Active learning framework with iterativeclustering for bioimage classification

摘要

Advances in imaging systems have yielded a flood of images into the research field. A semiautomated facility can reduce the laborious task of classifying this large number of images.Here we report the development of a novel framework, CARTA (Clustering-Aided RapidTraining Agent), applicable to bioimage classification that facilitates annotation and selectionof features. CARTA comprises an active learning algorithm combined with a genetic algorithmand self-organizing map. The framework provides an easy and interactive annotation methodand accurate classification. The CARTA framework enables classification of subcellularlocalization, mitotic phases and discrimination of apoptosis in images of plant and humancells with an accuracy level greater than or equal to annotators. CARTA can be applied toclassification of magnetic resonance imaging of cancer cells or multicolour time-course imagesafter surgery. Furthermore, CARTA can support development of customized features forclassification, high-throughput phenotyping and application of various classification schemesdependent on the user’s purpose.