PulseAugur
中
实时 11:03:52
English(EN) ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification

新的ProsMAE框架增强了组织病理学表示学习

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员开发了ProsMAE，一个新颖的多源掩码自编码器（Masked Autoencoder）框架，用于组织病理学表示学习。该方法利用来自PANDA、CAMELYON17和BRACS等不同数据集的图块来训练一个能够处理组织形态和采集条件变化的编码器。然后将预训练的编码器迁移用于ISUP分级分类，与标准的MAE基线相比，性能有所提高。 AI

影响 这项研究可能带来更准确、更鲁棒的AI模型，用于全切片图像的癌症诊断。

排序理由 该集群包含一篇详细介绍组织病理学表示学习新方法的学术论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的ProsMAE框架增强了组织病理学表示学习

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Anna Jung, Kyeonghun Kim, Youngung Han, Eunseob Choi, Jiwon Yang, Ken Ying-Kai Liao, Hyuk-Jae Lee, Nam-Joon Kim ·

    ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification

    arXiv:2607.08162v1 Announce Type: cross Abstract: Whole slide images (WSIs) provide rich diagnostic information for computational pathology, but their gigapixel scale, stain variation, scanner differences, tissue artifacts, and limited expert annotation make robust model training…

  2. arXiv cs.AI TIER_1 English(EN) · Nam-Joon Kim ·

    ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification

    Whole slide images (WSIs) provide rich diagnostic information for computational pathology, but their gigapixel scale, stain variation, scanner differences, tissue artifacts, and limited expert annotation make robust model training challenging. This paper presents a multi-source M…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification

    Whole slide images (WSIs) provide rich diagnostic information for computational pathology, but their gigapixel scale, stain variation, scanner differences, tissue artifacts, and limited expert annotation make robust model training challenging. This paper presents a multi-source M…

相关实体

相关话题