Computer-aided detection (CAD) of breast cancer on full field digital and screening film mammograms

Background: Mammography is acknowledged as the single most effective method of screening for breast cancer and is credited with helping to reduce breast cancer mortality by approximately 30%. CAD systems are a new tool in detecting breast cancers on screening mammograms and in detecting potentially suspicious abnormalities on a mammogram. The aim & objective is to main aim of the present study to evaluate the performance of Computer Aided Detection using Full Field Digital Mammography in Breast Cancer imaging. Subjects and Methods:In the present study, Cases with lump breast with clinical suspicion of breast cancer and post op recurrence of breast cancer were imaged with FFDM and images were read on the viewing monitor without and with the aid of CAD software. The present study confirms that the diagnosis of breast cancer is made only following histopathology of respected specimen. Results: The maximum incidence was in 41-50 years and 51-60 years which was 13 cases in each group (30 %). There were 25 cases out of 40 (62.5%) in which the lesion was marked by CAD. Out of which in 20 cases (50%) only one lesion was marked by CAD and in 4 cases (10%) two lesions were marked by CAD. The total number of lesions marked by CAD was 25 (62.5%). Majority of patients had scattered fibro glandular density of breast. This was present in 19 patients (47.5%). 10 patients (20%) had heterogeneously dense breast, 07 patients (17.5%) had fatty breast and 04 patients (10%) had extremely dense breast. In majority of cases the lesion type was mass alone which was present in 26 cases (60%). While 10 cases (25%) presented as mass with microcalcifications and 4 cases (10%) presented with microcalcifications alone. In 24 cases there was no spread of cluster of micro calcification (60%). In 7 cases (17.5%) the spread of cluster of micro calcification was <10mm, in 4 cases (10%) the spread of cluster of micro calcification was 21-30 mm and in 5 cases ( 12.5%) the spread of cluster of micro calcification was > 40mm. In majority of cases the HPE revealed DCIS which was seen in 22 cases (55%), 08 cases (20%) were invasive ductal carcinoma and 02 cases was invasive lobular carcinoma. In 22 cases (55%) the BIRADS for the breast affected with cancer was BIRADS-V. While in 14 cases (35%) the score was BIRADS-IV, 04 cases (10%) the score was BIRADS-VI and in 02 case (5%) the score was BIRADS-III. The sensitivity, specificity and accuracy of CAD for detection of mass were 70%, 100% and 85% respectively and for detection of cluster of microcalcification were 100% respectively. Conclusion: CAD with FFDM is good at detection of Microcalcifications. Detection of masses is better without the aid of CAD as compared to CAD. However detection of lesion improves if reading of mammogram is done both with and without CAD.

Download Full-text

Detection of Breast Cancer with Full-Field Digital Mammography and Computer-Aided Detection

American Journal of Roentgenology ◽

10.2214/ajr.07.3884 ◽

2009 ◽

Vol 192 (2) ◽

pp. 337-340 ◽

Cited By ~ 35

Author(s):

Juliette S. The ◽

Kathy J. Schilling ◽

Jeffrey W. Hoffmeister ◽

Euvondia Friedmann ◽

Ryan McGinnis ◽

...

Keyword(s):

Breast Cancer ◽

Digital Mammography ◽

Computer Aided Detection ◽

Full Field ◽

Full Field Digital Mammography ◽

Computer Aided

Download Full-text

Sensitivity of integral computer-aided detection with full-field digital mammography for detection of breast cancer according to different histopathological tumor types and appearances

Breast Cancer Research ◽

10.1186/bcr2666 ◽

2010 ◽

Vol 12 (S3) ◽

Cited By ~ 1

Author(s):

K Pinker ◽

N Perry ◽

S Milner ◽

K Mokbel ◽

S Duffy

Keyword(s):

Breast Cancer ◽

Digital Mammography ◽

Computer Aided Detection ◽

Full Field ◽

Full Field Digital Mammography ◽

Computer Aided ◽

Tumor Types

Download Full-text

Comparison of two software versions of a commercially available computer-aided detection (CAD) system for detecting breast cancer

Acta Radiologica ◽

10.3109/02841851003709490 ◽

2010 ◽

Vol 51 (5) ◽

pp. 482-490 ◽

Cited By ~ 7

Author(s):

Seung Ja Kim ◽

Woo Kyung Moon ◽

Soo-Yeon Kim ◽

Jung Min Chang ◽

Sun Mi Kim ◽

...

Keyword(s):

Breast Cancer ◽

False Positive ◽

Ductal Carcinoma ◽

Breast Cancers ◽

Computer Aided Detection ◽

Full Field ◽

Cad Systems ◽

Cad System ◽

Computer Aided ◽

Age Range

Background: The performance of the computer-aided detection (CAD) system can be determined by the sensitivity and false-positive marks rate, therefore these factors should be improved by upgrading the software version of the CAD system. Purpose: To compare retrospectively the performances of two software versions of a commercially available CAD system when applied to full-field digital mammograms for the detection of breast cancers in a screening group. Material and Methods: Versions 3.1 and 8.3 of a CAD software system (ImageChecker, R2 Technology) were applied to the full-field digital mammograms of 130 women (age range 36–80, mean age 53 years) with 130 breast cancers detected by screening. Results: The overall sensitivities of the version 3.1 and 8.3 CAD systems were 92.3% (120 of 130) and 96.2% (125 of 130) ( P=0.025), respectively, and sensitivities for masses were 78.3% (36 of 46) and 89.1% (41 of 46) ( P=0.024) and for microcalcifications 100% (84 of 84) and 100% (84 of 84), respectively. Version 8.3 correctly marked five lesions of invasive ductal carcinoma that were missed by version 3.1. Average numbers of false-positive marks per image were 0.38 (0.15 for calcifications, 0.23 for masses) for version 3.1 and 0.46 (0.13 for calcifications, 0.33 for masses) for version 8.3 ( P=0.1420). Conclusion: The newer version 8.3 of the CAD system showed better overall sensitivity for the detection of breast cancer than version 3.1 due to its improved sensitivity for masses when applied to full-field digital mammograms.

Download Full-text