An experimental study on classification of thyroid histopathology images using transfer learning

Abstract CAD systems for histopathology image analysis using machine learning is a well researched subject. Deep learning is playing a major role in advancing this research in the recent years. This paper presents an automated thyroid histopathology image classification system with deep neural networks using the theory of transfer learning and popular pre-trained convolutional neural networks (CNNs). In this experiment-based study, two forms of transfer learning namely feature extraction and fine tuning are applied on popular state-of-the-art CNN architectures such as VGGNet, ResNet, InceptionNet and DenseNet to classify thyroid histopathology images. Accuracy, precision, sensitivity, specificity, area under receiver operating characteristic (AUROC) analysis and F1-score are used to evaluate the performance of the architectures. The results are promising and demonstrate the feasibility of transfer learning for thyroid histopathology image analysis.

[1]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[3]  Chaoyang Zhang,et al.  Deep Learning Based Analysis of Histopathological Images of Breast Cancer , 2019, Front. Genet..

[4]  Fang Zhang,et al.  Deep convolutional activation features for large scale Brain Tumor histopathology image classification and segmentation , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[6]  Mats Andersson,et al.  Determining the scale of image patches using a deep learning approach , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[7]  J. Angel Arul Jothi,et al.  Effective segmentation and classification of thyroid histopathology images , 2016, Appl. Soft Comput..

[8]  Luiz Eduardo Soares de Oliveira,et al.  Deep features for breast cancer histopathological image classification , 2017, 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[9]  Xin-Ping Guan,et al.  Adversarial neural networks for basal membrane segmentation of microinvasive cervix carcinoma in histopathology images , 2017, 2017 International Conference on Machine Learning and Cybernetics (ICMLC).

[10]  Eunjeong Park,et al.  A method for classifying medical images using transfer learning: A pilot study on histopathology of breast cancer , 2017, 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom).

[11]  Bram van Ginneken,et al.  The importance of stain normalization in colorectal tissue classification with convolutional networks , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[12]  Saeed Hassanpour,et al.  Deep Learning for Classification of Colorectal Polyps on Whole-slide Images , 2017, Journal of pathology informatics.

[13]  A. Moslem,et al.  Epidemiology, incidence and mortality of thyroid cancer and their relationship with the human development index in the world: An ecology study in 2018 , 2019, Advances in Human Biology.

[14]  Shihui Ying,et al.  Histopathological image classification with bilinear convolutional neural networks , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[15]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[16]  Olaf Hellwich,et al.  Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology , 2017, Comput. Medical Imaging Graph..

[17]  Bart Liefers,et al.  Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning. , 2019, Biomedical optics express.

[18]  Lilly Suriani Affendey,et al.  Classification of Histopathology Images of Breast into Benign and Malignant using a Single-layer Convolutional Neural Network , 2017, ICISPC 2017.

[19]  Benjamin D. Smith,et al.  Projecting cancer incidence and deaths to 2030: the unexpected burden of thyroid, liver, and pancreas cancers in the United States. , 2014, Cancer research.

[20]  Ziba Gandomkar,et al.  MuDeRN: Multi-category classification of breast histopathological image using deep residual networks , 2018, Artif. Intell. Medicine.

[21]  Vahid Azimi,et al.  Deep learning based Nucleus Classification in pancreas histological images , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[22]  J. Angel Arul Jothi,et al.  Automatic classification of thyroid histopathology images using multi-classifier system , 2017, Multimedia Tools and Applications.

[23]  Nico Karssemeijer,et al.  Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[24]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[25]  Jia Guo,et al.  Cancer diagnosis by nuclear morphometry using spatial information , 2014, Pattern Recognit. Lett..

[26]  Qianni Zhang,et al.  Multi-scale context-aware networks for quantitative assessment of colorectal liver metastases , 2018, 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[27]  Nasir M. Rajpoot,et al.  Simultaneous Cell Detection and Classification in Bone Marrow Histology Images , 2019, IEEE Journal of Biomedical and Health Informatics.

[28]  Hiroharu Kawanaka,et al.  Automatic disease stage classification of glioblastoma multiforme histopathological images using deep convolutional neural network , 2018, Biomedical engineering letters.

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

[30]  Vijayan K. Asari,et al.  Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network , 2018, Journal of Digital Imaging.

[31]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[32]  Enrico Macii,et al.  Colorectal Cancer Classification using Deep Convolutional Networks - An Experimental Study , 2018, BIOIMAGING.

[33]  Mohit Agrawal,et al.  Towards Designing an Automated Classification of Lymphoma subtypes using Deep Neural Networks , 2019, COMAD/CODS.

[34]  Gustavo K. Rohde,et al.  Accurate diagnosis of thyroid follicular lesions from nuclear morphology using supervised learning , 2014, Medical Image Anal..

[35]  Lei Zhang,et al.  Deep Manifold Preserving Autoencoder for Classifying Breast Cancer Histopathological Images , 2020, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[36]  Hamid R. Tizhoosh,et al.  Convolutional neural networks for histopathology image classification: Training vs. Using pre-trained networks , 2017, 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA).