Abstract
Dermatologists recognize melanomas by inspecting images in which they identify human-comprehensible visual features. In this paper, we investigate to what extent such features correspond to the saliency areas identified on CNNs trained for classification. Our experiments, conducted on two neural architectures characterized by different depth and different resolution of the last convolutional layer, quantify to what extent thresholded Grad-CAM saliency maps can be used to identify visual features of skin cancer. We found that the best threshold value, i.e., the threshold at which we can measure the highest Jaccard index, varies significantly among features; ranging from 0.3 to 0.7. In addition, we measured Jaccard indices as high as 0.143, which is almost 50% of the performance of state-of-the-art architectures specialized in feature mask prediction at pixel-level, such as U-Net. Finally, a breakdown test between malignancy and classification correctness shows that higher resolution saliency maps could help doctors in spotting wrong classifications.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Arun, N., et al.: Assessing the (un)trustworthiness of saliency maps for localizing abnormalities in medical imaging (2020)
Brinker, T.J., Hekler, A., Enk, A.H., 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). https://doi.org/10.1016/j.ejca.2019.04.001
Brinker, T.J., Hekler, A., Utikal, J.S., et al.: Skin cancer classification using convolutional neural networks: systematic review. J. Med. Internet Res. 20(10) (2018). https://doi.org/10.2196/11936
Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), March 2018. https://doi.org/10.1109/wacv.2018.00097
Codella, N., Rotemberg, V., Tschandl, P., et al.: Skin lesion analysis toward Melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC), February 2019. arXiv: 1902.03368
Codella, N.C.F., Gutman, D., Celebi, M.E., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC), October 2017. arXiv: 1710.05006
Combalia, M., Codella, N.C.F., Rotemberg, V., et al.: BCN20000: dermoscopic lesions in the wild. arXiv:1908.02288 [cs, eess], August 2019. arXiv: 1908.02288
Curiel-Lewandrowski, C., et al.: Artificial intelligence approach in Melanoma. In: Fisher, D.E., Bastian, B.C. (eds.) Melanoma, pp. 1–31. Springer, New York (2019). https://doi.org/10.1007/978-1-4614-7322-0_43-1
Deng, J., Dong, W., Socher, R., et al.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE, Miami, June 2009. https://doi.org/10.1109/CVPR.2009.5206848
Donahue, J., Jia, Y., Vinyals, O., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: Proceedings of the 31st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 32, pp. 647–655. PMLR, Bejing, June 2014
Esteva, A., Kuprel, B., Novoa, R.A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115 (2017). https://doi.org/10.1038/nature21056
Gonzalez-Diaz, I.: DermaKNet: incorporating the knowledge of dermatologists to convolutional neural networks for skin lesion diagnosis. IEEE J. Biomed. Health Inform. 23(2), 547–559 (2019). https://doi.org/10.1109/JBHI.2018.2806962
Han, S.S., Kim, M.S., Lim, W., Park, G.H., Park, I., Chang, S.E.: Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm. J. Invest. Dermatol. 138(7), 1529–1538 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016
Holzinger, A.: Interactive machine learning for health informatics: when do we need the human-in-the-loop? Brain Inform. 3(2), 119–131 (2016)
Holzinger, A., Carrington, A., Müller, H.: Measuring the quality of explanations: the system causability scale (SCS). KI - Künstliche Intelligenz 34(2), 193–198 (2020)
Jahanifar, M., Tajeddin, N.Z., Asl, B.M., Gooya, A.: Supervised saliency map driven segmentation of lesions in dermoscopic images. IEEE J. Biomed. Health Inform. 23(2), 509–518 (2019). https://doi.org/10.1109/JBHI.2018.2839647
Jahanifar, M., Tajeddin, N.Z., Koohbanani, N.A., et al.: Segmentation of skin lesions and their attributes using multi-scale convolutional neural networks and domain specific augmentations (2018)
Kapishnikov, A., Bolukbasi, T., Viegas, F., Terry, M.: XRAI: better attributions through regions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019
Khan, M.A., et al.: Construction of saliency map and hybrid set of features for efficient segmentation and classification of skin lesion. Microscopy Res. Tech. 82(6), 741–763 (2019). https://doi.org/10.1002/jemt.23220
Mishra, N.K., Celebi, M.E.: An overview of Melanoma detection in dermoscopy images using image processing and machine learning, Janurary 2016. arXiv: 1601.07843
Nunnari, F., Bhuvaneshwara, C., Ezema, A.O., Sonntag, D.: A study on the fusion of pixels and patient metadata in CNN-based classification of skin lesion images. In: Holzinger, A., Kieseberg, P., Tjoa, A., Weippl, E. (eds.) CD-MAKE 2020. LNCS, vol. 12279, pp. 191–208. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-57321-8_11
Nunnari, F., Sonntag, D.: A CNN toolbox for skin cancer classification. CoRR abs/1908.08187 (2019)
Nunnari, F., Sonntag, D.: A software toolbox for deploying deep learning decision support systems with XAI capabilities. In: Companion of the 2021 ACM SIGCHI Symposium on Engineering Interactive Computing Systems. EICS 2021, pp. 44–49, Association for Computing Machinery, New York (2021). https://doi.org/10.1145/3459926.3464753
Petsiuk, V., Das, A., Saenko, K.: RISE: randomized input sampling for explanation of black-box models. In: Proceedings of the British Machine Vision Conference (BMVC) (2018)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Selvaraju, R.R., Cogswell, M., Das, A., et al.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
Sharif Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2014
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition, September 2014. arXiv:1409.1556
Smilkov, D., Thorat, N., Kim, B., et al.: SmoothGrad: removing noise by adding noise (2017)
Sun, J., Chakraborti, T., Noble, J.A.: A comparative study of explainer modules applied to automated skin lesion classification. In: Atzmüller, M., Kliegr, T., Schmid, U. (eds.) Proceedings of the First International Workshop on Explainable and Interpretable Machine Learning (XI-ML 2020) Co-located with the 43rd German Conference on Artificial Intelligence (KI 2020), Bamberg, Germany, 21 September 2020 (Virtual Workshop). CEUR Workshop Proceedings, vol. 2796. CEUR-WS.org (2020). http://ceur-ws.org/Vol-2796/xi-ml-2020_sun.pdf
Teso, S.: Toward faithful explanatory active learning with self-explainable neural nets. Interact. Adapt. Learn. 2444, 13 (2019)
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(1) (2018). https://doi.org/10.1038/sdata.2018.161
Zhou, S., Zhuang, Y., Meng, R.: Multi-category skin lesion diagnosis using dermoscopy images and deep CNN ensembles (2019)
Acknowledgements
This research is partly funded by the pAItient project (BMG) and the Endowed Chair of Applied Artificial Intelligence (Oldenburg University).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 IFIP International Federation for Information Processing
About this paper
Cite this paper
Nunnari, F., Kadir, M.A., Sonntag, D. (2021). On the Overlap Between Grad-CAM Saliency Maps and Explainable Visual Features in Skin Cancer Images. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds) Machine Learning and Knowledge Extraction. CD-MAKE 2021. Lecture Notes in Computer Science(), vol 12844. Springer, Cham. https://doi.org/10.1007/978-3-030-84060-0_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-84060-0_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-84059-4
Online ISBN: 978-3-030-84060-0
eBook Packages: Computer ScienceComputer Science (R0)
