Enhancing Lung Cancer Classification Using CNN and SVM Methods

The abstract presents a thorough review of the performance metrics of a classification model that was created to distinguish between benign or malignant instances of lung cancer. Precision, which measures how well the model classified positive predictions, performs admirably, showing values of 98.59% for malignant instances and 97.56% for benign cases. The model achieved an outstanding 98.03% overall accuracy on a dataset comprising 7650 photos. Recall, which measures how well the model can recognize true positives, also performs well, scoring 97.22% for malignant instances and 98.77% for benign cases. The harmonic mean of precision or recall, or F1-score, illustrates balanced performance; results for benign instances are 98.16%, while those for malignant patients are 97.90%. The model's ability to correctly diagnose lung cancer in both benign & malignant categories is supported by these measures taken together, indicating that it may be useful for improving clinical decision-making and patient outcomes in the field of oncology. The model is strong and reliable in categorizing lung cancer cases, as demonstrated by the high accuracy, precision, & recall scores. This provides important insights for researchers and medical professionals in their continued search for efficient cancer detection & treatment approaches.