首页/论文/1908.00410

arXiv 1908.004102019-08eess.IV

Pathological Myopic Image Analysis with Transfer Learning

Ruitao Xie, Libo Liu, Jingxin Liu, Connor S Qiu

备注：: MIDL 2019 [arXiv:1907.08612]

英文摘要：

We present a summary of transfer learning based methods for several challenging myopic fundus image analysis tasks including classification of pathological and non-pathological myopia,localisation of fovea,and segmentation of optic disc.By adapting existing popular deep learning architectures,our proposed methods have achieved 1st and 2nd place in several tasks at the Pathologic Myopia Challenge held at ISBI2019.

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。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

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。

继续探索

相关论文

Pathological myopia classification with simultaneous lesion segmentation using deep learning

Research Group Ophthalmology, KU Leuven（KU Leuven眼科研究组）；Ophthalmology Department, UZ Leuven（UZ Leuven眼科部）；ESAT-PSI, KU Leuven（KU Leuven ESAT-PSI）；Hasselt University（哈塞尔特大学）；VITO NV

This investigation reports on the results of convolutional neural networks developed for the recently introduced PathologicAL Myopia (PALM) dataset, which consists of 1200 fundus images. We propose a new Optic Nerve Head (ONH)-based prediction enhancement for the segmentation of atrophy and fovea. Models trained with 400 available training images achieved an AUC of 0.9867 for pathological myopia classification, and a Euclidean distance of 58.27 pixels on the fovea localization task, evaluated on a test set of 400 images. Dice and F1 metrics for semantic segmentation of lesions scored 0.9303 an…

2020-06-04cs.CVeess.IV

病理基础模型的迁移学习策略：脑肿瘤分类中的系统性评估

Transfer Learning Strategies for Pathological Foundation Models: A Systematic Evaluation in Brain Tumor Classification

Hokkaido University（北海道大学）；Hokkaido University Hospital（北海道大学医院）；Nakamura Memorial Hospital（中村纪念医院）；Sapporo Azabu Neurosurgical Hospital（札幌麻布神经外科医院）；Sapporo Hakuyokai Hospital（札幌白洋会医院）；Institute for Chemical Reaction Design and Discovery (WPI-ICReDD)（化学反应设计与发现研究所（WPI-ICReDD））

本文系统评估了病理基础模型在脑肿瘤分类中的迁移学习策略，发现仅需少量patch和线性探测即可取得稳健性能，而微调反而可能降低效果，提示应从训练编码器转向查询预训练编码器。

2025-04-08cs.CVeess.IV

CPIA数据集：一个用于自监督学习预训练的综合病理图像分析数据集

CPIA Dataset: A Comprehensive Pathological Image Analysis Dataset for Self-supervised Learning Pre-training

本文提出CPIA数据集，整合103个开源数据集构建含2142万余张标准化病理图像的大规模自监督预训练资源，覆盖48种以上器官和约100种疾病，并提供SOTA基线以促进病理图像分析研究。

2023-10-27eess.IV

CoCo DistillNet: a Cross-layer Correlation Distillation Network for Pathological Gastric Cancer Segmentation

Beijing University of Posts and Telecommunications（北京邮电大学）；Center for Research on Intelligent Perception and Computing, NLPR, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；Shandong University of Science and Technology（山东科技大学）；Artificial Intelligence Research, CAS (CAS-AIR)（中国科学院人工智能研究院）

In recent years, deep convolutional neural networks have made significant advances in pathology image segmentation. However, pathology image segmentation encounters with a dilemma in which the higher-performance networks generally require more computational resources and storage. This phenomenon limits the employment of high-accuracy networks in real scenes due to the inherent high-resolution of pathological images. To tackle this problem, we propose CoCo DistillNet, a novel Cross-layer Correlation (CoCo) knowledge distillation network for pathological gastric cancer segmentation. Knowledge di…

2021-11-12cs.CVeess.IV

使用传递对抗网络进行染色风格迁移

Stain Style Transfer using Transitive Adversarial Networks

College of Physics and Information Engineering, Fuzhou University（福州大学物理与信息工程学院）；Fujian Key Lab of Medical Instrumentation & Pharmaceutical Technology（福建省医疗器械与制药技术重点实验室）；Imperial Vision Technology（英视科技）；Fujian Provincial Cancer Hospital, The Affiliated Hospital of Fujian Medical University（福建医科大学附属福建省肿瘤医院）

针对医院间病理切片不成对导致颜色匹配困难的问题，提出传递对抗网络（TAN）进行染色风格迁移，无需专家挑选参考切片，相比最先进方法PSNR提高了0.87dB。

2019-10-23cs.CVeess.IV

Path-SAM2：将SAM2迁移用于数字病理语义分割

Path-SAM2: Transfer SAM2 for digital pathology semantic segmentation

Nanjing University（南京大学）；BISTU（北京信息科技大学）

本文提出Path-SAM2，首次将SAM2适配到病理语义分割任务，通过融合UNI病理视觉编码器并引入可学习KAN分类模块替代手动提示，在三个腺瘤病理数据集上取得了最先进性能。

2024-09-04cs.CVeess.IV

更多相关论文收起更多论文

Automatic lesion segmentation and Pathological Myopia classification in fundus images

Laboratory of Technological Innovation in Health, Federal University of Rio Grande do Norte（联邦里约格兰德大学健康技术创新实验室）

In this paper we present algorithms to diagnosis Pathological Myopia (PM) and detection of retinal structures and lesions such asOptic Disc (OD), Fovea, Atrophy and Detachment. All these tasks were performed in fundus imaging from PM patients and they are requirements to participate in the Pathologic Myopia Challenge (PALM). The challenge was organized as a half day Challenge, a Satellite Event of The IEEE International Symposium on Biomedical Imaging in Venice Italy.Our method applies different Deep Learning techniques for each task. Transfer learning is applied in all tasks using Xception as…

2020-02-15cs.LGeess.IVstat.ML

用于全切片病理图像生存分析的多模态跨任务交互

Multimodal Cross-Task Interaction for Survival Analysis in Whole Slide Pathological Images

School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）；School of Science, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）理学院）

本文提出多模态跨任务交互（MCTI）框架，利用亚型分类任务挖掘肿瘤区域并引入传输引导注意力模块建模任务间关联，有效融合病理图像与基因组数据，在三个公开基准上提升了生存预测性能。

2024-06-25cs.CVeess.IV

全局对比掩码自编码器是强大的病理表征学习者

Global Contrast Masked Autoencoders Are Powerful Pathological Representation Learners

Northeastern University（东北大学）；University of the Chinese Academy of Sciences（中国科学院大学）；The First Hospital of China Medical University（中国医科大学附属第一医院）

针对病理图像标注困难、数据缺乏的问题，提出全局对比掩码自编码器（GCMAE）自监督模型，学习局部-全局特征并提升跨数据集迁移性能，在三个HE染色病理数据集上验证有效性，并设计了自动化病理诊断流程。

2023-11-16cs.CVeess.IV

基于卷积神经网络的癌症细胞病理学图像分类：以乳腺癌为例

Convolutional neural network classification of cancer cytopathology images: taking breast cancer as an example

SouthWest JiaoTong University（西南交通大学）；University of Southampton（南安普顿大学）；Trine University（特里恩大学）；Hong Kong University of Science and Technology（香港科技大学）

针对乳腺癌病理诊断依赖人工、耗时且存在主观性的问题，提出基于Inceptionv3架构与迁移学习的CNN分类方法，结合图像分块与概率聚合策略，在BreaKHis数据集四种放大倍数下准确率均超0.92，提升了病理图像分类效率与精度。

2024-04-12cs.CVcs.LGeess.IV

Segmentation of Multimodal Myocardial Images Using Shape-Transfer GAN

Shenzhen University（深圳大学）

Myocardium segmentation of late gadolinium enhancement (LGE) Cardiac MR images is important for evaluation of infarction regions in clinical practice. The pathological myocardium in LGE images presents distinctive brightness and textures compared with the healthy tissues, making it much more challenging to be segment. Instead, the balanced-Steady State Free Precession (bSSFP) cine images show clearly boundaries and can be easily segmented. Given this fact, we propose a novel shape-transfer GAN for LGE images, which can 1) learn to generate realistic LGE images from bSSFP with the anatomical sh…

2019-08-14cs.CVeess.IV

基于视觉语言模型提示的无配对组织病理学虚拟染色的最优辅助方法

VLM-based Prompts as the Optimal Assistant for Unpaired Histopathology Virtual Staining

Fudan University（复旦大学）；Central South University（中南大学）；Harbin Institute of Technology（哈尔滨工业大学）；Chinese Academy of Sciences（中国科学院）

本研究首次将病理视觉语言大模型作为辅助工具，通过对比可学习提示和概念锚点，结合VLM约束的数据增强，实现无配对组织病理学虚拟染色，提升图像真实性和下游诊断精度。

2025-04-22cs.CVeess.IV

基于深度迁移学习的乳腺癌图像分类方法

Breast Cancer Image Classification Method Based on Deep Transfer Learning

The Hong Kong University of Science and Technology（香港科技大学）；University of Southampton（南安普顿大学）；Trine University（特莱恩大学）；Southwest Jiaotong University（西南交通大学）

针对乳腺癌病理图像分类的样本少、特征设计繁、准确率低问题，提出结合注意力机制与DenseNet结构、采用多级迁移学习的分类算法，测试集准确率超84.0%，优于现有模型，可用于医学乳腺癌检测。

2024-09-11cs.CVcs.LGeess.IV

AGMDT：基于邻接引导多域迁移的肾脏组织学图像虚拟染色

AGMDT: Virtual Staining of Renal Histology Images with Adjacency-Guided Multi-Domain Transfer

Peking University Third Hospital（北京大学第三医院）

本文提出AGMDT虚拟染色框架，通过肾小球检测与二分图匹配利用相邻多染色切片间的块级相关性，无需像素级对齐即可实现多域染色迁移，并在定量与形态学上优于现有方法。

2023-09-17cs.CVeess.IV

Virtual stain transfer in histology via cascaded deep neural networks

University of California, Los Angeles（加州大学洛杉矶分校）；California NanoSystems Institute (CNSI)（加州纳米系统研究所）；David Geffen School of Medicine（戴维·格芬医学院）

Pathological diagnosis relies on the visual inspection of histologically stained thin tissue specimens, where different types of stains are applied to bring contrast to and highlight various desired histological features. However, the destructive histochemical staining procedures are usually irreversible, making it very difficult to obtain multiple stains on the same tissue section. Here, we demonstrate a virtual stain transfer framework via a cascaded deep neural network (C-DNN) to digitally transform hematoxylin and eosin (H&E) stained tissue images into other types of histological stains. U…

2022-07-14cs.CVcs.LGeess.IV

通过随机图像质量迁移实现低场磁共振图像增强

Low-field magnetic resonance image enhancement via stochastic image quality transfer

Zhejiang Lab（之江实验室）；University College London（伦敦大学学院）；Great Ormond Street Hospital for Children（大奥蒙德街儿童医院）；University of Ibadan（伊巴丹大学）；Google DeepMind（谷歌DeepMind）

本文提出IQT框架，利用随机低场图像模拟器和各向异性U-Net从低场MRI预测高场图像，并通过仿真及多对比度临床数据验证其可提升分辨率、对比度与诊断价值。

2023-04-26cs.CVeess.IV