Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions

Yang, Nan; Ser, Javier Del; Walsh, Simon L.F.; Schönlieb, Carola-Bibiane; Roberts, Michael; Selby, Ian; Howard, Kit; Owen, John Mackenzie; Neville, Jon; Guiot, Julien; Ernst, Benoit; Pastor, Ana Belén; Alberich‐Bayarri, Ángel; Menzel, Marion I.; Walsh, Seán; Vos, Wim; Flerin, Nina; Charbonnier, Jean-Paul; Rikxoort, Eva M. van; Chatterjee, A.; Woodruff, Henry C.; Lambin, Philippe; Cerdá-Alberich, Leonor; Martí‐Bonmatí, Luis; Herrera, Francisco; Yang, Guang

doi:10.1016/j.inffus.2022.01.001

Cited by 85 publications

(44 citation statements)

References 168 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data provided include 50 training samples and the corresponding prostate masks and 30 test samples. Also, in the future, when facing the multicenter prostate cancer MRI data fusion problem, it is necessary to consider the problem of certain disparity in imaging results due to scanner, parameters, and environment ( Nan et al, 2022 ). In addition, it is possible to use a deep learning-based approach to construct scanner image invariant encoding based on the existing methods ( Moyer et al, 2020 ).…”

Section: Discussionmentioning

confidence: 99%

Computer-aided diagnosis of prostate cancer based on deep neural networks from multi-parametric magnetic resonance imaging

et al. 2022

Front. Physiol.

View full text Add to dashboard Cite

Objectives: To evaluate a new deep neural network (DNN)–based computer-aided diagnosis (CAD) method, namely, a prostate cancer localization network and an integrated multi-modal classification network, to automatically localize prostate cancer on multi-parametric magnetic resonance imaging (mp-MRI) and classify prostate cancer and non-cancerous tissues.Materials and methods: The PROSTAREx database consists of a “training set” (330 suspected lesions from 204 cases) and a “test set” (208 suspected lesions from 104 cases). Sequences include T2-weighted, diffusion-weighted, Ktrans, and apparent diffusion coefficient (ADC) images. For the task of abnormal localization, inspired by V-net, we designed a prostate cancer localization network with mp-MRI data as input to achieve automatic localization of prostate cancer. Combining the concepts of multi-modal learning and ensemble learning, the integrated multi-modal classification network is based on the combination of mp-MRI data as input to distinguish prostate cancer from non-cancerous tissues through a series of operations such as convolution and pooling. The performance of each network in predicting prostate cancer was examined using the receiver operating curve (ROC), and the area under the ROC curve (AUC), sensitivity (TPR), specificity (TNR), accuracy, and Dice similarity coefficient (DSC) were calculated.Results: The prostate cancer localization network exhibited excellent performance in localizing prostate cancer, with an average error of only 1.64 mm compared to the labeled results, an error of about 6%. On the test dataset, the network had a sensitivity of 0.92, specificity of 0.90, PPV of 0.91, NPV of 0.93, and DSC of 0.84. Compared with multi-modal classification networks, the performance of single-modal classification networks is slightly inadequate. The integrated multi-modal classification network performed best in classifying prostate cancer and non-cancerous tissues with a TPR of 0.95, TNR of 0.82, F1-Score of 0.8920, AUC of 0.912, and accuracy of 0.885, which fully confirmed the feasibility of the ensemble learning approach.Conclusion: The proposed DNN-based prostate cancer localization network and integrated multi-modal classification network yielded high performance in experiments, demonstrating that the prostate cancer localization network and integrated multi-modal classification network can be used for computer-aided diagnosis (CAD) of prostate cancer localization and classification.

show abstract

Section: Discussionmentioning

confidence: 99%

Computer-aided diagnosis of prostate cancer based on deep neural networks from multi-parametric magnetic resonance imaging

et al. 2022

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…Researchers should focus more on explainable AI solutions [134]. This could be achieved by sensitivity analysis [135], gradient-based methods [136], and data harmonisation strategies for multi-center studies [137].…”

Section: Discussionmentioning

confidence: 99%

Human Treelike Tubular Structure Segmentation: A Comprehensive Review and Future Perspectives

Li¹,

Tang²,

Yang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Various structures in human physiology follow a treelike morphology, which often expresses complexity at very fine scales. Examples of such structures are intrathoracic airways, retinal blood vessels, and hepatic blood vessels. Large collections of 2D and 3D images have been made available by medical imaging modalities such as magnetic resonance imaging (MRI), computed tomography (CT), Optical coherence tomography (OCT) and ultrasound in which the spatial arrangement can be observed. Segmentation of these structures in medical imaging is of great importance since the analysis of the structure provides insights into disease diagnosis, treatment planning, and prognosis. Manually labelling extensive data by radiologists is often time-consuming and error-prone. As a result, automated or semi-automated computational models have become a popular research field of medical imaging in the past two decades, and many have been developed to date. In this survey, we aim to provide a comprehensive review of currently publicly available datasets, segmentation algorithms, and evaluation metrics. In addition, current challenges and future research directions are discussed.

show abstract

“…In this scope, a number of existing harmonisation methods exist [50]. As far as DICOM metadata, curation workflows have been defined for all DICOM-defined objects.…”

Section: Data Harmonisationmentioning

confidence: 99%

Position of the AI for Health Imaging (AI4HI) network on metadata models for imaging biobanks

et al. 2022

Self Cite

View full text Add to dashboard Cite

A huge amount of imaging data is becoming available worldwide and an incredible range of possible improvements can be provided by artificial intelligence algorithms in clinical care for diagnosis and decision support. In this context, it has become essential to properly manage and handle these medical images and to define which metadata have to be considered, in order for the images to provide their full potential. Metadata are additional data associated with the images, which provide a complete description of the image acquisition, curation, analysis, and of the relevant clinical variables associated with the images. Currently, several data models are available to describe one or more subcategories of metadata, but a unique, common, and standard data model capable of fully representing the heterogeneity of medical metadata has not been yet developed. This paper reports the state of the art on metadata models for medical imaging, the current limitations and further developments, and describes the strategy adopted by the Horizon 2020 “AI for Health Imaging” projects, which are all dedicated to the creation of imaging biobanks.

show abstract

Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions

Cited by 85 publications

References 168 publications

Computer-aided diagnosis of prostate cancer based on deep neural networks from multi-parametric magnetic resonance imaging

Computer-aided diagnosis of prostate cancer based on deep neural networks from multi-parametric magnetic resonance imaging

Human Treelike Tubular Structure Segmentation: A Comprehensive Review and Future Perspectives

Position of the AI for Health Imaging (AI4HI) network on metadata models for imaging biobanks

Contact Info

Product

Resources

About