A Deep Learning Based Automatic Segmentation Approach For Anatomical Structures In Intensity Modulation Radiotherapy

Objective: To evaluate the automatic segmentation approach for organ at risk (OARs) and compare the parameters of dose volume histogram (DVH) in radiotherapy. Methodology: Thirty-three patients were selected to contour OARs using automatic segmentation approach which based on U Net, applying them to a number of the nasopharyngeal carcinoma (NPC), breast, and rectal cancer respectively. The automatic contours were transferred to the Pinnacle System to evaluate contour accuracy and compare the DVH parameters. Results: The time for manual contour was 56.5 +/- 9, 23.12 +/- 4.23 and 45.23 +/- 2.39min for the OARs of NPC, breast and rectal cancer, and for automatic contour was 1.5 +/- 0.23, 1.45 +/- 0.78 and 1.8 +/- 0.56 min. Automatic contours of Eye with the best Dice-similarity coefficients (DSC) of 0.907 +/- 0.02 while with the poorest DSC of 0.459 +/- 0.112 of Spinal Cord for NPC; And Lung with the best DSC of 0.944 +/- 0.03 while with the poorest DSC of 0.709 +/- 0.1 of Spinal Cord for breast; And Bladder with the best DSC of 0.91 +/- 0.04 while with the poorest DSC of 0.43 +/- 0.1 of Femoral heads for rectal cancer. The contours of Spinal Cord in H&N had poor results due to the division of the medulla oblongata. The contours of Femoral head, which different from what we expect, also due to manual contour result in poor DSC. Conclusion: The automatic contour approach based deep learning method with sufficient accuracy for research purposes. However, the value of DSC does not fully reflect the accuracy of dose distribution, but can cause dose changes due to the changes in the OARs volume and DSC from the data. Considering the significantly time-saving and good performance in partial OARs, the automatic contouring also plays a supervisory role.