Tuberculosis (TB) remains a significant global health challenge, characterized by high incidence and mortality rates on a global scale. With the rapid advancement of computer-aided diagnosis (CAD) tools in recent years, CAD has assumed an increasingly crucial role in supporting TB diagnosis. Nonetheless, the development of CAD for TB diagnosis heavily relies on well-annotated computerized tomography (CT) datasets. Currently, the available annotations in TB CT datasets are still limited, which in turn restricts the development of CAD tools for TB diagnosis to some extent. To address this limitation, we introduce DeepPulmoTB, a CT multi-task learning dataset explicitly designed for TB diagnosis. To demonstrate the advantages of DeepPulmoTB, we propose a novel multi-task learning model, DeepPulmoTBNet (DPTBNet), for the joint segmentation and classification of lesion tissues in CT images. The architecture of DPTBNet comprises two subnets: SwinUnetR for the segmentation task, and a lightweight multi-scale network for the classification task. Furthermore, to enhance the model's capacity to capture TB lesion features, we introduce an improved iterative optimization algorithm that refines feature maps by integrating probability maps obtained in previous iterations. Extensive experiments validate the effectiveness of DPTBNet and the practicality of the DeepPulmoTB dataset.
The shortage of new antibiotics makes infections caused by gram-negative (G-) bacteria a significant clinical problem. The key enzymes involved in folate biosynthesis represent important targets for drug discovery, and new antifolates with novel mechanisms are urgently needed. By targeting to dihydrofolate reductase (DHFR), a series of 1,3-diamino-7H-pyrrol[3,2-f]quinazoline (PQZ) compounds were designed, and exhibited potent antibacterial activities in vitro, especially against multi-drug resistant G- strains. Multiple experiments indicated that PQZ compounds contain a different molecular mechanism against the typical DHFR inhibitor, trimethoprim (TMP), and the thymidylate synthase (TS) was identified as another potential but a relatively weak target. A significant synergism between the representative compound, OYYF-175, and sulfamethoxazole (SMZ) was observed with a strong cumulative and significantly bactericidal effect at extremely low concentrations (2 μg/mL for SMZ and 0.03 pg/mL for OYYF-175), which could be resulted from the simultaneous inhibition of dihydropteroate synthase (DHPS), DHFR and TS. PQZ compounds exhibited therapeutic effects in a mouse model of intraperitoneal infections caused by Escherichia coli (E. coli). The co-crystal structure of OYYF-175-DHFR was solved and the detailed interactions were provided. The inhibitors reported represent innovative chemical structures with novel molecular mechanism of action, which will benefit the generation of new, efficacious bactericidal compounds.