Application of artificial intelligence-assisted image diagnosis software based on volume data reconstruction technique in medical imaging practice teaching.

BACKGROUND: In medical imaging courses, due to the complexity of anatomical relationships, limited number of practical course hours and instructors, how to improve the teaching quality of practical skills and self-directed learning ability has always been a challenge for higher medical education. Artificial intelligence-assisted diagnostic (AISD) software based on volume data reconstruction (VDR) technique is gradually entering radiology. It converts two-dimensional images into three-dimensional images, and AI can assist in image diagnosis. However, the application of artificial intelligence in medical education is still in its early stages. The purpose of this study is to explore the application value of AISD software based on VDR technique in medical imaging practical teaching, and to provide a basis for improving medical imaging practical teaching. METHODS: Totally 41 students majoring in clinical medicine in 2017 were enrolled as the experiment group. AISD software based on VDR was used in practical teaching of medical imaging to display 3D images and mark lesions with AISD. Then annotations were provided and diagnostic suggestions were given. Also 43 students majoring in clinical medicine from 2016 were chosen as the control group, who were taught with the conventional film and multimedia teaching methods. The exam results and evaluation scales were compared statistically between groups. RESULTS: The total skill scores of the test group were significantly higher compared with the control group (84.51 ± 3.81 vs. 80.67 ± 5.43). The scores of computed tomography (CT) diagnosis (49.93 ± 3.59 vs. 46.60 ± 4.89) and magnetic resonance (MR) diagnosis (17.41 ± 1.00 vs. 16.93 ± 1.14) of the experiment group were both significantly higher. The scores of academic self-efficacy (82.17 ± 4.67) and self-directed learning ability (235.56 ± 13.50) of the group were significantly higher compared with the control group (78.93 ± 6.29, 226.35 ± 13.90). CONCLUSIONS: Applying AISD software based on VDR to medical imaging practice teaching can enable students to timely obtain AI annotated lesion information and 3D images, which may help improve their image reading skills and enhance their academic self-efficacy and self-directed learning abilities.

Comparison of CT findings and histopathological characteristics of pulmonary cryptococcosis in immunocompetent and immunocompromised patients.

Pulmonary cryptococcosis (PC) is a common fungal infectious disease, and infection can occur in patients with any immune function. To better understand PC, we compared the CT findings and histopathological results in immunocompetent and immunocompromised patients. The clinical data of 68 patients with PC were collected retrospectively and divided into the immunocompetent group and immunocompromised group. The clinical characteristics, CT manifestations and histopathological characteristics of the two groups of patients were compared. Forty-two patients (61.8%) were immunocompetent, and 26 patients (38.2%) were immunocompromised. Compared with immunocompromised patients, 57.14% (24/42) of immunocompetent patients were asymptomatic (p = 0.002). Compared with immunocompetent patients, cough (14/26, 53.9%) and fever (13/26, 50.0%) were the main symptoms in immunocompromised patients (p = 0.044, p = 0.007). Nodular lesions (97.6%, 41/42) were the most common CT type in immunocompetent patients, and the CT characteristic was a single lesion (25/42, 59.5%); the main histopathological type was nodular fibrogranuloma (30/42, 71.4%), and the main histopathological characteristic was inflammatory granuloma (31/42, 73.81%) formed by macrophage phagocytosis of Cryptococcus. Consolidation (15/26, 57.7%) was more common in the CT type of immunocompromised patients. Multiple lesions (24/26, 92.31%), air bronchial signs (19/26, 73.081%) and cavities (9/26, 34.62%) were the main CT characteristics. The mucinous colloid type (19/26, 73.1%) was its main histopathological type, which was mainly characterized by a small amount of surrounding inflammatory cell infiltration (17/26, 65.4%). There were significant differences in the classification and characteristics of CT and pathology between the two groups (p < 0.05). Through the CT manifestations and histopathological characteristics of PC under different immune function states, it was found that immune function has a significant impact on the CT manifestations and histopathological characteristics of patients with PC.

Circ­TOP2A acts as a ceRNA for miR­346 and contributes to glioma progression via the modulation of sushi domain­containing 2.

Dysregulated circular RNAs (circRNAs) are involved in the carcinogenesis and progression of multiple human malignancies. Knowledge of circRNAs in glioma (GM) is limited and further study to uncover new therapeutic targets for GM is urgently required. The present study demonstrated that circ­TOP2A was elevated in GM tissue specimens and cells and that circ­TOP2A levels indicated an unfavorable clinical prognosis in GM. Functionally, circ­TOP2A knockdown reduced viability, migration and invasion and triggered apoptosis in LN229 cells. Ectopic expression of circ­TOP2A aggravated these malignant behaviors in U87MG cells. In terms of mechanism, RNA­seq was performed to discover the potential targets regulated by circ­TOP2A. Circ­TOP2A acted as a competing endogenous RNA to upregulate sushi domain­containing 2 (SUSD2) expression by sponging microRNA (miR) 346. Rescue assays revealed that the oncogenic function of circ­TOP2A was partially dependent on its regulation of the miR­346/SUSD2 axis. In conclusion, the present study identified that circ­TOP2A promoted GM proliferation and aggressiveness via miR­346/SUSD2 signaling, which is a potential prognostic biomarker and therapeutic target for GM.