Challenges and Lessons from MIDOG 2025: A Two-Stage Approach to Domain-Robust Mitotic Figure Detection

• URL: http://arxiv.org/abs/2509.02630v1
• Date: Mon, 01 Sep 2025 17:42:05 GMT
• Title: Challenges and Lessons from MIDOG 2025: A Two-Stage Approach to Domain-Robust Mitotic Figure Detection
• Authors: Euiseop Song, Jaeyoung Park, Jaewoo Park,
• Abstract summary: This paper describes our participation in the MIDOG 2025 challenge, focusing on robust mitotic figure detection.<n>We developed a two-stage pipeline combining Faster R-CNN for candidate detection with an ensemble of three classifiers for false positive reduction.<n>Our best submission achieved F1-score 0.2237 (Recall: 0.9528, Precision: 0.1267) using a Faster R-CNN trained solely on MIDOG++ dataset.
• Score: 9.314972045525133
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Mitotic figure detection remains a challenging task in computational pathology due to domain variability and morphological complexity. This paper describes our participation in the MIDOG 2025 challenge, focusing on robust mitotic figure detection across diverse tissue domains. We developed a two-stage pipeline combining Faster R-CNN for candidate detection with an ensemble of three classifiers (DenseNet-121, EfficientNet-v2, InceptionResNet-v2) for false positive reduction. Our best submission achieved F1-score 0.2237 (Recall: 0.9528, Precision: 0.1267) using a Faster R-CNN trained solely on MIDOG++ dataset. While our high recall demonstrates effective mitotic figure detection, the critically low precision (12.67%) reveals fundamental challenges in distinguishing true mitoses from morphologically similar imposters across diverse domains. Analysis of six submission variants showed that subsequent optimization attempts were counterproductive, highlighting the omplexity of domain generalization in histopathology. This work provides valuable insights into the practical challenges of developing robust mitotic figure detection algorithms and emphasizes the importance of effective false positive suppression strategies.

Related papers

• MIDOG 2025 Track 2: A Deep Learning Model for Classification of Atypical and Normal Mitotic Figures under Class and Hardness Imbalances [0.0]
  We propose a novel deep learning approach based on a ResNet backbone with specialized classification heads.<n>Our architecture uniquely models both the mitotic figure phenotype and the instance difficulty simultaneously.
  arXiv  Detail & Related papers  (2025-09-01T15:12:05Z)
• RF-DETR for Robust Mitotic Figure Detection: A MIDOG 2025 Track 1 Approach [0.0]
  This paper presents our approach for the MIDOG 2025 challenge Track 1, focusing on robust mitotic figure detection across diverse histological contexts.<n>We employed RF-DETR (Roboflow Detection Transformer) with hard negative mining, trained on MIDOG++ dataset.<n>On the preliminary test set, our method achieved an F1 score of 0.789 with a recall of 0.839 and precision of 0.746, demonstrating effective generalization across unseen domains.
  arXiv  Detail & Related papers  (2025-08-29T16:04:50Z)
• Solutions for Mitotic Figure Detection and Atypical Classification in MIDOG 2025 [9.85180336249631]
  We present our approach to the Mitosis Domain Generalization (MIDOG) 2025 Challenge, which consists of two distinct tasks.<n>For the mitotic figure detection task, we propose a two-stage detection-classification framework that first localizes candidate mitotic figures.<n>For the atypical mitosis classification task, we employ an ensemble strategy that integrates predictions from multiple state-of-the-art deep learning architectures.
  arXiv  Detail & Related papers  (2025-08-29T15:16:35Z)
• ConvNeXt with Histopathology-Specific Augmentations for Mitotic Figure Classification [1.398256265458105]
  We propose a solution based on the lightweight ConvNeXt architecture to maximize domain coverage.<n>On the preliminary leaderboard, our model achieved a balanced accuracy of 0.8961, ranking among the top entries.
  arXiv  Detail & Related papers  (2025-08-29T13:18:32Z)
• MitoDetect++: A Domain-Robust Pipeline for Mitosis Detection and Atypical Subtyping [5.8892536770897665]
  MitoDetect++ is a unified deep learning pipeline designed for the MIDOG 2025 challenge.<n>For detection, we employ a U-Net-based encoder-decoder architecture with EfficientNetV2-L as the backbone.<n>For classification, we leverage the Virchow2 vision transformer, fine-tuned efficiently using Low-Rank Adaptation (LoRA) to minimize resource consumption.
  arXiv  Detail & Related papers  (2025-08-28T18:19:51Z)
• A bag of tricks for real-time Mitotic Figure detection [0.0]
  We build on the efficient RTMDet single stage object detector to achieve high inference speed suitable for clinical deployment.<n>We employ targeted, hard negative mining on necrotic and debris tissue to reduce false positives.<n>On the preliminary test set of the MItosis DOmain Generalization (MIDOG) 2025 challenge, our single-stage RTMDet-S based approach reaches an F1 of 0.81.
  arXiv  Detail & Related papers  (2025-08-27T11:45:44Z)
• Domain Adaptive Synapse Detection with Weak Point Annotations [63.97144211520869]
  We present AdaSyn, a framework for domain adaptive synapse detection with weak point annotations. In the WASPSYN challenge at I SBI 2023, our method ranks the 1st place.
  arXiv  Detail & Related papers  (2023-08-31T05:05:53Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network [51.44506007844284]
  We propose a shape-aware relation network for accurate and real-time landmark detection in endoscopic submucosal dissection surgery. We first devise an algorithm to automatically generate relation keypoint heatmaps, which intuitively represent the prior knowledge of spatial relations among landmarks. We then develop two complementary regularization schemes to progressively incorporate the prior knowledge into the training process.
  arXiv  Detail & Related papers  (2021-11-08T07:57:30Z)
• Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition [49.163326827954656]
  We propose a novel multi-granular-temporal graph network for skeleton-based action classification. We develop a dual-head graph network consisting of two inter-leaved branches, which enables us to extract at least two-temporal resolutions. We conduct extensive experiments on three large-scale datasets.
  arXiv  Detail & Related papers  (2021-08-10T09:25:07Z)
• Data-driven generation of plausible tissue geometries for realistic photoacoustic image synthesis [53.65837038435433]
  Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties. We propose a novel approach to PAT data simulation, which we refer to as "learning to simulate" We leverage the concept of Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data to generate plausible tissue geometries.
  arXiv  Detail & Related papers  (2021-03-29T11:30:18Z)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)
• Fader Networks for domain adaptation on fMRI: ABIDE-II study [68.5481471934606]
  We use 3D convolutional autoencoders to build the domain irrelevant latent space image representation and demonstrate this method to outperform existing approaches on ABIDE data.
  arXiv  Detail & Related papers  (2020-10-14T16:50:50Z)

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.