Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Cervical cancer detection in cervical smear images using deep pyramid inference with refinement and spatial-aware booster

© The Institution of Engineering and Technology
Received 06/05/2020, Accepted 22/01/2021, Revised 22/12/2020, Published 29/01/2021

With the development of artificial intelligence and image processing technology, more and more intelligent diagnosis technologies are used in cervical cancer screening. Among them, the detection of cervical lesions by thin liquid-based cytology is the most common method for cervical cancer screening. At present, most cervical cancer detection algorithms use the object detection technology of natural images, and often only minor modifications are made while ignoring the specificity of the complex application scenario of cervical lesions detection in cervical smear images. In this study, the authors combine the domain knowledge of cervical cancer detection and the characteristics of pathological cells to design a network and propose a booster for cervical cancer detection (CCDB). The booster mainly consists of two components: the refinement module and the spatial-aware module. The characteristics of cancer cells are fully considered in the booster, and the booster is light and transplantable. As far as the authors know, they are the first to design a CCDB according to the characteristics of cervical cancer cells. Compared with baseline (Retinanet), the sensitivity at four false positives per image and average precision of the proposed method are improved by 2.79 and 7.2%, respectively.

Inspec keywords: object detection; cancer; medical image processing; biomedical optical imaging; gynaecology; cellular biophysics; image segmentation

Other keywords: cervical lesion detection; booster; object detection technology; image processing technology; intelligent diagnosis technologies; cervical cancer screening; cervical smear images; cervical cancer cells; cervical cancer detection algorithms

Subjects: Optical, image and video signal processing; Cellular biophysics; Patient diagnostic methods and instrumentation; Optical and laser radiation (biomedical imaging/measurement); Biology and medical computing; Computer vision and image processing techniques; Optical and laser radiation (medical uses)

References

    1. 1)
      • 27. Camargo, L.H., Diaz, G., Romero, E.: ‘Pap smear cell image classification using global mpeg-7 descriptors’, Diagn. Pathology, 2013, 8, p. S38.
    2. 2)
      • 59. Song, Y., Qin, J., Lei, B., et al: ‘Automated segmentation of overlapping cytoplasm in cervical smear images via contour fragments’. Proc. of the Thirty-Second AAAI Conf. on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symp. on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2018, pp. 168–175.
    3. 3)
      • 38. Girshick, R., Donahue, J., Darrell, T., et al: ‘Rich feature hierarchies for accurate object detection and semantic segmentation’. 2014 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, 2017, pp. 580–587.
    4. 4)
      • 10. Yang-Mao, S.F., Chan, Y.K., Chu, Y.P.: ‘Edge enhancement nucleus and cytoplast contour detector of cervical smear images’, IEEE Trans. Syst. Man Cybern. Part B (Cybern.), 2008, 38, (2), pp. 353–366.
    5. 5)
      • 56. Li, Z., Zhang, S., Zhang, J., et al: ‘MVP-net: multi-view FPN with position-aware attention for deep universal lesion detection’. Medical Image Computing and Computer Assisted Intervention - MICCAI 2019 - 22nd Int. Conf., Shenzhen, China, October 2019, pp. 13–21.
    6. 6)
      • 6. Bengtsson, E., Malm, P.: ‘Screening for cervical cancer using automated analysis of pap-smears’, Comput. Math. Methods Med., 2014, 2014, pp. 842037:1–842037:12.
    7. 7)
      • 14. GençTav, A., Aksoy, S., ÖNder, S.: ‘Unsupervised segmentation and classification of cervical cell images’, Pattern Recognit., 2012, 45, (12), pp. 4151–4168.
    8. 8)
      • 25. Lu, Z., Carneiro, G., Bradley, A.P.: ‘An improved joint optimization of multiple level set functions for the segmentation of overlapping cervical cells’, IEEE Trans. Image Process., 2015, 24, (4), pp. 1261–1272.
    9. 9)
      • 42. Dai, J., Li, Y., He, K., et al: ‘R-FCN: object detection via region-based fully convolutional networks’. Advances in Neural Information Processing Systems 29: Annual Conf. on Neural Information Processing Systems 2016, Barcelona, Spain, December 2016, pp. 379–387.
    10. 10)
      • 55. Ben-Cohen, A., Klang, E., Kerpel, A., et al: ‘Fully convolutional network and sparsity-based dictionary learning for liver lesion detection in ct examinations’, Neurocomputing, 2018, 275, pp. 1585–1594.
    11. 11)
      • 47. Redmon, J., Farhadi, A.: ‘YOLOv3: An Incremental Improvement’. CoRR, 2018, abs/1804.02767.
    12. 12)
      • 72. Jia, A.D., Li, B.Z., Zhang, C.C.: ‘Detection of cervical cancer cells based on strong feature cnn-svm network’, Neurocomputing, 2020, 411, pp. 112–127.
    13. 13)
      • 43. Liu, W., Anguelov, D., Erhan, D., et al: ‘SSD: single shot multiBox detector’. Computer Vision - ECCV 2016 - 14th European Conf., The Netherlands, October 2016, pp. 21–37.
    14. 14)
      • 11. Guan, T., Zhou, D., Liu, Y.: ‘Accurate segmentation of partially overlapping cervical cells based on dynamic sparse contour searching and gvf snake model’, IEEE J. Biomed. Health Inf., 2014, 19, (4), pp. 1494–1504.
    15. 15)
      • 41. Lin, T., Dollar, P., Girshick, R., et al: ‘Cascade R-CNN: delving into high quality object detection’. 2018 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT, USA, June 2018, pp. 6154–6162.
    16. 16)
      • 24. Lu, Z., Carneiro, G., Bradley, A.P.: ‘Automated nucleus and cytoplasm segmentation of overlapping cervical cells’. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, Nagoya, Japan, September 2013, pp. 452–460.
    17. 17)
      • 53. Teramoto, A., Fujita, H., Yamamuro, O., et al: ‘Automated detection of pulmonary nodules in pet/ct images: ensemble false-positive reduction using a convolutional neural network technique’, Med. Phys., 2016, 43, (6), pp. 2821–2827.
    18. 18)
      • 65. Tucker, J.: ‘Cerviscan: an image analysis system for experiments in automatic cervical smear prescreening’, Comput. Biomed. Res. J. Med. Imaging, 1976, 9, (2), pp. 93–107.
    19. 19)
      • 35. Zhang, J., He, J., Chen, T., et al: ‘Abnormal region detection in cervical smear images based on fully convolutional network’, IET Image Process., 2018, 13, (4), pp. 583–590.
    20. 20)
      • 18. Lu, Z., Carneiro, G., Bradley, A.P., et al: ‘Evaluation of three algorithms for the segmentation of overlapping cervical cells’, IEEE J. Biomed. Health Inf., 2016, 21, (2), pp. 441–450.
    21. 21)
      • 66. ‘Dataset’, https://tianchi.aliyun.com/competition/, accessed November 2019.
    22. 22)
      • 23. Song, Y., Tan, E.L., Jiang, X., et al: ‘Accurate cervical cell segmentation from overlapping clumps in pap smear images’, IEEE Trans. Med. Imaging, 2016, 36, (1), pp. 288–300.
    23. 23)
      • 5. Birdsong, G.G.: ‘Automated screening of cervical cytology specimens’, Human Pathology, 1996, 27, (5), pp. 468–481.
    24. 24)
      • 57. Zlocha, M., Dou, Q., Glocker, B.: ‘Improving retinaNet for CT lesion detection with dense masks from weak RECIST labels’. Medical Image Computing and Computer Assisted Intervention - MICCAI 2019 - 22nd Int. Conf., Shenzhen, China, October 2019, pp. 402–410.
    25. 25)
      • 26. Lu, Z., Carneiro, G., Bradley, A.P.: ‘Segmentation of overlapping cervical cells: a variational method with star-shape prior’. 2015 IEEE 12th Int. Symp. on Biomedical Imaging (ISBI), Brooklyn, NY, USA, April 2015, pp. 186–189.
    26. 26)
      • 12. Zhang, L., Kong, H., Chin, C.T., et al: ‘Segmentation of cytoplasm and nuclei of abnormal cells in cervical cytology using global and local graph cuts’, Comput. Med. Imaging Graph., 2014, 38, (5), pp. 369–380.
    27. 27)
      • 49. Law, H., Deng, J.: ‘Cornernet: detecting objects as paired keypoints’. Computer Vision - ECCV 2018 - 15th European Conf., Munich, Germany, September 2018, pp. 765–781.
    28. 28)
      • 62. Li, X., Hu, X., Yang, J.: ‘Spatial group-wise enhance: Improving semantic feature learning in convolutional networks’. CoRR, 2019, abs/1905.09646.
    29. 29)
      • 54. Esteva, A., Kuprel, B., Novoa, R.A., et al: ‘Dermatologist-level classification of skin cancer with deep neural networks’, Nature, 2017, 542, (7639), pp. 115–118.
    30. 30)
      • 50. Tian, Z., Shen, C., Chen, H., et al: ‘FCOS: fully convolutional one-stage object detection’. 2019 IEEE Int. Conf. on Computer Vision (ICCV 2019), Seoul, Korea (South), October November 2 2019, pp. 9626–9635.
    31. 31)
      • 63. Avaiable at https://cs.adelaide.edu.au/, accessed November 2019.
    32. 32)
      • 2. Davey, E., Barratt, A., Irwig, L., et al: ‘Effect of study design and quality on unsatisfactory rates, cytology classifications, and accuracy in liquid-based versus conventional cervical cytology: a systematic review’, The Lancet, 2006, 367, (9505), pp. 122–132.
    33. 33)
      • 22. Ali, S., Madabhushi, A.: ‘An integrated region-, boundary-, shape-based active contour for multiple object overlap resolution in histological imagery’, IEEE Trans. Med. Imaging, 2012, 31, (7), pp. 1448–1460.
    34. 34)
      • 1. Bray, F., Ferlay, J., Soerjomataram, I., et al: ‘Global cancer statistics 2018: globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries’, CA: a Cancer J. Clinicians, 2018, 68, (6), pp. 394–424.
    35. 35)
      • 58. Yan, K., Wang, X., Lu, L., et al: ‘Deeplesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning’, Neurocomput. J. Med. Imaging, 2018, 5, (3), p. 036501.
    36. 36)
      • 45. Redmon, J., Divvala, S., Girshick, R., et al: ‘You only look once: unified, real-time object detection’. 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, USA, June 27-30 2016, pp. 779–788.
    37. 37)
      • 3. Park, S.Y., Sargent, D., Lieberman, R., et al: ‘Domain-specific image analysis for cervical neoplasia detection based on conditional random fields’, IEEE Trans. Med. Imaging, 2011, 30, (3), pp. 867–878.
    38. 38)
      • 46. Redmon, J., Farhadi, A.: ‘YOLO9000: better, faster, stronger’. 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA, July 2017, pp. 6517–6525.
    39. 39)
      • 40. Ren, S., He, K., Girshick, R., et al: ‘Faster R-CNN: towards real-time object detection with region proposal networks’, IEEE Trans. Pattern Anal. Mach. Intell., 2017, 39, (6), pp. 1137–1149.
    40. 40)
      • 16. Chen, Y.F., Huang, P.C., Lin, K.C., et al: ‘Semi-automatic segmentation and classification of pap smear cells’, IEEE J. Biomed. Health Inf., 2013, 18, (1), pp. 94–108.
    41. 41)
      • 64. Phoulady, H.A., Mouton, P.R.: ‘A new cervical cytology dataset for nucleus detection and image classification (cervix93) and methods for cervical nucleus detection’. CoRR, 2018, abs/1811.09651.
    42. 42)
      • 68. Nguyen, L.D., Gao, R., Lin, D., et al: ‘Biomedical image classification based on a feature concatenation and ensemble of deep cnns’, J. Ambient Intell. Humanized Comput., 2019, 10, pp. 1–13.
    43. 43)
      • 9. Isa, N.M.: ‘Automated edge detection technique for pap smear images using moving k-means clustering and modified seed based region growing algorithm’, Int. J. Comput. Int. Manage., 2005, 13, (3), pp. 45–59.
    44. 44)
      • 4. Denny, L., Quinn, M., Sankaranarayanan, R.: ‘Screening for cervical cancer in developing countries’, Vaccine, 2006, 24, pp. S71–S77.
    45. 45)
      • 71. Gautam, S., Jith, N., Sao, A.K., et al: ‘Considerations for a PAP Smear Image Analysis System with CNN Features’. CoRR, 2018, abs/1806.09025.
    46. 46)
      • 32. Zhang, L., Lu, L., Nogues, I., et al: ‘Deeppap: deep convolutional networks for cervical cell classification’, IEEE J. Biomed. Health Inf., 2017, 21, (6), pp. 1633–1643.
    47. 47)
      • 19. Zhang, L., Kong, H., Liu, S., et al: ‘Graph-based segmentation of abnormal nuclei in cervical cytology’, Comput. Med. Imaging Graph., 2017, 56, pp. 38–48.
    48. 48)
      • 60. Chen, K., Wang, J., Pang, J., et al: ‘MMDetection: Open MMLab Detection Toolbox and Benchmark’. CoRR, 2019, abs/1906.07155.
    49. 49)
      • 67. Paszke, A., Gross, S., Chintala, S., et al: ‘Automatic differentiation in pytorch’. NIPS 2017 Workshop, Long Beach, CA, USA, 2017.
    50. 50)
      • 20. Zhang, L., Sonka, M., Lu, L., et al: ‘Combining fully convolutional networks and graph-based approach for automated segmentation of cervical cell nuclei’. 2017 IEEE 14th Int. Symp. on Biomedical Imaging (ISBI 2017), Melbourne, Australia, April 2017, pp. 406–409.
    51. 51)
      • 51. Kong, T., Sun, F., Liu, H., et al: ‘FoveaBox: Beyond Anchor-based Object Detector’. CoRR, 2019, abs/1904.03797.
    52. 52)
      • 36. Zhang, C., Liu, D., Wang, L., et al: ‘DCCL: a benchmark for cervical cytology analysis’. Int. Workshop on Machine Learning in Medical Imaging (MICCAI 2019), Shenzhen, China, October 2019, pp. 63–72.
    53. 53)
      • 52. Zhang, X., Wan, F., Liu, C., et al: ‘FreeAnchor: learning to match anchors for visual object detection’. Advances in Neural Information Processing Systems 32: Annual Conf. on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, BC, Canada, December 2019, pp. 147–155.
    54. 54)
      • 39. Girshick, R.: ‘Fast R-CNN’. 2015 IEEE Int. Conf. on Computer Vision (ICCV 2015), Santiago, Chile, December 2015, pp. 1440–1448.
    55. 55)
      • 13. Chankong, T., Theera-Umpon, N., Auephanwiriyakul, S.: ‘Automatic cervical cell segmentation and classification in pap smears’, Comput. Methods Programs Biomed., 2014, 113, (2), pp. 539–556.
    56. 56)
      • 15. GençPlissiti, M.E., Nikou, C.: ‘Overlapping cell nuclei segmentation using a spatially adaptive active physical model’, IEEE Trans. Image Process., 2012, 21, (11), pp. 4568–4580.
    57. 57)
      • 28. Jantzen, J., Norup, J., Dounias, G., et al: ‘Pap-smear benchmark data for pattern classification’. Nature inspired Smart Information Systems (NiSIS 2005), Albufeira, Portugal, 2015, pp. 1–9.
    58. 58)
      • 61. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, USA, June 2016, pp. 770–778.
    59. 59)
      • 8. Bamford, P., Lovell, B.: ‘A water immersion algorithm for cytological image segmentation’. Proc. APRS Image Segmentation Workshop, Sydney, Australia, December 1996, pp. 75–79.
    60. 60)
      • 37. Lin, T., Dollar, P., Girshick, R., et al: ‘Feature pyramid networks for object detection’. 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA, 2017, pp. 936–944.
    61. 61)
      • 29. Iliyasu, A.M., Fatichah, C.: ‘A quantum hybrid pso combined with fuzzy k-nn approach to feature selection and cell classification in cervical cancer detection’, Sensors, 2017, 17, (12), p. 2935.
    62. 62)
      • 7. Zhang, L., Kong, H., Ting-Chin, C.: ‘Automation-assisted cervical cancer screening in manual liquid-based cytology with hematoxylin and eosin staining’, Cytometry Part A, 2014, 85, (3), pp. 214–230.
    63. 63)
      • 69. Jith, O.N., Harinarayanan, K., Gautam, S., et al: ‘DeepCerv: dEep neural network for segmentation free robust cervical cell classification’. Computational Pathology and Ophthalmic Medical Image Analysis - First Int. Workshop, COMPAY 2018, and 5th Int. Workshop, OMIA 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 2018, pp. 86–94.
    64. 64)
      • 31. Tareef, A., Song, Y., Cai, W., et al: ‘Learning shape-driven segmentation based on neural network and sparse reconstruction toward automated cell analysis of cervical smears’. Int. Conf. on Neural Information Processing (ICONIP 2015), Istanbul, Turkey, November 2015, pp. 390–400.
    65. 65)
      • 17. Song, Y., Zhang, L., Chen, S., et al: ‘Accurate segmentation of cervical cytoplasm and nuclei based on multiscale convolutional network and graph partitioning’, IEEE Trans. Biomed. Eng., 2015, 62, (10), pp. 2421–2433.
    66. 66)
      • 33. Tareef, A., Song, Y., Cai, W., et al: ‘Diagnosing cervical cell images using pre-trained convolutional neural network as feature extractor’. 2017 IEEE Int. Conf. on Big Data and Smart Computing (BigComp 2017), Jeju Island, South Korea, February 2017, pp. 390–393.
    67. 67)
      • 48. Lin, T.-Y., Goyal, P., Girshick, R.B., et al: ‘Focal loss for dense object detection’. 2017 IEEE Int. Conf. on Computer Vision (ICCV 2017), Venice, Italy, October 2017, pp. 2999–3007.
    68. 68)
      • 44. Fu, C.Y., Liu, W., Ranga, A., et al: ‘DSSD: Deconvolutional Single Shot Detector’. CoRR, 2017, abs/1701.06659.
    69. 69)
      • 70. Lin, H., Hu, Y., Chen, S., et al: ‘Fine-grained classification of cervical cells using morphological and appearance based convolutional neural networks’, IEEE Access, 2019, 7, pp. 71541–71549.
    70. 70)
      • 34. Meiquan, X., Weixiu, Z., Yanhua, S., et al: ‘Cervical cytology intelligent diagnosis based on object detection technology’. 1st Conf. on Medical Imaging with Deep Learning (MIDL2018), Amsterdam, The Netherlands, 2018.
    71. 71)
      • 30. Teeyapan, K., Theera-Umpon, N., Auephanwiriyakul, S.: ‘Application of support vector based methods for cervical cancer cell classification’. 2015 IEEE Int. Conf. on Control System, Computing and Engineering (ICCSCE 2015), Penang, Malaysia, November 2015, pp. 514–519.
    72. 72)
      • 21. Kong, H., Gurcan, M., Belkacem-Boussaid, K.: ‘Partitioning histopathological images: an integrated framework for supervised color-texture segmentation and cell splitting’, IEEE Trans. Med. Imaging, 2011, 30, (9), pp. 1661–1677.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2020.0688
Loading

Related content

content/journals/10.1049/iet-ipr.2020.0688
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address