DeepACEv2: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks

TL;DR

DeepACEv2 is an advanced deep learning framework that automates chromosome enumeration in metaphase cell images, effectively handling occlusion and confusion through novel modules and loss functions, outperforming previous methods.

Contribution

The paper introduces DeepACEv2, a novel chromosome enumeration method with new modules like Hard Negative Anchors Sampling, Template Module, and a specialized loss, improving accuracy over prior approaches.

Findings

Achieves 71.39% Whole Correct Ratio (WCR) on clinical images.

Reduces Average Error Ratio (AER) to about 1.17%.

Demonstrates effectiveness of each module through ablation studies.

Abstract

Chromosome enumeration is an essential but tedious procedure in karyotyping analysis. To automate the enumeration process, we develop a chromosome enumeration framework, DeepACEv2, based on the region based object detection scheme. The framework is developed following three steps. Firstly, we take the classical ResNet-101 as the backbone and attach the Feature Pyramid Network (FPN) to the backbone. The FPN takes full advantage of the multiple level features, and we only output the level of feature map that most of the chromosomes are assigned to. Secondly, we enhance the region proposal network's ability by adding a newly proposed Hard Negative Anchors Sampling to extract unapparent but essential information about highly confusing partial chromosomes. Next, to alleviate serious occlusion problems, besides the traditional detection branch, we novelly introduce an isolated Template Module branch to extract unique embeddings of each proposal by utilizing the chromosome's geometric information. The embeddings are further incorporated into the No Maximum Suppression (NMS) procedure to improve the detection of overlapping chromosomes. Finally, we design a Truncated Normalized Repulsion Loss and add it to the loss function to avoid inaccurate localization caused by occlusion. In the newly collected 1375 metaphase images that came from a clinical laboratory, a series of ablation studies validate the effectiveness of each proposed module. Combining them, the proposed DeepACEv2 outperforms all the previous methods, yielding the Whole Correct Ratio(WCR)(%) with respect to images as 71.39, and the Average Error Ratio(AER)(%) with respect to chromosomes as about 1.17.