Complete fully automatic segmentation and 3-dimensional measurement of mediastinal lymph nodes for a new response evaluation criteria for solid tumors

• Autorzy: Kuo Chung-Feng Jeffrey , Hsun Lin Kuan , Weng Wei-Han , Barman Jagadish , Huang Chun-Chia , Chiu Chih-Wei , Lee Ji-Lun , Hsu Hsian-He

Identyfikatory

DOI

10.1016/j.bbe.2021.03.008

• Języki publikacji: EN

Abstrakty

EN

We aimed to automatically detect and segment mediastinal lymph nodes, and to establish an objective method and reliable new response evaluation criteria to monitor the effectiveness of cancer treatment. The image processing techniques were applied and developed 3D measurement of the mediastinal lymph nodes based on automatic settings when segmenting the lymph node image. A repeatable and consistent lymph node evaluation system was created based on such features as the position of occurrence, grayness, and number of serial sections of lymph nodes. A total of 200 lymph node samples from Tri-Service General Hospital, Taiwan, were examined for statistical analysis. The proposed approach used weighted k-nearest neighbors for classification, achieving superior results with an accuracy and specificity of 97.5% and 99.4%, respectively. The volume of the lymph nodes was used as the reference index for tumor invasiveness evaluation. The error in the lymph node volume was 1.71% according to the verification results. Receiver operating characteristic (ROC) curves for each analysis were constructed and the area under the curve (AUC) was calculated with histopathology diagnosis as outcome for determining the optimal volume threshold of benign and malignant lymph nodes. It was observed that the lymph node volume was highly correlated with tumor invasion (p-value was less than 0.05). The experiment showed that the volume for the area under the ROC curve was 0.90 of tumor invasion evaluation. The lymph node volume was most effective in predicting tumor invasiveness, with the value 798.53 mm3 used as the standard for judging benignity and malignancy.

Słowa kluczowe

EN

mediastinal lymph nodes; cancer invasiveness index; lung cancer; computed tomography; medical segmentation

PL

wskaźnik inwazyjności raka; rak płuc; tomografia komputerowa; segmentacja medyczna

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 2
• Strony: 617--635
• Opis fizyczny: Bibliogr. 66 poz., rys., tab.

Twórcy

autor

Kuo Chung-Feng Jeffrey

• Department of Materials Science and Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

autor

Hsun Lin Kuan

• Division of Thoracic Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, Republic of China

autor

Weng Wei-Han

• Department of Materials Science and Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

autor

Barman Jagadish

• Department of Materials Science and Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

autor

Huang Chun-Chia

• Department of Materials Science and Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

autor

Chiu Chih-Wei

• Department of Materials Science and Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

autor

Lee Ji-Lun

• Department of Materials Science and Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan

autor

Hsu Hsian-He

• Department of Radiology, Tri-Service General Hospital and National Defense Medical Center, Taipei, Taiwan

Bibliografia

• [1] Kamiyoshihara M, Kawashima O, Ishikawa S, Morishita Y. Mediastinal lymph node evaluation by computed tomographic scan in lung cancer. J Cardiovasc Surg 2001;42 (1):119–24.
• [2] Eisenhauer EA, Therasse P, Bogaerts J, Schwartz LH, Sargent D, Ford R, et al. New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer 2009;45(2):228–47.
• [3] Schwartz LH, Bogaerts J, Ford R, Shankar L, Therasse P, Gwyther S, et al. Evaluation of lymph nodes with RECIST 1.1. Eur J Cancer 2009;45(2):261–7.
• [4] Choe G, Schipper P. Quality of lymph node assessment and survival among patients with non–small cell lung cancer. JAMA Oncol 2018;4(1):87–8.
• [5] Carolus H, Iuga AI, Brosch T, Wiemker R, Thiele F, Höink A, et al. Automated detection and segmentation of mediastinal and axillary lymph nodes from CT using foveal fully convolutional networks. Medical Imaging. Comput-Aided Diagn 2020;11314:113141B.
• [6] Fréchet B, Kazakov J, Thiffault V, Ferraro P, Liberman M. Diagnostic accuracy of mediastinal lymph node staging techniques in the preoperative assessment of non-small cell lung cancer patients. J Bronchol Interv Pulmonol 2018;25 (1):17–24.
• [7] Tantraworasin A, Taioli E, Liu B, Kaufman AJ, Flores RM. Underperformance of mediastinal lymph node evaluation in resectable non-small cell lung cancer. Ann Thorac Surg 2018;105(3):943–9.
• [8] De Leyn P, Dooms C, Kuzdzal J, Lardinois D, Passlick B, RamiPorta R, et al. Revised ESTS guidelines for preoperative mediastinal lymph node staging for non-small-cell lung cancer. Eur J Cardiothorac Surg 2014;45(5):787–98.
• [9] Bouget D, Jørgensen A, Kiss G, Leira HO, Langø T. Semantic segmentation and detection of mediastinal lymph nodes and anatomical structures in CT data for lung cancer staging. Int J comput Assist Radiol Surg 2019;14(6):977–86.
• [10] Beichel RR, Wang Y. Computer-aided lymph node segmentation in volumetric CT data. Med Phys 2012;39 (9):5419–28.
• [11] Honea DM, Snyder WE. Three-dimensional active surface approach to lymph node segmentation. Medical Imaging 1999: Image Processing 1999;3661:1003–11.
• [12] Yan J, Zhuang TG, Zhao B, Schwartz LH. Lymph node segmentation from CT images using fast marching method. Comput Med Imaging Graph 2004;28(1–2):33–8.
• [13] Yan J, Zhao B, Wang L, Zelenetz A, Schwartz LH. Markercontrolled watershed for lymphoma segmentation in sequential CT images. Med Phys 2006;33(7Part1):2452–60.
• [14] Dornheim J, Seim H, Preim B, Hertel I, Strauss G. Segmentation of neck lymph nodes in CT datasets with stable 3D mass-spring models: Segmentation of neck lymph nodes. Acad Radiol 2007;14(11):1389–99.
• [15] Steger S, Ebert D, Erdt M. Lymph node segmentation in CT slices using dynamic programming. Proc IEEE Int Symp Biomed Imaging 2011:1990–3.
• [16] Yu P, Poh CL. Region-based snake with edge constraint for segmentation of lymph nodes on CT images. Comput Biol Med 2015;60:86–91.
• [17] Du J, Shen Y, Yan W, Wang J. Risk factors of lymph node metastasis in the splenic hilum of gastric cancer patients: a meta-analysis. World J Surg Oncol 2020;18(1):1–9.
• [18] Kano Y, Ohashi M, Ida S, Kumagai K, Makuuchi R, Sano T, et al. Therapeutic value of splenectomy to dissect splenic hilar lymph nodes for type 4 gastric cancer involving the greater curvature, compared with other types. Gastric Cancer 2020;23(5):927–36.
• [19] Zhong Q, Chen QY, Xu YC, Zhao G, Cai LS, Li GX, et al. Reappraise role of No. 10 lymphadenectomy for proximal gastric cancer in the era of minimal invasive surgery during total gastrectomy: a pooled analysis of 4 prospective trial. Gastric Cancer 2021;24:245–57.
• [20] Bando Y, Hinata N, Terakawa T, Furukawa J, Harada K, Nakano Y, et al. Diagnostic and therapeutic value of pelvic lymph node dissection in the fossa of Marcille in patients with clinically localized high-risk prostate cancer: Histopathological and molecular analyses. Prostate 2020;80(4):345–51.
• [21] Sebben M, Tafuri A, Porcaro AB, Artibani W, Cacciamani G, Response to: Bando, et al. Diagnostic and therapeutic value of pelvic lymph node dissection in the fossa of Marcille in patients with clinically localized high-risk prostate cancer: histological and molecular analyses. Prostate 2020;80 (10):795–6.
• [22] Matsumoto T, Murayama Y, Matsuo H, Okoch K, Koshiishi N, Harada Y, et al. 5-ALA-assistant automated detection of lymph node metastasis in gastric cancer patients. Gastric Cancer 2020;23:725–33.
• [23] Pak K, Kim K, Kim MH, Eom JS, Lee MK, Cho JS, et al. A decision tree model for predicting mediastinal lymph node metastasis in non-small cell lung cancer with F-18 FDG PET/ CT. PLoS ONE 2018;13(2) e0193403.
• [24] Bayanati H, Thornhill RE, Souza CA, Sethi-Virmani V, Gupta A, Maziak D, et al. Quantitative CT texture and shape analysis: can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer? Eur Radiol 2015;25(2):480–7.
• [25] Andersen MB, Harders SW, Ganeshan B, Thygesen J, Madsen HT, Rasmussen F. CT texture analysis can help differentiate between malignant and benign lymph nodes in the mediastinum in patients suspected for lung cancer. Acta Radiol 2016;57(6):669–76.
• [26] Pham TD, Watanabe Y, Higuchi M, Suzuki H. Texture Analysis and Synthesis of Malignant and Benign Mediastinal Lymph Nodes in Patients with Lung Cancer on Computed Tomography. Sci Rep 2017;7(1):1–10.
• [27] Tekchandani H, Verma S, Londhe ND. Mediastinal lymph node malignancy detection in computed tomography images using fully convolutional network. Biocybern Biomed Eng 2020;40(1):187–99.
• [28] Gao X, Ma T, Cui J, Zhang Y, Wang L, Li H, et al. A radiomicsbased model for prediction of lymph node metastasis in gastric cancer. Eur J Radiol 2020;129 109069.
• [29] Wang L, Gong J, Huang X, Lin G, Zheng B, Chen J, et al. CTbased radiomics nomogram for preoperative prediction of No. 10 lymph nodes metastasis in advanced proximal gastric cancer. Eur J Surg Oncol 2020 in press.
• [30] Mirniaharikandehei S, Heidari M, Danala G, Lakshmivarahan S, Zheng B. Applying a random projection algorithm to optimize machine learning model for predicting peritoneal metastasis in gastric cancer patients using CT images. Comput Methods Programs Biomed 2020;200(2021) 105937.
• [31] Yang L, Sun L, Liu J, Liu Q. (2019). Role of low dose 256-slice CT perfusion imaging in predicting mediastinal lymph node metastasis of lung cancer. Rev Assoc Med Bras, 65(6) (2019), pp.761-766.
• [32] Pak K, Kim K, Kim MH, Eom JS, Lee MK, Cho JS, et al. A decision tree model for predicting mediastinal lymph node metastasis in non-small cell lung cancer with F-18 FDG PET/ CT. PLoS ONE 2018;13(2) e0193403.
• [33] Yin G, Song Y, Li X, Zhu L, Su Q, Dai D, et al. Prediction of mediastinal lymph node metastasis based on 18 F-FDG PET/ CT imaging using support vector machine in non-small cell lung cancer. Eur Radiol 2021. in press.
• [34] Gao X, Chu C, Li Y, Lu P, Wang W, Liu W, et al. The method and efficacy of support vector machine classifiers based on texture features and multi-resolution histogram from 18FFDG PET-CT images for the evaluation of mediastinal lymph nodes in patients with lung cancer. Eur J Radiol 2015;84:312–7.
• [35] Zhong Y, Yuan M, Zhang T, Zhang YD, Li H, Yu TF. Radiomics approach to prediction of occult mediastinal lymph node metastasis of lung adenocarcinoma. AJR Am J Roentgenol 2018;211:109–13.
• [36] Tekchandani H, Verma S, Londhe N. Performance improvement of mediastinal lymph node severity detection using GAN and Inception network. Comput Methods Programs Biomed 2020;194 105478.
• [37] Wang H, Zhou Z, Li Y, Chen Z, Lu P, Wang W, et al. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images. EJNMMI Res 2017;7 (1):1–11.
• [38] Pham TD. Complementary features for radiomic analysis of malignant and benign mediastinal lymph nodes. In: 2017 IEEE Int Conf Image Process 2017, pp. 3849-3853.
• [39] Tekchandani H, Verma S, Londhe ND. Severity assessment of lymph nodes in CT images using deep learning paradigm. IEEE Int Conf Comput Methodol Commun 2018:686–91.
• [40] Oda H, Roth HR, Bhatia KK, Oda M, Kitasaka T, Iwano S, et al. Dense volumetric detection and segmentation of mediastinal lymph nodes in chest CT images. In Medical Imaging 2018: Comput-Aided Diagn, 10575 (2018), p. 1057502.
• [41] Zhao X, Xie P, Wang M, Li W, Pickhardt PJ, Xia W, et al. Deep learning–based fully automated detection and segmentation of lymph nodes on multiparametric-mri for rectal cancer: a multicentre study. EBioMedicine 2020;56 102780.
• [42] Gao Y, Zhang ZD, Li S, Guo YT, Wu QY, Liu SH, et al. Deep neural network-assisted computed tomography diagnosis of metastatic lymph nodes from gastric cancer. Chin Med J 2019;132(23):2804.
• [43] Barbu A, Suehling M, Xu X, Liu D, Zhou SK, Comaniciu D. Automatic detection and segmentation of lymph nodes from CT data. IEEE Trans Med Imaging 2011;31(2):240–50.
• [44] Shen C, Nguyen D, Zhou Z, Jiang SB, Dong B, Jia X. An introduction to deep learning in medical physics: advantages, potential, and challenges. Phys Med Biol 2020;65 (5):p. 05TR01.
• [45] Kuo CFJ, Huang CC, Siao JJ, Hsieh CW, Huy VQ, Ko KH, et al. Automatic lung nodule detection system using image processing techniques in computed tomography. Biomed Signal Process Control 2020;56 101659.
• [46] Chen CW, Luo J, Parker KJ. 1998. Image segmentation via adaptive K-mean clustering and knowledge-based morphological operations with biomedical applications. IEEE Trans Image Process, 7(12) (1998), pp.1673-1683.
• [47] Ahmed MN, Yamany SM, Mohamed N, Farag AA, Moriarty T. A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data. IEEE Trans Med Imag 2002;21 (3):193–9.
• [48] Li BN, Chui CK, Chang S, Ong SH. Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation. IEEE Trans. Med. Imag. 2020;41 (1):1–10.
• [49] Xu, Z., Chen, J., Wu, J., 2008. Clustering algorithm for intuitionistic fuzzy sets. Inf Sci. 178(19) (2008), pp.3775-3790.
• [50] Ko SJ, Lee TH. Center weighted median filters and their applications to image enhancement. IEEE Trans Circuits Syst 1991;38(9):984–93.
• [51] Varade RR, Dhotre MR, Pahurkar AB. A survey on various median filtering techniques for removal of impulse noise from digital images. Int J Adv Res Comput. Eng T 2013;2 (2):606–9.
• [52] Kuo CFJ, Ke BH, Wu NY, Kuo J, Hsu HH. Prognostic value of tumor volume for patients with advanced lung cancer treated with chemotherapy. Comput Meth Prog Bio 2017;144:165–77.
• [53] Kuo CFJ, Leu YS, Hu DJ, Huang CC, Siao JJ, Leon KBP. Application of intelligent automatic segmentation and 3D reconstruction of inferior turbinate and maxillary sinus from computed tomography and analyze the relationship between volume and nasal lesion. Biomed Signal Proce 2020;57(2020) 101660.
• [54] Yigit H. A weighting approach for KNN classifier. In: 2013 International conference on electronics, computer and computation (2013), pp. 228-231.
• [55] Shrivakshan GT, Chandrasekar C. A comparison of various edge detection techniques used in image processing. Int J Comput Sci 2012;9(5):269–76.
• [56] Larson MG. Analysis of variance. Circulation 2008;117:115–21. https://doi.org/10.1161/CIRCULATIONAHA.107.654335.
• [57] Glaze GM, Gross BH, Quint LE, Francis IR, Bookstein FL, Orringer MB. Normal mediastinal lymph nodes: number and size according to American Thoracic Society mapping. Am J Roentgenol 1985;144(2):261–5.
• [58] Lee CC, Lee ST, Chang CN, Pai PC, Chen YL, Hsieh TC, et al. 2011. Volumetric measurement for comparison of the accuracy between intraoperative CT and postoperative MR imaging in pituitary adenoma surgery. Am J Neuroradiol, 32 (8) (2011), pp.1539-1544.
• [59] Dang M, Modi J, Roberts M, Chan C, Mitchell JR. Validation study of a fast, accurate, and precise brain tumor volume measurement. Comput Methods Programs Biomed 2013;111 (2):480–7.
• [60] Turkbey B, Mani H, Aras O, Rastinehad AR, Shah V, Bernardo M, et al. Correlation of magnetic resonance imaging tumor volume with histopathology. J Urol 2012;188 (4):1157–63.
• [61] Haj Mohammad N, Bernards N, van Putten M, Lemmens VEPP, van Oijen MGH, van Laarhoven HWM. Volumeoutcome relation in palliative systemic treatment of metastatic oesophagogastric cancer. Eur J Cancer 2017;78:28–36.
• [62] Janssens GO, van Bockel LW, Doornaert PA, Bijl HP, van den Ende P, de Jong MA, et al. Computed tomography-based tumour volume as a predictor of outcome in laryngeal cancer: results of the phase 3 ARCON trial. Eur J Cancer 2014;50(6):1112–9.
• [63] BuganimY Rotter V. p53: balancing tumour suppression and implications for the clinic. Eur J Cancer 2009;45:217–34.
• [64] Hart PD. Receiver operating characteristic (ROC) curve analysis: A tutorial using body mass index (BMI) as a measure of obesity. J Phys Act Res 2016;1:5–8.
• [65] Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982;143(1):29–36.
• [66] Youden WJ. Index for rating diagnostic tests. Cancer 1950;3 (1):32–5.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).