TY - GEN
T1 - GAN-Based Image Enrichment in Digital Pathology Boosts Segmentation Accuracy
AU - Gupta, L.
AU - Klinkhammer, B.M.
AU - Boor, P.
AU - Merhof, D.
AU - Gadermayr, M.
N1 - Conference code: 232939
Cited By :19
Export Date: 14 December 2023
Correspondence Address: Gupta, L.; Institute of Imaging & Computer Vision, Germany; email: [email protected]
Funding details: Deutsche Forschungsgemeinschaft, DFG, ME3737/3-1
Funding text 1: Acknowledgment. This work was supported by the German Research Foundation (DFG) under grant no. ME3737/3-1.
Funding text 2: This work was supported by the German Research Foundation (DFG) under grant no. ME3737/3-1.
References: Bentaieb, A., Hamarneh, G., Adversarial stain transfer for histopathology image analysis (2018) IEEE Trans. Med. Imaging, 37 (3), pp. 792-802; Gadermayr, M., Appel, V., Klinkhammer, B.M., Boor, P., Merhof, D., Which way round? A study on the performance of stain-translation for segmenting arbitrarily dyed histological images (2018) MICCAI 2018. LNCS, 11071, pp. 165-173. , https://doi.org/10.1007/978-3-030-00934-2_19, Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.), pp. , Springer, Cham; Zanjani, F.G., Zinger, S., de With, P.H.N., Bejnordi, B.E., van der Laak, J.A.W.M., Histopathology stain-color normalization using deep generative models (2018) In: Proceedings of the Conference on Medical Imaging with Deep Learning, MIDL, 2018, pp. 1-11. , , pp; Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A., Image-to-image translation with conditional adversarial networks (2017) Proceedings of the International Conference on Computer Vision and Pattern Recognition, CVPR, , 2017; James, A.P., Dasarathy, B.V., Medical image fusion: A survey of the state of the art (2014) Inf. Fusion, 19, pp. 4-19; Ronneberger, O., Fischer, P., Brox, T., U-Net: Convolutional networks for biomedical image segmentation (2015) MICCAI 2015. LNCS, 9351, pp. 234-241. , https://doi.org/10.1007/978-3-319-24574-4_28, Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.), Springer, Cham; Wu, B., (2019) G2C: A Generator-To-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification; Zhao, Y., Towards MR-only radiotherapy treatment planning: Synthetic CT generation using multi-view deep convolutional neural networks (2018) MICCAI 2018. LNCS, 11070, pp. 286-294. , https://doi.org/10.1007/978-3-030-00928-1_33, Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.), Springer, Cham; Zhu, J.Y., Park, T., Isola, P., Efros, A.A., Unpaired image-to-image translation using cycle-consistent adversarial networks (2017) Proceedings of the International Conference on Computer Vision, ICCV, , 2017
PY - 2019
Y1 - 2019
N2 - We introduce the idea of ‘image enrichment’ whereby the information content of images is increased in order to enhance segmentation accuracy. Unlike in data augmentation, the focus is not on increasing the number of training samples (by adding new virtual samples), but on increasing the information for each sample. For this purpose, we use a GAN-based image-to-image translation approach to generate corresponding virtual samples from a given (original) image. The virtual samples are then merged with the original sample to create a multi-channel image, which serves as the enriched image. We train and test a segmentation network on enriched images showing kidney pathology and obtain segmentation scores exhibiting an improvement compared to conventional processing of the original images only. We perform an extensive evaluation and discuss the reasons for the improvement. © 2019, Springer Nature Switzerland AG.
AB - We introduce the idea of ‘image enrichment’ whereby the information content of images is increased in order to enhance segmentation accuracy. Unlike in data augmentation, the focus is not on increasing the number of training samples (by adding new virtual samples), but on increasing the information for each sample. For this purpose, we use a GAN-based image-to-image translation approach to generate corresponding virtual samples from a given (original) image. The virtual samples are then merged with the original sample to create a multi-channel image, which serves as the enriched image. We train and test a segmentation network on enriched images showing kidney pathology and obtain segmentation scores exhibiting an improvement compared to conventional processing of the original images only. We perform an extensive evaluation and discuss the reasons for the improvement. © 2019, Springer Nature Switzerland AG.
KW - Adversarial networks
KW - Augmentation
KW - Enrichment
KW - Histology
KW - Kidney
KW - Segmentation
KW - Sensor fusion
KW - Blast enrichment
KW - Image enhancement
KW - Image segmentation
KW - Medical computing
KW - Pathology
KW - Conventional processing
KW - Digital pathologies
KW - Information contents
KW - Segmentation accuracy
KW - Medical image processing
U2 - 10.1007/978-3-030-32239-7_70
DO - 10.1007/978-3-030-32239-7_70
M3 - Conference contribution
SN - 978-3-030-32238-0
VL - 11764 LNCS
T3 - Lecture Notes in Computer Science
BT - Medical Image Computing and Computer Assisted Intervention – MICCAI 2019
PB - Springer Nature
T2 - 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2019
Y2 - 13 October 2019 through 17 October 2019
ER -