Search

Summary: Background: Accurate identification of ovarian cancer (OC) is of paramount importance in clinical treatment success. Artificial intelligence (AI) is a potentially reliable assistant for the medical imaging recognition. We systematically review articles on the diagnostic performance of AI in OC from medical imaging for the first time. Methods: The Medline, Embase, IEEE, PubMed, Web of Science, and the Cochrane library databases were searched for related studies published until August 1, 2022. Inclusion criteria were studies that developed or used AI algorithms in the diagnosis of OC from medical images. The binary diagnostic accuracy data were extracted to derive the outcomes of interest: sensitivity (SE), specificity (SP), and Area Under the Curve (AUC). The study was registered with the PROSPERO, CRD42022324611. Findings: Thirty-four eligible studies were identified, of which twenty-eight studies were included in the meta-analysis with a pooled SE of 88% (95%CI: 85–90%), SP of 85% (82–88%), and AUC of 0.93 (0.91–0.95). Analysis for different algorithms revealed a pooled SE of 89% (85–92%) and SP of 88% (82–92%) for machine learning; and a pooled SE of 88% (84–91%) and SP of 84% (80–87%) for deep learning. Acceptable diagnostic performance was demonstrated in subgroup analyses stratified by imaging modalities (Ultrasound, Magnetic Resonance Imaging, or Computed Tomography), sample size (≤300 or >300), AI algorithms versus clinicians, year of publication (before or after 2020), geographical distribution (Asia or non Asia), and the different risk of bias levels (≥3 domain low risk or < 3 domain low risk). Interpretation: AI algorithms exhibited favorable performance for the diagnosis of OC through medical imaging. More rigorous reporting standards that address specific challenges of AI research could improve future studies. Funding: This work was supported by the Natural Science Foundation of China (No. 82073647 to Q-JW and No. 82103914 to T-TG), LiaoNing Revitalization Talents Program (No. XLYC1907102 to Q-JW), and 345 Talent Project of Shengjing Hospital of China Medical University (No. M0268 to Q-JW and No. M0952 to T-TG).

Protein synthesis in response to neuronal activity, known as activity-dependent translation, is critical for synaptic plasticity and memory formation. However, the signaling cascades that couple neuronal activity to the translational events remain elusive. In this study, we identified the role of calmodulin (CaM), a conserved Ca2+-binding protein, in ribosomal RNA (rRNA) biogenesis in neurons. We found the CaM-regulated rRNA synthesis is Ca2+-dependent and necessary for nascent protein synthesis and axon growth in hippocampal neurons. Mechanistically, CaM interacts with nucleolar DEAD (Asp–Glu–Ala–Asp) box RNA helicase (DDX21) in a Ca2+-dependent manner to regulate nascent rRNA transcription within nucleoli. We further found CaM alters the conformation of DDX21 to liberate the DDX21- sequestered RPA194, the catalytic subunit of RNA polymerase I, to facilitate transcription of ribosomal DNA. Using high-throughput screening, we identified the small molecules batefenterol and indacaterol that attenuate the CaM-DDX21 interaction and suppress nascent rRNA synthesis and axon growth in hippocampal neurons. These results unveiled the previously unrecognized role of CaM as a messenger to link the activity-induced Ca2+ influx to the nucleolar events essential for protein synthesis. We thus identified the ability of CaM to transmit information to the nucleoli of neurons in response to stimulation. [ABSTRACT FROM AUTHOR]

Background: Multiparameter, multimodality 18 F-FDG PET/MRI holds great potential for the diagnosis of cervical cancer based on the correlation between tumor glucose metabolism and imaging parameters.Purpose: To characterize the heterogeneity of tumor glucose metabolism by evaluating the correlation between 18 F-FDG uptake parameters and multiparametric functional MRI metrics in cervical carcinoma.Study Type: Retrospective.Population: Fifty-four patients with cervical carcinoma.Field Strength/sequence: Hybrid PET/MR (3T), multi-b DWI, and R2* mapping.Assessment: The maximum and mean standardized uptake values (SUVmax and SUVmean , respectively) from PET and functional MRI metrics (D, D*, f, and R2*) were obtained. Cervical carcinoma tissues also underwent HIF-1α, VEGF, and GLUT-1 immunohistochemical staining.Statistical Tests: Single-factor Spearman rank and Pearson correlation analysis and multiple linear regression (MLR) analysis were applied.Results: R2*, D, and f have different degrees of correlation (moderate, weak, moderately strong correlation, respectively) with SUVmax and SUVmean (r = 0.530 and 0.527, and P < 0.001 for R2*; r = -0.292 and -0.291, and P < 0.05 for D; r = 0.539 and 0.520, and P < 0.001 for f, respectively). Immunohistochemical staining showed that HIF-1α expression has a moderate degree of correlation with R2* (r = 0.491; P < 0.001); GLUT-1 expression was significantly correlated with SUVmax and SUVmean (r = 0.633 and 0.622; P < 0.001), and VEGF expression had a moderately strong correlation with f (r = 0.457; P = 0.001). If SUVmax is the dependent variable, MLR yields an R-squared value after adjustment (adjusted R-squared) = 0.358, and F = 10.833 (P < 0.001), and the fitting linear equation is Y (SUVmax ) = 9.184 + 0.161X1 (R2*)+50.343X2 (f)-4.780 (D). Otherwise, MLR yields the adjusted R-squared = 0.342, and F = 10.187 (P < 0.001), and the linear regression equation is Y (SUVmean ) = 5.925 + 0.102X1 (R2*)+28.029X2 (f)-2.907X3 (D).Data Conclusion: The functional MRI sequence parameters R2*, f, and D can provide information on the hypoxic condition, blood perfusion, and molecular diffusion of the tumor. 18 F-FDG PET/MR multi-imaging technique can be adopted to evaluate the heterogeneity of glucose metabolism in cervical carcinoma.Level Of Evidence: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;49:1704-1712. [ABSTRACT FROM AUTHOR]

Background: Multiparameter, multimodality 18 F-FDG PET/MRI holds great potential for the diagnosis of cervical cancer based on the correlation between tumor glucose metabolism and imaging parameters., Purpose: To characterize the heterogeneity of tumor glucose metabolism by evaluating the correlation between 18 F-FDG uptake parameters and multiparametric functional MRI metrics in cervical carcinoma., Study Type: Retrospective., Population: Fifty-four patients with cervical carcinoma., Field Strength/sequence: Hybrid PET/MR (3T), multi-b DWI, and R2* mapping., Assessment: The maximum and mean standardized uptake values (SUV max and SUV mean , respectively) from PET and functional MRI metrics (D, D*, f, and R2*) were obtained. Cervical carcinoma tissues also underwent HIF-1α, VEGF, and GLUT-1 immunohistochemical staining., Statistical Tests: Single-factor Spearman rank and Pearson correlation analysis and multiple linear regression (MLR) analysis were applied., Results: R2*, D, and f have different degrees of correlation (moderate, weak, moderately strong correlation, respectively) with SUV max and SUV mean (r = 0.530 and 0.527, and P < 0.001 for R2*; r = -0.292 and -0.291, and P < 0.05 for D; r = 0.539 and 0.520, and P < 0.001 for f, respectively). Immunohistochemical staining showed that HIF-1α expression has a moderate degree of correlation with R2* (r = 0.491; P < 0.001); GLUT-1 expression was significantly correlated with SUV max and SUV mean (r = 0.633 and 0.622; P < 0.001), and VEGF expression had a moderately strong correlation with f (r = 0.457; P = 0.001). If SUV max is the dependent variable, MLR yields an R-squared value after adjustment (adjusted R-squared) = 0.358, and F = 10.833 (P < 0.001), and the fitting linear equation is Y (SUV max ) = 9.184 + 0.161X1 (R2*)+50.343X2 (f)-4.780 (D). Otherwise, MLR yields the adjusted R-squared = 0.342, and F = 10.187 (P < 0.001), and the linear regression equation is Y (SUV mean ) = 5.925 + 0.102X1 (R2*)+28.029X2 (f)-2.907X3 (D)., Data Conclusion: The functional MRI sequence parameters R2*, f, and D can provide information on the hypoxic condition, blood perfusion, and molecular diffusion of the tumor. 18 F-FDG PET/MR multi-imaging technique can be adopted to evaluate the heterogeneity of glucose metabolism in cervical carcinoma., Level of Evidence: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;49:1704-1712., (© 2018 International Society for Magnetic Resonance in Medicine.)