Cancer is a generic term for a large group of diseases that can affect any part of the body. Lungs cancer is one of the most common and serious type of cancer. Lung cancer is the leading cause of cancer death worldwide [1]. In US alone, the estimated new lung cancer cases for 2017 are 222, 500 out of which 116, 990 are males and 105, 510 females. Estimated deaths are 155, 870 out of which 84, 590 are male and 71, 280 are female [2]. In India, the estimated cases of men and women in 2012 were 54000 & 17000 respectively [1]. Lungs cancer is a malignant lungs tumor characterized by uncontrolled cell growth in tissues of the lung. If it is left untreated, this growth can spread beyond the lungs by process of metastasis into nearby tissues or other parts of the body [3]. There are mainly two types of lungs cancer small-cell lungs carcinoma (SCLC) and non-small-cell lung carcinoma (NSCLC). NSCLC also categorized into three parts- Adenocarcinoma, Squamous cell carcinoma and Large cell carcinoma. The most common symptoms are coughing up blood, weight loss, shortness of breath, cough that does not go away, coughing up blood, fatigue, losing weight without trying, loss of appetite, shortness of breath and wheezing and chest pain. The vast majority (85%) of cases of lungs cancer are due to long -term tobacco smoking. About 10-15% of cases occur in people who have never smoked but it happened due to genetic factors, exposure to radon gas, asbestos, second hand smoke or other form of air pollution. Lungs cancer may be seen on chest radiographs and computed tomography but diagnosis confirmed by biopsy which is usually performed by bronchoscope or CT or by PET/CT guidance. F18-FDG PET/CT scanning is best for all types of cancers because of better sensitivity and specificity compared to anatomical imaging such as CT as it provides estimates of tumor glucose metabolism [4]. Standardized uptake value (SUV) is the semi-quantitative parameter which can be estimated from F18-FDG PET studies and routinely used for characterizing of the tumor and assessment of treatment response evaluation in these patients. The cut off value of SUV is 3.5 above which tumor is malignant otherwise benign [5]. However, there are many variables such as amount of activity injected, blood glucose level, time of injection and weight of patient, which can affect the estimation of SUV. Hence, majority of nuclear medicine physician rely more on their visual assessment and use it for reporting the F18-FDG PET/CT Scan. Now, the nuclear medicine community is looking for another reliable quantitative parameters extracted from the image that will be used in diagnosis and/or treatment response evaluation. Image processing algorithms have potential to assist in lesion (e.g. nodule) detection on PET/CT studies and to assess the stability or change in size of lesion on serial PET/CT studies. Comparison and evaluation of image processing techniques against each other require common data sets and standardized methods for evaluation. Investigators developing image processing algorithms need standardized databases with which to work. Therefore, there is a need for F18-FDG PET/CT image database as research resource for medical image processing. PET image texture analysis was proposed to characterize the heterogeneity of tumor F18-FDG uptake [6-9, 37]. F18-FDG uptake is not homogeneous across the tumor because of necrosis, cell proliferation, micro vessel density, and hypoxia [6, 10-12]. It has been shown that tumor heterogeneity can be associated with disease progression, response to therapy, and malignant behavior of the tumor [6, 13]. Texture analysis refers to a variety of mathematical methods that may be applied to describe the relationship between the grey level intensity of pixels or voxels and their position within an image. An advantage of measuring textural parameters is that it is a post processing technique that can be applied to data acquired during standard clinical imaging protocols thereby maximizing the information that can be derived from standard clinical images. A number of textural features can be derived that provide a measure of intralesional heterogeneity e.g. angular second moment, inverse difference moment, entropy, correlation etc. [6, 14, 26]. Texture analysis has been extensively used in CT images and has given promising results as a predictor of survival and in treatment response assessment in NSCLC and other carcinomas [15-18, 27], but it is still new and emerging field in PET/CT. Very few studies has been found in the literature in which texture analysis is used in F18-FDG PET/CT scans to predict patient outcome and treatment response in oncology[19-22, 34-36]. However, only one study has been found in literature on the prediction of treatment response of NSCLC using texture analysis in F18-FDG PET/CT scans [22]. Local Binary Pattern (LBP) is a method of texture analysis it is based on small area. It is based on the texture spectrum model and provides an additional statistical approach to texture analysis. In texture spectrum model a concept of texture unit is proposed. The texture unit is defined for each pixel value by the eight neighboring pixels values in a 3x3 matrix. Each neighboring pixel is compared to the central pixel and a texture unit value is assigned accordingly. Neighboring intensities with threshold lower values compared to the reference pixel are marked with 0, intensity values equal or greater than the reference pixel are marked with 1. The texture unit is read in starting from upper left corner of the newly calculated 3x3 matrix proceeding clockwise. The intent of this study is to construct a database of F18-FDG PET/ CT images of lung masses. [ABSTRACT FROM AUTHOR]