A new method for automatic counting of ovarian follicles on whole slide histological images based on convolutional neural network

The ovary is a complex endocrine organ that shows significant structural and functional changes in the female reproductive system over recurrent cycles. There are different types of follicles in the ovarian tissue. The reproductive potential of each individual depends on the numbers of these follicles. However, genetic mutations, toxins, and some specific drugs have an effect on follicles. To determine these effects, it is of great importance to count the follicles. The number of follicles in the ovary is usually counted manually by experts, which is a tedious, time-consuming and intense process. In some cases, the experts count the follicles in a subjective way due to their knowledge. In this study, for the first time, a method has been proposed for automatically counting the follicles of ovarian tissue. Our method primarily involves filter-based segmentation applied to whole slide histological images, based on a convolutional neural network (CNN). A new method is also proposed to eliminate the noise that occurs after the segmentation process and to determine the boundaries of the follicles. Finally, the follicles whose boundaries are determined are classified. To evaluate its performance, the results of the proposed method were compared with those obtained by two different experts and the results of the Faster R-CNN model. The number of follicles obtained by the proposed method was very close to the number of follicles counted by the experts. It was also found that the proposed method was much more successful than the Faster R-CNN model.

[1]  Amnon Shashua,et al.  Learning a Metric Embedding for Face Recognition using the Multibatch Method , 2016, NIPS.

[2]  Diego Klabjan,et al.  Convergence Analysis of Batch Normalization for Deep Neural Nets , 2017, ArXiv.

[3]  Hai Su,et al.  Beyond Classification: Structured Regression for Robust Cell Detection Using Convolutional Neural Network , 2015, MICCAI.

[4]  Lei Wang,et al.  HEp-2 Cell Image Classification With Deep Convolutional Neural Networks , 2015, IEEE Journal of Biomedical and Health Informatics.

[5]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[6]  F. Ebling,et al.  Methods for quantifying follicular numbers within the mouse ovary. , 2004, Reproduction.

[7]  C. Swanson,et al.  Ovarian Follicle Counts Using Proliferating Cell Nuclear Antigen (PCNA) and Semi-Automated Image Analysis in Rats , 2008, Toxicologic pathology.

[8]  O. Stegle,et al.  Deep learning for computational biology , 2016, Molecular systems biology.

[9]  Nasir M. Rajpoot,et al.  Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images , 2016, IEEE Trans. Medical Imaging.

[10]  Michael Legge,et al.  Stereological Assessment of Developing Mouse Ovarian Follicles in an in vitro Culture System , 2011, Anatomical record.

[11]  Stamatia Giannarou,et al.  Object recognition in the ovary: Quantification of oocytes from microscopic images , 2009, 2009 16th International Conference on Digital Signal Processing.

[12]  Gianluca Marcelli,et al.  Computer-Generated Ovaries to Assist Follicle Counting Experiments , 2015, PloS one.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

[15]  Muhammad Imran Razzak,et al.  Deep Learning for Medical Image Processing: Overview, Challenges and Future , 2017, ArXiv.

[16]  Dacheng Tao,et al.  Beyond Filters: Compact Feature Map for Portable Deep Model , 2017, ICML.

[17]  V. Milošević,et al.  Genistein affects ovarian folliculogenesis: A stereological study , 2012, Microscopy research and technique.

[18]  John A. Quinn,et al.  Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics , 2016, MLHC.

[19]  Zhi Jin,et al.  Improved relation classification by deep recurrent neural networks with data augmentation , 2016, COLING.

[20]  Alain Gougeon,et al.  Estimating human ovarian non-growing follicle number: the application of modern stereology techniques to an old problem. , 2007, Human reproduction.

[21]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[22]  Kevin Coward,et al.  Stereological point-counting; an accurate method for assessing ovarian function in tilapia , 2002 .

[23]  J. R. Figueiredo,et al.  In vitro culture of bovine preantral follicles: a review , 2014, Reproductive Biology and Endocrinology.

[24]  J S Charleston,et al.  An accurate, simple method for unbiased determination of primordial follicle number in the primate ovary. , 1997, Biology of reproduction.

[25]  Danny Ziyi Chen,et al.  A Deep Learning Approach for Semantic Segmentation in Histology Tissue Images , 2016, MICCAI.

[26]  Mark D. McDonnell,et al.  Understanding Data Augmentation for Classification: When to Warp? , 2016, 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[27]  Andrew Zisserman,et al.  Microscopy cell counting and detection with fully convolutional regression networks , 2018, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[28]  Janne Heikkilä,et al.  Transfer Learning for Cell Nuclei Classification in Histopathology Images , 2016, ECCV Workshops.

[29]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[30]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Bo Li,et al.  A Fast Face Detection Method via Convolutional Neural Network , 2018, Neurocomputing.

[32]  Jian Cheng,et al.  Quantized Convolutional Neural Networks for Mobile Devices , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[34]  L Aragón,et al.  Quantification of ovarian follicles in bluefin tuna Thunnus thynnus by two stereological methods. , 2010, Journal of fish biology.

[35]  Diego Klabjan,et al.  Regularization for Unsupervised Deep Neural Nets , 2016, AAAI.

[36]  Fabio A. González,et al.  A Deep Learning Architecture for Image Representation, Visual Interpretability and Automated Basal-Cell Carcinoma Cancer Detection , 2013, MICCAI.

[37]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

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

[39]  Nicolas Bousquet,et al.  High-throughput ovarian follicle counting by an innovative deep learning approach , 2018, Scientific Reports.

[40]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[41]  Nasir M. Rajpoot,et al.  Handcrafted features with convolutional neural networks for detection of tumor cells in histology images , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[42]  Nassir Navab,et al.  AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images , 2016, IEEE Trans. Medical Imaging.

[43]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

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

[45]  Almudena Veiga-Lopez,et al.  Developmental Programming: Differential Effects of Prenatal Testosterone and Dihydrotestosterone on Follicular Recruitment, Depletion of Follicular Reserve, and Ovarian Morphology in Sheep1 , 2009, Biology of reproduction.

[46]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Angel Cruz-Roa,et al.  Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features , 2014, Journal of medical imaging.

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

[49]  T. M. Shahriar Sazzad,et al.  An Automated Detection Process to Detect Ovarian Tissues Using Type P63 Digitized Color Images , 2015, 2015 IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI).

[50]  Saied Karbalay-Doust,et al.  Stereological estimation of ovarian oocyte volume, surface area and number: application on mice treated with nandrolone decanoate. , 2012, Folia histochemica et cytobiologica.

[51]  Shaogang Gong,et al.  Harmonious Attention Network for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[52]  Martin Urschler,et al.  Semantic Segmentation of Colon Glands with Deep Convolutional Neural Networks and Total Variation Segmentation , 2015, ArXiv.

[53]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[54]  Shaogang Gong,et al.  Person Re-Identification by Deep Joint Learning of Multi-Loss Classification , 2017, IJCAI.