A deep learning framework for prostate localization in cone beam CT-guided radiotherapy.

PURPOSE: To develop a deep learning-based model for prostate planning target volume (PTV) localization on cone beam computed tomography (CBCT) to improve the workflow of CBCT-guided patient setup. METHODS: A two-step task-based residual network (T(2) RN) is proposed to automatically identify inherent landmarks in prostate PTV. The input to the T(2) RN is the pretreatment CBCT images of the patient, and the output is the deep learning-identified landmarks in the PTV. To ensure robust PTV localization, the T(2) RN model is trained by using over thousand sets of CT images with labeled landmarks, each of the CTs corresponds to a different scenario of patient position and/or anatomy distribution generated by synthetically changing the planning CT (pCT) image. The changes, including translation, rotation, and deformation, represent vast possible clinical situations of anatomy variations during a course of radiation therapy (RT). The trained patient-specific T(2) RN model is tested by using 240 CBCTs from six patients. The testing CBCTs consists of 120 original CBCTs and 120 synthetic CBCTs. The synthetic CBCTs are generated by applying rotation/translation transformations to each of the original CBCT. RESULTS: The systematic/random setup errors between the model prediction and the reference are found to be <0.25/2.46 mm and 0.14/1.41° in translation and rotation dimensions, respectively. Pearson's correlation coefficient between model prediction and the reference is higher than 0.94 in translation and rotation dimensions. The Bland-Altman plots show good agreement between the two techniques. CONCLUSIONS: A novel T(2) RN deep learning technique is established to localize the prostate PTV for RT patient setup. Our results show that highly accurate marker-less prostate setup is achievable by leveraging the state-of-the-art deep learning strategy.