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

Search research articles

Related Experiment Video

Updated: Jan 10, 2026

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

Deep learning approaches for pathological image classification.

Masayuki Tsuneki¹

¹Medmain Research, Medmain Inc., Fukuoka, Japan; Division of Anatomy and Cell Biology of the Hard Tissue, Department of Tissue Regeneration and Reconstruction, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan.

Journal of Oral Biosciences

|November 22, 2025

Summary

Deep learning models enhance pathology diagnostics by classifying whole slide images. New methods address limited data for rare cancers, improving diagnostic accuracy and supporting precision medicine.

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

Automated Assessment of Ki-67 Labeling Index Using Cell-Level Detection and Classification in Whole-Slide Images.

Diagnostics (Basel, Switzerland)·2026

Same author

Correction: Tsuneki et al. Deep Learning-Based Screening of Urothelial Carcinoma in Whole Slide Images of Liquid-Based Cytology Urine Specimens. <i>Cancers</i> 2023, <i>15</i>, 226.

Cancers·2025

Same author

Evaluation of a Deep Learning Model for Metastatic Squamous Cell Carcinoma Prediction From Whole Slide Images.

Archives of pathology & laboratory medicine·2024

Same author

Novel Applications of Artificial Intelligence in Cancer Research.

Technology in cancer research & treatment·2023

Same author

Diagnostic Categories and Key Features for Pathological Diagnosis of Endoscopic Ultrasound-Guided Fine Needle Aspiration Biopsy Samples of Pancreatic Lesions: A Consensus Study.

Pancreas·2023

Same author

Deep Learning Approach to Classify Cutaneous Melanoma in a Whole Slide Image.

Cancers·2023

Area of Science:

Pathology
Computer-aided diagnosis
Deep learning

Background:

Deep learning models automate whole slide image interpretation in pathology.
Classification models show promise in distinguishing cancer subtypes and predicting molecular features.
Limited labeled data, especially for rare cancers, restricts conventional deep learning approaches.

Purpose of the Study:

To review methodologies for developing classification-based deep learning models in pathology.
To explore strategies for overcoming data limitations in deep learning for cancer diagnosis.
To highlight the role of deep learning in advancing precision medicine.

Main Methods:

Utilizes supervised learning with convolutional and recurrent neural networks.

Keywords:

Classification Computer vision Computer-aided diagnosis Deep learning Pathology

Related Experiment Videos

Last Updated: Jan 10, 2026

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

Employs transfer learning to improve model training with scarce datasets.

Introduces synthetic data generation using simulators and formula-driven approaches.

Main Results:

Transfer learning effectively enhances model training efficiency with limited data.
Synthetic data generation and formula-driven methods address limitations of conventional datasets.
Visualization tools like probability heatmaps are crucial for model validation and interpretability.

Conclusions:

Deep learning models will increasingly support precision medicine, extending beyond diagnosis to prognosis and treatment.
Augmented intelligence in deep learning offers comprehensive clinical support in pathology.
These advancements are vital given increasing demands and resource limitations in pathology.