RESUMEN
BACKGROUND: Artificial intelligence (AI) systems for automated chest x-ray interpretation hold promise for standardising reporting and reducing delays in health systems with shortages of trained radiologists. Yet, there are few freely accessible AI systems trained on large datasets for practitioners to use with their own data with a view to accelerating clinical deployment of AI systems in radiology. We aimed to contribute an AI system for comprehensive chest x-ray abnormality detection. METHODS: In this retrospective cohort study, we developed open-source neural networks, X-Raydar and X-Raydar-NLP, for classifying common chest x-ray findings from images and their free-text reports. Our networks were developed using data from six UK hospitals from three National Health Service (NHS) Trusts (University Hospitals Coventry and Warwickshire NHS Trust, University Hospitals Birmingham NHS Foundation Trust, and University Hospitals Leicester NHS Trust) collectively contributing 2 513 546 chest x-ray studies taken from a 13-year period (2006-19), which yielded 1 940 508 usable free-text radiological reports written by the contemporary assessing radiologist (collectively referred to as the "historic reporters") and 1 896 034 frontal images. Chest x-rays were labelled using a taxonomy of 37 findings by a custom-trained natural language processing (NLP) algorithm, X-Raydar-NLP, from the original free-text reports. X-Raydar-NLP was trained on 23 230 manually annotated reports and tested on 4551 reports from all hospitals. 1 694 921 labelled images from the training set and 89 238 from the validation set were then used to train a multi-label image classifier. Our algorithms were evaluated on three retrospective datasets: a set of exams sampled randomly from the full NHS dataset reported during clinical practice and annotated using NLP (n=103 328); a consensus set sampled from all six hospitals annotated by three expert radiologists (two independent annotators for each image and a third consultant to facilitate disagreement resolution) under research conditions (n=1427); and an independent dataset, MIMIC-CXR, consisting of NLP-annotated exams (n=252 374). FINDINGS: X-Raydar achieved a mean AUC of 0·919 (SD 0·039) on the auto-labelled set, 0·864 (0·102) on the consensus set, and 0·842 (0·074) on the MIMIC-CXR test, demonstrating similar performance to the historic clinical radiologist reporters, as assessed on the consensus set, for multiple clinically important findings, including pneumothorax, parenchymal opacification, and parenchymal mass or nodules. On the consensus set, X-Raydar outperformed historical reporter balanced accuracy with significance on 27 of 37 findings, was non-inferior on nine, and inferior on one finding, resulting in an average improvement of 13·3% (SD 13·1) to 0·763 (0·110), including a mean 5·6% (13·2) improvement in critical findings to 0·826 (0·119). INTERPRETATION: Our study shows that automated classification of chest x-rays under a comprehensive taxonomy can achieve performance levels similar to those of historical reporters and exhibit robust generalisation to external data. The open-sourced neural networks can serve as foundation models for further research and are freely available to the research community. FUNDING: Wellcome Trust.
Asunto(s)
Inteligencia Artificial , Interpretación de Imagen Asistida por Computador , Redes Neurales de la Computación , Humanos , Estudios Retrospectivos , Rayos XRESUMEN
The National COVID-19 Chest Imaging Database (NCCID) is a centralized UK database of thoracic imaging and corresponding clinical data. It is made available by the National Health Service Artificial Intelligence (NHS AI) Lab to support the development of machine learning tools focused on Coronavirus Disease 2019 (COVID-19). A bespoke cleaning pipeline for NCCID, developed by the NHSx, was introduced in 2021. We present an extension to the original cleaning pipeline for the clinical data of the database. It has been adjusted to correct additional systematic inconsistencies in the raw data such as patient sex, oxygen levels and date values. The most important changes will be discussed in this paper, whilst the code and further explanations are made publicly available on GitLab. The suggested cleaning will allow global users to work with more consistent data for the development of machine learning tools without being an expert. In addition, it highlights some of the challenges when working with clinical multi-center data and includes recommendations for similar future initiatives.
Asunto(s)
COVID-19 , Tórax , Humanos , Inteligencia Artificial , Aprendizaje Automático , Medicina Estatal , Radiografía Torácica , Tórax/diagnóstico por imagenRESUMEN
Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.
RESUMEN
The erosional morphology preserved at the sea bed in the eastern English Channel dominantly records denudation of the continental shelf by fluvial processes over multiple glacial-interglacial sea-level cycles rather than by catastrophic flooding through the Straits of Dover during the mid-Quaternary. Here, through the integration of multibeam bathymetry and shallow sub-bottom 2D seismic reflection profiles calibrated with vibrocore records, the first stratigraphic model of erosion and deposition on the eastern English Channel continental shelf is presented. Published Optical Stimulated Luminescence (OSL) and 14C ages were used to chronometrically constrain the stratigraphy and allow correlation of the continental shelf record with major climatic/sea-level periods. Five major erosion surfaces overlain by discrete sediment packages have been identified. The continental shelf in the eastern English Channel preserves a record of processes operating from Marine Isotope Stage (MIS) 6 to MIS 1. Planar and channelised erosion surfaces were formed by fluvial incision during lowstands or relative sea-level fall. The depth and lateral extent of incision was partly conditioned by underlying geology (rock type and tectonic structure), climatic conditions and changes in water and sediment discharge coupled to ice sheet dynamics and the drainage configuration of major rivers in Northwest Europe. Evidence for major erosion during or prior to MIS 6 is preserved. Fluvial sediments of MIS 2 age were identified within the Northern Palaeovalley, providing insights into the scale of erosion by normal fluvial regimes. Seismic and sedimentary facies indicate that deposition predominantly occurred during transgression when accommodation was created in palaeovalleys to allow discrete sediment bodies to form. Sediment reworking over multiple sea-level cycles (Saalian-Eemian-early Weichselian) by fluvial, coastal and marine processes created a multi-lateral, multi-storey succession of palaeovalley-fills that are preserved as a strath terrace. The data presented here reveal a composite erosional and depositional record that has undergone a high degree of reworking over multiple sea-level cycles leading to the preferential preservation of sediments associated with the most recent glacial-interglacial period.