CT Texture analysis and CT scores for characterization of fluid collections

被引:4
|
作者
Meyer, Hans-Jonas [1 ]
Schnarkowski, Benedikt [1 ]
Leonhardi, Jakob [1 ]
Mehdorn, Matthias [2 ]
Ebel, Sebastian [1 ]
Goessmann, Holger [1 ]
Denecke, Timm [1 ]
机构
[1] Univ Leipzig, Dept Diagnost & Intervent Radiol, Liebigstr 20, D-04103 Leipzig, Germany
[2] Univ Leipzig, Dept Visceral Transplant Thorac & Vasc Surg, Leipzig, Germany
关键词
Texture analysis; CT; Fluid collection; Drainage treatment; IMAGES;
D O I
10.1186/s12880-021-00718-w
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Background Texture analysis derived from Computed tomography (CT) might be able to better characterize fluid collections undergoing CT-guided percutaneous drainage treatment. The present study tested, whether texture analysis can reflect microbiology results in fluid collections suspicious for septic focus. Methods Overall, 320 patients with 402 fluid collections were included into this retrospective study. All fluid collections underwent CT-guided drainage treatment and were microbiologically evaluated. Clinically, serologically parameters and conventional imaging findings as well as textures features were included into the analysis. A new CT score was calculated based upon imaging features alone. Established CT scores were used as a reference standard. Results The present score achieved a sensitivity of 0.78, a specificity of 0.69, area under curve (AUC 0.82). The present score and the score by Gnannt et al. (AUC 0.81) were both statistically better than the score by Radosa et al. (AUC 0.75). Several texture features were statistically significant between infected fluid collections and sterile fluid collections, but these features were not significantly better compared with conventional imaging findings. Conclusions Texture analysis is not superior to conventional imaging findings for characterizing fluid collections. A novel score was calculated based upon imaging parameters alone with similar diagnostic accuracy compared to established scores using imaging and clinical features.
引用
收藏
页数:10
相关论文
共 50 条
  • [31] Texture-based CT Image Analysis of Asthma
    Hariharan, Harishwaran
    Wenzel, Sally
    Zheng, Bin
    Whiting, Bruce
    Pu, Jiantao
    Gur, David
    Leader, J. Ken
    MEDICAL IMAGING 2013: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING, 2013, 8672
  • [32] Texture Analysis of Brain CT Scans for ICP Prediction
    Chen, Wenan
    Smith, Rebecca
    Nabizadeh, Nooshin
    Ward, Kevin
    Cockrell, Charles
    Ha, Jonathan
    Najarian, Kayvan
    IMAGE AND SIGNAL PROCESSING, PROCEEDINGS, 2010, 6134 : 568 - 575
  • [33] Qualification of CT data for areal surface texture analysis
    Quinsat, Yann
    Guyon, Jean Baptiste
    Lartigue, Claire
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2019, 100 (9-12): : 3025 - 3035
  • [34] Observer-driven Texture Analysis in CT Imaging
    Kupinski, Matthew A.
    Garrett, Zachary
    Fan, Jiahua
    MEDICAL IMAGING 2020: IMAGE PERCEPTION, OBSERVER PERFORMANCE, AND TECHNOLOGY ASSESSMENT, 2020, 11316
  • [35] Texture analysis for vascular segmentation from CT images
    Podda, B
    Zanetti, G
    Giachetti, A
    CARS 2005: Computer Assisted Radiology and Surgery, 2005, 1281 : 206 - 211
  • [36] Qualification of CT data for areal surface texture analysis
    Yann Quinsat
    Jean Baptiste Guyon
    Claire Lartigue
    The International Journal of Advanced Manufacturing Technology, 2019, 100 : 3025 - 3035
  • [37] Improving feature extraction methods for CT texture analysis
    Giachetti, Andrea
    Melis, Cristiano
    Podda, Barbara
    PROCEEDINGS OF THE NINTH IASTED INTERNATIONAL CONFERENCE ON COMPUTER GRAPHICS AND IMAGING, 2007, : 114 - 119
  • [38] Application of texture analysis to ventilation SPECT/CT data
    Meier, Arndt
    Farrow, Catherine
    Harris, Benjamin E.
    King, Gregory G.
    Jones, Allan
    COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2011, 35 (06) : 438 - 450
  • [39] Characterization of PET/CT images using texture analysis: the past, the presenta... any future?
    Hatt, Mathieu
    Tixier, Florent
    Pierce, Larry
    Kinahan, Paul E.
    Le Rest, Catherine Cheze
    Visvikis, Dimitris
    EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2017, 44 (01) : 151 - 165
  • [40] Dual-Energy CT Texture Analysis With Machine Learning for the Evaluation and Characterization of Cervical Lymphadenopathy
    Seidler, Matthew
    Forghani, Behzad
    Reinhold, Caroline
    Perez-Lara, Almudena
    Romero-Sanchez, Griselda
    Muthukrishnan, Nikesh
    Wichmann, Julian L.
    Melki, Gabriel
    Yu, Eugene
    Forghani, Reza
    COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL, 2019, 17 : 1009 - 1015