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

Classification of Systems-I01:26

Classification of Systems-I

455
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
455
Classification of Leukocytes01:30

Classification of Leukocytes

4.4K
Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
4.4K
Aggregates Classification01:29

Aggregates Classification

572
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
572
Classification of Systems-II01:31

Classification of Systems-II

385
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
385
Methods of Classification and Identification01:28

Methods of Classification and Identification

701
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
701

You might also read

Related Articles

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

Sort by
Same author

Model uncertainty estimates for deep learning mammographic density prediction using ordinal and classification approaches.

Biomedical physics & engineering express·2026
Same author

A generalizable 3D framework and model for self-supervised learning in medical imaging.

NPJ digital medicine·2025
Same author

Enhancing breast cancer detection on screening mammogram using self-supervised learning and a hybrid deep model of Swin Transformer and convolutional neural networks.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Impact of menopause and age on breast density and background parenchymal enhancement in dynamic contrast-enhanced magnetic resonance imaging.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Artificial Intelligence-Assisted Detection of Breast Cancer Lymph Node Metastases in the Post-Neoadjuvant Treatment Setting.

Laboratory investigation; a journal of technical methods and pathology·2025
Same author

Understanding metric-related pitfalls in image analysis validation.

Nature methods·2024

Related Experiment Video

Updated: Nov 28, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.8K

Learning to segment images with classification labels.

Ozan Ciga1, Anne L Martel2

  • 1Department of Medical Biophysics, University of Toronto, Canada.

Medical Image Analysis
|December 1, 2020
PubMed
Summary

This study introduces a novel architecture for medical image segmentation that significantly reduces the need for extensive expert annotations. By utilizing image-level labels, it achieves performance comparable to fully annotated datasets, saving time and resources.

Keywords:
Digital histopathologyImage segmentationWeakly supervised learningWhole slide images

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.4K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.2K

Related Experiment Videos

Last Updated: Nov 28, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.8K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.4K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.2K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Machine Learning

Background:

  • Medical imaging tasks like classification and segmentation demand expert-annotated data, which is costly and time-consuming to acquire.
  • Segmentation annotation is particularly laborious, requiring precise boundary delineation, unlike simpler image-level classification.
  • Current datasets often use image patches with class labels, limiting their utility for whole slide image segmentation tasks, common in fields like breast cancer histopathology.

Purpose of the Study:

  • To develop a novel architecture that reduces the reliance on segmentation-level ground truth for training.
  • To enable the use of existing image-level labeled datasets for segmentation tasks with minimal additional annotation.
  • To decrease the time and cost associated with data curation for medical image segmentation.

Main Methods:

  • Proposed a new deep learning architecture designed to leverage image-level labels for segmentation tasks.
  • Developed a method to utilize minimal segmentation-level annotations (e.g., one per class) in conjunction with image-level labels.
  • Evaluated the architecture's performance on medical imaging segmentation tasks, comparing it against fully annotated datasets.

Main Results:

  • The proposed architecture effectively alleviates the need for extensive segmentation-level ground truth.
  • Achieved performance comparable to models trained on fully annotated datasets, even when using only one segmentation-level annotation per class.
  • Demonstrated the potential to unlock previously acquired image-level datasets for segmentation tasks.

Conclusions:

  • The novel architecture significantly reduces data annotation requirements for medical image segmentation.
  • It offers a cost-effective and efficient approach to training segmentation models, especially for whole slide imaging.
  • This method facilitates the broader application of machine learning in medical image analysis by overcoming data scarcity challenges.