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

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

Plasma metabolomics identifies trimethylamine N-oxide as an accelerator of gallstone disease accompanied by early neoplastic alterations in mice.

American journal of physiology. Gastrointestinal and liver physiology·2026

Same author

Platelet count, liver and spleen stiffness-based model reliably identifies esophageal varices needing treatment in acute-on-chronic liver failure.

Indian journal of gastroenterology : official journal of the Indian Society of Gastroenterology·2026

Same author

CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation.

Proceedings of machine learning research·2026

Same author

Outcome of marginal donors and recipients in living donor renal transplantation: A single-center study.

Saudi journal of kidney diseases and transplantation : an official publication of the Saudi Center for Organ Transplantation, Saudi Arabia·2026

Same author

Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models.

Proceedings of machine learning research·2026

Same author

Generation of a Compendium of Transcription Factor Cascades and Identification of Potential Therapeutic Targets Using Graph Machine Learning.

Genes·2025

Search research articles

Related Experiment Video

Updated: Oct 8, 2025

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

High Precision Mammography Lesion Identification From Imprecise Medical Annotations.

Ulzee An¹, Ankit Bhardwaj², Khader Shameer³

¹Department of Computer Science, University of California, Los Angeles, Los Angeles, CA, United States.

Frontiers in Big Data

|January 3, 2022

Summary

LatentCADx, a deep learning model, precisely annotates breast cancer lesions in mammograms despite coarse annotations. This improves diagnostic accuracy and lesion boundary detection, crucial for early cancer detection.

Keywords:

big data and analytics breast cancer computational diagnosis computer vision digital health oncology

More Related Videos

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

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: Oct 8, 2025

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

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

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Mammography is key for early breast cancer detection, but human diagnosis faces challenges with dense tissue patterns.
Current deep learning models struggle with precise lesion segmentation due to coarse, hand-drawn annotations.

Purpose of the Study:

To develop a deep learning model, LatentCADx, for accurate segmentation of breast cancer lesions from mammograms.
To overcome limitations of coarse annotations in medical image analysis.

Main Methods:

Proposed LatentCADx, a deep convolutional neural network (DCNN) segmentation model.
Employed joint classification training and a strict segmentation penalty to refine annotations.
Validated on a dataset of 2,620 mammogram case files.

Main Results:

LatentCADx achieved high performance: ROC of 0.97, AP of 0.87, and segmentation AP of 0.75 (IOU=0.5).
Demonstrated superior specificity (0.90) and sharper lesion boundaries compared to existing methods.
Reduced confused pixels by over 60%.

Conclusions:

LatentCADx effectively segments breast cancer lesions with high precision, even with limited annotation quality.
The model offers a significant advancement in automated mammogram analysis for improved breast cancer diagnosis.