Transfer Learning-Based Autosegmentation of Primary Tumor Volumes of Glioblastomas Using Preoperative MRI for Radiotherapy Treatment

Suqing Tian; Cuiying Wang; Ruiping Zhang; Zhuojie Dai; Lecheng Jia; Wei Zhang; Junjie Wang; Yinglong Liu

doi:10.3389/fonc.2022.856346

Transfer Learning-Based Autosegmentation of Primary Tumor Volumes of Glioblastomas Using Preoperative MRI for Radiotherapy Treatment

Front Oncol. 2022 Apr 14:12:856346. doi: 10.3389/fonc.2022.856346. eCollection 2022.

Authors

Suqing Tian¹, Cuiying Wang², Ruiping Zhang³, Zhuojie Dai⁴, Lecheng Jia⁵, Wei Zhang⁶, Junjie Wang¹, Yinglong Liu⁵

Affiliations

¹ Department of Radiation Oncology, Peking University Third Hospital, Beijing, China.
² Department of Oncology, Hainan Third People's Hospital, Sanya, China.
³ Department of Radiation Oncology, The First Hospital of Tsinghua University, Beijing, China.
⁴ United Imaging Research Institute of Intelligent Imaging, Beijing, China.
⁵ Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China.
⁶ Shanghai United Imaging Healthcare Co.Ltd., Shanghai, China.

Abstract

Objectives: Glioblastoma is the most common primary malignant brain tumor in adults and can be treated with radiation therapy. However, tumor target contouring for head radiation therapy is labor-intensive and highly dependent on the experience of the radiation oncologist. Recently, autosegmentation of the tumor target has been playing an increasingly important role in the development of radiotherapy plans. Therefore, we established a deep learning model and improved its performance in autosegmenting and contouring the primary gross tumor volume (GTV) of glioblastomas through transfer learning.

Methods: The preoperative MRI data of 20 patients with glioblastomas were collected from our department (ST) and split into a training set and testing set. We fine-tuned a deep learning model for autosegmentation of the hippocampus on separate MRI scans (RZ) through transfer learning and trained this deep learning model directly using the training set. Finally, we evaluated the performance of both trained models in autosegmenting glioblastomas using the testing set.

Results: The fine-tuned model converged within 20 epochs, compared to over 50 epochs for the model trained directly by the same training set, and demonstrated better autosegmentation performance [Dice similarity coefficient (DSC) 0.9404 ± 0.0117, 95% Hausdorff distance (95HD) 1.8107 mm ±0.3964mm, average surface distance (ASD) 0.6003 mm ±0.1287mm] than the model trained directly (DSC 0.9158±0.0178, 95HD 2.5761 mm ± 0.5365mm, ASD 0.7579 mm ± 0.1468mm) with the same test set. The DSC, 95HD, and ASD values of the two models were significantly different (P<0.05).

Conclusion: A model developed with semisupervised transfer learning and trained on independent data achieved good performance in autosegmenting glioblastoma. The autosegmented volume of glioblastomas is sufficiently accurate for radiotherapy treatment, which could have a positive impact on tumor control and patient survival.

Keywords: autosegmentation; deep learning; glioblastoma; radiotherapy treatment; transfer learning.