Abstract
Training generalizable data-driven models for medical imaging applications is especially challenging as acquiring and accessing sufficiently large medical datasets is often unfeasible. When trained on limited datasets, a high capacity model, as most leading neural network architectures are, is likely to overfit and thus generalize poorly to unseen data. Further aggravating the problem, data used to train models in medicine are typically collected in silos and from narrow data distributions that are determined by specific acquisition hardware, imaging protocols, and patient demographics. In addition, class imbalance within and across datasets is a common complication as disease conditions or sub-types have varying degrees of prevalence. In this paper, we motivate the need for generalizable training in the context of skin lesion classification by evaluating the performance of ResNet across 7 public datasets with dataset bias and class imbalance. To mitigate dataset bias, we extend the classification and contrastive semantic alignment (CCSA) loss that aims to learn domain-invariant features. As the CCSA loss requires labelled data from two domains, we propose a strategy to dynamically sample paired data in a setting where the set of available classes varies across domains. To encourage learning from underrepresented classes, the sampled class probabilities are used to weight the classification and alignment losses. Experimental results demonstrate improved generalizability as measured by the mean macro-average recall across the 7 datasets when training using the weighted CCSA loss and dynamic sampler.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ballerini, L., Fisher, R., Aldridge, B., Rees, J.: A color and texture based hierarchical K-NN approach to the classification of non-melanoma skin lesions. In: Celebi, M., Schaefer, G. (eds.) Lecture Notes in Computational Vision and Biomechanics, vol. 6, pp. 63–86. Springer, Dordrecht (2013). https://doi.org/10.1007/978-94-007-5389-1_4
Baur, C., Albarqouni, S., Navab, N.: Semi-supervised deep learning for fully convolutional networks. In: MICCAI, pp. 311–319 (2017)
Devries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv:abs/1708.04552 (2017)
Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., Swetter, S.M., Blau, H.M., Thrun, S.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017)
Gessert, N., Sentker, T., Madesta, F., Schmitz, R., Kniep, H.C., Baltruschat, I.M., Werner, R., Schlaefer, A.: Skin lesion diagnosis using ensembles, unscaled multi-crop evaluation and loss weighting. arXiv:abs/1808.01694 (2018)
Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D.: Domain generalization for object recognition with multi-task autoencoders. In: ICCV, pp. 2551–2559 (2015)
Gutman, D., et al.: Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv:abs/1605.01397 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Kawahara, J., Daneshvar, S., Argenziano, G., Hamarneh, G.: Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE J. Biomed. Health Inform. 23(2), 538–546 (2019)
Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Learning to generalize: meta-learning for domain generalization. In: AAAI (2018)
Li, H., Pan, S.J., Wang, S., Kot, A.C.: Domain generalization with adversarial feature learning. In: CVPR, pp. 5400–5409 (2018)
Mendonca, T., Ferreira, P.M., Marques, J.S., Marcal, A.R., Rozeira, J.: PH2 - a dermoscopic image database for research and benchmarking. In: EMBS, pp. 5437–5440 (2013)
Motiian, S., Piccirilli, M., Adjeroh, D.A., Doretto, G.: Unified deep supervised domain adaptation and generalization. In: ICCV, pp. 5715–5725 (2017)
Tschandl, P., Rosendahl, C., Kittler, H.: The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 (2018)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 2962–2971 (2017)
Weston, J., Ratle, F., Mobahi, H., Collobert, R.: Deep learning via semi-supervised embedding. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 639–655. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_34
Zhuang, Z., et al.: Discrimination-aware channel pruning for deep neural networks. In: NeurIPS, pp. 881–892 (2018)
Acknowledgement
We thank NVIDIA for supporting our research through their GPU Grant Program by donating the GeForce Titan V used in this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Yoon, C., Hamarneh, G., Garbi, R. (2019). Generalizable Feature Learning in the Presence of Data Bias and Domain Class Imbalance with Application to Skin Lesion Classification. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11767. Springer, Cham. https://doi.org/10.1007/978-3-030-32251-9_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-32251-9_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32250-2
Online ISBN: 978-3-030-32251-9
eBook Packages: Computer ScienceComputer Science (R0)