Format

Send to

Choose Destination
Nihon Hoshasen Gijutsu Gakkai Zasshi. 2018;74(3):251-261. doi: 10.6009/jjrt.2018_JSRT_74.3.251.

[Development of a Computer-aided Diagnosis System to Distinguish between Benign and Malignant Mammary Tumors in Dynamic Magnetic Resonance Images: Automatic Detection of the Position with the Strongest Washout Effect in the Tumor].

[Article in Japanese]

Author information

1
Department of Radiological Technology, National Hospital Organization Kyushu Cancer Center.
2
Department of Diagnostic Radiology, National Hospital Organization Kyushu Cancer Center.
3
Department of Breast Surgery, National Hospital Organization Kyushu Cancer Center.
4
Department of Diagnostic Pathology, National Hospital Organization Kyushu Cancer Center.

Abstract

We propose a computer-aided diagnostic (CAD) system that uses time-intensity curves to distinguish between benign and malignant mammary tumors. Many malignant tumors show a washout pattern in time-intensity curves. Therefore, we designed a program that automatically detects the position with the strongest washout effect using the technique, such as the subtraction technique, which extracts only the washout area in the tumor, and by scanning data in 2×2 pixel region of interest (ROI). Operation of this independently developed program was verified using a phantom system that simulated tumors. In three cases of malignant tumors, the washout pattern detection rate in images with manually set ROI was ≤6%, whereas the detection rate with our novel method was 100%. In one case of a benign tumor, when the same method was used, we checked that there was no washout effect and detected the persistent pattern. Thus, the distinction between benign and malignant tumors using our method was completely consistent with the pathological diagnoses made. Our novel method is therefore effective for differentiating between benign and malignant mammary tumors in dynamic magnetic resonance images.

KEYWORDS:

breast cancer; computer-aided diagnosis (CAD); mammary tumor; region of interest (ROI); time-intensity curve (TIC)

PMID:
29563394
DOI:
10.6009/jjrt.2018_JSRT_74.3.251
Free full text

Supplemental Content

Full text links

Icon for J-STAGE, Japan Science and Technology Information Aggregator, Electronic
Loading ...
Support Center