Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography

Abstract

Approximately 25% of the patients with muscle-invasive bladder cancer (MIBC) who are clinically node negative have occult lymph node metastases at radical cystectomy (RC) and pelvic lymph node dissection. The aim of this study was to evaluate preoperative CT-based radiomics to differentiate between pN+ and pN0 disease in patients with clinical stage cT2-T4aN0-N1M0 MIBC. Patients with cT2-T4aN0-N1M0 MIBC, of whom preoperative CT scans and pathology reports were available, were included from the prospective, multicenter CirGuidance trial. After manual segmentation of the lymph nodes, 564 radiomics features were extracted. A combination of different machine-learning methods was used to develop various decision models to differentiate between patients with pN+ and pN0 disease. A total of 209 patients (159 pN0; 50 pN+) were included, with a total of 3153 segmented lymph nodes. None of the individual radiomics features showed significant differences between pN+ and pN0 disease, and none of the radiomics models performed substantially better than random guessing. Hence, CT-based radiomics does not contribute to differentiation between pN+ and pN0 disease in patients with cT2-T4aN0-N1M0 MIBC.

Keywords: bladder cancer; computed tomography; machine learning; radiomics.

Figure 1

A schematic overview of the radiomics approach]. Inputs to the analyses were computed tomography (CT) of abdomen or CT urogram and corresponding segmentations of the lymph nodes (1). From these segmentations, 564 features quantifying intensity, shape and texture were extracted (2). A decision model was created (4) using the 100 best performing models (3) of 1000 candidate models. Adapted from Vos et al. [39]: the images under (1), texture features, numbers at (3), and output at (4) have been modified with respect to the original figure.

Figure 2

Flowchart of patients included in our post hoc analysis of the CirGuidance trial [33]. Reasons for exclusion were: lost to follow-up (n = 5), revoked permission to participate (n = 7), no cystectomy (n = 13), corrupted DICOM data (n = 13), aborted cystectomy (n = 5), CT-thorax provided (n = 5) or non-contrast scan (n = 2). In the end, 209 patients were included in this study.

Figure 3

Randomly selected example segmentations on computed tomography scans of four patients with muscle-invasive bladder cancer scheduled for radical cystectomy and pelvic lymph node dissection. Top row: segmentations of pelvic lymph nodes in four patients without (pN0) (A,B) and with (pN+) (C,D) nodal metastases at pelvic dissection. Bottom row: corresponding segmentations of the largest 2D axial cross-sectional area of the primary tumor (E–H).

Figure 4

Number of segmentations per patient in patients with pN0 (gray) or pN+ (blue) muscle-invasive bladder cancer.

Figure 5

Receiver operating characteristic curves of the radiomics models in the testing datasets based on: (1a) all lymph nodes—features combined over all nodes; (1b) all lymph nodes—mean of features per lymph node; (2a) lymph nodes > 15 mm—features combined over all nodes; (2b) lymph nodes > 15 mm—features combined over all nodes; (3a) largest five lymph nodes—features combined over all nodes; (3b) largest five lymph nodes—features combined over all nodes; and (4) features extracted from the largest 2D cross-sectional area of the primary tumor. The curves represent the mean of the 100× random-split cross-validations; for Model 1a, 95% confidence intervals are represented by the crosses.