Patch-Level Glioblastoma Subregion Classification with a Contrastive Learning-Based Encoder

• URL: http://arxiv.org/abs/2511.20221v1
• Date: Tue, 25 Nov 2025 11:49:18 GMT
• Title: Patch-Level Glioblastoma Subregion Classification with a Contrastive Learning-Based Encoder
• Authors: Juexin Zhang, Qifeng Zhong, Ying Weng, Ke Chen,
• Abstract summary: We developed a method that fine-tunes a pre-trained Vision Transformer (ViT) encoder with a dedicated classification head on the official training dataset.<n>Our model's performance on the online validation set, evaluated via the Synapse platform, yielded a Matthews Correlation Coefficient (MCC) of 0.7064 and an F1-score of 0.7676.<n>On the final test set, the model achieved an MCC of 0.6509 and an F1-score of 0.5330, which secured our team second place in the BraTS-Pathology 2025 Challenge.
• Score: 8.220201308071614
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The significant molecular and pathological heterogeneity of glioblastoma, an aggressive brain tumor, complicates diagnosis and patient stratification. While traditional histopathological assessment remains the standard, deep learning offers a promising path toward objective and automated analysis of whole slide images. For the BraTS-Path 2025 Challenge, we developed a method that fine-tunes a pre-trained Vision Transformer (ViT) encoder with a dedicated classification head on the official training dataset. Our model's performance on the online validation set, evaluated via the Synapse platform, yielded a Matthews Correlation Coefficient (MCC) of 0.7064 and an F1-score of 0.7676. On the final test set, the model achieved an MCC of 0.6509 and an F1-score of 0.5330, which secured our team second place in the BraTS-Pathology 2025 Challenge. Our results establish a solid baseline for ViT-based histopathological analysis, and future efforts will focus on bridging the performance gap observed on the unseen validation data.

Related papers

• FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation [63.7829089874007]
  This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation.<n>FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images.<n> Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2.
  arXiv  Detail & Related papers  (2026-01-22T01:34:39Z)
• Diagnostic Performance of Universal-Learning Ultrasound AI Across Multiple Organs and Tasks: the UUSIC25 Challenge [34.86849736082012]
  Current ultrasound AI remains fragmented into single-task tools.<n>General-purpose AI models achieve high accuracy and efficiency across multiple tasks using a single architecture.
  arXiv  Detail & Related papers  (2025-12-19T06:54:30Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• Classifying Histopathologic Glioblastoma Sub-regions with EfficientNet [0.6507401132790146]
  Glioblastoma (GBM) is the most common aggressive, fast-growing brain tumor, with a grim prognosis.<n>We designed a four-step deep learning approach to classify six (6) histological regions and quantitatively evaluated it on the BraTS-Path 2024 challenge dataset.<n> EfficientNet-B1 and EfficientNet-B4 achieved the best performance, achieving an F1 score of 0.98 in a 5-fold cross-validation configuration.
  arXiv  Detail & Related papers  (2025-11-12T02:14:23Z)
• 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)
• Deep Learning for Glioblastoma Morpho-pathological Features Identification: A BraTS-Pathology Challenge Solution [5.347187213114967]
  We present our approach to the BraTS-Path Challenge 2024.<n>We leverage a pre-trained model and fine-tune it on the BraTS-Path training dataset.<n>Our model exhibits perfect specificity of 0.898704, showing an exceptional capacity to correctly classify negative cases.
  arXiv  Detail & Related papers  (2025-07-24T06:47:23Z)
• TUMLS: Trustful Fully Unsupervised Multi-Level Segmentation for Whole Slide Images of Histology [41.94295877935867]
  We present a trustful fully unsupervised multi-level segmentation methodology (TUMLS) for whole slide images (WSIs)<n>TUMLS adopts an autoencoder (AE) as a feature extractor to identify the different tissue types within low-resolution training data.<n>This solution integrates seamlessly into clinicians, transforming the examination of a whole WSI into a review of concise, interpretable cross-level insights.
  arXiv  Detail & Related papers  (2025-04-17T07:48:05Z)
• The Skin Game: Revolutionizing Standards for AI Dermatology Model Comparison [0.6144680854063939]
  Deep Learning approaches in dermatological image classification have shown promising results, yet the field faces significant methodological challenges that impede proper evaluation.<n>This paper presents a systematic analysis of current methodological practices in skin disease classification research, revealing substantial inconsistencies in data preparation, augmentation strategies, and performance reporting.<n>We propose comprehensive methodological recommendations for model development, evaluation, and clinical deployment, emphasizing rigorous data preparation, systematic error analysis, and specialized protocols for different image types.
  arXiv  Detail & Related papers  (2025-02-04T17:15:36Z)
• Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective [32.93871326428446]
  Recent advances in artificial intelligence (AI) are revolutionizing medical imaging and computational pathology.<n>A constant challenge in the analysis of digital Whole Slide Images (WSIs) is the problem of aggregating tens of thousands of tile-level image embeddings to a slide-level representation.<n>This study conducts a benchmarking analysis of ten slide-level aggregation techniques across nine clinically relevant tasks.
  arXiv  Detail & Related papers  (2024-07-10T17:00:57Z)
• Virchow: A Million-Slide Digital Pathology Foundation Model [34.38679208931425]
  We present Virchow, a foundation model for computational pathology. Virchow is a vision transformer model with 632 million parameters trained on 1.5 million hematoxylin and eosin stained whole slide images.
  arXiv  Detail & Related papers  (2023-09-14T15:09:35Z)
• Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders [50.689585476660554]
  We propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models.
  arXiv  Detail & Related papers  (2022-12-14T06:04:18Z)
• Mitosis Detection, Fast and Slow: Robust and Efficient Detection of Mitotic Figures [3.047950378303433]
  We propose a robust and efficient two-stage mitosis detection framework, which comprises mitosis candidate segmentation and candidate refinement stages. EUNet can precisely segment candidates at a lower resolution to considerably speed up candidate detection. We demonstrate state-of-the-art performance and generalizability of the proposed model on the three largest publicly available mitosis datasets.
  arXiv  Detail & Related papers  (2022-08-26T11:14:59Z)
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis [48.64462717254158]
  We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos. When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
  arXiv  Detail & Related papers  (2022-07-23T19:17:26Z)

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.