Enhancing diagnostic information in abdominal computed tomography (CT) images through optimized image enhancement...

Area of Science:

• Medical Imaging
• Radiology
• Image Processing

Background:

• Accurate detection of abnormalities in computed tomography (CT) scans is crucial for diagnosing conditions like tumors and vascular issues.
• Existing medical image enhancement methods often struggle to balance image quality improvement with the preservation of diagnostic information.

Purpose of the Study:

• To develop and evaluate a novel sequential image enhancement pipeline specifically for abdominal CT scan images.
• To improve contrast, reduce noise, and sharpen structural details in CT images while maintaining diagnostic integrity.

Main Methods:

• A sequential pipeline integrating windowing, contrast-limited adaptive histogram equalization, non-local means denoising, and unsharp masking was proposed.
• The pipeline was evaluated on datasets from The Cancer Imaging Archive and the Medical Segmentation Decathlon.

Main Results:

• The proposed pipeline demonstrated significant improvements in image quality metrics, including a Peak Signal-to-Noise Ratio of 31.79 dB and a Universal Image Quality Index of 0.96.
• Quantitative and qualitative analyses confirmed enhanced contrast, effective noise suppression, and preserved structural details, confirming the method's effectiveness.

Conclusions:

• The novel image enhancement pipeline effectively improves the diagnostic quality of abdominal CT images.
• This approach offers a valuable tool for both clinical diagnosis and research purposes in medical imaging.