Several computer aided diagnosis (CAD) systems have been developed for mammography. They are widely used in certain countries such as the U.S. where mammography studies are conducted more frequently; however, they are not yet globally employed for clinical use due to their inconsistent performance, which can be attributed to their reliance on hand-crafted features. It is difficult to use hand-crafted features for mammogram images that vary due to factors such as the breast density of patients and differences in imaging devices. To address these problems, several studies have leveraged a deep convolutional neural network that does not require hand-crafted features. Among the recent object detectors, RetinaNet is particularly promising as it is a simpler one-stage object detector that is fast and efficient while achieving state-of-the-art performance. RetinaNet has been proven to perform conventional object detection tasks but has not been tested on detecting masses in mammograms. Thus, we propose a mass detection model based on RetinaNet. To validate its performance in diverse use cases, we construct several experimental setups using the public dataset INbreast and the in-house dataset GURO. In addition to training and testing on the same dataset (i.e., training and testing on INbreast), we evaluate our mass detection model in setups using additional training data (i.e., training on INbreast + GURO and testing on INbreast). We also evaluate our model in setups using pre-trained weights (i.e., using weights pre-trained on GURO, training and testing on INbreast). In all the experiments, our mass detection model achieves comparable or better performance than more complex state-of-the-art models including the two-stage object detector. Also, the results show that using the weights pre-trained on datasets achieves similar performance as directly using datasets in the training phase. Therefore, we make our mass detection model’s weights pre-trained on both GURO and INbreast publicly available. We expect that researchers who train RetinaNet on their in-house dataset for the mass detection task can use our pre-trained weights to leverage the features extracted from the datasets.

Background: Artificial intelligence (AI) algorithms for the independent assessment of screening mammograms have not been well established in a large screening cohort of Asian women. We compared the performance of screening digital mammography considering breast density, between radiologists and AI standalone detection among Korean women. Methods: We retrospectively included 89,855 Korean women who underwent their initial screening digital mammography from 2009 to 2020. Breast cancer within 12 months of the screening mammography was the reference standard, according to the National Cancer Registry. Lunit software was used to determine the probability of malignancy scores, with a cutoff of 10% for breast cancer detection. The AI’s performance was compared with that of the final Breast Imaging Reporting and Data System category, as recorded by breast radiologists. Breast density was classified into four categories (A–D) based on the radiologist and AI-based assessments. The performance metrics (cancer detection rate [CDR], sensitivity, specificity, positive predictive value [PPV], recall rate, and area under the receiver operating characteristic curve [AUC]) were compared across breast density categories. Results: Mean participant age was 43.5 ± 8.7 years; 143 breast cancer cases were identified within 12 months. The CDRs (1.1/1000 examination) and sensitivity values showed no significant differences between radiologist and AI-based results (69.9% [95% confidence interval [CI], 61.7–77.3] vs. 67.1% [95% CI, 58.8–74.8]). However, the AI algorithm showed better specificity (93.0% [95% CI, 92.9–93.2] vs. 77.6% [95% CI, 61.7–77.9]), PPV (1.5% [95% CI, 1.2–1.9] vs. 0.5% [95% CI, 0.4–0.6]), recall rate (7.1% [95% CI, 6.9–7.2] vs. 22.5% [95% CI, 22.2–22.7]), and AUC values (0.8 [95% CI, 0.76–0.84] vs. 0.74 [95% CI, 0.7–0.78]) (all P < 0.05). Radiologist and AI-based results showed the best performance in the non-dense category; the CDR and sensitivity were higher for radiologists in the heterogeneously dense category (P = 0.059). However, the specificity, PPV, and recall rate consistently favored AI-based results across all categories, including the extremely dense category. Conclusions: AI-based software showed slightly lower sensitivity, although the difference was not statistically significant. However, it outperformed radiologists in recall rate, specificity, PPV, and AUC, with disparities most prominent in extremely dense breast tissue.

Pulmonary tuberculosis (PTB) continues to be one of the significant public health threats with significant morbidity and mortality. The present study was aimed to assess the clinical characteristics and chest computed tomography (CT) findings of smear-positive and smear-negative PTB in hospitalized adult patients. Hospitalized adult patients diagnosed with PTB by positive Mycobacterium tuberculosis growth on acid-fast bacilli culture from bronchial aspiration or sputum from 2015 to 2017 were reviewed. Only the patients who had chest CT within 14 days of the diagnosis of PTB were included. Medical records and CT images were analyzed. A total of 189 patients was enrolled. The median age was 62 years, and there were 118 males (62.4%). More than half of the patients had underlying chronic medical conditions (55.5%). The most common CT finding was nodular lesions (96.8%). The patients were categorized in 2 groups of smear-positive (n = 94, 49.7%) and smear-negative (n = 95, 50.3%). Between 2 groups, there was no difference in underlying medical conditions. However, there were more lesions of cavity, consolidation, bronchiectasis, upper lobe involvement, multiple lobe involvement, and lymphadenopathy in the smear-positive group. A predictive model for smear-positive tuberculosis was created based on the comparison analysis that had an area of 0.724 under the receiver operating characteristic curve. In a multivariate logistic regression analysis, CT findings of consolidation (odds ratio [OR] 2.521, 95% confidence interval [CI] 1.175–5.408, P = .02), lymphadenopathy (OR 1.947, 95% CI 1.025–3.696, P = .04), and multi-lobe involvement (OR 2.795, 95% CI 1.084–7.205, P = .03) were associated with smear-positive PTB. PTB patients who have chest CT findings of cavity, consolidation, bronchiectasis, upper lobe involvement, multiple lobe involvement, and lymphadenopathy may be at higher risk for smear-positive TB. A predictive model may be helpful for further assessment.

Endothelial cell senescence is involved in endothelial dysfunction and vascular diseases. However, the detailed mechanisms of endothelial senescence are not fully understood. Here, we demonstrated that deficiency of developmentally regulated GTP-binding protein 2 (DRG2) induces senescence and dysfunction of endothelial cells. DRG2 knockout (KO) mice displayed reduced cerebral blood flow in the brain and lung blood vessel density. We also determined, by Matrigel plug assay, aorta ring assay, and in vitro tubule formation of primary lung endothelial cells, that deficiency in DRG2 reduced the angiogenic capability of endothelial cells. Endothelial cells from DRG2 KO mice showed a senescence phenotype with decreased cell growth and enhanced levels of p21 and phosphorylated p53, γH2AX, senescence-associated β-galactosidase (SA-β-gal) activity, and senescence-associated secretory phenotype (SASP) cytokines. DRG2 deficiency in endothelial cells upregulated arginase 2 (Arg2) and generation of reactive oxygen species. Induction of SA-β-gal activity was prevented by the antioxidant N-acetyl cysteine in endothelial cells from DRG2 KO mice. In conclusion, our results suggest that DRG2 is a key regulator of endothelial senescence, and its downregulation is probably involved in vascular dysfunction and diseases.

Lee S, et al. Ann Surg Treat Res. 2018 Jun;94(6):337-341. https://doi.org/10.4174/astr.2018.94.6.337

Yoon SH, et al. J Korean Med Sci. 2020 Nov;35(46):e413. https://doi.org/10.3346/jkms.2020.35.e413