Developing a Low Cost Image Marker to Identify Lymph Node Metastasis for Cervical Cancer Patients: An Initial Study

摘要

This study aims to utilize the primary tumor characteristics from CT images to detect lymph node (LN) metastasisfor accurately categorizing locally advanced cervical cancer patients (LACC). In clinical practice, LN metastasis is acritical indicator for patients’ prognostic assessment, which is usually investigated by PET/CT (i.e., positron emissiontomography/computed tomography) examination. However, the high cost of the PET/CT imaging modality limits itsapplication and also leads to heavy financial burden on patients. Thus it is clinically imperative to develop an economicsolution for the LN metastasis identification. For this purpose, a novel image marker was developed, which is based onthe primary cervical tumors segmented from CT images. Accordingly, a total of 99 handcrafted features were computed,and an optimal feature set was determined by Laplacian Score (LS) method. Next, a logistic regression model was appliedon the optimal feature set to generate a likelihood score for the identification of LN metastasis. Using a retrospectivedataset that contains a total of 82 LACC patients, this new model was trained and optimized by leave one out crossvalidation (LOOCV) strategy. The marker performance was assessed by receiver operator characteristic curve (ROC). Theresults indicate that the area under the ROC curve (AUC) of this identification model was 0.774±0.050, whichdemonstrates its strong discriminative power. This study may be able to provide gynecologic oncologists a CT imagebased low cost clinical marker to identify LN metastasis occurred on LACC patients.