A Protocol on Artificial Intelligence in Medical Theranosis and Patient Outcome Evaluation: Chemical Bioimaging Fingerprinting by Machine Learning and Deep Learning approaches for Medical Imagics in Theranosis

Theme: Chemical imaging biosensors have emerged as a monitoring tools of theranostic imagics using original medical images obtained from MRI-CT-PET hybrid information to predict the outcome of treatment. Rationale: Early information from chemical molecule images reduces the mortality due to cancer, tumors and dreadful brain, cardiac diseases. Innovation: Machine learning uses large data to have new predictive information while deep learning speculates all details based on previous a priori data information using a multilayered neural network of used datasets. Novelty: The present study proposes a new art of technical developments in nanotracers, hybrid ultrahigh NMR methods using previous NMR application studies by ML and DL as helpful to detect, to classify multiple diseases based on imaging dataset evaluation in making accurate diagnosis and assess the treatment outcome in less time with high specificity and sensitivity.