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

Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

209
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
209

You might also read

Related Articles

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

Sort by
Same author

Determining the age cut-off for increased surgical risk after Roux-en-Y gastric bypass in elderly patients: MBSAQIP 2015-2023 database analysis.

Surgical endoscopy·2026
Same author

Deep learning of CT imaging predicts PD-L1 expression and immunotherapy response in metastatic NSCLC: A multi-center study.

Cancer letters·2026
Same author

Microcystic lymphatic malformation of the small intestine presenting as acute abdominal pain in a 5-year-old boy: a case report and review of the literature.

Journal of medical case reports·2026
Same author

A self-supervised GNN-Transformer framework for weak microseismic signal identification.

Scientific reports·2026
Same author

Practical synthesis and photophysical characterization of full-color circularly polarized luminescent 4,7-diaryl-5,6-(<i>R</i>/<i>S</i>)-BINOL-<i>O</i>-[2,1,3]benzothiadiazoles.

RSC advances·2026
Same author

Comparison of one anastomosis gastric bypass to standard bariatric interventions: a propensity score matching analysis using the 2020-2023 Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program database.

Surgery for obesity and related diseases : official journal of the American Society for Bariatric Surgery·2026

Related Experiment Video

Updated: Jun 4, 2025

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

8.2K

ItpCtrl-AI: End-to-end interpretable and controllable artificial intelligence by modeling radiologists' intentions.

Trong-Thang Pham1, Jacob Brecheisen1, Carol C Wu2

  • 1AICV Lab, Department of EECS, University of Arkansas, AR 72701, USA.

Artificial Intelligence in Medicine
|December 17, 2024
PubMed
Summary

We developed ItpCtrl-AI, an interpretable AI framework for medical diagnosis that mimics radiologist eye gaze. This deep learning model enhances diagnostic accuracy and explainability in chest X-ray (CXR) analysis.

Keywords:
Computer-aided diagnosisGaze intentionInterpretable deep learningRadiologist’s intentionRadiologyVision-language model

More Related Videos

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

766
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

958

Related Experiment Videos

Last Updated: Jun 4, 2025

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

8.2K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

766
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

958

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Radiology

Background:

  • Deep learning models offer high performance in computer-aided diagnosis but often lack explainability, posing risks in critical medical applications like chest X-ray (CXR) interpretation.
  • The "black box" nature of many AI models hinders trust and adoption in clinical settings, particularly when diagnostic decisions require clear justification.

Purpose of the Study:

  • To introduce ItpCtrl-AI, a novel end-to-end interpretable and controllable framework for AI-driven medical diagnosis.
  • To emulate the decision-making process of radiologists, including their eye gaze patterns, to improve the explainability and controllability of AI diagnostic systems.
  • To develop and validate a new dataset, Diagnosed-Gaze++, that links medical findings with corresponding eye gaze data.

Main Methods:

  • The ItpCtrl-AI framework emulates radiologist eye gaze to identify focal areas and pixel significance, generating an attention heatmap.
  • The attention heatmap guides the extraction of visual information for diagnosing findings and reveals the model's decision-making rationale.
  • The framework incorporates user-directional input, enhancing its controllability, and utilizes the Diagnosed-Gaze++ dataset for training and validation.

Main Results:

  • Extensive experiments demonstrate the framework's effectiveness in generating accurate attention heatmaps and reliable diagnoses.
  • The model successfully identifies medical findings in CXR images and accurately reproduces the attention patterns observed in radiologists' eye gaze.
  • The developed Diagnosed-Gaze++ dataset aligns medical findings with eye gaze data, facilitating research in interpretable AI for medical diagnosis.

Conclusions:

  • ItpCtrl-AI provides an interpretable and controllable solution to the explainability challenge in deep learning-based medical diagnosis.
  • The framework's ability to mirror radiologist decision-making processes and eye gaze patterns enhances diagnostic accuracy and transparency.
  • The public release of the dataset, models, and code will support further advancements in explainable AI for radiology.