• Rahul Sawhney

Recent improvements in computers, machine learning, and especially deep learning for image recognition, have greatly assisted the process of automatic sickness detection from chest X-rays (CXRs). This study provides evidence of the usefulness of deep learning-based lung segmentation and bone shadow exclusion techniques for analysis of 2D CXRs in assisting radiologists in the detection of suspicious lesions and nodules in patients with lung cancer. The COUNTY X-RAY dataset (dataset #01) was used for segmentation, whereas the MONTGOMERY COUNTY X-RAY SET dataset (dataset #02) was used for training and validation. Both datasets were identical to the COUNTY X-RAY dataset. The results demonstrate the pre-processing approaches under examination are useful and helpful even in their rudimentary forms. Images which was preprocessed and were abnormal with manifestations of tuberculosis had much better accuracy and loss values after lung segmentation than the other datasets.

deep learning, convolutional neural network, GPU, COUNTY X-RAY, chest X-ray, segmentation, bone shadow exclusion, lung cancer.

"Deep Learning with Lung Segmentation and Bone Shadow Prohibition Methods for Chest X-Ray Investigation of Cellular breakdown in the lungs", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 4, page no.b565-b578, April-2023, Available :http://www.jetir.org/papers/JETIR2304168.pdf

"Deep Learning with Lung Segmentation and Bone Shadow Prohibition Methods for Chest X-Ray Investigation of Cellular breakdown in the lungs", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 4, page no. ppb565-b578, April-2023, Available at : http://www.jetir.org/papers/JETIR2304168.pdf