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

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A nanogram-sensitive workflow for oligonucleotide mass spectrometry using ion-pair-free nanoflow HILIC and RNase benchmarking.

Nucleic acids research·2026
Same author

Detection of an Antagonist Bound to the Neurokinin a Receptor in Styrene-Maleic Acid Lipid Particles by <sup>19</sup>F Ultrafast Magic-Angle Spinning Nuclear Magnetic Resonance Spectroscopy.

Chembiochem : a European journal of chemical biology·2026
Same author

NAIL-MS reveals tRNA and rRNA hypomodification as a consequence of 5-fluorouracil treatment.

Nucleic acids research·2025
Same author

Chemical reactivity of RNA and its modifications with hydrazine.

Communications chemistry·2025
Same author

NIR-excited imaging of drug-induced liver injury using a superoxide-activated ratiometric upconversion luminescence nanoprobe.

Talanta·2024
Same author

Deep causal learning for pancreatic cancer segmentation in CT sequences.

Neural networks : the official journal of the International Neural Network Society·2024

Related Experiment Video

Updated: Oct 31, 2025

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

7.1K

Computer-aided differentiates benign from malignant IPMN and MCN with a novel feature selection algorithm.

Chengkang Li1, Ran Wei1, Yishen Mao2

  • 1The School of Information Science and Technology of Fudan University, Shanghai 200433, China.

Mathematical Biosciences and Engineering : MBE
|July 2, 2021
PubMed
Summary

Accurately distinguishing benign from malignant pancreatic cystic neoplasms like intraductal papillary mucinous neoplasm (IPMN) and mucinous cystic neoplasm (MCN) is vital. A novel computer-aided diagnosis (CAD) system using radiomics and clinical data achieved high accuracy in differentiating these tumors.

Keywords:
IPMNMCNcomputer-aided diagnosisfeature extraction and selectionradiomics

More Related Videos

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.2K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.7K

Related Experiment Videos

Last Updated: Oct 31, 2025

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

7.1K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.2K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.7K

Area of Science:

  • Gastroenterology
  • Medical Imaging
  • Oncology

Background:

  • Preoperative differentiation between benign and malignant intraductal papillary mucinous neoplasms (IPMN) and mucinous cystic neoplasms (MCN) is critical for treatment planning.
  • Similarities in imaging and clinical features between benign and malignant lesions pose diagnostic challenges.

Purpose of the Study:

  • To develop and validate a robust computer-aided diagnosis (CAD) system for differentiating benign from malignant IPMN and MCN.
  • To leverage radiomics features and clinical indices for improved diagnostic accuracy.

Main Methods:

  • A CAD system was developed using radiomics features (436) and clinical indices (9) from 107 patients.
  • A novel feature selection algorithm, BLR (Bootstrapping repeated LASSO with Random selections), was employed.
  • A Support Vector Machine (SVM) model was trained on 90 patients and validated on 17 independent cases.

Main Results:

  • The CAD system demonstrated strong diagnostic performance.
  • Area under the receiver operating characteristic curve (AUC) was 0.83 in the cross-validation cohort.
  • AUC reached 0.92 in the independent testing cohort, confirming the system's effectiveness.

Conclusions:

  • The proposed CAD system effectively differentiates benign from malignant IPMN and MCN.
  • Radiomics combined with clinical indices offer a promising approach for preoperative diagnosis of pancreatic cystic neoplasms.
  • The developed CAD system shows significant potential for improving tumor diagnosis in clinical practice.