No abstract

This was performed to observe various radiological presentations of lung cancer at the initial evaluation and to elicit correlation to histopathological diagnosis in all patients to a tertiary chest care hospital. AIM: To study various radiological presentations among lung cancer patients Method: we included all the patients with lung cancer reviewed during a 12mth period between March 2012 to November 2014 who had a definite tissue diagnosis and whose staging based on CT thorax were available. RESULTS: 65 patients were evaluated. Right sided lesions predominated with 60% and on left side being 40%. On either side put together, upper lobe 46.15% & middle lobe 36.9% and lower lobe 16.9%.Based on location of tumor 26% of the lesions are peripherally located, 24.5% are central localization, 13.8% are located intermedially. Radiological pattern of presentation: 67% of the cases presented as mass lesions, 9% as obstructive pneumonitis and 23% as combined mass with collapse and 23.07% as pleural effusion. Histological pattern of presentation: squamous cell carcinoma is most common type with 49.23%, adeno 33%, small cell 15%, others 1.5% Most of the cases presented to the hospital in stage IV with 56.36% and stage IIIA 16.36% and stage IIIB as 18.18%. CONCLUSION: we observed most of the lung cancers presented as mass lesion with peripherally located tumor and the most common histological type is squamous cell carcinoma, presented at advanced stages.

No abstract

No abstract

With the ever-rising threat to security, multiple industries are always in search of safer communication techniques both in rest and transit. Multiple security institutions agree that any systems security can be modeled around three major concepts: Confidentiality, Availability, and Integrity. We try to reduce the holes in these concepts by developing a Deep Learning based Steganography technique. In our study, we have seen, data compression has to be at the heart of any sound steganography system. In this paper, we have shown that it is possible to compress and encode data efficiently to solve critical problems of steganography. The deep learning technique, which comprises an auto-encoder with Convolutional Neural Network as its building block, not only compresses the secret file but also learns how to hide the compressed data in the cover file efficiently. The proposed techniques can encode secret files of the same size as of cover, or in some sporadic cases, even larger files can be encoded. We have also shown that the same model architecture can theoretically be applied to any file type. Finally, we show that our proposed technique surreptitiously evades all popular steganalysis techniques.