An Automatic Identification of Lung Cancer from different types of Medical Images

PHF14 (PHD finger protein 14) is associated with Plant Homeodomain (PHD) Finger Protein family. This chromatin-binding protein interacts with histones. PHF14 overexpression has gained attention due to compelling evidence of its involvement in cell proliferation of various cell lines. PHF14 plays a critical function in the induction of pulmonary fibrosis, and actively participate in cell mitosis which makes it a probable target in the treatment of lung fibrosis and can also be utilized as a biomarker in evaluation and management of non small cell lung cancer. A model of PHF14 protein was prepared by homology modelling and was verified by Ramachandran plot. This model of PHF14 protein was acknowledged by Protein Model Data Base (PMDB) and has been assigned PMDB ID: PM0084114. The DrugBank database was used to obtain ligands, to dock against PHF14 by applying PatchDock technique. The structure of the selected ligand (DB08438) was then modified by means of ACD/ChemSketch 8.0 to secure 22 new in silico ligands, which were subjected to the docking procedure. The docking results identify ligand 31 to possess a high binding affinity with the target protein. The in silico docking results suggests that ligands 31, 12, 13, 14, 15, 16, 18, 19, 20, 21, 22, 23, 26, 29, 30, 31, 32, and 33 have a high preference for binding with PHF14 and these compounds should be thoroughly probed so as to develop potential chemical entities for the suppression of malignant transformation and tumorigenicity of non small cell lung cancer.

show abstract

Analysis of CBC and FCMC Clustering approaches for Skin Melanoma Segmentation using Dermoscopic Images

Maniraj

2022

RJPT

View full text Add to dashboard Cite

In this paper, clustering approaches are analyzed for skin lesion segmentation using dermoscopic images. Three widely used machine learning approaches for image segmentation are Centroid-based clustering (CBC). Fuzzy C-Means Clustering (FCMC), and Expectation-Maximization (EM)–E&M step algorithm. The difference between CBC and FCMC lies in the partitioning method. The former one uses hard partitioning, and the later uses a variable degree of membership. In the EM algorithm, statistical methods are employed for distance calculation whereas, in CBC, the Euclidean distance measure is used. The segmentation results of individual clustering approaches are combined to get the refined skin lesion. Results show that the combined segmentation provides promising results for skin lesion segmentation in comparison with CBC, FCMC and EM- M step algorithm.

show abstract

An Automatic Identification of Lung Cancer from different types of Medical Images

Cited by 3 publications

References 16 publications

Lung CT Image Segmentation: A Generalized Framework Based on U-Net Architecture and Preprocessing Models

Lung CT Image Segmentation: A Generalized Framework Based on U-Net Architecture and Preprocessing Models

Structure Prediction and In-silico Designing of Drugs against Plant Homeodomain Finger Protein 14 for Suppression of Malignant Transformation and Tumorigenicity of Non Small Cell Lung Cancer

Analysis of CBC and FCMC Clustering approaches for Skin Melanoma Segmentation using Dermoscopic Images

Contact Info

Product

Resources

About