Xuxin Chen1, Wei Liu2, Theresa C Thai3, Tara Castellano4, Camille C Gunderson4, Kathleen Moore4, Robert S Mannel4, Hong Liu1, Bin Zheng1, Yuchen Qiu5. 1. School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA. 2. School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an, 710021, China; School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA. 3. Department of Radiology, University of Oklahoma Health Sciences Center, Oklahoma City, OK, 73104, USA. 4. Department of Obstetrics and Gynecology, University of Oklahoma Health Sciences Center, Oklahoma City, OK, 73104, USA. 5. School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA. Electronic address: QIUYUCHEN@OU.EDU.
Abstract
BACKGROUND AND OBJECTIVE: In diagnosis of cervical cancer patients, lymph node (LN) metastasis is a highly important indicator for the following treatment management. Although CT/PET (i.e., computed tomography/positron emission tomography) examination is the most effective approach for this detection, it is limited by the high cost and low accessibility, especially for the rural areas in the U.S.A. or other developing countries. To address this challenge, this investigation aims to develop and test a novel radiomics-based CT image marker to detect lymph node metastasis for cervical cancer patients. METHODS: A total of 1,763 radiomics features were first computed from the segmented primary cervical tumor depicted on one CT image with the maximal tumor region. Next, a principal component analysis algorithm was applied on the initial feature pool to determine an optimal feature cluster. Then, based on this optimal cluster, the prediction models (i.e., logistic regression or support vector machine) were trained and optimized to generate an image marker to detect LN metastasis. In this study, a retrospective dataset containing 127 cervical cancer patients were established to build and test the model. The model was trained using a leave-one-case-out (LOCO) cross-validation strategy and image marker performance was evaluated using the area under receiver operation characteristic (ROC) curve (AUC). RESULTS: The results indicate that the SVM based imaging marker achieved an AUC value of 0.841 ± 0.035. When setting an operating threshold of 0.5 on model-generated prediction scores, the imaging marker yielded a positive and negative predictive value (PPV and NPV) of 0.762 and 0.765 respectively, while the total accuracy is 76.4%. CONCLUSIONS: This study initially verified the feasibility of utilizing CT image and radiomics technology to develop a low-cost image marker to detect LN metastasis for assisting stratification of cervical cancer patients.
BACKGROUND AND OBJECTIVE: In diagnosis of cervical cancerpatients, lymph node (LN) metastasis is a highly important indicator for the following treatment management. Although CT/PET (i.e., computed tomography/positron emission tomography) examination is the most effective approach for this detection, it is limited by the high cost and low accessibility, especially for the rural areas in the U.S.A. or other developing countries. To address this challenge, this investigation aims to develop and test a novel radiomics-based CT image marker to detect lymph node metastasis for cervical cancerpatients. METHODS: A total of 1,763 radiomics features were first computed from the segmented primary cervical tumor depicted on one CT image with the maximal tumor region. Next, a principal component analysis algorithm was applied on the initial feature pool to determine an optimal feature cluster. Then, based on this optimal cluster, the prediction models (i.e., logistic regression or support vector machine) were trained and optimized to generate an image marker to detect LN metastasis. In this study, a retrospective dataset containing 127 cervical cancerpatients were established to build and test the model. The model was trained using a leave-one-case-out (LOCO) cross-validation strategy and image marker performance was evaluated using the area under receiver operation characteristic (ROC) curve (AUC). RESULTS: The results indicate that the SVM based imaging marker achieved an AUC value of 0.841 ± 0.035. When setting an operating threshold of 0.5 on model-generated prediction scores, the imaging marker yielded a positive and negative predictive value (PPV and NPV) of 0.762 and 0.765 respectively, while the total accuracy is 76.4%. CONCLUSIONS: This study initially verified the feasibility of utilizing CT image and radiomics technology to develop a low-cost image marker to detect LN metastasis for assisting stratification of cervical cancerpatients.
Authors: Haruka Itakura; Achal S Achrol; Lex A Mitchell; Joshua J Loya; Tiffany Liu; Erick M Westbroek; Abdullah H Feroze; Scott Rodriguez; Sebastian Echegaray; Tej D Azad; Kristen W Yeom; Sandy Napel; Daniel L Rubin; Steven D Chang; Griffith R Harsh; Olivier Gevaert Journal: Sci Transl Med Date: 2015-09-02 Impact factor: 17.956
Authors: Hugo J W L Aerts; Emmanuel Rios Velazquez; Ralph T H Leijenaar; Chintan Parmar; Patrick Grossmann; Sara Carvalho; Sara Cavalho; Johan Bussink; René Monshouwer; Benjamin Haibe-Kains; Derek Rietveld; Frank Hoebers; Michelle M Rietbergen; C René Leemans; Andre Dekker; John Quackenbush; Robert J Gillies; Philippe Lambin Journal: Nat Commun Date: 2014-06-03 Impact factor: 14.919
Authors: Meijun Du; Karthik V Giridhar; Yijun Tian; Michael R Tschannen; Jing Zhu; Chiang-Ching Huang; Deepak Kilari; Manish Kohli; Liang Wang Journal: Oncotarget Date: 2017-07-22