×

Multicenter computer-aided diagnosis for lymph nodes using unsupervised domain-adaptation networks based on cross-domain confounding representations. (English) Zbl 1431.92097

Summary: To achieve the robust high-performance computer-aided diagnosis systems for lymph nodes, CT images may be typically collected from multicenter data, which cause the isolated performance of the model based on different data source centers. The variability adaptation problem of lymph node data which is related to the problem of domain adaptation in deep learning differs from the general domain adaptation problem because of the typically larger CT image size and more complex data distributions. Therefore, domain adaptation for this problem needs to consider the shared feature representation and even the conditioning information of each domain so that the adaptation network can capture significant discriminative representations in a domain-invariant space. This paper extracts domain-invariant features based on a cross-domain confounding representation and proposes a cycle-consistency learning framework to encourage the network to preserve class-conditioning information through cross-domain image translations. Compared with the performance of different domain adaptation methods, the accurate rate of our method achieves at least 4.4% points higher under multicenter lymph node data. The pixel-level cross-domain image mapping and the semantic-level cycle consistency provided a stable confounding representation with class-conditioning information to achieve effective domain adaptation under complex feature distribution.

MSC:

92C55 Biomedical imaging and signal processing
92-08 Computational methods for problems pertaining to biology

Software:

pix2pix; CycleGAN
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Wang, J.; Wang, Q.; Peng, J., Multi-task diagnosis for autism spectrum disorders using multi-modality features: a multi-center study, Human Brain Mapping, 38, 6, 3081-3097 (2017) · doi:10.1002/hbm.23575
[2] Yuan, L.; Wei, X.; Shen, H.; Zeng, L.-L.; Hu, D., Multi-center brain imaging classification using a novel 3D CNN approach, IEEE Access, 6, 49925-49934 (2018) · doi:10.1109/access.2018.2868813
[3] Van, E. A.; van Dijk, A. C.; Truijman, M. T. B., Multi-center MRI carotid plaque component segmentation using feature normalization and transfer learning, IEEE Transactions on Medical Imaging, 34, 6, 1294-1305 (2015) · doi:10.1109/tmi.2014.2384733
[4] Zuo, T.; Zeng, H.; Li, H., The influence of stage at diagnosis and molecular subtype on breast cancer patient survival:a hospital-based multi-center study, Chinese Journal of Cancer, 36, 1, 84 (2017) · doi:10.1186/s40880-017-0250-3
[5] Jing, Z.; Li, W.; Ogunbona, P., Joint geometrical and statistical alignment for visual domain adaptation, Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2017.547
[6] Hong, J.; Chen, H.; Feng, L., Disturbance Grassmann kernels for subspace-based learning, Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM · doi:10.1145/3219819.3219959
[7] Ganin, Y.; Ustinova, E.; Ajakan, H., Domain-adversarial training of neural networks, Journal of Machine Learning Research, 17, 2096-2030 (2017)
[8] Borgwardt, K. M.; Gretton, A.; Rasch, M. J.; Kriegel, H.-P.; Scholkopf, B.; Smola, A. J., Integrating structured biological data by kernel maximum mean discrepancy, Bioinformatics, 22, 14, e49-e57 (2006) · doi:10.1093/bioinformatics/btl242
[9] Tzeng, E.; Hoffman, J.; Ning, Z.; Saenko, K.; Darrell, T., Deep domain confusion: maximizing for domain invariance, Computer Science (2014), http://arxiv.org/abs/1412.3474
[10] Rozantsev, A.; Salzmann, M.; Fua, P., Beyond sharing weights for deep domain adaptation, IEEE Transactions on Pattern Analysis & Machine Intelligence, 41, 4, 801-814 (2018) · doi:10.1109/tpami.2018.2814042
[11] Sun, B.; Saenko, K., Deep CORAL: correlation alignment for deep domain adaptation, Proceedings of the European Conference on Computer Vision
[12] Bousmalis, K.; Trigeorgis, G.; Silberman, N.; Krishnan, D.; Erhan, D., Domain separation networks, Proceedings of the Advances in Neural Information Processing Systems
[13] Kim, T.; Cha, M.; Kim, H.; Lee, J.; Kim, J., Learning to Discover Cross-Domain Relations with Generative Adversarial Networks (2017), Seoul, Republic of Korea: Korea Intelligent Information Systems Society, Seoul, Republic of Korea
[14] Taigman, Y.; Polyak, A.; Wolf, L., Unsupervised cross-domain image generation (2016), http://arxiv.org/abs/1611.02200
[15] Liu, M. Y.; Breuel, T.; Kautz, J., Unsupervised image-to-image translation networks, Proceedings of the Advances in Neural Information Processing Systems
[16] Zhu, J. Y.; Park, T.; Isola, P.; Efros, A. A., Unpaired image-to-image translation using cycle-consistent adversarial networks, Proceedings of the IEEE International Conference on Computer Vision · doi:10.1109/iccv.2017.244
[17] Liu, M. Y.; Tuzel, O., Coupled generative adversarial networks, Proceedings of the Advances in Neural Information Processing Systems
[18] Kingma, D. P.; Welling, M., Auto-encoding variational bayes (2013), http://arxiv.org/abs/1312.6114
[19] Radford, A.; Metz, L.; Chintala, S., Unsupervised representation learning with deep convolutional generative adversarial networks (2015), http://arxiv.org/abs/1511.06434
[20] Lee, H.-Y.; Tseng, H.-Y.; Huang, J.-B.; Singh, M. K.; Yang, M.-H., Diverse image-to-image translation via disentangled representations, Proceedings of the European Conference on Computer Vision (ECCV), 35-51 (2018), Berlin, Germany: Springer, Berlin, Germany · doi:10.1007/978-3-030-01246-5_3
[21] Huang, X.; Liu, M. Y.; Belongie, S.; Kautz, J., Multimodal unsupervised image-to-image translation, Proceedings of the European Conference on Computer Vision (ECCV), 172-189 (2018), Berlin, Germany: Springer, Berlin, Germany · doi:10.1007/978-3-030-01219-9_11
[22] Royer, A.; Bousmalis, K.; Gouws, S.; Bertsch, F.; Murphy, K., XGAN: unsupervised image-to-image translation for many-to-many mappings (2017), http://arxiv.org/abs/1711.05139
[23] Sankaranarayanan, S.; Balaji, Y.; Castillo, C. D.; Chellappa, R., Generate to adapt: aligning domains using generative adversarial networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00887
[24] Goodfellow, I. J.; Pouget-Abadie, J.; Mirza, M., Generative adversarial nets, Proceedings of the International Conference on Neural Information Processing Systems
[25] Giovannini, M.; Botelberge, T.; Bories, E., Endoscopic ultrasound elastography for evaluation of lymph nodes and pancreatic masses: a multicenter study, World Journal of Gastroenterology, 15, 13, 1587-1593 (2009) · doi:10.3748/wjg.15.1587
[26] Dudea, S. M.; Carolina, B. J.; Dana, D.; Dan, V.; Simona, M.; Manuela Lavinia, L., Differentiating benign from malignant superficial lymph nodes with sonoelastography, Medical Ultrasonography, 15, 2, 132-139 (2013) · doi:10.11152/mu.2013.2066.152.smd1cbj2
[27] Netzer, Y.; Wang, T.; Coates, A.; Bissacco, A.; Wu, B.; Ng, A. Y., Reading digits in natural images with unsupervised feature learning, Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning
[28] Lecun, Y.; Bottou, L.; Bengio, Y.; Haffner, P., Gradient-based learning applied to document recognition, Proceedings of the IEEE, 86, 11, 2278-2324 (1998) · doi:10.1109/5.726791
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.