Universal detection and segmentation of lymph nodes in multi-parametric MRI

Tejas Sudharshan Mathai, Sungwon Lee, Thomas C. Shen, Daniel C. Elton, Zhiyong Lu, Ronald M. Summers

Abstract: Purpose Reliable measurement of lymph nodes (LNs) in multi-parametric MRI (mpMRI) studies of the body plays a major role in the assessment of lymphadenopathy and staging of metastatic disease. Previous approaches do not adequately exploit the complementary sequences in mpMRI to universally detect and segment lymph nodes, and they have shown fairly limited performance. Methods We propose a computer-aided detection and segmentation pipeline to leverage the T2 fat-suppressed (T2FS) and diffusion-weighted imaging (DWI) series from a mpMRI study. The T2FS and DWI series in 38 studies (38 patients) were co-registered and blended together using a selective data augmentation technique, such that traits of both series were visible in the same volume. A mask RCNN model was subsequently trained for universal detection and segmentation of 3D LNs. Results Experiments on 18 test mpMRI studies revealed that the proposed pipeline achieved a precision of $$\sim 58$$ ∼ 58 %, sensitivity of $$\sim 78$$ ∼ 78 % at 4 false positives (FP) per volume, and dice score of $$\sim 81$$ ∼ 81 %. This represented an improvement of $$\ge 12$$ ≥ 12 % in precision, $$\ge 15$$ ≥ 15 % in sensitivity at 4 FP/volume, and $$\ge 14$$ ≥ 14 % in dice score, respectively, over current approaches evaluated on the same dataset. Conclusion Our pipeline universally detected and segmented both metastatic and non-metastatic nodes in mpMRI studies. At test time, the input data used by the trained model could either be the T2FS series alone or a blend of co-registered T2FS and DWI series. Contrary to prior work, this eliminated the reliance on both the T2FS and DWI series in a mpMRI study.