Attention-effective multiple instance learning on weakly stem cell colony segmentation

TL;DR

This paper introduces a novel weakly supervised multiple instance learning approach using a U-net-like CNN for efficient, accurate, and interpretable stem cell colony classification without detailed annotations.

Contribution

It presents a single-model MIL framework that combines weak segmentation and classification for stem cell colonies, outperforming conventional methods by 15%.

Findings

Maximum accuracy of 95% in colony classification

Outperforms conventional methods by 15%

Enables interpretable localization without pixel-wise labels

Abstract

The detection of induced pluripotent stem cell (iPSC) colonies often needs the precise extraction of the colony features. However, existing computerized systems relied on segmentation of contours by preprocessing for classifying the colony conditions were task-extensive. To maximize the efficiency in categorizing colony conditions, we propose a multiple instance learning (MIL) in weakly supervised settings. It is designed in a single model to produce weak segmentation and classification of colonies without using finely labeled samples. As a single model, we employ a U-net-like convolution neural network (CNN) to train on binary image-level labels for MIL colonies classification. Furthermore, to specify the object of interest we used a simple post-processing method. The proposed approach is compared over conventional methods using five-fold cross-validation and receiver operating characteristic (ROC) curve. The maximum accuracy of the MIL-net is 95%, which is 15 % higher than the conventional methods. Furthermore, the ability to interpret the location of the iPSC colonies based on the image level label without using a pixel-wise ground truth image is more appealing and cost-effective in colony condition recognition.