# MiTHras: Task-specific Hierarchical Semi-supervised Contrastive Masked Autoencoder for Mitotic Figure Analysis

arXiv: https://arxiv.org/abs/2609.24736 · HTML: https://mlsanity.com/paper/2609.24736/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 52 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Benchmarking Self-Supervised Learning on Diverse Pathology Datasets](https://mlsanity.com/paper/2212.04690/) (2022)
- [Contrastive Masked Autoencoders are Stronger Vision Learners](https://mlsanity.com/paper/2207.13532/) (2022)
- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [VICRegL: Self-Supervised Learning of Local Visual Features](https://mlsanity.com/paper/2210.01571/) (2022)
- [Diffusion Models as Masked Autoencoders](https://mlsanity.com/paper/2304.03283/) (2023)
- [Multimodal Prototyping for cancer survival prediction](https://mlsanity.com/paper/2407.00224/) (2024)
- [Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challenge](https://mlsanity.com/paper/2309.15589/) (2023)
- [SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners](https://mlsanity.com/paper/2205.14540/) (2022)
- [Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarios](https://mlsanity.com/paper/2410.16038/) (2024)
- [Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br)](https://mlsanity.com/paper/2501.04467/) (2025)
- [Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge](https://mlsanity.com/paper/2108.11269/) (2021)
- [IMPaSh: A Novel Domain-shift Resistant Representation for Colorectal Cancer Tissue Classification](https://mlsanity.com/paper/2208.11052/) (2022)
- [Mitosis Detection, Fast and Slow: Robust and Efficient Detection of Mitotic Figures](https://mlsanity.com/paper/2208.12587/) (2022)
- [MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis](https://mlsanity.com/paper/2308.16561/) (2023)
- [CAMP: Continuous and Adaptive Learning Model in Pathology](https://mlsanity.com/paper/2407.09030/) (2024)
- [Improving mitosis detection on histopathology images using large vision-language models](https://mlsanity.com/paper/2310.07176/) (2023)
- [A novel dataset and a two-stage mitosis nuclei detection method based on hybrid anchor branch](https://mlsanity.com/paper/2301.07627/) (2023)

## Abstract (arXiv)

Mitotic figure (MF) analysis supports tumor grading and prognostic assessment, but automated models remain sensitive to differences in tissue type and image acquisition. We present MiTHras, a task-specific pretraining framework that combines pseudo-label-guided image- and token-level contrastive learning with masked reconstruction. We construct TCGA-MF-Pseudo, a corpus of 1.8 million cell-centered images from 14 TCGA cohorts spanning 11 organ sites. Comprehensive evaluation on MF classification, detection, count-based survival prediction, and subtype classification demonstrates the efficacy of MiTHras. It achieves the highest mean F1 on all three MF classification benchmarks and both subtype benchmarks. MiTHras also outperforms general-purpose and pathology foundation encoders by a larger margin under frozen-encoder linear probing than under full fine-tuning. Although detection gains are modest due to a shared candidate-detection stage, ablations confirm that token-level supervision improves typical-versus-atypical classification and linear probing. These findings establish that MiTHras yields robust, transferable representations for automated mitotic activity assessment.