Breast Cancer Histopathology Image Classification Using an Ensemble of Deep Learning Models.

Breast cancer is one of the major public health issues and is considered a leading cause of cancer-related deaths among women worldwide. Its early diagnosis can effectively help in increasing the chances of survival rate. To this end, biopsy is usually followed as a gold standard approach in which tissues are collected for microscopic analysis. However, the histopathological analysis of breast cancer is non-trivial, labor-intensive, and may lead to a high degree of disagreement among pathologists. Therefore, an automatic diagnostic system could assist pathologists to improve the effectiveness of diagnostic processes. This paper presents an ensemble deep learning approach for the definite classification of non-carcinoma and carcinoma breast cancer histopathology images using our collected dataset. We trained four different models based on pre-trained VGG16 and VGG19 architectures. Initially, we followed 5-fold cross-validation operations on all the individual models, namely, fully-trained VGG16, fine-tuned VGG16, fully-trained VGG19, and fine-tuned VGG19 models. Then, we followed an ensemble strategy by taking the average of predicted probabilities and found that the ensemble of fine-tuned VGG16 and fine-tuned VGG19 performed competitive classification performance, especially on the carcinoma class. The ensemble of fine-tuned VGG16 and VGG19 models offered sensitivity of 97.73% for carcinoma class and overall accuracy of 95.29%. Also, it offered an F1 score of 95.29%. These experimental results demonstrated that our proposed deep learning approach is effective for the automatic classification of complex-natured histopathology images of breast cancer, more specifically for carcinoma images.

Mesenchymal stromal cells encapsulated in licensing hydrogels exert delocalized systemic protection against ulcerative colitis via subcutaneous xenotransplantation.

The ability of mesenchymal stromal cells (MSCs) to release a plethora of immunomodulatory factors makes them valuable candidates to overcome inflammatory bowel diseases (IBD). However, this cell therapy approach is still limited by major issues derived from nude MSC-administration, including a rapid loss of their immunomodulatory phenotype that impairs factor secretion, low persistence and impossibility to retrieve the cells in case of adverse effects. Here, we designed a licensing hydrogel system to address these limitations and thus, obtain a continuous delivery of bioactive factors. IFNγ-loaded heparin-coated beads were included in injectable in situ crosslinking alginate hydrogels, providing a 3D microenvironment that ensured continuous inflammatory licensing, cell persistence and implant retrievability. Licensing-hydrogel encapsulated human MSCs (hMSCs) were subcutaneously xenotransplanted in an acute mouse model of ulcerative colitis. Results showed that encapsulated hMSCs exerted a delocalized systemic protection, not presenting significant differences to healthy mice in the disease activity index, colon weight/length ratio and histological score. At day 7, cells were easily retrieved and ex vivo assays showed fully viable hMSCs that retained an immunomodulatory phenotype, as they continued secreting factors including PGE2 and Gal-9. Our data demonstrate the capacity of licensing hydrogel-encapsulated hMSCs to limit the in vivo progression of IBD.