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 Illness01:17

Classification of Illness

8.1K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
8.1K
Reducing Line Loss01:18

Reducing Line Loss

215
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
215
Sensitivity, Specificity, and Predicted Value01:13

Sensitivity, Specificity, and Predicted Value

773
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
773
Classification of Systems-I01:26

Classification of Systems-I

356
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:
356
Loss of Tumor Suppressor Gene Functions01:12

Loss of Tumor Suppressor Gene Functions

5.2K
Tumor suppressor genes are normal genes that can slow down cell division, repair DNA mistakes, or program the cells for apoptosis in case of irreparable damage. Hence, they play an essential role in preventing the proliferation of damaged cells.
When the tumor suppressor genes develop mutations or are lost, cells start growing out of control, leading to cancer. However, a single functional copy of the tumor suppressor gene is enough for the cells to maintain their normal functions and cell...
5.2K
Classification of Systems-II01:31

Classification of Systems-II

253
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,
253

You might also read

Related Articles

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

Sort by
Same author

Detecting Performance Drift in AI Models for Medical Image Analysis Using CUSUM Chart.

Journal of imaging informatics in medicine·2026
Same author

Synthetic data in radiological imaging: current state and future outlook.

BJR artificial intelligence·2026
Same author

Multimodal Learning with Privileged Report Supervision for Generalizable Tuberculosis Detection on Chest Radiographs.

Journal of medical systems·2026
Same author

Oral Cancer Detection By Using Tabular Data Synthesis and Classification.

Proceedings ... ICDM workshops. IEEE International Conference on Data Mining·2026
Same author

Artificial Intelligence-Based Diagnosis of Kaposi Sarcoma Using Digital Photographs in Dark-Skinned Patients in Uganda.

JCO global oncology·2026
Same author

Evaluating Explainability: A Framework for Systematic Assessment of Explainable AI Features in Medical Imaging.

Bioengineering (Basel, Switzerland)·2026

Related Experiment Video

Updated: Oct 8, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

Novel loss functions for ensemble-based medical image classification.

Sivaramakrishnan Rajaraman1, Ghada Zamzmi1, Sameer K Antani1

  • 1National Library of Medicine, National Institutes of Health, Bethesda, MD, United States of America.

Plos One
|December 30, 2021
PubMed
Summary

This study benchmarks loss functions for multi-class classification in pediatric chest X-rays, finding that model ensembles significantly improve pneumonia detection accuracy compared to individual models.

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Related Experiment Videos

Last Updated: Oct 8, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Area of Science:

  • Artificial Intelligence
  • Medical Imaging Analysis
  • Deep Learning

Background:

  • Medical images often show multiple abnormalities, necessitating multi-class classifiers.
  • Deep neural network performance is influenced by dataset characteristics and loss functions.
  • Cross-entropy loss, commonly used, can bias models toward majority classes.

Purpose of the Study:

  • To comprehensively analyze and select appropriate loss functions for multi-class classification tasks.
  • To benchmark state-of-the-art loss functions and propose improved ones.
  • To enhance diagnostic accuracy for pediatric chest X-ray (CXR) classification.

Main Methods:

  • Benchmarking various loss functions for deep learning classifiers.
  • Utilizing a pediatric chest X-ray dataset with normal, bacterial pneumonia, and viral pneumonia labels.
  • Constructing prediction-level and model-level ensembles for improved classification.

Main Results:

  • Weighted averaging of top-3 and top-5 model-level ensembles significantly outperformed individual models and existing literature.
  • Achieved a high Matthews Correlation Coefficient (MCC) of 0.9068.
  • Localization studies confirmed models learned task-specific features and identified disease regions.

Conclusions:

  • Ensemble methods with carefully selected loss functions can significantly improve multi-class classification in medical imaging.
  • The proposed approach offers a robust solution for pediatric pneumonia detection from chest X-rays.
  • Further research into loss function optimization for medical AI is warranted.