Compressed sensing and deep learning reconstruction for women’s pelvic MRI denoising: Utility for improving image quality and examination time in routine clinical practice

Ueda, Takahiro; Ohno, Yoshiharu; Yamamoto, Kaori; Iwase, Akiyoshi; Fukuba, Takashi; Hanamatsu, Satomu; Obama, Yuki; Ikeda, Hirotaka; Ikedo, Masato; Yui, Masao; Murayama, Kazuhiro; Toyama, Hiroshi

doi:10.1016/j.ejrad.2020.109430

Cited by 59 publications

(61 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

“…The further reduction in the scanning time by the combination of the DLR and compressed sensing is consistent with the results of a recent report. 17 The image degradation accompanying compressed sensing is caused mainly by noise amplification, which increases logarithmically with the reduction factor of compressed sensing. 24 , 25 Therefore, the noise amplification accompanying the compressed sensing was also controlled by the DLR and resulted in the synergic effect of reducing the scanning time.…”

Section: Discussionmentioning

confidence: 99%

“…2 ). For each tissue, we calculated the signal-to-noise ratio (SNR) and contrast-to-noise ratio of the muscle (CNR) using the following formulas from the literature: 17 , 18 SNR = SI tissue /SD background air , CNR = SI tissue – SI muscle /SI muscle . SI was taken as the average signal intensity of the ROIs, and SD as the standard deviation of the ROIs.…”

Section: Methodsmentioning

confidence: 99%

“…2). For each tissue, we calculated the signal-to-noise ratio (SNR) and contrastto-noise ratio of the muscle (CNR) using the following formulas from the literature: 17,18…”

Section: Quantitative Image Analysismentioning

confidence: 99%

See 3 more Smart Citations

Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Kashiwagi

Tanaka

Yamashita

et al. 2021

Acta Radiologica Open

View full text Add to dashboard Cite

Background Several deep learning-based methods have been proposed for addressing the long scanning time of magnetic resonance imaging. Most are trained using brain 3T magnetic resonance images, but is unclear whether performance is affected when applying these methods to different anatomical sites and at different field strengths. Purpose To validate the denoising performance of deep learning-based reconstruction method trained by brain and knee 3T magnetic resonance images when applied to lumbar 1.5T magnetic resonance images. Material and Methods Using a 1.5T scanner, we obtained lumber T2-weighted sequences in 10 volunteers using three different scanning times: 228 s (standard), 119 s (double-fast), and 68 s (triple-fast). We compared the images obtained by the standard sequence with those obtained by the deep learning-based reconstruction-applied faster sequences. Results Signal-to-noise ratio values were significantly higher for deep learning-based reconstruction-double-fast than for standard and did not differ significantly between deep learning-based reconstruction-triple-fast and standard. Contrast-to-noise ratio values also did not differ significantly between deep learning-based reconstruction-triple-fast and standard. Qualitative scores for perceived signal-to-noise ratio and overall image quality were significantly higher for deep learning-based reconstruction-double fast and deep learning-based reconstruction-triple-fast than for standard. Average scores for sharpness, contrast, and structure visibility were equal to or higher for deep learning-based reconstruction-double-fast and deep learning-based reconstruction-triple-fast than for standard, but the differences were not statistically significant. The average scores for artifact were lower for deep learning-based reconstruction-double-fast and deep learning-based reconstruction-triple-fast than for standard, but the differences were not statistically significant. Conclusion The deep learning-based reconstruction method trained by 3T brain and knee images may reduce the scanning time of 1.5T lumbar magnetic resonance images by one-third without sacrificing image quality.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…2). For each tissue, we calculated the signal-to-noise ratio (SNR) and contrastto-noise ratio of the muscle (CNR) using the following formulas from the literature: 17,18…”

Section: Quantitative Image Analysismentioning

confidence: 99%

See 2 more Smart Citations

Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Kashiwagi

Tanaka

Yamashita

et al. 2021

Acta Radiologica Open

View full text Add to dashboard Cite

show abstract

“…This CT scan was used for attenuation coefficient (AC) instead of disease diagnosis, with its effective radiation dose (~2.4 mSv) being significantly lower than a typical diagnostic body CT exam and the CT component of a typical modern PET/CT exam (~5-10 mSv) [13][14][15]. With the constant advancements of CT tube and detector technologies [16], patient-specific scan technologies, and artificial intelligence (AI)-based CT dose reduction technologies (e.g., TrueFidelity Deep Learning Image Reconstruction from GE Healthcare [17,18], Advanced Intelligent Clear-IQ Engine from Canon Medical Systems USA Inc. [19][20][21], among others), there is considerable promise for the CT component of whole-body PET/CT exam to routinely achieve sub-mSv effective doses in the future, which means the entire whole-body PET/CT exam with ultra-low-activity of 18 F-FDG can be accomplished under 2 mSv. This will provide unprecedented possibilities for a variety of clinical scenarios such as longitudinal scans of (cancer) patients when monitoring the therapeutic response [22,23], as well as routine (repeated) scans in pediatric patients [24].…”

mentioning

confidence: 99%

Dynamic PET imaging with ultra-low-activity of 18F-FDG: unleashing the potential of total-body PET

Lan

Fan

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

A Faster Prostate MRI: Comparing a Novel Denoised, Single‐Average T₂ Sequence to the Conventional Multiaverage T₂ Sequence Regarding Lesion Detection and PI‐RADS Score Assessment

Kelleher

Macdonald

Jaffe

et al. 2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background: The T 2 w sequence is a standard component of a prostate MRI examination; however, it is time-consuming, requiring multiple signal averages to achieve acceptable image quality. Purpose/Hypothesis: To determine whether a denoised, single-average T 2 sequence (T 2 -R) is noninferior to the standard multiaverage T 2 sequence (T 2 -S) in terms of lesion detection and PI-RADS score assessment. Study Type: Retrospective. Population: A total of 45 males (age range 60-75 years) who underwent clinically indicated prostate MRI examinations, 21 of whom had pathologically proven prostate cancer. Field Strength/Sequence: A 3 T; T 2 w FSE, DWI with ADC maps, and dynamic contrast-enhanced images with color-coded perfusion maps. T 2 -R images were created from the raw data utilizing a single "average" with iterative denoising. Assessment: Nine readers randomly assessed complete exams including T 2 -R and T 2 -S images in separate sessions. PI-RADS version 2.1 was used. All readers then compared the T 2 -R and T 2 -S images side by side to evaluate subjective preference. An additional detailed image quality assessment was performed by three senior level readers. Statistical Tests: Generalized linear mixed effects models for differences in lesion detection, image quality features, and overall preference between T 2 -R and T 2 -S sequences. Intraclass correlation coefficients (ICC) were used to assess reader agreement for all comparisons. A significance threshold of P = 0.05 was used for all statistical tests. Results: There was no significant difference between sequences regarding identification of lesions with PI-RADS ≥3 (P = 0.10) or PI-RADS score (P = 0.77). Reader agreement was excellent for lesion identification (ICC = 0.84). There was no significant overall preference between the two sequences regarding image quality (P = 0.07, 95% CI: [À0.23, 0.01]). Reader agreement was good regarding sequence preference (ICC = 0.62). Data Conclusion: Use of single-average, denoised T 2 -weighted images was noninferior in prostate lesion detection or PI-RADS scoring when compared to standard multiaverage T 2 -weighted images. Evidence Level: 3. Technical Efficacy: Stage 3.

show abstract

Compressed sensing and deep learning reconstruction for women’s pelvic MRI denoising: Utility for improving image quality and examination time in routine clinical practice

Cited by 59 publications

References 34 publications

Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Dynamic PET imaging with ultra-low-activity of 18F-FDG: unleashing the potential of total-body PET

A Faster Prostate MRI: Comparing a Novel Denoised, Single‐Average T₂ Sequence to the Conventional Multiaverage T₂ Sequence Regarding Lesion Detection and PI‐RADS Score Assessment

Contact Info

Product

Resources

About

Compressed sensing and deep learning reconstruction for women’s pelvic MRI denoising: Utility for improving image quality and examination time in routine clinical practice

Cited by 59 publications

References 34 publications

Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Dynamic PET imaging with ultra-low-activity of 18F-FDG: unleashing the potential of total-body PET

A Faster Prostate MRI: Comparing a Novel Denoised, Single‐Average T2 Sequence to the Conventional Multiaverage T2 Sequence Regarding Lesion Detection and PI‐RADS Score Assessment

Contact Info

Product

Resources

About

A Faster Prostate MRI: Comparing a Novel Denoised, Single‐Average T₂ Sequence to the Conventional Multiaverage T₂ Sequence Regarding Lesion Detection and PI‐RADS Score Assessment