Analysis of Abdominal Computed Tomography Images for Automatic Liver Cancer Diagnosis Using Image Processing...

Area of Science:

• Medical Imaging
• Computer-Aided Diagnosis
• Artificial Intelligence in Medicine

Background:

• Medical image analysis leverages image processing algorithms for diagnosing organ abnormalities.
• CT imaging is crucial for radiologists and physicians in detecting pathological conditions.

Purpose of the Study:

• To develop an automated computer-aided diagnosis (CAD) system for liver cancer detection from low-contrast CT images.
• To classify liver tumors as malignant or benign prior to segmentation and to quantify tumor burden.
• To enable automatic tumor segmentation and grading using advanced image processing techniques.

Main Methods:

• A novel Fuzzy Linguistic Constant (FLC) was developed for medical image enhancement.
• Fuzzy membership functions and structural similarity index were employed for malignancy classification.
• Morphological image processing techniques were utilized for automatic tumor segmentation and grading.

Main Results:

• The algorithm achieved a 98.3% classification accuracy for liver tumors using Support Vector Machine (SVM).
• The system demonstrated an improved tumor detection rate of 78% with a precision of 0.6.
• Validation was performed on a dataset comprising 179 clinical cases (98 benign, 81 malignant).

Conclusions:

• The developed algorithm provides an efficient tool for radiologists to differentiate between malignant and benign liver tumors.
• The CAD system facilitates automatic tumor segmentation and localization, aiding in diagnosis and surgical planning.
• This methodology supports medical practitioners in liver cancer diagnosis and treatment strategy development.