Automatic Detection and Classification of Rib Fractures on Thoracic CT Using Convolutional Neural Network: Accuracy and Feasibility

Zhou Qing-Qing,Wang Jiashuo,Tang Wen,Hu Zhang-Chun,Xia Zi-Yi,Xue-Song Li,Zhang Rongguo,Yin Xindao,Zhang Bing,Zhang Hong 대한영상의학회 2020 Korean Journal of Radiology Vol.21 No.7

Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. Materials and Methods: This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. Results: A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. Conclusion: Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists’ workload.

Multiple Effects of a Novel Epothilone Analog on Cellular Processes and Signaling Pathways Regulated by Rac1 GTPase in the Human Breast Cancer Cells

Zhang, Hong,An, Fan,Tang, Li,Qiu, Rongguo The Korean Society of Pharmacology 2014 The Korean Journal of Physiology & Pharmacology Vol.18 No.2

The epothilones are a class of microtubule inhibitors that exhibit a strong antitumor activity. UTD2 is a novel epothilone analog generated by genetic manipulation of the polyketide biosynthetic gene cluster. This study investigated the effects of UTD2 on the actin cytoskeleton and its critical regulators, and the signaling pathways which are essential for cell motility, growth and survival in MCF-7 breast cancer cells. Results showed that UTD2 inhibited the cellular functions of actin cytoskeleton, such as wound-closure, migration and invasion, as well as adhesion. Our study further demonstrated that UTD2 suppressed Rac1 GTPase activation and reduced the activity of PAK1, which is a downstream effector of Rac1, while the activity of Cdc42 was not affected. Additionally, the phosphorylation of p38 and ERK were significantly inhibited, but the phosphorylation of JNK remained the same after UTD2 treatment. Moreover, UTD2 inhibited the activity and mRNA expression of MMP-2, which plays a key role in cell motility. UTD2 also reduced the phosphorylation of Akt, which is an important signaling kinase regulating the cell survival through Rac1. Furthermore, UTD2 interrupted the synergy between Rac1 and Raf in focus formation assays. Taken together, these results indicated that UTD2 exerted multiple effects on the actin cytoskeleton and signaling pathways associated with Rac1. This study provided novel insights into the molecular mechanism of the antineoplastic and antimetastatic activities of epothilones. Our findings also suggest that the signaling pathways regulated by Rac1 may be evaluated as biomarkers for the response to therapy in clinical trials of epothilones.

Age and petrogenesis of Mingshui-Shuangjingzi granites from the northern Beishan area, northwest China, and their implications for tectonic evolution

Wen Zhang,Victoria Pease,Qingpeng Meng,Rongguo Zheng,Tairan Wu 한국지질과학협의회 2017 Geosciences Journal Vol.21 No.5

The Mingshui and Shuangjingzi granitic plutons are exposed in the northern Beishan area, in the southern Central Asia Orogenic Belt. U-Pb zircon dating indicates that Mingshui secondary intrusive lithosfacies and Shuangjingzi quartz monzodiorite formed at 328 ± 2 Ma and 272 ± 2 Ma, respectively. The former is composed of grey white monzogranites and potassic altered flesh red monzogranites. Geochemistry indicates they are calc-alkaline I-type granites. Shuangjingzi granites are mainly composed of unfractionated calc-alkaline I-type quartz monzodiorite, granodiorite and monzogranite. The Mingshui grey white monzogranites with negative initial εNd (–2.0 to –1.7) and moderate initial 87Sr/86Sr values (0.706740 to 0.710092) were probably derived from mixing of the depleted mantle (juvenile) component and the Palaeoproterozoic–Archean crust (or sedimentary) component and represent volcanic arc granites. The Shuangjingzi quartz monzodiorites are most likely derived from mafic to intermediate igneous protolith and represent post-collisional granites. This work, combined with the regional geology, suggests the Palaeo-Asian Ocean closed between 328 Ma and 272 Ma in the northern Beishan area.

Prediction of the Development of Pulmonary Fibrosis Using Serial Thin-Section CT and Clinical Features in Patients Discharged after Treatment for COVID-19 Pneumonia

Yu Minhua,Liu Ying,Xu Dan,Zhang Rongguo,Lan Lan,Xu Haibo 대한영상의학회 2020 Korean Journal of Radiology Vol.21 No.6

Objective: To identify predictors of pulmonary fibrosis development by combining follow-up thin-section CT findings and clinical features in patients discharged after treatment for COVID-19. Materials and Methods: This retrospective study involved 32 confirmed COVID-19 patients who were divided into two groups according to the evidence of fibrosis on their latest follow-up CT imaging. Clinical data and CT imaging features of all the patients in different stages were collected and analyzed for comparison. Results: The latest follow-up CT imaging showed fibrosis in 14 patients (male, 12; female, 2) and no fibrosis in 18 patients (male, 10; female, 8). Compared with the non-fibrosis group, the fibrosis group was older (median age: 54.0 years vs. 37.0 years, p = 0.008), and the median levels of C-reactive protein (53.4 mg/L vs. 10.0 mg/L, p = 0.002) and interleukin-6 (79.7 pg/L vs. 11.2 pg/L, p = 0.04) were also higher. The fibrosis group had a longer-term of hospitalization (19.5 days vs. 10.0 days, p = 0.001), pulsed steroid therapy (11.0 days vs. 5.0 days, p < 0.001), and antiviral therapy (12.0 days vs. 6.5 days, p = 0.012). More patients on the worst-state CT scan had an irregular interface (59.4% vs. 34.4%, p = 0.045) and a parenchymal band (71.9% vs. 28.1%, p < 0.001). On initial CT imaging, the irregular interface (57.1%) and parenchymal band (50.0%) were more common in the fibrosis group. On the worst-state CT imaging, interstitial thickening (78.6%), air bronchogram (57.1%), irregular interface (85.7%), coarse reticular pattern (28.6%), parenchymal band (92.9%), and pleural effusion (42.9%) were more common in the fibrosis group. Conclusion: Fibrosis was more likely to develop in patients with severe clinical conditions, especially in patients with high inflammatory indicators. Interstitial thickening, irregular interface, coarse reticular pattern, and parenchymal band manifested in the process of the disease may be predictors of pulmonary fibrosis. Irregular interface and parenchymal band could predict the formation of pulmonary fibrosis early.