O‐MedAL: Online active deep learning for medical image analysis

Active learning (AL) methods create an optimized labeled training set from unlabeled data. We introduce a novel online active deep learning method for medical image analysis. We extend our MedAL AL framework to present new results in this paper. A novel sampling method queries the unlabeled examples that maximize the average distance to all training set examples. Our online method enhances performance of its underlying baseline deep network. These novelties contribute to significant performance improvements, including improving the model's underlying deep network accuracy by 6.30%, using only 25% of the labeled dataset to achieve baseline accuracy, reducing backpropagated images during training by as much as 67%, and demonstrating robustness to class imbalance in binary and multiclass tasks.

[1]  Dana Angluin.  Queries revisited , 2004, Theor. Comput. Sci..

[2]  Lixu Gu,et al.  Minimization of annotation work: diagnosis of mammographic masses via active learning , 2018, Physics in medicine and biology.

[3]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[4]  Bram van Ginneken,et al.  On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis , 2016, IEEE Transactions on Medical Imaging.

[5]  Jun Zhou,et al.  Maximizing Expected Model Change for Active Learning in Regression , 2013, 2013 IEEE 13th International Conference on Data Mining.

[6]  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).

[7]  Yi Yang,et al.  Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization , 2015, International Journal of Computer Vision.

[8]  Xavier Giró-i-Nieto,et al.  Cost-Effective Active Learning for Melanoma Segmentation , 2017, NIPS 2017.

[9]  Polina Golland,et al.  Interactive Whole-Heart Segmentation in Congenital Heart Disease , 2015, MICCAI.

[10]  Mark Craven,et al.  Curious machines: active learning with structured instances , 2008 .

[11]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[12]  David D. Lewis,et al.  Heterogeneous Uncertainty Sampling for Supervised Learning , 1994, ICML.

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

[14]  Horst K. Hahn,et al.  A comparison of sampling strategies for histological image analysis , 2011, Journal of pathology informatics.

[15]  D. Sculley,et al.  Online Active Learning Methods for Fast Label-Efficient Spam Filtering , 2007, CEAS.

[16]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[17]  Catarina Eloy,et al.  BACH: Grand Challenge on Breast Cancer Histology Images , 2018, Medical Image Anal..

[18]  Jung-Hwan Oh,et al.  Similarity-Based Active Learning for Image Classification Under Class Imbalance , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[19]  Pedro Costa,et al.  EyeWeS: Weakly Supervised Pre-Trained Convolutional Neural Networks for Diabetic Retinopathy Detection , 2019, 2019 16th International Conference on Machine Vision Applications (MVA).

[20]  Joachim Denzler,et al.  Selecting Influential Examples: Active Learning with Expected Model Output Changes , 2014, ECCV.

[21]  Pedro Costa,et al.  MedAL: Accurate and Robust Deep Active Learning for Medical Image Analysis , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[22]  David A. Cohn,et al.  Active Learning with Statistical Models , 1996, NIPS.

[23]  Raymond J. Mooney,et al.  Diverse ensembles for active learning , 2004, ICML.

[24]  C. Lee Giles,et al.  Learning on the border: active learning in imbalanced data classification , 2007, CIKM '07.

[25]  Adam A. Miller,et al.  ACTIVE LEARNING TO OVERCOME SAMPLE SELECTION BIAS: APPLICATION TO PHOTOMETRIC VARIABLE STAR CLASSIFICATION , 2011, 1106.2832.

[26]  Ran El-Yaniv,et al.  Online Choice of Active Learning Algorithms , 2003, J. Mach. Learn. Res..

[27]  H. Sebastian Seung,et al.  Information, Prediction, and Query by Committee , 1992, NIPS.

[28]  Joel H. Saltz,et al.  Comparison of Different Classifiers with Active Learning to Support Quality Control in Nucleus Segmentation in Pathology Images , 2018, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[29]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[31]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[32]  Zoubin Ghahramani,et al.  Deep Bayesian Active Learning with Image Data , 2017, ICML.

[33]  Ana Maria Mendonça,et al.  End-to-End Adversarial Retinal Image Synthesis , 2018, IEEE Transactions on Medical Imaging.

[34]  Lei Zhang,et al.  Fine-Tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[36]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Sanjoy Dasgupta,et al.  A General Agnostic Active Learning Algorithm , 2007, ISAIM.

[38]  Jaime G. Carbonell,et al.  Active Learning from Peers , 2017, NIPS.