MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

A Deep Learning-Based Tumor Auto-Contouring Algorithm for Real-Time Tumor Tracking Using Linac-MR

J Yun1*, E Yip2 , Z Gabos3 , S Baker4 , D Yee5 , K Wachowicz6 , S Rathee7 , B G Fallone8 , (1),(2),(6),(7),(8) Department of Medical Physics, Cross Cancer Institute, Edmonton, AB, (3),(5) Department of Radiation Oncology, Cross Cancer Institute, Edmonton, AB, (4) Department of Radiation Oncology, Erasmus MC Cancer Institute, Rotterdam, EA

Presentations

(Thursday, 8/2/2018) 7:30 AM - 9:30 AM

Room: Karl Dean Ballroom B1

Purpose: To develop and evaluate a deep learning-based tumor auto-contouring algorithm for real-time tumor tracking using linac-MR.

Methods: We modified and implemented a specific kind of neural network known as U-net in our auto-contouring algorithm, which was responsible for tumor segmentation from its surrounding anatomy. U-net was chosen due to its ideal network structure capable of combining low resolution context information and high resolution details of the input image in pixel-wise classification. Six non-small cell lung cancer patients were imaged with 3T MRI at ~4 frames per second (2D sagittal plane, free breathing). For each patient, an expert delineated gold standard contours (ROI_std) of the lung tumor in 130 consecutive images. ROI_std were delineated on 3T images. However, to evaluate our algorithm in the 0.5T linac-MR environment, the 3T-acquired images were noise-degraded to reflect the worst-case image quality of lung tumor at 0.5T. For each patient, the first 30 ROI_std were used for algorithm training, and the remaining 100 ROI_std were used for auto-contouring validation. Once trained, our algorithm was applied to segment tumors from the remaining 100 pseudo-0.5T images, generating 100 ROI_auto per patient. In each image, the dice similarity index (DSI), Hausdorff distance (HD), and centroid position difference (Δd_centroid) were calculated between ROI_std and ROI_auto to measure their similarity.

Results: We achieved 87 – 92% DSI, 2.4 – 3.9mm HD, and 0.9 – 1.5mm Δd_centroid from six patients' data. Our algorithm successfully segmented the shape of moving tumors that exhibit significant shape changes during breathing (e.g., partial omission of tumor), and/or are surrounded by challenging anatomy (e.g., diffuse boundary between tumor and adjacent tissue).

Conclusion: We developed a deep learning-based tumor auto-contouring algorithm, and evaluated its performance with in-vivo MR images. Our algorithm showed promising results (>87% DSI) suggesting the feasibility of auto-contouring moving tumors on MR images.

Keywords

MRI, Image-guided Therapy, Radiation Therapy

Taxonomy

IM/TH- MRI in Radiation Therapy: MRI/Linear accelerator combined- IGRT and tracking

Contact Email