Advertisement

Cell Detection with Deep Learning Accelerated by Sparse Kernel

  • Junzhou HuangEmail author
  • Zheng Xu
Chapter
Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Abstract

As lung cancer is one of the most frequent and serious disease causing death for both men and women, early diagnosis and differentiation of lung cancers is clinically important. Computerized tissue histopathology image analysis and computer-aided diagnosis is very efficient and has become amenable. The cell detection process is the most basic step among the computer-aided histopathology image analysis applications. In this chapter, we study a deep convolutional neural network-based method for the lung cancer cell detection problem. This problem is very challenging due to many reasons, e.g., cell clumping and overlapping, high complexity of the cell detection methods, and the lack of humanly annotated datasets. To address these issues, we introduce a deep learning-based cell detection method for the effectiveness, as the deep learning methods have been demonstrated to be repeatedly successful in various computer vision applications in the last decade. However, this method still takes very long time to detect cells in very small images, e.g., \(512\times 512\), albeit it is very effective in the cell detection task. In order to reduce the overall time cost of this method, we combine this method with the sparse kernel technique to significantly accelerate the cell detection process, up to 500 times. With the aforementioned advances, our numerical results confirm that the resulting method is able to outperform most state-of-the-art cell detection methods in terms of both efficiency and effectiveness.

References

  1. 1.
    Demir C, Yener B (2005) Automated cancer diagnosis based on histopathological images: a systematic survey. Tech. Rep, Rensselaer Polytechnic InstituteGoogle Scholar
  2. 2.
    Gurcan MN, Boucheron LE, Can A, Madabhushi A, Rajpoot NM, Yener B (2009) Histopathological image analysis: a review. IEEE Rev Biomed Eng 2:147–171CrossRefGoogle Scholar
  3. 3.
    Irshad H, Veillard A, Roux L, Racoceanu D (2014) Methods for nuclei detection, segmentation, and classification in digital histopathology: a review current status and future potential. IEEE Rev Biomed Eng 7:97–114CrossRefGoogle Scholar
  4. 4.
    Rathore S, Hussain M, Ali A, Khan A (2013) A recent survey on colon cancer detection techniques. IEEE/ACM Trans Comput Biol Bioinform 10(3):545–563CrossRefGoogle Scholar
  5. 5.
    Veta M, Pluim JPW, van Diest PJ, Viergever MA (2014) Breast cancer histopathology image analysis: a review. IEEE Trans Biomed Eng 61(5):1400–1411CrossRefGoogle Scholar
  6. 6.
    Zhang C, Yarkony J, Hamprecht FA (2014) Cell detection and segmentation using correlation clustering. In: Medical image computing and computer-assisted intervention–MICCAI. Springer, Berlin, pp 9–16Google Scholar
  7. 7.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  8. 8.
    Mualla F, Scholl S, Sommerfeldt B, Maier A, Hornegger J (2013) Automatic cell detection in bright-field microscope images using sift, random forests, and hierarchical clustering. IEEE Trans Med Imaging 32(12):2274–2286CrossRefGoogle Scholar
  9. 9.
    Lu C, Mandal M (2014) Toward automatic mitotic cell detection and segmentation in multispectral histopathological images. IEEE J Biomed Health Inform 18(2):594–605CrossRefGoogle Scholar
  10. 10.
    Bise R, Sato Y (2015) Cell detection from redundant candidate regions under nonoverlapping constraints. IEEE Trans Med Imaging 34(7):1417–1427CrossRefGoogle Scholar
  11. 11.
    Al-Kofahi Y, Lassoued W, Lee W, Roysam B (2010) Improved automatic detection and segmentation of cell nuclei in histopathology images. IEEE Trans Biomed Eng 57(4):841–852CrossRefGoogle Scholar
  12. 12.
    Buggenthin F, Marr C, Schwarzfischer M, Hoppe PS, Hilsenbeck O, Schroeder T, Theis FJ (2013) An automatic method for robust and fast cell detection in bright field images from high-throughput microscopy. BMC Bioinform 14(1):297CrossRefGoogle Scholar
  13. 13.
    Liu F, Yang L (2015) A novel cell detection method using deep convolutional neural network and maximum-weight independent set. In: Medical image computing and computer-assisted intervention–MICCAI 2015. Springer, Berlin, pp 349–357Google Scholar
  14. 14.
    Chen T, Chefdhotel C (2014) Deep learning based automatic immune cell detection for immunohistochemistry images. In: Machine learning in medical imaging. Springer, Berlin, pp 17–24Google Scholar
  15. 15.
    Su H, Xing F, Kong X, Xie Y, Zhang S, Yang L (2015) Robust cell detection and segmentation in histopathological images using sparse reconstruction and stacked denoising autoencoders. In: Medical image computing and computer-assisted intervention–MICCAI 2015. Springer, Berlin, pp 383–390Google Scholar
  16. 16.
    Xie Y, Kong X, Xing F, Liu F, Su H, Yang L (2015) Deep voting: a robust approach toward nucleus localization in microscopy images. In: Medical image computing and computer-assisted intervention–MICCAI 2015. Springer, Berlin, pp 374–382Google Scholar
  17. 17.
    Afridi MJ, Liu X, Shapiro E, Ross A (2015) Automatic in vivo cell detection in mri. In: Medical image computing and computer-assisted intervention–MICCAI 2015. Springer, Berlin, pp 391–399Google Scholar
  18. 18.
    Chaudhury KN, Puspoki Z, Muňoz-Barrutia A, Sage D, Unser M (2010) Fast detection of cells using a continuously scalable mexican-hat-like template. In: 2010 IEEE international symposium on biomedical imaging: from nano to macro. IEEE, pp 1277–1280Google Scholar
  19. 19.
    Mayerich D, Kwon J, Panchal A, Keyser J, Choe Y (2011) Fast cell detection in high-throughput imagery using gpu-accelerated machine learning. In: 2011 IEEE international symposium on biomedical imaging: from nano to macro. IEEE, pp 719–723Google Scholar
  20. 20.
    Massoudi A, Semenovich D, Sowmya A (2012) Cell tracking and mitosis detection using splitting flow networks in phase-contrast imaging. In: 2012 annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE, pp 5310–5313Google Scholar
  21. 21.
    Dong B, Shao L, Da Costa M, Bandmann O, Frangi AF (2015) Deep learning for automatic cell detection in wide-field microscopy zebrafish images. In: 2015 IEEE 12th international symposium on biomedical imaging (ISBI). IEEE, pp 772–776Google Scholar
  22. 22.
    Xu Y, Mo T, Feng Q, Zhong P, Lai M, Chang EI et al (2014) Deep learning of feature representation with multiple instance learning for medical image analysis. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 1626–1630Google Scholar
  23. 23.
    Verbancsics P, Harguess J (2015) Image classification using generative neuro evolution for deep learning. In: 2015 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 488–493Google Scholar
  24. 24.
    Liang M, Li Z, Chen T, Zeng J (2015) Integrative data analysis of multi-platform cancer data with a multimodal deep learning approach. IEEE/ACM Trans Comput Biol Bioinform (TCBB) 12(4):928–937CrossRefGoogle Scholar
  25. 25.
    Xie Y, Xing F, Kong X, Su H, Yang L (2015) Beyond classification: Structured regression for robust cell detection using convolutional neural network. In: Medical image computing and computer-assisted intervention–MICCAI 2015. Springer, Berlin, pp 358–365Google Scholar
  26. 26.
    Yu Z, Chen H, You J, Wong H-S, Liu J, Li L, Han G (2014) Double selection based semi-supervised clustering ensemble for tumor clustering from gene expression profiles. IEEE/ACM Trans Comput Biol Bioinform (TCBB) 11(4):727–740CrossRefGoogle Scholar
  27. 27.
    Ibrahim R, Yousri NA, Ismail MA, El-Makky NM (2014) Multi-level gene/mirna feature selection using deep belief nets and active learning. In: 2014 36th annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE, pp 3957–3960Google Scholar
  28. 28.
    Yu Z, Chen H, You J, Liu J, Wong H-S, Han G, Li L (2015) Adaptive fuzzy consensus clustering framework for clustering analysis of cancer data. IEEE/ACM Trans Comput Biol Bioinform 12(4):887–901Google Scholar
  29. 29.
    Li W, Zhang J, McKenna SJ (2015) Multiple instance cancer detection by boosting regularised trees. In: Medical image computing and computer-assisted intervention–MICCAI 2015. Springer, Berlin, pp 645–652Google Scholar
  30. 30.
    Azizi S, Imani F, Zhuang B, Tahmasebi A, Kwak JT, Xu S, Uniyal N, Turkbey B, Choyke P, Pinto P et al (2015) Ultrasound-based detection of prostate cancer using automatic feature selection with deep belief networks. In: Medical image computing and computer-assisted intervention–MICCAI 2015. Springer, Berlin, pp 70–77Google Scholar
  31. 31.
    Kandemir M, Wojek C, Hamprecht FA (2015) Cell event detection in phase-contrast microscopy sequences from few annotations. In: Medical image computing and computer-assisted intervention–MICCAI 2015. Springer, Berlin, pp 316–323Google Scholar
  32. 32.
    Xing F, Su H, Neltner J, Yang L (2014) Automatic ki-67 counting using robust cell detection and online dictionary learning. IEEE Trans Biomed Eng 61(3):859–870Google Scholar
  33. 33.
    Fu H, Qiu G, Shu J, Ilyas M (2014) A novel polar space random field model for the detection of glandular structures. IEEE Trans Med Imaging 33(3):764–776CrossRefGoogle Scholar
  34. 34.
    Lou X, Schiegg M, Hamprecht FA (2014) Active structured learning for cell tracking: algorithm, framework, and usability. IEEE Trans Med Imaging 33(4):849–860CrossRefGoogle Scholar
  35. 35.
    Litjens G, Debats O, Barentsz J, Karssemeijer N, Huisman H (2014) Computer-aided detection of prostate cancer in mri. IEEE Trans Med Imaging 33(5):1083–1092CrossRefGoogle Scholar
  36. 36.
    Lo C-M, Chen R-T, Chang Y-C, Yang Y-W, Hung M-J, Huang C-S, Chang R-F (2014) Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed. IEEE Trans Med Imaging 33(7):1503–1511CrossRefGoogle Scholar
  37. 37.
    Cameron A, Khalvati F, Haider M, Wong A (2015) A quantitative radiomics approach for prostate cancer detection, maps: a quantitative radiomics approach for prostate cancer detectionGoogle Scholar
  38. 38.
    Cruz-Roa AA, Ovalle JEA, Madabhushi A, Osorio FAG (2013) A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection. In: Medical image computing and computer-assisted intervention–MICCAI 2013. Springer, Berlin, pp 403–410Google Scholar
  39. 39.
    Marasco WA, Phan SH, Krutzsch H, Showell HJ, Feltner DE, Nairn R, Becker EL, Ward PA (1984) Purification and identification of formyl-methionyl-leucyl-phenylalanine as the major peptide neutrophil chemotactic factor produced by escherichia coli. J Biol Chem 259(9):5430–5439Google Scholar
  40. 40.
    Mualla F, Schöll S, Sommerfeldt B, Maier A, Steidl S, Buchholz R, Hornegger J (2014) Unsupervised unstained cell detection by sift keypoint clustering and self-labeling algorithm. In: Medical image computing and computer-assisted intervention–MICCAI 2014. Springer, Berlin, pp 377–384Google Scholar
  41. 41.
    Xing F, Su H, Yang L (2013) An integrated framework for automatic ki-67 scoring in pancreatic neuroendocrine tumor. In: Medical image computing and computer-assisted intervention–MICCAI 2013. Springer, Berlin, pp 436–443Google Scholar
  42. 42.
    Chakraborty A, Roy-Chowdhury AK (2015) Context aware spatio-temporal cell tracking in densely packed multilayer tissues. Med Image Analy 19(1):149–163CrossRefGoogle Scholar
  43. 43.
    Veta M, Van Diest PJ, Willems SM, Wang H, Madabhushi A, Cruz-Roa A, Gonzalez F, Larsen AB, Vestergaard JS, Dahl AB et al (2015) Assessment of algorithms for mitosis detection in breast cancer histopathology images. Med Image Anal 20(1):237–248CrossRefGoogle Scholar
  44. 44.
    Ali S, Lewis J, Madabhushi A (2013) Spatially aware cell cluster (spaccl) graphs: predicting outcome in oropharyngeal p16+ tumors. In: Medical image computing and computer-assisted intervention–MICCAI 2013. Springer, Berlin, pp 412–419Google Scholar
  45. 45.
    Pan H, Xu Z, Huang J (2015) An effective approach for robust lung cancer cell detection. In: International workshop on patch-based techniques in medical imaging. Springer, Berlin, pp 87–94Google Scholar
  46. 46.
    Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: Convolutional architecture for fast feature embedding. In: Proceedings of the ACM international conference on multimedia. ACM, pp 675–678Google Scholar
  47. 47.
    Xu Z, Huang J (2015) Efficient lung cancer cell detection with deep convolution neural network. In: International workshop on patch-based techniques in medical imaging. Springer, Berlin, pp 79–86Google Scholar
  48. 48.
    Li H, Zhao R, Wang X (2014) Highly efficient forward and backward propagation of convolutional neural networks for pixelwise classification. arXiv:1412.4526
  49. 49.
    National Lung Screening Trial Research Team et al. (2011) The national lung screening trial: overview and study design1. RadiologyGoogle Scholar
  50. 50.
    Arteta C, Lempitsky V, Noble JA, Zisserman A (2012) Learning to detect cells using non-overlapping extremal regions. In: Medical image computing and computer-assisted intervention–MICCAI 2012. Springer, Berlin, pp 348–356Google Scholar
  51. 51.
    LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRefGoogle Scholar
  52. 52.
    Xu Z, Huang J (2016) Detecting 10,000 cells in one second. In: International conference on medical image computing and computer-assisted intervention. Springer, Berlin, pp 676–684Google Scholar
  53. 53.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105Google Scholar
  54. 54.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9Google Scholar
  55. 55.
    Wang S, Yao J, Xu Z, Huang J (2016) Subtype cell detection with an accelerated deep convolution neural network. In: International conference on medical image computing and computer-assisted intervention. Springer, Berlin, pp 640–648Google Scholar
  56. 56.
    Recht B, Re C, Wright S, Niu F (2011) Hogwild: a lock-free approach to parallelizing stochastic gradient descent. In: Advances in neural information processing systems, pp 693–701Google Scholar
  57. 57.
    Han S, Pool J, Tran J, Dally W (2015) Learning both weights and connections for efficient neural network. In: Advances in neural information processing systems, pp 1135–1143Google Scholar

Copyright information

© Springer International Publishing Switzerland 2017

Authors and Affiliations

  1. 1.University of Texas at ArlingtonArlingtonUSA

Personalised recommendations