Die DPG-Frühjahrstagung in Dresden musste abgesagt werden! Lesen Sie mehr ...
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
BP: Fachverband Biologische Physik
BP 19: Poster VII
BP 19.5: Poster
Dienstag, 17. März 2020, 14:00–16:00, P2/3OG
AI Developer: a general tool for deep-learning image classification in life science and beyond — Martin Kräter1,2, Shada Abuhattum1,2, Despina Soteriou1, Jochen Guck1,2, and •Maik Herbig1,2 — 1Max Planck Institute for the Science of Light, Erlangen — 2Biotechnology Center of the TU Dresden, Dresden
The publication record on artificial intelligence (AI) -based image analysis has increased drastically over the last years. However, all application cases consist of individual solutions with high specificity for a particular use. Here, we present an easy-to-use, adaptable, open source software, called AIDeveloper (AID) to train neural nets (NN) for image classification without the need for programming. The software provides a variety of NN-architectures that can be simply selected for training. AID allows the user to apply trained models on new data, obtain metrics for classification performance, and export final models to different formats. The working principles of AID are first illustrated by training a convolutional neural net (CNN) on a large standard dataset consisting of images of different objects (CIFAR-10). We further demonstrate the range of possible applications on selected biophysical and biomedical problems, such as distinguishing differentiated and non-differentiated stem cells, performing a whole blood cell count, and classifying B- and T-cells, all based on cell images alone. Thus, AID can empower anyone to develop, train, and apply NNs for image classification. Moreover, models can be generated by non-programmers, exported, and used on different devices, which allows for an interdisciplinary use.