Abstract
For the purpose of accurate diagnosis and early treatment for cancers, the classification and identification of different tumors is the key problem of computer-aided diagnosis system. In this paper, an improved semi-supervised tumor identification method is proposed, which takes advantage of the Fuzzy c-means clustering algorithm and offers a pathological degree tree based on ten three-dimentional (3-D) and two dimentional (2-D) tumor features. In addition, a great deal of complicated data processing is distributed in the fog computing architecture. First, we carry out the segmentation of tumors by using FRFCM algorithm, and complete the 3-D modeling. Then, the pathological shape features of 3-D and 2-D tumors are extracted from modeling, for constructing a group of feature vector. Finally, based on the landmark information of labeled samples provided by standard database and experts, we realize an improved semi-supervised FCM clustering to guide the tumor identification. The experiments are conducted by using medical CT scans of 143 patients including 452 tumors. Overall, the best average identification accuracy of \(94.6\%\) has been recorded for this proposed method, the ability of machine learning to recognize the benign, malignant and false-positive tumors is improved effectively under imbalanced data sets.
Similar content being viewed by others
References
Armato SG, McLennan G, Bidaut L (2011) The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. Med Phys 38(2):915–931
Ayman EB, Garth MB, Georgy G, Kenji S, Kazunori O, Ahmed E, Ahmed S, Behnoush A (2013 ) Computer-aided diagnosis systems for lung cancer: challenges and methodologies. Int J Biomed Imaging:46 (Article ID: 942353)
Chang XJ, Yu YL, Yang Y, Xing EP (2017) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Pattern Anal Mach Intell 39(8):1617–1632
Chen XF, Li J, Huang XY, Ma JF, Lou WJ (2015) New publicly verifiable databases with efficient updates. IEEE Trans Dependable Secure Comput 12(5):546–556
Chen XF, Li J, Weng J, Ma JF, Lou WJ (2016) Verifiable computation over large database with incremental updates. IEEE Trans Comput 65(10):3184–3195
DOI K (2014) Current status and future potential of computer-aided diagnosis in medical imaging. Br J Radiol 78(SUOOL–1):S3–S19
Dou Q, Chen H, Yu LQ, Zhao L, Qin J, Wang DF, Vincent CTM, Shi L, Heng PA (2016) Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks. IEEE Trans Med Imaging 35(5):1182–1195
Endo Y, Hamasuna Y, Yamashiro M, Miyamoto S (2009) On semi-supervised fuzzy c-means clustering. In: IEEE international conference on fuzzy systems (FUZZ-IEEE 2009), pp 1119–1124
Fantine M, Jean-Philippe V (2014) A bagging SVM to learn from positive and unlabeled examples. Pattern Recogn Lett 37(1):201–209
Flavio B, Rodolfo M, Zhu J, Sateesh A (2012) Fog computing and its role in the internet of things. In: ACM SIGCOMM international conference on mobile cloud computing, pp 13–16, August 2012
Han FF, Zhang GP, Wang HF, Song BW, Lu HB, Zhao DZ, Zhao H, Liang ZR (2013) A texture feature analysis for diagnosis of pulmonary nodules using LIDC-IDRI database. In: IEEE international conference on medical imaging physics and engineering, pp 14–18
Hu MK (1962) Visual pattern recognition by moment if variants. IEEE Trans Inf Theory (IT-08):179–187
Jamshid D, Hamdan A, Manlio V, Ye XJ (2008) Segmentation of pulmonary nodules in thoracic CT scans: a region growing approach. IEEE Trans Med Imaging 27(4):467–480
Julian A (2014) Biometrics in the cloud. Biometrics in the new world, pp 37–46
Keelin M, Ginneken BV, Schilham A, Prokop M (2009) A large scale evaluation of automatic pulmonary nodule detection in chest CT using local image features and k-nearest-neighbor classification. Med Image Anal 13(5):757–770. https://doi.org/10.1007/s00500-017-2608-5
Kim S, Lee I (2017) Iot device security based on proxy re-encryption. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-017-0602-5
Korsuk S, Shan EAR, Yee-Wah T, David RJS, Ian AC, Nasir MR (2016) Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. IEEE Trans Med Imaging 35(5):1196–1206
Kuruvilla J, Gunavathi K (2014) Lung cancer classification using neural networks for CT images. Comput Methods Programs Biomed 113(1):202–209
Li J, Chen XF, Li MQ, Li JW, Lee PPC, Lou WJ (2014) Secure deduplication with efficient and reliable convergent key management. IEEE Trans Parallel Distrib Syst 25(6):1615–1625
Li J, Li YK, Chen XF, Lee PPC, Lou WJ (2015a) A hybrid cloud approach for secure authorized deduplication. IEEE Trans Parallel Distrib Syst 26(5):1206–1216
Li J, Zhang YH, Chen XF, Xiang Y (2017a) Secure attribute-based data sharing for resource-limited users in cloud computing. Comput Secur 72:1–12. https://doi.org/10.1016/j.cose
Li JJ, Lu K, Zhu L, Li ZH (2017b) Locality-constrained transfer coding for heterogeneous domain adaptation. In: Huang Z, Xiao X, Cao X (eds) Databases theory and applications. Lecture notes in computer science. ADC 2017, pp 193–204
Li L, Li JW, Chen XF, Jia CF, Lou WJ (2015b) Identity-based encryption with outsourced revocation in cloud computing. IEEE Trans Comput 64(2):425–437
Li P, Li J, Huang ZG, Li T, Gao CZ, Yiu SM, Chen K (2017c) Multi-key privacy-preserving deep learning in cloud computing. Future Gen Comput Syst 74(C):76–85
Li P, Li L, Huang ZG, Gao CZ, Chen WB, Chen K (2017d) Privacy-preserving outsourced classification in cloud computing. Cluster Comput. https://doi.org/10.1007/s10586-017-0849-9
Li ZH, Nie FP, Chang XJ, Yang Y (2017e) Beyond trace ratio: weighted harmonic mean of trace ratios for multiclass discriminant analysis. IEEE Trans Knowl Data Eng 29(10):2100–2110
Liu H, Zhang CH (2012) 3-D visualization surface rendering algorithm based on medical image. Comput Aided Des Appl 9(1):79–86
Liu H, Zhang CM, Su ZY, Wang K, Deng K (2015) Research on a pulmonary nodule segmentation method combining fast self-adaptive FCM and classification. Comput Math Methods Med. https://doi.org/10.1155/2015/185726
Liu H, Geng FH, Guo Q, Zhang CQ, Zhang CM (2017a) A fast weak-supervised pulmonary nodule segmentation method based on modified self-adaptive FCM algorithm. Soft Comput. https://doi.org/10.1007/s00500-017-2608-5
Liu LY, Zhu L, Li ZH (2017b) Learning robust graph hashing for efficient similarity search. In: Huang Z, Xiao X, Cao X (eds) Databases theory and applications. Lecture Notes in Computer Science. ADC 2017, pp 110–122
Lokesh G, Mandyam DS (1987) Contour sequence moments for the classification of closed planar shapes. Pattern Recogn 20(3):267–272
Majid H, Saeid G (2014) A review on modern distributed computing paradigms: cloud computing, jungle computing, and fog computing. J Comput Inf Technol 22(2):69–84
Marc C, Frank DS, Johan AKS, Bart DM (2015) A robust ensemble approach to learn from positive and unlabeled data using SVM base models. Neurocomputing 160(C):73–84
Maxine T, Rudi D, Bart J (2011) A novel computer-aided lung nodule detection system for CT images. Med Phys 38(10):5630–5645
Orozco HM, Villegas OOV, Sánchez VGC, Domínguez HJO, Alfaro HJNA (2015) Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine. BioMed Eng Online 14(1):1–20
Qiu T, Liu XZ, Feng L, Zhou Y, Zheng KY (2016) An efficient tree-based self-organizing protocol for internet of things. IEEE Access 4(6):3535–3546
Rebecca LS, Kimberly DM, Ahmedin JDVM (2017) Cancer statistics 2017. CA Cancer J Clin 67(1):7–30
Roy W, Bill NS, Scott J (2015) Enabling the internet of things. Computer 48(1):28–35
Setio AA, Ciompi F, Litjens G, Gerke P, Jacobs C, van Riel SJ, Wille M, ang Naqibullah MM, Sanchez CI, van Ginneken B (2016) Pulmonary nodule detection in CT images: false positive reduction using multiview convolutional networks. IEEE Trans Med Imaging 35(5):1160–1169
Sun T, Wang JJ, Li X, Lv PP, Liu F, Luo YX, Gao Q, Zhu HP, Guo XH (2013) Comparative evaluation of support vector machines for computer aided diagnosis of lung cancer in CT based on a multidimensional data set. Comput Methods Progr Biomed 111(2):519–524
Tian YF, Lu ST, Yang CY (2013) Macro–pico amplitude-space sharing with optimized Han–Kobayashi coding. IEEE Trans Commun 61(10):4404–4415
Trang KL (2013) Segmentation of lung vessels together with nodules in CT images using morphological operations and level set method. J Med Bioeng 2(1):5–10
Vivek S, Bipin KT, Vinay KP (2014) Biometric recognition by hybridization of evolutionary fuzzy clustering with functional neural networks. J Ambient Intell Humaniz Comput 5(4):525–537
Witold P, James W (1997) Fuzzy clustering with partial supervision. IEEE Trans Syst Man Cybern Part B Cybern 27(5):787–795
Wu JS, Guo S, Li J, Zeng DZ (2016a) Big data meet green challenges: BIG data toward green applications. IEEE Syst J 3:888–900
Wu JS, Guo S, Li J, Zeng DZ (2016b) Big data meet green challenges: greening big data. IEEE Syst J 3:873–887
Zheng FH, Zhang CM, Zhang XF, Liu Y (2013) A fast anti-noise fuzzy c-means algorithm for image segmentation. In: IEEE international conference on image processing (ICIP), pp 2728–2732
Acknowledgements
This work is supported by National Natural Science Foundation (61572286, U1609218 and 61472220), Natural Science Foundation of Shandong Province (2016ZRB 01143), and the Fostering Project of Dominant Discipline an Talent Team of Shandong Province Higher Education. The authors sincerely thank Dr. Guangli Wang for her efforts to carefully label and verify the ground truth of the dataset, also gratefully acknowledge the helpful comments and suggestions of the reviewers, which have improved the presentation significantly.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xu, J., Liu, H., Shao, W. et al. Quantitative 3-D shape features based tumor identification in the fog computing architecture. J Ambient Intell Human Comput 10, 2987–2997 (2019). https://doi.org/10.1007/s12652-018-0695-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-018-0695-5