Dataset Information

Accelerate gas diffusion-weighted MRI for lung morphometry with deep learning.

ABSTRACT:

Objectives

Multiple 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.

Methods

A 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.

Results

Each 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 (L_m) values.

Conclusions

DC-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.

SUBMITTER: Duan C

PROVIDER: S-EPMC8276538 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundHyperpolarized gas MRI can quantify regional lung ventilation via biomarkers, including the ventilation defect percentage (VDP). VDP is computed from segmentations derived from spatially co-registered functional hyperpolarized gas and structural proton (1 H)-MRI. Although acquired at similar lung inflation levels, they are frequently misaligned, requiring a lung cavity estimation (LCE). Recently, single-channel, mono-modal deep learning (DL)-based methods have shown promise for pulmonary image segmentation problems. Multichannel, multimodal approaches may outperform single-channel alternatives.PurposeWe hypothesized that a DL-based dual-channel approach, leveraging both 1 H-MRI and Xenon-129-MRI (129 Xe-MRI), can generate LCEs more accurately than single-channel alternatives.Study typeRetrospective.PopulationA total of 480 corresponding 1 H-MRI and 129 Xe-MRI scans from 26 healthy participants (median age [range]: 11 [8-71]; 50% females) and 289 patients with pulmonary pathologies (median age [range]: 47 [6-83]; 51% females) were split into training (422 scans [88%]; 257 participants [82%]) and testing (58 scans [12%]; 58 participants [18%]) sets.Field strength/sequence1.5-T, three-dimensional (3D) spoiled gradient-recalled 1 H-MRI and 3D steady-state free-precession 129 Xe-MRI.AssessmentWe developed a multimodal DL approach, integrating 129 Xe-MRI and 1 H-MRI, in a dual-channel convolutional neural network. We compared this approach to single-channel alternatives using manually edited LCEs as a benchmark. We further assessed a fully automatic DL-based framework to calculate VDPs and compared it to manually generated VDPs.Statistical testsFriedman tests with post hoc Bonferroni correction for multiple comparisons compared single-channel and dual-channel DL approaches using Dice similarity coefficient (DSC), average boundary Hausdorff distance (average HD), and relative error (XOR) metrics. Bland-Altman analysis and paired t-tests compared manual and DL-generated VDPs. A P value < 0.05 was considered statistically significant.ResultsThe dual-channel approach significantly outperformed single-channel approaches, achieving a median (range) DSC, average HD, and XOR of 0.967 (0.867-0.978), 1.68 mm (37.0-0.778), and 0.066 (0.246-0.045), respectively. DL-generated VDPs were statistically indistinguishable from manually generated VDPs (P = 0.710).Data conclusionOur dual-channel approach generated LCEs, which could be integrated with ventilated lung segmentations to produce biomarkers such as the VDP without manual intervention.Evidence level4.Technical efficacyStage 1.

Project description:Diffusion weighted imaging (DWI) constitutes a major functional parameter performed in Magnetic Resonance Imaging (MRI). The DW sequence is performed by acquiring a set of native images described by their b-values, each b-value representing the strength of the diffusion MR gradients specific to that sequence. By fitting the data with models describing the motion of water in tissue, an apparent diffusion coefficient (ADC) map is built and allows the assessment of water mobility inside the tissue. The high cellularity of tumors restricts the water diffusion and decreases the value of ADC within tumors, which makes them appear hypointense on ADC maps. The role of this sequence now largely exceeds its first clinical apparitions in neuroimaging, whereby the method helped diagnose the early phases of cerebral ischemic stroke. The applications extend to whole-body imaging for both neoplastic and non-neoplastic diseases. This review emphasizes the integration of DWI in the genitourinary system imaging by outlining the sequence's usage in female pelvis, prostate, bladder, penis, testis and kidney MRI. In gynecologic imaging, DWI is an essential sequence for the characterization of cervix tumors and endometrial carcinomas, as well as to differentiate between leiomyosarcoma and benign leiomyoma of the uterus. In ovarian epithelial neoplasms, DWI provides key information for the characterization of solid components in heterogeneous complex ovarian masses. In prostate imaging, DWI became an essential part of multi-parametric Magnetic Resonance Imaging (mpMRI) to detect prostate cancer. The Prostate Imaging-Reporting and Data System (PI-RADS) scoring the probability of significant prostate tumors has significantly contributed to this success. Its contribution has established mpMRI as a mandatory examination for the planning of prostate biopsies and radical prostatectomy. Following a similar approach, DWI was included in multiparametric protocols for the bladder and the testis. In renal imaging, DWI is not able to robustly differentiate between malignant and benign renal tumors but may be helpful to characterize tumor subtypes, including clear-cell and non-clear-cell renal carcinomas or low-fat angiomyolipomas. One of the most promising developments of renal DWI is the estimation of renal fibrosis in chronic kidney disease (CKD) patients. In conclusion, DWI constitutes a major advancement in genitourinary imaging with a central role in decision algorithms in the female pelvis and prostate cancer, now allowing promising applications in renal imaging or in the bladder and testicular mpMRI.

Project description:ObjectivesTo investigate the diagnostic performance of deep transfer learning (DTL) to detect liver cirrhosis from clinical MRI.MethodsThe dataset for this retrospective analysis consisted of 713 (343 female) patients who underwent liver MRI between 2017 and 2019. In total, 553 of these subjects had a confirmed diagnosis of liver cirrhosis, while the remainder had no history of liver disease. T2-weighted MRI slices at the level of the caudate lobe were manually exported for DTL analysis. Data were randomly split into training, validation, and test sets (70%/15%/15%). A ResNet50 convolutional neural network (CNN) pre-trained on the ImageNet archive was used for cirrhosis detection with and without upstream liver segmentation. Classification performance for detection of liver cirrhosis was compared to two radiologists with different levels of experience (4th-year resident, board-certified radiologist). Segmentation was performed using a U-Net architecture built on a pre-trained ResNet34 encoder. Differences in classification accuracy were assessed by the χ2-test.ResultsDice coefficients for automatic segmentation were above 0.98 for both validation and test data. The classification accuracy of liver cirrhosis on validation (vACC) and test (tACC) data for the DTL pipeline with upstream liver segmentation (vACC = 0.99, tACC = 0.96) was significantly higher compared to the resident (vACC = 0.88, p < 0.01; tACC = 0.91, p = 0.01) and to the board-certified radiologist (vACC = 0.96, p < 0.01; tACC = 0.90, p < 0.01).ConclusionThis proof-of-principle study demonstrates the potential of DTL for detecting cirrhosis based on standard T2-weighted MRI. The presented method for image-based diagnosis of liver cirrhosis demonstrated expert-level classification accuracy.Key points• A pipeline consisting of two convolutional neural networks (CNNs) pre-trained on an extensive natural image database (ImageNet archive) enables detection of liver cirrhosis on standard T2-weighted MRI. • High classification accuracy can be achieved even without altering the pre-trained parameters of the convolutional neural networks. • Other abdominal structures apart from the liver were relevant for detection when the network was trained on unsegmented images.