Cone-beam CT-guided PTNB is a highly accurate and safe technique with which to diagnose pulmonary lesions with reasonable radiation exposure.

Key Points Question Can a deep learning–based algorithm accurately discriminate abnormal chest radiograph results showing major thoracic diseases from normal chest radiograph results? Findings In this diagnostic study of 54 221 chest radiographs with normal findings and 35 613 with abnormal findings, the deep learning–based algorithm for discrimination of chest radiographs with pulmonary malignant neoplasms, active tuberculosis, pneumonia, or pneumothorax demonstrated excellent and consistent performance throughout 5 independent data sets. The algorithm outperformed physicians, including radiologists, and enhanced physician performance when used as a second reader. Meaning A deep learning–based algorithm may help improve diagnostic accuracy in reading chest radiographs and assist in prioritizing chest radiographs, thereby increasing workflow efficacy.

Formyl peptide receptor-like 1 (FPRL1) is an important classical chemoattractant receptor that is expressed in phagocytic cells in the peripheral blood and brain. Recently, various novel agonists have been identified from several origins, such as host-derived molecules. Activation of FPRL1 is closely related to inflammatory responses in the host defense mechanism and neurodegenerative disorders. In the present study we identified several novel peptides by screening hexapeptide libraries that inhibit the binding of one of FPRL1’s agonists (Trp-Lys-Tyr-Met-Val-d-Met-CONH2 (WKYMVm)) to its specific receptor, FPRL1, in RBL-2H3 cells. Among the novel peptides, Trp-Arg-Trp-Trp-Trp-Trp-CONH2 (WRWWWW (WRW4)) showed the most potent activity in terms of inhibiting WKYMVm binding to FPRL1. We also found that WRW4 inhibited the activation of FPRL1 by WKYMVm, resulting in the complete inhibition of the intracellular calcium increase, extracellular signal-regulated kinase activation, and chemotactic migration of cells toward WKYMVm. For the receptor specificity of WRW4 to the FPR family, we observed that WRW4 specifically inhibit the increase in intracellular calcium by the FPRL1 agonists MMK-1, amyloid β42 (Aβ42) peptide, and F peptide, but not by the FPR agonist, fMLF. To investigate the effect of WRW4 on endogenous FPRL1 ligand-induced cellular responses, we examined its effect on Aβ42 peptide in human neutrophils. Aβ42 peptide-induced superoxide generation and chemotactic migration of neutrophils were inhibited by WRW4, which also completely inhibited the internalization of Aβ42 peptide in human macrophages. WRW4 is the first specific FPRL1 antagonist and is expected to be useful in the study of FPRL1 signaling and in the development of drugs against FPRL1-related diseases.

Background Detection of active pulmonary tuberculosis on chest radiographs (CRs) is critical for the diagnosis and screening of tuberculosis. An automated system may help streamline the tuberculosis screening process and improve diagnostic performance. Methods We developed a deep learning–based automatic detection (DLAD) algorithm using 54c221 normal CRs and 6768 CRs with active pulmonary tuberculosis that were labeled and annotated by 13 board-certified radiologists. The performance of DLAD was validated using 6 external multicenter, multinational datasets. To compare the performances of DLAD with physicians, an observer performance test was conducted by 15 physicians including nonradiology physicians, board-certified radiologists, and thoracic radiologists. Image-wise classification and lesion-wise localization performances were measured using area under the receiver operating characteristic (ROC) curves and area under the alternative free-response ROC curves, respectively. Sensitivities and specificities of DLAD were calculated using 2 cutoffs (high sensitivity [98%] and high specificity [98%]) obtained through in-house validation. Results DLAD demonstrated classification performance of 0.977–1.000 and localization performance of 0.973–1.000. Sensitivities and specificities for classification were 94.3%–100% and 91.1%–100% using the high-sensitivity cutoff and 84.1%–99.0% and 99.1%–100% using the high-specificity cutoff. DLAD showed significantly higher performance in both classification (0.993 vs 0.746–0.971) and localization (0.993 vs 0.664–0.925) compared to all groups of physicians. Conclusions Our DLAD demonstrated excellent and consistent performance in the detection of active pulmonary tuberculosis on CR, outperforming physicians, including thoracic radiologists.

No abstract