MC3DU-Net: a multisequence cascaded pipeline for the detection and segmentation of pancreatic cysts in MRI.
Deep learning
Detection and segmentation of pancreatic cysts
Hard negative patch mining
Multisequence MRI
Journal
International journal of computer assisted radiology and surgery
ISSN: 1861-6429
Titre abrégé: Int J Comput Assist Radiol Surg
Pays: Germany
ID NLM: 101499225
Informations de publication
Date de publication:
05 Oct 2023
05 Oct 2023
Historique:
received:
14
03
2023
accepted:
12
09
2023
medline:
5
10
2023
pubmed:
5
10
2023
entrez:
5
10
2023
Statut:
aheadofprint
Résumé
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. 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. 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. 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.
Identifiants
pubmed: 37796412
doi: 10.1007/s11548-023-03020-y
pii: 10.1007/s11548-023-03020-y
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2023. CARS.
Références
Siegel RL, Miller KD, Fuchs HE, Jemal A (2021) Cancer statistics 2021. CA Cancer J Clin 71(1):7–33
doi: 10.3322/caac.21654
pubmed: 33433946
Mizrahi JD, Surana R, Valle JW, Shroff RT (2020) Pancreatic cancer. The Lancet 395(10242):2008–2020
doi: 10.1016/S0140-6736(20)30974-0
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-2027
doi: 10.1594/ecr2018/C-2027
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):738–753
doi: 10.1016/j.pan.2017.07.007
pubmed: 28735806
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 18:1350–1357
doi: 10.1007/s11605-014-2510-8
pubmed: 24668367
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 12:101–109
doi: 10.1007/s11605-007-0367-9
pubmed: 17917784
Liu X, Song L, Liu S, Zhang Y (2021) A review of deep-learning-based medical image segmentation methods. Sustainability 13(3):1224
doi: 10.3390/su13031224
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
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Proceedings of 19
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):203–211
doi: 10.1038/s41592-020-01008-z
pubmed: 33288961
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):245
doi: 10.3390/s22010245
Dmitriev K, Gutenko I, Nadeem S, Kaufman A (2016) Pancreas and cyst segmentation. In: Medical imaging 2016: image processing. SPIE, pp 628–634
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
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):514–525
doi: 10.1109/TMI.2019.2930679
pubmed: 31352338
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):901
doi: 10.3390/diagnostics11050901
pubmed: 34069328
pmcid: 8158747
Aurelio YS, De Almeida GM, de Castro CL, Braga AP (2019) Learning from imbalanced data sets with weighted cross-entropy function. Neural Process Lett 50:1937–1949
doi: 10.1007/s11063-018-09977-1
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
doi: 10.1613/jair.953
Douzas G, Bacao F (2018) Effective data generation for imbalanced learning using conditional generative adversarial networks. Expert Syst Appl 91:464–471
doi: 10.1016/j.eswa.2017.09.030
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 36:61–78
doi: 10.1016/j.media.2016.10.004
pubmed: 27865153
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 35:18–31
doi: 10.1016/j.media.2016.05.004
pubmed: 27310171
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):4971–4982
doi: 10.1002/mp.14429
pubmed: 32748401
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):1431–1442
doi: 10.1109/JBHI.2023.3238183
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):75–87
doi: 10.1109/TMI.2021.3104460
pubmed: 34383646
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 240:107647
doi: 10.1016/j.cmpb.2023.107647
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 155:106657
doi: 10.1016/j.compbiomed.2023.106657
pubmed: 36791551
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 83:104583
doi: 10.1016/j.bspc.2023.104583
Zhang D, Huang G, Zhang Q, Han J, Han J, Yu Y (2021) Cross-modality deep feature learning for brain tumor segmentation. Pattern Recogn 110:107562
doi: 10.1016/j.patcog.2020.107562
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):7930–7945
doi: 10.1002/mp.15285
pubmed: 34658035
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
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
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):296–307
doi: 10.1002/jmri.28275
pubmed: 35635494
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
Maier-Hein et al. Metrics reloaded: recommendations for image analysis validation. arXiv, Jun 2022, https://arxiv.org/abs/2206.01653