Skip to main content
Erschienen in: European Radiology 10/2022

10.06.2022 | Gastrointestinal

Comparison of utility of deep learning reconstruction on 3D MRCPs obtained with three different k-space data acquisitions in patients with IPMN

verfasst von: Takahiro Matsuyama, Yoshiharu Ohno, Kaori Yamamoto, Masato Ikedo, Masao Yui, Minami Furuta, Reina Fujisawa, Satomu Hanamatsu, Hiroyuki Nagata, Takahiro Ueda, Hirotaka Ikeda, Saki Takeda, Akiyoshi Iwase, Takashi Fukuba, Hokuto Akamatsu, Ryota Hanaoka, Ryoichi Kato, Kazuhiro Murayama, Hiroshi Toyama

Erschienen in: European Radiology | Ausgabe 10/2022

Einloggen, um Zugang zu erhalten

Abstract

Objective

To compare the utility of deep learning reconstruction (DLR) for improving acquisition time, image quality, and intraductal papillary mucinous neoplasm (IPMN) evaluation for 3D MRCP obtained with parallel imaging (PI), multiple k-space data acquisition for each repetition time (TR) technique (Fast 3D mode multiple: Fast 3Dm) and compressed sensing (CS) with PI.

Materials and methods

A total of 32 IPMN patients who had undergone 3D MRCPs obtained with PI, Fast 3Dm, and CS with PI and reconstructed with and without DLR were retrospectively included in this study. Acquisition time, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) obtained with all protocols were compared using Tukey’s HSD test. Results of endoscopic ultrasound, ERCP, surgery, or pathological examination were determined as standard reference, and distribution classifications were compared among all 3D MRCP protocols by McNemar’s test.

Results

Acquisition times of Fast 3Dm and CS with PI with and without DLR were significantly shorter than those of PI with and without DLR (p < 0.05). Each MRCP sequence with DLR showed significantly higher SNRs and CNRs than those without DLR (p < 0.05). IPMN distribution accuracy of PI with and without DLR and Fast 3Dm with DLR was significantly higher than that of Fast 3Dm without DLR and CS with PI without DLR (p < 0.05).

Conclusion

DLR is useful for improving image quality and IPMN evaluation capability on 3D MRCP obtained with PI, Fast 3Dm, or CS with PI. Moreover, Fast 3Dm and CS with PI may play as substitution to PI for MRCP in patients with IPMN.

Key Points

• Mean examination times of multiple k-space data acquisitions for each TR and compressed sensing with parallel imaging were significantly shorter than that of parallel imaging (p < 0.0001).
When comparing image quality of 3D MRCPs with and without deep learning reconstruction, deep learning reconstruction significantly improved signal-to-noise ratio and contrast-to-noise ratio (p < 0.05).
• IPMN distribution accuracies of parallel imaging with and without deep learning reconstruction (with vs. without: 88.0% vs. 88.0%) and multiple k-space data acquisitions for each TR with deep learning reconstruction (86.0%) were significantly higher than those of others (p < 0.05).
Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Zurück zum Zitat Basturk O, Hong SM, Wood LD et al (2015) A revised classification system and recommendations from the Baltimore consensus meeting for neoplastic precursor lesions in the pancreas. Am J Surg Pathol. 39(12):1730–1741CrossRef Basturk O, Hong SM, Wood LD et al (2015) A revised classification system and recommendations from the Baltimore consensus meeting for neoplastic precursor lesions in the pancreas. Am J Surg Pathol. 39(12):1730–1741CrossRef
2.
Zurück zum Zitat Tanaka M, Fernández-Del Castillo C et al (2017) Revisions of international consensus Fukuoka guidelines for the management of IPMN of the pancreas. Pancreatology. 17(5):738–753CrossRef Tanaka M, Fernández-Del Castillo C et al (2017) Revisions of international consensus Fukuoka guidelines for the management of IPMN of the pancreas. Pancreatology. 17(5):738–753CrossRef
3.
Zurück zum Zitat Vege SS, Ziring B, Jain R, Moayyedi P, Clinical Guidelines Committee; American Gastroenterology Association (2015) American gastroenterological association institute guideline on the diagnosis and management of asymptomatic neoplastic pancreatic cysts. Gastroenterology. 148(4):819–822CrossRef Vege SS, Ziring B, Jain R, Moayyedi P, Clinical Guidelines Committee; American Gastroenterology Association (2015) American gastroenterological association institute guideline on the diagnosis and management of asymptomatic neoplastic pancreatic cysts. Gastroenterology. 148(4):819–822CrossRef
4.
Zurück zum Zitat European Study Group on Cystic Tumours of the Pancreas (2018) European evidence-based guidelines on pancreatic cystic neoplasms. Gut. 67(5):789–804CrossRef European Study Group on Cystic Tumours of the Pancreas (2018) European evidence-based guidelines on pancreatic cystic neoplasms. Gut. 67(5):789–804CrossRef
5.
Zurück zum Zitat Rossi RE, Massironi S (2018) Intraductal papillary mucinous neoplasms of the pancreas: a clinical challenge. Expert Rev Gastroenterol Hepatol. 12(11):1123–1133CrossRef Rossi RE, Massironi S (2018) Intraductal papillary mucinous neoplasms of the pancreas: a clinical challenge. Expert Rev Gastroenterol Hepatol. 12(11):1123–1133CrossRef
6.
Zurück zum Zitat Deshmane A, Gulani V, Griswold MA, Seiberlich N (2012) Parallel MR imaging. J Magn Reson Imaging. 36(1):55–72CrossRef Deshmane A, Gulani V, Griswold MA, Seiberlich N (2012) Parallel MR imaging. J Magn Reson Imaging. 36(1):55–72CrossRef
7.
Zurück zum Zitat Feng L, Benkert T, Block KT, Sodickson DK, Otazo R, Chandarana H (2017) Compressed sensing for body MRI. J Magn Reson Imaging. 45(4):966–987CrossRef Feng L, Benkert T, Block KT, Sodickson DK, Otazo R, Chandarana H (2017) Compressed sensing for body MRI. J Magn Reson Imaging. 45(4):966–987CrossRef
8.
Zurück zum Zitat Ueda T, Ohno Y, Yamamoto K et al (2021) Compressed sensing and deep learning reconstruction for women’s pelvic MRI denoising: utility for improving image quality and examination time in routine clinical practice. Eur J Radiol. 134:109430CrossRef Ueda T, Ohno Y, Yamamoto K et al (2021) Compressed sensing and deep learning reconstruction for women’s pelvic MRI denoising: utility for improving image quality and examination time in routine clinical practice. Eur J Radiol. 134:109430CrossRef
9.
Zurück zum Zitat Ikeda H, Ohno Y, Murayama K et al (2021) Compressed sensing and parallel imaging accelerated T2 FSE sequence for head and neck MR imaging: comparison of its utility in routine clinical practice. Eur J Radiol. 135:109501CrossRef Ikeda H, Ohno Y, Murayama K et al (2021) Compressed sensing and parallel imaging accelerated T2 FSE sequence for head and neck MR imaging: comparison of its utility in routine clinical practice. Eur J Radiol. 135:109501CrossRef
10.
Zurück zum Zitat Mugler JP, Menzel MI, Horger W, Kiefer B (2006) Efficient phase-encoding for 3D turbo-spin-echo imaging with very long echo trains. Proc Intl Soc Mag Reson Med 14:2429 Mugler JP, Menzel MI, Horger W, Kiefer B (2006) Efficient phase-encoding for 3D turbo-spin-echo imaging with very long echo trains. Proc Intl Soc Mag Reson Med 14:2429
11.
Zurück zum Zitat Mugler JP 3rd. (2014) Optimized three-dimensional fast-spin-echo MRI. J Magn Reson Imaging. 39(4):745–767CrossRef Mugler JP 3rd. (2014) Optimized three-dimensional fast-spin-echo MRI. J Magn Reson Imaging. 39(4):745–767CrossRef
12.
Zurück zum Zitat Akatsuka J, Yamamoto Y, Sekine T et al (2019) Illuminating clues of cancer buried in prostate MR image: deep learning and expert approaches. Biomolecules. 9(11):673CrossRef Akatsuka J, Yamamoto Y, Sekine T et al (2019) Illuminating clues of cancer buried in prostate MR image: deep learning and expert approaches. Biomolecules. 9(11):673CrossRef
13.
Zurück zum Zitat Kidoh M, Shinoda K, Kitajima M et al (2020) Deep learning based noise reduction for brain MR imaging: tests on phantoms and healthy volunteers. Magn Reson Med Sci. 19(3):195–206CrossRef Kidoh M, Shinoda K, Kitajima M et al (2020) Deep learning based noise reduction for brain MR imaging: tests on phantoms and healthy volunteers. Magn Reson Med Sci. 19(3):195–206CrossRef
14.
Zurück zum Zitat Qiu D, Zhang S, Liu Y, Zhu J, Zheng L (2020) Super-resolution reconstruction of knee magnetic resonance imaging based on deep learning. Comput Methods Programs Biomed. 187:105059CrossRef Qiu D, Zhang S, Liu Y, Zhu J, Zheng L (2020) Super-resolution reconstruction of knee magnetic resonance imaging based on deep learning. Comput Methods Programs Biomed. 187:105059CrossRef
15.
Zurück zum Zitat Yokota Y, Takeda C, Kidoh M et al (2021) Effects of deep learning reconstruction technique in high-resolution non-contrast magnetic resonance coronary angiography at a 3-tesla machine. Can Assoc Radiol J. 72(1):120–127CrossRef Yokota Y, Takeda C, Kidoh M et al (2021) Effects of deep learning reconstruction technique in high-resolution non-contrast magnetic resonance coronary angiography at a 3-tesla machine. Can Assoc Radiol J. 72(1):120–127CrossRef
16.
Zurück zum Zitat Isogawa K, Ida T, Shiodera T et al (2018) Deep shrinkage convolutional neural network for adaptive noise reduction. IEEE Signal Processing Letters 25(2):224–228CrossRef Isogawa K, Ida T, Shiodera T et al (2018) Deep shrinkage convolutional neural network for adaptive noise reduction. IEEE Signal Processing Letters 25(2):224–228CrossRef
17.
Zurück zum Zitat Yokoyama K, Nakaura T, Iyama Y et al (2016) Usefulness of 3D hybrid profile order technique with 3T magnetic resonance cholangiography: comparison of image quality and acquisition time. J Magn Reson Imaging. 44(5):1346–1353CrossRef Yokoyama K, Nakaura T, Iyama Y et al (2016) Usefulness of 3D hybrid profile order technique with 3T magnetic resonance cholangiography: comparison of image quality and acquisition time. J Magn Reson Imaging. 44(5):1346–1353CrossRef
18.
Zurück zum Zitat Chen Z, Sun B, Duan Q et al (2019) Three-dimensional breath-hold MRCP using SPACE pulse sequence at 3 T: comparison with conventional navigator-triggered technique. AJR Am J Roentgenol. 213(6):1247–1252CrossRef Chen Z, Sun B, Duan Q et al (2019) Three-dimensional breath-hold MRCP using SPACE pulse sequence at 3 T: comparison with conventional navigator-triggered technique. AJR Am J Roentgenol. 213(6):1247–1252CrossRef
19.
Zurück zum Zitat Sahani D, Prasad S, Saini S, Mueller P (2002) Cystic pancreatic neoplasms evaluation by CT and magnetic resonance cholangiopancreatography. Gastrointest Endosc Clin N Am. 12(4):657–672CrossRef Sahani D, Prasad S, Saini S, Mueller P (2002) Cystic pancreatic neoplasms evaluation by CT and magnetic resonance cholangiopancreatography. Gastrointest Endosc Clin N Am. 12(4):657–672CrossRef
20.
Zurück zum Zitat Kawamoto S, Lawler LP, Horton KM, Eng J, Hruban RH, Fishman EK (2006) MDCT of intraductal papillary mucinous neoplasm of the pancreas: evaluation of features predictive of invasive carcinoma. AJR Am J Roentgenol. 186(3):687–695CrossRef Kawamoto S, Lawler LP, Horton KM, Eng J, Hruban RH, Fishman EK (2006) MDCT of intraductal papillary mucinous neoplasm of the pancreas: evaluation of features predictive of invasive carcinoma. AJR Am J Roentgenol. 186(3):687–695CrossRef
21.
Zurück zum Zitat Tanaka M (2015) Current roles of endoscopy in the management of intraductal papillary mucinous neoplasm of the pancreas. Dig Endosc. 27(4):450–457CrossRef Tanaka M (2015) Current roles of endoscopy in the management of intraductal papillary mucinous neoplasm of the pancreas. Dig Endosc. 27(4):450–457CrossRef
22.
Zurück zum Zitat Costa DAPD, Guerra JG, Goldman SM et al (2019) Magnetic resonance cholangiopancreatography (MRCP) versus endosonography-guided fine needle aspiration (EUS-FNA) for diagnosis and follow-up of pancreatic intraductal papillary mucinous neoplasms. Arq Bras Cir Dig 32(4):e1471CrossRef Costa DAPD, Guerra JG, Goldman SM et al (2019) Magnetic resonance cholangiopancreatography (MRCP) versus endosonography-guided fine needle aspiration (EUS-FNA) for diagnosis and follow-up of pancreatic intraductal papillary mucinous neoplasms. Arq Bras Cir Dig 32(4):e1471CrossRef
23.
Zurück zum Zitat Svanholm H, Starklint H, Gundersen HJ, Fabricius J, Barlebo H, Olsen S (1989) Reproducibility of histomorphologic diagnoses with special reference to the kappa statistic. APMIS. 197(8):689–698CrossRef Svanholm H, Starklint H, Gundersen HJ, Fabricius J, Barlebo H, Olsen S (1989) Reproducibility of histomorphologic diagnoses with special reference to the kappa statistic. APMIS. 197(8):689–698CrossRef
24.
Zurück zum Zitat Mandrekar JN (2011) Measures of interrater agreement. J Thorac Oncol. 6(1):6–7CrossRef Mandrekar JN (2011) Measures of interrater agreement. J Thorac Oncol. 6(1):6–7CrossRef
25.
Zurück zum Zitat Cristobal-Huerta A, Poot DHJ, Vogel MW, Krestin GP, Hernandez-Tamames JA (2019) Compressed sensing 3D-GRASE for faster high-resolution MRI. Magn Reson Med. 82(3):984–999CrossRef Cristobal-Huerta A, Poot DHJ, Vogel MW, Krestin GP, Hernandez-Tamames JA (2019) Compressed sensing 3D-GRASE for faster high-resolution MRI. Magn Reson Med. 82(3):984–999CrossRef
26.
Zurück zum Zitat Sartoretti T, Sartoretti E, Wyss M et al (2019) Compressed SENSE accelerated 3D T1w black blood turbo spin echo versus 2D T1w turbo spin echo sequence in pituitary magnetic resonance imaging. Eur J Radiol. 120:108667CrossRef Sartoretti T, Sartoretti E, Wyss M et al (2019) Compressed SENSE accelerated 3D T1w black blood turbo spin echo versus 2D T1w turbo spin echo sequence in pituitary magnetic resonance imaging. Eur J Radiol. 120:108667CrossRef
27.
Zurück zum Zitat Hausmann D, Niemann T, Kreul D et al (2019) Free-breathing dynamic contrast-enhanced imaging of the upper abdomen using a cartesian compressed-sensing sequence with hard-gated and motion-state-resolved reconstruction. Invest Radiol. 54(11):728–736CrossRef Hausmann D, Niemann T, Kreul D et al (2019) Free-breathing dynamic contrast-enhanced imaging of the upper abdomen using a cartesian compressed-sensing sequence with hard-gated and motion-state-resolved reconstruction. Invest Radiol. 54(11):728–736CrossRef
28.
Zurück zum Zitat Bratke G, Rau R, Weiss K et al (2019) Accelerated MRI of the lumbar spine using compressed sensing: quality and efficiency. J Magn Reson Imaging. 49(7):e164–e175CrossRef Bratke G, Rau R, Weiss K et al (2019) Accelerated MRI of the lumbar spine using compressed sensing: quality and efficiency. J Magn Reson Imaging. 49(7):e164–e175CrossRef
29.
Zurück zum Zitat Morita K, Nakaura T, Maruyama N et al (2020) Hybrid of compressed sensing and parallel imaging applied to three-dimensional isotropic T2-weighted turbo spin-echo MR imaging of the lumbar spine. Magn Reson Med Sci. 19(1):48–55CrossRef Morita K, Nakaura T, Maruyama N et al (2020) Hybrid of compressed sensing and parallel imaging applied to three-dimensional isotropic T2-weighted turbo spin-echo MR imaging of the lumbar spine. Magn Reson Med Sci. 19(1):48–55CrossRef
Metadaten
Titel
Comparison of utility of deep learning reconstruction on 3D MRCPs obtained with three different k-space data acquisitions in patients with IPMN
verfasst von
Takahiro Matsuyama
Yoshiharu Ohno
Kaori Yamamoto
Masato Ikedo
Masao Yui
Minami Furuta
Reina Fujisawa
Satomu Hanamatsu
Hiroyuki Nagata
Takahiro Ueda
Hirotaka Ikeda
Saki Takeda
Akiyoshi Iwase
Takashi Fukuba
Hokuto Akamatsu
Ryota Hanaoka
Ryoichi Kato
Kazuhiro Murayama
Hiroshi Toyama
Publikationsdatum
10.06.2022
Verlag
Springer Berlin Heidelberg
Erschienen in
European Radiology / Ausgabe 10/2022
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI
https://doi.org/10.1007/s00330-022-08877-2

Weitere Artikel der Ausgabe 10/2022

European Radiology 10/2022 Zur Ausgabe

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.