@article{PfeilFrohmeSchulze2018, author = {Pfeil, Juliane and Frohme, Marcus and Schulze, Katja}, title = {Mobile microscopy for the examination of blood samples}, series = {EMBnet.journal}, volume = {23}, journal = {EMBnet.journal}, issn = {2226-6089}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:526-opus4-10509}, pages = {e904}, year = {2018}, abstract = {The analysis of blood is one of the best possibilities to diagnose and control diseases and deficiency symptoms. Common blood tests that are performed in medical laboratories are time-consuming and work-intensive. In under-developed areas, there is often also a lack of specialised staff and facilities. The development of a mobile microscopic system that contains an automated image analysis and that can be used via a smartphone, could represent a valuable help to improve the diagnostic care, especially in those areas. it aims to enable a very fast, cheap, location- and knowledge-independent application for many use cases.}, language = {en} } @article{PfeilNechyporenkoFrohmeetal.2022, author = {Pfeil, Juliane and Nechyporenko, Alina and Frohme, Marcus and Hufert, Frank T. and Schulze, Katja}, title = {Examination of blood samples using deep learning and mobile microscopy}, series = {BMC Bioinformatics}, volume = {23}, journal = {BMC Bioinformatics}, publisher = {BioMed Central}, issn = {1471-2105}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:526-opus4-15802}, year = {2022}, abstract = {Microscopic examination of human blood samples is an excellent opportunity to assess general health status and diagnose diseases. Conventional blood tests are performed in medical laboratories by specialized professionals and are time and labor intensive. The development of a point-of-care system based on a mobile microscope and powerful algorithms would be beneficial for providing care directly at the patient's bedside. For this purpose human blood samples were visualized using a low-cost mobile microscope, an ocular camera and a smartphone. Training and optimisation of different deep learning methods for instance segmentation are used to detect and count the different blood cells. The accuracy of the results is assessed using quantitative and qualitative evaluation standards.}, language = {en} } @inproceedings{HollmannRegiererD'Eliaetal.2018, author = {Hollmann, Susanne and Regierer, Babette and D'Elia, Domenica and Frohme, Marcus and Gruden, Kristina and Pfeil, Juliane and Baebler, Spela and Sezerman, Ugur and Evelo, Chris T. and Erhart, Friederike and Huppertz, Berthold and Bongcam-Rudloff, Erik and Trefois, Christophe and Gruca, Aleksandra and Duca, Deborah and Colotti, Gianni and Merino-Martinez, Roxana and Ouzounis, Christos and Hunewald, Oliver and He, Feng and Kremer, Andreas}, title = {Standardisation in life-science research - Making the case for harmonization to improve communication and sharing of data amongst researchers}, editor = {Kalajdziski, Slobodan and Ackovska, Nevena}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:526-opus4-20118}, pages = {11}, year = {2018}, abstract = {Modern, high-throughput methods for the analysis of genetic information, gene and metabolic products and their interactions offer new opportunities to gain comprehensive information on life processes. The data and knowledge generated open diverse application possibilities with enormous innovation potential. To unlock that potential skills in generating but also properly annotating the data for further data integration and analysis are needed. The data need to be made computer readable and interoperable to allow integration with existing knowledge leading to actionable biological insights. To achieve this, we need common standards and standard operating procedures as well as workflows that allow the combination of data across standards. Currently, there is a lack of experts who understand the principles and possess knowledge of the principles and relevant tools. This is a major barrier hindering the implementation of FAIR (findable, accessible, interoperable and reusable) data principles and the actual reusability of data. This is mainly due to insufficient and unequal education of the scientists and other stakeholders involved in producing and handling big data in life science that is inherently varied and complex in nature, and large in volume. Due to the interdisciplinary nature of life science research, education within this field faces numerous hurdles including institutional barriers, lack of local availability of all required expertise, as well as lack of appropriate teaching material and appropriate adaptation of curricula.}, language = {en} } @article{PfeilSiptrothPospisiletal.2023, author = {Pfeil, Juliane and Siptroth, Julienne and Pospisil, Heike and Frohme, Marcus and Hufert, Frank T. and Moskalenko, Olga and Yateem, Murad and Nechyporenko, Alina}, title = {Classification of Microbiome Data from Type 2 Diabetes Mellitus Individuals with Deep Learning Image Recognition}, series = {Big Data and Cognitive Computing}, volume = {7}, journal = {Big Data and Cognitive Computing}, number = {1}, publisher = {MDPI}, issn = {2504-2289}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:526-opus4-17184}, year = {2023}, abstract = {Microbiomic analysis of human gut samples is a beneficial tool to examine the general well-being and various health conditions. The balance of the intestinal flora is important to prevent chronic gut infections and adiposity, as well as pathological alterations connected to various diseases. The evaluation of microbiome data based on next-generation sequencing (NGS) is complex and their interpretation is often challenging and can be ambiguous. Therefore, we developed an innovative approach for the examination and classification of microbiomic data into healthy and diseased by visualizing the data as a radial heatmap in order to apply deep learning (DL) image classification. The differentiation between 674 healthy and 272 type 2 diabetes mellitus (T2D) samples was chosen as a proof of concept. The residual network with 50 layers (ResNet-50) image classification model was trained and optimized, providing discrimination with 96\% accuracy. Samples from healthy persons were detected with a specificity of 97\% and those from T2D individuals with a sensitivity of 92\%. Image classification using DL of NGS microbiome data enables precise discrimination between healthy and diabetic individuals. In the future, this tool could enable classification of different diseases and imbalances of the gut microbiome and their causative genera.}, language = {en} }