Image quality assessment using deep learning in high b-value diffusion-weighted breast MRI.
Ontology highlight
ABSTRACT:
SUBMITTER: Kapsner LA
PROVIDER: S-EPMC10310703 | biostudies-literature | 2023 Jun
REPOSITORIES: biostudies-literature
Publications
Image quality assessment using deep learning in high b-value diffusion-weighted breast MRI.
Kapsner Lorenz A LA Balbach Eva L EL Folle Lukas L Laun Frederik B FB Nagel Armin M AM Liebert Andrzej A Emons Julius J Ohlmeyer Sabine S Uder Michael M Wenkel Evelyn E Bickelhaupt Sebastian S
Scientific reports 20230629 1
The objective of this IRB approved retrospective study was to apply deep learning to identify magnetic resonance imaging (MRI) artifacts on maximum intensity projections (MIP) of the breast, which were derived from diffusion weighted imaging (DWI) protocols. The dataset consisted of 1309 clinically indicated breast MRI examinations of 1158 individuals (median age [IQR]: 50 years [16.75 years]) acquired between March 2017 and June 2020, in which a DWI sequence with a high b-value equal to 1500 s/ ...[more]
Similar Datasets
Project description:ObjectivesMultiple b-value gas diffusion-weighted MRI (DW-MRI) enables non-invasive and quantitative assessment of lung morphometry, but its long acquisition time is not well-tolerated by patients. We aimed to accelerate multiple b-value gas DW-MRI for lung morphometry using deep learning.MethodsA deep cascade of residual dense network (DC-RDN) was developed to reconstruct high-quality DW images from highly undersampled k-space data. Hyperpolarized 129Xe lung ventilation images were acquired from 101 participants and were retrospectively collected to generate synthetic DW-MRI data to train the DC-RDN. Afterwards, the performance of the DC-RDN was evaluated on retrospectively and prospectively undersampled multiple b-value 129Xe MRI datasets.ResultsEach slice with size of 64 × 64 × 5 could be reconstructed within 7.2 ms. For the retrospective test data, the DC-RDN showed significant improvement on all quantitative metrics compared with the conventional reconstruction methods (p < 0.05). The apparent diffusion coefficient (ADC) and morphometry parameters were not significantly different between the fully sampled and DC-RDN reconstructed images (p > 0.05). For the prospectively accelerated acquisition, the required breath-holding time was reduced from 17.8 to 4.7 s with an acceleration factor of 4. Meanwhile, the prospectively reconstructed results showed good agreement with the fully sampled images, with a mean difference of -0.72% and -0.74% regarding global mean ADC and mean linear intercept (Lm) values.ConclusionsDC-RDN is effective in accelerating multiple b-value gas DW-MRI while maintaining accurate estimation of lung microstructural morphometry, facilitating the clinical potential of studying lung diseases with hyperpolarized DW-MRI.Key points• The deep cascade of residual dense network allowed fast and high-quality reconstruction of multiple b-value gas diffusion-weighted MRI at an acceleration factor of 4. • The apparent diffusion coefficient and morphometry parameters were not significantly different between the fully sampled images and the reconstructed results (p > 0.05). • The required breath-holding time was reduced from 17.8 to 4.7 s and each slice with size of 64 × 64 × 5 could be reconstructed within 7.2 ms.
| S-EPMC8276538 | biostudies-literature
Project description:In recent years, deep learning (DL) networks have been widely used in super-resolution (SR) and exhibit improved performance. In this paper, an image quality assessment (IQA)-guided single image super-resolution (SISR) method is proposed in DL architecture, in order to achieve a nice tradeoff between perceptual quality and distortion measure of the SR result. Unlike existing DL-based SR algorithms, an IQA net is introduced to extract perception features from SR results, calculate corresponding loss fused with original absolute pixel loss, and guide the adjustment of SR net parameters. To solve the problem of heterogeneous datasets used by IQA and SR networks, an interactive training model is established via cascaded network. We also propose a pairwise ranking hinge loss method to overcome the shortcomings of insufficient samples during training process. The performance comparison between our proposed method with recent SISR methods shows that the former achieves a better tradeoff between perceptual quality and distortion measure than the latter. Extensive benchmark experiments and analyses also prove that our method provides a promising and opening architecture for SISR, which is not confined to a specific network model.
| S-EPMC7595386 | biostudies-literature
Project description:In this paper, we present a deep learning method, DDMReg, for accurate registration between diffusion MRI (dMRI) datasets. In dMRI registration, the goal is to spatially align brain anatomical structures while ensuring that local fiber orientations remain consistent with the underlying white matter fiber tract anatomy. DDMReg is a novel method that uses joint whole-brain and tract-specific information for dMRI registration. Based on the successful VoxelMorph framework for image registration, we propose a novel registration architecture that leverages not only whole brain information but also tract-specific fiber orientation information. DDMReg is an unsupervised method for deformable registration between pairs of dMRI datasets: it does not require nonlinearly pre-registered training data or the corresponding deformation fields as ground truth. We perform comparisons with four state-of-the-art registration methods on multiple independently acquired datasets from different populations (including teenagers, young and elderly adults) and different imaging protocols and scanners. We evaluate the registration performance by assessing the ability to align anatomically corresponding brain structures and ensure fiber spatial agreement between different subjects after registration. Experimental results show that DDMReg obtains significantly improved registration performance compared to the state-of-the-art methods. Importantly, we demonstrate successful generalization of DDMReg to dMRI data from different populations with varying ages and acquired using different acquisition protocols and different scanners.
| S-EPMC9273049 | biostudies-literature
Project description:ObjectiveTo assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm.Materials and methodsThis retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher's exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE.ResultsA total of 773 consecutive patients (median age 61 [IQR 56-67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67-76%] vs. 63% [95% CI 56-69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62-80%] vs. 75% [95% CI 63-85%]), positive predictive value (44% [95% CI 39-49%] vs. 38% [95% CI 32-43%]), or negative predictive value (89% [95% CI 86-92%] vs. 89% [95% CI 85-93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54-5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63-4.24; P = 0.24).ConclusionOur study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology.
| S-EPMC11300622 | biostudies-literature
Project description:Background Perfusion imaging is important to identify a target mismatch in stroke but requires contrast agents and postprocessing software. Purpose To use a deep learning model to predict the hypoperfusion lesion in stroke and identify patients with a target mismatch profile from diffusion-weighted imaging (DWI) and clinical information alone, using perfusion MRI as the reference standard. Materials and Methods Imaging data sets of patients with acute ischemic stroke with baseline perfusion MRI and DWI were retrospectively reviewed from multicenter data available from 2008 to 2019 (Imaging Collaterals in Acute Stroke, Diffusion and Perfusion Imaging Evaluation for Understanding Stroke Evolution 2, and University of California, Los Angeles stroke registry). For perfusion MRI, rapid processing of perfusion and diffusion software automatically segmented the hypoperfusion lesion (time to maximum, ≥6 seconds) and ischemic core (apparent diffusion coefficient [ADC], ≤620 × 10-6 mm2/sec). A three-dimensional U-Net deep learning model was trained using baseline DWI, ADC, National Institutes of Health Stroke Scale score, and stroke symptom sidedness as inputs, with the union of hypoperfusion and ischemic core segmentation serving as the ground truth. Model performance was evaluated using the Dice score coefficient (DSC). Target mismatch classification based on the model was compared with that of the clinical-DWI mismatch approach defined by the DAWN trial by using the McNemar test. Results Overall, 413 patients (mean age, 67 years ± 15 [SD]; 207 men) were included for model development and primary analysis using fivefold cross-validation (247, 83, and 83 patients in the training, validation, and test sets, respectively, for each fold). The model predicted the hypoperfusion lesion with a median DSC of 0.61 (IQR, 0.45-0.71). The model identified patients with target mismatch with a sensitivity of 90% (254 of 283; 95% CI: 86, 93) and specificity of 77% (100 of 130; 95% CI: 69, 83) compared with the clinical-DWI mismatch sensitivity of 50% (140 of 281; 95% CI: 44, 56) and specificity of 89% (116 of 130; 95% CI: 83, 94) (P < .001 for all). Conclusion A three-dimensional U-Net deep learning model predicted the hypoperfusion lesion from diffusion-weighted imaging (DWI) and clinical information and identified patients with a target mismatch profile with higher sensitivity than the clinical-DWI mismatch approach. ClinicalTrials.gov registration nos. NCT02225730, NCT01349946, NCT02586415 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Kallmes and Rabinstein in this issue.
| S-EPMC10068889 | biostudies-literature
Project description:Diffusion-weighted (DW) MRI is a rapid technique that measures the mobility of water molecules within tissue, reflecting the cellular microenvironment. At DW MRI, breast cancers typically exhibit reduced diffusivity and appear hyperintense to surrounding tissues. On the basis of this characteristic, DW MRI may offer an unenhanced method to detect breast cancer without the costs and safety concerns associated with dynamic contrast material-enhanced MRI, the current reference standard in the setting of high-risk screening. This application of DW MRI has not been widely explored but is particularly timely given the growing health concerns related to the long-term use of gadolinium-based contrast material. Moreover, increasing breast density notification legislation across the United States is raising awareness of the limitations of mammography in women with dense breasts, emphasizing the need for additional cost-effective supplemental screening examinations. Preliminary studies suggest unenhanced MRI with DW MRI may provide higher sensitivity than screening mammography for the detection of breast malignancies. Larger prospective multicenter trials are needed to validate single-center findings and assess the performance of DW MRI for generalized breast cancer screening. Standardization of DW MRI acquisition and interpretation is essential to ensure reliable sensitivity and specificity, and an optimal approach for screening using readily available techniques is proposed here.
| S-EPMC6884069 | biostudies-literature
Project description:ObjectiveThis study evaluated the effect of an accelerated three-dimensional (3D) T1-weighted pediatric brain MRI protocol using a deep learning (DL)-based reconstruction algorithm on scan time and image quality.Materials and methodsThis retrospective study included 46 pediatric patients who underwent conventional and accelerated, pre- and post-contrast, 3D T1-weighted brain MRI using a 3T scanner (SIGNA Premier; GE HealthCare) at a single tertiary referral center between March 1, 2023, and April 30, 2023. Conventional scans were reconstructed using intensity Filter A (Conv), whereas accelerated scans were reconstructed using intensity Filter A (Fast_A) and a DL-based algorithm (Fast_DL). Image quality was assessed quantitatively based on the coefficient of variation, relative contrast, apparent signal-to-noise ratio (aSNR), and apparent contrast-to-noise ratio (aCNR) and qualitatively according to radiologists' ratings of overall image quality, artifacts, noisiness, gray-white matter differentiation, and lesion conspicuity.ResultsThe acquisition times for the pre- and post-contrast scans were 191 and 135 seconds, respectively, for the conventional scan. With the accelerated protocol, these were reduced to 135 and 80 seconds, achieving time reductions of 29.3% and 40.7%, respectively. DL-based reconstruction significantly reduced the coefficient of variation, improved the aSNR, aCNR, and overall image quality, and reduced the number of artifacts compared with the conventional acquisition method (all P < 0.05). However, the lesion conspicuity remained similar between the two protocols.ConclusionUtilizing a DL-based reconstruction algorithm in accelerated 3D T1-weighted pediatric brain MRI can significantly shorten the acquisition time, enhance image quality, and reduce artifacts, making it a viable option for pediatric imaging.
| S-EPMC11794287 | biostudies-literature
Project description:BackgroundA variety of external factors might seriously degrade PET image quality and lead to inconsistent results. The aim of this study is to explore a potential PET image quality assessment (QA) method with deep learning (DL).MethodsA total of 89 PET images were acquired from Peking Union Medical College Hospital (PUMCH) in China in this study. Ground-truth quality for images was assessed by two senior radiologists and classified into five grades (grade 1, grade 2, grade 3, grade 4, and grade 5). Grade 5 is the best image quality. After preprocessing, the Dense Convolutional Network (DenseNet) was trained to automatically recognize optimal- and poor-quality PET images. Accuracy (ACC), sensitivity, specificity, receiver operating characteristic curve (ROC), and area under the ROC Curve (AUC) were used to evaluate the diagnostic properties of all models. All indicators of models were assessed using fivefold cross-validation. An image quality QA tool was developed based on our deep learning model. A PET QA report can be automatically obtained after inputting PET images.ResultsFour tasks were generated. Task2 showed worst performance in AUC,ACC, specificity and sensitivity among 4 tasks, and task1 showed unstable performance between training and testing and task3 showed low specificity in both training and testing. Task 4 showed the best diagnostic properties and discriminative performance between poor image quality (grade 1, grade 2) and good quality (grade 3, grade 4, grade 5) images. The automated quality assessment of task 4 showed ACC = 0.77, specificity = 0.71, and sensitivity = 0.83, in the train set; ACC = 0.85, specificity = 0.79, and sensitivity = 0.91, in the test set, respectively. The ROC measuring performance of task 4 had an AUC of 0.86 in the train set and 0.91 in the test set. The image QA tool could output basic information of images, scan and reconstruction parameters, typical instances of PET images, and deep learning score.ConclusionsThis study highlights the feasibility of the assessment of image quality in PET images using a deep learning model, which may assist with accelerating clinical research by reliably assessing image quality.
| S-EPMC10243071 | biostudies-literature
Project description:ObjectiveTo investigate the clinical feasibility of synthetic diffusion-weighted imaging (sDWI) at different b-values in patients with breast cancer by assessing the diagnostic image quality and the quantitative measurements compared with conventional diffusion-weighted imaging (cDWI).Materials and methodsFifty patients with breast cancer were assessed using cDWI at b-values of 800 and 1500 s/mm² (cDWI800 and cDWI1500) and sDWI at b-values of 1000 and 1500 s/mm² (sDWI1000 and sDWI1500). Qualitative analysis (normal glandular tissue suppression, overall image quality, and lesion conspicuity) was performed using a 4-point Likert-scale for all DWI sets and the cancer detection rate (CDR) was calculated. We also evaluated cancer-to-parenchyma contrast ratios for each DWI set in 45 patients with the lesion identified on any of the DWI sets. Statistical comparisons were performed using Friedman test, one-way analysis of variance, and Cochran's Q test.ResultsAll parameters of qualitative analysis, cancer-to-parenchyma contrast ratios, and CDR increased with increasing b-values, regardless of the type of imaging (synthetic or conventional) (p < 0.001). Additionally, sDWI1500 provided better lesion conspicuity than cDWI1500 (3.52 ± 0.92 vs. 3.39 ± 0.90, p < 0.05). Although cDWI1500 showed better normal glandular tissue suppression and overall image quality than sDWI1500 (3.66 ± 0.78 and 3.73 ± 0.62 vs. 3.32 ± 0.90 and 3.35 ± 0.81, respectively; p < 0.05), there was no significant difference in their CDR (90.0%). Cancer-to-parenchyma contrast ratios were greater in sDWI1500 than in cDWI1500 (0.63 ± 0.17 vs. 0.55 ± 0.18, p < 0.001).ConclusionsDWI1500 can be feasible for evaluating breast cancers in clinical practice. It provides higher tumor conspicuity, better cancer-to-parenchyma contrast ratio, and comparable CDR when compared with cDWI1500.
| S-EPMC7371621 | biostudies-literature
Project description:ObjectiveThe A6702 multisite trial confirmed that apparent diffusion coefficient (ADC) measures can improve breast MRI accuracy and reduce unnecessary biopsies, but also found that technical issues rendered many lesions non-evaluable on diffusion-weighted imaging (DWI). This secondary analysis investigated factors affecting lesion evaluability and impact on diagnostic performance.MethodsThe A6702 protocol was IRB-approved at 10 institutions; participants provided informed consent. In total, 103 women with 142 MRI-detected breast lesions (BI-RADS assessment category 3, 4, or 5) completed the study. DWI was acquired at 1.5T and 3T using a four b-value, echo-planar imaging sequence. Scans were reviewed for multiple quality factors (artifacts, signal-to-noise, misregistration, and fat suppression); lesions were considered non-evaluable if there was low confidence in ADC measurement. Associations of lesion evaluability with imaging and lesion characteristics were determined. Areas under the receiver operating characteristic curves (AUCs) were compared using bootstrapping.ResultsThirty percent (42/142) of lesions were non-evaluable on DWI; 23% (32/142) with image quality issues, 7% (10/142) with conspicuity and/or localization issues. Misregistration was the only factor associated with non-evaluability (P = 0.001). Smaller (≤10 mm) lesions were more commonly non-evaluable than larger lesions (p <0.03), though not significant after multiplicity correction. The AUC for differentiating benign and malignant lesions increased after excluding non-evaluable lesions, from 0.61 (95% CI: 0.50-0.71) to 0.75 (95% CI: 0.65-0.84).ConclusionImage quality remains a technical challenge in breast DWI, particularly for smaller lesions. Protocol optimization and advanced acquisition and post-processing techniques would help to improve clinical utility.
| S-EPMC7835633 | biostudies-literature