Artificial intelligence in acute respiratory distress syndrome: A systematic review.

BACKGROUND AND OBJECTIVE: Acute respiratory distress syndrome (ARDS) is a life-threatening pulmonary disease with a high clinical and cost burden across the globe. Artificial intelligence (AI), an emerging area, has been used for various purposes in ARDS. We aim to summarize the currently available literature on various applications of AI in ARDS through a systematic review. METHODOLOGY: PubMed was searched from inception to February 2021 to collate all the studies. Additionally, a bibliographic search of included studies and a random search on Google, Google Scholar, and Research Gate were performed to identify relevant articles. Studies published in English language that employed data about developing and/or assessing the role of AI in the various aspects of ARDS were considered for this review. Three independent reviewers performed study selection and data extraction; any disagreements were settled through consensus or discussion with another member of the research team. RESULTS: A total of 19 studies published between the year 2002 and 2020 were included. In these included studies, AI was used for various purposes in ARDS such as diagnosis (n = 10; 53 %), risk stratification (n = 1; 5 %), prediction of severity (n = 3; 17 %), management (n = 2; 10 %), prediction of mortality (n = 2; 10 %), and decision making (n = 1; 5 %). The area under the curve among the developed models in the included studies ranged between 0.8 and 1, which is considered to be very good to excellent. CONCLUSION: AI is revolutionizing healthcare and has a wide range of applications in ARDS, such as minimizing cost and enhancing outcomes.

Multiresolution image registration for multimodal brain images and fusion for better neurosurgical planning.

BACKGROUND: Imaging modalities in medicine gives complementary information. Inadequacy in clinical information made single imaging modality insufficient. There is a need for computer-based system that permits rapid acquisition of digital medical images and performs multi-modality registration, segmentation and three-dimensional planning of minimally invasive neurosurgical procedures. In this regard proposed article presents multimodal brain image registration and fusion for better neurosurgical planning. METHODS: In proposed work brain data is acquired from Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) modalities. CT and MRI images are pre-processed and given for image registration. BSpline deformable registration and multiresolution image registration is performed on the CT and MRI sequence. CT is fixed image and MRI is moving image for registration. Later end result is fusion of CT and registered MRI sequences. RESULTS: BSpline deformable registration is performed on the slices gave promising results but on the sequences noise have been introduced in the resultant image because of multimodal and multiresolution input images. Then multiresolution registration technique is performed on the CT and MRI sequence of the brain which gave promising results. CONCLUSION: The end resultant fused images are validated by the radiologists and mutual information measure is used to validate registration results. It is found that CT and MRI sequence with more number of slices gave promising results. Few cases with deformation during misregistrations recorded with low mutual information of about 0.3 and which is not acceptable and few recorded with 0.6 and above mutual information during registration gives promising results.