Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

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

Sort by

Same author

Clinical benefits and current challenges of photon-counting detector CT in vascular imaging.

Radiology advances·2026

Same author

Hallucination at low radiation dose: Evaluation of two deep-learning reconstruction methods in high-resolution chest CT.

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

Same author

Accuracy and precision of automated kidney stone detection on CT.

Abdominal radiology (New York)·2026

Same author

The Uncoupling of CT Dose and Noise.

Radiology·2026

Same author

A framework for quantifying and leveraging uncertainty in pre-trained CT denoising model.

IEEE transactions on bio-medical engineering·2026

Same author

Mitigating CT number variability between scanners, tube potentials, and patient sizes using spectral CT virtual monoenergetic imaging.

Physics in medicine and biology·2026

Search research articles

Related Experiment Video

Updated: Oct 13, 2025

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

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

Published on: August 16, 2020

Deep-learning model observer for a low-contrast hepatic metastases localization task in computed tomography.

Hao Gong¹, Joel G Fletcher¹, Jay P Heiken¹

¹Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA.

Medical Physics

|November 18, 2021

Summary

Deep-learning model observers (DL-MO) accurately predict radiologist performance in abdominal CT tasks, showing potential for image quality assessment. This validates DL-MO for challenging low-contrast lesion detection in CT imaging.

Keywords:

X-ray CT deep learning hepatic metastases model observer task-based image quality assessment

More Related Videos

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

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

Published on: October 10, 2018

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

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

Published on: November 30, 2016

Related Experiment Videos

Last Updated: Oct 13, 2025

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

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

Published on: August 16, 2020

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

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

Published on: October 10, 2018

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

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

Published on: November 30, 2016

Area of Science:

Medical Imaging
Artificial Intelligence
Radiology

Background:

Conventional model observers (MO) struggle with realistic anatomical backgrounds in CT.
Deep learning-based model observers (DL-MO) offer a potential solution but require validation for complex tasks.
Assessing image quality in abdominal CT, particularly for low-contrast lesions, remains challenging.

Purpose of the Study:

To validate a deep-learning-based model observer (DL-MO) for a low-contrast hepatic metastases localization task in abdominal CT.
To compare the performance of the DL-MO against human radiologists and a conventional Channelized Hoteling Observer (CHO).
To evaluate the generalization capability of the DL-MO in realistic clinical scenarios.

Main Methods:

Adapted a DL-MO framework using synthesized abdominal CT exams with realistic lesion/noise characteristics.
Generated 10 experimental conditions varying lesion size/contrast, radiation dose, and reconstruction type.
Compared DL-MO performance (area under localization ROC curves) with 3 radiologists and a CHO across 100 trials per condition.

Main Results:

DL-MO performance strongly correlated with radiologist performance (Pearson's r=0.987).
DL-MO performance was comparable to grouped radiologists (mean difference -3.3%).
Conventional CHO showed weaker correlation (r=0.812) and significant performance bias (-29.5%).

Conclusions:

DL-MO shows significant potential for accurate image quality assessment in abdominal CT.
DL-MO performance closely mimics human radiologists in challenging localization tasks.
DL-MO offers a promising tool for evaluating CT image quality in clinical settings.