Answers are grounded in this paper and cite their sources.
Nodule segmentation using enhanced clustering increases accuracy in images, suggesting improved diagnosis.
The early stages of the condition are notoriously difficult to diagnose due to the fact that abnormal cells with dimensions less than very small are notoriously difficult to spot by imaging. If identification occurs at an earlier stage, then there is a chance that the probability of extending the lifespan of the individual may increase. Nevertheless, because of the enormous dimensionality of the database space, timely diagnosis is a challenging task. In this paper, nodule segmentation is proposed using Enhanced Local Information Weighted Intuitionistic Fuzzy C-Means (ELWI-FCM) clustering. After pre-processing, segmentation is performed by ELWI-FCM. To optimize the performance of FCM, the improved Golden Eagle Optimization (IGEO) algorithm is used. For classifying the nodules as normal or affected, the pre-trained DenseNet201 model is utilized. Experiments are conducted over the LIDC-IDRI dataset. Experimental results show that the proposed ELWI-FCM-IGEO attains better accuracy, precision, F1-score, sensitivity, and specificity compared to existing models.
No takes yet. Share an insight, caveat, or question.
Sandhya et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: