# Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks

arXiv: https://arxiv.org/abs/1810.05943 · HTML: https://mlsanity.com/paper/1810.05943/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2018.

## Built on by (most cited first, 7 of 7)

- [ClusterFormer: Clustering As A Universal Visual Learner](https://mlsanity.com/paper/2309.13196/) (2023)
- [A Novel Application of Image-to-Image Translation: Chromosome Straightening Framework by Learning from a Single Image](https://mlsanity.com/paper/2103.02835/) (2021)
- [ChrSNet: Chromosome Straightening using Self-attention Guided Networks](https://mlsanity.com/paper/2207.00147/) (2022)
- [Tokensome: Towards a Genetic Vision-Language GPT for Explainable and Cognitive Karyotyping](https://mlsanity.com/paper/2403.11073/) (2024)
- [Supervised Contrastive Learning for Fine-grained Chromosome Recognition](https://mlsanity.com/paper/2312.07623/) (2023)
- [Perturb-and-Restore: Simulation-driven Structural Augmentation Framework for Imbalance Chromosomal Anomaly Detection](https://mlsanity.com/paper/2604.00854/) (2026)
- [Aycromo: An Open-Source Platform for Automatic Chromosome Detection in Metaphase Images Based on Deep Learning](https://mlsanity.com/paper/2604.24685/) (2026)

## Abstract (arXiv)

Chromosome classification is critical for karyotyping in abnormality diagnosis. To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks. The approach consists of one global-scale network (G-Net) and one local-scale network (L-Net). It follows three stages. The first stage is to learn both global and local features. We extract global features and detect finer local regions via the G-Net. By proposing a varifocal mechanism, we zoom into local parts and extract local features via the L-Net. Residual learning and multi-task learning strategies are utilized to promote high-level feature extraction. The detection of discriminative local parts is fulfilled by a localization subnet of the G-Net, whose training process involves both supervised and weakly-supervised learning. The second stage is to build two multi-layer perceptron classifiers that exploit features of both two scales to boost classification performance. The third stage is to introduce a dispatch strategy of assigning each chromosome to a type within each patient case, by utilizing the domain knowledge of karyotyping. Evaluation results from 1909 karyotyping cases showed that the proposed Varifocal-Net achieved the highest accuracy per patient case (%) 99.2 for both type and polarity tasks. It outperformed state-of-the-art methods, demonstrating the effectiveness of our varifocal mechanism, multi-scale feature ensemble, and dispatch strategy. The proposed method has been applied to assist practical karyotype diagnosis.