Deep learning on compressed sensing measurements in pneumonia detection

• Published in: International journal of imaging systems and technology 2022-01, Vol.32 (1), p.41-54
• Main Authors: Islam, Sheikh Rafiul, Maity, Santi P., Ray, Ajoy Kumar, Mandal, Mrinal
• Format: Article
• Language: English
• Subjects: autoencoder; CNN; compressed sensing; Deep learning; Disease control; Medical imaging; Pneumonia; pneumonia detection
• ISSN: 0899-9457; 1098-1098
• DOI: 10.1002/ima.22651

Pneumonia is one of the very common life‐threatening diseases and needs proper diagnosis at an early stage to be cured expeditiously. Medical practitioners use chest X‐ray as the best imaging modality to identify pneumonia. Due to the limited facilities available at the remote places and the need of maintaining the social distancing imposed by the recent outbreak of coronavirus disease, one may not have ease of access to a professional radiologist. This article proposes a deep learning (DL) framework that detects pneumonia from X‐ray images to assist the medical practitioners located at distant places. The X‐ray images are captured as compressed sensing (CS) measurements i.e. very few numbers of samples are observed in order to obtain an energy efficient and bandwidth preserving system to be utilized for far‐end pneumonia detection purpose. Extensive simulation results show that the proposed approach enables the detection of pneumonia with 96.48% accuracy when only 30% samples are transmitted.