Panoramic photoacoustic computed tomography with learning-based classification enhances breast lesion
Xin Tong1, Cindy Z Liu1, Yilin Luo1
1Caltech Optical Imaging Laboratory, Andrew and Peggy Cherng Department of Medical Engineering, Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, USA.
Nature Biomedical Engineering
|June 24, 2025
Summary
Photoacoustic computed tomography (PACT) offers a new, non-invasive method for breast cancer diagnosis. This advanced imaging technique accurately characterizes breast lesions, showing promise as a sensitive tool for evaluation.
Area of Science:
- Biomedical Imaging
- Medical Physics
- Oncology
Background:
- Breast cancer diagnosis faces challenges with current methods like mammography, ultrasound, and MRI due to radiation, low sensitivity in dense breasts, lack of specificity, and high costs.
- Existing imaging modalities have limitations including ionizing radiation, operator dependency, and patient exclusion criteria.
Purpose of the Study:
- To introduce and evaluate a workflow using panoramic Photoacoustic Computed Tomography (PACT) for comprehensive breast lesion characterization.
- To assess PACT's ability to visualize tumor-related vasculature changes irrespective of breast density.
- To develop and validate machine learning models for distinguishing normal from suspicious breast tissue and differentiating malignant from benign lesions.
Main Methods:
- A workflow utilizing panoramic PACT was developed for breast lesion evaluation.
- Learning-based classifiers were trained on PACT features from 78 breasts in 39 patients to differentiate tissue types.
- 13 distinct features were used to differentiate between malignant and benign lesions, and a model was developed for lesion segmentation.
Main Results:
- The PACT-based classifiers achieved a maximum area under the receiver operating characteristic curve of 0.89, comparable to conventional imaging standards.
- PACT provided detailed visualization of vasculature, overcoming limitations associated with breast density.
- The study successfully differentiated malignant and benign lesions and developed a lesion segmentation model.
Conclusions:
- Photoacoustic Computed Tomography (PACT) demonstrates potential as a non-invasive, sensitive, and accurate imaging tool for breast lesion evaluation.
- PACT overcomes limitations of conventional breast imaging techniques, offering high-resolution visualization of vasculature.
- The developed learning-based models show promise for automated breast lesion characterization and segmentation using PACT.
Related Concept Videos
01:27Imaging Studies III: Computed Tomography
56
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
56
01:10Computed Tomography
6.4K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
6.4K