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

Fatal Intra-abdominal Hemorrhage in Eosinophilic Granulomatosis with Polyangiitis: An Autopsy Case Report.

Internal medicine (Tokyo, Japan)·2026
Same author

Vedolizumab for stricturing Crohn's disease of the terminal ileum - an international multicenter cohort study.

BMC gastroenterology·2026
Same author

Esophageal schwannoma: MRI-pathology correlation with lymphoid cuffing.

Japanese journal of radiology·2026
Same author

Investigation into the utility of ultra-high-resolution mode on dynamic-ventilation computed tomography using sponge phantoms.

Scientific reports·2025
Same author

Feasibility and efficacy of a thermal ablation device utilizing a nitinol-based coil.

Acta radiologica (Stockholm, Sweden : 1987)·2025
Same author

Prospective pilot evaluation of dark borosilicate oral contrast media for the evaluation of the stomach and small bowel using CT.

Abdominal radiology (New York)·2025
Same journal

AVA: Automated Viewability Analysis for Ureteroscopic Intrarenal Surgery.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same journal

Kidney Endoscopy Video to Preoperative CT Alignment for Depth Estimation.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same journal

Deep learning‑based cell type prediction in lung tissue from brightfield histology using CODEX-derived labels.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same journal

Reconstructing physiological signals from fMRI across the adult lifespan.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same journal

Axially Swept Light-Sheet Microscopy using scattering and fluorescence contrast mechanisms.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same journal

Analytic Bounds on GAMLSS Model Variability of Normative White Matter Brain Charts.

Proceedings of SPIE--the International Society for Optical Engineering·2026
See all related articles

Related Experiment Video

Updated: Sep 20, 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

6.9K

A 25-reader performance study for hepatic metastasis detection: lessons from unsupervised learning.

Scott S Hsieh1, Akitoshi Inoue1, Parvathy Sudhir Pillai1

  • 1Department of Radiology, Mayo Clinic, Rochester, MN, 55901, USA.

Proceedings of Spie--The International Society for Optical Engineering
|June 9, 2022
PubMed
Summary
This summary is machine-generated.

Unsupervised learning identified radiologist performance patterns. Certain liver lesions were missed by many readers, while subtle lesions showed higher subspecialist confidence, informing targeted radiology training.

Keywords:
low contrast detectionreader variabilityunsupervised learning

More Related Videos

Advanced Animal Model of Colorectal Metastasis in Liver: Imaging Techniques and Properties of Metastatic Clones
11:43

Advanced Animal Model of Colorectal Metastasis in Liver: Imaging Techniques and Properties of Metastatic Clones

Published on: November 30, 2016

12.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Related Experiment Videos

Last Updated: Sep 20, 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

6.9K
Advanced Animal Model of Colorectal Metastasis in Liver: Imaging Techniques and Properties of Metastatic Clones
11:43

Advanced Animal Model of Colorectal Metastasis in Liver: Imaging Techniques and Properties of Metastatic Clones

Published on: November 30, 2016

12.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Area of Science:

  • Radiology
  • Medical Imaging
  • Machine Learning

Background:

  • Radiologist performance in detecting liver metastases on CT scans exhibits significant variability.
  • Individual radiologists may possess unique weaknesses in identifying specific types of lesions.
  • Unsupervised learning offers a potential method to uncover these performance patterns.

Purpose of the Study:

  • To investigate the utility of unsupervised learning in identifying idiosyncratic performance patterns among radiologist readers of liver CT scans.
  • To determine if specific lesion characteristics correlate with reader confidence and detection accuracy.

Main Methods:

  • Twenty-five radiologists (subspecialists and trainees) evaluated 40 liver CT exams, marking metastases and assigning confidence ratings.
  • A matrix of reader confidence ratings was constructed, with rows representing readers and columns representing metastases.
  • A clustergram analysis was employed to group similar readers and metastases based on confidence ratings.

Main Results:

  • A cluster of atypical lesions was identified, which were missed by multiple readers, including subspecialists.
  • A separate cluster revealed that subspecialists demonstrated higher confidence in diagnosing small, subtle lesions compared to trainees.
  • The clustergram analysis provided insights into reader variability and lesion detection challenges.

Conclusions:

  • Unsupervised learning can reveal reader-specific weaknesses and strengths in interpreting liver CT scans.
  • Findings highlight the need for targeted training to address challenges with atypical and subtle liver metastases.
  • This approach can inform educational strategies for improving radiologist performance in liver lesion detection.