arXiv 2307.032112023-07-06q-bio.QMcs.CVcs.LGeess.IV

PseudoCell：将困难负样本挖掘作为伪标签用于基于深度学习的中心母细胞检测

PseudoCell: Hard Negative Mining as Pseudo Labeling for Deep Learning-Based Centroblast Cell Detection

Vidyasirimedhi Institute of Science & Technology（威达西里梅迪科学技术研究所）；Mahidol University（玛希隆大学）

Narongrid Seesawad, Piyalitt Ittichaiwong, Thapanun Sudhawiyangkul, Phattarapong Sawangjai, Peti Thuwajit, Paisarn Boonsakan, Supasan Sripodok, Kanyakorn Veerak… 展开作者

Narongrid Seesawad, Piyalitt Ittichaiwong, Thapanun Sudhawiyangkul, Phattarapong Sawangjai, Peti Thuwajit, Paisarn Boonsakan, Supasan Sripodok, Kanyakorn Veerakanjana, Phoomraphee Luenam, Komgrid Charngkaew, Ananya Pongpaibul, Napat Angkathunyakul, Narit Hnoohom, Sumeth Yuenyong, Chanitra Thuwajit, Theerawit Wilaiprasitporn

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出PseudoCell目标检测框架，利用病理医生标签与基于形态学特征的伪负样本自动检测中心母细胞，可消除WSI上58.18%至99.35%的非目标区域，从而减轻病理医生工作负担。

摘要：

基于深度学习的图像块分类模型已被用于H&E染色组织样本的全玻片图像（WSI），以辅助病理医生对滤泡性淋巴瘤患者进行分级。然而，这些方法仍然需要病理医生手动识别中心母细胞并提供精细标注才能获得最佳性能。为了解决这一问题，我们提出了PseudoCell，一个在WSI中自动检测中心母细胞的目标检测框架（源代码可在https://github.com/IoBT-VISTEC/PseudoCell.git获取）。该框架融合了病理医生提供的中心母细胞标签，并利用细胞形态学特征对欠采样的假阳性预测结果进行筛选，从而获得伪负样本标签。通过使用PseudoCell，病理医生的工作负担可以减轻，因为它能准确缩小组织检查中需要关注的区域。根据置信度阈值的不同，PseudoCell可以消除WSI上58.18%至99.35%的非中心母细胞组织区域。本研究提出了一种实用的中心母细胞预筛查方法，其改进无需病理医生提供精细标注。关于PseudoCell实际应用的详细指导在讨论部分中提供。

英文摘要：

Patch classification models based on deep learning have been utilized in whole-slide images (WSI) of H&E-stained tissue samples to assist pathologists in grading follicular lymphoma patients. However, these approaches still require pathologists to manually identify centroblast cells and provide refined labels for optimal performance. To address this, we propose PseudoCell, an object detection framework to automate centroblast detection in WSI (source code is available at https://github.com/IoBT-VISTEC/PseudoCell.git). This framework incorporates centroblast labels from pathologists and combines them with pseudo-negative labels obtained from undersampled false-positive predictions using the cell's morphological features. By employing PseudoCell, pathologists' workload can be reduced as it accurately narrows down the areas requiring their attention during examining tissue. Depending on the confidence threshold, PseudoCell can eliminate 58.18-99.35% of non-centroblasts tissue areas on WSI. This study presents a practical centroblast prescreening method that does not require pathologists' refined labels for improvement. Detailed guidance on the practical implementation of PseudoCell is provided in the discussion section.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。