Objectives To evaluate the efficacy of interferon (IFN) maintenance therapy in patients with small cell lung cancer (SCLC). Methods We searched MEDLINE (1966-Jan.2006), EMbase (1984-Jan.2006), The Cochrane Library(Issue 1, 2006)and the Chinese Biomedical Database (1980-Jan.2006). We checked the references in the reports of related studies and handsearched the education books of ASCO and ESMO meetings. The quality of the included trials was evaluated. Data were extracted by two reviewers independently into a specially designed extraction form. The Cochrane Collaboration’s RevMan 4.2.7 software was used for data analysis. Results Five randomized controlled trials involving 587 patients were included. The pooled result of the 5 studies showed that IFN plus chemotherapy induction treatment did not have a significant effect on 1-year (RR 1.19, 95%CI 0.88-1.6) or 2-year survival rate (RR 1.44, 95% CI 0.99-2.10). However, IFN maintenance therapy significantly increased 2-year (RR 2.08, 95%CI 1.16-3.72) and 1-year survival (RR 2.99, 95%CI 1.13-7.93). Conclusion IFN maintenance therapy may increase 2-year and 1-year survival rates after patients have achieved complete or partial response to chemotherapy. Further randomized, double-blind multi-center trials are needed to investigate this further.
Objectives To evaluate the clinical effectiveness and safety of combined induction therapy of interferon (IFN) with chemotherapy for survival of the patients with advanced non-small cell lung cancer (NSCLC) by meta-analysis. Methods All clinical trials of addition of IFN plus chemotherapy versus chemotherapy alone for induction therapy to advanced NSCLC patients in MEDLINE (1966-2006), EMBASE (1984-2006.1) and The Cochrane Library (Issue 1,2006) were identified. The references of related studies and Education Books of ASCO and ESMO meeting were handsearched. The quality of included trials was evaluated. Data were extracted by two reviewers independently with a designed extraction form. RevMan 4.2.7 software was used for data analysis. Results Five randomized controlled trials involving 360 patients were included. The pooled result of 3 studies showed that IFN plus chemotherapy induction treatment did not improve 1-year survival rate with RR 0.76, 95%CI 0.46 to 1.26. The pooled result of 5 studies showed that IFN plus chemotherapy induction treatment did not improve response rate with RR 1.40, (0.83 2.34). The pooled result showed that IFN plus chemotherapy induction treatment might significantly increase leukopenia and thrombocytopenia with RR 2.61,95%CI1.70 to 3.99) and RR 4.78,95%CI 1.87 to 12.19 respectively . Conclusion Insufficient data exists to state whether IFN plus chemotherapy induction treatment can improve 1-year survival rate and response rate. IFN plus chemotherapy may increase occurrence of leucopenia and thrombocytopenia. Further studies are warranted.
This article aims to combine deep learning with image analysis technology and propose an effective classification method for distal radius fracture types. Firstly, an extended U-Net three-layer cascaded segmentation network was used to accurately segment the most important joint surface and non joint surface areas for identifying fractures. Then, the images of the joint surface area and non joint surface area separately were classified and trained to distinguish fractures. Finally, based on the classification results of the two images, the normal or ABC fracture classification results could be comprehensively determined. The accuracy rates of normal, A-type, B-type, and C-type fracture on the test set were 0.99, 0.92, 0.91, and 0.82, respectively. For orthopedic medical experts, the average recognition accuracy rates were 0.98, 0.90, 0.87, and 0.81, respectively. The proposed automatic recognition method is generally better than experts, and can be used for preliminary auxiliary diagnosis of distal radius fractures in scenarios without expert participation.
Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion using generative adversarial network (GAN) and convolutional neural network (CNN) under image enhancement. The generator aimed at high-frequency feature images and used double discriminators to target the fusion images after inverse transform; Then high-frequency feature images were fused by trained GAN model, and low-frequency feature images were fused by CNN pre-training model based on transfer learning. Experimental results showed that, compared with the current advanced fusion algorithm, the proposed method had more abundant texture details and clearer contour edge information in subjective representation. In the evaluation of objective indicators, QAB/F, information entropy (IE), spatial frequency (SF), structural similarity (SSIM), mutual information (MI) and visual information fidelity for fusion (VIFF) were 2.0%, 6.3%, 7.0%, 5.5%, 9.0% and 3.3% higher than the best test results, respectively. The fused image can be effectively applied to medical diagnosis to further improve the diagnostic efficiency.