Enhancing Lung Cancer Detection and Localization with a Hybrid VGG-19 and Adaptive Neuro-Fuzzy Inference System (ANFIS) Approach on Imaging Data

Timely and precise identification and categorization of lung cancer are crucial for improving patient survival rates. Although diagnostic technologies have made progress, the complex characteristics of malignant tumors provide considerable difficulties in analyzing lung images. In this study, a groundbreaking approach is introduced, merging the Adaptive Neuro-Fuzzy Inference System (ANFIS) with the VGG-19 deep learning framework to effectively address these complexities. The model, trained on the varied lung imaging data from the IQ-OTH/NCCD dataset, has exceptional performance in precisely recognizing, predicting, and pinpointing lung cancer symptoms. The VGG-19 model is utilized because of its extensive capacity to extract intricate information from pictures, accurately identifying possible cancers. After extracting the data, ANFIS utilizes a fuzzy logic framework to analyze these features, enabling a detailed identification of cancer patterns that enhances both accuracy and interpretability. This technique combines the advanced capabilities of neural networks with the valuable insights of fuzzy logic, establishing a new standard for accuracy in medical diagnoses. The results of our research show considerable improvements in important diagnostic measures, such as accuracy in classifying, reliability in predicting, and precision in locating. These advancements represent a major progress compared to current diagnostic methods, and underscore the transformative potential of integrating AI with traditional medical imaging techniques.