Elsevier

Academic Radiology

Volume 20, Issue 4, April 2013, Pages 471-477
Academic Radiology

Original investigation
Improved Differential Diagnosis of Breast Masses on Ultrasonographic Images with a Computer-Aided Diagnosis Scheme for Determining Histological Classifications

https://doi.org/10.1016/j.acra.2012.11.007Get rights and content

Objectives

A computer-aided diagnosis (CAD) scheme for determining histological classifications of breast masses is expected to be useful for clinicians in making a differential diagnosis. The purpose of this study was to evaluate the usefulness of using the CAD scheme on ultrasonographic images.

Methods

The database consisted of 390 breast ultrasonographic images with masses. Three experienced clinicians independently provided subjective ratings on the likelihood of malignancy for each of the 390 masses. Fifty benign masses (25 cysts and 25 fibroadenomas) and 50 malignant masses (25 noninvasive ductal carcinomas and 25 invasive ductal carcinomas) were selected as unknown cases for an observer study based on a stratified randomization method with the ratings. The likelihood of the histological classification in each unknown case was evaluated by the CAD scheme with image features that clinicians commonly use for describing masses. In the observer study, seven observers provided their confidence levels regarding the malignancy of the unknown case before and after viewing the likelihood of the histological classification. The usefulness of the CAD scheme was evaluated with a multireader multicase receiver operating characteristic (ROC) analysis.

Results

The areas under the ROC curves (AUCs) for all observers were improved by use of the CAD scheme. The average AUC increased from 0.716 without to 0.864 with the CAD scheme (P = .006).

Conclusion

The presentation of the likelihood of the histological classification evaluated by the CAD scheme improved the clinicians' performance and therefore would be useful in making a differential diagnosis of masses on ultrasonographic images.

Section snippets

Materials and methods

Institutional review board approval was obtained for this study.

Results

For the 100 cases used in the observer study, the sensitivity, the specificity, and the AUC of the CAD scheme trained by use of the other cases were 90% (45/50), 92% (46/50), and 0.95, respectively.

Figure 2 shows the average ROC curves for all observers in distinguishing between benign and malignant masses without and with CAD. The average AUC for all observers increased from 0.716 without to 0.864 with CAD (P = .006). Table 1 shows the AUCs for each observer with and without CAD. All

Discussion

The observer study showed that the AUCs for all observers increased with the likelihood of histological classification evaluated by the CAD scheme. The gain in the average AUCs for the general group was higher than that for the expert group. The general clinicians probably tended to accept the computer output comparatively easily. This would imply that the performance of the CAD scheme is very important. Although the average AUCs for the expert group were also improved with the CAD scheme, the

Conclusion

The presentation of the likelihood of the histological classification evaluated by the CAD scheme showed beneficial effects for most cases, and it improved the clinicians' performance in the observer study. The CAD scheme is therefore considered to be useful for clinicians in making a differential diagnosis of masses on ultrasonographic images.

References (14)

  • P. Crystal et al.

    Using sonography to screen women with mammographically dense breasts

    Am J Roentegenol AJR

    (2003)
  • E. Tohno et al.

    Ultrasound screening of breast cancer

    Breast Cancer

    (2009)
  • W.A. Berg et al.

    Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer

    JAMA

    (2008)
  • X. Ying et al.

    A comparison of mammography and ultrasound in women with breast disease: a receiver operating characteristic analysis

    Breast J

    (2012)
  • E. Tohno et al.

    Occurrence of focal detection abnormalities in breast cancer screening by ultrasound

    J Jpn Assoc Breast Cancer Screen

    (2000)
  • K. Doi

    Computer-aided diagnosis in medical imaging: historical review, current status and future potential

    Comput Med Imaging Graph

    (2007)
  • Y. Jiang et al.

    Improving breast cancer diagnosis with computer-aided diagnosis

    Acad Radiol

    (1999)
There are more references available in the full text version of this article.

Cited by (0)

View full text
Copyright © 2013 AUR. Published by Elsevier Inc. All rights reserved.