Automatic Detection and Classification of Lung Nodules in CT Image Using Optimized Neuro Fuzzy Classifier with Cuckoo...

Area of Science:

• Medical Imaging
• Artificial Intelligence in Oncology
• Computational Pathology

Background:

• Lung nodules are critical indicators of lung cancer, necessitating accurate early detection for improved patient survival.
• Existing methods for lung nodule detection and cancer staging require further accuracy enhancements.

Purpose of the Study:

• To develop an advanced method for lung nodule detection and lung cancer stage classification.
• To improve the accuracy of lung cancer diagnosis through a two-part classification system.

Main Methods:

• A two-part classification system was developed: one for normal/abnormal detection using Naive Bayes, and another for staging using a Neuro Fuzzy classifier with Cuckoo Search.
• Ten features from segmented lung region images were utilized for detection and classification.

Main Results:

• The proposed method demonstrated improved classification accuracy for lung cancer detection and staging.
• Performance was validated through comparison with Support Vector Machine (SVM), Neural Network, and standard Neuro Fuzzy classifiers.

Conclusions:

• The proposed system offers enhanced accuracy in lung nodule detection and lung cancer staging.
• This advancement has the potential to significantly contribute to timely patient treatment and improved survival rates.