Bulk Production Augmentation Towards Explainable Melanoma Diagnosis

Although highly accurate automated diagnostic techniques for melanoma have been reported, the realization of a system capable of providing diagnostic evidence based on medical indices remains an open issue because of difficulties in obtaining reliable training data. In this paper, we propose bulk production augmentation (BPA) to generate high-quality, diverse pseudo-skin tumor images with the desired structural malignant features for additional training images from a limited number of labeled images. The proposed BPA acts as an effective data augmentation in constructing the feature detector for the atypical pigment network (APN), which is a key structure in melanoma diagnosis. Experiments show that training with images generated by our BPA largely boosts the APN detection performance by 20.0 percentage points in the area under the receiver operating characteristic curve, which is 11.5 to 13.7 points higher than that of conventional CycleGAN-based augmentations in AUC.

[1]  Gerald Schaefer,et al.  Lesion border detection in dermoscopy images , 2009, Comput. Medical Imaging Graph..

[2]  Nils Gessert,et al.  Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data , 2019, MethodsX.

[3]  Masafumi Hagiwara,et al.  An improved Internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm , 2008, Comput. Medical Imaging Graph..

[4]  David I. McLean,et al.  Detection and Analysis of Irregular Streaks in Dermoscopic Images of Skin Lesions , 2013, IEEE Transactions on Medical Imaging.

[5]  Shin Ishii,et al.  Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Hayit Greenspan,et al.  GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification , 2018, Neurocomputing.

[7]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[8]  Quoc V. Le,et al.  Randaugment: Practical automated data augmentation with a reduced search space , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[9]  Ning Qian,et al.  On the momentum term in gradient descent learning algorithms , 1999, Neural Networks.

[10]  G. Argenziano,et al.  Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions. Comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis. , 1998, Archives of dermatology.

[11]  Alexei A. Efros,et al.  Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[12]  H. Oka,et al.  Parameterization of Dermoscopic Findings for the Internet-based Melanoma Screening System , 2007, 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing.

[13]  Yong Xia,et al.  Attention Residual Learning for Skin Lesion Classification , 2019, IEEE Transactions on Medical Imaging.

[14]  Stein Olav Skrøvseth,et al.  Bayesian multiscale analysis of images modeled as Gaussian Markov random fields , 2012, Comput. Stat. Data Anal..

[15]  Masafumi Hagiwara,et al.  Quantitative assessment of tumour extraction from dermoscopy images and evaluation of computer-based extraction methods for an automatic melanoma diagnostic system , 2006, Melanoma research.

[16]  M. G. Fleming,et al.  Dermoscopy of pigmented skin lesions: results of a consensus meeting via the Internet. , 2003, Journal of the American Academy of Dermatology.

[17]  Chen Huang,et al.  Learning Deep Representation for Imbalanced Classification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  W. Barhoumi,et al.  Pigment network detection in dermatoscopic images for melanoma diagnosis , 2014 .

[19]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[20]  Randy H. Moss,et al.  Automatic detection of blue-white veil and related structures in dermoscopy images , 2008, Comput. Medical Imaging Graph..

[21]  Hitoshi Iyatomi,et al.  Towards Explainable Melanoma Diagnosis: Prediction of Clinical Indicators Using Semi-supervised and Multi-task Learning , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[22]  Harald Kittler,et al.  The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions , 2018, Scientific Data.

[23]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[24]  E. Gassner,et al.  Automated melanoma recognition , 2001, IEEE Transactions on Medical Imaging.

[25]  H. Koga,et al.  Computer-based classification of dermoscopy images of melanocytic lesions on acral volar skin. , 2008, The Journal of investigative dermatology.

[26]  S. Han,et al.  Classification of the Clinical Images for Benign and Malignant Cutaneous Tumors Using a Deep Learning Algorithm. , 2018, The Journal of investigative dermatology.

[27]  Giancarlo Mauri,et al.  Infinite Brain MR Images: PGGAN-based Data Augmentation for Tumor Detection , 2019, Neural Approaches to Dynamics of Signal Exchanges.

[28]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[29]  Ghassan Hamarneh,et al.  Seven-Point Checklist and Skin Lesion Classification Using Multitask Multimodal Neural Nets , 2019, IEEE Journal of Biomedical and Health Informatics.

[30]  Verónica Vilaplana,et al.  BCN20000: Dermoscopic Lesions in the Wild , 2019, Scientific data.

[31]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[32]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[33]  Toshiaki Saida,et al.  Significance of dermoscopic patterns in detecting malignant melanoma on acral volar skin: results of a multicenter study in Japan. , 2004, Archives of dermatology.

[34]  Noel C. F. Codella,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) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[35]  P Altmeyer,et al.  Diagnostic and neural analysis of skin cancer (DANAOS). A multicentre study for collection and computer‐aided analysis of data from pigmented skin lesions using digital dermoscopy , 2003, The British journal of dermatology.

[36]  Hitoshi Iyatomi,et al.  Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning , 2018, ArXiv.