Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A cascaded deep network for automated tumor detection and segmentation in clinical PET imaging of diffuse large B-cell lymphoma (2403.07092v1)

Published 11 Mar 2024 in eess.IV, cs.CV, cs.LG, and physics.med-ph

Abstract: Accurate detection and segmentation of diffuse large B-cell lymphoma (DLBCL) from PET images has important implications for estimation of total metabolic tumor volume, radiomics analysis, surgical intervention and radiotherapy. Manual segmentation of tumors in whole-body PET images is time-consuming, labor-intensive and operator-dependent. In this work, we develop and validate a fast and efficient three-step cascaded deep learning model for automated detection and segmentation of DLBCL tumors from PET images. As compared to a single end-to-end network for segmentation of tumors in whole-body PET images, our three-step model is more effective (improves 3D Dice score from 58.9% to 78.1%) since each of its specialized modules, namely the slice classifier, the tumor detector and the tumor segmentor, can be trained independently to a high degree of skill to carry out a specific task, rather than a single network with suboptimal performance on overall segmentation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. “A clinical evaluation of the International Lymphoma Study Group classification of non-Hodgkin’s lymphoma. The Non-Hodgkin’s Lymphoma Classification Project,” Blood 89, 3909–3918 (Jun 1997).
  2. Weisman, A. J., Kim, J., Lee, I., McCarten, K. M., Kessel, S., Schwartz, C. L., Kelly, K. M., Jeraj, R., Cho, S. Y., and Bradshaw, T. J., “Automated quantification of baseline imaging PET metrics on FDG PET/CT images of pediatric Hodgkin lymphoma patients,” EJNMMI Phys 7, 76 (Dec 2020).
  3. Slattery, A., “Validating an image segmentation program devised for staging lymphoma,” Australas Phys Eng Sci Med 40, 799–809 (Dec 2017).
  4. Capobianco, N., Meignan, M., Cottereau, A. S., Vercellino, L., Sibille, L., Spottiswoode, B., Zuehlsdorff, S., Casasnovas, O., Thieblemont, C., and Buvat, I., “F-FDG Uptake Classification Enables Total Metabolic Tumor Volume Estimation in Diffuse Large B-Cell Lymphoma,” J Nucl Med 62, 30–36 (01 2021).
  5. Guo, B., Tan, X., Ke, Q., and Cen, H., “Prognostic value of baseline metabolic tumor volume and total lesion glycolysis in patients with lymphoma: A meta-analysis,” PLoS One 14(1), e0210224 (2019).
  6. Vercellino, L., Cottereau, A. S., Casasnovas, O., Tilly, H., Feugier, P., Chartier, L., Fruchart, C., Roulin, L., Oberic, L., Pica, G. M., Ribrag, V., Abraham, J., Simon, M., Gonzalez, H., Bouabdallah, R., Fitoussi, O., Sebban, C., López-Guillermo, A., Sanhes, L., Morschhauser, F., Trotman, J., Corront, B., Choufi, B., Snauwaert, S., Godmer, P., Briere, J., Salles, G., Gaulard, P., Meignan, M., and Thieblemont, C., “High total metabolic tumor volume at baseline predicts survival independent of response to therapy,” Blood 135, 1396–1405 (04 2020).
  7. Martín-Saladich, Q., Reynés-Llompart, G., Sabaté-Llobera, A., Palomar-Muñoz, A., Domingo-Domènech, E., and Cortés-Romera, M., “Comparison of different automatic methods for the delineation of the total metabolic tumor volume in I-II stage Hodgkin Lymphoma,” Sci Rep 10, 12590 (07 2020).
  8. Casasnovas, R.-O., Kanoun, S., Tal, I., Cottereau, A.-S., Edeline, V., Brice, P., Bouabdallah, R., Salles, G. A., Stamatoullas, A., Dupuis, J., Reman, O., Gastinne, T., Joly, B., Bouabdallah, K., Nicolas-Virelizier, E., Andre, M., Mounier, N., Ferme, C., Meignan, M., and Berriolo-Riedinger, A., “Baseline total metabolic volume (tmtv) to predict the outcome of patients with advanced hodgkin lymphoma (hl) enrolled in the ahl2011 lysa trial.,” Journal of Clinical Oncology 34(15_suppl), 7509–7509 (2016).
  9. Willemink, M. J., Koszek, W. A., Hardell, C., Wu, J., Fleischmann, D., Harvey, H., Folio, L. R., Summers, R. M., Rubin, D. L., and Lungren, M. P., “Preparing Medical Imaging Data for Machine Learning,” Radiology 295, 4–15 (04 2020).
  10. Lundervold, A. S. and Lundervold, A., “An overview of deep learning in medical imaging focusing on mri,” Zeitschrift fur Medizinische Physik 29(2), 102–127 (2019). Special Issue: Deep Learning in Medical Physics.
  11. Buvat, I. and Orlhac, F., “The T.R.U.E. Checklist for Identifying Impactful Artificial Intelligence-Based Findings in Nuclear Medicine: Is It True? Is It Reproducible? Is It Useful? Is It Explainable?,” J Nucl Med 62, 752–754 (06 2021).
  12. Yousefirizi, F., Jha, A. K., Brosch-Lenz, J., Saboury, B., and Rahmim, A., “Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging,” PET Clin 16, 577–596 (Oct 2021).
  13. He, K., Gkioxari, G., Dollar, P., and Girshick, R., “Mask r-cnn,” IEEE transactions on pattern analysis and machine intelligence 42(2), 386–397 (2020).
  14. Kumar, A., Fulham, M., Feng, D., and Kim, J., “Co-Learning Feature Fusion Maps from PET-CT Images of Lung Cancer,” IEEE Trans Med Imaging (Jun 2019).
  15. Blanc-Durand, P., Van Der Gucht, A., Schaefer, N., Itti, E., and Prior, J. O., “Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study,” PLoS One 13(4), e0195798 (2018).
  16. Lempitsky, V., Kohli, P., Rother, C., and Sharp, T., “Image segmentation with a bounding box prior,” in [2009 IEEE 12th International Conference on Computer Vision ], 277–284 (2009).
  17. Weisman, A. J., Kieler, M. W., Perlman, S. B., Hutchings, M., Jeraj, R., Kostakoglu, L., and Bradshaw, T. J., “Convolutional Neural Networks for Automated PET/CT Detection of Diseased Lymph Node Burden in Patients with Lymphoma,” Radiol Artif Intell 2, e200016 (Sep 2020).
  18. He, K., Zhang, X., Ren, S., and Sun, J., “Deep residual learning for image recognition,” in [2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ], 770–778 (2016).
  19. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L., “Imagenet: A large-scale hierarchical image database,” in [2009 IEEE Conference on Computer Vision and Pattern Recognition ], 248–255 (2009).
  20. Ren, S., He, K., Girshick, R., and Sun, J., “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans Pattern Anal Mach Intell 39, 1137–1149 (06 2017).
  21. Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S., “Feature pyramid networks for object detection,” (2016).
  22. Yousefirizi, F., Bloise, I., Martineau, P., Wilson, D., Benard, F., Bradshaw, T., Rahmim, A., and Uribe, C. F., “Reproducibility of a semi-automatic gradient-based segmentation approach for lymphoma pet,” European Journal of Nuclear Medicine and Molecular Imaging 48(1) (2021).
  23. Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P., “Focal loss for dense object detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence 42(2), 318–327 (2020).
  24. Sudre, C. H., Li, W., Vercauteren, T., Ourselin, S., and Jorge Cardoso, M., “Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations,” Deep learning in medical image analysis and multimodal learning for clinical decision support : Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, held in conjunction with MICCAI 2017 Quebec City, QC,… 2017, 240–248 (2017). 34104926[pmid].
  25. Weisman, A. J., Kieler, M. W., Perlman, S., Hutchings, M., Jeraj, R., Kostakoglu, L., and Bradshaw, T. J., “Comparison of 11 automated PET segmentation methods in lymphoma,” Phys Med Biol 65, 235019 (11 2020).
  26. Foster, B., Bagci, U., Mansoor, A., Xu, Z., and Mollura, D. J., “A review on segmentation of positron emission tomography images,” Comput Biol Med 50, 76–96 (Jul 2014).
  27. Rizwan I Haque, I. and Neubert, J., “Deep learning approaches to biomedical image segmentation,” Informatics in Medicine Unlocked 18, 100297 (2020).
  28. Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y., “Deformable convolutional networks,” 764–773, IEEE (2017).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Shadab Ahamed (16 papers)
  2. Natalia Dubljevic (4 papers)
  3. Ingrid Bloise (7 papers)
  4. Claire Gowdy (4 papers)
  5. Patrick Martineau (5 papers)
  6. Don Wilson (4 papers)
  7. Carlos F. Uribe (7 papers)
  8. Arman Rahmim (54 papers)
  9. Fereshteh Yousefirizi (16 papers)
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now