Related Experiment Video
Updated: May 5, 2026
05:44
Ultrasonographic Evaluation of Breast Cancer-related Lymphedema
Published on: January 12, 2017
10.0K
Classification of Breast Lymphedema in a Racially Diverse Cohort.
J G Chen1, C B Perez2, A Coogan2
1Larner College of Medicine, University of Vermont, Burlington, VT, USA.
Lymphology
|November 13, 2024
Summary
Breast lymphedema classification is crucial for patient care. New ultrasound and machine learning methods show promise for identifying and grading breast lymphedema severity after breast cancer treatment.
Area of Science:
- Oncology
- Medical Imaging
- Biostatistics
Background:
- Breast lymphedema is a common complication following breast cancer treatment, impacting patient quality of life.
- Current classification systems for breast lymphedema lack rigor, hindering effective management.
- Accurate classification is needed to guide treatment and improve patient outcomes.
Purpose of the Study:
- To explore and develop classification approaches for breast lymphedema.
- To utilize breast ultrasound, physical examination, and patient-reported outcomes for classification.
- To establish a rigorous system for breast lymphedema assessment.
Main Methods:
- Enrolled 80 patients (60 breast cancer survivors, 20 controls) from two institutions.
- Performed bilateral breast ultrasound to measure dermal thickness.
- Assessed physical signs and patient-reported quality of life impacts.
- Developed an ultrasound-based metric and a machine learning classifier.
Main Results:
- Ultrasound-defined breast lymphedema was present in 72% of invasive breast cancer patients.
- An ultrasound-based metric of dermal thickness difference was derived.
- A multiparameter machine learning classifier identified three distinct patient groups based on lymphedema severity.
Conclusions:
- Both an ultrasound-based measure and a multiparameter classifier show potential for rigorous breast lymphedema classification.
- These novel methods warrant further validation in larger patient cohorts.
- Improved classification can lead to better patient management and quality of life.
