# Cancer-Analysis-in-R
Initial Multiple Regression Analysis of Color Values in Relation to Mean Area for Cancer Cells

Cancer	

Description

This dataset contains measurements for 167 breast biopsies diagnosed as ductal carcinoma in situ (DCIS) or benign usual ductal hyperplasia (UDH). Measurements were obtained by segmenting each biopsy into nuclei, and recording the area and color of each nuclei. Colors measured using several scales, and measurements were aggregated to the biopsy level by averaging or taking standard deviations across nuclei. The goal of this project is to explore how average nuclear area, which is known to be correlated with malignancy, is correlated with the intensity and variability of different colors in the biopsied tissue.

Source
Data downloaded from https://datadryad.org/stash/dataset/doi:10.5061/dryad.pv85m. Some details explaining the measurements are provided in the corresponding publication, "Computational Pathology to Discriminate Benign from Malignant Intraductal Proliferations of the Breast" which is available here: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0114885.

The data set contains the following columns:
  	Variable 	  	Description
      	ID          		Unique biopsy identifier				
	Mean_Area         	Average nuclear area across nuclei
	ClassGrade		Class (UDH vs. DCIS) and nuclear grade (I-III)    
	ER			Estrogen receptive positive or negative. Unkown if blank.    
	Mean_mean_R    		Average red intensity across nuclei on RGB scale
	Mean_mean_G     	Average green intensity across nuclei on RGB scale
	Mean_mean_B   		Average blue intensity across nuclei on RGB scale
	Mean_mean_HSV    	Average lightness/value across nuclei on HSV scale
	Mean_mean_Lab 		Average lightness across nuclei on Lab and Luv scale
	Mean_mean_HE   		Average lightness across nuclei from H&E color deconvolution
	Mean_mean_BR     	Average lightness across nuclei on BR grey scale
	SD_mean_R     		Standard deviation of red intensity across nuclei on RGB scale
	SD_mean_G     		Standard deviation of green intensity across nuclei on RGB scale
	SD_mean_B   		Standard deviation of blue intensity across nuclei on RGB scale
	SD_mean_HSV   		Standard deviation of lightness/value across nuclei on HSV scale
	SD_mean_Lab   		Standard deviation of lightness across nuclei on Lab and Luv scale
	SD_mean_HE 		Standard deviation of lightness across nuclei from H&E color deconvolution
	SD_mean_BR 		Standard deviation of lightness across nuclei on BR grey scale