Abstract
AbstractAlgorithms that can classify hyper-scale multi-modal datasets, comprising of millions of images, into constituent modality types can help researchers quickly retrieve and classify diagnostic imaging data, accelerating clinical outcomes. This research aims to demonstrate that a deep neural network that is trained on a hyper-scale dataset (4.5 million images) composed of heterogeneous multi-modal data, can be used to obtain significant modality classification accuracy (96%). By combining 102 medical imaging datasets, a dataset of 4.5 million images was created. A ResNet-50, ResNet-18 and VGG16 were trained to classify these images by the imaging modality used to capture them (Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), and X-ray) across many body locations. The classification accuracy of the models was then tested on unseen data.The best performing model achieved classification accuracy of 96% on unseen data. The model achieved a balanced accuracy of 86%.This research shows it is possible to train Deep Learning (DL) Convolutional Neural Networks (CNNs) with hyper-scale multimodal data-sets, composed of millions of images. The trained model can be used to classify images by modality, with the best performing model achieving a classification accuracy of 96%. Such models can find use in real-world applications with volumes of image data in the hyper-scale range, such as medical imaging repositories, or national healthcare institutions. Further research can expand this classification capability to include 3D-scans.
Publisher
Cold Spring Harbor Laboratory
Reference116 articles.
1. Hafizović, L. , Č aušević, A. , Deumić, A. , Bećirović, L. S. , Pokvić, L. G. , and Badnjević, A. , “The use of artificial intelligence in diagnostic medical imaging: Systematic literature review,” in [2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)], 1–6, IEEE (2021).
2. A new contrast based multimodal medical image fusion framework;Neurocomputing,2015
3. Developing intelligent medical image modality classification system using deep transfer learning and lda;Scientific reports,2020
4. Deep learning and process understanding for data-driven Earth system science
5. Machine learning for the study of plankton and marine snow from images;Ann. Rev. Mar. Sci,2022
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献