Mitosis Detection from Partial Annotation by Dataset Generation via Frame-Order Flipping

TL;DR

This paper introduces a novel mitosis detection approach that leverages partial annotations by generating fully labeled datasets through frame-order flipping and image blending, reducing the need for extensive manual labeling.

Contribution

It presents a new dataset generation technique from partial labels using frame-order flipping and alpha-blending, enabling effective training with less manual annotation effort.

Findings

Outperforms existing methods on four datasets

Effective training with partially annotated sequences

Reduces manual labeling requirements

Abstract

Detection of mitosis events plays an important role in biomedical research. Deep-learning-based mitosis detection methods have achieved outstanding performance with a certain amount of labeled data. However, these methods require annotations for each imaging condition. Collecting labeled data involves time-consuming human labor. In this paper, we propose a mitosis detection method that can be trained with partially annotated sequences. The base idea is to generate a fully labeled dataset from the partial labels and train a mitosis detection model with the generated dataset. First, we generate an image pair not containing mitosis events by frame-order flipping. Then, we paste mitosis events to the image pair by alpha-blending pasting and generate a fully labeled dataset. We demonstrate the performance of our method on four datasets, and we confirm that our method outperforms other comparisons which use partially labeled sequences.