Mitosis sequence detection using hidden conditional random fields

TL;DR: A fully-automated mitosis event detector using hidden conditional random fields for cell populations imaged with time-lapse phase contrast microscopy that achieved 95% precision and 85% recall in very challenging image sequences of multipolar-shaped C3H10T1/2 mesenchymal stem cells is proposed.

Abstract: We propose a fully-automated mitosis event detector using hidden conditional random fields for cell populations imaged with time-lapse phase contrast microscopy. The method consists of two stages that jointly optimize recall and precision. First, we apply model-based microscopy image preconditioning and volumetric segmentation to identify candidate spatiotemporal sub-regions in the input image sequence where mitosis potentially occurred. Then, we apply a learned hidden conditional random field classifier to classify each candidate sequence as mitosis or not. The proposed detection method achieved 95% precision and 85% recall in very challenging image sequences of multipolar-shaped C3H10T1/2 mesenchymal stem cells. The superiority of the method was further demonstrated by comparisons with conditional random field and support vector machine classifiers. Moreover, the proposed method does not depend on empirical parameters, ad hoc image processing, or cell tracking; and can be straightforwardly adapted to different cell types.