딥러닝을 이용한 창상 분할 알고리즘
Development of wound segmentation deep learning algorithm
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Diagnosing wounds presents a significant challenge in clinical settings due to its complexity and the subjective assessments by clinicians. Wound deep learning algorithms quantitatively assess wounds, overcoming these challenges. However, a limitation in existing research is reliance on specific datasets. To address this limitation, we created a compre- hensive dataset by combining open dataset with self-produced dataset to enhance clinical applicability. In the annotation process, machine learning based on Gradient Vector Flow (GVF) was utilized to improve objectivity and efficiency over time. Furthermore, the deep learning model was equipped U-net with residual blocks. Significant improvements were observed using the input dataset with images cropped to contain only the wound region of interest (ROI), as opposed to original sized dataset. As a result, the Dice score remarkably increased from 0.80 using the original dataset to 0.89 using the wound ROI crop dataset. This study highlights the need for diverse research using comprehensive datasets. In future study, we aim to further enhance and diversify our dataset to encompass different environments and ethnicities.
Abstract
Diagnosing wounds presents a significant challenge in clinical settings due to its complexity and the subjective assessments by clinicians. Wound deep learning algorithms quantitatively assess wounds, overcoming these challenges. However, a limitation in existing research is reliance on specific datasets. To address this limitation, we created a compre- hensive dataset by combining open dataset with self-produced dataset to enhance clinical applicability. In the annotation process, machine learning based on Gradient Vector Flow (GVF) was utilized to improve objectivity and efficiency over time. Furthermore, the deep learning model was equipped U-net with residual blocks. Significant improvements were observed using the input dataset with images cropped to contain only the wound region of interest (ROI), as opposed to original sized dataset. As a result, the Dice score remarkably increased from 0.80 using the original dataset to 0.89 using the wound ROI crop dataset. This study highlights the need for diverse research using comprehensive datasets. In future study, we aim to further enhance and diversify our dataset to encompass different environments and ethnicities.
참고문헌 (14)
- Sen CK, "Human skin wounds : a major and snowballing threat to public health and the economy", Wound Repair Regen, 17(6), pp.763~771 (2009)
- Marijanovic D, "A Systematic Overview of Recent Methods for Non-Contact Chronic Wound Analysis", Appl Sci Basel, 10(21) (2020)
- Gurkan A, "Pressure injuries in surgical patients : a comparison of Norton, Braden and Waterlow risk assessment scales", J Wound Care, 31(2), pp.170~177 (2022)
- Khoo R, "The Evolving Field of Wound Measurement Techniques : A Literature Review", Wounds, 28(6), pp.175~181 (2016)
- Shah A, "Wound Measurement Techniques : Comparing the Use of Ruler Method, 2D Imaging and 3D Scanner", J Am Coll Clin Wound Spec, 5(3), pp.52~57 (2013)
- Lu H, "Wound intensity correction and segmentation with convolutional neural networks", Concurr Comput Pract Exp, 29(6) (2017)
- Wang C, "A unified framework for automatic wound segmentation and analysis with deep convolutional neural networks", Annu Int Conf IEEE Eng Med Biol Soc, 2015, pp.2415~2418 (2015)
- Scebba G, "Detect-and-segment : A deep learning approach to automate wound image segmentation", Inform Med Unlock, 29, pp.100884~ (2022)
- Xu T, "Gradient vector flow based active shape model for lung field segmentation in chest radiographs", Annu Int Conf IEEE Eng Med Biol Soc, 2009, pp.3561~3564 (2009)
- Yang SJ, "Sequential change of wound calculated by image analsis using a color patch method during a secondary intention healing", PLoS One, 11(9), pp.e0163092~ (2016)
- Xanthopoulos P, "Robust data mining" (2012), Springer Science & Business Media
- Cho IH, "Preprocessing effect by using k-means clustering and merging algorithms in MR cardiac left ventricle segmentation", J Biomed Eng Res, pp.24~ (2003)
- Ronneberger O, "U-net: Convolutional networks for biomedical image segmentation", Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference (2015), Springer International Publishing
- Koonce B, "Convolutional Neural Networks with Swift for TensorFlow: Image Recognition and Dataset Categorization", pp.63~72 (2021)