ArtifactID: Identifying artifacts in low-field MRI of the brain using deep learning

A Technologist's Vigilance: Identifying and Correcting a Cotton Ball-Induced MRI Artefact to Prevent Misdiagnosis in Pediatric Patients

Wrap-around artefacts in magnetic resonance imaging (MRI) are common, typically caused by anatomical structures outside the Field of View (FOV) overlapping into the imaging area. This paper reports a rare source of wrap-around artifact, a wet cotton ball, whose image was inadvertently included in cranial imaging, potentially leading to misdiagnosis as pathological conditions such as otomastoiditis, postoperative changes, or intracranial hemorrhage. Hence, there is a need to enhance MRI technologists' awareness of such artifacts. We analyzed four consecutive cases of cranial MRI scans with similar artifacts, all located on the right side of the brain but in different regions. On axial T2-weighted images (T2WI) and T2 fluid-attenuated inversion recovery (T2FLAIR) sequences, the artifacts appeared as oval-shaped, relatively well-defined heterogeneous high signals. On axial T1-weighted images (T1WI), signal intensity and border clarity varied, with artifact locations slightly more lateral compared to T2WI and T2FLAIR. The artifacts in the first three cases were not identified by the MRI technologists. However, in the fourth case, a patient with head trauma, the MRI technologist noticed inconsistencies in the artifact characteristics across different sequences, as well as similarities to a previous case of cranial trauma, which raised suspicion of an artifact. Systematic image analysis and equipment inspection subsequently revealed a wet cotton ball attached to the outer surface of the head-and-neck coil, inadvertently left there by a radiology nurse during preparation for a previous case. Upon removal of the cotton ball and rescanning the sequences with artifacts in cases 3 and 4, the artifacts disappeared, confirming the wet cotton ball as the source. Additionally, upon review, similar artifacts were found in the first two cases but overlooked due to various reasons. The aim of this study is to improve MRI technologists' recognition of artifacts caused by non-metallic foreign objects, avoiding misdiagnosis, and to prompt us to refine our examination protocols and enhance radiology nurses' awareness of MRI safety.

Deep Learning-Enabled Automated Quality Control for Liver MR Elastography: Initial Results

BACKGROUND

Several factors can impair image quality and reliability of liver magnetic resonance elastography (MRE), such as inadequate driver positioning, insufficient wave propagation and patient-related factors.

PURPOSE

To report initial results on automatic classification of liver MRE image quality using various deep learning (DL) architectures.

STUDY TYPE

Retrospective, single center, IRB-approved human study.

POPULATION

Ninety patients (male = 51, mean age 52.8 ± 14.1 years).

FIELD STRENGTHS/SEQUENCES

1.5 T and 3 T MRI, 2D GRE, and 2D SE-EPI.

ASSESSMENT

The curated dataset was comprised of 914 slices obtained from 149 MRE exams in 90 patients. Two independent observers examined the confidence map overlaid elastograms (CMOEs) for liver stiffness measurement and assigned a quality score (non-diagnostic vs. diagnostic) for each slice. Several DL architectures (ResNet18, ResNet34, ResNet50, SqueezeNet, and MobileNetV2) for binary quality classification of individual CMOE slice inputs were evaluated, using an 8-fold stratified cross-validation (800 slices) and a test dataset (114 slices). A majority vote ensemble combining the models' predictions of the highest-performing architecture was evaluated.

STATISTICAL TEST

The inter-observer agreement and the agreement between DL models and one observer were assessed using Cohen's unweighted Kappa coefficient. Accuracy, precision, and recall of the cross-validation and the ensemble were calculated for the test dataset.

RESULTS

The average accuracy across the eight models trained using each architecture ranged from 0.692 to 0.851 for the test dataset. The ensemble of the best performing architecture (SqueezeNet) yielded an accuracy of 0.921. The inter-observer agreement was excellent (Kappa 0.896 [95% CI 0.845-0.947]). The agreement between observer 1 and the predictions of each SqueezeNet model was slight to almost perfect (Kappa range: 0.197-0.831) and almost perfect for the ensemble (Kappa: 0.833).

CONCLUSION

Our initial study demonstrates an automated DL-based approach for classifying liver 2D MRE diagnostic quality with an average accuracy of 0.851 (range 0.675-0.921) across the SqueezeNet models.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 1.

Automated detection of motion artifacts in brain MR images using deep learning

Quality assessment, including inspecting the images for artifacts, is a critical step during magnetic resonance imaging (MRI) data acquisition to ensure data quality and downstream analysis or interpretation success. This study demonstrates a deep learning (DL) model to detect rigid motion in T1-weighted brain images. We leveraged a 2D convolutional neural network (CNN) trained on motion-synthesized data for three-class classification and tested it on publicly available retrospective and prospective datasets. Grad-CAM heatmaps enabled the identification of failure modes and provided an interpretation of the model's results. The model achieved average precision and recall metrics of 85% and 80% on six motion-simulated retrospective datasets. Additionally, the model's classifications on the prospective dataset showed 93% agreement with the labeling of a radiologist a strong inverse correlation (-0.84) compared to average edge strength, an image quality metric indicative of motion. This model is aimed at inline automatic detection of motion artifacts, accelerating part of the time-consuming quality assessment (QA) process and augmenting expertise on-site, particularly relevant in low-resource settings where local MR knowledge is scarce.

Inline automatic quality control of 2D phase-contrast flow MRI for subject-specific scan time adaptation

PURPOSE

To develop an inline automatic quality control to achieve consistent diagnostic image quality with subject-specific scan time, and to demonstrate this method for 2D phase-contrast flow MRI to reach a predetermined SNR.

METHODS

We designed a closed-loop feedback framework between image reconstruction and data acquisition to intermittently check SNR (every 20 s) and automatically stop the acquisition when a target SNR is achieved. A free-breathing 2D pseudo-golden-angle spiral phase-contrast sequence was modified to listen for image-quality messages from the reconstructions. Ten healthy volunteers and 1 patient were imaged at 0.55 T. Target SNR was selected based on retrospective analysis of cardiac output error, and performance of the automatic SNR-driven "stop" was assessed inline.

RESULTS

SNR calculation and automated segmentation was feasible within 20 s with inline deployment. The SNR-driven acquisition time was 2 min 39 s ± 67 s (aorta) and 3 min ± 80 s (main pulmonary artery) with a min/max acquisition time of 1 min 43 s/4 min 52 s (aorta) and 1 min 43 s/5 min 50 s (main pulmonary artery) across 6 healthy volunteers, while ensuring a diagnostic measurement with relative absolute error in quantitative flow measurement lower than 2.1% (aorta) and 6.3% (main pulmonary artery).

CONCLUSION

The inline quality control enables subject-specific optimized scan times while ensuring consistent diagnostic image quality. The distribution of automated stopping times across the population revealed the value of a subject-specific scan time.

Bringing MRI to low- and middle-income countries: Directions, challenges and potential solutions

The global disparity of magnetic resonance imaging (MRI) is a major challenge, with many low- and middle-income countries (LMICs) experiencing limited access to MRI. The reasons for limited access are technological, economic and social. With the advancement of MRI technology, we explore why these challenges still prevail, highlighting the importance of MRI as the epidemiology of disease changes in LMICs. In this paper, we establish a framework to develop MRI with these challenges in mind and discuss the different aspects of MRI development, including maximising image quality using cost-effective components, integrating local technology and infrastructure and implementing sustainable practices. We also highlight the current solutions-including teleradiology, artificial intelligence and doctor and patient education strategies-and how these might be further improved to achieve greater access to MRI.

Towards a unified approach for unsupervised brain MRI Motion Artefact Detection with few shot Anomaly Detection

Automated Motion Artefact Detection (MAD) in Magnetic Resonance Imaging (MRI) is a field of study that aims to automatically flag motion artefacts in order to prevent the requirement for a repeat scan. In this paper, we identify and tackle the three current challenges in the field of automated MAD; (1) reliance on fully-supervised training, meaning they require specific examples of Motion Artefacts (MA), (2) inconsistent use of benchmark datasets across different works and use of private datasets for testing and training of newly proposed MAD techniques and (3) a lack of sufficiently large datasets for MRI MAD. To address these challenges, we demonstrate how MAs can be identified by formulating the problem as an unsupervised Anomaly Detection (AD) task. We compare the performance of three State-of-the-Art AD algorithms DeepSVDD, Interpolated Gaussian Descriptor and FewSOME on two open-source Brain MRI datasets on the task of MAD and MA severity classification, with FewSOME achieving a MAD AUC >90% on both datasets and a Spearman Rank Correlation Coefficient of 0.8 on the task of MA severity classification. These models are trained in the few shot setting, meaning large Brain MRI datasets are not required to build robust MAD algorithms. This work also sets a standard protocol for testing MAD algorithms on open-source benchmark datasets. In addition to addressing these challenges, we demonstrate how our proposed 'anomaly-aware' scoring function improves FewSOME's MAD performance in the setting where one and two shots of the anomalous class are available for training. Code available at https://github.com/niamhbelton/Unsupervised-Brain-MRI-Motion-Artefact-Detection/.

Developing and deploying deep learning models in brain magnetic resonance imaging: A review

Magnetic resonance imaging (MRI) of the brain has benefited from deep learning (DL) to alleviate the burden on radiologists and MR technologists, and improve throughput. The easy accessibility of DL tools has resulted in a rapid increase of DL models and subsequent peer-reviewed publications. However, the rate of deployment in clinical settings is low. Therefore, this review attempts to bring together the ideas from data collection to deployment in the clinic, building on the guidelines and principles that accreditation agencies have espoused. We introduce the need for and the role of DL to deliver accessible MRI. This is followed by a brief review of DL examples in the context of neuropathologies. Based on these studies and others, we collate the prerequisites to develop and deploy DL models for brain MRI. We then delve into the guiding principles to develop good machine learning practices in the context of neuroimaging, with a focus on explainability. A checklist based on the United States Food and Drug Administration's good machine learning practices is provided as a summary of these guidelines. Finally, we review the current challenges and future opportunities in DL for brain MRI.

Detection of Intracerebral Hemorrhage Using Low-Field, Portable Magnetic Resonance Imaging in Patients With Stroke

BACKGROUND

Neuroimaging is essential for detecting spontaneous, nontraumatic intracerebral hemorrhage (ICH). Recent data suggest ICH can be characterized using low-field magnetic resonance imaging (MRI). Our primary objective was to investigate the sensitivity and specificity of ICH on a 0.064T portable MRI (pMRI) scanner using a methodology that provided clinical information to inform rater interpretations. As a secondary aim, we investigated whether the incorporation of a deep learning (DL) reconstruction algorithm affected ICH detection.

METHODS

The pMRI device was deployed at Yale New Haven Hospital to examine patients presenting with stroke symptoms from October 26, 2020 to February 21, 2022. Three raters independently evaluated pMRI examinations. Raters were provided the images alongside the patient's clinical information to simulate real-world context of use. Ground truth was the closest conventional computed tomography or 1.5/3T MRI. Sensitivity and specificity results were grouped by DL and non-DL software to investigate the effects of software advances.

RESULTS

A total of 189 exams (38 ICH, 89 acute ischemic stroke, 8 subarachnoid hemorrhage, 3 primary intraventricular hemorrhage, 51 no intracranial abnormality) were evaluated. Exams were correctly classified as positive or negative for ICH in 185 of 189 cases (97.9% overall accuracy). ICH was correctly detected in 35 of 38 cases (92.1% sensitivity). Ischemic stroke and no intracranial abnormality cases were correctly identified as blood-negative in 139 of 140 cases (99.3% specificity). Non-DL scans had a sensitivity and specificity for ICH of 77.8% and 97.1%, respectively. DL scans had a sensitivity and specificity for ICH of 96.6% and 99.3%, respectively.

CONCLUSIONS

These results demonstrate improvements in ICH detection accuracy on pMRI that may be attributed to the integration of clinical information in rater review and the incorporation of a DL-based algorithm. The use of pMRI holds promise in providing diagnostic neuroimaging for patients with ICH.

Should artificial intelligence be used in conjunction with Neuroimaging in the diagnosis of Alzheimer's disease?

Alzheimer's disease (AD) is a progressive, neurodegenerative disorder that affects memory, thinking, behavior, and other cognitive functions. Although there is no cure, detecting AD early is important for the development of a therapeutic plan and a care plan that may preserve cognitive function and prevent irreversible damage. Neuroimaging, such as magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET), has served as a critical tool in establishing diagnostic indicators of AD during the preclinical stage. However, as neuroimaging technology quickly advances, there is a challenge in analyzing and interpreting vast amounts of brain imaging data. Given these limitations, there is great interest in using artificial Intelligence (AI) to assist in this process. AI introduces limitless possibilities in the future diagnosis of AD, yet there is still resistance from the healthcare community to incorporate AI in the clinical setting. The goal of this review is to answer the question of whether AI should be used in conjunction with neuroimaging in the diagnosis of AD. To answer the question, the possible benefits and disadvantages of AI are discussed. The main advantages of AI are its potential to improve diagnostic accuracy, improve the efficiency in analyzing radiographic data, reduce physician burnout, and advance precision medicine. The disadvantages include generalization and data shortage, lack of in vivo gold standard, skepticism in the medical community, potential for physician bias, and concerns over patient information, privacy, and safety. Although the challenges present fundamental concerns and must be addressed when the time comes, it would be unethical not to use AI if it can improve patient health and outcome.

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Artificial Intelligence (AI) techniques of deep learning have revolutionized the disease diagnosis with their outstanding image classification performance. In spite of the outstanding results, the widespread adoption of these techniques in clinical practice is still taking place at a moderate pace. One of the major hindrance is that a trained Deep Neural Networks (DNN) model provides a prediction, but questions about why and how that prediction was made remain unanswered. This linkage is of utmost importance for the regulated healthcare domain to increase the trust in the automated diagnosis system by the practitioners, patients and other stakeholders. The application of deep learning for medical imaging has to be interpreted with caution due to the health and safety concerns similar to blame attribution in the case of an accident involving autonomous cars. The consequences of both a false positive and false negative cases are far reaching for patients' welfare and cannot be ignored. This is exacerbated by the fact that the state-of-the-art deep learning algorithms comprise of complex interconnected structures, millions of parameters, and a 'black box' nature, offering little understanding of their inner working unlike the traditional machine learning algorithms. Explainable AI (XAI) techniques help to understand model predictions which help develop trust in the system, accelerate the disease diagnosis, and meet adherence to regulatory requirements. This survey provides a comprehensive review of the promising field of XAI for biomedical imaging diagnostics. We also provide a categorization of the XAI techniques, discuss the open challenges, and provide future directions for XAI which would be of interest to clinicians, regulators and model developers.

Superconducting magnet designs and MRI accessibility: A review

Presently, magnetic resonance imaging (MRI) magnets must deliver excellent magnetic field (B₀ ) uniformity to achieve optimum image quality. Long magnets can satisfy the homogeneity requirements but require considerable superconducting material. These designs result in large, heavy, and costly systems that aggravate as field strength increases. Furthermore, the tight temperature tolerance of niobium titanium magnets adds instability to the system and requires operation at liquid helium temperature. These issues are crucial factors in the disparity of MR density and field strength use across the globe. Low-income settings show reduced access to MRI, especially to high field strengths. This article summarizes the proposed modifications to MRI superconducting magnet design and their impact on accessibility, including compact, reduced liquid helium, and specialty systems. Reducing the amount of superconductor inevitably entails shrinking the magnet size, resulting in higher field inhomogeneity. This work also reviews the state-of-the-art imaging and reconstruction methods to overcome this issue. Finally, we summarize the current and future challenges and opportunities in the design of accessible MRI.

Low-field MRI: Clinical promise and challenges

Modern MRI scanners have trended toward higher field strengths to maximize signal and resolution while minimizing scan time. However, high-field devices remain expensive to install and operate, making them scarce outside of high-income countries and major population centers. Low-field strength scanners have drawn renewed academic, industry, and philanthropic interest due to advantages that could dramatically increase imaging access, including lower cost and portability. Nevertheless, low-field MRI still faces inherent limitations in image quality that come with decreased signal. In this article, we review advantages and disadvantages of low-field MRI scanners, describe hardware and software innovations that accentuate advantages and mitigate disadvantages, and consider clinical applications for a new generation of low-field devices. In our review, we explore how these devices are being or could be used for high acuity brain imaging, outpatient neuroimaging, MRI-guided procedures, pediatric imaging, and musculoskeletal imaging. Challenges for their successful clinical translation include selecting and validating appropriate use cases, integrating with standards of care in high resource settings, expanding options with actionable information in low resource settings, and facilitating health care providers and clinical practice in new ways. By embracing both the promise and challenges of low-field MRI, clinicians and researchers have an opportunity to transform medical care for patients around the world. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 6.