Search research articles

Related Concept Videos

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy

You might also read

Related Articles

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

Sort by

Same author

Multivariate associations between sleep patterns and self-regulation in adolescence: Canonical correlation analysis across ABCD and NCANDA cohorts.

Chronobiology international·2026

Same author

Leveraging Machine Learning to Advance Alcohol Research: Current Applications, Challenges, and Opportunities.

Alcohol research : current reviews·2026

Same author

Using deep learning to identify brain networks mediating cognitive and motor impairments in alcohol use disorder.

Translational psychiatry·2026

Same author

Developing ICU Clinical Behavioral Atlas Using Ambient Intelligence and Computer Vision.

NEJM AI·2026

Same author

Sex-specific differences in brain activity dynamics of youth with a family history of substance use disorder.

Nature. Mental health·2025

Same author

GAMMA-PD: Graph-based Analysis of Multi-Modal Motor Impairment Assessments in Parkinson's Disease.

Graphs in biomedical image analysis : 6th International Workshop, GRAIL 2024, held in conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceeding. GRAIL (Workshop) (6th : 2024 : Marrakesh, Morocco)·2025

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

Search research articles

Related Experiment Video

Updated: Nov 28, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Training confounder-free deep learning models for medical applications.

Qingyu Zhao¹, Ehsan Adeli^1,2, Kilian M Pohl^3,4

¹Department of Psychiatry & Behavioral Sciences, Stanford University, Stanford, CA, 94305, USA.

Nature Communications

|November 27, 2020

Summary

This study introduces a new deep learning method to reduce bias in medical imaging analysis. The approach effectively derives features invariant to confounding factors, improving diagnostic accuracy.

Related Experiment Videos

Last Updated: Nov 28, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Artificial Intelligence
Medical Imaging Analysis
Biostatistics

Background:

Confounding effects (biases) pose significant challenges in deep learning for medical imaging, leading to spurious associations.
Traditional methods for bias mitigation are not always suitable for end-to-end deep learning models that automatically extract image features.
Novel strategies are required to address confounding in deep learning-based medical image analysis.

Purpose of the Study:

To develop an end-to-end deep learning approach for deriving features invariant to confounding factors in medical imaging.
To account for intrinsic correlations between confounders and prediction outcomes.
To reduce bias in deep learning models applied to medical imaging studies.

Main Methods:

An end-to-end deep learning framework is proposed, integrating concepts from statistical methods and fair machine learning.
The method derives features that are invariant to confounding variables.
The approach accounts for correlations between confounders and the prediction outcome.

Main Results:

The method was evaluated on predicting HIV diagnosis from brain MRIs.
It was used to identify sex differences in adolescent brain morphology.
Bone age was determined from children's X-ray images, demonstrating reduced bias.
Accurate predictions were achieved while mitigating confounding effects.

Conclusions:

The proposed method effectively derives bias-invariant features from medical images using deep learning.
This approach holds promise for improving the reliability and accuracy of deep learning models in medical research.
The method successfully reduces biases associated with confounding factors in various medical imaging applications.