• Zhonghua yi xue za zhi · Dec 2020

    [The value of conventional magnetic resonance imaging based radiomic model in predicting the texture of pituitary macroadenoma].

    • J M Chen, Q Wan, H Y Zhu, Y Q Ge, L L Wu, J Zhai, and Z M Ding.
    • Medical Imaging Central, Yijishan Hospital of Wannan Medical College, Wuhu 241001, China.
    • Zhonghua Yi Xue Za Zhi. 2020 Dec 8; 100 (45): 3626-3631.

    AbstractObjective: To investigate the value of conventional magnetic resonance imaging (MRI) based radiomic model in predicting the texture of pituitary macroadenoma. Methods: The complete data of 101 patients with pituitary macroadenoma confirmed by surgery and pathology in Yijishan Hospital of Wannan Medical College from December 2014 to December 2019 were retrospectively analyzed. According to the texture of the intraoperative pituitary tumor, patients were divided into soft group (n=58) and hard group (n=43). They were randomly divided into training group (n=72) and validation group (n=29) at a ratio of 7∶3. All patients underwent conventional MRI scan of the pituitary gland. Itk-snap software was used to manually outline the T(1)-weighted image (T(1)WI), T(2)-weighted image (T(2)WI) and enhanced T(1)WI image section by section on tumor area of interest (ROI) and perform three-dimensional fusion. Then AK software was imported to extract texture features. The regression analysis methods of minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) were used for feature selection and radiomic signature establishment. The reliability of the model was verified by 100 leave-group-out cross validation (LGOCV), and the predictive ability of the model was evaluated by drawing the receiver operating characteristic (ROC) curve. The decision curve analysis (DCA) was used to evaluate the clinical application value of the model. Results: The AUC (Area Under the ROC Curve) (95%CI) values of T1WI, T2WI, enhanced T1WI, and the combined sequence model to predict the texture of pituitary macroadenomas in the training and validation groups were 0.91 (0.84-0.98) and 0.90 (0.78-1.00), 0.86 (0.78-0.95) and 0.83 (0.64-1.00), 0.90 (0.83-0.97) and 0.89 (0.77-1.00),0.92 (0.85-0.98) and 0.91 (0.79-1.00), respectively. DCA demonstrated that T(1)WI, T(2)WI, enhanced T(1)WI, and combined sequence model all had good net benefits in clinical practice. Conclusions: T(1)WI, T(2)WI, enhanced T(1)WI, and combined sequence model of conventional MRI all had high efficacy in predicting the texture of pituitary macroadenoma, which provided a new quantitative method for predicting the texture of pituitary macroadenoma.

      Pubmed     Copy Citation     Plaintext  

      Add institutional full text...

    Notes

     
    Knowledge, pearl, summary or comment to share?
    300 characters remaining
    help        
    You can also include formatting, links, images and footnotes in your notes
    • Simple formatting can be added to notes, such as *italics*, _underline_ or **bold**.
    • Superscript can be denoted by <sup>text</sup> and subscript <sub>text</sub>.
    • Numbered or bulleted lists can be created using either numbered lines 1. 2. 3., hyphens - or asterisks *.
    • Links can be included with: [my link to pubmed](http://pubmed.com)
    • Images can be included with: ![alt text](https://bestmedicaljournal.com/study_graph.jpg "Image Title Text")
    • For footnotes use [^1](This is a footnote.) inline.
    • Or use an inline reference [^1] to refer to a longer footnote elseweher in the document [^1]: This is a long footnote..

    hide…