Colorectal image analysis for polyp diagnosis.

Colorectal polyp is an important early manifestation of colorectal cancer, which is significant for the prevention of colorectal cancer. Despite timely detection and manual intervention of colorectal polyps can reduce their chances of becoming cancerous, most existing methods ignore the uncertainties and location problems of polyps, causing a degradation in detection performance. To address these problems, in this paper, we propose a novel colorectal image analysis method for polyp diagnosis via PAM-Net. Specifically, a parallel attention module is designed to enhance the analysis of colorectal polyp images for improving the certainties of polyps. In addition, our method introduces the GWD loss to enhance the accuracy of polyp diagnosis from the perspective of polyp location. Extensive experimental results demonstrate the effectiveness of the proposed method compared with the SOTA baselines. This study enhances the performance of polyp detection accuracy and contributes to polyp detection in clinical medicine.

[Application of mycobacterial interspersed repetitive units in typing Mycobacterium tuberculosis in Shandong].

OBJECTIVE: To evaluate the application of mycobacterial interspersed repetitive units (MIRU) in typing Mycobacterium tuberculosis in Shandong. METHOD: 826 strains of M. tuberculosis from laboratories of 12 county tuberculosis dispensaries in Shandong were cultured and typed by MIRU genotyping in the KICID laboratory. RESULTS: The 826 strains were typed to 201 distinct MIRU patterns, and 123 isolates were unique, 703 strains were grouped into 1 of 78 different MIRU clusters, and the MIRU genotype of the largest cluster was 223325173533. Among the clustered strains, 18 patients had an epidemiological history of contact. The Hunter-Gaston discriminatory index was 0.90. The allelic diversity of the sample was calculated for each other of the MIRU loci, and showed that MIRU26 had 10 alleles and was highly discriminative, while other five MIRU loci (MIRU31, 10, 39, 40, 4) were moderately discriminative. The reproducibility of the MIRU method was 100%. It took about RMB yen50 to genotype one strain. CONCLUSIONS: MIRU genotyping is a reproducible, fast, simple, and relatively cheap method. But because the isolates of 223325173533 genotype are predominant (30.89% of the isolates) in Shandong Province, it needs a second method IS6110 RFLP or by adding other more discriminative variable-number tandem repeat (VNTR) loci to improve the discriminative power.