Decrease in interpretation time for both novice and experienced readers using a concurrent computer-aided detection system for digital breast tomosynthesis
- 79 Downloads
To compare the diagnostic performance and interpretation time of digital breast tomosynthesis (DBT) for both novice and experienced readers with and without using a computer-aided detection (CAD) system for concurrent read.
CAD system was developed for concurrent read in DBT interpretation. In this observer performance study, we used an enriched sample of 100 DBT cases including 70 with and 30 without breast cancers. Image interpretation was performed by four radiologists with different experience levels (two experienced and two novice). Each reader completed two reading sessions (at a minimum 2-month interval), once with and once without CAD. Three different rating scales were used to record each reader’s interpretation. Reader performance with and without CAD was reported and compared for each radiologist. Reading time for each case was also recorded.
Average area under the receiver operating characteristic curve values for BI-RADS scale on using CAD were 0.778 and 0.776 without using CAD, demonstrating no statistically significant differences. Results were consistent when the probability of malignancy and percentage probability of malignancy scales were used. Reading times per case were 72.07 s and 62.03 s (SD, 37.54 s vs 34.38 s) without and with CAD, respectively. The average difference in reading time on using CAD was a statistically significant decrease of 10.04 ± 1.85 s, providing 14% decrease in time. The time-reducing effect was consistently observed in both novice and experienced readers.
DBT combined with CAD reduced interpretation time without diagnostic performance loss to novice and experienced readers.
• The use of a concurrent DBT-CAD system shortened interpretation time.
• The shortened interpretation time with DBT-CAD did not come at a cost to diagnostic performance to novice or experienced readers.
• The concurrent DBT-CAD system improved the efficiency of DBT interpretation.
KeywordsDigital breast tomosynthesis Computer-assisted diagnosis Breast cancer
Digital breast tomosynthesis
Full-field digital mammography
This study has received funding by the R&D Convergence Program (Grant Number: CAP-13-3-KERI) of the National Research Council of Science & Technology (NST) of the Republic of Korea.
Compliance with ethical standards
The scientific guarantor of this publication is Hak Hee Kim.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
Mingyu Han kindly provided statistical advice for this manuscript.
Written informed consent was waived by the Institutional Review Board.
Institutional Review Board approval was obtained.
• performed at one institution
- 2.Independent UK Panel on Breast Cancer Screening (2012) The benefits and harms of breast cancer screening: an independent review. Lancet 380:1778–1786Google Scholar
- 17.He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, p 770–778Google Scholar
- 18.Jeong JW, Chae SH, Cho YL et al (2017) A deep convolutional neural network based false positive reduction in mass detection algorithm on digital breast tomosynthesis images. Int J CARS 12(Suppl 1):S273Google Scholar
- 20.Chae EY, Kim HH, Cha JH, Shin HJ, Choi WJ (2016) Detection and characterization of breast lesions in a selective diagnostic population: diagnostic accuracy study for comparison between one-view digital breast tomosynthesis and two-view full-field digital mammography. Br J Radiol 89:20150743CrossRefGoogle Scholar
- 26.McCarthy AM, Kontos D, Synnestvedt M et al (2014) Screening outcomes following implementation of digital breast tomosynthesis in a general-population screening program. J Natl Cancer Inst 106(11). https://doi.org/10.1093/jnci/dju316