Razmjooy N., Rajinikanth V. (Eds.) Frontiers of Artificial Intelligence in Medical Imaging

IOP Publishing Ltd, 2022. — 253 p. — (IOP Series in Artificial Intelligence in the Biomedical Sciences). — ISBN 978-0-7503-4010-6.Границы искусственного интеллекта в медицинской визуализации
In the current era, several facilities are employed in the health care domain to support the early diagnosis, appropriate treatment planning, and execution to treat and help the patient to recover from infectious and acute diseases. The traditional disease detection procedures are considerably enhanced by using a range of diagnostic hardware and software. Modern facilities in the health care domain provide the necessary support for humankind to have a disease-free life. Due to significant disease occurrence rates, several automatic disease detection systems are employed in hospitals to support faster disease detection. The traditional methods found in hospitals are still in use along with these methods; recent advancements, such as computerized patient screening, are also adopted to reduce the disease burden. An overview of the modern disease detection schemes present in hospitals is discussed in this chapter1 Health informatics system
2 Medical-imaging-supported disease diagnosis
3 Traditional and AI-based data enhancement Navid Razmjooy and Venkatesan Rajinikanth
4 Computer-aided-scheme for automatic classification of brain MRI slices into normal/Alzheimer’s disease
5 Design of a system for melanoma diagnosis using image processing and hybrid optimization techniques
6 Evaluation of COVID-19 lesion from CT scan slices: a study using entropy-based thresholding and DRLS segmentation
7 Automated classification of brain tumors into LGG/HGG using concatenated deep and handcrafted features
8 Detection of brain tumors in MRI slices using traditional features with AI scheme: a study
9 Framework to classify EEG signals into normal/schizophrenic classes with machine-learning scheme
10 Computerized classification of multichannel EEG signals into normal/autistic classes using image-to-signal transformation