Artificial Intelligence (AI) is a cutting-edge technology that analyzes complex data using computer algorithms. Diagnostic imaging is one of the most potential clinical uses of AI, and increasing effort is being put toward optimizing its functionality to make a wide range of clinical problems easier to identify and quantify. Research employing computeraided diagnostics has demonstrated exceptional precision, sensitivity, and specificity in identifying minute radiographic irregularities, which has promise for enhancing public health. However, lesion identification is often used to define result assessment in AI imaging research, neglecting the nature and biological aggressiveness of a lesion. This might lead to a distorted portrayal of AI's performance. Some AI imaging research evaluate clinically significant results, whereas others compute sensitivity and specificity to quantify diagnostic accuracy. Though AI frequently picks up on little changes to images, more significant outcome factors include newly discovered advanced disease, illnesses that need to be treated, or circumstances that might have an impact on long-term survival. AI-based research should concentrate on clinically significant events since they have a significant impact on quality of life, such as symptoms, the requirement for disease-modifying medication, and death. Numerous research have demonstrated that AI outperforms normal reading in terms of specificity and recall rates; nevertheless, the kind and biological aggressiveness of a lesion are often overlooked in the estimation of accuracy and sensitivity.