Discrimination between malignant and benign mass-like lesions from breast dynamic contrast enhanced MRI: semi-automatic vs. manual analysis of the signal time-intensity curves

Yin, Jiandong; Yang, Jiawen; Jiang, Zejun

doi:10.7150/jca.23283



International Journal of Biological Sciences

International Journal of Medical Sciences

Theranostics

Journal of Genomics

Nanotheranostics

Global reach, higher impact

Full Text | PDF

J Cancer 2018; 9(5):834-840. doi:10.7150/jca.23283 This issue Cite

Research Paper

Discrimination between malignant and benign mass-like lesions from breast dynamic contrast enhanced MRI: semi-automatic vs. manual analysis of the signal time-intensity curves

Jiandong Yin^1✉, Jiawen Yang¹, Zejun Jiang²

1. Department of Radiology, Shengjing Hospital of China Medical University
2. Sino-Dutch Biomedical and Information Engineering School of Northeastern University

Citation:

Yin J, Yang J, Jiang Z. Discrimination between malignant and benign mass-like lesions from breast dynamic contrast enhanced MRI: semi-automatic vs. manual analysis of the signal time-intensity curves. J Cancer 2018; 9(5):834-840. doi:10.7150/jca.23283. https://www.jcancer.org/v09p0834.htm

Other styles

Abstract

Purpose: To investigate the performance of a new semi-automatic method for analyzing the signal time-intensity curve (TIC) obtained by breast dynamic contrast enhancement (DCE)-MRI.

Methods: In the conventional method, a circular region of interest was drawn manually onto the map reflecting the maximum slope of increase (MSI) to delineate the suspicious lesions. The mean TIC was determined subjectively as one of three different wash-out patterns. In the new method, the lesion area was identified semi-automatically. The mean TIC was categorized quantitatively. In addition to the MSI, other quantitative parameters were calculated, including the signal intensity slope (SI_slope), initial percentage of enhancement (E_initial), percentage of peak enhancement (E_peak), early signal enhancement ratio (ESER), and second enhancement percentage (SEP). The performances were compared with receiver operating characteristic (ROC) analysis and Wilcoxon's test.

Results: For TIC categorization results, the diagnostic accuracy rates were 61.54% with the traditional manual method and 76.92% with the new method. For the mean MSI values from the manual method, the accuracy was 63.41%. For the mean TIC derived using the semi-automatic method, the diagnostic accuracy were 82.05% for SI_slope, 67.31% for MSI, 61.53% for E_initial, 64.75% for E_peak, 64.74% for ESER, and 52.56% for SEP, respectively. For the lesion regions identified by the semi-automatic method, the diagnostic accuracy for above mentioned parameters were 80.13%, 69.87%, 61.54%, 63.47%, 64.74% and 55.13%, respectively.

Conclusion: With respect to the analysis of TIC from breast DCE-MRI, the results demonstrated that the new method increased the diagnostic accuracy, and should be considered as a supplementary tool for distinguishing benign and malignant lesions.

Keywords: manual method, semi-automatic method, breast lesion, quantitative parameter, time intensity curve

Citation styles

APA

Yin, J., Yang, J., Jiang, Z. (2018). Discrimination between malignant and benign mass-like lesions from breast dynamic contrast enhanced MRI: semi-automatic vs. manual analysis of the signal time-intensity curves. Journal of Cancer, 9(5), 834-840. https://doi.org/10.7150/jca.23283.

ACS

Yin, J.; Yang, J.; Jiang, Z. Discrimination between malignant and benign mass-like lesions from breast dynamic contrast enhanced MRI: semi-automatic vs. manual analysis of the signal time-intensity curves. J. Cancer 2018, 9 (5), 834-840. DOI: 10.7150/jca.23283.

NLM

CSE

Yin J, Yang J, Jiang Z. 2018. Discrimination between malignant and benign mass-like lesions from breast dynamic contrast enhanced MRI: semi-automatic vs. manual analysis of the signal time-intensity curves. J Cancer. 9(5):834-840.

This is an open access article distributed under the terms of the Creative Commons Attribution (CC BY-NC) license (https://creativecommons.org/licenses/by-nc/4.0/). See http://ivyspring.com/terms for full terms and conditions.