Background: We investigated inflammation-induced changes in femoral hematopoietic bone marrow using advanced magnetic resonance imaging (MRI) techniques, including T2-weighted imaging, scalar T2 mapping, and machine learning-enhanced T2 distribution analysis to improve the detection of bone marrow microstructural alterations. Findings were correlated with histological markers and systemic inflammation. Methods: Using a 9.4-T magnet, T2-weighted and multislice multiecho sequences were applied to evaluate bone marrow in female C57BL/6J mice divided into three groups: (1) controls; (2) lipopolysaccharide-induced acute inflammation (LPS); and (3) streptozotocin (STZ)- and LPS-induced diabetic inflammation (STZ + LPS). T2 relaxation times and their distributions with scalar mapping and model-informed machine learning (MIML) were analyzed. Correlations with histological iron levels and blood neutrophil counts were assessed. Results: T2-weighted imaging showed a reduced signal-to-noise ratio in inflamed bone marrow (p = 0.034). Scalar T2 mapping identified decreased T2 relaxation times (p = 0.042), moderately correlating with neutrophil counts (ρ = 0.027) and iron levels (ρ = 0.016). MIML-enhanced T2 distribution analysis exhibited superior sensitivity than scalar T2 mapping, revealing significant reductions in the first T2 distribution peak (p = 0.0025), which strongly correlated with neutrophil counts (ρ = 0.0016) and iron sequestration (ρ = 0.0002). Histology confirmed elevated iron deposits in inflamed marrow, aligning with systemic inflammation. Conclusion: Combining T2-weighted imaging, scalar T2 mapping, and MIML-enhanced T2 distribution analysis offers complementary insights into inflammation-induced bone marrow remodeling. T2 distribution analysis emerged as a more sensitive tool for detecting microstructural changes, such as iron sequestration, supporting its potential as a noninvasive biomarker for diagnosing and monitoring inflammatory diseases. Relevance statement: This study highlights the potential of advanced MRI T2 analysis and machine learning methods for noninvasive detection of inflammation-induced microstructural changes in bone marrow, offering promising diagnostic tools for inflammatory diseases. Key Points: This study investigated inflammation-induced changes in bone marrow with T2 MRI and MIML. MIML outperformed quantitative scalar T2 analysis, increasingly detecting inflammation and iron sequestration in the hematopoietic bone marrow. T2 MRI with MIML analysis could aid in the early diagnosis and management of inflammatory diseases. Graphical
Background: Virtual contrast-enhanced (vCE) imaging techniques are an emerging topic of research in breast MRI. Purpose: To investigate how different combinations of T1-weighted (T1w), T2-weighted (T2w), and diffusion-weighted imaging (DWI) impact the performance of vCE breast MRI. Materials and Methods: The IRB-approved, retrospective study included 1064 multiparametric breast MRI scans (age:52±12 years) obtained from 2017-2020 (single site, two 3T MRI). Eleven independent neural networks were trained to derive vCE images from varying input combinations of T1w, T2w, and multi-b-value DWI sequences (b-value=50–1500s/mm 2 ). Three readers evaluated the vCE images with regards to qualitative scores of diagnostic image quality, image sharpness, satisfaction with contrast/signal-to-noise-ratio, and lesion/non-mass enhancement conspicuity. Quantitative metrics (SSIM, PSNR, NRMSE, and median symmetrical accuracy) were analyzed and statistically compared between the input combinations for the full breast volume and both enhancing and non-enhancing target findings. Results: The independent test set consisted of 187 cases. The quantitative metrics significantly improved in target findings when multi-b-value DWI sequences were included during vCE training (p<.05). Non-significant effects (p>.05) were observed for the quantitative metrics on the full breast volume when comparing input combinations including T1w. Using T1w and DWI acquisitions during vCE training is necessary to achieve high satisfaction with contrast/SNR and good conspicuity of the enhancing findings. The input combination of T1w, T2w, and DWI sequences with three b-values showed the best qualitative performance. Conclusion: vCE breast MRI performance is significantly influenced by input sequences. Quantitative metrics and visual quality of vCE images significantly benefit when a multi b-value DWI is added to morphologic T1w-/T2w-sequences as input for model training. Key Results: The inclusion of diffusion-weighted imaging significantly improves the conspicuity of lesions/non-mass enhancements and satisfaction with the image contrast in virtual contrast-enhanced breast MRI. The quality of virtual contrast-enhanced breast MRI scans benefits from the inclusion of high-resolution morphologic T1-weighted image acquisitions. Quantitative metrics such as the structural similarity index and peak signal-to-noise ratio calculated over the entire breast volume insufficiently reflect variations in lesion/non-mass enhancement’s individual characteristics.
Diffusion-weighted imaging (DWI) combined with radiomics can aid in the differentiation of breast lesions. Segmentation characteristics, however, might influence radiomic features. To evaluate feature stability, we implemented a standardized pipeline featuring shifts and shape variations of the underlying segmentations. A total of 103 patients were retrospectively included in this IRB-approved study after multiparametric diagnostic breast 3T MRI with a spin-echo diffusion-weighted sequence with echoplanar readout (b-values: 50, 750 and 1500 s/mm2). Lesion segmentations underwent shifts and shape variations, with >100 radiomic features extracted from apparent diffusion coefficient (ADC) maps for each variation. These features were then compared and ranked based on their stability, measured by the Overall Concordance Correlation Coefficient (OCCC) and Dynamic Range (DR). Results showed variation in feature robustness to segmentation changes. The most stable features, excluding shape-related features, were FO (Mean, Median, RootMeanSquared), GLDM (DependenceNonUniformity), GLRLM (RunLengthNonUniformity), and GLSZM (SizeZoneNonUniformity), which all had OCCC and DR > 0.95 for both shifting and resizing the segmentation. Perimeter, MajorAxisLength, MaximumDiameter, PixelSurface, MeshSurface, and MinorAxisLength were the most stable features in the Shape category with OCCC and DR > 0.95 for resizing. Considering the variability in radiomic feature stability against segmentation variations is relevant when interpreting radiomic analysis of breast DWI data.
5 October 2026 in Journal of Magnetic Resonance Imaging
Background: Diffusion‐weighted imaging (DWI) can support lesion detection and characterization in breast MRI. Therefore, DWI is increasingly being incorporated into breast MRI protocols to address some of the shortcomings of routine clinical breast MRI. However, especially high b value DWI can be prone to intensity artifacts that can affect diagnostic image assessment. Purpose: To detect hyper‐ and hypointense artifacts on high b value DWI ( b = 1500 s/mm 2 ) using deep learning, employing either a binary classification (artifact presence) or a multiclass classification (artifact intensity) approach on a slice‐wise dataset. Study Type: Retrospective. Study Population: 11,806 DWI slices were acquired from 156 examinations performed on female patients between 2022 and mid‐2023. For both hyper‐ and hypointense artifact classification, the slices were split into test, validation, and holdout test set with 8164/1806/1836 and 8164/1820/1822 slices in these sets respectively. Field Strength/Sequence: 3 T spin‐echo planar diffusion‐weighted sequence with b values: 50, 750, and 1500 s/mm 2 . Assessment: Three convolutional neural network (CNN) architectures (DenseNet121, ResNet18, and SEResNet50) were trained for binary classification of hyper‐ and hypointense artifacts on slice‐wise labeled data. The best performing model (DenseNet121) was applied to an independent holdout test set and further trained separately for multiclass classification. Statistical Tests: Performance of the networks was evaluated using accuracy, precision, recall, and areas under the receiver operating characteristic curve (AUROC) and under the precision recall curve (AUPRC). Radiologist evaluated bounding box positions on a 5‐point Likert‐like scale across 150 slices for validation and 200 slices for the holdout test set, derived from the network's Grad‐CAM heatmaps. Results: DenseNet121 achieved AUROCs of 0.91 and 0.95 for hyper‐ and hypointense artifact detection, respectively, and weighted AUROCs of 0.84 and 0.90 for multiclass classification on single‐slice high b value diffusion‐weighted images, achieving mean scores of 3.52 ± 0.81 for hyperintense artifacts and 3.62 ± 0.65 for hypointense artifacts. Data Conclusion: Hyper‐ and hypointense artifact detection in slice‐wise breast DWI MRI dataset ( b = 1500 s/mm 2 ) using CNNs, particularly DenseNet121, suggests potential reliability and requires further validation. Evidence Level: 3. Technical Efficacy: Stage 3.
Background Breast magnetic resonance imaging (MRI) protocols often include T2-weighted fat-saturated (T2w-FS) sequences, which are vital for tissue characterization but significantly increase scan time. Purpose This study aims to evaluate whether a 2D-U-Net neural network can generate virtual T2w-FS images from routine multiparametric breast MRI sequences. Materials and Methods This IRB approved, retrospective study included n=914 breast MRI examinations performed between January 2017 and June 2020. The dataset was divided into training (n=665), validation (n=74), and test sets (n=175). The U-Net was trained on T1-weighted (T1w), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) sequences to generate virtual T2w-FS images (VirtuT2). Quantitative metrics and a qualitative multi-reader assessment by two radiologists were used to evaluate the VirtuT2 images. Results VirtuT2 images demonstrated high structural similarity (SSIM=0.87) and peak signal-to-noise ratio (PSNR=24.90) compared to original T2w-FS images. High level of the frequency error norm (HFNE=0.87) indicates strong blurring presence in the VirtuT2 images, which was also confirmed in qualitative reading. Radiologists correctly identified VirtuT2 images with 92.3% and 94.2% accuracy, respectively. No significant difference in diagnostic image quality (DIQ) was noted for one reader (p=0.21), while the other reported significantly lower DIQ for VirtuT2 (p<=0.001). Moderate inter-reader agreement was observed for edema detection on T2w-FS images (ƙ=0.43), decreasing to fair on VirtuT2 images (ƙ=0.36). Conclusion The 2D-U-Net can technically generate virtual T2w-FS images with high similarity to real T2w-FS images, though blurring remains a limitation. Further investigation of other architectures and using larger datasets are needed to improve clinical applicability. Summary Statement Virtual T2-weighted fat-saturated images can be generated from routine breast MRI sequences using convolutional neural networks, showing high structural similarity but with notable blurring, necessitating further refinement for clinical use. Key Results Images with T2w-FS characteristics can be virtually generated from T1w and DWI images using deep learning Image blurring occurring in the VirtuT2 image limit clinical use for the current moment Further investigation of different architectures and with larger datasets are necessary in the future to improve the VirtuT2 performance.