No abstract

Purpose This study aimed to develop deep learning (DL) models based on multicentre biparametric magnetic resonance imaging (bpMRI) for the diagnosis of clinically significant prostate cancer (csPCa) and compare the performance of these models with that of the Prostate Imaging and Reporting and Data System (PI-RADS) assessment by expert radiologists based on multiparametric MRI (mpMRI). Methods We included 1861 consecutive male patients who underwent radical prostatectomy or biopsy at seven hospitals with mpMRI. These patients were divided into the training (1216 patients in three hospitals) and external validation cohorts (645 patients in four hospitals). PI-RADS assessment was performed by expert radiologists. We developed DL models for the classification between benign and malignant lesions (DL-BM) and that between csPCa and non-csPCa (DL-CS). An integrated model combining PI-RADS and the DL-CS model, abbreviated as PIDL-CS, was developed. The performances of the DL models and PIDL-CS were compared with that of PI-RADS. Results In each external validation cohort, the area under the receiver operating characteristic curve (AUC) values of the DL-BM and DL-CS models were not significantly different from that of PI-RADS (P > 0.05), whereas the AUC of PIDL-CS was superior to that of PI-RADS (P < 0.05), except for one external validation cohort (P > 0.05). The specificity of PIDL-CS for the detection of csPCa was much higher than that of PI-RADS (P < 0.05). Conclusion Our proposed DL models can be a potential non-invasive auxiliary tool for predicting csPCa. Furthermore, PIDL-CS greatly increased the specificity of csPCa detection compared with PI-RADS assessment by expert radiologists, greatly reducing unnecessary biopsies and helping radiologists achieve a precise diagnosis of csPCa.

Background Silk glands are used by silkworms to spin silk fibers for making their cocoons. These have recently been regarded as bioreactor hosts for the cost-effective production of other valuable exogenous proteins and have drawn wide attention. Results In this study, we established a transgenic silkworm strain which synthesizes the recombinant human lactoferrin (rhLF) in the silk gland and spins them into the cocoon by our previously constructed silk gland based bioreactor system. The yield of the rhLF with the highest expression level was estimated to be 12.07 mg/g cocoon shell weight produced by the transgenic silkworm strain 34. Utilizing a simple purification protocol, 9.24 mg of the rhLF with recovery of 76.55% and purity of 95.45% on average could be purified from 1 g of the cocoons. The purified rhLF was detected with a secondary structure similar with the commercially purchased human lactoferrin. Eight types of N-glycans which dominated by the GlcNAc (4) Man (3) (61.15%) and the GlcNAc (3) Man (3) (17.98%) were identified at the three typical N-glycosylation sites of the rhLF. Biological activities assays showed the significant evidence that the purified rhLF could relief the lipopolysaccharide (LPS)-induced cell inflammation in RAW264.7 cells and exhibit potent antibacterial bioactivities against the Escherichia coli ( E. coli ) and Bacillus subtilis. Conclusions These results show that the middle silk gland of silkworm can be an efficient bioreactor for the mass production of rhLF and the potential application in anti-inflammation and antibacterial. Electronic supplementary material The online version of this article (10.1186/s13036-019-0186-z) contains supplementary material, which is available to authorized users.