방사선종양학

본문글자크기
  • [Clin Oncol (R Coll Radiol).] A New Approach to Quantify and Grade Radiation Dermatitis Using Deep-Learning Segmentation in Skin Photographs

    [Clin Oncol (R Coll Radiol).] A New Approach to Quantify and Grade Radiation Dermatitis Using Deep-Learning Segmentation in Skin Photographs

    연세의대 / 박예인, 홍채선*, 김진성*

  • 출처
    Clin Oncol (R Coll Radiol).
  • 등재일
    2022 Jul 30
  • 저널이슈번호
    S0936-6555(22)00313-2. doi: 10.1016/j.clon.2022.07.001.
  • 내용

    바로가기  >

    Abstract
    Aims: Objective evaluation of radiation dermatitis is important for analysing the correlation between the severity of radiation dermatitis and dose distribution in clinical practice and for reliable reporting in clinical trials. We developed a novel radiation dermatitis segmentation system based on convolutional neural networks (CNNs) to consistently evaluate radiation dermatitis.

    Materials and methods: The radiation dermatitis segmentation system is designed to segment the radiation dermatitis occurrence area using skin photographs and skin-dose distribution. A CNN architecture with a dilated convolution layer and skip connection was designed to estimate the radiation dermatitis area. Seventy-three skin photographs obtained from patients undergoing radiotherapy were collected for training and testing. The ground truth of radiation dermatitis segmentation is manually delineated from the skin photograph by an experienced radiation oncologist and medical physicist. We converted the skin photographs to RGB (red-green-blue) and CIELAB (lightness (L∗), red-green (a∗) and blue-yellow (b∗)) colour information and trained the network to segment faint and severe radiation dermatitis using three different input combinations: RGB, RGB + CIELAB (RGBLAB) and RGB + CIELAB + skin-dose distribution (RGBLAB_D). The proposed system was evaluated using the Dice similarity coefficient (DSC), sensitivity, specificity and normalised Matthews correlation coefficient (nMCC). A paired t-test was used to compare the results of different segmentation performances.

    Results: Optimal data composition was observed in the network trained for radiation dermatitis segmentation using skin photographs and skin-dose distribution. The average DSC, sensitivity, specificity and nMCC values of RGBLAB_D were 0.62, 0.61, 0.91 and 0.77, respectively, in faint radiation dermatitis, and 0.69, 0.78, 0.96 and 0.83, respectively, in severe radiation dermatitis.

    Conclusion: Our study showed that CNN-based radiation dermatitis segmentation in skin photographs of patients undergoing radiotherapy can describe radiation dermatitis severity and pattern. Our study could aid in objectifying the radiation dermatitis grading and analysing the reliable correlation between dosimetric factors and the morphology of radiation dermatitis.

     

     

    Affiliations

    Y I Park  1 , S H Choi  2 , C-S Hong  3 , M-S Cho  4 , J Son  4 , M C Han  5 , J Kim  5 , H Kim  5 , D W Kim  5 , J S Kim  6
    1 Department of Radiation Oncology, Yonsei University College of Medicine, Seoul, South Korea; Medical Physics and Biomedical Engineering Lab (MPBEL), Yonsei University College of Medicine, Seoul, South Korea.
    2 Department of Radiation Oncology, Yonsei University College of Medicine, Seoul, South Korea; Department of Radiation Oncology, Yongin Severance Hospital, Yongin, South Korea.
    3 Department of Radiation Oncology, Yonsei University College of Medicine, Seoul, South Korea. Electronic address: cs.hong@yuhs.ac.
    4 Department of Radiation Oncology, Yongin Severance Hospital, Yongin, South Korea.
    5 Department of Radiation Oncology, Yonsei University College of Medicine, Seoul, South Korea.
    6 Department of Radiation Oncology, Yonsei University College of Medicine, Seoul, South Korea; Medical Physics and Biomedical Engineering Lab (MPBEL), Yonsei University College of Medicine, Seoul, South Korea. Electronic address: JINSUNG@yuhs.ac.

  • 키워드
    Convolutional neural networks; dermatitis grading scale; radiation dermatitis; radiation therapy; skin toxicity; skin-dose distribution.
  • 연구소개
    방사선 피부염의 객관적이고 신뢰할 수 있는 평가를 위해 CNN (Convolutional Neural Networks)을 기반으로 새로운 방사선 피부염 세분화 시스템을 개발했습니다. 이 연구는 방사선 치료를 받는 환자의 피부 사진에서 CNN 기반 방사선 피부염 세분화가 방사선 피부염 심각성 및 패턴을 설명할 수 있음을 보여주었습니다. 우리의 연구는 방사선 피부염 등급을 객관화하고 선량 측정 인자와 방사선 피부염의 형태 사이의 신뢰할 수 있는 상관관계를 분석하는 데 도움이 될 수 있습니다.
  • 편집위원

    인공지능을 이용하여 방사선 피부염의 정도와 분포양상을 객관적으로 평가할 수 있음을 제시함

    2022-08-25 13:49:30

  • 덧글달기
    덧글달기
       IP : 18.232.127.73

    등록