방사선종양학

본문글자크기
  • [Cancers (Basel).] Deep-Learning-Based Automatic Detection and Segmentation of Brain Metastases with Small Volume for Stereotactic Ablative Radiotherapy

    [Cancers (Basel).] Deep-Learning-Based Automatic Detection and Segmentation of Brain Metastases with Small Volume for Stereotactic Ablative Radiotherapy

    연세의대 / 유상균, 김태형, 윤홍인*, 김진성*

  • 출처
    Cancers (Basel).
  • 등재일
    2022 May 23
  • 저널이슈번호
    14(10):2555. doi: 10.3390/cancers14102555.
  • 내용

    바로가기  >

    Abstract
    Recently, several efforts have been made to develop the deep learning (DL) algorithms for automatic detection and segmentation of brain metastases (BM). In this study, we developed an advanced DL model to BM detection and segmentation, especially for small-volume BM. From the institutional cancer registry, contrast-enhanced magnetic resonance images of 65 patients and 603 BM were collected to train and evaluate our DL model. Of the 65 patients, 12 patients with 58 BM were assigned to test-set for performance evaluation. Ground-truth for BM was assigned to one radiation oncologist to manually delineate BM and another one to cross-check. Unlike other previous studies, our study dealt with relatively small BM, so the area occupied by the BM in the high-resolution images were small. Our study applied training techniques such as the overlapping patch technique and 2.5-dimensional (2.5D) training to the well-known U-Net architecture to learn better in smaller BM. As a DL architecture, 2D U-Net was utilized by 2.5D training. For better efficacy and accuracy of a two-dimensional U-Net, we applied effective preprocessing include 2.5D overlapping patch technique. The sensitivity and average false positive rate were measured as detection performance, and their values were 97% and 1.25 per patient, respectively. The dice coefficient with dilation and 95% Hausdorff distance were measured as segmentation performance, and their values were 75% and 2.057 mm, respectively. Our DL model can detect and segment BM with small volume with good performance. Our model provides considerable benefit for clinicians with automatic detection and segmentation of BM for stereotactic ablative radiotherapy.

     

     

     

    Affiliations

    Sang Kyun Yoo  1   2 , Tae Hyung Kim  1   3 , Jaehee Chun  1   2   4 , Byong Su Choi  1   2 , Hojin Kim  1 , Sejung Yang  5 , Hong In Yoon  1 , Jin Sung Kim  1   2   4
    1 Department of Radiation Oncology, Yonsei Cancer Center, Yonsei University College of Medicine, Seoul 03722, Korea.
    2 Medical Physics and Biomedical Engineering Lab (MPBEL), Yonsei University College of Medicine, Seoul 03722, Korea.
    3 Department of Radiation Oncology, Nowon Eulji Medical Center, Eulji University College of Medicine, Seoul 01830, Korea.
    4 Oncosoft Inc., Seoul 03787, Korea.
    5 Department of Biomedical Engineering, Yonsei University, Wonju 26493, Korea.

  • 키워드
    autosegmentation; brain metastases; convolutional neural network; deep learning; magnetic resonance imaging; stereotactic ablative radiotherapy.
  • 연구소개
    방사선치료 기술이 발전됨에 따라 뇌 전이 치료에 있어 체부정위적 방사선치료(SABR)의 사용이 증가하고 있습니다. 하지만 부피가 작은 뇌 전이의 경우, 이를 발견하고 방사선치료를 위해 구획화하는 것은 상당한 노력이 필요합니다. 본 연구에서는 딥러닝을 이용하여, 뇌 전이를 자동으로 발견하고 구획화하는 모델을 개발하였습니다. 많이 알려져 있는 U-Net 에 Overlapping patch 기술과 2.5D 학습을 추가하여 작은 부피의 뇌 전이를 발견하기 위해 노력하였습니다. 총 65명의 환자의 603개의 뇌 전이를 대상으로 하였고, 이 중 부피가 0.04 cc 이하의 뇌 전이는 24%를 차지하였습니다. 뇌 전이 발견 성능은 민감도(sensitivity) 97%, 위양성은 환자당 1.25개였습니다. 구획화 성능의 경우는 Dice coefficient with dilation 이 75%, 95% Hausdorff distance 가 2mm 로 상당히 우수하였습니다. 본 연구결과는 작은 부피의 뇌 전이를, 인공지능을 이용하여 자동으로 발견하고 구획화가 가능함을 보여준 연구로, 방사선종양학과 의사에게 상당한 도움이 될 것으로 생각합니다.
  • 덧글달기
    덧글달기
       IP : 3.237.232.196

    등록