Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative Analysis
<b>Purpose:</b> Breath-hold T2-weighted half-Fourier acquisition single-shot turbo spin echo (HASTE) magnetic resonance imaging (MRI) of the upper abdomen with a slice thickness below 5 mm suffers from high image noise and blurring. The purpose of this prospective study was to improve im...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Current Oncology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1718-7729/32/1/30 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588728606916608 |
|---|---|
| author | Felix Kubicka Qinxuan Tan Tom Meyer Dominik Nickel Elisabeth Weiland Moritz Wagner Stephan Rodrigo Marticorena Garcia |
| author_facet | Felix Kubicka Qinxuan Tan Tom Meyer Dominik Nickel Elisabeth Weiland Moritz Wagner Stephan Rodrigo Marticorena Garcia |
| author_sort | Felix Kubicka |
| collection | DOAJ |
| description | <b>Purpose:</b> Breath-hold T2-weighted half-Fourier acquisition single-shot turbo spin echo (HASTE) magnetic resonance imaging (MRI) of the upper abdomen with a slice thickness below 5 mm suffers from high image noise and blurring. The purpose of this prospective study was to improve image quality and accelerate imaging acquisition by using single-breath-hold T2-weighted HASTE with deep learning (DL) reconstruction (DL-HASTE) with a 3 mm slice thickness. <b>Method:</b> MRI of the upper abdomen with DL-HASTE was performed in 35 participants (5 healthy volunteers and 30 patients) at 3 Tesla. In a subgroup of five healthy participants, signal-to-noise ratio (SNR) analysis was used after DL reconstruction to identify the smallest possible layer thickness (1, 2, 3, 4, 5 mm). DL-HASTE was acquired with a 3 mm slice thickness (DL-HASTE-3 mm) in 30 patients and compared with 5 mm DL-HASTE (DL-HASTE-5 mm) and with standard HASTE (standard-HASTE-5 mm). Image quality and motion artifacts were assessed quantitatively using Laplacian variance and semi-quantitatively by two radiologists using five-point Likert scales. <b>Results:</b> In the five healthy participants, DL-HASTE-3 mm was identified as the optimal slice (SNR 23.227 ± 3.901). Both DL-HASTE-3 mm and DL-HASTE-5 mm were assigned significantly higher overall image quality scores than standard-HASTE-5 mm (Laplacian variance, both <i>p</i> < 0.001; Likert scale, <i>p</i> < 0.001). Compared with DL-HASTE-5 mm (1.10 × 10<sup>−5</sup> ± 6.93 × 10<sup>−6</sup>), DL-HASTE-3 mm (1.56 × 10<sup>−5</sup> ± 8.69 × 10<sup>−6</sup>) provided a significantly higher SNR Laplacian variance (<i>p</i> < 0.001) and sharpness sub-scores for the intestinal tract, adrenal glands, and small anatomic structures (bile ducts, pancreatic ducts, and vessels; <i>p</i> < 0.05). Lesion detectability was rated excellent for both DL-HASTE-3 mm and DL-HASTE-5 mm (both: 5 [IQR4–5]) and was assigned higher scores than standard-HASTE-5 mm (4 [IQR4–5]; <i>p</i> < 0.001). DL-HASTE reduced the acquisition time by 63–69% compared with standard-HASTE-5 mm (<i>p</i> < 0.001). <b>Conclusions</b>: DL-HASTE is a robust abdominal MRI technique that improves image quality while at the same time reducing acquisition time compared with the routine clinical HASTE sequence. Using ultra-thin DL-HASTE-3 mm results in an even greater improvement with a similar SNR. |
| format | Article |
| id | doaj-art-d2e17ab933f94b12a84e6a45ffda910f |
| institution | Kabale University |
| issn | 1198-0052 1718-7729 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Current Oncology |
| spelling | doaj-art-d2e17ab933f94b12a84e6a45ffda910f2025-01-24T13:28:25ZengMDPI AGCurrent Oncology1198-00521718-77292025-01-013213010.3390/curroncol32010030Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative AnalysisFelix Kubicka0Qinxuan Tan1Tom Meyer2Dominik Nickel3Elisabeth Weiland4Moritz Wagner5Stephan Rodrigo Marticorena Garcia6Department of Radiology, Charité—Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Charitéplatz 1, 10117 Berlin, GermanyDepartment of Radiology, Charité—Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Charitéplatz 1, 10117 Berlin, GermanyDepartment of Radiology, Charité—Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Charitéplatz 1, 10117 Berlin, GermanyMR Applications Predevelopment, Siemens Healthcare GmbH, Allee am Roethelheimpark 2, 91052 Erlangen, GermanyMR Applications Predevelopment, Siemens Healthcare GmbH, Allee am Roethelheimpark 2, 91052 Erlangen, GermanyDepartment of Radiology, Charité—Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Charitéplatz 1, 10117 Berlin, GermanyDepartment of Radiology, Charité—Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Charitéplatz 1, 10117 Berlin, Germany<b>Purpose:</b> Breath-hold T2-weighted half-Fourier acquisition single-shot turbo spin echo (HASTE) magnetic resonance imaging (MRI) of the upper abdomen with a slice thickness below 5 mm suffers from high image noise and blurring. The purpose of this prospective study was to improve image quality and accelerate imaging acquisition by using single-breath-hold T2-weighted HASTE with deep learning (DL) reconstruction (DL-HASTE) with a 3 mm slice thickness. <b>Method:</b> MRI of the upper abdomen with DL-HASTE was performed in 35 participants (5 healthy volunteers and 30 patients) at 3 Tesla. In a subgroup of five healthy participants, signal-to-noise ratio (SNR) analysis was used after DL reconstruction to identify the smallest possible layer thickness (1, 2, 3, 4, 5 mm). DL-HASTE was acquired with a 3 mm slice thickness (DL-HASTE-3 mm) in 30 patients and compared with 5 mm DL-HASTE (DL-HASTE-5 mm) and with standard HASTE (standard-HASTE-5 mm). Image quality and motion artifacts were assessed quantitatively using Laplacian variance and semi-quantitatively by two radiologists using five-point Likert scales. <b>Results:</b> In the five healthy participants, DL-HASTE-3 mm was identified as the optimal slice (SNR 23.227 ± 3.901). Both DL-HASTE-3 mm and DL-HASTE-5 mm were assigned significantly higher overall image quality scores than standard-HASTE-5 mm (Laplacian variance, both <i>p</i> < 0.001; Likert scale, <i>p</i> < 0.001). Compared with DL-HASTE-5 mm (1.10 × 10<sup>−5</sup> ± 6.93 × 10<sup>−6</sup>), DL-HASTE-3 mm (1.56 × 10<sup>−5</sup> ± 8.69 × 10<sup>−6</sup>) provided a significantly higher SNR Laplacian variance (<i>p</i> < 0.001) and sharpness sub-scores for the intestinal tract, adrenal glands, and small anatomic structures (bile ducts, pancreatic ducts, and vessels; <i>p</i> < 0.05). Lesion detectability was rated excellent for both DL-HASTE-3 mm and DL-HASTE-5 mm (both: 5 [IQR4–5]) and was assigned higher scores than standard-HASTE-5 mm (4 [IQR4–5]; <i>p</i> < 0.001). DL-HASTE reduced the acquisition time by 63–69% compared with standard-HASTE-5 mm (<i>p</i> < 0.001). <b>Conclusions</b>: DL-HASTE is a robust abdominal MRI technique that improves image quality while at the same time reducing acquisition time compared with the routine clinical HASTE sequence. Using ultra-thin DL-HASTE-3 mm results in an even greater improvement with a similar SNR.https://www.mdpi.com/1718-7729/32/1/30MRIdeep learningthin sliceHASTEabdomenhigh resolution |
| spellingShingle | Felix Kubicka Qinxuan Tan Tom Meyer Dominik Nickel Elisabeth Weiland Moritz Wagner Stephan Rodrigo Marticorena Garcia Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative Analysis Current Oncology MRI deep learning thin slice HASTE abdomen high resolution |
| title | Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative Analysis |
| title_full | Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative Analysis |
| title_fullStr | Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative Analysis |
| title_full_unstemmed | Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative Analysis |
| title_short | Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative Analysis |
| title_sort | deep learning based reconstruction of single breath hold 3 mm haste improves abdominal image quality and reduces acquisition time a quantitative analysis |
| topic | MRI deep learning thin slice HASTE abdomen high resolution |
| url | https://www.mdpi.com/1718-7729/32/1/30 |
| work_keys_str_mv | AT felixkubicka deeplearningbasedreconstructionofsinglebreathhold3mmhasteimprovesabdominalimagequalityandreducesacquisitiontimeaquantitativeanalysis AT qinxuantan deeplearningbasedreconstructionofsinglebreathhold3mmhasteimprovesabdominalimagequalityandreducesacquisitiontimeaquantitativeanalysis AT tommeyer deeplearningbasedreconstructionofsinglebreathhold3mmhasteimprovesabdominalimagequalityandreducesacquisitiontimeaquantitativeanalysis AT dominiknickel deeplearningbasedreconstructionofsinglebreathhold3mmhasteimprovesabdominalimagequalityandreducesacquisitiontimeaquantitativeanalysis AT elisabethweiland deeplearningbasedreconstructionofsinglebreathhold3mmhasteimprovesabdominalimagequalityandreducesacquisitiontimeaquantitativeanalysis AT moritzwagner deeplearningbasedreconstructionofsinglebreathhold3mmhasteimprovesabdominalimagequalityandreducesacquisitiontimeaquantitativeanalysis AT stephanrodrigomarticorenagarcia deeplearningbasedreconstructionofsinglebreathhold3mmhasteimprovesabdominalimagequalityandreducesacquisitiontimeaquantitativeanalysis |