Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning

Accurate automated medical image recognition, including classification and segmentation, is one of the most challenging tasks in medical image analysis. Recently, deep learning methods have achieved remarkable success in medical image classification and segmentation, clearly becoming the state-of-the-art methods. However, most of these methods are unable to provide uncertainty quantification (UQ) for their output, often being overconfident, which can lead to disastrous consequences. Bayesian Deep Learning (BDL) methods can be used to quantify uncertainty of traditional deep learning methods, and thus address this issue. We apply three uncertainty quantification methods to deal with uncertainty during skin cancer image classification. They are as follows: Monte Carlo (MC) dropout, Ensemble MC (EMC) dropout and Deep Ensemble (DE). To further resolve the remaining uncertainty after applying the MC, EMC and DE methods, we describe a novel hybrid dynamic BDL model, taking into account uncertainty, based on the Three-Way Decision (TWD) theory. The proposed dynamic model enables us to use different UQ methods and different deep neural networks in distinct classification phases. So, the elements of each phase can be adjusted according to the dataset under consideration. In this study, two best UQ methods (i.e., DE and EMC) are applied in two classification phases (the first and second phases) to analyze two well-known skin cancer datasets, preventing one from making overconfident decisions when it comes to diagnosing the disease. The accuracy and the F1-score of our final solution are, respectively, 88.95% and 89.00% for the first dataset, and 90.96% and 91.00% for the second dataset. Our results suggest that the proposed TWDBDL model can be used effectively at different stages of medical image analysis.

[1]  Lahouari Ghouti,et al.  A fully-automated deep learning pipeline for cervical cancer classification , 2020, Expert Syst. Appl..

[2]  Debayan Ganguly,et al.  Transfer Learning in Skin Lesion Classification , 2020 .

[3]  Siegfried Wahl,et al.  Leveraging uncertainty information from deep neural networks for disease detection , 2016, Scientific Reports.

[4]  Moloud Abdar,et al.  A mixed solution-based high agreement filtering method for class noise detection in binary classification , 2020 .

[5]  Natan T. Shaked,et al.  TOP-GAN: Label-Free Cancer Cell Classification Using Deep Learning with a Small Training Set , 2018, ArXiv.

[6]  Chee Peng Lim,et al.  Adaptive melanoma diagnosis using evolving clustering, ensemble and deep neural networks , 2020, Knowl. Based Syst..

[7]  Prabhat,et al.  Scalable Bayesian Optimization Using Deep Neural Networks , 2015, ICML.

[8]  Gongning Luo,et al.  Commensal correlation network between segmentation and direct area estimation for bi-ventricle quantification , 2019, Medical Image Anal..

[9]  Hang Lei,et al.  Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization , 2019 .

[10]  Renato A. Krohling,et al.  An Attention-Based Mechanism to Combine Images and Metadata in Deep Learning Models Applied to Skin Cancer Classification , 2021, IEEE Journal of Biomedical and Health Informatics.

[11]  Marc Combalia,et al.  Uncertainty Estimation in Deep Neural Networks for Dermoscopic Image Classification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  M. Shamim Hossain,et al.  Cervical cancer classification using convolutional neural networks and extreme learning machines , 2020, Future Gener. Comput. Syst..

[13]  U. Rajendra Acharya,et al.  A novel method for sentiment classification of drug reviews using fusion of deep and machine learning techniques , 2020, Knowl. Based Syst..

[14]  Yoshua Bengio,et al.  Understanding intermediate layers using linear classifier probes , 2016, ICLR.

[15]  Moloud Abdar,et al.  A Hybrid Latent Space Data Fusion Method for Multimodal Emotion Recognition , 2019, IEEE Access.

[16]  Trevor Darrell,et al.  Uncertainty-guided Continual Learning with Bayesian Neural Networks , 2019, ICLR.

[17]  Igor Kononenko,et al.  Machine learning for medical diagnosis: history, state of the art and perspective , 2001, Artif. Intell. Medicine.

[18]  Lutz Prechelt,et al.  Early Stopping - But When? , 2012, Neural Networks: Tricks of the Trade.

[19]  Alexandre Alahi,et al.  MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[20]  P. C. Siddalingaswamy,et al.  Automated detection of melanocytes related pigmented skin lesions: A clinical framework , 2019, Biomed. Signal Process. Control..

[21]  Changhu Wang,et al.  Network Morphism , 2016, ICML.

[22]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[23]  Ruxandra Stoean,et al.  Analysis on the potential of an EA–surrogate modelling tandem for deep learning parametrization: an example for cancer classification from medical images , 2018, Neural Computing and Applications.

[24]  Sébastien Ourselin,et al.  Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks , 2018, Neurocomputing.

[25]  Qi Wu,et al.  Medical image classification using synergic deep learning , 2019, Medical Image Anal..

[26]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[27]  Renee Ka Yin Chin,et al.  The Effectiveness of Data Augmentation for Melanoma Skin Cancer Prediction Using Convolutional Neural Networks , 2020, 2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET).

[28]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[29]  N. Razavian,et al.  Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning , 2018, Nature Medicine.

[30]  Lars Schmidt-Thieme,et al.  Scalable Gaussian process-based transfer surrogates for hyperparameter optimization , 2017, Machine Learning.

[31]  Aryan Mobiny,et al.  Risk-Aware Machine Learning Classifier for Skin Lesion Diagnosis , 2019, Journal of clinical medicine.

[32]  Yarin Gal,et al.  BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning , 2019, NeurIPS.

[33]  U. Rajendra Acharya,et al.  NE-nu-SVC: A New Nested Ensemble Clinical Decision Support System for Effective Diagnosis of Coronary Artery Disease , 2019, IEEE Access.

[34]  Peter Henderson,et al.  Bayesian Policy Gradients via Alpha Divergence Dropout Inference , 2017, ArXiv.

[35]  U. Rajendra Acharya,et al.  Hybrid particle swarm optimization for rule discovery in the diagnosis of coronary artery disease , 2019, Expert Syst. J. Knowl. Eng..

[36]  M.M.A. Hashem,et al.  A Comparative Study of Neural Network Architectures for Lesion Segmentation and Melanoma Detection , 2020, 2020 IEEE Region 10 Symposium (TENSYMP).

[37]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[38]  Daniel Angerhausen,et al.  Bayesian Deep Learning for Exoplanet Atmospheric Retrieval , 2018, ArXiv.

[39]  Yarin Gal,et al.  A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks , 2019, ArXiv.

[40]  Dustin Tran,et al.  Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches , 2018, ICLR.

[41]  Ronald M. Summers,et al.  Machine learning and radiology , 2012, Medical Image Anal..

[42]  Hao Chen,et al.  Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks , 2017, IEEE Transactions on Medical Imaging.

[43]  Andrew Gordon Wilson,et al.  A Simple Baseline for Bayesian Uncertainty in Deep Learning , 2019, NeurIPS.

[44]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[45]  Naveen Garg,et al.  DropConnect is effective in modeling uncertainty of Bayesian deep networks , 2019, Scientific Reports.

[46]  Yiyu Yao,et al.  Three-way decisions with probabilistic rough sets , 2010, Inf. Sci..

[47]  Erik Cambria,et al.  ABCDM: An Attention-based Bidirectional CNN-RNN Deep Model for sentiment analysis , 2021, Future Gener. Comput. Syst..

[48]  Zoubin Ghahramani,et al.  A Theoretically Grounded Application of Dropout in Recurrent Neural Networks , 2015, NIPS.

[49]  Dan Wang,et al.  Unlabeled skin lesion classification by self-supervised topology clustering network , 2021, Biomed. Signal Process. Control..

[50]  Sina Honari,et al.  Distribution Matching Losses Can Hallucinate Features in Medical Image Translation , 2018, MICCAI.

[51]  Marco Novelli,et al.  Deep learning for prediction of colorectal cancer outcome: a discovery and validation study , 2020, The Lancet.

[52]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

[53]  Bethanney Janney.J,et al.  Classification of melanoma from Dermoscopic data using machine learning techniques , 2018, Multimedia Tools and Applications.

[54]  Alex Kendall,et al.  What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? , 2017, NIPS.

[55]  Priti P. Rege,et al.  Skin Lesion Classification Using Deep Learning , 2021 .

[56]  Saeid Nahavandi,et al.  Integration of Ensemble and Evolutionary Machine Learning Algorithms for Monitoring Diver Behavior Using Physiological Signals , 2019, IEEE Access.

[57]  Muhammad Attique Khan,et al.  Pixels to Classes: Intelligent Learning Framework for Multiclass Skin Lesion Localization and Classification , 2021, Comput. Electr. Eng..

[58]  U. Rajendra Acharya,et al.  Automated Detection of Autism Spectrum Disorder Using a Convolutional Neural Network , 2020, Frontiers in Neuroscience.

[59]  Guido Bologna,et al.  A Two-Step Rule-Extraction Technique for a CNN , 2020, Electronics.

[60]  Dan Zhang,et al.  GP-CNN-DTEL: Global-Part CNN Model With Data-Transformed Ensemble Learning for Skin Lesion Classification , 2020, IEEE Journal of Biomedical and Health Informatics.