Search

Background: Chest X-ray imaging based abnormality localization, essential in diagnosing various diseases, faces significant clinical challenges due to complex interpretations and the growing workload of radiologists. While recent advances in deep learning offer promising solutions, there is still a critical issue of domain inconsistency in cross-domain transfer learning, which hampers the efficiency and accuracy of diagnostic processes. This study aims to address the domain inconsistency problem and improve autonomic abnormality localization performance of heterogeneous chest X-ray image analysis, particularly in detecting abnormalities, by developing a self-supervised learning strategy called "BarlwoTwins-CXR"., Methods: We utilized two publicly available datasets: the NIH Chest X-ray Dataset and the VinDr-CXR. The BarlowTwins-CXR approach was conducted in a two-stage training process. Initially, self-supervised pre-training was performed using an adjusted Barlow Twins algorithm on the NIH dataset with a Resnet50 backbone pre-trained on ImageNet. This was followed by supervised fine-tuning on the VinDr-CXR dataset using Faster R-CNN with Feature Pyramid Network (FPN). The study employed mean Average Precision (mAP) at an Intersection over Union (IoU) of 50% and Area Under the Curve (AUC) for performance evaluation., Results: Our experiments showed a significant improvement in model performance with BarlowTwins-CXR. The approach achieved a 3% increase in mAP50 accuracy compared to traditional ImageNet pre-trained models. In addition, the Ablation CAM method revealed enhanced precision in localizing chest abnormalities. The study involved 112,120 images from the NIH dataset and 18,000 images from the VinDr-CXR dataset, indicating robust training and testing samples., Conclusion: BarlowTwins-CXR significantly enhances the efficiency and accuracy of chest X-ray image-based abnormality localization, outperforming traditional transfer learning methods and effectively overcoming domain inconsistency in cross-domain scenarios. Our experiment results demonstrate the potential of using self-supervised learning to improve the generalizability of models in medical settings with limited amounts of heterogeneous data. This approach can be instrumental in aiding radiologists, particularly in high-workload environments, offering a promising direction for future AI-driven healthcare solutions., (© 2024. The Author(s).)

The incidence of gastric cancer is increasing year by year. Most gastric cancers are already in the advanced stage with poor prognosis when diagnosed, which means the current treatment is not satisfactory. Angiogenesis is an important link in the occurrence and development of tumors, and there are multiple anti-angiogenesis targeted therapies. To comprehensively evaluate the efficacy and safety of anti-angiogenic targeted drugs alone and in combination against gastric cancer, we systematically searched and sorted out relevant literature. In this review, we summarized the efficacy and safety of Ramucirumab, Bevacizumab, Apatinib, Fruquintinib, Sorafenib, Sunitinib, Pazopanib on gastric cancer when used alone or in combination based on prospective clinical trials reported in the literature, and sorted response biomarkers. We also summarized the challenges faced by anti-angiogenesis therapy for gastric cancer and available solutions. Finally, the characteristics of the current clinical research are summarized and suggestions and prospects are raised. This review will serve as a good reference for the clinical research of anti-angiogenic targeted drugs in the treatment of gastric cancer., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Xu, Luo, Wang, Li, Ma, Huang, Zhang, Yang, Li, Zheng, Fang and Yan.)