# Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images

arXiv: https://arxiv.org/abs/1904.00839 · HTML: https://mlsanity.com/paper/1904.00839/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2019.

## Built on by (most cited first, 6 of 6)

- [Deep Learning for Computational Cytology: A Survey](https://mlsanity.com/paper/2202.05126/) (2022)
- [AI in Thyroid Cancer Diagnosis: Techniques, Trends, and Future Directions](https://mlsanity.com/paper/2308.13592/) (2023)
- [Machine Learning and Transformers for Thyroid Carcinoma Diagnosis: A Review](https://mlsanity.com/paper/2403.13843/) (2024)
- [From Data to Insights: A Comprehensive Survey on Advanced Applications in Thyroid Cancer Research](https://mlsanity.com/paper/2401.03722/) (2024)
- [From Pixel to Slide image: Polarization Modality-based Pathological Diagnosis Using Representation Learning](https://mlsanity.com/paper/2401.01496/) (2024)
- [ThyroidEffi 1.0: A Cost-Effective System for High-Performance Multi-Class Thyroid Carcinoma Classification](https://mlsanity.com/paper/2504.14139/) (2025)

## Abstract (arXiv)

We consider preoperative prediction of thyroid cancer based on ultra-high-resolution whole-slide cytopathology images. Inspired by how human experts perform diagnosis, our approach first identifies and classifies diagnostic image regions containing informative thyroid cells, which only comprise a tiny fraction of the entire image. These local estimates are then aggregated into a single prediction of thyroid malignancy. Several unique characteristics of thyroid cytopathology guide our deep-learning-based approach. While our method is closely related to multiple-instance learning, it deviates from these methods by using a supervised procedure to extract diagnostically relevant regions. Moreover, we propose to simultaneously predict thyroid malignancy, as well as a diagnostic score assigned by a human expert, which further allows us to devise an improved training strategy. Experimental results show that the proposed algorithm achieves performance comparable to human experts, and demonstrate the potential of using the algorithm for screening and as an assistive tool for the improved diagnosis of indeterminate cases.