Lung Cancer Segmentation with Three-Parameter Logistic Type Distribution Model

Lung cancer is the leading cause of mortality in the world affecting both men and women equally. When a radiologist just focuses on the patient’s body, it increases the amount of strain on the radiologist and the likelihood of missing pathological information such as abnormalities are increased. One of the primary objectives of this research work is to develop computer-assisted diagnosis and detection of lung cancer. It also intends to make it easier for radiologists to identify and diagnose lung cancer accurately. The proposed strategy which was based on a unique image feature, took into consideration the spatial interaction of voxels that were next to one another. Using the U-NET+Three parameter logistic distribution-based technique, we were able to replicate the situation. The proposed technique had an average Dice co-efficient (DSC) of 97.3%, a sensitivity of 96.5% and a specificity of 94.1% when tested on the Luna-16 dataset. This research investigates how diverse lung segmentation, juxta pleural nodule inclusion, and pulmonary nodule segmentation approaches may be applied to create Computer Aided Diagnosis (CAD) systems. When we compared our approach to four other lung segmentation methods, we discovered that ours was the most successful. We employed 40 patients from Luna-16 datasets to evaluate this. In terms of DSC performance, the findings demonstrate that the suggested technique outperforms the other strategies by a significant margin.