Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies

• URL: http://arxiv.org/abs/2509.02601v2
• Date: Fri, 17 Oct 2025 12:39:43 GMT
• Title: Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies
• Authors: Piotr Giedziun, Jan Sołtysik, Mateusz Górczany, Norbert Ropiak, Marcin Przymus, Piotr Krajewski, Jarosław Kwiecień, Artur Bartczak, Izabela Wasiak, Mateusz Maniewski,
• Abstract summary: We present a solution for the MIDOG 2025 Challenge Track2, addressing binary classification of normal mitotic figures (NMFs) versus atypical mitotic figures (AMFs)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a solution for the MIDOG 2025 Challenge Track~2, addressing binary classification of normal mitotic figures (NMFs) versus atypical mitotic figures (AMFs). The approach leverages pathology-specific foundation model H-optimus-0, selected based on recent cross-domain generalization benchmarks and our empirical testing, with Low-Rank Adaptation (LoRA) fine-tuning and MixUp augmentation. Implementation includes soft labels based on multi-expert consensus, hard negative mining, and adaptive focal loss, metric learning and domain adaptation. The method demonstrates both the promise and challenges of applying foundation models to this complex classification task, achieving reasonable performance in the preliminary evaluation phase.

Related papers

• Parameter-efficient fine-tuning (PEFT) of Vision Foundation Models for Atypical Mitotic Figure Classification [0.0]
  Atypical mitotic figures (AMFs) are rare abnormal cell divisions associated with tumor aggressiveness and poor prognosis.<n>The MID 2025OG challenge introduced a dedicated track for atypical mitosis classification.<n>We investigated the use of large vision foundation models, including Virchow, Virchow2, and UNI, with Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning.
  arXiv  Detail & Related papers  (2025-09-21T05:46:54Z)
• Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification [0.0]
  We leveraged Pathology Foundation Models (PFMs) pre-trained on large histopathology datasets.<n>During training, we employ a fisheye transform to emphasize mitoses and Fourier Domain Adaptation using ImageNet target images.<n>We ensembled multiple PFMs to integrate complementary morphological insights, achieving a high balanced accuracy on the Preliminary Evaluation Phase dataset.
  arXiv  Detail & Related papers  (2025-08-29T03:24:57Z)
• A multi-task neural network for atypical mitosis recognition under domain shift [3.2490463485798338]
  An approach based on multi-task learning is proposed for addressing this problem.<n>By exploiting auxiliary tasks, correlated to the main classification task, the proposed approach aims to aid the model to focus only on the object to classify.<n>The proposed approach shows promising performance in a preliminary evaluation conducted on three distinct datasets.
  arXiv  Detail & Related papers  (2025-08-28T17:39:30Z)
• Automated Classification of Normal and Atypical Mitotic Figures Using ConvNeXt V2: MIDOG 2025 Track 2 [0.026042848991788176]
  This paper presents our solution for the MIDOG 2025 Challenge Track 2, which focuses on binary classification of normal mitotic figures (NMFs) versus atypical mitotic figures (AMFs)<n>Our approach leverages a ConvNeXt V2 base model with center cropping preprocessing and 5-fold cross-validation ensemble strategy.<n>The solution demonstrates the effectiveness of modern convolutional architectures for mitotic figure subtyping while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2025-08-26T09:11:12Z)
• MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification [8.74505335529696]
  Meta-language foundation models (VLFMs) have shown promise in addressing data scarcity for whole slide image (WSI) classification via zero-shot adaptation.<n>These methods remain outperformed by conventional multiple instance learning (MIL) approaches trained on large datasets.<n>While existing few-shot methods improve diagnostic accuracy with limited annotations, their reliance on conventional classifier designs introduces critical vulnerabilities to data scarcity.
  arXiv  Detail & Related papers  (2025-08-13T17:32:42Z)
• CLIP Meets Diffusion: A Synergistic Approach to Anomaly Detection [54.85000884785013]
  Anomaly detection is a complex problem due to the ambiguity in defining anomalies, the diversity of anomaly types, and the scarcity of training data.<n>We propose CLIPfusion, a method that leverages both discriminative and generative foundation models.<n>We believe that our method underscores the effectiveness of multi-modal and multi-model fusion in tackling the multifaceted challenges of anomaly detection.
  arXiv  Detail & Related papers  (2025-06-13T13:30:15Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters [69.24377241408851]
  Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. We propose to base the selection on gradient-signal-to-noise ratio (GSNR) of network's parameters.
  arXiv  Detail & Related papers  (2023-10-11T10:21:34Z)
• Balanced Classification: A Unified Framework for Long-Tailed Object Detection [74.94216414011326]
  Conventional detectors suffer from performance degradation when dealing with long-tailed data due to a classification bias towards the majority head categories. We introduce a unified framework called BAlanced CLassification (BACL), which enables adaptive rectification of inequalities caused by disparities in category distribution. BACL consistently achieves performance improvements across various datasets with different backbones and architectures.
  arXiv  Detail & Related papers  (2023-08-04T09:11:07Z)
• Stacking Ensemble Learning in Deep Domain Adaptation for Ophthalmic Image Classification [61.656149405657246]
  Domain adaptation is effective in image classification tasks where obtaining sufficient label data is challenging. We propose a novel method, named SELDA, for stacking ensemble learning via extending three domain adaptation methods. The experimental results using Age-Related Eye Disease Study (AREDS) benchmark ophthalmic dataset demonstrate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2022-09-27T14:19:00Z)
• Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function [106.69643619725652]
  We develop a training strategy that allows even a simple BiLSTM model, when trained with cross-entropy loss, to achieve competitive results. We report state-of-the-art results for text classification task on several benchmark datasets.
  arXiv  Detail & Related papers  (2020-09-08T21:55:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.