Related Experiment Videos
Computer-aided diagnosis in full digital mammography.
S Nawano1, K Murakami, N Moriyama
1Department of Radiology, National Cancer Center Hospital, East, Chiba, Japan.
Investigative Radiology
|April 10, 1999
Summary
Computer-aided diagnosis (CAD) using Fuji Computed Radiography demonstrates high detection rates for breast tumors and microcalcifications. Mammographic reading with CAD significantly improves breast cancer diagnostic accuracy.
Area of Science:
- Radiology
- Medical Imaging
- Oncology
Background:
- Early detection of breast cancer is crucial for effective treatment.
- Computer-aided diagnosis (CAD) systems aim to enhance the accuracy of mammographic interpretations.
- Fuji Computed Radiography is a digital mammography system used in breast cancer screening.
Purpose of the Study:
- To evaluate the detection rates of breast tumors and microcalcifications using CAD with Fuji Computed Radiography.
- To determine if CAD improves the diagnostic accuracy of mammographic readings for breast cancer.
Main Methods:
- Analysis of 4148 digital mammograms from Fuji Computed Radiography 9000, including 267 breast cancer cases.
- Software program used to extract detection rates for tumors and microcalcifications.
- Observer performance studies with five radiologists using receiver operating characteristic (ROC) analysis on 344 mammograms.
Main Results:
- Sensitivity for detecting breast tumors was 89.9% and for clustered microcalcifications was 92.8%.
- False-positive rates were 1.35 per image for tumors and 0.40 per image for microcalcifications.
- The average Az value in observer studies was higher with CAD, indicating significantly superior performance (P < 0.022).
Conclusions:
- CAD based on Fuji Computed Radiography provides effective detection of breast tumors and microcalcifications.
- Mammographic reading augmented with this CAD system shows potential for improved breast cancer diagnostic accuracy.