학술논문
WHAT CAN WE ACTUALLY SEE USING COMPUTER AIDED DETECTION IN MAMMOGRAPHY?/STO ZAPRAVO MOZEMO VIDJETI PRIMJENOM RACUNALNO POTPOMOGNUTE ANALIZE KOD MAMOGRAFIJE?
Original Scientific Paper
Original Scientific Paper
Document Type
Report
Source
Acta Clinica Croatica. December 2020, Vol. 59 Issue 4, p576, 6 p.
Subject
Language
English
ISSN
0353-9466
Abstract
Introduction Breast cancer is the most common cancer in women and also one of the biggest healthcare issues. Early screening with mammography and advancements in therapy have significantly reduced mortality [...]
The main goal of this study was to compare the results of computer aided detection (CAD) analysis in screening mammography with the results independently obtained by two radiologists for the same samples and to determine the sensitivity and specificity of CAD for breast lesions. A total of436 mammograms were analyzed with CAD. For each screening mammogram, the changes in breast tissue recognized by CAD were compared to the interpretations of two radiologists. The sensitivity and specificity of CAD for breast lesions were calculated using contingency table. The sensitivity of CAD for all lesions was 54% and specificity 16%. CAD sensitivity for suspicious lesions only was 86%. CAD sensitivity for microcalcifications was 100% and specificity 45%. CAD mainly 'mistook' glandular parenchyma, connective tissue and blood vessels for breast lesions, and blood vessel calcifications and axillary folds for microcalcifications. In this study, we confirmed CAD as an excellent tool for recognizing microcalcifications with 100% sensitivity. However, it should not be used as a stand-alone tool in breast screening mammography due to the high rate of false-positive results. Key words: Breast neoplasm; Image interpretation computer-assisted; Mammography; Computer aided detection (CAD); CAD sensitivity; CAD specificity Svrha ovoga istrazivanja bila je usporediti rezultate racunalno potpomognute analize (computer aided detection, CAD) u probirnoj mamografiji s rezultatima analize dva neovisna radiologa te utvrditi osjetljivost i specificnost CAD-a za lezije u dojkama. Analizirali smo 436 mamograma pomocu CAD-a i usporedili rezultate s interpretacijom dva neovisna radiologa. Izracunali smo osjetljivost i specificnost CAD-a za lezije u dojkama putem tablica kontingencije. Osjetljivost CAD-a za otkrivanje svih lezija u dojkama iznosila je 54%, a specificnost 16%. Osjetljivost CAD-a za sumnjive lezije bila je 86%, a za mikrokalcifikacije 100% uz specificnost od 45%. CAD je uglavnom pogresno interpretirao zljezdani parenhim, vezivno tkivo i krvne zile kao tvorbe u dojkama, dok je kalcifikacije u krvim zilama i aksilarni nabor mijesao s mikrokalcifikacijama. Ovom studijom smo potvrdili da je CAD izvrstan alat za otkrivanje mikrokalcifikacija s osjetljivoscu od 100%. No, ipak se ne bi trebao rabiti kao jedina metoda u probirnoj mamografiji dojki uzimajuci u obzir kolicinu lazno pozitivnih rezultata koja je prilicno visoka. Kljucne rijeci: Karcinom dojke; Racunalno potpomognuta analiza slika; Mamografija; Racunalno potpomognuta analiza (CAD); Osjetljivost CAD; Specificnost CAD
The main goal of this study was to compare the results of computer aided detection (CAD) analysis in screening mammography with the results independently obtained by two radiologists for the same samples and to determine the sensitivity and specificity of CAD for breast lesions. A total of436 mammograms were analyzed with CAD. For each screening mammogram, the changes in breast tissue recognized by CAD were compared to the interpretations of two radiologists. The sensitivity and specificity of CAD for breast lesions were calculated using contingency table. The sensitivity of CAD for all lesions was 54% and specificity 16%. CAD sensitivity for suspicious lesions only was 86%. CAD sensitivity for microcalcifications was 100% and specificity 45%. CAD mainly 'mistook' glandular parenchyma, connective tissue and blood vessels for breast lesions, and blood vessel calcifications and axillary folds for microcalcifications. In this study, we confirmed CAD as an excellent tool for recognizing microcalcifications with 100% sensitivity. However, it should not be used as a stand-alone tool in breast screening mammography due to the high rate of false-positive results. Key words: Breast neoplasm; Image interpretation computer-assisted; Mammography; Computer aided detection (CAD); CAD sensitivity; CAD specificity Svrha ovoga istrazivanja bila je usporediti rezultate racunalno potpomognute analize (computer aided detection, CAD) u probirnoj mamografiji s rezultatima analize dva neovisna radiologa te utvrditi osjetljivost i specificnost CAD-a za lezije u dojkama. Analizirali smo 436 mamograma pomocu CAD-a i usporedili rezultate s interpretacijom dva neovisna radiologa. Izracunali smo osjetljivost i specificnost CAD-a za lezije u dojkama putem tablica kontingencije. Osjetljivost CAD-a za otkrivanje svih lezija u dojkama iznosila je 54%, a specificnost 16%. Osjetljivost CAD-a za sumnjive lezije bila je 86%, a za mikrokalcifikacije 100% uz specificnost od 45%. CAD je uglavnom pogresno interpretirao zljezdani parenhim, vezivno tkivo i krvne zile kao tvorbe u dojkama, dok je kalcifikacije u krvim zilama i aksilarni nabor mijesao s mikrokalcifikacijama. Ovom studijom smo potvrdili da je CAD izvrstan alat za otkrivanje mikrokalcifikacija s osjetljivoscu od 100%. No, ipak se ne bi trebao rabiti kao jedina metoda u probirnoj mamografiji dojki uzimajuci u obzir kolicinu lazno pozitivnih rezultata koja je prilicno visoka. Kljucne rijeci: Karcinom dojke; Racunalno potpomognuta analiza slika; Mamografija; Racunalno potpomognuta analiza (CAD); Osjetljivost CAD; Specificnost CAD