• Utsab Ray
• Jayanta Mallick
• Karabi Ganguly
• Sandip Bag
• Sabyasachi Sen

The study of thoracic diseases and their classification has been one of the most fascinating research subjects in recent years. The quantity of medical picture collections is expanding quickly in to document diseases in hospital due to the different implementations of clinical graphics in medical institutions, pathology, and diagnostic centres. Despite that fact that there have been many studies on this topic, this area is still complex and challenging. The publications did use a variety of classification methods for their medical content. The main drawback of conventional approaches is indeed the semantic gap among high-level corpora observed by people and medical imaging devices' restricted participants expressed. The comprehensive CNN model neuronal network is a new technique that was developed as a result of the challenges associated with processing and querying enormous datasets. Recently, machine vision or medical engineering have benefited greatly from deep learning techniques. In this study, we proposed and examined a robust, fully-connected cognitive intranet for identifying chest diseases. The suggested model consists of pooling, Densenet 121, convolutional, and fully connected layers. There are fifteen output units in the last fully connected layer. One of fifteen disorders will be predicted by each transmitter. A publicly accessible dataset named Chest X-Ray 8 was utilized to train this model. It contains fifteen categories with corresponding labelling but no finding images. The performance of this model in multiclass classification is surprising. The comparative study shows how effective the suggested model is in terms of the ROC curve. For categorising classification digital records for diverse thoracic disorders, the suggested approach is very appropriate.

thoracic, CNN, DenseNet 121, diseases, chest x-ray, ROC Curve, classification.

"EXAMINIATION OF ARTIFICIAL INTELLIGENCE IN IMAGE PROCESSING DEPLOYING DEEP LEARNING TO IDENTIFY ABNORMAL PHYSIOLOGICAL CONDITIONS FROM CHEST XRAY ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.h26-h33, March-2023, Available :http://www.jetir.org/papers/JETIR2303705.pdf

"EXAMINIATION OF ARTIFICIAL INTELLIGENCE IN IMAGE PROCESSING DEPLOYING DEEP LEARNING TO IDENTIFY ABNORMAL PHYSIOLOGICAL CONDITIONS FROM CHEST XRAY ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. pph26-h33, March-2023, Available at : http://www.jetir.org/papers/JETIR2303705.pdf