A convolutional neural network for contouring metastatic lymph nodes on diffusion-weighted magnetic resonance images for assessment of radiotherapy response

Abstract

Background and purpose: Retrieving quantitative parameters from magnetic resonance imaging (MRI), e.g. for early assessment of radiotherapy treatment response, necessitates contouring regions of interest, which is timeconsuming and prone to errors. This becomes more pressing for daily imaging on MRI-guided radiotherapy systems. Therefore, we trained a deep convolutional neural network to automatically contour involved lymph nodes on diffusion-weighted (DW) MRI of head and neck cancer (HNC) patients receiving radiotherapy. Materials and methods: DW-images from 48 HNC patients (18 induction-chemotherapy + chemoradiotherapy; 30 definitive chemoradiotherapy) with 68 involved lymph nodes were obtained on a diagnostic 1.5 T MRscanner prior to and 2-3 timepoints throughout treatment. A radiation oncologist delineated the lymph nodes on the b = 50 s/mm 2 images. A 3D U-net was trained to contour involved lymph nodes. Its performance was evaluated in all 48 patients using 8-fold cross-validation and calculating the Dice similarity coefficient (DSC) and the absolute difference in median apparent diffusion coefficient (ΔADC) between the manual and generated contours. Additionally, the performance was evaluated in an independent dataset of three patients obtained on a 1.5 T MR-Linac. Results: In the definitive chemoradiotherapy patients (n = 96 patients/lymphnodes/timepoints) the DSC was 0.87 (0.81-0.91) [median (1st-3rd quantiles)] and ΔADC was 1.9% (0.8-3.4%) and both remained stable throughout treatment. The network performed worse in the patients receiving induction-chemotherapy (n = 65), with DSC = 0.80 (0.71-0.87) and ΔADC = 3.3% (1.6-8.0%). The network performed well on the MR-Linac data (n = 8) with DSC = 0.80 (0.75-0.82) and ΔADC = 4.0% (0.6-9.1%). Conclusions: We established accurate automatic contouring of involved lymph nodes for HNC patients on diagnostic and MR-Linac DW-images.

Artificial Intelligence in magnetic Resonance guided Radiotherapy: Medical and physical considerations on state of art and future perspectives

“…As regards the head and neck region, Gurney-Champion et al trained a 3D U-net on DW 1.5 T MR images from 51 head and neck patients to automatically delineate lymph-node chains. Fast (55 ms) and accurate (within inter-observer variability) results were observed considering DW-images acquired using a diagnostic scanner and an MR-Linac [100].…”

Quantitative magnetic resonance imaging on hybrid magnetic resonance linear accelerators: Perspective on technical and clinical validation

“…Functional magnetic resonance imaging (MRI) has been shown in a number of recent studies to provide not only beneficial information for target volume delineation [1] , [2] , but more importantly also prognostic information with respect to outcome after radiotherapy (RT) [3] , [4] . In terms of quantitative MRI techniques in a clinical context, so far mainly diffusion weighted imaging (DWI) and dynamic contrast enhanced (DCE) MRI have been used to predict RT response [5] , [6] .…”

Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning

“…Supervised ML algorithms use training data with known input (predictors) and output (responses) values, to detect patterns and correlation through the learning process [7] , which can then be used to predict whether investigator contours “pass” or “fail” pre-trial outlining exercises. Whilst several studies have investigated the use of AI for auto-segmentation contouring in radiotherapy planning [8] , [9] , [10] , the use of ML to assess TV and OAR contour conformity is limited.…”