How Important Is Each Dermoscopy Image?

Deep neural networks (DNNs) have revolutionized the field of dermoscopy image analysis. Systems based on DNNs are able to achieve impressive diagnostic performances, even outperforming experienced dermatologists. However, DNNs strongly rely on the quantity and quality of the training data. Real world data sets, including those related to dermoscopy, are often severely imbalanced and of reduced dimensions. Thus, models trained on these data sets typically become biased and fail to generalize well to new images. Sample weighting strategies have been proposed to overcome the previous limitations with promising results. Nonetheless, they have been poorly investigated in the context of dermoscopy image analysis. This paper addresses this issue through the extensive comparison of several sample weighting methods, namely class balance and curriculum learning. The results show that each sample weighting strategy influences the performance of the model in different ways, with most finding a compromise between correctly classifying the most common classes or biasing the model towards the less represented classes. Furthermore, the features learned by each model differ significantly, depending on the training strategy.

[1]  Li Fei-Fei,et al.  MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels , 2017, ICML.

[2]  Yang Song,et al.  Class-Balanced Loss Based on Effective Number of Samples , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Noel C. F. Codella,et al.  Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC) , 2019, ArXiv.

[4]  Harald Kittler,et al.  Descriptor : The HAM 10000 dataset , a large collection of multi-source dermatoscopic images of common pigmented skin lesions , 2018 .

[5]  Cheng Deng,et al.  Balanced Self-Paced Learning for Generative Adversarial Clustering Network , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Cristina Nader Vasconcelos,et al.  Experiments using deep learning for dermoscopy image analysis , 2017, Pattern Recognit. Lett..

[7]  Alain Pitiot,et al.  Fusing fine-tuned deep features for skin lesion classification , 2019, Comput. Medical Imaging Graph..

[8]  Anna Choromanska,et al.  Towards Automated Melanoma Detection With Deep Learning: Data Purification and Augmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[9]  Costantino Grana,et al.  Augmenting data with GANs to segment melanoma skin lesions , 2019, Multimedia Tools and Applications.

[10]  Jorge S. Marques,et al.  Deep Attention Model for the Hierarchical Diagnosis of Skin Lesions , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[11]  Balázs Harangi,et al.  Skin lesion detection based on an ensemble of deep convolutional neural network , 2017, J. Biomed. Informatics.

[12]  Martial Hebert,et al.  Learning to Model the Tail , 2017, NIPS.

[13]  Eduardo Valle,et al.  Data Augmentation for Skin Lesion Analysis , 2018, OR 2.0/CARE/CLIP/ISIC@MICCAI.

[14]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Foster Provost,et al.  Machine Learning from Imbalanced Data Sets 101 , 2008 .

[17]  Tyler B. Johnson,et al.  Training Deep Models Faster with Robust, Approximate Importance Sampling , 2018, NeurIPS.

[18]  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).

[19]  Pietro Perona,et al.  The Devil is in the Tails: Fine-grained Classification in the Wild , 2017, ArXiv.

[20]  Abhinav Gupta,et al.  Training Region-Based Object Detectors with Online Hard Example Mining , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Jorge S. Marques,et al.  Improving Dermoscopy Image Classification Using Color Constancy , 2015, IEEE Journal of Biomedical and Health Informatics.

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

[23]  Jorge S. Marques,et al.  A Survey of Feature Extraction in Dermoscopy Image Analysis of Skin Cancer , 2019, IEEE Journal of Biomedical and Health Informatics.

[24]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  Zhiguo Jiang,et al.  Classification for Dermoscopy Images Using Convolutional Neural Networks Based on Region Average Pooling , 2018, IEEE Access.

[26]  Nils Gessert,et al.  Skin Lesion Classification Using CNNs With Patch-Based Attention and Diagnosis-Guided Loss Weighting , 2019, IEEE Transactions on Biomedical Engineering.

[27]  Chunhua Shen,et al.  A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification , 2020, IEEE Transactions on Medical Imaging.

[28]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[29]  M. Emre Celebi,et al.  Dermoscopy Image Analysis: Overview and Future Directions , 2019, IEEE Journal of Biomedical and Health Informatics.

[30]  François Fleuret,et al.  Not All Samples Are Created Equal: Deep Learning with Importance Sampling , 2018, ICML.

[31]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[32]  Ghassan Hamarneh,et al.  Generalizable Feature Learning in the Presence of Data Bias and Domain Class Imbalance with Application to Skin Lesion Classification , 2019, MICCAI.

[33]  Sharath Pankanti,et al.  Deep learning ensembles for melanoma recognition in dermoscopy images , 2016, IBM J. Res. Dev..