Abstract
Atopic dermatitis (AD), also known as eczema, is one of the most common chronic skin diseases. AD severity is primarily evaluated based on visual inspections by clinicians, but is subjective and has large inter- and intra-observer variability in many clinical study settings. To aid the standardisation and automating the evaluation of AD severity, this paper introduces a CNN computer vision pipeline, EczemaNet, that first detects areas of AD from photographs and then makes probabilistic predictions on the severity of the disease. EczemaNet combines transfer and multitask learning, ordinal classification, and ensembling over crops to make its final predictions. We test EczemaNet using a set of images acquired in a published clinical trial, and demonstrate low RMSE with well-calibrated prediction intervals. We show the effectiveness of using CNNs for non-neoplastic dermatological diseases with a medium-size dataset, and their potential for more efficiently and objectively evaluating AD severity, which has greater clinical relevance than mere classification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
As well as the area of the affected region in the case of EASI.
- 2.
RoI, of arbitrary size, were labelled by 3 volunteers given a set of 50 expert-labelled images, where 1 volunteer was instructed directly by an expert. 431 photos were deemed difficult to label by the volunteers and hence left out of our dataset.
- 3.
The full data pipeline is provided in Supp. Fig. 1.
- 4.
In practice, EASI and SASSAD are assessed across different regions of the body, which we do not consider in this work.
- 5.
Crops were preprocessed by bilinearly resampling to 224Â \(\times \)Â 224px.
- 6.
We convolve the probability mass functions of the predicted severity of the 7 disease signs, assuming that the predictions are independent random variables.
- 7.
We also observed a similar ranking across models for SASSAD (Supp. Figure 3) and TISS (Supp. Figure 4), as well as across the individual signs.
- 8.
References
Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: USENIX Symposium on Operating Systems Design and Implementation, pp. 265–283 (2016)
Alam, M.N., Munia, T.T.K., Tavakolian, K., Vasefi, F., MacKinnon, N., Fazel-Rezai, R.: Automatic detection and severity measurement of eczema using image processing. In: EMBC, pp. 1365–1368. IEEE (2016)
Ashukha, A., Lyzhov, A., Molchanov, D., Vetrov, D.: Pitfalls of in-domain uncertainty estimation and ensembling in deep learning. In: International Conference on Learning Representations (2020)
Berth-Jones, J.: Six area, six sign atopic dermatitis (SASSAD) severity score: a simple system for monitoring disease activity in atopic dermatitis. Br. J. Dermatol. 135, 25–30 (1996)
Brinker, T.J., et al.: Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task. Eur. J. Cancer 113, 47–54 (2019)
Cardoso, J.S., Costa, J.F.: Learning to classify ordinal data: the data replication method. JMLR 8(Jul), 1393–1429 (2007)
Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115–118 (2017)
Frank, E., Hall, M.: A simple approach to ordinal classification. In: De Raedt, L., Flach, P. (eds.) ECML 2001. LNCS (LNAI), vol. 2167, pp. 145–156. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-44795-4_13
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: ICML, pp. 1321–1330 (2017)
Hameed, N., Shabut, A.M., Hossain, M.A.: Multi-class skin diseases classification using deep convolutional neural network and support vector machine. In: SKIMA, pp. 1–7. IEEE (2018)
Hanifin, J., et al.: The eczema area and severity index (EASI): assessment of reliability in atopic dermatitis. Exp. Dermatol. 10(1), 11–18 (2001)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)
Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR, pp. 7310–7311 (2017)
Padilla, D., Yumang, A., Diaz, A.L., Inlong, G.: Differentiating atopic dermatitis and psoriasis chronic plaque using convolutional neural network mobilenet architecture. In: HNICEM, pp. 1–6 (2019)
Pal, A., Chaturvedi, A., Garain, U., Chandra, A., Chatterjee, R., Senapati, S.: Severity assessment of psoriatic plaques using deep CNN based ordinal classification. In: Stoyanov, D., et al. (eds.) CARE/CLIP/OR 2.0/ISIC -2018. LNCS, vol. 11041, pp. 252–259. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01201-4_27
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS, pp. 91–99 (2015)
Schmitt, J., et al.: Assessment of clinical signs of atopic dermatitis: a systematic review and recommendation. J. Allergy Clin. Immunol. 132(6), 1337–1347 (2013)
Schmitt, J., et al.: The Harmonising Outcome Measures for Eczema (HOME) statement to assess clinical signs of atopic eczema in trials. J. Allergy Clin. Immunol. 134(4), 800–807 (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15(1), 1929–1958 (2014)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818–2826 (2016)
Thomas, K., et al.: A multicentre randomised controlled trial and economic evaluation of ion-exchange water softeners for the treatment of eczema in children: the softened water eczema trial (SWET). Health Technol. Assess. 15(8), 1–156 (2011)
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)
Weidinger, S., Beck, L.A., Bieber, T., Kabashima, K., Irvine, A.D.: Atopic dermatitis. Nat. Rev. Dis. Primers 4(1), 1 (2018)
Wolkerstorfer, A., De Waard van der Spek, F., Glazenburg, E., Mulder, P., Oranje, A.: Scoring the severity of atopic dermatitis: three item severity score as a rough system for daily practice and as a pre-screening tool for studies. Acta Dermato-Venereologica 79, 356–359 (1999)
Wu, H., et al.: A deep learning, image based approach for automated diagnosis for inflammatory skin diseases. Ann. Transl. Med. 8(9) (2020)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: NeurIPS, pp. 3320–3328 (2014)
Zuberbier, T., et al.: Patient perspectives on the management of atopic dermatitis. J. Allergy Clin. Immunol. 118(1), 226–232 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Pan, K., Hurault, G., Arulkumaran, K., Williams, H.C., Tanaka, R.J. (2020). EczemaNet: Automating Detection and Severity Assessment of Atopic Dermatitis. In: Liu, M., Yan, P., Lian, C., Cao, X. (eds) Machine Learning in Medical Imaging. MLMI 2020. Lecture Notes in Computer Science(), vol 12436. Springer, Cham. https://doi.org/10.1007/978-3-030-59861-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-59861-7_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59860-0
Online ISBN: 978-3-030-59861-7
eBook Packages: Computer ScienceComputer Science (R0)
