Mammographic quantitative image analysis and biologic image composition for breast lesion characterization and...

Area of Science:

• Radiology and Medical Imaging
• Biomedical Engineering
• Oncology

Background:

• Accurate differentiation between benign and malignant breast lesions is crucial for effective patient management.
• Quantitative Image Analysis (QIA) is an established method for mammographic lesion characterization.
• Novel imaging techniques are needed to enhance diagnostic accuracy in mammography.

Purpose of the Study:

• To evaluate if biologic image composition, assessed via three-compartment breast (3CB) imaging, can improve malignancy probability estimation when combined with mammographic quantitative image analysis (QIA).

Main Methods:

• Dual-energy mammography was used to image 45 breast lesions.
• Lesions were analyzed using QIA alone, 3CB composition measures alone, and a combined QIA + 3CB approach.
• Performance was assessed using Receiver Operating Characteristic (ROC) analysis, comparing the area under the curve (AUC).

Main Results:

• The QIA alone method achieved an AUC of 0.81.
• The 3CB alone method yielded an AUC of 0.72.
• The combined QIA + 3CB method resulted in an AUC of 0.86, showing a trend towards improvement over QIA alone.

Conclusions:

• The three-compartment breast (3CB) imaging modality, when combined with quantitative image analysis (QIA), shows potential additive value in distinguishing benign from malignant breast lesions.
• This pilot study suggests that incorporating breast lesion composition data may enhance mammographic assessments.
• Further research is warranted to validate these findings in larger cohorts.