Artifacts in magnetic resonance imaging

Automatic quality control of brain 3D FLAIR MRIs for a clinical data warehouse

Clinical data warehouses, which have arisen over the last decade, bring together the medical data of millions of patients and offer the potential to train and validate machine learning models in real-world scenarios. The quality of MRIs collected in clinical data warehouses differs significantly from that generally observed in research datasets, reflecting the variability inherent to clinical practice. Consequently, the use of clinical data requires the implementation of robust quality control tools. By using a substantial number of pre-existing manually labelled T1-weighted MR images (5,500) alongside a smaller set of newly labelled FLAIR images (926), we present a novel semi-supervised adversarial domain adaptation architecture designed to exploit shared representations between MRI sequences thanks to a shared feature extractor, while taking into account the specificities of the FLAIR thanks to a specific classification head for each sequence. This architecture thus consists of a common invariant feature extractor, a domain classifier and two classification heads specific to the source and target, all designed to effectively deal with potential class distribution shifts between the source and target data classes. The primary objectives of this paper were: (1) to identify images which are not proper 3D FLAIR brain MRIs; (2) to rate the overall image quality. For the first objective, our approach demonstrated excellent results, with a balanced accuracy of 89%, comparable to that of human raters. For the second objective, our approach achieved good performance, although lower than that of human raters. Nevertheless, the automatic approach accurately identified bad quality images (balanced accuracy >79%). In conclusion, our proposed approach overcomes the initial barrier of heterogeneous image quality in clinical data warehouses, thereby facilitating the development of new research using clinical routine 3D FLAIR brain images.

The Role of Dynamic Contrast Enhanced Magnetic Resonance Imaging in Evaluating Prostate Adenocarcinoma: A Partially-Blinded Retrospective Study of a Prostatectomy Patient Cohort With Whole Gland Histopathology Correlation and Application of PI-RADS or TNM Staging

BACKGROUND

Dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) in the current Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS v2.1) is considered optional, with primary scoring based on T2-weighted imaging (T2WI) and diffusion weighted imaging (DWI). Our study is designed to assess the relative contribution of DCE MRI in a patient-cohort with whole mount prostate histopathology and spatially-mapped prostate adenocarcinoma (PCa) for reference.

METHODS

We performed a partially-blinded retrospective review of 47 prostatectomy patients with recent multi-parametric MRI (mpMRI). Scans included T2WI, DWI with apparent diffusion coefficient (ADC) mapping, and DCE imaging. Lesion conspicuity was scored on a 10-point scale with ≥ 6 considered "positive," and image quality was assessed on a 4-point scale for each sequence. The diagnostic contribution of DCE images was evaluated on a 4-point scale. The mpMRI studies were assigned PI-RADS scores and tumor, node, metastasis (TNM) T-stage with blinded comparison to spatially-mapped whole-mount pathology. Results were compared to the prospective clinical reports, which used standardized PI-RADS templates that emphasize T2WI, DWI and ADC.

RESULTS

Per lesion sensitivity for PCa was 93.5%, 82.6%, 63.0%, and 58.7% on T2WI, DCE, ADC and DWI, respectively. Mean lesion conspicuity was 8.5, 7.9, 6.2, and 6.1, on T2W, DCE, ADC and DWI, respectively. The higher values on T2WI and DCE imaging were not significantly different from each other but were both significantly different from DWI and ADC (p < 0.001). DCE scans were determined to have a marked diagnostic contribution in 83% of patients, with the most common diagnostic yield being detection of contralateral peripheral zone tumor or delineating presence/absence of extra-prostatic extension (EPE), contributing to more accurate PCa staging by PI-RADS or TNM, as compared to histopathology.

CONCLUSION

We demonstrate that DCE may contribute to lesion detection and local staging as compared to T2WI plus DWI-ADC alone and that lesion conspicuity using DCE is markedly improved as compared to DWI-ADC. These findings support modification of PI-RADS v2.1 to include use of DCE acquisitions and that a TNM staging is feasible on mpMRI as compared to surgical pathology.

Meta-learning guidance for robust medical image synthesis: Addressing the real-world misalignment and corruptions

Deep learning-based image synthesis for medical imaging is currently an active research topic with various clinically relevant applications. Recently, methods allowing training with misaligned data have started to emerge, yet current solution lack robustness and cannot handle other corruptions in the dataset. In this work, we propose a solution to this problem for training synthesis network for datasets affected by mis-registration, artifacts, and deformations. Our proposed method consists of three key innovations: meta-learning inspired re-weighting scheme to directly decrease the influence of corrupted instances in a mini-batch by assigning lower weights in the loss function, non-local feature-based loss function, and joint training of image synthesis network together with spatial transformer (STN)-based registration networks with specially designed regularization. Efficacy of our method is validated in a controlled synthetic scenario, as well as public dataset with such corruptions. This work introduces a new framework that may be applicable to challenging scenarios and other more difficult datasets.

Multimodal Cross Global Learnable Attention Network for MR images denoising with arbitrary modal missing

Magnetic Resonance Imaging (MRI) generates medical images of multiple sequences, i.e., multimodal, from different contrasts. However, noise will reduce the quality of MR images, and then affect the doctor's diagnosis of diseases. Existing filtering methods, transform-domain methods, statistical methods and Convolutional Neural Network (CNN) methods main aim to denoise individual sequences of images without considering the relationships between multiple different sequences. They cannot balance the extraction of high-dimensional and low-dimensional features in MR images, and hard to maintain a good balance between preserving image texture details and denoising strength. To overcome these challenges, this work proposes a controllable Multimodal Cross-Global Learnable Attention Network (MMCGLANet) for MR image denoising with Arbitrary Modal Missing. Specifically, Encoder is employed to extract the shallow features of the image which share weight module, and Convolutional Long Short-Term Memory(ConvLSTM) is employed to extract the associated features between different frames within the same modal. Cross Global Learnable Attention Network(CGLANet) is employed to extract and fuse image features between multimodal and within the same modality. In addition, sequence code is employed to label missing modalities, which allows for Arbitrary Modal Missing during model training, validation, and testing. Experimental results demonstrate that our method has achieved good denoising results on different public and real MR image dataset.

The current state of forensic imaging - recommended radiological tools and international guidelines

The last few decades have seen the emergence of forensic imaging, both clinical and post-mortem. Year after year, the scientific community has refined the radiological tools that can be used for post-mortem and clinical forensic purposes. As a result, scientific societies have published recommendations that are essential for the daily work of forensic imaging. This third part of the review of the current state of forensic imaging describes these recommended radiological tools and also presents an overview of the various international guidelines dealing with post mortem imaging that can be found in the literature or that have been written by scientific societies.

Assessment of the thoracic aorta after aortic root replacement and/or ascending aortic surgery using 3D relaxation-enhanced angiography without contrast and triggering

Objective

Relaxation-Enhanced Angiography without Contrast and Triggering (REACT) is a novel 3D isotropic flow-independent non-contrast-enhanced MRA (non-CE-MRA) and has shown promising results in imaging of the thoracic aorta, primarily in patients without prior aortic surgery. The purpose of this study was to evaluate the performance of REACT after surgery of the aortic root and/or ascending aorta by performing an intraindividual comparison to CE-MRA.

Material and methods

This retrospective single center study included 58 MRI studies of 34 patients [mean age at first examination 45.64 ± 11.13 years, 31 (53.44%) female] after ascending aortic surgery. MRI was performed at 1.5T using REACT (ECG- and respiratory-triggering, Compressed SENSE factor 9, acquired spatial resolution 1.69 × 1.70 × 1.70 mm3) and untriggered 3D CE-MRA. Independently, two radiologists measured maximum and minimum vessel diameters (inner-edge) and evaluated image quality and motion artifacts on 5-point scales (5 = excellent) for the following levels: mid-graft, distal anastomosis, ascending aorta, aortic arch, and descending aorta. Additionally, readers evaluated MRAs for the presence of aortic dissection (AD) and graded the quality of depiction as well as their diagnostic confidence using 5-point scales (5 = excellent).

Results

Vessel diameters were comparable between CE-MRA and REACT (total acquisition time: 05:42 ± 00:38 min) with good to excellent intersequence agreement (ICC = 0.86-0.96). At the distal anastomosis (minimum/maximum, p < .001/p = .002) and at the ascending aorta (minimum/maximum, p = .002/p = .06), CE-MRA yielded slightly larger diameters. Image quality for all levels combined was higher in REACT [median (IQR); 3.6 (3.2-3.93) vs. 3.9 (3.6-4.13), p = .002], with statistically significant differences at mid-graft [3.0 (2.5-3.63) vs. 4.0 (4.0-4.0), p < .001] and ascending aorta [3.25 (3.0-4.0) vs. 4.0 (3.5-4.0), p < .001]. Motion artifacts were more present in CE-MRA at all levels (p < .001). Using CE-MRA as the standard of reference, readers detected all 25 cases of residual AD [Stanford type A: 21 (84.0%); Stanford type B: 4 (16.0%)] in REACT with equal quality of depiction [4.0 (3.0-4.5) vs. 4.0 (3.0-4.0), p = .41] and diagnostic confidence [4.0 (3.0-4.0) vs. 4.0 (3.0-4.0), p = .81) in both sequences.

Conclusions

This study indicates the feasibility of REACT for assessment of the thoracic aorta after ascending aortic surgery and expands its clinical use for gadolinium-free MRA to these patients.

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.

Accelerating veterinary low field MRI acquisitions using the deep learning based denoising solution HawkAI

Magnetic resonance imaging (MRI) has changed veterinary diagnosis but its long-sequence time can be problematic, especially because animals need to be sedated during the exam. Unfortunately, shorter scan times implies a fall in overall image quality and diagnosis reliability. Therefore, we developed a Generative Adversarial Net-based denoising algorithm called HawkAI. In this study, a Standard-Of-Care (SOC) MRI-sequence and then a faster sequence were acquired and HawkAI was applied to the latter. Radiologists were then asked to qualitatively evaluate the two proposed images based on different factors using a Likert scale (from 1 being strong preference for HawkAI to 5 being strong preference for SOC). The aim was to prove that they had at least no preference between the two sequences in terms of Signal-to-Noise Ratio (SNR) and diagnosis. They slightly preferred HawkAI in terms of SNR (confidence interval (CI) being [1.924-2.176]), had no preference in terms of Artifacts Presence, Diagnosis Pertinence and Lesion Conspicuity (respective CIs of [2.933-3.113], [2.808-3.132] and [2.941-3.119]), and a very slight preference for SOC in terms of Spatial Resolution and Image Contrast (respective CIs of [3.153-3.453] and [3.072-3.348]). This shows the possibility to acquire images twice as fast without any major drawback compared to a longer acquisition.

Use of Carbon Fiber Implants to Improve the Safety and Efficacy of Radiation Therapy for Spine Tumor Patients

Current standard of care treatment for patients with spine tumors includes multidisciplinary approaches, including the following: (1) surgical tumor debulking, epidural spinal cord decompression, and spine stabilization techniques; (2) systemic chemo/targeted therapies; (3) radiation therapy; and (4) surveillance imaging for local disease control and recurrence. Titanium pedicle screw and rod fixation have become commonplace in the spine surgeon's armamentarium for the stabilization of the spine following tumor resection and separation surgery. However, the high degree of imaging artifacts seen with titanium implants on postoperative CT and MRI scans can significantly hinder the accurate delineation of vertebral anatomy and adjacent neurovascular structures to allow for the safe and effective planning of downstream radiation therapies and detection of disease recurrence. Carbon fiber-reinforced polyetheretherketone (CFR-PEEK) spine implants have emerged as a promising alternative to titanium due to the lack of artifact signals on CT and MRI, allowing for more accurate and safe postoperative radiation planning. In this article, we review the tenants of the surgical and radiation management of spine tumors and discuss the safety, efficacy, and current limitations of CFR-PEEK spine implants in the multidisciplinary management of spine oncology patients.

Integration and Potential Applications of Cardiovascular Computed Tomography in Cardio-Oncology

PURPOSE OF REVIEW

Cardiovascular computed tomography (CCT) is a versatile, readily available, and non-invasive imaging tool with high-resolution capabilities in many cardiovascular diseases (CVD). Our review explains the increased risk of CVD among patients with cancer due to chemoradiotherapies, shared risk factors and cancer itself and explores the expanding role of CCT in the detection, surveillance, and management of numerous CVD among these patients.

RECENT FINDINGS

Recent research has highlighted the versatility and enhanced resolution capabilities of CCT in assessing a wide range of cardiovascular diseases. Early detection of cardiac changes and monitoring of disease progression in asymptomatic patients with cancer may lessen the severity of CVD. It offers an essential means to assess for coronary artery disease when patients are either unable to safely undergo stress testing for ischemia evaluation or at risk of complications from invasive coronary angiography. Furthermore, CCT extends its utility to valvular diseases, cardiomyopathies, pericardial diseases, cardiac masses, and radiation-induced cardiovascular diseases, allowing for a comprehensive, noninvasive assessment of the entire spectrum of cancer treatment associated CVD. Looking to the future, the integration of artificial intelligence and machine learning algorithms holds potential for automated image interpretation, improved precision and earlier detection of subclinical cardiac deterioration, allowing opportunities for earlier intervention and disease prevention. CCT is a useful imaging modality for assessing the myriad cardiovascular manifestations of diseases such as coronary artery disease, cardiomyopathies, pericardial disesaes, cardiac masses and radiation-induced cardiovascular diseases. CCT has several advantages. Readily available non-cardiac chest CT scans of patients with cancer may help with improved cardiovascular care, enhanced ASCVD risk stratification and toxicity surveillance.

Interference of titanium and zirconia implants on dental-dedicated MR image quality: ex vivo and in vivo assessment

OBJECTIVES

To assess the impact of titanium and zirconia implants on dental-dedicated MR image (ddMRI) quality ex vivo (magnetic field distortion [MFD]) and in vivo (artefacts).

METHODS

ddMR images were acquired (MAGNETOM Free.Max, 0.55 T, Siemens Healthineers AG, Forchheim, Germany) using a dental-dedicated coil (Rapid Biomedical, Rimpar, Germany). Ex vivo: three phantoms were manufactured: one agar-embedded titanium implant, one agar-embedded zirconia implant, and one control phantom (agar 1.5%). Field map analysis of images acquired at 0.55 T, 1.5 T, and 3.0 T (MAGNETOM Sola and MAGNETOM Lumina, respectively, Siemens Healthineers AG, Forchheim, Germany) was done to illustrate the extent and severity of MFD caused by the implants. In vivo (0.55 T only): a splint was designed to serve as an implant carrier, allowing diverse implant positions (0, 1, 2, or 5 implants). A volunteer was imaged using multiple pulse sequences. Three blinded observers scored the images twice for the presence, severity, and type of artefacts, illustrated by descriptive statistics and inter- and intra-observer reproducibility (kappa statistics).

RESULTS

Ex vivo: titanium produced more severe MFD than zirconia. MFD extent and amplitude increased with field strength (0.55 T < 1.5 T < 3.0 T). In vivo: titanium produced more artefacts than zirconia, generally as signal voids in tooth crowns close to implants. Inter- and intra-observer reproducibility ranged from 0.28 to 0.64 and 0.32 to 0.57, respectively.

CONCLUSIONS

The prevalence of artefacts increased with magnetic field strength. Titanium generated larger MFD than zirconia. For both materials, artefacts were visible mainly in the crown area. Observer reproducibility needs improvement by dedicated ddMRI training.

Improved diagnostic accuracy for leptomeningeal dissemination in pediatric brain tumors using contrast-enhanced FLAIR imaging

Background

Central nervous system cancers are a leading cause of childhood cancer-related mortality. Accurate staging and assessment of leptomeningeal spread, particularly in aggressive neoplasms such as embryonal tumors, is crucial for treatment planning and prognosis. Conventional diagnostic methods, relying on magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) cytology, have limitations, including high false-negative rates and sensitivity issues. In this retrospective study, we aim to compare the diagnostic sensitivity of contrast-enhanced T2-weighted fluid-attenuated inversion recovery (CE-T2W-FLAIR) and 2D and 3D contrast-enhanced T1-weighted imaging (CE-T1WI) for detecting leptomeningeal disease.

Methods

We retrospectively reviewed 1372 MRI brain studies of 297 patients aged 1-19 years. We included only those MRI examinations adhering to our neuro-oncology protocol while excluding incomplete or suboptimal studies. A control group without leptomeningeal disease was matched for disease and age. Three groups of 2 neuroradiologists each, blinded to case status, reviewed the images using various sequences. The results were compared using the McNemar test and chi-squared test for P-values.

Results

The sensitivity of CE-T2W-FLAIR sequence was significantly higher compared with that of CE-T1WI (P = .025). There was no statistically significant difference between the sensitivity of 2D CE-T1WI and 3D CE-T1WI (P = .3173). The specificity of the 3D CE-T1WI was significantly lower compared with those of CE-T2W-FLAIR and 2D CE-T1WI (P = .014). The positive predictive values for CE-T2W-FLAIR, 2D CE-T1WI, and 3D CE-T1WI were 100%, 100%, and 68.4%, respectively, whereas the negative predictive values were 100%, 85.7%, and 85.71%, respectively.

Conclusions

The inclusion of CE-T2W-FLAIR in the MRI protocol improves sensitivity and specificity in diagnosing leptomeningeal spread in pediatric brain tumors.

Diffusion MRI Metrics Characterize Postoperative Clinical Outcomes After Surgery for Cervical Spondylotic Myelopathy

BACKGROUND AND OBJECTIVES

Advanced diffusion-weighted MRI (DWI) modeling, such as diffusion tensor imaging (DTI) and diffusion basis spectrum imaging (DBSI), may help guide rehabilitation strategies after surgical decompression for cervical spondylotic myelopathy (CSM). Currently, however, postoperative DWI is difficult to interpret, owing to signal distortions from spinal instrumentation. Therefore, we examined the relationship between postoperative DTI/DBSI-extracted from the rostral C3 spinal level-and clinical outcome measures at 2-year follow-up after decompressive surgery for CSM.

METHODS

Fifty patients with CSM underwent complete clinical and DWI evaluation-followed by DTI/DBSI analysis-at baseline and 2-year follow-up. Clinical outcomes included the modified Japanese Orthopedic Association score and comprehensive patient-reported outcomes. DTI metrics included apparent diffusion coefficient, fractional anisotropy, axial diffusivity, and radial diffusivity. DBSI metrics evaluated white matter tracts through fractional anisotropy, fiber fraction, axial diffusivity, and radial diffusivity as well as extra-axonal pathology through restricted and nonrestricted fraction. Cross-sectional Spearman's correlations were used to compare postoperative DTI/DBSI metrics with clinical outcomes.

RESULTS

Twenty-seven patients with CSM, including 15, 7, and 5 with mild, moderate, and severe disease, respectively, possessed complete baseline and postoperative DWI scans. At 2-year follow-up, there were 10 significant correlations among postoperative DBSI metrics and postoperative clinical outcomes compared with 3 among postoperative DTI metrics. Of the 13 significant correlations, 7 involved the neck disability index (NDI). The strongest relationships were between DBSI axial diffusivity and NDI (r = 0.60, P < .001), DBSI fiber fraction and NDI (r s = -0.58, P < .001), and DBSI restricted fraction and NDI (r s = 0.56, P < .001). The weakest correlation was between DTI apparent diffusion coefficient and NDI (r = 0.35, P = .02).

CONCLUSION

Quantitative measures of spinal cord microstructure after surgery correlate with postoperative neurofunctional status, quality of life, and pain/disability at 2 years after decompressive surgery for CSM. In particular, DBSI metrics may serve as meaningful biomarkers for postoperative disease severity for patients with CSM.

Intra-Operative Tumour Detection and Staging in Pancreatic Cancer Surgery: An Integrative Review of Current Standards and Future Directions

BACKGROUND

Surgical resection for pancreatic ductal adenocarcinoma (PDAC) entails the excision of the primary tumour and regional lymphadenectomy. This traditional strategy is challenged by the high rate of early recurrence, suggesting inadequate disease staging. Novel methods of intra-operative staging are needed to allow surgical resection to be tailored to the disease's biology.

METHODS

A search of published articles on the PubMed and Embase databases was performed using the terms 'pancreas' OR 'pancreatic' AND 'intra-operative staging/detection' OR 'guided surgery'. Articles published between January 2000 and June 2023 were included. Technologies that offered intra-operative staging and tailored treatment were curated and summarised in the following integrative review.

RESULTS

lymph node (LN) mapping and radioimmunoguided surgery have shown promising results but lacked practicality to facilitate real-time intra-operative staging for PDAC. Fluorescence-guided surgery (FGS) offers high contrast and sensitivity, enabling the identification of cancerous tissue and positive LNs with improved precision following intravenous administration of a fluorescent agent. The unique properties of optical coherence tomography and ultrasound elastography lend themselves to be platforms for virtual biopsy intra-operatively.

CONCLUSIONS

Accurate intra-operative staging of PDAC, localisation of metastatic LNs, and identification of extra-pancreatic disease remain clinically unmet needs under current detection methods and staging standards. Tumour-specific FGS combined with other diagnostic and therapeutic modalities could improve tumour detection and staging in patients with PDAC.

Spatial and Modal Optimal Transport for Fast Cross-Modal MRI Reconstruction

Multi-modal magnetic resonance imaging (MRI) plays a crucial role in comprehensive disease diagnosis in clinical medicine. However, acquiring certain modalities, such as T2-weighted images (T2WIs), is time-consuming and prone to be with motion artifacts. It negatively impacts subsequent multi-modal image analysis. To address this issue, we propose an end-to-end deep learning framework that utilizes T1-weighted images (T1WIs) as auxiliary modalities to expedite T2WIs' acquisitions. While image pre-processing is capable of mitigating misalignment, improper parameter selection leads to adverse pre-processing effects, requiring iterative experimentation and adjustment. To overcome this shortage, we employ Optimal Transport (OT) to synthesize T2WIs by aligning T1WIs and performing cross-modal synthesis, effectively mitigating spatial misalignment effects. Furthermore, we adopt an alternating iteration framework between the reconstruction task and the cross-modal synthesis task to optimize the final results. Then, we prove that the reconstructed T2WIs and the synthetic T2WIs become closer on the T2 image manifold with iterations increasing, and further illustrate that the improved reconstruction result enhances the synthesis process, whereas the enhanced synthesis result improves the reconstruction process. Finally, experimental results from FastMRI and internal datasets confirm the effectiveness of our method, demonstrating significant improvements in image reconstruction quality even at low sampling rates.

Use of Ultra-Short Echo Time MRI to Improve Temporal Bone Imaging

OBJECTIVE

The short T2 nature of cortical bone causes it to appear similar to air on MR, forcing clinicians to rely on computed tomography imaging, with its attendant ionizing radiation exposure, to define temporal bone structures. Through the use of novel MR sequences with ultra-short echo times (UTE), short T2 structures are now able to be visualized, allowing for improved understanding of anatomical relationships.

METHODS

Eight patients (50% female) undergoing MR imaging of the skull base for diagnostic purposes (62.5% for vestibular schwannoma surveillance) at a tertiary care center were enrolled to evaluate the safety and efficacy of UTE imaging. CT scans were completed in 37.5% of the patients as part of their workup and used for comparison purposes. The repetition time, short echo time, and long echo time for the UTE sequence were 11, 0.032, and 2.2 msec, respectively.

RESULTS

The protocol added 6 min to the total scanning time, and all patients tolerated the sequence without issue. The ossicles, mastoid air cells, antrum, and epitympanum were able to be seen and had a high Dice similarity coefficient when compared to CT (>0.5). UTE allowed for clear delineation of all segments of the facial nerve with a signal-to-noise ratio of 35 (although the BRAVO sequences had a superior ratio of 140). Vestibular schwannomas were able to be distinguished from normal brain parenchyma.

CONCLUSIONS

UTE is safe and effective for visualizing anatomic structures not normally seen on traditional MRI, potentially allowing for improved surgical planning in patients.

LEVEL OF EVIDENCE

3 Laryngoscope, 134:4691-4696, 2024.

Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report

Radiation therapy plays a crucial role in cancer treatment, necessitating precise delivery of radiation to tumors while sparing healthy tissues over multiple days. Computed tomography (CT) is integral for treatment planning, offering electron density data crucial for accurate dose calculations. However, accurately representing patient anatomy is challenging, especially in adaptive radiotherapy, where CT is not acquired daily. Magnetic resonance imaging (MRI) provides superior soft-tissue contrast. Still, it lacks electron density information, while cone beam CT (CBCT) lacks direct electron density calibration and is mainly used for patient positioning. Adopting MRI-only or CBCT-based adaptive radiotherapy eliminates the need for CT planning but presents challenges. Synthetic CT (sCT) generation techniques aim to address these challenges by using image synthesis to bridge the gap between MRI, CBCT, and CT. The SynthRAD2023 challenge was organized to compare synthetic CT generation methods using multi-center ground truth data from 1080 patients, divided into two tasks: (1) MRI-to-CT and (2) CBCT-to-CT. The evaluation included image similarity and dose-based metrics from proton and photon plans. The challenge attracted significant participation, with 617 registrations and 22/17 valid submissions for tasks 1/2. Top-performing teams achieved high structural similarity indices (≥0.87/0.90) and gamma pass rates for photon (≥98.1%/99.0%) and proton (≥97.3%/97.0%) plans. However, no significant correlation was found between image similarity metrics and dose accuracy, emphasizing the need for dose evaluation when assessing the clinical applicability of sCT. SynthRAD2023 facilitated the investigation and benchmarking of sCT generation techniques, providing insights for developing MRI-only and CBCT-based adaptive radiotherapy. It showcased the growing capacity of deep learning to produce high-quality sCT, reducing reliance on conventional CT for treatment planning.

Enhancing the Understanding of Breast Vascularity Through Insights From Dynamic Contrast-Enhanced Magnetic Resonance Imaging: A Comprehensive Review

Breast vascularity plays a crucial role in both physiological and pathological processes, particularly in the development and progression of breast cancer. Understanding vascular changes within breast tissue is essential for accurate diagnosis, treatment planning, and monitoring therapeutic response. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has emerged as a valuable tool for evaluating breast vascularity due to its ability to provide detailed functional and morphological insights. DCE-MRI utilizes contrast agents to highlight blood flow and vessel permeability, making it especially useful in differentiating between benign and malignant lesions. This review explores the significance of DCE-MRI in breast vascularity assessment, highlighting its principles, clinical applications, and role in detecting malignancy through vascular changes. We also examine its utility in monitoring treatment response and quantitative analysis of perfusion metrics such as Ktrans and extracellular-extravascular volume (Ve). While DCE-MRI offers remarkable diagnostic accuracy, challenges remain regarding its cost, accessibility, and potential overlap of enhancement patterns between benign and malignant conditions. The review further discusses emerging technologies and future directions for DCE-MRI, including advanced imaging techniques and machine learning-based quantification. Overall, DCE-MRI stands out as a powerful tool in the comprehensive evaluation of breast vascularity, with significant potential to improve patient outcomes in breast cancer management.

DNA origami-templated gold nanorod dimer nanoantennas: enabling addressable optical hotspots for single cancer biomarker SERS detection

The convergence of DNA origami and surface-enhanced Raman spectroscopy (SERS) has opened a new avenue in bioanalytical sciences, particularly in the detection of single-molecule proteins. This breakthrough has enabled the development of advanced sensor technologies for diagnostics. DNA origami offers a highly controllable framework for the precise positioning of nanostructures, resulting in superior SERS signal amplification. In our investigation, we have successfully designed and synthesized DNA origami-based gold nanorod monomer and dimer assemblies. Moreover, we have evaluated the potential of dimer assemblies for label-free detection of a single biomolecule, namely epidermal growth factor receptor (EGFR), a crucial biomarker in cancer research. Our findings have revealed that the significant Raman amplification generated by DNA origami-assembled gold nanorod dimer nanoantennas facilitates the label-free identification of Raman peaks of single proteins, which is a prime aim in biomedical diagnostics. The present work represents a significant advancement in leveraging plasmonic nanoantennas to realize single protein SERS for the detection of various cancer biomarkers with single-molecule sensitivity.

Applications of Multimodal Artificial Intelligence in Non-Hodgkin Lymphoma B Cells

Given advancements in large-scale data and AI, integrating multimodal artificial intelligence into cancer research can enhance our understanding of tumor behavior by simultaneously processing diverse biomedical data types. In this review, we explore the potential of multimodal AI in comprehending B-cell non-Hodgkin lymphomas (B-NHLs). B-cell non-Hodgkin lymphomas (B-NHLs) represent a particular challenge in oncology due to tumor heterogeneity and the intricate ecosystem in which tumors develop. These complexities complicate diagnosis, prognosis, and therapy response, emphasizing the need to use sophisticated approaches to enhance personalized treatment strategies for better patient outcomes. Therefore, multimodal AI can be leveraged to synthesize critical information from available biomedical data such as clinical record, imaging, pathology and omics data, to picture the whole tumor. In this review, we first define various types of modalities, multimodal AI frameworks, and several applications in precision medicine. Then, we provide several examples of its usage in B-NHLs, for analyzing the complexity of the ecosystem, identifying immune biomarkers, optimizing therapy strategy, and its clinical applications. Lastly, we address the limitations and future directions of multimodal AI, highlighting the need to overcome these challenges for better clinical practice and application in healthcare.

In vivo assessment of artefacts in MRI images caused by conventional twistflex and various fixed orthodontic CAD/CAM retainers

PURPOSE

To assess magnetic resonance imaging (MRI) artefacts caused by different computer-aided design/computer-aided manufacturing (CAD/CAM) retainers in comparison with conventional hand bent stainless steel twistflex retainers in vivo.

MATERIALS AND METHODS

MRI scans (3 Tesla) were performed on a male volunteer with different CAD/CAM retainers (cobalt-chromium, CoCr; nickel-titanium, NiTi; grade 5 titanium, Ti5) and twistflex retainers inserted. A total of 126 landmarks inside and outside the retainer area (RA; from canine to canine) were evaluated by two blinded radiologists using an established five-point visibility scoring (1: excellent, 2: good, 3: moderate, 4: poor, 5: not visible). Friedman and two-tailed Wilcoxon tests were used for statistical analysis (significance level: p < 0.05).

RESULTS

Twistflex retainers had the strongest impact on the visibility of all landmarks inside (4.0 ± 1.5) and outside the RA (1.7 ± 1.2). In contrast, artefacts caused by CAD/CAM retainers were limited to the dental area inside the RA (CoCr: 2.2 ± 1.2) or did not impair MRI-based diagnostics in a clinically relevant way (NiTi: 1.0 ± 0.1; Ti5: 1.4 ± 0.6).

CONCLUSION

The present study on a single test person demonstrates that conventional stainless steel twistflex retainers can severely impair the diagnostic value in head/neck and dental MRI. By contrast, CoCr CAD/CAM retainers can cause artefacts which only slightly impair dental MRI but not head/neck MRI, whereas NiTi and Ti5 CAD/CAM might be fully compatible with both head/neck and dental MRI.

In vivo human knee varus-valgus loading apparatus for analysis of MRI-based intratissue strain and relaxometry

The diagnosis of early-stage osteoarthritis remains as an unmet challenge in medicine and a roadblock to evaluating the efficacy of disease-modifying treatments. Recent studies demonstrate that unique patterns of intratissue cartilage deformation under cyclic loading can serve as potential biomarkers to detect early disease pathogenesis. However, a workflow to obtain deformation, strain maps, and quantitative MRI metrics due to the loading of articular cartilage in vivo has not been fully developed. In this study, we characterize and demonstrate an apparatus that is capable of applying a varus-valgus load to the human knee in vivo within an MRI environment to enable the measurement of cartilage structure and mechanical function. The apparatus was first tested in a lab environment, then the functionality and utility of the apparatus were examined during varus loading in a clinical 3T MRI system for human imaging. We found that the device enables quantitative MRI metrics for biomechanics and relaxometry data acquisition during joint loading leading to compression of the medial knee compartment. Integration with spiral DENSE MRI during cyclic loading provided time-dependent displacement and strain maps within the tibiofemoral cartilage. The results from these procedures demonstrate that the performance of this loading apparatus meets the design criteria and enables a simple and practical workflow for future studies of clinical cohorts, and the identification and validation of imaging-based biomechanical biomarkers.

Using teach-back in patient education to improve patient satisfaction and the clarity of magnetic resonance imaging

OBJECTIVE

To explore the effects of using the teach-back method prior to contrast-enhanced magnetic resonance imaging (MRI) on patients' knowledge and satisfaction as well as the clarity of the resulting scans.

METHODS

A total of 254 patients who underwent contrast-enhanced MRI examination from July 4, 2022 to September 19, 2022 were enrolled and assigned to the intervention and control groups. Patients in the intervention group received education using the teach-back method, while those in the control group were given routine health education. A questionnaire that included patients' knowledge of contrast-enhanced MRI examination was answered before and after patient education. Data on patient satisfaction with nursing services were also collected. The clarity of the MRI images of all patients was assessed.

RESULTS

The scores of knowledge related to MRI after receiving education were significantly higher than those before receiving education (P < 0.001), and there were no significant differences between the intervention and control groups (11.27 ± 9.74 vs. 12.07 ± 8.71, P = 0.498). The score of satisfaction with nursing service in the teach-back group was significantly higher than that in the control group (39.82 ± 0.86 vs. 38.59 ± 3.73, P < 0.001), as was the image clarity score (96.4 ± 0.5 vs. 95.0 ± 0.4, P = 0.039).

CONCLUSION

Teach-back improves patient satisfaction and contrast-enhanced MRI clarity.

PRACTICE IMPLICATIONS

Including teach-back in patient education improves patient satisfaction and contrast-enhanced MRI clarity.

Changes in cortical grey matter volume with Cognitive Orientation to daily Occupational Performance intervention in children with developmental coordination disorder

Introduction

Cognitive Orientation to daily Occupational Performance (CO-OP) is a cognitive-based, task-specific intervention recommended for children with developmental coordination disorder (DCD). We recently showed structural and functional brain changes after CO-OP, including increased cerebellar grey matter. This study aimed to determine whether CO-OP intervention induced changes in cortical grey matter volume in children with DCD, and if these changes were associated with improvements in motor performance and movement quality.

Methods

This study is part of a randomized waitlist-control trial (ClinicalTrials.gov ID: NCT02597751). Children with DCD (N = 78) were randomized to either a treatment or waitlist group and underwent three MRIs over 6 months. The treatment group received intervention (once weekly for 10 weeks) between the first and second scan; the waitlist group received intervention between the second and third scan. Cortical grey matter volume was measured using voxel-based morphometry (VBM). Behavioral outcome measures included the Performance Quality Rating Scale (PQRS) and Bruininks-Oseretsky Test of Motor Proficiency-2 (BOT-2). Of the 78 children, 58 were excluded (mostly due to insufficient data quality), leaving a final N = 20 for analyses. Due to the small sample size, we combined both groups to examine treatment effects. Cortical grey matter volume differences were assessed using a repeated measures ANOVA, controlling for total intracranial volume. Regression analyses examined the relationship of grey matter volume changes to BOT-2 (motor performance) and PQRS (movement quality).

Results

After CO-OP, children had significantly decreased grey matter in the right superior frontal gyrus and middle/posterior cingulate gyri. We found no significant associations of grey matter volume changes with PQRS or BOT-2 scores.

Conclusion

Decreased cortical grey matter volume generally reflects greater brain maturity. Decreases in grey matter volume after CO-OP intervention were in regions associated with self-regulation and motor control, consistent with our other studies. Decreased grey matter volume may be due to focal increases in synaptic pruning, perhaps as a result of strengthening networks in the brain via the repeated learning and actions in therapy. Findings from this study add to the growing body of literature demonstrating positive neuroplastic changes in the brain after CO-OP intervention.

Cortical grey matter volume differences in children with developmental coordination disorder compared to typically developing children

Introduction

The cause of Developmental Coordination Disorder (DCD) is unknown, but neuroimaging evidence suggests that DCD may be related to altered brain development. Children with DCD show less structural and functional connectivity compared to typically developing (TD) children, but few studies have examined cortical volume in children with DCD. The purpose of this study was to investigate cortical grey matter volume using voxel-based morphometry (VBM) in children with DCD compared to TD children.

Methods

This cross-sectional study was part of a larger randomized-controlled trial (ClinicalTrials.gov ID: NCT02597751) that involved various MRI scans of children with/without DCD. This paper focuses on the anatomical scans, performing VBM of cortical grey matter volume in 30 children with DCD and 12 TD children. Preprocessing and VBM data analysis were conducted using the Computational Anatomy Tool Box-12 and a study-specific brain template. Differences between DCD and TD groups were assessed using a one-way ANOVA, controlling for total intracranial volume. Regression analyses examined if motor and/or attentional difficulties predicted grey matter volume. We used threshold-free cluster enhancement (5,000 permutations) and set an alpha level of 0.05. Due to the small sample size, we did not correct for multiple comparisons.

Results

Compared to the TD group, children with DCD had significantly greater grey matter in the left superior frontal gyrus. Lower motor scores (meaning greater impairment) were related to greater grey matter volume in left superior frontal gyrus, frontal pole, and right middle frontal gyrus. Greater grey matter volume was also significantly correlated with higher scores on the Conners 3 ADHD Index in the left superior frontal gyrus, superior parietal lobe, and precuneus. These results indicate that greater grey matter volume in these regions is associated with poorer motor and attentional skills.

Discussion

Greater grey matter volume in the left superior frontal gyrus in children with DCD may be a result of delayed or absent healthy cortical thinning, potentially due to altered synaptic pruning as seen in other neurodevelopmental disorders. These findings provide further support for the hypothesis that DCD is related to altered brain development.

One model to unite them all: Personalized federated learning of multi-contrast MRI synthesis

Curation of large, diverse MRI datasets via multi-institutional collaborations can help improve learning of generalizable synthesis models that reliably translate source- onto target-contrast images. To facilitate collaborations, federated learning (FL) adopts decentralized model training while mitigating privacy concerns by avoiding sharing of imaging data. However, conventional FL methods can be impaired by the inherent heterogeneity in the data distribution, with domain shifts evident within and across imaging sites. Here we introduce the first personalized FL method for MRI Synthesis (pFLSynth) that improves reliability against data heterogeneity via model specialization to individual sites and synthesis tasks (i.e., source-target contrasts). To do this, pFLSynth leverages an adversarial model equipped with novel personalization blocks that control the statistics of generated feature maps across the spatial/channel dimensions, given latent variables specific to sites and tasks. To further promote communication efficiency and site specialization, partial network aggregation is employed over later generator stages while earlier generator stages and the discriminator are trained locally. As such, pFLSynth enables multi-task training of multi-site synthesis models with high generalization performance across sites and tasks. Comprehensive experiments demonstrate the superior performance and reliability of pFLSynth in MRI synthesis against prior federated methods.

Unveiling the Temporal Aspect of MRI Tattoo Reactions: A Prospective Evaluation of a Newly-Acquired Tattoo with Multiple MRI Scans

BACKGROUND Over the past 30 years, painful reactions during magnetic resonance imaging (MRI) in tattooed individuals have been sporadically reported. These complications manifest as burning pain in tattooed skin areas, occasionally with swelling and redness, often leading to termination of the scanning. The exact cause is unclear, but iron oxide pigments in permanent make-up or elements in carbon black tattoos may play a role. Additionally, factors like tattoo age, design, and color may influence reactions. The existing literature lacks comprehensive evidence, leaving many questions unanswered. CASE REPORT We present the unique case of a young man who experienced recurring painful reactions in a recently applied black tattoo during multiple MRI scans. Despite the absence of ferrimagnetic ingredients in the tattoo ink, the patient reported intense burning sensations along with transient erythema and edema. Interestingly, the severity of these reactions gradually decreased over time, suggesting a time-dependent factor contributing to the problem. This finding highlights the potential influence of pigment particle density in the skin on the severity and risk of MRI interactions. We hypothesize that the painful sensations could be triggered by excitation of dermal C-fibers by conductive elements in the tattoo ink, likely carbon particles. CONCLUSIONS Our case study highlights that MRI-induced tattoo reactions may gradually decrease over time. While MRI scans occasionally can cause transient reactions in tattoos, they do not result in permanent skin damage and remain a safe and essential diagnostic tool. Further research is needed to understand the mechanisms behind these reactions and explore preventive measures.

Toward diffusion tensor imaging as a biomarker in neurodegenerative diseases: technical considerations to optimize recordings and data processing

Neuroimaging biomarkers have shown high potential to map the disease processes in the application to neurodegenerative diseases (NDD), e.g., diffusion tensor imaging (DTI). For DTI, the implementation of a standardized scanning and analysis cascade in clinical trials has potential to be further optimized. Over the last few years, various approaches to improve DTI applications to NDD have been developed. The core issue of this review was to address considerations and limitations of DTI in NDD: we discuss suggestions for improvements of DTI applications to NDD. Based on this technical approach, a set of recommendations was proposed for a standardized DTI scan protocol and an analysis cascade of DTI data pre-and postprocessing and statistical analysis. In summary, considering advantages and limitations of the DTI in NDD we suggest improvements for a standardized framework for a DTI-based protocol to be applied to future imaging studies in NDD, towards the goal to proceed to establish DTI as a biomarker in clinical trials in neurodegeneration.

Brain-implanted conductors amplify radiofrequency fields in rodents: Advantages and risks

Over the past few decades, daily exposure to radiofrequency (RF) fields has been increasing due to the rapid development of wireless and medical imaging technologies. Under extreme circumstances, exposure to very strong RF energy can lead to heating of body tissue, even resulting in tissue injury. The presence of implanted devices, moreover, can amplify RF effects on surrounding tissue. Therefore, it is important to understand the interactions of RF fields with tissue in the presence of implants, in order to establish appropriate wireless safety protocols, and also to extend the benefits of medical imaging to increasing numbers of people with implanted medical devices. This study explored the neurological effects of RF exposure in rodents implanted with neuronal recording electrodes. We exposed freely moving and anesthetized rats and mice to 950 MHz RF energy while monitoring their brain activity, temperature, and behavior. We found that RF exposure could induce fast onset firing of single neurons without heat injury. In addition, brain implants enhanced the effect of RF stimulation resulting in reversible behavioral changes. Using an optical temperature measurement system, we found greater than tenfold increase in brain temperature in the vicinity of the implant. On the one hand, our results underline the importance of careful safety assessment for brain-implanted devices, but on the other hand, we also show that metal implants may be used for neurostimulation if brain temperature can be kept within safe limits.

Generative interpolation and restoration of images using deep learning for improved 3D tissue mapping

The development of novel imaging platforms has improved our ability to collect and analyze large three-dimensional (3D) biological imaging datasets. Advances in computing have led to an ability to extract complex spatial information from these data, such as the composition, morphology, and interactions of multi-cellular structures, rare events, and integration of multi-modal features combining anatomical, molecular, and transcriptomic (among other) information. Yet, the accuracy of these quantitative results is intrinsically limited by the quality of the input images, which can contain missing or damaged regions, or can be of poor resolution due to mechanical, temporal, or financial constraints. In applications ranging from intact imaging (e.g. light-sheet microscopy and magnetic resonance imaging) to sectioning based platforms (e.g. serial histology and serial section transmission electron microscopy), the quality and resolution of imaging data has become paramount. Here, we address these challenges by leveraging frame interpolation for large image motion (FILM), a generative AI model originally developed for temporal interpolation, for spatial interpolation of a range of 3D image types. Comparative analysis demonstrates the superiority of FILM over traditional linear interpolation to produce functional synthetic images, due to its ability to better preserve biological information including microanatomical features and cell counts, as well as image quality, such as contrast, variance, and luminance. FILM repairs tissue damages in images and reduces stitching artifacts. We show that FILM can decrease imaging time by synthesizing skipped images. We demonstrate the versatility of our method with a wide range of imaging modalities (histology, tissue-clearing/light-sheet microscopy, magnetic resonance imaging, serial section transmission electron microscopy), species (human, mouse), healthy and diseased tissues (pancreas, lung, brain), staining techniques (IHC, H&E), and pixel resolutions (8 nm, 2 μm, 1mm). Overall, we demonstrate the potential of generative AI in improving the resolution, throughput, and quality of biological image datasets, enabling improved 3D imaging.

Intra-patient and inter-observer image quality analysis in liver MRI study with gadoxetic acid using two different multi-arterial phase techniques

PURPOSE

To evaluate intra-patient and interobserver agreement in patients who underwent liver MRI with gadoxetic acid using two different multi-arterial phase (AP) techniques.

METHODS

A total of 154 prospectively enrolled patients underwent clinical gadoxetic acid-enhanced liver MRI twice within 12 months, using two different multi-arterial algorithms: CAIPIRINHA-VIBE and TWIST-VIBE. For every patient, breath-holding time, body mass index, sex, age were recorded. The phase without contrast media and the APs were independently evaluated by two radiologists who quantified Gibbs artefacts, noise, respiratory motion artefacts, and general image quality. Presence or absence of Gibbs artefacts and noise was compared by the McNemar's test. Respiratory motion artefacts and image quality scores were compared using Wilcoxon signed rank test. Interobserver agreement was assessed by Cohen kappa statistics.

RESULTS

Compared with TWIST-VIBE, CAIPIRINHA-VIBE images had better scores for every parameter except higher noise score. Triple APs were always acquired with TWIST-VIBE but failed in 37% using CAIPIRINHA-VIBE: 11% have only one AP, 26% have two. Breath-holding time was the only parameter that influenced the success of multi-arterial techniques. TWIST-VIBE images had worst score for Gibbs and respiratory motion artefacts but lower noise score.

CONCLUSION

CAIPIRINHA-VIBE images were always diagnostic, but with a failure of triple-AP in 37%. TWIST-VIBE was successful in obtaining three APs in all patients. Breath-holding time is the only parameter which can influence the preliminary choice between CAIPIRINHA-VIBE and TWIST-VIBE algorithm.

ADVANCES IN KNOWLEDGE

If the patient is expected to perform good breath-holds, TWIST-VIBE is preferable; otherwise, CAIPIRINHA-VIBE is more appropriate.

Marker-controlled watershed algorithm and fuzzy C-means clustering machine learning: automated segmentation of glioblastoma from MRI images in a case series

INTRODUCTION AND IMPORTANCE

Automated segmentation of glioblastoma multiforme (GBM) from MRI images is crucial for accurate diagnosis and treatment planning. This paper presents a new and innovative approach for automating the segmentation of GBM from MRI images using the marker-controlled watershed segmentation (MCWS) algorithm.

CASE PRESENTATION AND METHODS

The technique involves several image processing techniques, including adaptive thresholding, morphological filtering, gradient magnitude calculation, and regional maxima identification. The MCWS algorithm efficiently segments images based on local intensity structures using the watershed transform, and fuzzy c-means (FCM) clustering improves segmentation accuracy. The presented approach achieved improved segmentation accuracy in detecting and segmenting GBM tumours from axial T2-weighted (T2-w) MRI images, as demonstrated by the mean characteristics performance metrics for GBM segmentation (sensitivity: 0.9905, specificity: 0.9483, accuracy: 0.9508, precision: 0.5481, F_measure: 0.7052, and jaccard: 0.9340).

CLINICAL DISCUSSION

The results of this study underline the importance of reliable and accurate image segmentation for effective diagnosis and treatment planning of GBM tumours.

CONCLUSION

The MCWS technique provides an effective and efficient approach for the segmentation of challenging medical images.

Deep learning-accelerated image reconstruction in back pain-MRI imaging: reduction of acquisition time and improvement of image quality

INTRODUCTION

Low back pain is a global health issue causing disability and missed work days. Commonly used MRI scans including T1-weighted and T2-weighted images provide detailed information of the spine and surrounding tissues. Artificial intelligence showed promise in improving image quality and simultaneously reducing scan time. This study evaluates the performance of deep learning (DL)-based T2 turbo spin-echo (TSE, T2DLR) and T1 TSE (T1DLR) in lumbar spine imaging regarding acquisition time, image quality, artifact resistance, and diagnostic confidence.

MATERIAL AND METHODS

This retrospective monocentric study included 60 patients with lower back pain who underwent lumbar spinal MRI between February and April 2023. MRI parameters and DL reconstruction (DLR) techniques were utilized to acquire images. Two neuroradiologists independently evaluated image datasets based on various parameters using a 4-point Likert scale.

RESULTS

Accelerated imaging showed significantly less image noise and artifacts, as well as better image sharpness, compared to standard imaging. Overall image quality and diagnostic confidence were higher in accelerated imaging. Relevant disk herniations and spinal fractures were detected in both DLR and conventional images. Both readers favored accelerated imaging in the majority of examinations. The lumbar spine examination time was cut by 61% in accelerated imaging compared to standard imaging.

CONCLUSION

In conclusion, the utilization of deep learning-based image reconstruction techniques in lumbar spinal imaging resulted in significant time savings of up to 61% compared to standard imaging, while also improving image quality and diagnostic confidence. These findings highlight the potential of these techniques to enhance efficiency and accuracy in clinical practice for patients with lower back pain.

Air bubble artifact: why postmortem brain MRI should always be combined with postmortem CT

Forensic pathology increasingly uses postmortem magnetic resonance imaging (PMMRI), particularly in pediatric cases. It should be noted that each (sudden and unexpected) death of an infant or child should have a forensic approach as well. Current postmortem imaging protocols do not focus adequately on forensic queries. First, it is important to demonstrate or rule out bleeding, especially in the brain. Thus, when incorporating PMMRI, a blood sensitive sequence (T2* and/or susceptibility weighted imaging (SWI)) should always be included. Secondly, as intracranial air might mimic small focal intracerebral hemorrhages, PMMRI should be preceded by postmortem CT (PMCT) since air is easily recognizable on CT. This will be illustrated by a case of a deceased 3-week-old baby. Finally, note that postmortem scans will often be interpreted by clinical radiologists, sometimes with no specific training, which makes this case report relevant for a broader audience.

Deep learning-accelerated image reconstruction in MRI of the orbit to shorten acquisition time and enhance image quality

BACKGROUND AND PURPOSE

This study explores the use of deep learning (DL) techniques in MRI of the orbit to enhance imaging. Standard protocols, although detailed, have lengthy acquisition times. We investigate DL-based methods for T2-weighted and T1-weighted, fat-saturated, contrast-enhanced turbo spin echo (TSE) sequences, aiming to improve image quality, reduce acquisition time, minimize artifacts, and enhance diagnostic confidence in orbital imaging.

METHODS

In a 3-Tesla MRI study of 50 patients evaluating orbital diseases from March to July 2023, conventional (TSES ) and DL TSE sequences (TSEDL ) were used. Two neuroradiologists independently assessed the image datasets for image quality, diagnostic confidence, noise levels, artifacts, and image sharpness using a randomized and blinded 4-point Likert scale.

RESULTS

TSEDL significantly reduced image noise and artifacts, enhanced image sharpness, and decreased scan time, outperforming TSES (p < .05). TSEDL showed superior overall image quality and diagnostic confidence, with relevant findings effectively detected in both DL-based and conventional images. In 94% of cases, readers preferred accelerated imaging.

CONCLUSION

The study proved that using DL for MRI image reconstruction in orbital scans significantly cut acquisition time by 69%. This approach also enhanced image quality, reduced image noise, sharpened images, and boosted diagnostic confidence.

New clinical opportunities of low-field MRI: heart, lung, body, and musculoskeletal

Contemporary whole-body low-field MRI scanners (< 1 T) present new and exciting opportunities for improved body imaging. The fundamental reason is that the reduced off-resonance and reduced SAR provide substantially increased flexibility in the design of MRI pulse sequences. Promising body applications include lung parenchyma imaging, imaging adjacent to metallic implants, cardiac imaging, and dynamic imaging in general. The lower cost of such systems may make MRI favorable for screening high-risk populations and population health research, and the more open configurations allowed may prove favorable for obese subjects and for pregnant women. This article summarizes promising body applications for contemporary whole-body low-field MRI systems, with a focus on new platforms developed within the past 5 years. This is an active area of research, and one can expect many improvements as MRI physicists fully explore the landscape of pulse sequences that are feasible, and as clinicians apply these to patient populations.

Unveiling the Intricacies: A Comprehensive Review of Magnetic Resonance Imaging (MRI) Assessment of T2-Weighted Hyperintensities in the Neuroimaging Landscape

T2-weighted hyperintensities in neuroimaging represent areas of heightened signal intensity on magnetic resonance imaging (MRI) scans, holding crucial importance in neuroimaging. This comprehensive review explores the T2-weighted hyperintensities, providing insights into their definition, characteristics, clinical relevance, and underlying causes. It highlights the significance of these hyperintensities as sensitive markers for neurological disorders, including multiple sclerosis, vascular dementia, and brain tumors. The review also delves into advanced neuroimaging techniques, such as susceptibility-weighted and diffusion tensor imaging, and the application of artificial intelligence and machine learning in hyperintensities analysis. Furthermore, it outlines the challenges and pitfalls associated with their assessment and emphasizes the importance of standardized protocols and a multidisciplinary approach. The review discusses future directions for research and clinical practice, including the development of biomarkers, personalized medicine, and enhanced imaging techniques. Ultimately, the review underscores the profound impact of T2-weighted hyperintensities in shaping the landscape of neurological diagnosis, prognosis, and treatment, contributing to a deeper understanding of complex neurological conditions and guiding more informed and effective patient care.

A three-dimensional Magnetic Resonance Spin Tomography in Time-domain protocol for high-resolution multiparametric quantitative magnetic resonance imaging

Magnetic Resonance Spin TomogrAphy in Time-domain (MR-STAT) is a multiparametric quantitative MR framework, which allows for simultaneously acquiring quantitative tissue parameters such as T1, T2, and proton density from one single short scan. A typical two-dimensional (2D) MR-STAT acquisition uses a gradient-spoiled, gradient-echo sequence with a slowly varying RF flip-angle train and Cartesian readouts, and the quantitative tissue maps are reconstructed by an iterative, model-based optimization algorithm. In this work, we design a three-dimensional (3D) MR-STAT framework based on previous 2D work, in order to achieve better image signal-to-noise ratio, higher though-plane resolution, and better tissue characterization. Specifically, we design a 7-min, high-resolution 3D MR-STAT sequence, and the corresponding two-step reconstruction algorithm for the large-scale dataset. To reduce the long acquisition time, Cartesian undersampling strategies such as SENSE are adopted in our transient-state quantitative framework. To reduce the computational burden, a data-splitting scheme is designed for decoupling the 3D reconstruction problem into independent 2D reconstructions. The proposed 3D framework is validated by numerical simulations, phantom experiments, and in vivo experiments. High-quality knee quantitative maps with 0.8 × 0.8 × 1.5 mm3 resolution and bilateral lower leg maps with 1.6 mm isotropic resolution can be acquired using the proposed 7-min acquisition sequence and the 3-min-per-slice decoupled reconstruction algorithm. The proposed 3D MR-STAT framework could have wide clinical applications in the future.

Deep Learning Accelerated Image Reconstruction of Fluid-Attenuated Inversion Recovery Sequence in Brain Imaging: Reduction of Acquisition Time and Improvement of Image Quality

RATIONALE AND OBJECTIVES

Fluid-attenuated inversion recovery (FLAIR) imaging is playing an increasingly significant role in the detection of brain metastases with a concomitant increase in the number of magnetic resonance imaging (MRI) examinations. Therefore, the purpose of this study was to investigate the impact on image quality and diagnostic confidence of an innovative deep learning-based accelerated FLAIR (FLAIRDLR) sequence of the brain compared to conventional (standard) FLAIR (FLAIRS) imaging.

MATERIALS AND METHODS

Seventy consecutive patients with staging cerebral MRIs were retrospectively enrolled in this single-center study. The FLAIRDLR was conducted using the same MRI acquisition parameters as the FLAIRS sequence, except for a higher acceleration factor for parallel imaging (from 2 to 4), which resulted in a shorter acquisition time of 1:39 minute instead of 2:40 minutes (-38%). Two specialized neuroradiologists evaluated the imaging datasets using a Likert scale that ranged from 1 to 4, with 4 indicating the best score for the following parameters: sharpness, lesion demarcation, artifacts, overall image quality, and diagnostic confidence. Additionally, the image preference of the readers and the interreader agreement were assessed.

RESULTS

The average age of the patients was 63 ± 11years. FLAIRDLR exhibited significantly less image noise than FLAIRS, with P-values of< .001 and< .05, respectively. The sharpness of the images and the ability to detect lesions were rated higher in FLAIRDLR, with a median score of 4 compared to a median score of 3 in FLAIRS (P-values of<.001 for both readers). In terms of overall image quality, FLAIRDLR was rated superior to FLAIRS, with a median score of 4 vs 3 (P-values of<.001 for both readers). Both readers preferred FLAIRDLR in 68/70 cases.

CONCLUSION

The feasibility of deep learning FLAIR brain imaging was shown with additional 38% reduction in examination time compared to standard FLAIR imaging. Furthermore, this technique has shown improvement in image quality, noise reduction, and lesion demarcation.

A systematic review of (semi-)automatic quality control of T1-weighted MRI scans

PURPOSE

Artifacts in magnetic resonance imaging (MRI) scans degrade image quality and thus negatively affect the outcome measures of clinical and research scanning. Considering the time-consuming and subjective nature of visual quality control (QC), multiple (semi-)automatic QC algorithms have been developed. This systematic review presents an overview of the available (semi-)automatic QC algorithms and software packages designed for raw, structural T1-weighted (T1w) MRI datasets. The objective of this review was to identify the differences among these algorithms in terms of their features of interest, performance, and benchmarks.

METHODS

We queried PubMed, EMBASE (Ovid), and Web of Science databases on the fifth of January 2023, and cross-checked reference lists of retrieved papers. Bias assessment was performed using PROBAST (Prediction model Risk Of Bias ASsessment Tool).

RESULTS

A total of 18 distinct algorithms were identified, demonstrating significant variations in methods, features, datasets, and benchmarks. The algorithms were categorized into rule-based, classical machine learning-based, and deep learning-based approaches. Numerous unique features were defined, which can be roughly divided into features capturing entropy, contrast, and normative measures.

CONCLUSION

Due to dataset-specific optimization, it is challenging to draw broad conclusions about comparative performance. Additionally, large variations exist in the used datasets and benchmarks, further hindering direct algorithm comparison. The findings emphasize the need for standardization and comparative studies for advancing QC in MR imaging. Efforts should focus on identifying a dataset-independent measure as well as algorithm-independent methods for assessing the relative performance of different approaches.

Biodegradable AZ91 magnesium alloy/sirolimus/poly D, L-lactic-co-glycolic acid-based substrate for cardiovascular device application

Biodegradable drug-eluting stents (DESs) are gaining importance owing to their attractive features, such as complete drug release to the target site. Magnesium (Mg) alloys are promising materials for future biodegradable DESs. However, there are few explorations using biodegradable Mg for cardiovascular stent application. In this present study, sirolimus-loaded poly D, L-lactic-co-glycolic acid (PLGA)-coated/ sirolimus-fixed/AZ91 Mg alloy-based substrate was developed via a layer-by-layer approach for cardiovascular stent application. The AZ91 Mg alloy was prepared through the squeeze casting technique. The casted AZ91 Mg alloy (Mg) was alkali-treated to provide macroporous networks to hold the sirolimus and PLGA layers. The systematic characterization was investigated via electrochemical, optical, physicochemical, and in-vitro biological characteristics. The presence of the Mg17 Al12 phase in the Mg sample was found in the x-ray diffraction system (XRD) spectrum which influences the corrosion behavior of the developed substrate. The alkali treatment increases the substrate's hydrophilicity which was confirmed through static contact angle measurement. The anti-corrosion characteristic of casted-AZ91 Mg alloy (Mg) was slightly less than the sirolimus-loaded PLGA-coated alkali-treated AZ91 Mg alloy (Mg/Na/S/P) substrate. However, dissolution rates for both substrates were found to be controlled at cell culture conditions. Radiographic densities of AZ91 Mg alloy substrates (Mg, Mg/Na, and Mg/Na/S/P) were measured to be 0.795 ± 0.015, 0.742 ± 0.01, and 0.712 ± 0.017, respectively. The star-shaped structure of 12% sirolimus/PLGA ensures the bioavailability of the drugs. Sirolimus release kinetic was fitted up to 80% with the "Higuchi model" for Mg samples, whereas Mg/Na/S/P showed 45% fitting with a zero-order mechanism. The Mg/Na/S/P substrate showed a 70% antithrombotic effect compared to control. Further, alkali treatment enhances the antibacterial characteristic of AZ91 Mg alloy. Also, the alkali-treated sirolimus-loaded substrates (Mg/Na/S and Mg/Na/S/P) inhibit the valvular interstitial cell's growth significantly in in-vitro. Hence, the results imply that sirolimus-loaded PLGA-coated AZ91 Mg alloy-based substrate can be a potential candidate for cardiovascular stent application.

Liver Anatomy 2.0 Quiz: Test Your Knowledge

The liver is one the largest organs in the abdomen and the most frequent site of metastases for gastrointestinal tumors. Surgery on this complex and highly vascularized organ can be associated with high morbidity even in experienced hands. A thorough understanding of liver anatomy is key to approaching liver surgery with confidence and preventing complications. The aim of this quiz is to provide an active learning tool for a comprehensive understanding of liver anatomy and its integration into clinical practice.

A Lightweight Deep Learning Framework for Automatic MRI Data Sorting and Artifacts Detection

The purpose of this study is to develop a lightweight and easily deployable deep learning system for fully automated content-based brain MRI sorting and artifacts detection. 22092 MRI volumes from 4076 patients between 2017 and 2021 were involved in this retrospective study. The dataset mainly contains 4 common contrast (T1-weighted (T1w), contrast-enhanced T1-weighted (T1c), T2-weighted (T2w), fluid-attenuated inversion recovery (FLAIR)) in three perspectives (axial, coronal, and sagittal), and magnetic resonance angiography (MRA), as well as three typical artifacts (motion, aliasing, and metal artifacts). In the proposed architecture, a pre-trained EfficientNetB0 with the fully connected layers removed was used as the feature extractor and a multilayer perceptron (MLP) module with four hidden layers was used as the classifier. Precision, recall, F1_Score, accuracy, the number of trainable parameters, and float-point of operations (FLOPs) were calculated to evaluate the performance of the proposed model. The proposed model was also compared with four other existing CNN-based models in terms of classification performance and model size. The overall precision, recall, F1_Score, and accuracy of the proposed model were 0.983, 0.926, 0.950, and 0.991, respectively. The performance of the proposed model was outperformed the other four CNN-based models. The number of trainable parameters and FLOPs were the smallest among the investigated models. Our proposed model can accurately sort head MRI scans and identify artifacts with minimum computational resources and can be used as a tool to support big medical imaging data research and facilitate large-scale database management.

Aqueous Dispersion of Manganese-Zinc Ferrite Nanoparticles Protected by PEG as a T2 MRI Temperature Contrast Agent

Mixed manganese-zinc ferrite nanoparticles coated with PEG were studied for their potential usefulness in MRI thermometry as temperature-sensitive contrast agents. Particles in the form of an 8.5 nm core coated with a 3.5 nm layer of PEG were fabricated using a newly developed, one-step method. The composition of Mn0.48Zn0.46Fe2.06O4 was found to have a strong thermal dependence of magnetization in the temperature range between 5 and 50 °C. Nanoparticles suspended in an agar gel mimicking animal tissue and showing non-significant impact on cell viability in the biological test were studied with NMR and MRI over the same temperature range. For the concentration of 0.017 mg/mL of Fe, the spin-spin relaxation time T2 increased from 3.1 to 8.3 ms, while longitudinal relaxation time T1 shows a moderate decrease from 149.0 to 125.1 ms. A temperature map of the phantom exposed to the radial temperature gradient obtained by heating it with an 808 nm laser was calculated from T2 weighted spin-echo differential MR images. Analysis of temperature maps yields thermal/spatial resolution of 3.2 °C at the distance of 2.9 mm. The experimental relaxation rate R2 data of water protons were compared with those obtained from calculations using a theoretical model incorporating the motion averaging regime.

A generalized dual-domain generative framework with hierarchical consistency for medical image reconstruction and synthesis

Medical image reconstruction and synthesis are critical for imaging quality, disease diagnosis and treatment. Most of the existing generative models ignore the fact that medical imaging usually occurs in the acquisition domain, which is different from, but associated with, the image domain. Such methods exploit either single-domain or dual-domain information and suffer from inefficient information coupling across domains. Moreover, these models are usually designed specifically and not general enough for different tasks. Here we present a generalized dual-domain generative framework to facilitate the connections within and across domains by elaborately-designed hierarchical consistency constraints. A multi-stage learning strategy is proposed to construct hierarchical constraints effectively and stably. We conducted experiments for representative generative tasks including low-dose PET/CT reconstruction, CT metal artifact reduction, fast MRI reconstruction, and PET/CT synthesis. All these tasks share the same framework and achieve better performance, which validates the effectiveness of our framework. This technology is expected to be applied in clinical imaging to increase diagnosis efficiency and accuracy.

A framework applicable in different imaging modalities can facilitate the medical imaging reconstruction efficiency but hindered by inefficient information communication across the data acquisition and imaging domains. Here, Jiadong Zhang and coworkers report a dual-domain generative framework to explore the underlying patterns across domains and apply their method to routine imaging modalities (computed tomography, positron emission tomography, magnetic resonance imaging) under one framework.

Ferrous Illusion: A Unique Case of Welding Fume Particles Appearing as Metallic Artifacts in MRI

A rare cause of metallic artifacts over the scalp on magnetic resonance imaging (MRI) is welding fume particles that contain paramagnetic iron oxide particles. These introduce distortion of the magnetic field homogeneity and result in susceptibility artifacts. They may erroneously be reported as a pathology such as calcified lesions; therefore, awareness among radiologists is required. We report a case of a 52-year-old male, an industrial inspector by profession, who presented to the neurology clinic with headaches for which an MRI of the brain without contrast was advised. There was no brain parenchymal signal abnormality; however, numerous small rounded altered signal foci were identified along the scalp, especially in the vertex region, which returned central hypointense and marginal hyperintense signal on all sequences. The imaging signals were suspicious for calcified scalp lesions, and the patient was recalled for clinical examination, which was unremarkable for cutaneous or subcutaneous abnormality on the scalp or elsewhere over the body. A detailed history was taken retrospectively, revealing that the patient had walked through a room where welding was being done before presenting for an MRI exam, without taking a shower. The various altered signal foci over the scalp on MRI based on their shape were hence identified as welding fume particles. These were fine enough not to be visible by the naked eye but determined by the MRI machine because of their magnetic susceptibility artifact. We aim to increase radiologists' awareness of such artifacts that may be seen in patients with occupational exposure to these particles to avoid misdiagnosis of other pathologies.

Miniaturized MR-compatible ultrasound system for real-time monitoring of acoustic effects in mice using high-resolution MRI

Visualization of focused ultrasound in high spatial and temporal resolution is crucial for accurately and precisely targeting brain regions noninvasively. Magnetic resonance imaging (MRI) is the most widely used noninvasive tool for whole-brain imaging. However, focused ultrasound studies employing high-resolution (> 9.4 T) MRI in small animals are limited by the small size of the radiofrequency (RF) volume coil and the noise sensitivity of the image to external systems such as bulky ultrasound transducers. This technical note reports a miniaturized ultrasound transducer system packaged directly above a mouse brain for monitoring ultrasound-induced effects using high-resolution 9.4 T MRI. Our miniaturized system integrates MR-compatible materials with electromagnetic (EM) noise reduction techniques to demonstrate echo-planar imaging (EPI) signal changes in the mouse brain at various ultrasound acoustic intensities. The proposed ultrasound-MRI system will enable extensive research in the expanding field of ultrasound therapeutics.

Within-Modality Synthesis and Novel Radiomic Evaluation of Brain MRI Scans

One of the most common challenges in brain MRI scans is to perform different MRI sequences depending on the type and properties of tissues. In this paper, we propose a generative method to translate T2-Weighted (T2W) Magnetic Resonance Imaging (MRI) volume from T2-weight-Fluid-attenuated-Inversion-Recovery (FLAIR) and vice versa using Generative Adversarial Networks (GAN). To evaluate the proposed method, we propose a novel evaluation schema for generative and synthetic approaches based on radiomic features. For the evaluation purpose, we consider 510 pair-slices from 102 patients to train two different GAN-based architectures Cycle GAN and Dual Cycle-Consistent Adversarial network (DC2Anet). The results indicate that generative methods can produce similar results to the original sequence without significant change in the radiometric feature. Therefore, such a method can assist clinics to make decisions based on the generated image when different sequences are not available or there is not enough time to re-perform the MRI scans.