[Level set method reconciled with a dynamic weighting factor for B-mode ultrasound image segmentation]

Area of Science:

• Medical Imaging
• Image Processing
• Computational Biology

Background:

• Accurate segmentation of lesions in B-type ultrasound images is crucial for diagnosis.
• Existing level set methods can be computationally intensive and may lack precision.

Purpose of the Study:

• To develop a modified level set method for precise and fast segmentation of B-type ultrasound image lesions.
• To improve the accuracy and efficiency of lesion segmentation in ultrasound imaging.

Main Methods:

• The study adapted the region level set method by incorporating information theory's entropy.
• A dynamic weighting factor was introduced, responding to local gray level gradients to guide contour evolution.
• Segmentation calculations were localized to the contour area, reducing computational complexity.

Main Results:

• The proposed method demonstrated improved accuracy in segmenting B-type ultrasound image lesions.
• Experiments showed a significant reduction in time consumption compared to existing level set methods.
• The dynamic weighting factor effectively evaluated lesion contour pixels.

Conclusions:

• The modified level set method with dynamic weighting factors enhances lesion contour evaluation.
• Local calculation strategies significantly improve segmentation efficiency for B-type ultrasound images.
• This approach offers a more precise and faster solution for ultrasound lesion segmentation.