KEYWORDS: Breast, Tissues, Image segmentation, Data modeling, Magnetic resonance imaging, Image registration, Medical imaging, Cancer, Breast cancer, Artificial intelligence
Breast Magnetic Resonance Imaging (MRI) is recognized as the most sensitive imaging method for the early detection of breast cancer in women who carry a lifetime risk for breast cancer higher than or equal to 20%. Given the aggressive biology of cancers in this population, early detection is crucial for a favorable prognosis. This study aimed to use artificial intelligence for the detection of lesions at the earliest stage in high-risk women. A Generative Adversarial Network (GAN) detected lesions in breast MR data by quantifying anomaly as divergence from healthy breast tissue appearance. First, follow-up images of patients were aligned and the breast was segmented automatically. Then, the GAN created a model of healthy variability of appearance change during follow-up in 64x64-sized image patches sampled only at healthy tissue locations in follow-up image sequences. During the assessment of new data, each image position was compared with the model yielding an anomaly score. On a image patch level, we evaluated if this anomaly score identifies confirmed lesions, as well as lesionfree regions, where lesions appear during later follow-up studies. In the first experiment of lesion detection, a mean sensitivity of 99.5% and a mean specificity of 84% was achieved. When applying the model to studies denoted as lesion-free, subsequently occurring lesions were predicted with a mean sensitivity of 92.7% and a mean specificity of 78.8%.
The purpose of this study was to compare the radiologist`s performance in detecting small low-contrast objects with hardcopy and softcopy reading of digital mammograms. 12 images of a contrast-detail (CD) phantom without and with 25.4 mm, 50.8 mm, and 76.2 mm additional polymethylmetacrylate (PMMA) attenuation were acquired with a caesium iodid/amorphous silicon flat panel detector under standard exposure conditions. The phantom images were read by three independent observers, by conducting a four-alternative forced-choice experiment. Reading of the hardcopy was done on a mammography viewbox under standardized reading conditions. For soft copy reading, a dedicated workstation with two 2K monitors was used. CD-curves and image quality figure (IQF) values were calculated from the correct detection rates of randomly located gold disks in the phantom. The figures were compared for both reading conditions and for different PMMA layers. For all types of exposures, soft copy reading resulted in significantly better contrast-detail characteristics and IQF values, as compared to hard copy reading of laser printouts. (p< 0.01). The authors conclude that the threshold contrast characteristics of digital mammograms displayed on high-resolution monitors are sufficient to make soft copy reading of digital mammograms feasible.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.