Interactive 3D U-net for the segmentation of the pancreas in computed tomography scans

被引:32
|
作者
Boers, T. G. W. [1 ]
Hu, Y. [2 ]
Gibson, E. [2 ]
Barratt, D. C. [2 ]
Bonmati, E. [2 ]
Krdzalic, J. [3 ]
van der Heijden, F. [1 ]
Hermans, J. J. [3 ]
Huisman, H. J. [4 ]
机构
[1] Univ Twente, Fac Sci & Technol, Enschede, Netherlands
[2] UCL, Dept Med Phys & Biomed Engn, London, England
[3] Radboud UMC, Dept Radiol & Nucl Med, Nijmegen, Netherlands
[4] Radboud UMC, Diagnost Image Anal Grp, Nijmegen, Netherlands
来源
PHYSICS IN MEDICINE AND BIOLOGY | 2020年 / 65卷 / 06期
关键词
deep learning; pancreatic cancer; interactive segmentation; U-net; IMAGE QUALITY;
D O I
10.1088/1361-6560/ab6f99
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
The increasing incidence of pancreatic cancer will make it the second deadliest cancer in 2030. Imaging based early diagnosis and image guided treatment are emerging potential solutions. Artificial intelligence (AI) can help provide and improve widespread diagnostic expertise and accurate interventional image interpretation. Accurate segmentation of the pancreas is essential to create annotated data sets to train AI, and for computer assisted interventional guidance. Automated deep learning segmentation performance in pancreas computed tomography (CT) imaging is low due to poor grey value contrast and complex anatomy. A good solution seemed a recent interactive deep learning segmentation framework for brain CT that helped strongly improve initial automated segmentation with minimal user input. This method yielded no satisfactory results for pancreas CT, possibly due to a sub-optimal neural network architecture. We hypothesize that a state-of-the-art U-net neural network architecture is better because it can produce a better initial segmentation and is likely to be extended to work in a similar interactive approach. We implemented the existing interactive method, iFCN, and developed an interactive version of U-net method we call iUnet. The iUnet is fully trained to produce the best possible initial segmentation. In interactive mode it is additionally trained on a partial set of layers on user generated scribbles. We compare initial segmentation performance of iFCN and iUnet on a 100CT dataset using dice similarity coefficient analysis. Secondly, we assessed the performance gain in interactive use with three observers on segmentation quality and time. Average automated baseline performance was 78% (iUnet) versus 72% (FCN). Manual and semi-automatic segmentation performance was: 87% in 15 min. for manual, and 86% in 8 min. for iUNet. We conclude that iUnet provides a better baseline than iFCN and can reach expert manual performance significantly faster than manual segmentation in case of pancreas CT. Our novel iUnet architecture is modality and organ agnostic and can be a potential novel solution for semi-automatic medical imaging segmentation in general.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Automated segmentation of computed tomography colonography images using a 3D U-Net
    Barr, Keiran
    Laframboise, Jacob
    Ungi, Tamas
    Hookey, Lawrence
    Fichtinger, Gabor
    MEDICAL IMAGING 2020: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING, 2021, 11315
  • [2] 3D Inception U-Net for Aorta Segmentation using Computed Tomography Cardiac Angiography
    Ravichandran, Savitha Rani
    Nataraj, Balaji
    Huang, Su
    Qin, Zhiliang
    Lu, Zhongkang
    Katsuki, Akie
    Huang, Weimin
    Zeng, Zeng
    2019 IEEE EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL & HEALTH INFORMATICS (BHI), 2019,
  • [3] 3d U-Net with ROI Segmentation of Kidneys and Masses in CT Scans
    Mitchell, Connor
    Xing, Shuwei
    Fenster, Aaron
    KIDNEY AND KIDNEY TUMOR SEGMENTATION, KITS 2023, 2024, 14540 : 93 - 96
  • [4] U-net Segmentation of Lung Cancer CT Scans for 3D Rendering
    Ismail, Hanin Monir
    McKee, Gerard T.
    2024 5TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, ROBOTICS AND CONTROL, AIRC 2024, 2024, : 35 - 40
  • [5] Applying 3D U-Net Architecture to the Task of Multi-Organ Segmentation in Computed Tomography
    Radiuk, Pavlo
    APPLIED COMPUTER SYSTEMS, 2020, 25 (01) : 43 - 50
  • [6] Brain Tumor Segmentation from 3D MRI Scans Using U-Net
    Montaha S.
    Azam S.
    Rakibul Haque Rafid A.K.M.
    Hasan M.Z.
    Karim A.
    SN Computer Science, 4 (4)
  • [7] Segmentation of bones in medical dual-energy computed tomography volumes using the 3D U-Net
    Sanchez, Jose Carlos Gonzalez
    Magnusson, Maria
    Sandborg, Michael
    Tedgren, Asa Carlsson
    Malusek, Alexandr
    PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 2020, 69 : 241 - 247
  • [8] 3D U-Net for Brain Tumour Segmentation
    Mehta, Raghav
    Arbel, Tal
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2018, PT II, 2019, 11384 : 254 - 266
  • [9] An Ensemble of 3D U-Net Based Models for Segmentation of Kidney and Masses in CT Scans
    Golts, Alex
    Khapun, Daniel
    Shats, Daniel
    Shoshan, Yoel
    Gilboa-Solomon, Flora
    KIDNEY AND KIDNEY TUMOR SEGMENTATION, KITS 2021, 2022, 13168 : 103 - 115
  • [10] Left Ventricular Myocardium Segmentation in Coronary Computed Tomography Angiography using 3D Deep Attention U-Net
    He, Xiuxiu
    Guo, Bangjun
    Lei, Yang
    Harms, Joseph
    Wang, Tonghe
    Liu, Tian
    Zhang, Longjiang
    Yang, Xiaofeng
    MEDICAL IMAGING 2020: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING, 2021, 11317