Research on PET/CT Image Segmentation and Its Development
FANG Ling-ling1, QIU Tian-shuang2, PAN Xiao-hang1, QIAO Ming-ze1
1. College of Computer and Information Technology, Liaoning Normal University, Dalian, Liaoning 116029, China;
2. Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning 116023, China
Abstract：With the rapid progress of precision medical technology,the segmentation of lesion regions in PET/CT images has played an important role in the development of medical plans.PET/CT combines two advanced imaging technologies organically:PET (functional metabolic imaging) and CT (anatomical structure imaging),which is an important progress in image diagnostics.Combined with the segmentation methods,this paper describes the characteristics of PET/CT images,the analysis of the current methods and the clinical application.Finally,the paper elaborates the development trend of PET/CT image segmentation technology.
[1] National Research Council (US) Committee on a framework for developing a new taxonomy of disease.Toward precision medicine:building a knowledge network for biomedical research and a new taxonomy of disease[R].National Academies Press (US),2011.
[2] Dhara A K,Mukhopadhyay S,Khandelwal N.Computer-aided detection and analysis of pulmonary nodule from CT images:a survey[J].IETE Technical Review,2012,29(4):265-275.
[3] Ballangan C,Wang X,Fulham M,et al.Automated delineation of lung tumors in PET images based on monotonicity and a tumor-customized criterion[J].IEEE Transactions on Information Technology in Biomedicine,2011,15(5):691-702.
[4] Fried D,Zhang L,Fave X,et al.MO-DE-207B-10:Impact of morphologic characteristics on radiomics features from contrast-enhanced CT for primary lung tumors[J].Medical Physics,2016,43(6):3706-3706.
[5] Daouk J,Bailly P,Bouzerar R,et al.Effect of tomographic operator inaccuracies and respiratory motion on PET/CT lung nodule images smearing[J].Nuclear Medicine Communications,2017,38(2):178-184.
[6] Nermina B,Amera S,Renata M,et al.Advantages of combined PET-CT in mediastinal staging in patients with non-small cell lung carcinoma[J].Acta Informatica Medica,2016,24(2):99-102.
[7] Zheng X,Tian G,Huang S C,et al.A hybrid clustering method for ROI delineation in small animal dynamic PET images:application to the automatic estimation of FDG input functions[J].IEEE Engineering in Medicine & Biology Society,2011,15(2):195-205.
[8] Zsoter N,Bandi P,Szabo G,et al.PET-CT based automated lung nodule detection[A].IEEE Annual International Conference on Engineering in Medicine and Biology Society[C].IEEE,2012.4974-4977.
[9] Mharib A M,Ramli A R,Mashohor S,et al.Survey on liver CT image segmentation methods[J].Artificial Intelligence Review,2012,37(2):83-95.
[10] Sharifi M,Yousefnia H,Bahramisamani A,et al.Optimized production,quality control,biological evaluation and PET/CT imaging of 68Ga-PSMA-617 in breast adenocarcinoma model[J].Radio Chimica Acta,2017,105(5):399-407.
[11] Karki K,Hugo G,Saraiya S,et al.TU-H-CAMPUS-JeP2-02:Interobserver variability of CT,PET-CT and MRI based primary tumor delineation for lung cancer[J].Medical Physics,2016,43(6):3782-3782.
[12] Hines J P,Howard B E,Hoxworth J M,et al.Positive and negative predictive value of PET-CT in skull base lesions:case series and systematic literature review[J].J Neurol Surg Rep,2016,77(01):39-45.
[13] Biehl K J,Kong F M,Dehdashti F,et al.18F-FDG PET definition of gross tumor volume for radiotherapy of non-small cell lung cancer:is a single standardized uptake value threshold approach appropriate?[J].Journal of Nuclear Medicine,2006,47(11):1808-1812.
[14] Belhassen S,Zaidi H.A novel fuzzy C-means algorithm for unsupervised heterogeneous tumor quantification in PET[J].Medical Physics,2010,37(3):1309-1324.
[15] Mu W,Chen Z,Shen W,et al.A segmentation algorithm for quantitative analysis of heterogeneous tumors of the cervix with 18F-FDG PET/CT[J].IEEE Transactions on Biomedical Engineering,2015,62(10):2465-2479.
[16] Xu Z,Bagci U,Udupa J K,et al.Fuzzy connectedness image co-segmentation for hybrid PET/MRI and PET/CT scans.Computational Methods for Molecular Imaging[M].Springer International Publishing,2015.15-24.
[17] Han D,Bayouth J,Song Q,et al.Globally optimal tumor segmentation in PET-CT images:a graph-based co-segmentation method[A].Information Processing in Medical Imaging[C].Springer,2011.245-256.
[18] Guo Y,Feng Y,Sun J,et al.Automatic lung tumor segmentation on PET/CT images using fuzzy Markov random field model[J].Computational and Mathematical Methods in Medicine,2014,1:171-188.
[19] Hussein S,Green A,Watane A,et al.Automatic segmentation and quantification of white and brown adipose tissues from PET/CT scans[J].IEEE Transactions on Medical Imaging,2017,36(3):734-744.
[20] Wanet M,Lee J A,Weynand B,et al.Gradient-based delineation of the primary GTV on FDG-PET in non-small cell lung cancer:a comparison with threshold-based approaches,CT and surgical specimens[J].Journal of the European Society for Therapeutic Radiology & Oncology,2011,98(1):117-125.
[21] Jin Z,Arimura H,Shioyama Y,et al.Computer-assisted delineation of lung tumor regions in treatment planning CT images with PET/CT image sets based on an optimum contour selection method[J].Journal of Radiation Research,2014,55(6):1153-62.
[22] Hatt M,Tixier F,Pierce L,et al.Characterization of PET/CT images using texture analysis:the past,the present and future[J].European Journal of Nuclear Medicine Molecular Imaging,2017,44(1):1-15.
[23] Jung Y H,Kim J,Feng D,et al.Occlusion and slice-based volume rendering augmentation for PET-CT[J].IEEE Journal of Biomedical & Health Informatics,2016,21(4):1005-1014.
[24] Bagci U,Udupa J K,Yao J,et al.Co-segmentation of functional and anatomical images[J].Medical Image Computing and Computer-assisted Intervention,2012,15(3):459-467.
[25] Yu K,Chen X,Zhu W,et al.A novel 3D graph cut based co-segmentation of lung tumor on PET-CT images with gaussian mixture models[A].SPIE Medical Imaging[C].SPIE,2016.1-7.
[26] Cremonesi M,Gilardi L,Ferrari M E,et al.Role of interim 18 F-FDG-PET/CT for the early prediction of clinical outcomes of non-small cell lung cancer (NSCLC) during radiotherapy or chemo-radiotherapy.A systematic review[J].European Journal of Nuclear Medicine & Molecular Imaging,2017,44(11):1915-1927.
[27] Cui H,Wang X,Feng D.Automated localization and segmentation of lung tumor from PET-CT thorax volumes based on image feature analysis[A].IEEE Annual International Conference on Engineering in Medicine and Biology Society[C].IEEE,2012.5384-5387.
[28] Bagci U,Udupa J K,Mendhiratta N,et al.Joint segmentation of anatomical and functional images:applications in quantification of lesions from PET,PET-CT,MRI-PET,and MRI-PET-CT images[J].Medical Image Analysis,2013,17(8):929-945.
[29] Ju W,Xiang D,Zhang B,et al.Random walk and graph cut for co-segmentation of lung tumor on PET-CT images[J].IEEE Transactions on Image Processing,2015,24(12):5854-5867.
[30] Song Q,Bai J,Han D,et al.Optimal co-segmentation of tumor in PET-CT images with context information[J].IEEE Transactions on Medical Imaging,2013,32(9):1685-1697.
[31] Hu Y C,Grossberg M,Mageras G.Tumor segmentation with multi-modality image in conditional random field framework with logistic regression models[A].IEEE International Conference on Engineering in Medicine and Biology Society (EMBC)[C].IEEE,2014.6450-6454.
[32] Lecca M,Messelodi S,Serapioni R P.A new region-based active contour model for object segmentation[J].Journal of Mathematical Imaging & Vision,2015,53(2):233-249.
[33] 王相海,方玲玲.活动轮廓模型的图像分割方法综述[J].模式识别与人工智能,2013,8:751-760. WANG Xiang-hai,FANG Ling-ling.Overview of image segmentation methods of active contour model[J].Pattern Recognition and Artificial Intelligence,2013,8:751-760.(in Chinese)
[34] Markel D,Zaidi H,El N I.Novel multimodality segmentation using level sets and Jensen-renyi divergence[J].Medical Physics,2013,40(12):1-15.
[35] El N I,Yang D,Apte A,et al.Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning[J].Medical Physics,2007,34(12):4738-4749.
[36] Qiang Y,Zhang X,Ji G,et al.Automated lung nodule segmentation using an active contour model based on PET/CT images[J].Journal of Computational & Theoretical Nanoscience,2015,12(8):1972-1976.
[37] Derraz F,Pinti A,Peyrodie L,et al.Joint variational segmentation of CT/PET data using non-local active contours and belief functions[J].Pattern Recognition & Image Analysis,2015,25(3):407-412.
[38] Yu H,Caldwell C,Mah K,et al.Coregistered FDG PET/CT-based textural characterization of head and neck cancer for radiation treatment planning[J].IEEE Transactions on Medical Imaging,2009,28(3):374-383.
[39] Markel D,Caldwell C,Alasti H,et al.Automatic segmentation of lung carcinoma using 3D texture features in 18-FDG PET/CT[J].International Journal of Molecular Imaging,2013,11:1-13.
[40] Lee J G,Jun S,Cho Y W,et al.Deep learning in medical imaging:general overview[J].Korean Journal of Radiology,2017,18(4):570-584.
[41] Greenspan H,van Ginneken B,Summers R M.Guest editorial deep learning in medical imaging:overview and future promise of an exciting new technique[J].IEEE Transactions on Medical Imaging,2016,35(5):1153-1159.
[42] Enlitic technology detected lung cancer nodules in chest CT images[ON].http://www.enlitic.com/science.html#deep-learning,2015.
[43] Ronneberger O,Fischer P,Brox T.U-Net:Convolutional Networks for Biomedical Image Segmentation[A].International Conference on Medical Image Computing and Computer-Assisted Intervention[C].Springer,2015:234-241.
[44] Sridhar P,Mercier G,Tan J,et al.FDG PET metabolic tumor volume segmentation and pathologic volume of primary human solid tumors[J].AjrAmerican Journal of Roentgenology,2014,202(5):1114-1119.
[45] Schinagl D A,Span P N,van den Hoogen F J,et al.Pathology-based validation of FDG PET segmentation tools for volume assessment of lymph node metastases from head and neck cancer[J].European Journal of Nuclear Medicine & Molecular Imaging,2013,40(12):1828-1835.
[46] Zaidi H,et al.Comparative methods for PET image segmentation in pharyngolaryngeal squamous cell carcinoma[J].European Journal of Nuclear Medicine & Molecular Imaging,2012,39(5):881-891.
[47] Heuvelmans M A,Oudkerk M.Management of subsolid pulmonary nodules in CT lung cancer screening[J].Thorac Dis,2015,7(7):1103-1106.
[48] Wanet M,Lee J A,Weynand B,et al.Gradient-based delineation of the primary GTV on FDG-PET in non-small cell lung cancer:a comparison with threshold-based approaches,CT and surgical specimens[J].Radiother Oncol,2011,98(1):117-125.
[49] Wu K,Ung Y C,Hornby J,et al.PET CT thresholds for radiotherapy target definition in non-small-cell lung cancer:how close are we to the pathologic findings?[J].International Journal of Radiation Oncology Biology Physics,2010,77(3):699-706.
[50] Schaefer A,Kim Y J,Kremp S,et al.PET-based delineation of tumour volumes in lung cancer:comparison with pathological findings[J].European Journal of Nuclear Medicine & Molecular Imaging,2013,40(8):1233-1244.
[51] Sharif M S,Abbod M,Amira A,et al.Artificial neural network-based system for PET volume segmentation[J].International Journal of Biomedical Imaging,2010,105610:1-11.
[52] Zhang Y,Hu J,Lu H J,et al.Determination of an optimal standardized uptake value of fluorodeoxyglucose for positron emission tomography imaging to assess pathological volumes of cervical cancer:a prospective study[J].Plos One,2016,8(11):1-7.
[53] Chen S W,et al.Which FDG/PET parameters of the primary tumors in colonor sigmoid cancer provide the best correlation with the pathological findings?[J].European Journal of Radiology,2013,82(9):405-410.
[54] Buijsen J,et al.FDG-PET provides the best correlation with the tumor specimen compared to MRI and CT in rectal cancer[J].Radiother Oncol,2011,98(2):270-276.
[55] Bai J,Song Q,Wu X.Globally optimal lung tumor co-segmentation of 4D CT and PET images[J].The International Society for Optical Engineering,2013,8669(6):1-7.
[56] Li H,Bai J,Wu X,et al.Semi-automated co-segmentation of tumor volume using multimodality PET-CT in non-small cell lung cancer (NSCLC)[J].Journal of Cancer and Clinical Research,2014,1(3):1-6.
[57] Song Q,Chen M,Bai J,et al.Surface-region context in optimal multi-object graph-based segmentation:robust delineation of pulmonary tumors[J].Information Processing in Medical Imaging,2011,22(8):61-72.
[58] Fried D,Zhang L,Fave X,et al.MO-DE-207B-10:impact of morphologic characteristics on radiomics features from contast-enhanced CT for primary lung tumors[J].Medical Physics,2016,43(6):3706-3706.
2018, Vol. 46 
