Fontanella Alessandro, Li Wenwen, Mair Grant, Antoniou Antreas, Platt Eleanor, Armitage Paul, Trucco Emanuele, Wardlaw Joanna M, Storkey Amos
The University of Edinburgh School of Informatics, Edinburgh, UK
The University of Edinburgh Centre for Clinical Brain Sciences, Edinburgh, UK.
Stroke Vasc Neurol. 2025 Aug 26;10(4):499-507. doi: 10.1136/svn-2024-003372.
CT is commonly used to image patients with ischaemic stroke but radiologist interpretation may be delayed. Machine learning techniques can provide rapid automated CT assessment but are usually developed from annotated images which necessarily limits the size and representation of development data sets. We aimed to develop a deep learning (DL) method using CT brain scans that were labelled but not annotated for the presence of ischaemic lesions.
We designed a convolutional neural network-based DL algorithm to detect ischaemic lesions on CT. Our algorithm was trained using routinely acquired CT brain scans collected for a large multicentre international trial. These scans had previously been labelled by experts for acute and chronic appearances. We explored the impact of ischaemic lesion features, background brain appearances and timing of CT (baseline or 24-48 hour follow-up) on DL performance.
From 5772 CT scans of 2347 patients (median age 82), 54% had visible ischaemic lesions according to experts. Our DL method achieved 72% accuracy in detecting ischaemic lesions. Detection was better for larger (80% accuracy) or multiple (87% accuracy for two, 100% for three or more) lesions and with follow-up scans (76% accuracy vs 67% at baseline). Chronic brain conditions reduced accuracy, particularly non-stroke lesions and old stroke lesions (32% and 31% error rates, respectively).
DL methods can be designed for ischaemic lesion detection on CT using the vast quantities of routinely collected brain scans without the need for lesion annotation. Ultimately, this should lead to more robust and widely applicable methods.
CT常用于对缺血性中风患者进行成像，但放射科医生的解读可能会延迟。机器学习技术可以提供快速的CT自动评估，但通常是从带注释的图像中开发的，这必然限制了开发数据集的大小和代表性。我们旨在使用标记但未标注缺血性病变的脑部CT扫描开发一种深度学习（DL）方法。
我们设计了一种基于卷积神经网络的DL算法来检测CT上的缺血性病变。我们的算法使用为一项大型多中心国际试验收集的常规脑部CT扫描进行训练。这些扫描先前已由专家标记为急性和慢性表现。我们探讨了缺血性病变特征、背景脑表现和CT时间（基线或24 - 48小时随访）对DL性能的影响。
在2347例患者（中位年龄82岁）的5772次CT扫描中，根据专家判断，54%有可见的缺血性病变。我们的DL方法在检测缺血性病变方面的准确率达到72%。对于较大的病变（准确率80%）或多个病变（两个病变时准确率87%，三个或更多病变时准确率100%）以及随访扫描（准确率76%，基线时为67%），检测效果更好。慢性脑部疾病会降低准确率，尤其是非中风病变和陈旧性中风病变（错误率分别为32%和31%）。
DL方法可通过大量常规收集的脑部扫描设计用于CT上缺血性病变的检测，而无需病变标注。最终，这应会带来更强大且广泛适用的方法。
