A clinical consensus-compliant deep learning approach to quantitatively evaluate human in vitro fertilization early embryonic development with optical microscope images.

The selection of embryos is a key for the success of in vitro fertilization (IVF). However, automatic quality assessment on human IVF embryos with optical microscope images is still challenging. In this study, we developed a clinical consensus-compliant deep learning approach, named Esava (Embryo Segmentation and Viability Assessment), to quantitatively evaluate the development of IVF embryos using optical microscope images. In total 551 optical microscope images of human IVF embryos of day-2 to day-3 were collected, preprocessed, and annotated. Using the Faster R-CNN model as baseline, our Esava model was constructed, refined, trained, and validated for precise and robust blastomere detection. A novel algorithm Crowd-NMS was proposed and employed in Esava to enhance the object detection and to precisely quantify the embryonic cells and their size uniformity. Additionally, an innovative GrabCut-based unsupervised module was integrated for the segmentation of blastomeres and embryos. Independently tested on 94 embryo images for blastomere detection, Esava obtained the high rates of 0.9940, 0.9121, and 0.9531 for precision, recall, and mAP respectively, and gained significant advances compared with previous computational methods. Intraclass correlation coefficients indicated the consistency between Esava and three experienced embryologists. Another test on 51 extra images demonstrated that Esava surpassed other tools significantly, achieving the highest average precision 0.9025. Moreover, it also accurately identified the borders of blastomeres with mIoU over 0.88 on the independent testing dataset. Esava is compliant with the Istanbul clinical consensus and compatible to senior embryologists. Taken together, Esava improves the accuracy and efficiency of embryonic development assessment with optical microscope images.

Blocking IL-10 signalling at the time of immunization does not increase unwanted side effects in mice.

BACKGROUND: Cancer therapeutic vaccine induced cytotoxic T cell (CTL) responses are pivotal for the killing of tumour cells. Blocking interleukin 10 (IL-10) signalling at the time of immunization increases vaccine induced CTL responses and improves prevention of tumour growth in animal models compared to immunization without an IL-10 signalling blockade. Therefore, this immunization strategy may have potential to curtail cancer in a clinical setting. However, IL-10 deficiency leads to autoimmune disease in the gut. Blocking IL-10 at the time of immunization may result in unwanted side effects, especially immune-pathological diseases in the intestine. METHODS: We investigated whether blocking IL-10 at the time of immunization results in intestinal inflammation responses in a mouse TC-1 tumour model and in a NOD autoimmune disease prone mouse model. RESULTS: We now show that blocking IL-10 at the time of immunization increases IL-10 production by CD4+ T cells in the spleen and draining lymph nodes, and does not result in blood cell infiltration to the intestines leading to intestinal pathological changes. Moreover, immunization with papillomavirus like particles combined with simultaneously blocking IL-10 signalling does not increase the incidence of autoimmune disease in Non-obese diabetic (NOD) mice. CONCLUSIONS: Our results indicate that immunization with an IL-10 inhibitor may facilitate the generation of safe, effective therapeutic vaccines against chronic viral infection and cancer.

Blocking IL-10 signalling at the time of immunization renders the tumour more accessible to T cell infiltration in mice.

We recently reported that blockade of IL-10 signalling at the time of a human papillomavirus (HPV) long E7 peptide/LPS immunization leads to the regression of established HPV-16 immortalized tumours in mice similar to that induced by long E7 peptide/incomplete Freund's adjuvant (IFA)-based vaccination. In this paper, we demonstrated that blockade of IL-10 signalling at the time of long E7 peptide/LPS could elicit stronger T cells responses and render the tumour more accessible for immune cell infiltration than vaccination with long E7 peptide/IFA. Furthermore, priming with long E7 peptide/LPS and IL10 signalling blockade then boosting with long E7 peptide/IFA elicits stronger CD8+ T cell responses than long E7 peptide/IFA immunization. The results suggest that priming with long E7 peptide/LPS and IL10 signalling inhibitor, then boosting with long E7 peptide/IFA elicits may lead to better HPV infection related tumour regression in clinic.