Correction for Magnetic Field Inhomogeneities and Normalization of Voxel Values Are Needed to Better Reveal the Potential of MR Radiomic Features in Lung Cancer

Abstract

Purpose: To design and validate a preprocessing procedure dedicated to T2-weighted MR images of lung cancers so as to improve the ability of radiomic features to distinguish between adenocarcinoma and other histological types. Materials and Methods: A discovery set of 52 patients with advanced lung cancer who underwent T2-weighted MR imaging at 3 Tesla in a single center study from August 2017 to May 2019 was used. Findings were then validated using a validation set of 19 additional patients included from May to October 2019. Tumor type was obtained from the pathology report after trans-thoracic needle biopsy, metastatic lymph node or metastasis samples, or surgical excisions. MR images were preprocessed using N4ITK bias field correction and by normalizing voxel intensities with fat as a reference region. Segmentation and extraction of radiomic features were performed with LIFEx software on the raw images, on the N4ITK-corrected images and on the fully preprocessed images. Two analyses were conducted where radiomic features were extracted: (1) from the whole tumor volume (3D analysis); (2) from all slices encompassing the tumor (2D analysis). Receiver operating characteristic (ROC) analysis was used to identify features that could distinguish between adenocarcinoma and other histological types. Sham experiments were also designed to control the number of false positive findings. Results: There were 31 (12) adenocarcinomas and 21 (7) other histological types in the discovery (validation) set. In 2D, preprocessing increased the number of discriminant radiomic features from 8 without preprocessing to 22 with preprocessing. 2D analysis yielded more features able to identify adenocarcinoma than 3D analysis (12 discriminant radiomic features after preprocessing in 3D). Preprocessing did not increase false positive findings as no discriminant features were identified in any of the sham experiments. The greatest sensitivity of the 2D analysis applied to preprocessed data was confirmed in the validation set. Conclusion: Correction for magnetic field inhomogeneities and normalization of voxel values are essential to reveal the full potential of radiomic features to identify the tumor histological type from MR T2-weighted images, with classification performance similar to those reported in PET/CT and in multiphase CT in lung cancers.

Keywords: MRI normalization; T2-weighted MR images; bias field correction; histological types of lung cancer; lung cancer; radiomics.

Figure 1

Data selection pipelines.

Figure 2

Example of ROI positioning for three candidate reference tissues: subcutaneous fat in red color, vertebral body in green color, pectoral muscle in blue color.

Figure 3

Bias field as estimated using the N4ITK algorithm. The bias field is displayed in color and superimposed to the image in gray scale.

Figure 4

Example of tumor segmentation for two patients. First row: patient with a lung adenocarcinoma of the right lower lobe (long axis: 77 mm). Raw image (A) and image after N4ITK correction with the segmented tumor volume in pink (B). Second row: patient with a squamous cell carcinoma of the left upper lobe (long axis: 93 mm). Raw image (C) and image after N4ITK correction with the segmented tumor volume in pink (D).

Figure 5

Boxplot showing the values of the 2D “GLCM-correlation” feature for the group of patients with adenocarcinomas (ADK) and the group of patients having a different histological status (OTH).