Deep learning-based pulmonary tuberculosis automated detection on chest radiography: large-scale independent testing Wen Zhou, Guanxun Cheng, Ziqi Zhang, Litong Zhu, Stefan Jaeger, Fleming Y. M. Lure, Lin Guo

The brain has long been considered an immune-privileged organ due to the presence of the blood-brain barrier (BBB). However, recent discoveries have revealed the underestimated role of T cells in the brain through the meningeal lymphatic system. Age is the primary risk factor for Alzheimer’s disease (AD), resulting in marked age-dependent changes in T cells. Manipulating peripheral T cell immune response has been shown to impact AD, but the relationship between T cell aging and AD remains poorly understood. Given the limited success of targeting amyloid beta (Aβ) and the growing evidence of T cells’ involvement in non-lymphoid organ aging, a deeper understanding of the relationship between T cells and AD in the context of aging is crucial for advancing therapeutic progress. In this review, we comprehensively examine existing studies on T cells and AD and offer an integrated perspective on their interconnections in the context of aging. This understanding can inform the development of new interventions to prevent or treat AD.

OBJECTIVE: Diagnosis of tuberculosis (TB) in multi-slice spiral computed tomography (CT) images is a difficult task in many TB prevalent locations in which experienced radiologists are lacking. To address this difficulty, we develop an automated detection system based on artificial intelligence (AI) in this study to simplify the diagnostic process of active tuberculosis (ATB) and improve the diagnostic accuracy using CT images. DATA: A CT image dataset of 846 patients is retrospectively collected from a large teaching hospital. The gold standard for ATB patients is sputum smear, and the gold standard for normal and pneumonia patients is the CT report result. The dataset is divided into independent training and testing data subsets. The training data contains 337 ATB, 110 pneumonia, and 120 normal cases, while the testing data contains 139 ATB, 40 pneumonia, and 100 normal cases, respectively. METHODS: A U-Net deep learning algorithm was applied for automatic detection and segmentation of ATB lesions. Image processing methods are then applied to CT layers diagnosed as ATB lesions by U-Net, which can detect potentially misdiagnosed layers, and can turn 2D ATB lesions into 3D lesions based on consecutive U-Net annotations. Finally, independent test data is used to evaluate the performance of the developed AI tool. RESULTS: For an independent test, the AI tool yields an AUC value of 0.980. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value are 0.968, 0.964, 0.971, 0.971, and 0.964, respectively, which shows that the AI tool performs well for detection of ATB and differential diagnosis of non-ATB (i.e. pneumonia and normal cases). CONCLUSION: An AI tool for automatic detection of ATB in chest CT is successfully developed in this study. The AI tool can accurately detect ATB patients, and distinguish between ATB and non- ATB cases, which simplifies the diagnosis process and lays a solid foundation for the next step of AI in CT diagnosis of ATB in clinical application.

Background: Accurate and rapid diagnosis of coronavirus disease (COVID-19) is crucial for timely quarantine and treatment. Purpose: In this study, a deep learning algorithm-based AI model using ResUNet network was developed to evaluate the performance of radiologists with and without AI assistance in distinguishing COVID-19 infected pneumonia patients from other pulmonary infections on CT scans. Methods: For model development and validation, a total number of 694 cases with 111,066 CT slides were retrospectively collected as training data and independent test data in the study. Among them, 118 are confirmed COVID-19 infected pneumonia cases and 576 are other pulmonary infection cases (e.g. tuberculosis cases, common pneumonia cases and non-COVID-19 viral pneumonia cases). The cases were divided into training and testing datasets. The independent test was performed by evaluating and comparing the performance of three radiologists with different years of practice experience in distinguishing COVID-19 infected pneumonia cases with and without the AI assistance. Results: Our final model achieved an overall test accuracy of 0.914 with an area of the receiver operating characteristic (ROC) curve (AUC) of 0.903 in which the sensitivity and specificity are 0.918 and 0.909, respectively. The deep learning-based model then achieved a comparable performance by improving the radiologists’ performance in distinguish COVOD-19 from other pulmonary infections, yielding better average accuracy and sensitivity, from 0.941 to 0.951 and from 0.895 to 0.942, respectively, when compared to radiologists without using AI assistance. Conclusion: A deep learning algorithm-based AI model developed in this study successfully improved radiologists’ performance in distinguishing COVID-19 from other pulmonary infections using chest CT images.

Cancer is one of the major threats to human health and lives. However, effective cancer treatments remain a great challenge in clinical medicine. As a common approach for cancer treatment, chemotherapy has saved the life of millions of people; however, patients who have gone through chemotherapy often suffer from severe side effects owing to the inherent cytotoxicity of anti-cancer drugs. Stabilizing the blood concentration of an anti-cancer drug will reduce the occurrence or severity of side effects, and relies on using an appropriate drug delivery system (DDS) for achieving sustained or even on-demand drug delivery. However, this is still an unmet clinical challenge since the mainstay of anti-cancer drugs is small molecules, which tend to be diffused rapidly in the body, and conventional DDSs exhibit the burst release phenomenon. Here, we establish a class of DDSs based on biodegradable core–shell microspheres with encapsulated doxorubicin hydrochloride-loaded gold nanoparticles (DOX@Au@MSs), with the core–shell microspheres being made of poly(lactic-co-glycolic acid) in the current study. By harnessing the physical barrier of the biodegradable shell of core–shell microspheres, DOX@Au@MSs can provide a sustained release of the anti-cancer drug in the test duration (which is 21 days in the current study). Thanks to the photothermal properties of the encapsulated gold nanoparticle carriers, the core–shell biodegradable microspheres can be ruptured through remotely controlled near-infrared (NIR) light, thereby achieving an NIR-controlled triggered release of the anti-cancer drug. Furthermore, the route of the DOX-Au@MS-enabled controlled release of the anti-cancer drug can provide durable cancer cell ablation for the long period of 72 h.

In order to investigate the effectiveness and accuracy of magnetic resonance imaging (MRI) in the diagnosis of benign and malignant thoracic tumors, the research retrospectively selected 80 patients with thoracic tumors admitted from May 2019 to May 2020 as the study subject and all patients were underwent MRI detection. Using pathological diagnostic results as the gold standard, the research analyzed the detection of benign and malignant thoracic tumors by MRI, as well as the diagnostic sensitivity and specificity. After pathological diagnosis, there were 35 malignant tumors and 45 benign tumors. 41 cases of malignant tumors and 39 cases of benign tumors were diagnosed by MRI, with a diagnostic sensitivity of 80.00%, a diagnostic specificity of 71.11%, and a diagnostic compliance rate of 75.00%. In the MRI diagnosis of tumors in different parts of the chest, the diagnostic sensitivity for lung tumors, mediastinal tumors, chest wall tumors, and esophageal tumors was 83.33%, 71.43%, 83.33%, 75.00%, and 87.50%, respectively, and the specificity was 66.67%, 77.78%, 57.14%, 50.00%, and 91.67% according to and breast tumors, respectively. And the accuracy was 73.33%, 75.00%, 69.23, 62.50%, and 90.00%, respectively, with the highest diagnostic sensitivity, specificity, and accuracy for breast tumors. MRI has a good effect on the diagnosis of benign and malignant thoracic tumors and has a high diagnostic value, which is helpful to identify the location, nature, source, and lesion scope of the tumor. It is safe and worthy of promotion.