A Bi-level representation learning model for medical visual question answering.

Medical Visual Question Answering (VQA) targets at answering questions related to given medical images and it contains tremendous potential in healthcare services. However, researches on medical VQA are still facing challenges, particularly on how to learn a fine-grained multimodal semantic representation from relatively small volume of data resources for answer prediction. Moreover, the long-tailed distribution labels of medical VQA data frequently result in poor performance of models. To this end, we propose a novel bi-level representation learning model with two reasoning modules to learn bi-level representations for the medical VQA task. One is sentence-level reasoning to learn sentence-level semantic representations from multimodal input. The other is token-level reasoning that employs an attention mechanism to generate a multimodal contextual vector by fusing image features and word embeddings. The contextual vector is used to filter irrelevant semantic representations from sentence-level reasoning to generate a fine-grained multimodal representation. Furthermore, a label-distribution-smooth margin loss is proposed to minimize generalization error bound of long-tailed distribution datasets by modifying margin bound of different labels in training set. Based on standard VQA-Rad dataset and PathVQA dataset, the proposed model achieves 0.7605 and 0.5434 on accuracy, 0.7741 and 0.5288 on F1-score, respectively, outperforming a set of state-of-the-art baseline models.

Neuroprotective role of BNIP3 under oxidative stress through autophagy in neuroblastoma cells.

Reactive oxygen species (ROS) are produced due to oxidative stress which has wide range of affiliation with different diseases including cancer, heart failure, diabetes and neurodegenerative diseases like Alzheimer's disease, Parkinson's disease, ischemic and hemorrhagic diseases. This study shows the involvement of BNIP3 in the amplification of metabolic pathways related to cellular quality control and cellular self defence mechanism in the form of autophagy. We used conventional methods to induce autophagy by treating the cells with H2O2. MTT assay was performed to observe the cellular viability in stressed condition. MDC staining was carried out for detection of autophagosomes formation which confirmed the autophagy. Furthermore, expression of BNIP3 was validated by western blot analysis with LC3 antibody. From these results it is clear that BNIP3 plays a key role in defence mechanism by removing the misfolded proteins through autophagy. These results enhance the practical application of BNIP3 in neuroblastoma cells and are helpful in reducing the chances of neurodegenerative diseases. Although, the exact mode of action is still unknown but these findings unveil a molecular mechanism for the role of autophagy in cell death and provide insight into complex relationship between ROS and non-apoptotic programmed cell death.