Automatic quality control of brain T1-weighted magnetic resonance images for a clinical data warehouse

Bottani, Simona; Burgos, Ninon; Maire, Aurélien; Wild, Adam; Ströer, Sébastian; Dormont, Didier; Colliot, Olivier

doi:10.1016/j.media.2021.102219

Cited by 28 publications

(57 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the same dataset as in our previous study, where we randomly selected 5500 images that were acquired on various scanners (Siemens, GE, Philips and Toshiba). 4 Motion artefacts were manually annotated as a three-grade level by two annotators. A score of (0) was given when no motion was seen, ( 1) when the structures of the brain were distinguishable despite the presence of motion and (2) when the structures were difficult to distinguish.…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…To classify motion artefacts, we implemented a CNN composed of five convolutional blocks and three fully connected layers (denoted as Conv5FC3) that proved successful in our previous work. 4 Each convolutional block is made of a convolutional layer, a batch normalisation layer, a ReLU activation function and a max pooling layer. We used the ADAM optimiser, the weighted binary cross-entropy loss and a batch size of 16.…”

Section: Proposed Approachmentioning

confidence: 99%

“…While we obtained good results for the classification of images which are not proper 3D T1w brain MRI and for recognising low quality images, we encountered difficulties in detecting motion in the images. 4 MRIs are sensitive to motion induced by patient movement during the acquisition process. As they require a long acquisition time, subjects are more likely to move during the examination, which causes artefacts (blurring, ringing, ghosting or signal loss) in the reconstructed image.…”

Section: Introductionmentioning

confidence: 99%

“…5 Previously, we found that 25% of MRIs in the CDW were totally unusable, and almost a third had a very low quality especially due to motion. 4 A study conducted in a single hospital showed that the prevalence of repeating an MRI examination due to the presence of motion was up to 20% of all the acquisitions. 6 Beyond the cost that this represents for hospitals, these studies are highlighting the fact that many images present in the PACS are corrupted by motion.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Transfer learning from synthetic to routine clinical data for motion artefact detection in brain T1-weighted MRI

Loizillon

Bottani

Maire³

et al. 2023

Medical Imaging 2023: Image Processing

Self Cite

View full text Add to dashboard Cite

Clinical data warehouses (CDWs) contain the medical data of millions of patients and represent a great opportunity to develop computational tools. MRIs are particularly sensitive to patient movements during image acquisition, which will result in artefacts (blurring, ghosting and ringing) in the reconstructed image. As a result, a significant number of MRIs in CDWs are unusable because corrupted by these artefacts. Since their manual detection is impossible due to the number of scans, it is necessary to develop a tool to automatically exclude images with motion in order to fully exploit CDWs. In this paper, we propose a CNN for the automatic detection of motion in 3D T1-weighted brain MRI. Our transfer learning approach, based on synthetic motion generation, consists of two steps: a pre-training on research data using synthetic motion, followed by a fine-tuning step to generalise our pre-trained model to clinical data, relying on the manual labelling of 5500 images. The objectives were both (1) to be able to exclude images with severe motion, (2) to detect mild motion artefacts. Our approach achieved excellent accuracy for the first objective with a balanced accuracy nearly similar to that of the annotators (balanced accuracy>80%). However, for the second objective, the performance was weaker and substantially lower than that of human raters. Overall, our framework will be useful to take advantage of CDWs in medical imaging and to highlight the importance of a clinical validation of models trained on research data.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Proposed Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Transfer learning from synthetic to routine clinical data for motion artefact detection in brain T1-weighted MRI

Loizillon

Bottani

Maire³

et al. 2023

Medical Imaging 2023: Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…They are based on training supervised models that require both high and low-quality images and predict the quality scores using a set of scored images labelled by experts. For example, [Bottani et al, 2021] developed a supervised method based on CNN to compute quality scores. To train and validate the model, they asked trained raters to annotate the images following a visual pre-defined QC protocol.…”

Section: Supervised -Image-level Classificationmentioning

confidence: 99%

An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training

Ravì¹,

Barkhof²,

Alexander³

et al. 2022

Preprint

View full text Add to dashboard Cite

Large medical imaging data sets are becoming increasingly available. A common challenge in these data sets is to ensure that each sample meets minimum quality requirements devoid of significant artefacts. Despite a wide range of existing automatic methods having been developed to identify imperfections and artefacts in medical imaging, they mostly rely on data-hungry methods. In particular, the lack of sufficient scans with artefacts available for training has created a barrier in designing and deploying machine learning in clinical research. To tackle this problem, we propose a novel framework having four main components: (1) a set of artefact generators inspired by magnetic resonance physics to corrupt brain MRI scans and augment a training dataset, (2) a set of abstract and engineered features to represent images compactly, (3) a feature selection process that depends on the class of artefact to improve classification performance, and (4) a set of Support Vector Machine (SVM) classifiers trained to identify artefacts. Our novel contributions are threefold: first, we use the novel physics-based artefact generators to generate synthetic brain MRI scans with controlled artefacts as a data augmentation technique. This will avoid the labour-intensive collection and labelling process of scans with rare artefacts. Second, we propose a large pool of abstract and engineered image features developed to identify 9 different artefacts for structural MRI. Finally, we use an artefact-based feature selection block that, for each class of artefacts, finds the set of features that provide the best classification performance. We performed validation experiments on a large data set of scans with artificially-generated artefacts, and in a multiple sclerosis clinical trial where real artefacts were identified by experts, showing that the proposed pipeline outperforms traditional methods. In particular, our data augmentation increases performance by up to 12.5 percentage points on the accuracy, F1, F2, precision and recall. At the same time, the computation cost of our pipeline remains low -less than a second to process a single scan-with potential for real-time deployment. Our artefact simulators obtained using adversarial learning enable the training of a quality control system for brain MRI that otherwise would have required a much larger number of scans in both supervised and unsupervised settings. We believe that systems for quality control will enable a wide range of high throughput clinical applications based on the use of automatic image-processing pipelines.

show abstract

Reproducibility in Machine Learning for Medical Imaging

2023

View full text Add to dashboard Cite

Reproducibility is a cornerstone of science, as the replication of findings is the process through which they become knowledge. It is widely considered that many fields of science are undergoing a reproducibility crisis. This has led to the publications of various guidelines in order to improve research reproducibility.This didactic chapter intends at being an introduction to reproducibility for researchers in the field of machine learning for medical imaging. We first distinguish between different types of reproducibility. For each of them, we aim at defining it, at describing the requirements to achieve it, and at discussing its utility. The chapter ends with a discussion on the benefits of reproducibility and with a plea for a nondogmatic approach to this concept and its implementation in research practice.

show abstract

Automatic quality control of brain T1-weighted magnetic resonance images for a clinical data warehouse

Cited by 28 publications

References 52 publications

Transfer learning from synthetic to routine clinical data for motion artefact detection in brain T1-weighted MRI

Transfer learning from synthetic to routine clinical data for motion artefact detection in brain T1-weighted MRI

An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training

Reproducibility in Machine Learning for Medical Imaging

Contact Info

Product

Resources

About