Radiation Dose Reduction in Digital Mammography by Deep-Learning Algorithm Image Reconstruction: A Preliminary Study

Purpose@#To develop a denoising convolutional neural network-based image processing technique and investigate its efficacy in diagnosing breast cancer using low-dose mammography imaging. @*Materials and Methods@#A total of 6 breast radiologists were included in this prospective study. All radiologists independently evaluated low-dose images for lesion detection and rated them for diagnostic quality using a qualitative scale. After application of the denoising network, the same radiologists evaluated lesion detectability and image quality. For clinical application, a consensus on lesion type and localization on preoperative mammographic examinations of breast cancer patients was reached after discussion. Thereafter, coded low-dose, reconstructed full-dose, and full-dose images were presented and assessed in a random order. @*Results@#Lesions on 40% reconstructed full-dose images were better perceived when compared with low-dose images of mastectomy specimens as a reference. In clinical application, as compared to 40% reconstructed images, higher values were given on full-dose images for resolution (p < 0.001); diagnostic quality for calcifications (p < 0.001); and for masses, asymmetry, or architectural distortion (p = 0.037). The 40% reconstructed images showed comparable values to 100% full-dose images for overall quality (p = 0.547), lesion visibility (p = 0.120), and contrast (p = 0.083), without significant differences. @*Conclusion@#Effective denoising and image reconstruction processing techniques can enable breast cancer diagnosis with substantial radiation dose reduction.

Correlation between MR Image-Based Radiomics Features and Risk Scores Associated with Gene Expression Profiles in Breast Cancer

Purpose@#To investigate the correlation between magnetic resonance (MR) image-based radiomics features and the genomic features of breast cancer by focusing on biomolecular intrinsic subtypes and gene expression profiles based on risk scores. @*Materials and Methods@#We used the publicly available datasets from the Cancer Genome Atlas and the Cancer Imaging Archive to extract the radiomics features of 122 breast cancers on MR images. Furthermore, PAM50 intrinsic subtypes were classified and their risk scores were determined from gene expression profiles. The relationship between radiomics features and biomolecular characteristics was analyzed. A penalized generalized regression analysis was performed to build prediction models. @*Results@#The PAM50 subtype demonstrated a statistically significant association with the maximum 2D diameter (p = 0.0189), degree of correlation (p = 0.0386), and inverse difference moment normalized (p = 0.0337). Among risk score systems, GGI and GENE70 shared 8 correlated radiomic features (p = 0.0008–0.0492) that were statistically significant. Although the maximum 2D diameter was most significantly correlated to both score systems (p = 0.0139, and p = 0.0008), the overall degree of correlation of the prediction models was weak with the highest correlation coefficient of GENE70 being 0.2171. @*Conclusion@#Maximum 2D diameter, degree of correlation, and inverse difference moment normalized demonstrated significant relationships with the PAM50 intrinsic subtypes along with gene expression profile-based risk scores such as GENE70, despite weak correlations.

Associations between gene expression profiles of invasive breast cancer and Breast Imaging Reporting and Data System MRI lexicon

PURPOSE: To evaluate whether the Breast Imaging Reporting and Data System (BI-RADS) MRI lexicon could reflect the genomic information of breast cancers and to suggest intuitive imaging features as biomarkers. METHODS: Matched breast MRI data from The Cancer Imaging Archive and gene expression profile from The Cancer Genome Atlas of 70 invasive breast cancers were analyzed. Magnetic resonance images were reviewed according to the BI-RADS MRI lexicon of mass morphology. The cancers were divided into 2 groups of gene clustering by gene set enrichment an alysis. Clinicopathologic and imaging characteristics were compared between the 2 groups. RESULTS: The luminal subtype was predominant in the group 1 gene set and the triple-negative subtype was predominant in the group 2 gene set (55 of 56, 98.2% vs. 9 of 14, 64.3%). Internal enhancement descriptors were different between the 2 groups; heterogeneity was most frequent in group 1 (27 of 56, 48.2%) and rim enhancement was dominant in group 2 (10 of 14, 71.4%). In group 1, the gene sets related to mammary gland development were overexpressed whereas the gene sets related to mitotic cell division were overexpressed in group 2. CONCLUSION: We identified intuitive imaging features of breast MRI associated with distinct gene expression profiles using the standard imaging variables of BI-RADS. The internal enhancement pattern on MRI might reflect specific gene expression profiles of breast cancers, which can be recognized by visual distinction.

Harmonic ultrasonography for the detection of microlithiasis in the gallbladder

PURPOSE: To validate the use of harmonic ultrasonography (US) in the detection of gallbladder microlithiasis. METHODS: From November 30, 2012, to January 18, 2014, fundamental US (FUS) and harmonic US with a high background noise (HUS-N) were performed for evaluation of gallbladder during the routine abdomen US. During the US, a dot-like stone (or stones) with Brownian motion was regarded as a positive finding of microlithiasis. Fifty-five patients with microlithiasis in the gallbladder detected on US were enrolled as the subjects of a retrospective review. With respect to the obtained images, two abdominal radiologists independently scored the conspicuity of gallbladder microlithiasis on FUS and HUS-N by using a 4-grade scale. The statistical analysis employed a kappa test and a Wilcoxon rank-sum test. RESULTS: For FUS, the conspicuity grades of gallbladder microlithiasis were G1 in 25 and 37, G2 in 21 and 9, G3 in 6 and 6, G4 in 3 and 3 patients, while HUS-N showed G1 in 0 and 0, G2 in 3 and 2, G3 in 12 and 15, and G4 in 40 and 38 patients, respectively, by each of the two radiologists. The kappa value was 0.633 for FUS between the two radiologists and 0.708 for HUS-N. HUS-N showed better conspicuity of gallbladder microlithiasis than FUS with significant P-values of less than 0.001 and 0.001 for the two radiologists, respectively. CONCLUSION: Compared with FUS, HUS-N enables better detection of microlithiasis in the gallbladder.

Korea's Contribution to Radiological Research Included in Science Citation Index Expanded, 1986-2010

OBJECTIVE: To evaluate scientific papers published by Korean radiologists in the Science Citation Index Expanded (SCIE) radiology journals, between 1986 and 2010. MATERIALS AND METHODS: The Institute for Scientific Information Web of Knowledge-Web of Science (SCIE) database was searched for all articles published by Korean radiologists, in SCIE radiology journals, between 1986 and 2010. We performed the analysis by typing "Korea" and "radiol" in the address section and selecting the subject area of "Radiology, Nuclear Medicine, and Medical Imaging" with the use of the general search function of the software. Analyzed parameters included the total number of publications, document types, journals, and institutions. In addition, we analyzed where Korea ranks, compared to other countries, in terms of the number of published articles. All these data were analyzed according to five time periods: 1986-1990, 1991-1995, 1996-2000, 2001-2005, and 2006-2010. RESULTS: Overall, 4974 papers were published by Korean radiologists, in 99 different SCIE journals, between 1986 and 2010, of which 4237 (85.2%) were article-type papers. Of the total 115395 articles, worldwide, published in radiology journals, Korea's share was 3.7%, with an upward trend over time (p < 0.005). The journal with the highest number of articles was the American Journal of Roentgenology (n = 565, 13.3%). The institution which produced the highest number of publications was Seoul National University (n = 932, 22.0%). CONCLUSION: The number of scientific articles published by Korean radiologists in the SCIE radiology journals has increased significantly between 1986 and 2010. Korea was ranked 4th among countries contributing to radiology research during the last 5 years.