Top

International Journal of Computer Assisted Radiology and Surgery

Published in:

05-10-2023 | Magnetic Resonance Cholangio Pancreatography | Original Article

MC3DU-Net: a multisequence cascaded pipeline for the detection and segmentation of pancreatic cysts in MRI

Authors: Nir Mazor, Gili Dar, Richard Lederman, Naama Lev-Cohain, Jacob Sosna, Leo Joskowicz

Published in: International Journal of Computer Assisted Radiology and Surgery | Issue 3/2024

Abstract

Purpose

Radiological detection and follow-up of pancreatic cysts in multisequence MRI studies are required to assess the likelihood of their malignancy and to determine their treatment. The evaluation requires expertise and has not been automated. This paper presents MC3DU-Net, a novel multisequence cascaded pipeline for the detection and segmentation of pancreatic cysts in MRI studies consisting of coronal MRCP and axial TSE MRI sequences.

Methods

MC3DU-Net leverages the information in both sequences by computing a pancreas Region of Interest (ROI) segmentation in the TSE MRI scan, transferring it to MRCP scan, and then detecting and segmenting the cysts in the ROI of the MRCP scan. Both the voxel-level ROI of the pancreas and the segmentation of the cysts are performed with 3D U-Nets trained with Hard Negative Patch Mining, a new technique for class imbalance correction and for the reduction in false positives.

Results

MC3DU-Net was evaluated on a dataset of 158 MRI patient studies with a training/validation/testing split of 118/17/23. Ground truth segmentations of a total of 840 cysts were manually obtained by expert clinicians. MC3DU-Net achieves a mean recall of 0.80 ± 0.19, a mean precision of 0.75 ± 0.26, a mean Dice score of 0.80 ± 0.19 and a mean ASSD of 0.60 ± 0.53 for pancreatic cysts of diameter > 5 mm, which is the clinically relevant endpoint.

Conclusion

MC3DU-Net is the first fully automatic method for detection and segmentation of pancreatic cysts in MRI. Automatic detection and segmentation of pancreatic cysts in MRI can be performed accurately and reliably. It may provide a method for precise disease evaluation and may serve as a second expert reader.

Siegel RL, Miller KD, Fuchs HE, Jemal A (2021) Cancer statistics 2021. CA Cancer J Clin 71(1):7–33CrossRefPubMed

Mizrahi JD, Surana R, Valle JW, Shroff RT (2020) Pancreatic cancer. The Lancet 395(10242):2008–2020CrossRef

Bertuzzo L, Zamboni GA, Mannelli L, Negrelli R, Pozzi-Mucelli R (2018) MRI imaging of branch-duct IPMN: evaluation of agreement between experienced observers from multiple centres.‏ Eur Soc Radiol. https://doi.org/10.1594/ecr2018/C-2027CrossRef

Tanaka M, Fernández-del Castillo C, Kamisawa T, Jang JY, Levy P, Ohtsuka T, Wolfgang CL (2017) Revisions of international consensus Fukuoka guidelines for the management of IPMN of the pancreas. Pancreatology 17(5):738–753CrossRefPubMed

Goh BK, Tan DM, Ho MM, Lim TK, Chung AY, Ooi LL (2014) Utility of the Sendai consensus guidelines for branch-duct intraductal papillary mucinous neoplasms: systematic review. J Gastrointest Surg 18:1350–1357CrossRefPubMed

Waters JA, Schmidt CM, Pinchot JW, White PB, Cummings OW, Pitt HA, Lillemoe KD (2008) CT vs MRCP: optimal classification of IPMN type and extent. J Gastrointest Surg 12:101–109CrossRefPubMed

Liu X, Song L, Liu S, Zhang Y (2021) A review of deep-learning-based medical image segmentation methods. Sustainability 13(3):1224CrossRef

Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Proceedings of 19^th international conference medical image computing and computer-assisted interventions. Springer, pp 424–432

Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Proceedings of 19^th international conference on medical image computing and computer-assisted interventions. Springer, pp. 234–241

10.

Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2):203–211CrossRefPubMed

11.

Oh S, Kim YJ, Park YT, Kim KG (2022) Automatic pancreatic cyst lesion segmentation on EUS images using a deep-learning approach. Sensors 22(1):245ADSCrossRef

12.

Dmitriev K, Gutenko I, Nadeem S, Kaufman A (2016) Pancreas and cyst segmentation. In: Medical imaging 2016: image processing. SPIE, pp 628–634‏

13.

Zhou Y, Xie L, Fishman EK, Yuille AL (2017) Deep supervision for pancreatic cyst segmentation in abdominal CT scans. In: Proceedings of international conference on medical image computing and computer-assisted intervent. Springer, pp 222–230

14.

Xie L, Yu Q, Zhou Y, Wang Y, Fishman EK, Yuille AL (2019) Recurrent saliency transformation network for tiny target segmentation in abdominal CT scans. IEEE Trans Med Imaging 39(2):514–525CrossRefPubMed

15.

Abel L, Wasserthal J, Weikert T, Sauter AW, Nesic I, Obradovic M, Friebe B (2021) Automated detection of pancreatic cystic lesions on CT using deep learning. Diagnostics 11(5):901CrossRefPubMedPubMedCentral

16.

Aurelio YS, De Almeida GM, de Castro CL, Braga AP (2019) Learning from imbalanced data sets with weighted cross-entropy function. Neural Process Lett 50:1937–1949CrossRef

17.

Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357CrossRef

18.

Douzas G, Bacao F (2018) Effective data generation for imbalanced learning using conditional generative adversarial networks. Expert Syst Appl 91:464–471CrossRef

19.

Kamnitsas K, Ledig C, Newcombe VF, Simpson JP, Kane AD, Menon DK, Glocker B (2017) Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61–78CrossRefPubMed

20.

Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Larochelle H (2017) Brain tumor segmentation with deep neural networks. Med Image Anal 35:18–31CrossRefPubMed

21.

Chen Y, Ruan D, Xiao J, Wang L, Sun B, Saouaf R, Fan Z (2020) Fully automated multiorgan segmentation in abdominal magnetic resonance imaging with deep neural networks. Med Phys 47(10):4971–4982CrossRefPubMed

22.

Lei T, Sun R, Du X, Fu H, Zhang C, Nandi AK (2023) SGU-Net: shape-guided ultralight network for abdominal image segmentation. IEEE J Biomed Health Inform 27(3):1431–1442CrossRef

23.

Chen X, Chen Z, Li J, Zhang YD, Lin X, Qian X (2021) Model-driven deep learning method for pancreatic cancer segmentation based on spiral-transformation. IEEE Trans Med Imaging 41(1):75–87CrossRefPubMed

24.

Hille G, Agrawal S, Tummala P, Wybranski C, Pech M, Surov A, Saalfeld S (2023) Joint liver and hepatic lesion segmentation in MRI using a hybrid CNN with transformer layers. Comput Methods Progr Biomed 240:107647CrossRef

25.

Wang F, Cheng C, Cao W, Wu Z, Wang H, Wei W, Liu Z (2023) MFCNet: A multi-modal fusion and calibration networks for 3D pancreas tumor segmentation on PET-CT images. Comput Biol Med 155:106657CrossRefPubMed

26.

Yao Y, Chen Y, Gou S, Chen S, Zhang X, Tong N (2023) Auto-segmentation of pancreatic tumor in multi-modal image using transferred DSMask R-CNN network. Biomed Signal Process Control 83:104583CrossRef

27.

Zhang D, Huang G, Zhang Q, Han J, Han J, Yu Y (2021) Cross-modality deep feature learning for brain tumor segmentation. Pattern Recogn 110:107562CrossRef

28.

Huang S, Cheng Z, Lai L, Zheng W, He M, Li J, Yang X (2021) Integrating multiple MRI sequences for pelvic organs segmentation via the attention mechanism. Med Phys 48(12):7930–7945CrossRefPubMed

29.

Kumar V, Sharma MK, Jehadeesan R, Venkatraman B, Sheet D (2021) Adversarial training of deep convolutional neural network for multi-organ segmentation from multi-sequence MRI of the abdomen. In: Proceedings of IEEE international conference on intelligent technologies (CONIT), pp 1–6

30.

Asaturyan H, Thomas EL, Fitzpatrick J, Bell JD, Villarini, B (2019) Advancing pancreas segmentation in multi-protocol MRI volumes using Hausdorff-sine loss function. In: Proceedings of 10^th international of workshop on machine learning in medical imaging. Springer, pp 27–35

31.

Lin D, Wang Z, Li H, Zhang H, Deng L, Ren H, Wang M (2023) Automated measurement of pancreatic fat deposition on Dixon MRI using nnU-Net. J Magn Reson Imaging 57(1):296–307CrossRefPubMed

32.

Yushkevich PA, Gao Y, Gerig G (2016) ITK-SNAP: an interactive tool for semi-automatic segmentation of multi-modality biomedical images. In: Proceedings of 38^th international IEEE conference on engineering medicine and biology, IEEE. pp 3342–3345

33.

Maier-Hein et al. Metrics reloaded: recommendations for image analysis validation. arXiv, Jun 2022, https://arxiv.org/abs/2206.01653

Title: MC3DU-Net: a multisequence cascaded pipeline for the detection and segmentation of pancreatic cysts in MRI
Authors: Nir Mazor
Gili Dar
Richard Lederman
Naama Lev-Cohain
Jacob Sosna
Leo Joskowicz
Publication date: 05-10-2023
Publisher: Springer International Publishing
Keywords: Magnetic Resonance Cholangio Pancreatography
Pancreatic Cyst
Published in: International Journal of Computer Assisted Radiology and Surgery / Issue 3/2024
Print ISSN: 1861-6410
Electronic ISSN: 1861-6429
DOI: https://doi.org/10.1007/s11548-023-03020-y

Keynote webinar | Spotlight on medication adherence

Springer Medicine

MC3DU-Net: a multisequence cascaded pipeline for the detection and segmentation of pancreatic cysts in MRI

Abstract

Purpose

Methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 3/2024

Computer-assisted preoperative planning system with an automated registration method in prosthesis-driven oral implantology

Minimal data requirement for realistic endoscopic image generation with Stable Diffusion

Improved identification of tumors in 18F-FDG-PET examination by normalizing the standard uptake in the liver based on blood test data

MAIRNet: weakly supervised anatomy-aware multimodal articulated image registration network

Catheter navigation support for mechanical thrombectomy guidance: 3D/2D multimodal catheter-based registration with no contrast dye fluoroscopy

Reconstruction of dental roots for implant planning purposes: a retrospective computational and radiographic assessment of single-implant cases