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

Combining RNAScope and RCA reveals a novel epitheliotropic bovine xipapillomavirus in udder papillomas.

Veterinary microbiology·2025
Same author

Novel immunodominant neoepitope in a KPC mouse model of pancreatic cancer allowing identification of tumor-specific T cells.

Oncoimmunology·2025
Same author

Susceptibility of Non-Tuberculous Mycobacteria Biofilm to Common Disinfectants in Aquaculture Systems.

Journal of fish diseases·2025
Same author

Systemic Granulomatosis in the Meagre <i>Argyrosomus regius</i>: Fishing for a Plausible Etiology.

Veterinary sciences·2024
Same author

First Molecular Characterisation of Porcine Parvovirus 7 (PPV7) in Italy.

Viruses·2024
Same author

Ovine papillomavirus type 3 virus-like particle-based tools for diagnosis and detection of infection.

Vaccine·2024

Related Experiment Video

Updated: Jul 30, 2025

Sectioning Mammary Gland Whole Mounts for Lesion Identification
09:22

Sectioning Mammary Gland Whole Mounts for Lesion Identification

Published on: July 24, 2017

10.6K

Canine Mammary Tumor Histopathological Image Classification via Computer-Aided Pathology: An Available Dataset for

Giovanni P Burrai1,2, Andrea Gabrieli1, Marta Polinas1

  • 1Department of Veterinary Medicine, University of Sassari, Via Vienna 2, 07100 Sassari, Italy.

Animals : an Open Access Journal From MDPI
|May 13, 2023
PubMed
Summary

Computer-aided pathology (CAD) systems show promise in classifying canine mammary tumors (CMTs). These digital pathology tools achieved up to 85% accuracy, aiding cancer research.

Keywords:
CMT datasetbreast cancercanine mammary tumor (CMTs)deep learninghistological classificationmachine learning

More Related Videos

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment &#8212; Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.4K
Pathological Analysis of Lung Metastasis Following Lateral Tail-Vein Injection of Tumor Cells
08:54

Pathological Analysis of Lung Metastasis Following Lateral Tail-Vein Injection of Tumor Cells

Published on: May 20, 2020

9.1K

Related Experiment Videos

Last Updated: Jul 30, 2025

Sectioning Mammary Gland Whole Mounts for Lesion Identification
09:22

Sectioning Mammary Gland Whole Mounts for Lesion Identification

Published on: July 24, 2017

10.6K
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment &#8212; Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.4K
Pathological Analysis of Lung Metastasis Following Lateral Tail-Vein Injection of Tumor Cells
08:54

Pathological Analysis of Lung Metastasis Following Lateral Tail-Vein Injection of Tumor Cells

Published on: May 20, 2020

9.1K

Area of Science:

  • Veterinary pathology
  • Artificial intelligence in oncology
  • Digital pathology

Background:

  • Histopathology is the standard for classifying canine mammary tumors (CMTs) but is subjective and time-consuming.
  • Digital pathology (DP) and computer-aided pathology (CAD) offer potential improvements in accuracy and efficiency.
  • High inter-observer variability in histopathology can impact canine mammary tumor classification.

Purpose of the Study:

  • To evaluate the efficacy of CAD systems in differentiating benign from malignant canine mammary tumors.
  • To assess the performance of various CAD architectures for CMT classification.
  • To explore the integration of artificial intelligence in veterinary cancer diagnostics.

Main Methods:

  • Utilized a dataset (CMTD) of 1056 hematoxylin and eosin JPEG images from 20 benign and 24 malignant CMTs.
  • Developed three CAD systems combining convolutional neural networks (VGG16, Inception v3, EfficientNet) as feature extractors with classifiers (SVM, SGB).
  • Trained and validated models, initially on a human breast cancer dataset (BreakHis), then applied to the CMT dataset.

Main Results:

  • CAD systems achieved classification accuracies ranging from 0.63 to 0.85 on the CMT dataset.
  • The EfficientNet framework combined with Support Vector Machines (SVM) demonstrated the highest performance, with accuracies between 0.82 and 0.85.
  • Model performance varied across different CAD architectures and classifier combinations.

Conclusions:

  • Digital pathology and CAD systems show significant potential for improving canine mammary tumor classification accuracy.
  • The integration of AI and machine learning in veterinary oncology research offers promising diagnostic perspectives.
  • CAD systems can assist in overcoming the limitations of traditional histopathology for CMT diagnosis.