Clinical study on improving the diagnostic accuracy of adult elbow joint cartilage injury by multisequence magnetic resonance imaging.

Regarding the 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors, the isocitrate dehydrogenase (IDH) mutation status is one of the most important factors for CNS tumor classification. The aim of our study is to analyze which of the commonly used magnetic resonance imaging (MRI) sequences is best suited to obtain this information non-invasively using radiomics-based machine learning models. We developed machine learning models based on different MRI sequences and determined which of the MRI sequences analyzed yields the highest discriminatory power in predicting the IDH mutation status. In our retrospective IRB-approved study, we used the MRI images of 106 patients with histologically confirmed gliomas. The MRI images were acquired using the T1 sequence with and without administration of a contrast agent, the T2 sequence, and the Fluid-Attenuated Inversion Recovery (FLAIR) sequence. To objectively compare performance in predicting the IDH mutation status as a function of the MRI sequence used, we included only patients in our study cohort for whom MRI images of all four sequences were available. Seventy-one of the patients had an IDH mutation, and the remaining 35 patients did not have an IDH mutation (IDH wild-type). For each of the four MRI sequences used, 107 radiomic features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects associated with the data partitioning. Feature preselection and subsequent model development were performed using Random Forest, Lasso regression, LDA, and Naïve Bayes. The performance of all models was determined with independent test data. Among the different approaches we examined, the T1-weighted contrast-enhanced sequence was found to be the most suitable for predicting IDH mutations status using radiomics-based machine learning models. Using contrast-enhanced T1-weighted MRI images, our seven-feature model developed with Lasso regression achieved a mean area under the curve (AUC) of 0.846, a mean accuracy of 0.792, a mean sensitivity of 0.847, and a mean specificity of 0.681. The administration of contrast agents resulted in a significant increase in the achieved discriminatory power. Our analyses show that for the prediction of the IDH mutation status using radiomics-based machine learning models, among the MRI images acquired with the commonly used MRI sequences, the contrast-enhanced T1-weighted images are the most suitable.

Radiomics-driven machine learning models for noninvasive prediction of pathological differentiation in hepatocellular carcinoma: insights from multisequence magnetic resonance imaging (MRI).

Evaluation of giant arachnoid granulations with high-resolution 3D-volumetric MR sequences at 3T

The objective of this study was to investigate the application effect of deep learning model combined with different magnetic resonance imaging (MRI) sequences in the evaluation of cartilage injury of knee osteoarthritis (KOA). Specifically, an image superresolution algorithm based on an improved multiscale wide residual network model was proposed and compared with the single-shot multibox detector (SSD) algorithm, superresolution convolutional neural network (SRCNN) algorithm, and enhanced deep superresolution (EDSR) algorithm. Meanwhile, 104 patients with KOA diagnosed with cartilage injury were selected as the research subjects and underwent MRI scans, and the diagnostic performance of different MRI sequences was analyzed using arthroscopic results as the gold standard. It was found that the image reconstructed by the model in this study was clear enough, with minimum noise and artifacts, and the overall quality was better than that processed by other algorithms. Arthroscopic analysis found that grade I and grade II lesions concentrated on patella (26) and femoral trochlear (15). In addition to involving the patella and femoral trochlea, grade III and grade IV lesions gradually developed into the medial and lateral articular cartilage. The 3D-DS-WE sequence was found to be the best sequence for diagnosing KOA injury, with high diagnostic accuracy of over 95% in grade IV lesions. The consistency test showed that the 3D-DESS-WE sequence and T2∗ mapping sequence had a strong consistency with the results of arthroscopy, and the Kappa consistency test values were 0.748 and 0.682, respectively. In conclusion, MRI based on deep learning could clearly show the cartilage lesions of KOA. Of different MRI sequences, 3D-DS-WE sequence and T2∗ mapping sequence showed the best diagnosis results for different degrees of KOA injury.

THU0533 A SINGLE MRI DIXON SEQUENCE TO ASSESS DISEASE ACTIVITY AND CARTILAGE IN EARLY RHEUMATOID HANDS: ONE SEQUENCE TO ASSESS THEM ALL?

Automated delineation of organs play a vital role during the treatment planning for clinical practitioner. With magnetic resonance (MR) images being widely used in radio-therapy, the organ delineation from multi-sequence MR images has become more desirable. Segmenting abdominal organs from MR images is critical in surgical planning. However, the organs segmentation from MR volume is a challenging task, as there are different visual appearances for the same organ in the different sequences of MR images. Recently, convolutional neural network (CNN) methods have achieved promising results in automating organ delineation. However, the performance of deep learning (DL) to emerging approaches such as adversarial learning in the field of segmentation are rarely explored. In this paper, we have trained an encoder-decoder like architecture as a segmentation network, using segmentation loss minimization along with training it to adversarial attack another CNN implementing the visual Turing test discriminator. This way of adversarial training has shown significant improvement in performance. We have used the CHAOS-19 dataset of abdominal MRI for segmentation of the liver, left kidney, right kidney, and spleen. We have used Dice coefficient (DC) to measure the performance, and achieved an average DC of 0.97 with the faster convergence.

The objective of this research is to solve the problem of target location mapping in breast cancer (BC) radiotherapy. We proposed a BC magnetic resonance (MR) images mapping model based on clustering algorithms. Compared with Digital Radiography (DR) and Computed Tomography (CT), MR images have unparalleled advantages in soft tissue imaging, and it can clearly distinguish the invasive range of breast tumors and surrounding tissues. The work used T1-weighted, T2-weighted, fat suppression sequence and enhancement sequence MR images from 12 patients with breast cancer to study. The MR images of the four sequences were clustered and compared using k-means and fuzzy c-means clustering methods. The experimental results show that using clustering algorithm, especially the k-means clustering combined with the MR images of multiple sequences, can well determine the region of breast tumors. At the same time, we compared the snake model and mapped the breast cancer MR images of the T1 sequence. The experimental results show that the k-means clustering combined with the multi-sequence MR images has higher mapping accuracy and robustness to noise. This shows that our method is feasible. It can solve the problem of lack of standard in breast cancer bed mapping.

Hepatocellular carcinoma (HCC), the most common primary hepatic malignancy, usually develops in patients with cirrhosis, growing sequentially from low-grade dysplastic nodules to frank malignant HCC. Its recognition is critical because curative treatment and prognosis require early diagnosis. Survival in patients with HCC relates directly to the number, size, and extent of lesions at diagnosis. Imaging of HCC is complicated because the tumor has a varied imaging appearance and frequently coexists with other cirrhotic nodules. Magnetic resonance imaging (MRI), the best available diagnostic technique, offers good contrast resolution and diagnostic sensitivity ranging from 33% to 77%. The main difficulty is not in diagnosing large tumors, but rather small tumors (<2 cm), because of considerable overlap on imaging between benign (regenerative), borderline (dysplastic), and malignant nodules. Increasing degrees of histological malignancy are associated with increasing arterialization and loss of portal blood supply; therefore, recognition of HCC requires dynamic imaging with gadolinium-enhanced T1-weighted sequence. Typically, HCC is a focal lesion with high signal intensity on T2-weighted images, variable signal intensity on T1-weighted images, intense arterial phase enhancement after gadolinium injection, and isointensity or hypointensity at the portal venous phase. The sensitivity of MRI for detecting small lesions is low, and improvement is still needed. Newer contrast agents, higher field strength (3 Tesla) imaging, and perfusion and diffusion MRI techniques possibly will provide greater sensitivity and specificity for detecting small HCCs in the future.

Segmentation of brain lesions in Magnetic Resonance Imaging (MRI) is a difficult task to be mastered by the specialist. This is due to the presence of noise, partial volume effects and susceptibility artifacts in the images and on the borders of the regions of interest. These problems can interfere with the results when manual segmentation is used. Manual segmentation uses local anatomic information based on the user's background; that implies the necessity of constant human intervention. Deformable model approaches attempt to minimize these drawbacks by outlining the region of interest semi-automatically. These methods have been shown to be effective in the extraction of the lesion boundaries in brain MR images. The proposed method employs the multi-channel version of the Mumford-Shah model via level set methods in order to segment multi-sequence brain magnetic resonance (MR) images: FLAIR (Fluid attenuated inversion recovery), T 1 and T 2 - weighted images. Results showed that segmentation of multi-sequence images using this methodology yielded superior results than using each sequence alone. As a consequence, medical doctors can exploit the segmentation results to follow up their patients' status by controlling the evolution or involution of brain lesions.

Multimodal spatial-based segmentation framework for white matter lesions in multi-sequence magnetic resonance images

Continuing the search for MR imaging biomarkers for MGMT promoter methylation status: conventional and perfusion MRI revisited

The differentiation of brucellar spondylitis (BS) from tuberculous spondylitis (TS) on magnetic resonance imaging (MRI) is a critical clinical challenge. While deep learning holds promise, the optimal architectural strategy for integrating information from multi-sequence MRI remains unclear. This study systematically compared distinct deep learning architectures to identify a valid and effective integration strategy for this diagnostic problem. In this retrospective, single-center diagnostic study, we included 235 patients with surgically and pathologically confirmed BS (n = 82) or TS (n = 153) from January 2014 to December 2024. We systematically evaluated four distinct architectural strategies for processing sagittal T1-weighted, T2-weighted, and fat-suppressed MRI sequences: (1) baseline models trained on single sequences; (2) a single-branch model that fused sequences as input channels; (3) a heterogeneous multi-branch model using different backbones for each sequence; and (4) a homogeneous multi-branch model using identical backbones. Models were developed on patient-level data splits for training (70%), validation (15%), and internal testing (15%). The primary performance metric was the area under the receiver operating characteristic curve (AUC) on the test set. Statistical significance of performance differences between models was assessed using the DeLong test, with P values adjusted for multiple comparisons using the Benjamini-Hochberg procedure. The single-branch fusion model, which treated the three sequences as channels in a single input, failed to learn, yielding performance equivalent to random chance (test AUC range: 0.474-0.538). In stark contrast, both the single-sequence and multi-branch architectures proved to be effective. The best single-sequence model achieved a test AUC of 0.765 (95% CI 0.759-0.771). The optimal multi-branch model, which successfully integrated all three sequences, achieved a comparable test AUC of 0.764 (95% CI 0.757-0.770). The choice of architecture for integrating multi-sequence MRI data is a critical determinant of model viability. Our findings demonstrate that naive channel wise fusion is an invalid strategy for this task. In contrast, both processing a single MRI sequence and utilizing a multi-branch parallel-processing architecture are valid and effective strategies, achieving comparable diagnostic performance. This study clarifies the architectural principles required for successfully applying deep learning to this multi-modal diagnostic challenge.

To compare diagnostic accuracy of T2-weighted magnetic resonance (MR) imaging with that of multiparametric (MP) MR imaging combining T2-weighted imaging with diffusion-weighted (DW) MR imaging, dynamic contrast material-enhanced (DCE) MR imaging, or both in the detection of locally recurrent prostate cancer (PCa) after radiation therapy (RT). This retrospective HIPAA-compliant study was approved by the institutional review board; informed consent was waived. Fifty-three men (median age, 70 years) suspected of having post-RT recurrence of PCa underwent MP MR imaging, including DW and DCE sequences, within 6 months after biopsy. Two readers independently evaluated the likelihood of PCa with a five-point scale for T2-weighted imaging alone, T2-weighted imaging with DW imaging, T2-weighted imaging with DCE imaging, and T2-weighted imaging with DW and DCE imaging, with at least a 4-week interval between evaluations. Areas under the receiver operating characteristic curve (AUC) were calculated. Interreader agreement was assessed, and quantitative parameters (apparent diffusion coefficient [ADC], volume transfer constant [K(trans)], and rate constant [k(ep)]) were assessed at sextant- and patient-based levels with generalized estimating equations and the Wilcoxon rank sum test, respectively. At biopsy, recurrence was present in 35 (66%) of 53 patients. In detection of recurrent PCa, T2-weighted imaging with DW imaging yielded higher AUCs (reader 1, 0.79-0.86; reader 2, 0.75-0.81) than T2-weighted imaging alone (reader 1, 0.63-0.67; reader 2, 0.46-0.49 [P ≤ .014 for all]). DCE sequences did not contribute significant incremental value to T2-weighted imaging with DW imaging (reader 1, P > .99; reader 2, P = .35). Interreader agreement was higher for combinations of MP MR imaging than for T2-weighted imaging alone (κ = 0.34-0.63 vs κ = 0.17-0.20). Medians of quantitative parameters differed significantly (P < .0001 to P = .0233) between benign tissue and PCa (ADC, 1.64 × 10(-3) mm(2)/sec vs 1.13 × 10(-3) mm(2)/sec; K(trans), 0.16 min(-1) vs 0.33 min(-1); k(ep), 0.36 min(-1) vs 0.62 min(-1)). MP MR imaging has greater accuracy in the detection of recurrent PCa after RT than T2-weighted imaging alone, with no additional benefit if DCE is added to T2-weighted imaging and DW imaging.

To determine accuracy, intermethod agreement, and inter-reviewer agreement for multisequence magnetic resonance imaging (MRI) and 2-view orthogonal myelography in small-breed dogs with first-time intervertebral disk (IVD) extrusion. Prospective evaluation study. 24 dogs with thoracolumbar IVD extrusion. Each dog underwent MRI and myelography. Images obtained with each modality were independently evaluated and assigned standardized scores in a blinded manner by 3 reviewers. Results were compared with surgical findings. Inter-reviewer and intermethod agreements were assessed via κ statistics. Accuracy was assessed as the percentage of dogs for which ≥ 2 of 3 reviewers recorded findings identical to those determined surgically. Inter-reviewer agreement was substantial for site (κ = 0.70) and side of IVD extrusion (κ = 0.62) in T2-weighted magnetic resonance images and was substantial for site (κ = 0.72) and fair for side of extrusion (κ = 0.37) in myelographic images. Agreement for site between each modality and surgical findings was near perfect (κ = 0.94 and 0.88 for MRI and myelography, respectively). Intermethod agreement was substantial for site (κ = 0.71) and moderate for side of extrusion (κ = 0.40). Accuracy of MRI for site and side was 100% when results for T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequences were combined. Accuracy of myelography was 90.9% and 54.5% for site and side, respectively. Agreement between imaging results and surgical findings for identification of IVD extrusion sites in small-breed dogs was similar for MRI and myelography. However, MRI appeared to be more accurate than myelography and allowed evaluation of extradural compressive mass composition.

Background: Individual skull models of bone density and geometry are important when planning the expected transcranial ultrasound acoustic field and estimating mechanical and thermal safety in low-intensity transcranial ultrasound stimulation (TUS) studies. Computed tomography (CT) images have typically been used to estimate skull acoustic properties. However, obtaining CT images in research participants may be prohibitive due to exposure to ionising radiation and limited access to CT scanners within research groups. Objective: We present a validated open-source tool for researchers to obtain individual skull estimates from T1-weighted MR images, for use in acoustic simulations. We refined a previously trained and validated 3D convolutional neural network (CNN) to generate 100 keV pseudo-CTs. The network was pretrained on 110 individuals and refined and tested on a database of 37 healthy control individuals. We compared simulations based on reference CTs to simulations based on our pseudo-CTs and binary skull masks, a common alternative in the absence of CT. Compared with reference CTs, our CNN produced pseudo-CTs with a mean absolute error of 109.8 ± 13.0 HU across the whole head and 319.3 ± 31.9 HU in the skull. In acoustic simulations, the focal pressure was statistically equivalent for simulations based on reference CT and pseudo-CT (0.48 ± 0.04 MPa and 0.50 ± 0.04 MPa respectively) but not for binary skull masks (0.28 ± 0.05 MPa). We show that our network can produce pseudo-CT comparable to reference CTs in healthy individuals, and that these can be used in acoustic simulations.