Graph Convolutional Neural Networks for Medical Image Analysis

用于医学图像分析的图卷积神经网络

• 批准号: 2270805
• 金额: --
• 依托单位: Heriot-Watt University
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2019
• 资助国家: 英国
• 起止时间: 2019 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2270805
• 关键词: Graph; Convolutional; Neural; Networks; Medical

Deep Learning-based Artificial Intelligence, in particular Convolutional Neural Networks (CNNs), has seen exponential growth in many pattern recognition challenges since the early 2010s. While CNNs were originally developed to act on data defined on regular cartesian grids, such as images, audio, and text data, they have recently been extended to work on irregularly connected data, such as graphs. This opens the door to a whole new set of potential applications where graphs arise, either naturally (e.g. surface or volumetric meshes representing shapes) or as a useful intermediate representation (e.g. superpixels representing a medical image). The project will apply graph CNNs to medical image analysis. For example, to identify and outline (segment) a specific structure of interest in a medical image. This is useful in many clinical areas, including cancer (e.g. tumour segmentation to determine treatment effect), neurodegenerative disorders (e.g. parcellation to detect early dementia), cardiovascular diseases (e.g. quantifying coronary artery disease), and musculoskeletal problems.

自2010年代初以来，基于深度学习的人工智能，特别是卷积神经网络（CNN），在许多模式识别挑战中呈指数级增长。虽然CNN最初被开发用于处理在规则网格上定义的数据，例如图像，音频和文本数据，但它们最近已扩展到处理不规则连接的数据，例如图形。这为一系列全新的潜在应用打开了大门，在这些应用中，图形可以自然地出现（例如，表示形状的表面或体积网格），也可以作为有用的中间表示（例如，表示医学图像的超像素）。该项目将把图CNN应用于医学图像分析。例如，为了识别和勾画（分割）医学图像中的特定感兴趣结构。这在许多临床领域中是有用的，包括癌症（例如肿瘤分割以确定治疗效果）、神经退行性疾病（例如包裹以检测早期痴呆）、心血管疾病（例如量化冠状动脉疾病）和肌肉骨骼问题。

项目成果

Segmentation of Skin Lesions by Superpixel Classification with Graph-Context CNN

使用图上下文 CNN 进行超像素分类来分割皮肤病变

• 发表时间: 2021
• 作者: Angel Victor Juanco Muller

Head and Neck Tumor Segmentation and Outcome Prediction

头颈肿瘤分割和结果预测

• 发表时间: 2023
• 作者: Ángel Víctor Juanco-Müller

The topology-overlap trade-off in retinal arteriole-venule segmentation

• DOI: 10.1117/12.2654014
• 发表时间: 2023-03
• 期刊: American journal of infection control
• 影响因子: 4.9
• 作者: Ángel Víctor Juanco-Müller;J. Mota;K. Goatman;C. Hoogendoorn

Head and Neck Tumor Segmentation and Outcome Prediction - Second Challenge, HECKTOR 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings

头颈肿瘤分割和结果预测 - 第二次挑战赛，HECKTOR 2021，与 MICCAI 2021 同期举行，法国斯特拉斯堡，2021 年 9 月 27 日，会议记录

• DOI: 10.1007/978-3-030-98253-9_24
• 发表时间: 2022
• 作者: Juanco-Müller Á