Top

Journal of Imaging Informatics in Medicine

Published in:

Open Access 01-08-2020 | Lymphoma | Original Paper

Tumor Segmentation and Feature Extraction from Whole-Body FDG-PET/CT Using Cascaded 2D and 3D Convolutional Neural Networks

Authors: Skander Jemaa, Jill Fredrickson, Richard A. D. Carano, Tina Nielsen, Alex de Crespigny, Thomas Bengtsson

Published in: Journal of Imaging Informatics in Medicine | Issue 4/2020

Abstract

¹⁸F-Fluorodeoxyglucose-positron emission tomography (FDG-PET) is commonly used in clinical practice and clinical drug development to identify and quantify metabolically active tumors. Manual or computer-assisted tumor segmentation in FDG-PET images is a common way to assess tumor burden, such approaches are both labor intensive and may suffer from high inter-reader variability. We propose an end-to-end method leveraging 2D and 3D convolutional neural networks to rapidly identify and segment tumors and to extract metabolic information in eyes to thighs (whole body) FDG-PET/CT scans. The developed architecture is computationally efficient and devised to accommodate the size of whole-body scans, the extreme imbalance between tumor burden and the volume of healthy tissue, and the heterogeneous nature of the input images. Our dataset consists of a total of 3664 eyes to thighs FDG-PET/CT scans, from multi-site clinical trials in patients with non-Hodgkin’s lymphoma (NHL) and advanced non-small cell lung cancer (NSCLC). Tumors were segmented and reviewed by board-certified radiologists. We report a mean 3D Dice score of 88.6% on an NHL hold-out set of 1124 scans and a 93% sensitivity on 274 NSCLC hold-out scans. The method is a potential tool for radiologists to rapidly assess eyes to thighs FDG-avid tumor burden.

Kello G et al: Progress and Promise of FDG-PET Imaging for Cancer Patient Management and Oncologic Drug Development. Clin Cancer Res 2005;11(8):2785–2808

St-Pierre F, Broski SM, LaPlant BR, et al: Detection of extranodal and spleen involvement by FDG-PET imaging predicts adverse survival in untreated follicular lymphoma. Am J Hematol 2019;94:786–793. https://doi.org/10.1002/ajh.25493

Chen HHW, Chiu N-T, et al: Prognostic Value of Whole-Body Total Lesion Glycolysis at Pretreatment FDG PET/CT in Non-Small Cell Lung Cancer. Radiology 2012;264(2):559–566CrossRef

Young H, et al: Measurement of clinical and subclinical tumor response using [18F]-fluorodeoxyglucose and positron emission tomography: review and 1999 EORTC recommendations. Eur J Cancer 1999;35(13):1773–1782

Cheson B, et al: Revised Response Criteria for Malignant Lymphoma. J Clin Oncol 2007;25(5):579–586

Cheson B, et al: Recommendations for Initial Evaluation, Staging, and Response Assessment of Hodgkin and Non-Hodgkin Lymphoma: The Lugano Classification. J Clin Oncol 2014;32(27):3059–3067CrossRef

Long J, Shelhamer E, Darrell T: Fully convolutional networks for semantic segmentation,CVPR. IEEE Computer Society, 2015, pp 3431–3440

He K, Gkioxari G, Dollar P, Girshick P: Mask R-CNN, In: 2017 IEEE International Conference on Computer Vision. IEEE, 2017, pp 2980–2988. https://doi.org/10.1109/ICCV.2017.322

Yan K, et al: DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. J Med Imag 2018;5(3):1–11. https://doi.org/10.1117/1.JMI.5.3.036501

10.

Kamnitsas K, et al: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation, Med Image Anal 2017;36:61–78CrossRef

11.

Milletari F, Navab N, Ahmadi S: V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation, in Proc. Fourth International Conference on 3D Vision (3DV), 2016, pp 565–571. https://doi.org/10.1109/3DV.2016.79

12.

Ronneberger O, Fischer P, Brox T: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF Eds. MICCAI 2015. LNCS, 9351, 2015, pp. 234–241. Springer, Cham. https://doi.org/10.1007/978-3-319-24574-428

13.

He K, Zhang X, Ren S, Sun J: Deep Residual Learning for Image Recognition, 2015. https://arxiv.org/abs/1512.03385

14.

Chollet F: Xception: Deep learning with depthwise separable convolutions. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

15.

Yu F, Koltun V: Multi-Scale Context Aggregation by Dilated Convolutions, 2016. https://arxiv.org/abs/1511.07122

16.

Bauer C, Sun S, Sun W, et al. Automated measurement of uptake in cerebellum, liver, and aortic arch in full-body FDG PET/CT scans. Med Phys 2012;39(6):3112–23. https://doi.org/10.1118/1.4711815.

17.

Mathworks: Segment Lungs from 3-D Chest Scan and Calculate Lung Volume https://www.mathworks.com/help/images/segment-lungs-from-3-d-chest-mri-data.html. Accessed 25 Oct 2019

18.

Zou KH, Wareld SK, Bharatha A, et al: Statistical validation of image segmentation quality based on a spatial overlap index. Acad Radiol 2004;11(2):178–89. https://doi.org/10.1016/S1076-6332(03)00671-8

19.

Vitolo U, Trněný M, Belada D, Burke JM, Carella AM, Chua N, Abrisqueta P, Demeter J, Flinn I, Hong X, Kim WS, Pinto A, Shi YK, Tatsumi Y, Oestergaard MZ, Wenger M, Fingerle-Rowson G, Catalani O, Nielsen T, Martelli M, Sehn LH. Obinutuzumab or Rituximab Plus Cyclophosphamide, Doxorubicin, Vincristine, and Prednisone in Previously Untreated Diffuse Large B-Cell Lymphoma. J Clin Oncol 2017;35(31):3529–3537

20.

Marcus R, Davies A, Ando K, Klapper W, Opat S, Owen C, Phillips E, Sangha R, Schlag R, Seymour JF, Townsend W, Trněný M, Wenger M, Fingerle-Rowson G, Rufibach K, Moore T, Herold M, Hiddemann W. Obinutuzumab for the First-Line Treatment of Follicular Lymphoma. N Engl J Med 2017;377(14):1331–1344

21.

Kingma DP, Ba J: Adam: a method for stochastic optimization. In: 2015 Proceedings of the 3rd International Conference on Learning Representations (ICLR), 2015. Preprint at http://arxiv.org/abs/1412.6980

22.

Huang, B., Chen, Z., Wu, P.-M., et al: Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study. Contrast Media Mol Imaging 2018. https://doi.org/10.1155/2018/8923028

23.

Teramoto A, Fujita H, Yamamuro O, TamakiT: Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique. Med Phys 2015;49(6):2821–2827. https://doi.org/10.1118/1.4711815

Title: Tumor Segmentation and Feature Extraction from Whole-Body FDG-PET/CT Using Cascaded 2D and 3D Convolutional Neural Networks
Authors: Skander Jemaa
Jill Fredrickson
Richard A. D. Carano
Tina Nielsen
Alex de Crespigny
Thomas Bengtsson
Publication date: 01-08-2020
Publisher: Springer International Publishing
Keywords: Lymphoma
NSCLC
NSCLC
Diffuse Large B-Cell Lymphoma
Diffuse Large B-Cell Lymphoma
Published in: Journal of Imaging Informatics in Medicine / Issue 4/2020
Print ISSN: 2948-2925
Electronic ISSN: 2948-2933
DOI: https://doi.org/10.1007/s10278-020-00341-1

At a glance: The STEP trials

Springer Medicine

Tumor Segmentation and Feature Extraction from Whole-Body FDG-PET/CT Using Cascaded 2D and 3D Convolutional Neural Networks

Abstract

At a glance: The STEP trials

Springer Medicine

Abstract

Please log in to get access to this content

Other articles of this Issue 4/2020

Skin Lesion Segmentation with Improved Convolutional Neural Network

Framework for Extracting Critical Findings in Radiology Reports

Natural Language Processing in Dutch Free Text Radiology Reports: Challenges in a Small Language Area Staging Pulmonary Oncology

Automatic Segmentation of Meniscus in Multispectral MRI Using Regions with Convolutional Neural Network (R-CNN)

Deep Multi-Scale 3D Convolutional Neural Network (CNN) for MRI Gliomas Brain Tumor Classification

A Weak and Semi-supervised Segmentation Method for Prostate Cancer in TRUS Images