We propose a new training scheme for domain generalization in mitotic figure detection. Mitotic figures show different characteristics for each scanner. We consider each scanner as a 'domain' and the image distribution specified for each domain as 'style'. The goal is to train our network to be robust on scanner types by using various 'style' images. To expand the style variance, we transfer a style of the training image into arbitrary styles, by defining a module based on StarGAN. Our model with the proposed training scheme shows positive performance on MIDOG Preliminary Test-Set containing scanners never seen before.
Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, UK（华威大学计算机科学系组织图像分析中心，英国）；School of Clinical Dentistry, University of Sheffield, Sheffield, UK（谢菲尔德大学口腔临床学院，英国）
The detection of mitotic figures from different scanners/sites remains an important topic of research, owing to its potential in assisting clinicians with tumour grading. The MItosis DOmain Generalization (MIDOG) challenge aims to test the robustness of detection models on unseen data from multiple scanners for this task. We present a short summary of the approach employed by the TIA Centre team to address this challenge. Our approach is based on a hybrid detection model, where mitotic candidates are segmented on stain normalised images, before being refined by a deep learning classifier. Cros…
Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification
Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）；University of Veterinary Medicine, Vienna（维也纳兽医大学）；Center for AI and Data Science, Julius-Maximilians-Universität Würzburg（维尔茨堡大学朱利叶斯-马克西米利安人工智能与数据科学中心）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Flensburg University of Applied Sciences（弗伦斯堡应用技术大学）
Learning New Tricks from Old Dogs -- Inter-Species, Inter-Tissue Domain Adaptation for Mitotic Figure Assessment
Pattern Recognition Lab（模式识别实验室）；Computer Sciences（计算机科学（学院））；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）；Institute of Veterinary Pathology（兽医病理学研究所）；Freie Universität Berlin（柏林自由大学）；Institute of Neuropathology（神经病理学研究所）
Classifying Mitotic Figures in the MIDOG25 Challenge with Deep Ensemble Learning and Rule Based Refinement
IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, University of Augsburg, Germany（转化医学研究信息基础设施，应用计算机科学学院，乌尔姆大学）；Department of Neuropathology, Pathology, Medical Faculty, University of Augsburg, Germany（神经病理学系，病理学，医学系，乌尔姆大学）；DigiHealth Institute, Neu-Ulm University of Applied Sciences, Germany（DigiHealth研究所，纽乌尔姆应用科学大学）；Institute of Medical Data Science, University Hospital Würzburg, Germany（医学数据科学研究所，乌尔姆大学医院）
Challenges and Lessons from MIDOG 2025: A Two-Stage Approach to Domain-Robust Mitotic Figure Detection
Department of Medicine, Korea University Graduate School（韩国大学研究生院医学系）；Department of Medicine, Dongguk University（东国大学医学系）；Department of Computer Science and Engineering, Sogang University（ソガン大学计算机科学与工程系）
Pan-Cancer mitotic figures detection and domain generalization: MIDOG 2025 Challenge
Department of Medical Physics and Biomedical Engineering, UCL, UK（医学物理与生物医学工程系，UCL，英国）；Department of Radiotherapy, University College London Hospitals, London, UK（放射治疗系，University College London Hospitals，伦敦，英国）；Centre for Evolution and Cancer, The Institute of Cancer Research, London, UK（进化与癌症中心，癌症研究所在伦敦，英国）
Field Of Interest Proposal for Augmented Mitotic Cell Count: Comparison of two Convolutional Networks
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Freie Universität Berlin（柏林自由大学）
大多数人类肿瘤分级系统以及兽医组织病理学分级系统都是基于组织学切片特定参考区域中有丝分裂像的绝对计数。由于在诊断环境中，用于鉴定的时间是有限的，因此病理学家通常几乎任意地选择假定具有最高有丝分裂活性的感兴趣的某个领域。然而，由于有丝分裂像在载玻片上通常非常稀疏，并且通常具有斑片状分布，这造成了已知能够影响肿瘤定位的采样问题。另一方面，核分裂像的自动检测还不能被认为是足够可靠的临床应用。为了帮助人类专家的工作，同时减少肿瘤分级的差异，评估整个载玻片图像（WSI）的最高有丝分裂活性并将其用作人类计数的参考区域是有益的。对于这项任务，我们比较了两种基于卷积神经网络（CNN）的感兴趣区域建议方法。对于这两种方法，CNN执行WSI的分割以评估有丝分裂活性。第一种方法以原始图像分辨率执行分割，而第二种方法以显著降低的分辨率执行分割操作，从而降低处理复杂度。我们使用32个完全注释的犬肥大细胞肿瘤全切片图像的数据集来评估该方法，其中22个用于网络训练，10个用于测试。我们的研究结果表明，虽然基于精细分辨率网络的方法与真实有丝分裂活性的总体相关性相当高（0.94 vs. 0.83），但感兴趣的领域选择仅略好。这两种方法都提出了在各自载玻片的上四分位数中包含有丝分裂计数的感兴趣区域。
Technische Hochschule Ingolstadt（因戈尔施塔特应用技术大学）；Schwarzman Animal Medical Center（施瓦茨曼动物医疗中心）；Tribun Health；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；University of Veterinary Medicine Vienna（维也纳兽医大学）
Mitotic activity is key for the assessment of malignancy in many tumors. Moreover, it has been demonstrated that the proportion of abnormal mitosis to normal mitosis is of prognostic significance. Atypical mitotic figures (MF) can be identified morphologically as having segregation abnormalities of the chromatids. In this work, we perform, for the first time, automatic subtyping of mitotic figures into normal and atypical categories according to characteristic morphological appearances of the different phases of mitosis. Using the publicly available MIDOG21 and TUPAC16 breast cancer mitosis da…
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Freie Universität Berlin（柏林自由大学）；Animal Medical Center（动物医疗中心）；University of Pennsylvania（宾夕法尼亚大学）；University of Veterinary Medicine Hannover（汉诺威兽医大学）；Synlab’s VPG Histology（Synlab VPG组织学部门）；Michigan State University（密歇根州立大学）；Idorsia Pharmaceuticals Ltd（Idorsia制药有限公司）；International Zoo Veterinary Group（国际动物园兽医集团）；University of Bern（伯尔尼大学）；IDEXX Vet Med Labor GmbH（爱德士兽医实验室有限责任公司）
Density of mitotic figures in histologic sections is a prognostically relevant characteristic for many tumours. Due to high inter-pathologist variability, deep learning-based algorithms are a promising solution to improve tumour prognostication. Pathologists are the gold standard for database development, however, labelling errors may hamper development of accurate algorithms. In the present work we evaluated the benefit of multi-expert consensus (n = 3, 5, 7, 9, 11) on algorithmic performance. While training with individual databases resulted in highly variable F$_1$ scores, performance was n…
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Freie Universität Berlin（柏林自由大学）；University of Bern（伯尔尼大学）；IDEXX Laboratories（艾迪克斯实验室）
Manual count of mitotic figures, which is determined in the tumor region with the highest mitotic activity, is a key parameter of most tumor grading schemes. It can be, however, strongly dependent on the area selection due to uneven mitotic figure distribution in the tumor section.We aimed to assess the question, how significantly the area selection could impact the mitotic count, which has a known high inter-rater disagreement. On a data set of 32 whole slide images of H&E-stained canine cutaneous mast cell tumor, fully annotated for mitotic figures, we asked eight veterinary pathologists (fi…
Freie Universität Berlin（柏林自由大学）；Eindhoven University of Technology（埃因霍温理工大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；University Medical Center Utrecht（乌得勒支大学医学中心）
Pathologist-defined labels are the gold standard for histopathological data sets, regardless of well-known limitations in consistency for some tasks. To date, some datasets on mitotic figures are available and were used for development of promising deep learning-based algorithms. In order to assess robustness of those algorithms and reproducibility of their methods it is necessary to test on several independent datasets. The influence of different labeling methods of these available datasets is currently unknown. To tackle this, we present an alternative set of labels for the images of the aux…
RF-DETR for Robust Mitotic Figure Detection: A MIDOG 2025 Track 1 Approach
Wrocław University of Science and Technology（沃斯拉夫科学与技术大学）；Cancer Center Sp. z o. o.（癌症中心有限公司）；Hospital for Lung Diseases - Rebirth（肺病医院 - Rebirth）；Maria Sklodowska-Curie National Research Institute of Oncology（玛丽·斯克洛多夫斯卡国家癌症研究所）；Pathology Department（病理部门）；th Military Research Hospital in Bydgoszcz（比多日斯茨第10军科研医院）；Department of Tumor Pathology and Pathomorphology（肿瘤病理学与病理形态学部门）；Oncology Centre Prof. Franciszek Łukaszczyk Memorial Hospital（弗雷德里克·卢卡斯茨基纪念医院肿瘤中心）；Doctoral School of Medical and Health Sciences, Nicolaus Copernicus University in Toruń（医学与健康科学博士学校，尼古拉斯·哥白尼大学在托伦）；Department of Obstetrics, Gynaecology and Oncology, Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Torun（妇产科与肿瘤学部门，比多日斯茨学院，尼古拉斯·哥白尼大学在托伦）
Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies
Wrocław University of Science and Technology（沃拉什大学科学与技术学院）；Cancer Center Sp. z o. o.（癌症中心有限公司）；Hospital for Lung Diseases - Rebirth（肺病医院-重生）；Maria Sklodowska-Curie National Research Institute of Oncology（玛丽·斯克洛多夫斯卡国家癌症研究院）；Pathology Department（病理部门）；th Military Research Hospital in Bydgoszcz（比多斯茨第10军科研医院）；Department of Tumor Pathology and Pathomorphology（肿瘤病理与组织病理学部门）；Oncology Centre Prof. Franciszek Łukaszczyk Memorial Hospital（弗雷德里克·卢卡斯茨基纪念医院肿瘤中心）；Doctoral School of Medical and Health Sciences, Nicolaus Copernicus University in Toruń（医学与健康科学博士学院，尼古拉斯·哥白尼大学图努恩分校）；Department of Obstetrics, Gynaecology and Oncology, Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Torun（妇产科与肿瘤学系，比多斯茨医学院，尼古拉斯·哥白尼大学图努恩分校）
Domain variability is a common bottle neck in developing generalisable algorithms for various medical applications. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a target representative feature space through unpaired image to image translation (CycleGAN). We comprehensively evaluate the performanceand usefulness by utilising the transformation to mitosis detection with candidate proposal and classification. This work presents a simple yet effective multi-step mitotic figure detection algorithm developed as a baseli…
Norwegian University of Science and Technology（挪威科技大学）
Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures. However, current state-of-the-art limit anonymization to the task of face anonymization. In this paper, we propose a novel anonymization framework (DeepPrivacy2) for realistic anonymization of human figures and faces. We introduce a new large and diverse dataset for human figure synthesis, which significantly improves image quality and diversity of generated images. Furthermore, we propose a style-based GAN that produces high quality, diverse and editable anonymizations. We demonstrate that our full-b…
OMG-Net: A Deep Learning Framework Deploying Segment Anything to Detect Pan-Cancer Mitotic Figures from Haematoxylin and Eosin-Stained Slides
University College London（伦敦大学学院）；University College London Hospitals NHS Foundation Trust（伦敦大学学院医院 NHS 基金会信托）；University College London Cancer Institute（伦敦大学学院癌症研究所）；Royal National Orthopaedic Hospital NHS Foundation Trust（皇家国立骨科医院 NHS 基金会信托）；University Hospital Basel（巴塞尔大学医院）；University of Basel（巴塞尔大学）；Rutgers Biomedical and Health Sciences（罗格斯生物医学与健康科学学院）；Rutgers University（罗格斯大学）；The Robert Jones and Agnes Hunt Orthopaedic Hospital（罗伯特·琼斯和艾格尼丝·亨特骨科医院）；Keele University（基尔大学）
Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation
Flensburg University of Applied Sciences（弗劳恩霍夫应用科技大学）；University of Veterinary Medicine, Vienna（维也纳兽医大学）；The Schwarzman Animal Medical Center（施瓦茨曼动物医疗中心）；Diffusely（扩散地）；Freie Universität Berlin（柏林自由大学）；Technische Hochschule Ingolstadt（因戈尔施塔特技术大学）；Medical University of Vienna（维也纳医学大学）；Julius-Maximilians-Universität Würzburg（维尔茨堡约瑟夫-马克斯姆-大学）
Mars Digital Technologies（玛氏数字科技）；Antech Diagnostics（Antech诊断公司）；Stanford University（斯坦福大学）
Background: Histopathology is an important modality for the diagnosis and management of many diseases in modern healthcare, and plays a critical role in cancer care. Pathology samples can be large and require multi-site sampling, leading to upwards of 20 slides for a single tumor, and the human-expert tasks of site selection and and quantitative assessment of mitotic figures are time consuming and subjective. Automating these tasks in the setting of a digital pathology service presents significant opportunities to improve workflow efficiency and augment human experts in practice. Approach: Mul…
Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures
Flensburg University of Applied Sciences（弗伦斯堡应用科学大学）；University of Veterinary Medicine, Vienna（维也纳兽医大学）；Freie Universität Berlin（柏林自由大学）；Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）；Medical University of Vienna（维也纳医科大学）；Julius-Maximilians-Universität Würzburg（维尔zburg大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）
Efficient Fine-Tuning of DINOv3 Pretrained on Natural Images for Atypical Mitotic Figure Classification
Mines Paris, PSL University, Center for Computational Biology（巴黎 Mines 大学计算生物学中心）；Mines Paris, PSL University, Center for Mathematical Morphology（巴黎 Mines 大学数学形态学中心）；Sanofi（桑福有限公司）；Institut Curie, PSL University（Curie 机构，巴黎 Mines 大学）；INSERM, U1331 Computational Oncology（INSERM，U1331 计算肿瘤学）；Department of Pathology, University Hospital of Nantes（南特大学医院病理学系）
Xidian University（西安电子科技大学）；Ocean University of China（中国海洋大学）
Mitotic figure count is an important marker of tumor proliferation and has been shown to be associated with patients' prognosis. Deep learning based mitotic figure detection methods have been utilized to automatically locate the cell in mitosis using hematoxylin \& eosin (H\&E) stained images. However, the model performance deteriorates due to the large variation of color tone and intensity in H\&E images. In this work, we proposed a two stage mitotic figure detection framework by fusing a detector and a deep ensemble classification model. To alleviate the impact of color variation in H\&E ima…
Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br)
University of Veterinary Medicine, Vienna（维也纳兽医大学）；The Schwarzman Animal Medical Center（施瓦茨曼动物医疗中心）；Flensburg University of Applied Sciences（弗伦斯堡应用科学大学）；Freie Universität Berlin（柏林自由大学）；Medical University of Vienna（维也纳医科大学）；Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）
Breast cancer is the most commonly diagnosed cancer worldwide, with over two million new cases each year. During diagnostic tumour grading, pathologists manually count the number of dividing cells (mitotic figures) in biopsy or tumour resection specimens. Since the process is subjective and time-consuming, data-driven artificial intelligence (AI) methods have been developed to automatically detect mitotic figures. However, these methods often generalise poorly, with performance reduced by variations in tissue types, staining protocols, or the scanners used to digitise whole-slide images. Domai…
On the Value of PHH3 for Mitotic Figure Detection on H&E-stained Images
Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）；Gestalt Diagnostics（格式塔诊断公司）；University of Veterinary Medicine, Vienna（维也纳兽医大学）；Freie Universität Berlin（柏林自由大学）；SeaWorld Yas Island（海洋世界亚斯岛）；Cornell University（康奈尔大学）；USAMV（克卢日-纳波卡兽医与医学大学）；Medical University of Vienna（维也纳医科大学）；Hoffmann-La Roche（罗氏公司）；Ross University School of Veterinary Medicine（罗斯大学兽医学院）；University of Florida（佛罗里达大学）；University Hospital Erlangen（埃尔兰根大学医院）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；IDEXX Laboratories（爱德士实验室）；The Schwarzman Animal Medical Center（施瓦茨曼动物医疗中心）
Assessing the Mitotic Count has a known high degree of intra- and inter-rater variability. Computer-aided systems have proven to decrease this variability and reduce labeling time. These systems, however, are generally highly dependent on their training domain and show poor applicability to unseen domains. In histopathology, these domain shifts can result from various sources, including different slide scanning systems used to digitize histologic samples. The MItosis DOmain Generalization challenge focused on this specific domain shift for the task of mitotic figure detection. This work presen…
Fu Foundation School of Engineering and Applied Science（傅 foundation 工程与应用科学学院）；Columbia University（哥伦比亚大学）；University of Michigan（密歇根大学）；Department of Computer Science（计算机科学系）；Lubin School of Business（鲁宾商学院）；Pace University（佩斯大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Multispectral Spatial Characterization: Application to Mitosis Detection in Breast Cancer Histopathology
University Joseph Fourier（约瑟夫·傅里叶大学）；IPAL, CNRS UMI 2955（IPAL，法国国家科学研究中心UMI 2955）；CoSMo Software（CoSMo软件公司）；Temasys Communications（Temasys通信公司）；University Pierre and Marie Curie（皮埃尔和玛丽·居里大学）
SWAN -- Enabling Fast and Mobile Histopathology Image Annotation through Swipeable Interfaces
Flensburg University of Applied Sciences（弗劳恩霍夫应用科技大学）；University of Veterinary Medicine（兽医大学）；Schwarzman Animal Medical Center（施瓦茨曼动物医疗中心）；Medical University of Vienna（维也纳医学大学）；Technische Hochschule Ingolstadt（英戈尔施塔特技术大学）
Chulalongkorn University（朱拉隆功大学）；King Chulalongkorn Memorial Hospital（朱拉隆功国王纪念医院）；NVIDIA AI Technology Center（英伟达人工智能技术中心）
Mitotic count (MC) is an important histological parameter for cancer diagnosis and grading, but the manual process for obtaining MC from whole-slide histopathological images is very time-consuming and prone to error. Therefore, deep learning models have been proposed to facilitate this process. Existing approaches utilize a two-stage pipeline: the detection stage for identifying the locations of potential mitotic cells and the classification stage for refining prediction confidences. However, this pipeline formulation can lead to inconsistencies in the classification stage due to the poor pred…
The effective localization of mitosis is a critical precursory task for deciding tumor prognosis and grade. Automated mitosis detection through deep learning-oriented image analysis often fails on unseen patient data due to inherent domain biases. This paper proposes a domain homogenizer for mitosis detection that attempts to alleviate domain differences in histology images via adversarial reconstruction of input images. The proposed homogenizer is based on a U-Net architecture and can effectively reduce domain differences commonly seen with histology imaging data. We demonstrate our domain ho…
