Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

  1. Home
  3. Concomitant Prediction Of The Ki67 And Pit-1 Expression In Pituitary Adenoma Using Different Radiomics Models.
  1. Home
  3. Concomitant Prediction Of The Ki67 And Pit-1 Expression In Pituitary Adenoma Using Different Radiomics Models.

Related Experiment Video

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

Concomitant Prediction of the Ki67 and PIT-1 Expression in Pituitary Adenoma Using Different Radiomics Models.

Fangzheng Liu1, Yuying Zang2, Limei Feng2

  • 1Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No.119 South Fourth Ring West Road, Fengtai District, 100070, Beijing, China.

Journal of Imaging Informatics in Medicine
|May 15, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

This study developed a deep learning radiomics (DLR) model to predict Ki67 and PIT-1 expression in pituitary adenomas (PAs). The DLR model demonstrated superior performance compared to classic machine learning and deep learning models.

Keywords:
Ki67PIT-1Pituitary AdenomaRadiomics

More Related Videos

Multiplexed Immunofluorescence Analysis and Quantification of Intratumoral PD-1+ Tim-3+ CD8+ T Cells
09:32

Multiplexed Immunofluorescence Analysis and Quantification of Intratumoral PD-1+ Tim-3+ CD8+ T Cells

Published on: February 8, 2018

14.6K
Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.2K

Related Experiment Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Multiplexed Immunofluorescence Analysis and Quantification of Intratumoral PD-1+ Tim-3+ CD8+ T Cells
09:32

Multiplexed Immunofluorescence Analysis and Quantification of Intratumoral PD-1+ Tim-3+ CD8+ T Cells

Published on: February 8, 2018

14.6K
Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
10:17

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Published on: January 8, 2018

13.2K

Area of Science:

  • Radiology
  • Oncology
  • Biomedical Imaging

Background:

  • Pituitary adenomas (PAs) are common tumors requiring accurate preoperative assessment.
  • Predicting Ki67 and pituitary transcription factor 1 (PIT-1) expression is crucial for PA management.
  • Current methods for predicting these markers preoperatively are limited.

Purpose of the Study:

  • To develop and evaluate radiomics models for the preoperative prediction of high Ki67 and positive PIT-1 expression in pituitary adenomas.
  • To compare the performance of classic machine learning (CML), deep learning (DL), and deep learning radiomics (DLR) models.

Main Methods:

  • Retrospective analysis of 247 patients with PAs.
  • Extraction of imaging features from T1WI, T1CE, and T2WI MRI sequences.
  • Development of CML, DL, and DLR models using selected features.
  • Evaluation of model performance using AUC, sensitivity, specificity, accuracy, NPV, and PPV.

    • Main Results:

    • The DLR model, utilizing 107 selected features, outperformed CML and DL models.
    • In the test set, the DLR model achieved an AUC of 0.827, with sensitivity, specificity, accuracy, NPV, and PPV of 0.792, 0.800, 0.796, 0.800, and 0.792, respectively.
    • A DL radiomics nomogram (DLRN) was constructed to assist clinical decision-making.

    Conclusions:

    • The DLR model demonstrates superior efficacy in simultaneously predicting Ki67 and PIT-1 expression in PAs compared to CML and DL models.
    • Radiomics, particularly DLR, offers a promising non-invasive approach for preoperative stratification of pituitary adenomas.