Magnetic Resonance Imaging Sequences Research Articles

Advancing Diagnostics: The Role of Ultrasound and MR Imaging in Evaluating Musculotendinous Pathologies of the Shoulder Joint – A Comprehensive Literature Review

Musculotendinous pathologies of the shoulder joint are a common source of pain and functional impairment, often requiring precise imaging for accurate diagnosis and management. This review explores the roles of ultrasound (US) and magnetic resonance imaging (MRI) in evaluating these conditions, focusing on their diagnostic strengths, limitations, and clinical applications. Ultrasound offers dynamic, real-time assessment with high accuracy for superficial structures, making it a cost-effective option for evaluating rotator cuff tears and tendinopathies. MRI, on the other hand, is the gold standard for comprehensive imaging of deep soft tissues, labral injuries, and subtle intra-articular abnormalities. Recent advances in both modalities, including AI-powered ultrasound and faster MRI sequences, have enhanced diagnostic capabilities. This review synthesizes evidence from the past decade, comparing the sensitivity, specificity, and cost-effectiveness of US and MRI while discussing scenarios where their integration can provide the most benefit. The findings emphasize the need for modality selection tailored to clinical presentations, the expertise of practitioners, and healthcare resource availability. Future research should aim to standardize imaging protocols and explore innovative multimodal approaches to improve diagnostic accuracy further.

Unlocking Chemotherapy Success: The Role of Diffusion Tensor Imaging in Breast Cancer Treatment

Background: This study investigates the role of Diffusion Tensor Imaging (DTI) in predicting the response to neoadjuvant chemotherapy (NAC) in patients with locally advanced breast cancer. Methods: A Diffusion Tensor Imaging magnetic resonance imaging (DTI MRI) sequence, evaluating water diffusion along tissue structures, was performed before and after two chemotherapy cycles. This study included 23 patients with 27 malignant masses, comparing changes in DTI parameters with Residual Cancer Burden (RCB) scores. Results: We found a significant correlation between changes in specific DTI parameters (e.g., λ2, FA, RA) and pathological response, suggesting that DTI could serve as a sensitive marker for early chemotherapy response. However, differences in sensitivity were observed between DTI sequences with 6 and 12 directions, indicating that 12-direction DTI may provide better diagnostic accuracy. The percentage change in DTI parameters, particularly FA, demonstrated a strong ability to predict pathological complete response (pCR) with high sensitivity. Conclusions: As a non-invasive tool, DTI has the potential to assess chemotherapy efficacy, although larger studies with standardized protocols are necessary to validate its clinical utility.

Normal Facial Nerve Enhancement on Volumetric Interpolated Breath-hold Examination MRI Sequence.

Enhancement of the facial nerve can be seen on magnetic resonance imaging (MRI) due to its rich arteriovenous plexus. Classically, enhancement of the facial nerve beyond the geniculate ganglion has been described as a normal finding, while enhancement of the canalicular and labyrinthine segments is considered abnormal. We hypothesize facial nerve enhancement of the canalicular and labyrinthine segments is a normal finding on the post-contrast T-weighted, fat-saturated VIBE (volumetric interpolated breath-hold examination) sequence on both 1.5T and 3T scanners. Fifty patients without facial nerve symptoms undergoing MRI using the internal auditory canal (IAC) protocol were identified at our institution, 25 cases on a 1.5T scanner and 25 cases on a 3T scanner; a total of 100 facial nerves. Presence or absence of enhancement of the facial nerve segments on the postcontrast T1-weighted, fat-saturated VIBE sequence were independently analyzed by two neuroradiologists. On 1.5T, out of 50 facial nerves evaluated, percentage of nerves with enhancement at each segment was as follows: 80% canalicular, 92% labyrinthine, 100% tympanic, 100% mastoid, and 80% intraparotid. On 3T, out of 50 facial nerves evaluated, percentage of nerves with enhancement at each segment was as follows: 60% canalicular, 84% labyrinthine, 98% tympanic, 100% mastoid, and 93% intraparotid. Enhancement of the canalicular and labyrinthine segments of the facial nerve is a normal finding on the postcontrast, T1-weighted fat-saturated VIBE sequence. Careful attention to clinical history and asymmetry should be considered before calling abnormality of the facial nerve. IAC, Internal auditory canal; VIBE, Volumetric interpolated breath-hold examination.

Diagnosis and evaluation of cervical ossification of the posterior longitudinal ligament on Zero-Echo Time Magnetic Resonance Imaging: an illustrative case series.

Computed tomography (CT) scans are widely used clinically in the diagnosis of ossification of the posterior longitudinal ligament (OPLL). Conventionally acquired magnetic resonance imaging (MRI) is limited by insufficient signal intensity within bone tissue. Osseus conspicuity may be enhanced by applying sequences with "CT-like" bone contrast zero-echo time (ZTE) MRI. This is a case series aimed to understand if ZTE-MRI is sensitive in detecting cervical OPLL and if this modality is suitable for evaluating OPLL morphology. A retrospective review was performed to identify adult patients with available cervical ZTE-MRI and CT scans. ZTE-MRI and CT were evaluated for their ability to detect OPLL by 2 attending spine surgeons, 1 spine surgery clinical fellow, and 1 senior orthopedic resident. The phenotype of OPLL was then described and compared between the two modalities. A total of 50 patients were reviewed. All clinicians detected 4 cases of OPLL on CT, and the same cases were independently found on ZTE-MRI. The modalities were then compared to assess the phenotype of OPLL. ZTE-MRI may have the potential to obviate the need for concurrent CT scans in diagnosing OPLL. When OPLL was suspected on MRI, ZTE-MRI could confirm the OPLL diagnosis. With conventional MRI sequences that include additional post-processed ZTE-MRI, clinicians can also assess OPLL morphology and the resulting spinal cord change to make a complete diagnosis and identify patients at higher risk for progression or complications. ZTE-MRI avoids CT-related radiation, can improve diagnosis, and decrease health costs.

Predicting intraoperative 5-ALA-induced tumor fluorescence via MRI and deep learning in gliomas with radiographic lower-grade characteristics.

Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a tenfold cross-validation procedure. Our proposed approach's performance was assessed using mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.

Magnetic resonance imaging characterization of an α‐synuclein model of Parkinson's disease

AbstractParkinson's disease (PD) is primarily characterized by three histological hallmarks: dopaminergic neuronal degeneration, α‐synuclein accumulation and iron deposition. Over the last years, neuroimaging, particularly magnetic resonance imaging (MRI) has provided invaluable insights into the mechanisms underlying the disease. However, no imaging method has yet been able to translate α‐synuclein protein accumulation and spreading. Amongst the animal models mimicking the disease, the α‐synuclein rat, generated through the injection of human α‐synuclein, has been characterized in terms of behavioural and histological aspects but not thoroughly explored in MRI. The aim of this study is, therefore, to identify the radiological signature from several MRI sequences, while controlling for histological and behavioural characteristics. Rats were assessed for motor and cognitive functions over a 4‐month period. During this time, three MRI sessions, including both morphological and functional sequences, were conducted. Histological studies evaluated the three main hallmarks of PD. The progressive dopaminergic neurodegeneration and the spread of human α‐synuclein corresponded to the level of sensorimotor, attentional and learning deficits observed in this PD model. MRI analyses showed progressive structural abnormalities in the midbrain, diencephalon and several cortical structures, as well as a pattern of hyperconnectivity in the basal ganglia and cortical networks. The regions affected in imaging demonstrated the highest load of human α‐synuclein. This model's structural and functional MRI changes could serve as indirect indicators of α‐synuclein accumulation and its association with impaired non‐motor functions.

Machine learning prediction of brain metastasis invasion pattern on brain MRI scans

Abstract Background Brain metastasis invasion pattern (BMIP) is an emerging biomarker associated with recurrence-free and overall survival in patients, and differential response to therapy in preclinical models. Currently, BMIP can only be determined from the histopathological examination of surgical specimens, precluding its use as a biomarker prior to therapy initiation. The aim of this study was to investigate the potential of machine learning (ML) approaches to develop a non-invasive magnetic resonance imaging (MRI)-based biomarker for BMIP determination. Methods From an initial cohort of 329 patients, a subset of 132 patients met inclusion criteria for this retrospective study. We evaluated the ability of an expert neuroradiologist to reliably predict BMIP. Thereafter, the dataset was randomly divided into training/validation (80% of cases) and test subsets (20% of cases). Ground truth for BMIP was histopathologic evaluation of resected specimens. Following MRI sequence co-registration, advanced feature extraction techniques deriving hand-crafted radiomic features with traditional ML classifiers and convolution-based deep learning (CDL) models were trained and evaluated. Different ML approaches were used individually or using ensembling techniques to determine the model with the best performance for BMIP prediction. Results Expert evaluation of brain MRI scans could not reliably predict BMIP, with an accuracy of 44-59% depending on the semantic feature used. Among the different ML and CDL models evaluated, the best performing model achieved an accuracy of 85% and an F1-score of 90%. Conclusion ML approaches can effectively predict BMIP, representing a non-invasive MRI-based approach to guide management of patients with brain metastases.

Quantification of breast biopsy clip marker artifact on routine breast MRI sequences: a phantom study

BackgroundTo investigate the artifact sizes of four common breast clip-markers on a standard breast magnetic resonance imaging (MRI) protocol in an in vitro phantom model.MethodsUsing 1.5-T and 3-T whole-body scanners with an 18-channel breast coil, artifact dimensions of four breast biopsy markers in an agarose-gel phantom were measured by two readers on images obtained with the following sequences: T2-weighted fast spin-echo short inversion time fat-suppressed inversion-recovery with magnitude reconstruction (T2-TIRM); T1-weighted spoiled gradient-echo with fat suppression (T1_FL3D), routinely used for dynamic contrast-enhanced imaging; diffusion-weighted imaging (DWI), including a readout segmented echo-planar imaging (RESOLVE-DWI) and echo-planar imaging sequence (EPI-DWI). After outlining the artifacts by freehand regions of interest, sagittal and lateral diameters in axial images were measured.ResultsInterreader agreement for artifact size quantification was high, depending on the sequence (80.4–94.8%). Overall, the size, shape, and appearance of artifacts depended on clip type and MRI sequence. The artifact size ranged from 5.7 × 8.5 mm2 to 13.4 × 17.7 mm2 at 1.5 T and from 6.6 × 8.2 mm2 to 17.7 × 20.7 mm2 at 3 T. Clip artifacts were largest on EPI-DWI and RESOLVE-DWI (p ≤ 0.016). In three out of four clips, T2-TIRM showed the smallest artifact (p ≤ 0.002), while in one clip the artifact was smallest on T1_FL3D (p = 0.026). With the exception of one clip in the RESOLVE sequence, all clips showed a decrease in the artifact area from DWI to ADC images (p ≤ 0.037).ConclusionBreast clip-marker MRI artifact appearances depend on clip type, field strength, and sequence and may reach a significant size, potentially obscuring smaller lesions and hindering accurate assessment of breast tumors.Relevance statementConsiderable variations in artifact size and characteristics across different breast clips, MRI sequences, and field strengths exist. Awareness of these artifacts and their characteristics is essential to ensure accurate interpretation of scans and appropriate treatment planning.Key PointsAwareness of breast clip artifacts is essential for accurate interpretation of MRI.The appearance of artifacts depends on breast clip type, field strength, and sequence.Clip-related artifacts might hinder the visibility of small lesions.Graphical

Dental Implant Artifacts in MRI: Compatibility and Considerations

This review investigated dental implant artifacts in magnetic resonance imaging (MRI) and their safety in clinical practice. Dental prostheses, including implants, crowns, and orthodontic appliances, cause artifacts due to their high magnetic susceptibility, particularly in materials like iron, stainless steel, and cobalt-chromium. Titanium implants are considered safe under MRI environments according to the American Society for Testing and Material (ASTM) standards, with no reported thermal injury or dislodgement during examinations. Despite limited artifacts from titanium's paramagnetic nature, minute ferromagnetic components can still affect visualization. Thus, reducing artifacts in oral and maxillofacial MRI scans is crucial. Two main categories of artifact reduction techniques are identified: improved porous titanium or alternative materials like zirconia and adjusting MR parameters with advanced sequences. Recommendations include increasing the readout bandwidth, reducing slice thickness, using spin-echo sequences instead of gradient-echo, and employing short tau inversion recovery or DIXON techniques for fat suppression. Additional methods like VAT, VAT-SEMAC combination, and MAVRIC show promise, although applicability may be restricted in specific MRI scanners. Continuous advancements in dental implant materials and MRI sequences are needed to improve imaging quality and reduce artifacts. Collaboration among dental practitioners, radiologists, and MRI technologists is essential for refining techniques and ensuring patient safety. Although overall dental implant artifacts pose challenges, safety in MRI is well-established. Ongoing developments hold significant potential to enhance MRI imaging quality in patients with dental devices

The influence of preformed metal crowns versus zirconia crowns on the diagnostic quality of magnetic resonance images.

The purpose of this study was to investigate and compare in vitro the influence of preformed metal crowns (PMC) versus zirconia crowns (ZC) on the extent of artifact formation and the diagnostic quality of magnetic resonance imaging (MRI). Standard crown tooth preparations were performed on Typodont models. PMC and ZC were cemented on all primary molar teeth (n = 8) of the respective models. MRI scans were taken for the Typodont alone (control), PMC, and ZC, using a 3T MRI machine and common MRI sequences. The diameter of image distortion was measured around the dental materials. Data was analyzed using a mixed model analysis. The average artifact size for PMC was 54.9mm (range 19.6-110.7mm) and 12.8mm (range 5.5-20.7mm) for ZC. The artifact size was associated with the MRI pulse sequence and dental material, with PMC showing larger artifact diameters than ZC for all MRI sequences (p < 0.001). The control had sensitive sequences for AxT2* and DWI sequences with MRI artifacts of 11.4mm and 10.7mm, respectively. It is important that dentists are aware of the potential of dental materials to cause unfavourable MRI artifacts. When areas of the brain requiring MRI preclude the use of PMC, ZC may be considered as an alternative to extractions. Further clinical studies are required to evaluate the impact of dental materials on the image quality of MR scans in vivo.

Bright middle cerebellar peduncle sign in multiple system atrophy with predominant cerebellar ataxia is more apparent in double-inversion recovery imaging than in conventional imaging.

Multiple system atrophy (MSA) is a neurodegenerative disorder that presents as parkinsonism, cerebellar ataxia, and autonomic dysfunction. Magnetic resonance imaging (MRI) findings of MSA are reported to be the atrophy of the putamen/pons/cerebellum, hot cross bun sign, and bright middle cerebellar peduncle (MCP) sign. Here, we assessed the sensitivity of detecting the bright MCP sign in patients with MSA cerebellar variant (MSA-C) using a double inversion recovery (DIR) procedure, comparing it to the sensitivity of detection by T2-weighted image (T2WI) and fluid-attenuated inversion recovery (FLAIR) sequences on conventional MRI. We evaluated 6 MSA-C patients and 6 control patients (multiple sclerosis, neuromyelitis optica, and spinocerebellar atrophy). Characteristics of all the patients were collected, and MRI was analyzed. Two neurologists independently evaluated the visualization of the bright MCP sign using a 4-point visual grade from Grade 0 to Grade 3. Differences in grade between DIR and T2WI or FLAIR were statistically analyzed. Also, as a quantitative analysis, the signal intensity of the MCP lesion was compared with that of the ipsilateral thalamus, and the MCP/thalamus ratio was evaluated. As a result, DIR more sensitively showed the bright MCP signs of MSA-C patients than T2WI or FLAIR. Also, the bright MCP sign deteriorated and expanded over time in the cases we followed with MRI. We also evaluated hot cross bun sign in the pons, but the hot cross bun sign in MSA-C patients was not significantly different between the DIR and conventional MRI sequences. The DIR procedure can be a more sensitive method for detecting the involvement of MCP lesions in MSA-C.

Functional localization of the human auditory and visual thalamus using a thalamic localizer functional magnetic resonance imaging task

Abstract Functional magnetic resonance imaging (fMRI) of the auditory and visual sensory systems of the human brain is an active area of investigation in the study of human health and disease. The medial geniculate nucleus (MGN) and lateral geniculate nucleus (LGN) are key thalamic nuclei involved in the processing and relay of auditory and visual information, respectively, and are the subject of blood-oxygen-level-dependent (BOLD) fMRI studies of neural activation and functional connectivity in human participants. However, localization of BOLD fMRI signal originating from neural activity in MGN and LGN remains a technical challenge, due, in part, to the poor definition of boundaries of these thalamic nuclei in standard T1-weighted and T2-weighted magnetic resonance imaging sequences. Here, we report the development and evaluation of an auditory and visual sensory thalamic localizer (TL) fMRI task that produces participant-specific functionally-defined regions of interest (fROIs) of both MGN and LGN, using 3 Tesla multiband fMRI and a clustered-sparse temporal acquisition sequence, in less than 16 minutes of scan time. We demonstrate the use of MGN and LGN fROIs obtained from the TL fMRI task in standard resting-state functional connectivity (RSFC) fMRI analyses in the same participants. In RSFC analyses, we validated the specificity of MGN and LGN fROIs for signals obtained from primary auditory and visual cortex, respectively, and benchmarked their performance against alternative atlas- and segmentation-based localization methods. The TL fMRI task and analysis code (written in Presentation and MATLAB, respectively) have been made freely available to the wider research community.

NIMG-66. DEFINING PROGRESSIVE DISEASE: LOCALIZING VOXEL-AT-RISK ON MAGNETIC RESONANCE IMAGING USING DEEP LEARNING

Abstract Follow-up magnetic resonance imaging (MRI) of post-treatment glioblastoma (GBM) can be diagnostically challenging in differentiating progressive disease (PD) from coexisting treatment-related changes. The study aim was to train a machine learning model using multiple MRI timepoints from treated GBM patients with subsequent PD or at least six months of tumor-like, persistently stable disease (SD) to estimate PD risk. A retrospective, post-treatment GBM cohort (n=189) with 453 timepoints was identified with available MRI sequences (T1-weighted with and without contrast, T2-weighted, and fluid-attenuated inversion recovery). PD cases (n=154) showed new, enhancing PD followed by death within 3-6 months; timepoints included the MRI on the PD diagnosis date and the one directly prior. SD cases (n=35) exhibited stable, tumor-like enhancement over timepoints. Cases underwent voxel-wise annotation of PD versus SD. A multiclass, three-dimensional nnU-Net was trained to label voxels as PD, SD, or neither using timepoint sequences with five-fold cross-validation. Model performance was assessed using the ratio of predicted PD/SD voxels compared to each case’s actual PD or SD status. Classification accuracy of PD versus SD status, PD case-wise sensitivity and specificity, and a Receiver Operating Characteristic (ROC) analysis using the PD/SD ratio were presented. The five-fold model ensemble was evaluated on a holdout test set. Validation set performance showed 74.3% accuracy, 0.73 PD case-wise sensitivity, and 0.80 specificity. The holdout set exhibited 79.8% accuracy, 0.81 sensitivity, and 0.78 specificity for PD cases. The ROC analysis showed an area under the curve of 0.80 and 0.83 on the validation and holdout sets, respectively. The model showed high performance and classification accuracy in predicting which voxels were at risk of PD in post-treatment GBM cases. The model also differentiated between PD and SD regions. The model’s predicted PD/SD ratio may be clinically used to stratify patients’ PD risk.

NIMG-52. ARTIFICIAL INTELLIGENCE-BASED VOLUMETRIC KINETICS FOR EVALUATING TREATMENT RESPONSE IN IDH-MUTANT GLIOMA TREATED WITH IMMUNOTHERAPY

Abstract BACKGROUND Interpretating radiographic findings of glioma patients receiving immunotherapy is challenging. Repeated imaging is often required for clinical decisions, potentially delaying next line of treatment. Here we assess a glioma segmentation AI model to evaluate treatment response in IDH-mutant glioma patients receiving nivolumab. METHODS Clinical magnetic resonance imaging (MRI)s from twenty-nine patients enrolled in a clinical trial (NCT03718767) were retrospectively analyzed. All patients had at least two sequential MRIs, including baseline study. T2, T1 (pre/post-contrast), and T2 FLAIR MRI sequences were pre-processed using publicly available AI-based whole-brain segmentation models. Lesion contours were derived from a validated 4-class brain tumor segmentation AI model, distinguishing healthy brain parenchyma, peri-lesional edema, non-contrast enhancing volume (NEV), and contrast-enhancing volume (CEV). Total lesion burden volume (TLBV=NEV + CEV + Edema) was also calculated. Growth rates between responders (R) and non-responders (NR), defined as progression-free survival ≥ or &amp;lt; 6months, respectively, were compared using a Wilcoxon Rank Sum Test. RESULTS The R group displayed significantly lower median rates of change for CEV (R -35% vs. NR +142% p = 4.31e-04) and TLBV (R +6% vs NR +43% p = 1.55e-03), compared to NR from baseline to post-cycle 1-2. Additionally, similar trends persisted at post-cycle 3-4 for CEV (R -41% vs. NR +367% p = 3.03e-03) and TLBV (R +12% vs. NR +40% p = 7.74e-03). Although NR showed a higher average baseline TLBV, there was no discernible correlation detected between baseline TLBV and the rate of change during treatment. CONCLUSIONS AI-based volumetric analysis offers an objective response assessment, showing promise in tracking disease progression in IDH-mutant glioma patients on nivolumab, potentially enabling earlier identification of progressive disease and allowing for timely treatment adjustments. A larger prospective study is warranted to refine volumetric pattern analysis for early clinical decisions in immunotherapy.

High-quality multimodal MRI with simultaneous EEG using conductive ink and polymer-thick film nets

Objective. Combining magnetic resonance imaging (MRI) and electroencephalography (EEG) provides a powerful tool for investigating brain function at varying spatial and temporal scales. Simultaneous acquisition of both modalities can provide unique information that a single modality alone cannot reveal. However, current simultaneous EEG-fMRI studies are limited to a small set of MRI sequences due to the image quality and safety limitations of commercially available MR-conditional EEG nets. We tested whether the Inknet2, a high-resistance polymer thick film based EEG net that uses conductive ink, could enable the acquisition of a variety of MR image modalities with minimal artifacts by reducing the radiofrequency-shielding caused by traditional MR-conditional nets.Approach. We first performed simulations to model the effect of the EEG nets on the magnetic field and image quality. We then performed phantom scans to test image quality with a conventional copper EEG net, with the new Inknet2, and without any EEG net. Finally, we scanned five human subjects at 3 Tesla (3 T) and three human subjects at 7 Tesla (7 T) with and without the Inknet2 to assess structural and functional MRI image quality.Main results. Across these simulations, phantom scans, and human studies, the Inknet2 induced fewer artifacts than the conventional net and produced image quality similar to scans with no net present.Significance. Our results demonstrate that high-quality structural and functional multimodal imaging across a variety of MRI pulse sequences at both 3 T and 7 T is achievable with an EEG net made with conductive ink and polymer thick film technology.

Added value of volumetric MRI pulse sequence 3D VISTA (Volume ISotopic Turbo spin echo Acquisition) in perianal fistula depiction and characterization

PurposeDiagnosis of perianal fistula represents a challenge for surgeons. It is well known that magnetic resonance imaging (MRI) plays an important role in that. The new 3D MRI sequence VISTA (Volume ISotopic Turbo spin echo Acquisition) can improve detection and characterization of perianal fistula compared with two-dimensional (2D) sequences. The aim of the study was to compare the diagnostic performance of the new 3D MRI sequence VISTA with the widely routinely used T2 FSE pulse sequence in depiction and characterization of perianal fistula by using the contrast-enhanced (CE) 3D T1 sequence THRIVE (T1-weighted high-resolution isotropic volume examination) as a reference standard.Material and methodsForty adult patients were enrolled in this prospective study. They underwent MRI perianal region examination using routine T2 TSE and CE 3D T1 sequence THRIVE with addition of the new 3D MRI sequence VISTA. T2, 3D VISTA and (CE) 3D T1 sequence THRIVE images were evaluated by two radiologists separately for detection and characterization of perianal fistula, then comparison between of T2 and 3D VISTA sequences was done using (CE) 3D T1 sequence THRIVE as a reference. Each sequence sensitivity, specificity and accuracy were calculated by both readers.ResultsFor reader 1, the sensitivity, specificity and accuracy were 92.5%, 90.5% and 93.6% for 3D VISTA and 84.1%, 83.7% and 87.3% for T2 FSE. For reader 2, the sensitivity, specificity and accuracy were 91.5%, 92.8% and 94.8% for 3D VISTA and 82.9%, 84.5% and 86.7% for T2 FSE.ConclusionsUsing CE 3D T1 sequence THRIVE as the reference standard, 3D VISTA pulse sequence on the perianal region has better diagnostic performance in the detection and characterization of perianal fistula as compared to the routinely used T2 FSE sequence.

An MRI-Based Method for the Morphologic Assessment of the Anterior Tibial Tuberosity.

Background: A prominent anterior tibial tuberosity (or tibial tubercle) can be seen in ongoing Osgood-Schlatter disease (OSD) in teenagers or as a sequela of OSD in adults. Current radiological methods do not provide a true anatomical assessment of the tibial tuberosity; therefore, we proposed and developed a Magnetic Resonance Imaging (MRI)-based method for measuring the anterior tibial tuberosity index, aiming to deal with the current lack of effective techniques for accurately assessing these particular morphologic features. Methods: A retrospective study included 47 knees with tibial tuberosity measurements on both true sagittal MPR images of 3D proton density (PD)-weighted MRI sequences and lateral knee radiographs. The same landmarks were followed and the anterior tibial tuberosity index (ATTI) was measured. Results: The comparison of the results obtained by the two methods demonstrates that our method is reliable and reproducible with substantial inter- and intra-observer agreement. The intraclass correlation coefficient was 0.9250 (95% CI: 0.8654 to 0.9582), indicating excellent reliability between the two methods. A strong positive correlation was also identified, with a correlation coefficient of r = 0.8746 (95% CI: 0.7845 to 0.9286, p < 0.0001) between the two methods. No significant deviation from linearity was observed by analyzing the linear model validity using the cusum test (p = 0.62). Conclusions: Based on these results, we encourage the use of 3D PD-weighted MRI sequences for the measurement of the anterior tibial tuberosity on MRI in order to avoid unnecessary exposure to ionizing radiation and potentially obtain a more accurate measurement. Future larger studies should also explore the benefit of utilizing 3D sequences over 2D lateral projections to minimize measuring bias.

SDR2Tr‐GAN: A Novel Medical Image Fusion Pipeline Based on GAN With SDR2 Module and Transformer Optimization Strategy

ABSTRACTIn clinical practice, radiologists diagnose brain tumors with the help of different magnetic resonance imaging (MRI) sequences and judge the type and grade of brain tumors. It is hard to realize the brain tumor computer‐aided diagnosis system only with a single MRI sequence. However, the existing multiple MRI sequence fusion methods have limitations in the enhancement of tumor details. To improve fusion details of multi‐modality MRI images, a novel conditional generative adversarial fusion network based on three discriminators and a Staggered Dense Residual2 (SDR2) module, named SDR2Tr‐GAN, was proposed in this paper. In the SDR2Tr‐GAN network pipeline, the generator consists of an encoder, decoder, and fusion strategy that can enhance the feature representation. SDR2 module is developed with Res2Net into the encoder to extract multi‐scale features. In addition, a Multi‐Head Spatial/Channel Attention Transformer, as a fusion strategy to strengthen the long‐range dependencies of global context information, is integrated into our pipeline. A Mask‐based constraint as a novel fusion optimization mechanism was designed, focusing on enhancing salient feature details. The Mask‐based constraint utilizes the segmentation mask obtained by the pre‐trained Unet and Ground Truth to optimize the training process. Meanwhile, MI and SSIM loss jointly improve the visual perception of images. Extensive experiments were conducted on the public BraTS2021 dataset. The visual and quantitative results demonstrate that the proposed method can simultaneously enhance both global image quality and local texture details in multi‐modality MRI images. Besides, our SDR2Tr‐GAN outperforms the other state‐of‐the‐art fusion methods regarding subjective and objective evaluation.

Prediction of early recurrence of adult-type diffuse gliomas following radiotherapy using multi-modal magnetic resonance images.

Adult-type diffuse gliomas are among the central nervous system's most aggressive malignant primary neoplasms. Despite advancements in systemic therapies and technological improvements in radiation oncology treatment delivery, the survival outcome for these patients remains poor. Fast and accurate assessment of tumor response to oncologic treatments is crucial, as it can enable the early detection of recurrent or refractory gliomas, thereby allowing timely intervention with life-prolonging salvage therapies. Radiomics is a developing field with great potential to improve medical image interpretation. This study aims to apply a radiomics-based predictive model for classifying response to radiotherapy within the first 3 months post-treatment. Ninety-five patients were selected from the Burdenko Glioblastoma Progression Dataset. Tumor regions were delineated in the axial plane on contrast-enhanced T1(CE T1W) and T2 fluid-attenuated inversion recovery (T2_FLAIR) magnetic resonance imaging (MRI). Hand-crafted radiomic (HCR) features, including first- and second-order features, were extracted using PyRadiomics (3.7.6) in Python (3.10). Then, recursive feature elimination with a random forest (RF) classifier was applied for feature dimensionality reduction. RF and support vector machine (SVM) classifiers were built to predict treatment outcomes using the selected features. Leave-one-out cross-validation was employed to tune hyperparameters and evaluate the models. For each segmented target, 186 HCR features were extracted from the MRI sequence. Using the top-ranked radiomic features from a combination of CE T1W and T2_FLAIR, an optimized classifier achieved the highest averaged area under the curve (AUC) of 0.829±0.075 using the RF classifier. The HCR features of CE T1W produced the worst outcomes among all models (0.603±0.024 and 0.615±0.075 for RF and SVM classifiers, respectively). We developed and evaluated a radiomics-based predictive model for early tumor response to radiotherapy, demonstrating excellent performance supported by high AUC values. This model, harnessing radiomic features from multi-modal MRI, showed superior predictive performance compared to single-modal MRI approaches. These results underscore the potential of radiomics in clinical decision support for this disease process.

Comparison of Imaging Characteristics in Pediatric Patients With Trochlear Versus Medial Femoral Condyle Osteochondritis Dissecans.

Although osteochondritis dissecans (OCD) lesions are well-described in the femoral condyles and have been associated with varus limb alignment, there is limited data on OCD lesions in the trochlea. To compare the baseline imaging characteristics in pediatric patients with trochlear OCD with those with medial femoral condyle (MFC) OCD to understand whether measures of coronal plane alignment predispose to OCD development by anatomic location. Cross-sectional study; Level of evidence, 3. This study retrospectively reviewed all pediatric patients (age ≤18 years) diagnosed with isolated trochlear OCD at a tertiary-care medical center from January 2016 to May 2023; all included patients had weight-bearing hip-to-ankle alignment radiographs. Hip-knee-ankle angle (HKA), mechanical lateral distal femoral angle (mLDFA), medial proximal tibial angle (MPTA), mechanical axis deviation (MAD), Caton-Deschamps Index (CDI), patellar tilt, and sulcus angle were measured on initial/preoperative anteroposterior and lateral knee radiographs. Tibial tubercle-trochlear groove (TT-TG) distance and OCD lesion size were measured on initial/preoperative magnetic resonance imaging sequences. Patients were 1 to 2 matched based on age (±2 years) and sex to a cohort with isolated MFC OCD. A total of 18 extremities in 16 patients were included in the trochlear OCD cohort and matched to 36 extremities in the MFC OCD cohort. The mean age at the first clinical visit for all patients was 14.8 ± 1.5 years and did not differ significantly between the two groups (P = .40). The extremities with trochlear OCD had significantly less varus HKA (1°± 2° vs -1°± 2°; P = .004) and MAD (4 ± 8 vs -3 ± 8 mm; P = .004) compared with the MFC cohort as well as lower mLDFA (86°± 2° vs 88°± 2°; P = .004). There were no differences in MPTA, CDI, patellar tilt, sulcus angle, TT-TG distance, or OCD lesion size between groups. Pediatric patients with trochlear OCD had statistically less varus coronal plane alignment compared with age- and sex-matched patients with MFC OCD, with the latter exhibiting more significant varus based on the HKA and MAD.