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: Mar 3, 2026

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

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

Published on: August 16, 2020

Global detection approach for clustered microcalcifications in mammograms using a deep learning network.

Juan Wang¹, Robert M Nishikawa², Yongyi Yang¹

¹Illinois Institute of Technology, Medical Imaging Research Center, Department of Electrical and Computer Engineering, Chicago, Illinois, United States.

Journal of Medical Imaging (Bellingham, Wash.)

|May 4, 2017

Summary

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

Molecular cloning and heterologous expression of an acid-stable endoxylanase gene from Penicillium oxalicum in Trichoderma reesei.

Journal of microbiology and biotechnology·2013

Same author

Increasing gastric juice pH level prior to anti-Helicobacter pylori therapy may be beneficial to the healing of duodenal ulcers.

Experimental and therapeutic medicine·2013

Same author

Inhibitory effect of glutathione on oxidative liver injury induced by dengue virus serotype 2 infections in mice.

PloS one·2013

Same author

Efficacy of tribendimidine against Angiostrongylus cantonensis infection in the mice.

Parasitology research·2013

Same author

Double-bundle anatomical versus single-bundle isometric medial patellofemoral ligament reconstruction for patellar dislocation.

International orthopaedics·2013

Same author

Fatty acid binding proteins FABP9 and FABP10 participate in antibacterial responses in Chinese mitten crab, Eriocheir sinensis.

PloS one·2013

A new deep convolutional neural network (CNN) directly detects clustered microcalcifications (MCs) in mammograms, outperforming traditional methods. This AI approach reduces false positives, improving accuracy for MC detection in breast cancer screening.

Area of Science:

Medical Imaging
Artificial Intelligence
Computer-Aided Diagnosis

Background:

Traditional microcalcification (MC) detection relies on identifying individual MCs, which are then clustered.
This method is prone to false positives (FPs) from similar image patterns.

Purpose of the Study:

To investigate a direct detection approach for clustered MCs using a deep convolutional neural network (CNN).
To evaluate the CNN's performance against a traditional MC detector with FP suppression.

Main Methods:

Developed a CNN classifier that takes large image windows as input.
Trained the CNN to automatically extract multi-scale image features relevant to MCs.
Evaluated performance using receiver operating characteristic (ROC) and free-response ROC (FROC) analyses on diverse mammogram datasets.

Keywords:

clustered microcalcifications computer-aided detection convolutional neural network deep learning

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Related Experiment Videos

Last Updated: Mar 3, 2026

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

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

Published on: August 16, 2020

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Main Results:

CNN achieved an area under the ROC curve of 0.971 for region classification, surpassing the MC detector's 0.944.
At 90% sensitivity in full mammogram detection, the CNN yielded 0.69 FP clusters/image, significantly lower than the MC detector's 1.17 FP clusters/image.

Conclusions:

Direct detection using CNNs with global image features is more effective for discriminating clustered MCs from FPs.
This approach offers improved accuracy for clustered MC detection in mammography.