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

Natural history study of adults with primary central nervous system tumors: Initial results for first 1000 participants.

Neuro-oncology practiceĀ·2026
Same author

Preventing Post-ERCP Pancreatitis: A Pragmatic Clinical Pathway from Periprocedural Prophylaxis to Early Postprocedural Triage.

Journal of clinical medicineĀ·2026
Same author

Aspirin (Acetylsalicylic Acid) Exerts Antineoplastic Effects on Bile Duct Carcinoma Cells Through Modulation of COX-2/ EGFR, AMPK, and IGF-1R Signaling Pathways.

The Turkish journal of gastroenterology : the official journal of Turkish Society of GastroenterologyĀ·2026
Same author

Case Report: Molecular diagnostics and clinical courses of two adult spinal pilocytic astrocytoma long-term survivors with GTF2I::BRAF fusion.

Frontiers in oncologyĀ·2026
Same author

Association of human papillomavirus infection with seminal parameters, anti-sperm antibody, and sperm DNA integrity in Korean men: A preliminary study.

Clinical and experimental reproductive medicineĀ·2026
Same author

Pharmacokinetics and Renal Safety Evaluation of Colistin Methanesulfonate Sodium in Korean Healthy Male Volunteers: An Open-Label, Multiple-Dose Study.

Drug design, development and therapyĀ·2026

Related Experiment Video

Updated: Sep 19, 2025

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer
03:55

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer

Published on: June 9, 2023

628

Enhancing biliary tract cancer diagnosis using AI-driven 3D optical diffraction tomography.

Se Woo Park1, Hee Chan Moon2, Seok Jin Hong3

  • 1Division of Gastroenterology, Department of Internal Medicine, Hallym University Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Hwaseong, Republic of Korea.

Methods (San Diego, Calif.)
|June 8, 2025
PubMed
Summary

Biliary tract cancer cells show increased lipid droplets (LDs). A new deep learning method using 3D optical diffraction tomography accurately classifies these cancer cells based on LD features for early detection.

Keywords:
Biliary tract cancerBiomarkerLipid dropletMachine learningMetabolic imagingOptical diffraction tomography

More Related Videos

Computed Tomography-guided Time-domain Diffuse Fluorescence Tomography in Small Animals for Localization of Cancer Biomarkers
12:24

Computed Tomography-guided Time-domain Diffuse Fluorescence Tomography in Small Animals for Localization of Cancer Biomarkers

Published on: July 17, 2012

12.5K
Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization
09:49

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Published on: December 2, 2013

10.4K

Related Experiment Videos

Last Updated: Sep 19, 2025

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer
03:55

Computer-Aided Three-Dimensional Visualization in the Treatment of Locally Advanced Thyroid Cancer

Published on: June 9, 2023

628
Computed Tomography-guided Time-domain Diffuse Fluorescence Tomography in Small Animals for Localization of Cancer Biomarkers
12:24

Computed Tomography-guided Time-domain Diffuse Fluorescence Tomography in Small Animals for Localization of Cancer Biomarkers

Published on: July 17, 2012

12.5K
Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization
09:49

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Published on: December 2, 2013

10.4K

Area of Science:

  • Biophysics
  • Cell Biology
  • Medical Imaging

Background:

  • Biliary tract cancer (BTC) exhibits unique metabolic changes, especially in lipid metabolism.
  • Lipid droplets (LDs) are key organelles involved in cellular lipid homeostasis.
  • Altered LD characteristics may serve as biomarkers for BTC.

Purpose of the Study:

  • To develop an automated system for classifying biliary tract cancer cells.
  • To investigate the utility of lipid droplet (LD) characteristics for BTC detection.
  • To combine 3D optical diffraction tomography (ODT) with deep learning for enhanced diagnostics.

Main Methods:

  • Cultured human BTC cell lines (SNU1196, SNU308, SNU478) and normal cholangiocytes (H69).
  • Acquired 3D refractive index tomograms using ODT.
  • Developed and evaluated a convolutional neural network (CNN) model (EfficientNet-b3) for automated classification based on LD features (volume, mass, count).
  • Incorporated LD metadata and multi-view score fusion to improve diagnostic performance.

Main Results:

  • BTC cells displayed significantly higher LD volume, mass, and count than normal cells.
  • The EfficientNet-b3 model achieved high accuracy (93.79%) and AUC (0.982).
  • Incorporating LD metadata and multi-view fusion further improved performance (AUC: 0.999, accuracy: 98.61%).
  • LayerCAM analysis confirmed the model's focus on LD-rich regions.

Conclusions:

  • Lipid droplet characteristics are distinct in biliary tract cancer cells.
  • 3D ODT combined with deep learning offers a powerful tool for automated BTC classification.
  • This approach shows significant potential for early detection and future clinical applications in biliary tract cancer.