari El Republic, Yoshkar-Ola



References

1. Комарова В.П., Комарова Л.Е., Поддубная И.В. Фулвестрант в современной терапии распространенного рака молочной железы: фармакоэкономическое обоснование. Современная онкология. 2007; 9 (3): 33–35.

2. Bleyer A., Welch H.G. Effect of Three Decades of Screening Mammography on Breast- Cancer Incidence. N. Engl. J. Med. 2012; 367: 1998–2005. DOI: 10.1056/NEJMoa1206809.

3. Состояние онкологической помощи населению России в 2014 году; Под ред. А.Д. Каприна, В.В. Старинского, Г.В. Петровой. М.: МНИОИ им. П.А. Герцена – филиал ФГБУ «НМИРЦ» Минздрава России, 2015. 235 с.

4. Комарова Л.Е. Маммографический скрининг (состояние вопроса и перспективы). Российский онкологический журнал. 2015; 4: 9–16.

5. Клюшкин И.В., Пасынков Д.В., Бусыгина О.В., Пасынкова О.О. К вопросу о возможном повышении риска рака молочной железы у пациенток, перенесших оперативные вмешательства на ней по поводу доброкачественной патологии. Казанский медицинский журнал. 2015; 96 (3): 316–321. DOI: 10.17750/KMJ2015-316.

6. Baker J.A., Rosen E.L., Lo J.Y., Gimenez E.I., Walsh R., Soo M.S. Computer-Aided Detection (CAD) in Screening Mammography: Sensitivity of Commercial CAD Systems for Detecting Architectural Distortion. Am. J. Roentgenol. 2003; 181: 1083–1088. DOI: 10.2214/ajr.181.4.1811083.

7. Lehman C.D., Wellman R.D., Buist D.S., Kerlikowske K., Tosteson A.N., Miglioretti D.L. Diagnostic Accuracy of Digital Screening Mammography With and Without Computer-Aided Detection. JAMA Intern. Med. 2015; 175 (11): 1828–1837. DOI: 10.1001/jamainternmed.2015.5231.

8. Пасынков Д.В., Клюшкин И.В., Бусыгина О.В. Способ повышения чувствительности и специфичности систем компьютерного анализа маммографических изображений при высокой плотности паренхимы молочной железы. Казанский медицинский журнал. 2016; 97 (3): 443–449. DOI: 10.17750/KMJ2016-.

9. Никитин О.Р., Пасечник А.С. Оконтуривание и сегментация в задачах автоматизированной диагностики пато логий. Методы и устройства передачи и обработки информации. 2009; 11: 300–309.

10. Chinu A.C. Overview and Comparative Analysis of Edge Detection Techniques in Digital Image Processing. Intern. J. Inform. Comput. Technol. 2014; 4 (10): 973–980.

11. Egoshin I., Pasynkov D., Kolchev A., Kliouchkin I. Value of nested contours analysis algorithm in mammographic image processing. Int. J. Comput. Assist. Radiol. Surg. 2016; 11 (1): S278.

12. Calas M.G.B., Gutfilen B., Pereira W.C.A. CAD and mammography: why use this tool? Radiol. Bras. 2012; 45 (1): 25–29.

13. Fuster D., Pagès M., Granados U. Update on PET/CT colonography in the diagnosis of colorectal cancer. Revista Española de Medicina Nuclear e Imagen Molecular. 2016; 35 (4): 246–252. DOI: 10.1016/j.remn.2016.05.001.

14. Kakinuma R., Ashizawa K., Kobayashi T. Comparison of sensitivity of lung nodule detection between radiologists and technologists on low-dose CT lung cancer screening images. Br. J. Radiol. 2012; 85 (1017): e603–e608. DOI: 10.1259/bjr/75768386

15. Cao J.Q., Olson R.A., Tyldesley S.K. Comparison of recurrence and survival rates after breast-conserving therapy and mastectomy in young women with breast cancer. Current Oncol. 2013; 20 (6): e593–e601. DOI: 10.3747/co.20.1543.

16. Пасынков Д.В., Клюшкин И.В., Бусыгина О.В. Контурный анализ маммографических изображений доброкачественной и злокачественной патологии молочной железы. Казанский медицинский журнал. 2015; 96 (3): 322–325. DOI: 10.17750/KMJ2015-322.


Review

For citations:


Pasynkov D.V., Egoshin I.A., Kolchev A.A., Kliouchkin I.V., Busygina O.V. Diagnostic Value of 1st and 2nd Generation Computer Aided Detection Systems for Mammography: a Comparative Assessment. Medical Visualization. 2017;(1):90-102. (In Russ.) https://doi.org/10.24835/1607-0763-2017-1-90-102

Views: 1285


ISSN 1607-0763 (Print)
ISSN 2408-9516 (Online)