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

Sex-specific associations of perioperative Resolvin D1 and D2 dynamics with postoperative atrial fibrillation in cardiac surgery: a secondary analysis of a prospective observational study.

European heart journal open·2026
Same author

Performance of Multimodal Large Language Models in Detection and Position Assessment of Thoracic Devices on Chest Radiographs.

Diagnostics (Basel, Switzerland)·2026
Same author

Inverse relationship between neoantigen clonality and T-cell activity reveals distinct immune phenotypes in HNSCC.

Journal of translational medicine·2026
Same author

Demographic prompt cues shift clinical recommendations in multimodal large language models: a multi-model audit of 25,380 dental radiograph assessments.

BMC oral health·2026
Same author

Antimicrobial Stewardship in oral and maxillofacial surgery: melting the iceberg.

Antimicrobial stewardship & healthcare epidemiology : ASHE·2026
Same author

Dislocation angle predicts complications following mandibular condylar fracture treatment: a retrospective cohort study.

Frontiers in oral health·2026
Same journal

Correction: Iliuta et al. Impact of Pulmonary Hypertension on Mortality After Surgery for Aortic Stenosis. <i>Medicina</i> 2022, <i>58</i>, 1231.

Medicina (Kaunas, Lithuania)·2026
Same journal

Prognostic Value of BUN-Based Ratios for Mortality and Prolonged Hospitalization in Acute Upper Gastrointestinal Bleeding: Comparison with Established Risk Scores.

Medicina (Kaunas, Lithuania)·2026
Same journal

One-Year Comparative Outcomes of Conventional Versus Accelerated Corneal Cross-Linking in Progressive Keratoconus.

Medicina (Kaunas, Lithuania)·2026
Same journal

Beyond the Intestinal Mucosa in Long-Standing Inflammatory Bowel Disease: Consequences of Chronic Inflammation and Endoscopic Approaches to Diagnosis and Management.

Medicina (Kaunas, Lithuania)·2026
Same journal

Biological and Metabolic Correlates of Psychological Resilience in Maintenance Hemodialysis: An Exploratory Gender-Based Study.

Medicina (Kaunas, Lithuania)·2026
Same journal

Influence of Mitral Annular Calcification Assessed by Cardiac Computed Tomography on Procedural and Clinical Outcomes of Transcatheter Aortic Valve Implantation.

Medicina (Kaunas, Lithuania)·2026
See all related articles

Related Experiment Video

Updated: Jan 10, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Automatic Apparent Nasal Index from Single Facial Photographs Using a Lightweight Deep Learning Pipeline: A Pilot

Babak Saravi1, Lara Schorn1, Julian Lommen1

  • 1Department of Oral, Maxillofacial and Facial Plastic Surgery, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, Germany.

Medicina (Kaunas, Lithuania)
|November 27, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning pipeline for automatic nasal index calculation from single frontal photographs. The method enables fast, reproducible classification of nasal proportions for surgical planning and research.

Keywords:
anthropometryclinicalcomputercomputer-assisteddecision support systemsdeep learningimage processingneural networksnoseplasticrhinoplastysurgery

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.2K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

808

Related Experiment Videos

Last Updated: Jan 10, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.2K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

808

Area of Science:

  • Computer vision
  • Medical imaging
  • Plastic surgery

Background:

  • Manual nasal proportion measurement is time-consuming and variable.
  • Accurate quantification is crucial for facial plastic and reconstructive surgery.
  • A reproducible automated method is needed.

Purpose of the Study:

  • Develop a deep learning pipeline for nose localization and apparent nasal index (aNI) computation.
  • Enable automatic classification into five standard anthropometric categories.
  • Provide a fast and reproducible alternative to manual measurements.

Main Methods:

  • Utilized a dataset of 29,998 frontal facial images (CelebA).
  • Trained a lightweight YOLOv8n detector for nose localization.
  • Computed apparent nasal index (aNI) from detected bounding boxes.
  • Evaluated performance using detection metrics, agreement statistics (MAE, RMSE, R², Bland-Altman), and classification accuracy (macro-F1).

Main Results:

  • Achieved 99.97% nose detection coverage on the test set.
  • Demonstrated strong agreement with ground truth aNI (MAE 3.04, R² 0.819).
  • Attained 80.7% accuracy and 0.705 macro-F1 for five-class nasal proportion categorization.

Conclusions:

  • A compact deep learning detector accurately estimates nasal index from single photographs.
  • The pipeline offers fast, reproducible, and reliable five-class nasal categorization.
  • This approach serves as a valuable decision-support tool for surgical planning and morphometric research.