Smart healthcare relies on artificial intelligence (AI) functions for learning and analysis of patient data. Since large and diverse datasets for training of Machine Learning (ML) models can rarely be found in individual medical centers, classical centralized AI requires moving privacy-sensitive data from medical institutions to data centers that process the fused information. Training on data centers thus requires higher communication resource/energy demands while violating privacy. This is considered today as a significant bottleneck in pursuing scientific collaboration across trans-national clinical medical research centers. Recently, federated learning (FL) has emerged as a distributed AI approach that enables the cooperative training of ML models, without the need of sharing patient data. This paper dives into the analysis of different FL methods and proposes a real-time distributed networking framework based on the Message Queuing Telemetry Transport (MQTT) protocol. In particular, we design a number of solutions for ML over networks, based on FL tools relying on a parameter server (PS) and fully decentralized paradigms driven by consensus methods. The proposed approach is validated in the context of brain tumor segmentation, using a modified version of the popular U-NET model with representative clinical datasets obtained from the daily clinical workflow. The FL process is implemented on multiple physically separated machines located in different countries and communicating over the Internet. The real-time test-bed is used to obtain measurements of training accuracy vs. latency trade-offs, and to highlight key operational conditions that affect the performance in real deployments.
Although it is well known that chromosomes are non-randomly organized during interphase, it is not completely clear whether higher-order chromatin structure is transmitted from mother to daughter cells. Therefore, we addressed the question of how chromatin is rearranged during interphase and whether heterochromatin pattern is transmitted after mitosis. We additionally tested the similarity of chromatin arrangement in sister interphase nuclei. We noticed a very active cell rotation during interphase, especially when histone hyperacetylation was induced or transcription was inhibited. This natural phenomenon can influence the analysis of nuclear arrangement. Using photoconversion of Dendra2-tagged core histone H4 we showed that the distribution of chromatin in daughter interphase nuclei differed from that in mother cells. Similarly, the nuclear distribution of heterochromatin protein 1β (HP1β) was not completely identical in mother and daughter cells. However, identity between mother and daughter cells was in many cases evidenced by nucleolar composition. Moreover, morphology of nucleoli, HP1β protein, Cajal bodies, chromosome territories, and gene transcripts were identical in sister cell nuclei. We conclude that the arrangement of interphase chromatin is not transmitted through mitosis, but the nuclear pattern is identical in naturally synchronized sister cells. It is also necessary to take into account the possibility that cell rotation and the degree of chromatin condensation during functionally specific cell cycle phases might influence our view of nuclear architecture.
In biomedical image analysis, object description and classification tasks are very common. Our work relates to the problem of classification of Human Epithelial (HEp-2) cells.Since the crucial part of each classification process is the feature extraction and selection, much attention should be concentrated to the development of proper image descriptors. In this article, we introduce a new efficient texture-based image descriptor for HEp-2 images. We compare proposed descriptor with LBP, Haralick features (GLCM statistics) and Tamura features using the public MIVIA HEp-2 Images Dataset. Our descriptor outperforms all previously mentioned approaches and the kNN classifier based solely on the proposed descriptor achieve the accuracy as high as 91.1%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.