Deep Transparent Prediction through Latent Representation Analysis

The paper presents a novel deep learning approach, which extracts latent information from trained Deep Neural Networks (DNNs) and derives concise representations that are analyzed in an effective, unified way for prediction purposes. It is well known that DNNs are capable of analyzing complex data; however, they lack transparency in their decision making, in the sense that it is not straightforward to justify their prediction, or to visualize the features on which the decision was based. Moreover, they generally require large amounts of data in order to learn and become able to adapt to different environments. This makes their use difficult in healthcare, where trust and personalization are key issues. Transparency combined with high prediction accuracy are the targeted goals of the proposed approach. It includes both supervised DNN training and unsupervised learning of latent variables extracted from the trained DNNs. Domain Adaptation from multiple sources is also presented as an extension, where the extracted latent variable representations are used to generate predictions in other, non-annotated, environments. Successful application is illustrated through a large experimental study in various fields: prediction of Parkinson's disease from MRI and DaTScans; prediction of COVID-19 and pneumonia from CT scans and X-rays; optical character verification in retail food packaging.

[1]  Stefanos Kollias,et al.  Capsule Routing via Variational Bayes , 2019, AAAI.

[2]  Chao Yang,et al.  A Survey on Deep Transfer Learning , 2018, ICANN.

[3]  Stefanos D. Kollias,et al.  Image indexing and retrieval using expressive fuzzy description logics , 2008, Signal Image Video Process..

[4]  Ali Farhadi,et al.  Unsupervised Deep Embedding for Clustering Analysis , 2015, ICML.

[5]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[6]  Daniel Cremers,et al.  Clustering with Deep Learning: Taxonomy and New Methods , 2018, ArXiv.

[7]  Andreas Stafylopatis,et al.  Adaptation and contextualization of deep neural network models , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[8]  Yannis Avrithis,et al.  Broadcast news parsing using visual cues: a robust face detection approach , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

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

[10]  Bo Yang,et al.  Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering , 2016, ICML.

[11]  A. Singleton,et al.  The Parkinson Progression Marker Initiative (PPMI) , 2011, Progress in Neurobiology.

[12]  Mark Swainson,et al.  Multi-Source Deep Domain Adaptation for Quality Control in Retail Food Packaging , 2020, ArXiv.

[13]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

[14]  Andre Esteva,et al.  A guide to deep learning in healthcare , 2019, Nature Medicine.

[15]  Imou,et al.  SEMANTIC IMAGE ANALYSIS USING A SYMBOLIC NEURAL ARCHITECTURE , 2010 .

[16]  Mengjie Zhang,et al.  Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation , 2016, ECCV.

[17]  X. He,et al.  Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans , 2020, medRxiv.

[18]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[19]  Joseph Paul Cohen,et al.  COVID-19 Image Data Collection: Prospective Predictions Are the Future , 2020, The Journal of Machine Learning for Biomedical Imaging.

[20]  Purang Abolmaesumi,et al.  Detection and grading of prostate cancer using temporal enhanced ultrasound: combining deep neural networks and tissue mimicking simulations , 2017, International Journal of Computer Assisted Radiology and Surgery.

[21]  Qiang Liu,et al.  A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture , 2018, IEEE Access.

[22]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[24]  Mei Wang,et al.  Deep Visual Domain Adaptation: A Survey , 2018, Neurocomputing.

[25]  Giorgos B. Stamou,et al.  Lower and Upper Bounds for SPARQL Queries over OWL Ontologies , 2015, Description Logics.

[26]  Stefanos D. Kollias,et al.  An End-to-End Deep Neural Architecture for Optical Character Verification and Recognition in Retail Food Packaging , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[27]  Yannis Avrithis,et al.  Bottom-up spatiotemporal visual attention model for video analysis , 2007 .

[28]  Andreas Stafylopatis,et al.  Interweaving deep learning and semantic techniques for emotion analysis in human-machine interaction , 2015, 2015 10th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP).

[29]  Andreas Stafylopatis,et al.  Machine Learning for Neurodegenerative Disorder Diagnosis - Survey of Practices and Launch of Benchmark Dataset , 2018, Int. J. Artif. Intell. Tools.

[30]  Nikhil Rasiwasia,et al.  Combining deep learning and unsupervised clustering to improve scene recognition performance , 2015, 2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP).

[31]  Luc Bidaut,et al.  A Unified Deep Learning Approach for Prediction of Parkinson's Disease , 2019, IET Image Process..

[32]  Mark Swainson,et al.  Deep Bayesian Self-Training , 2018, Neural Computing and Applications.

[33]  Andreas Stafylopatis,et al.  Predicting Parkinson’s Disease using Latent Information extracted from Deep Neural Networks , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[34]  Andreas Stafylopatis,et al.  Deep neural architectures for prediction in healthcare , 2017, Complex & Intelligent Systems.

[35]  Shengxiang Yang,et al.  A Scalable Test Suite for Continuous Dynamic Multiobjective Optimization , 2019, IEEE Transactions on Cybernetics.