Automatic computer aided analysis algorithms and system for adrenal tumors on CT images

Area of Science:

• Radiology
• Medical Imaging
• Artificial Intelligence in Medicine

Background:

• Adrenal tumors disrupt adrenocortical cell function, causing various diseases.
• Accurate diagnosis of adrenal tumors is crucial for appropriate treatment planning.
• Current diagnosis relies heavily on experienced radiologists interpreting numerous CT images.

Purpose of the Study:

• To develop an automated computer-aided analysis system for adrenal tumor detection and classification.
• To improve the efficiency and accuracy of adrenal tumor diagnosis.

Main Methods:

• The system integrates automatic segmentation, feature extraction, and classification algorithms.
• Developed using MATLAB Graphical User Interface (GUI).

Main Results:

• The automated system achieved 90% accuracy in segmenting and classifying adrenal tumors.
• Tested on a dataset of 436 CT images.

Conclusions:

• The developed computer-aided analytic system demonstrates stability and reliability.
• Offers a promising tool for objective and efficient adrenal tumor diagnosis.