# Teacher-Student chain for efficient semi-supervised histology image classification

arXiv: https://arxiv.org/abs/2003.08797 · HTML: https://mlsanity.com/paper/2003.08797/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [Extending the WILDS Benchmark for Unsupervised Adaptation](https://mlsanity.com/paper/2112.05090/) (2021)
- [NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentation](https://mlsanity.com/paper/2102.09099/) (2021)
- [Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis](https://mlsanity.com/paper/2208.08789/) (2022)
- [MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis](https://mlsanity.com/paper/2308.16561/) (2023)
- [Stain Based Contrastive Co-training for Histopathological Image Analysis](https://mlsanity.com/paper/2206.12505/) (2022)
- [Self-training of Machine Learning Models for Liver Histopathology: Generalization under Clinical Shifts](https://mlsanity.com/paper/2211.07692/) (2022)
- [Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Review](https://mlsanity.com/paper/2410.19820/) (2024)
- [Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction](https://mlsanity.com/paper/2311.10305/) (2023)

## Abstract (arXiv)

Deep learning shows great potential for the domain of digital pathology. An automated digital pathology system could serve as a second reader, perform initial triage in large screening studies, or assist in reporting. However, it is expensive to exhaustively annotate large histology image databases, since medical specialists are a scarce resource. In this paper, we apply the semi-supervised teacher-student knowledge distillation technique proposed by Yalniz et al. (2019) to the task of quantifying prognostic features in colorectal cancer. We obtain accuracy improvements through extending this approach to a chain of students, where each student's predictions are used to train the next student i.e. the student becomes the teacher. Using the chain approach, and only 0.5% labelled data (the remaining 99.5% in the unlabelled pool), we match the accuracy of training on 100% labelled data. At lower percentages of labelled data, similar gains in accuracy are seen, allowing some recovery of accuracy even from a poor initial choice of labelled training set. In conclusion, this approach shows promise for reducing the annotation burden, thus increasing the affordability of automated digital pathology systems.