Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization

Artificial intelligence (AI) is the most discussed and intriguing topic nowadays in many fields, including medicine and, in particular, medical image analysis.

The different peculiarities of AI, such as features extraction, patterns recognition, classification, when applied to medical image analysis yield fundamental information useful to help the doctor in formulating diagnoses and following the evolution of the disease during treatments. In fact, AI, and specifically machine learning, provides a possibility to monitor patients and quickly identify all the changes in their condition. This is mandatory in those pathologies in which diagnosis and intervention time plays a fundamental role, like in tumour, in neurodegenerative pathologies, and so on.

The possibility of processing massive amounts of data in limited time allows to recognize complex patterns in image data, as well as to identify disease characteristics that could be overlooked by a tired or insufficiently trained eye.

Applications of AI in classical medical images analysis have already provided interesting results, adapting methodologies and algorithms to the specificities of the images; nevertheless, there are still challenges to be faced, as how to organise and preprocess data collected by different institutions with different protocols and how to improve image data sharing, with data and privacy security.

The possibility of processing a massive amount of data and extracting organised information is a challenge in any field of everyday life, but it is of growing importance when dealing with the health of the population. In almost all the diagnostic procedures, diagnosis is formulated on the basis of images acquired with different technological devices so having peculiar visive characteristics: radiography, echography, CT, MRI, and so on, each requiring a specific human training for an effective interpretation. The need for early diagnosis for a fast disease identification suggests supporting the doctor with an effective and easy to use tool that allows classification based on the analysis of medical images and data processing. The continuous collection of historical medical images represents the knowledge from experience, to be improved time by time, thus yielding updated and focused algorithms.

The main topics suggested are:

• Artificial intelligence methods for diagnostic images: how to adapt and implement general purpose methods to medical image analysis.
• Artificial intelligence in image analysis for cancer diagnosis and prognosis: the possibility of early detection of cancer even when hidden to human eyes and to monitor the therapies effects.
• Artificial intelligence in image analysis for disease prediction and treatment selection: the possibility, based on historical data, of predicting disease evolution as well as suggesting suitable treatment.
• Shared data basis construction for deep learning analysis, classification and diagnosis.
• Optimization of image acquisition for A.I. analysis

Keywords

• Diagnostic images
• Images classification
• Machine learning for image databases
• A.I. in visual diagnostics
• Disease evolution prediction

---

Guest Advisors

Prof. Daniela Iacoviello has been Associate Professor in Control Engineering in Sapienza University of Rome, in the Department of Computer, Control and Management Engineering since 2020. She is member of the Editorial Board of Control Engineering and Practice, Journal of Control, Automation and Systems and associate Editor for Europe of Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization and member of the Program Committee of many international Conferences. Since 2002 she has been professor in automatic control and control in biological systems for the courses in Clinical and Biomedical Engineering. Her main research interests are in optimal control, image analysis, modeling and identification with more than 120 published papers and H -index 22.

Prof. Paolo Di Giamberardino is Associate Professor in Control Engineering at the Department of Computer, Control and Management Engineering A. Ruberti. Md in Electronic Engineering and PhD in Systems Engineering from Sapienza University of Rome. He has published numerous articles (98 on Scopus, 645 citations, H-index 15). Member of the Editorial Board of international journals, editor of special issues, member of the technical/scientific committee of international conferences, organiser of international conferences. Main research interests: analysis and control of non-linear discrete time or continuous systems under sampling; planning, control and coordination of mobile robots; control and communication for fixed and mobile networks of sensors; vision systems for robot control; systems for e-learning and for remote measurement, monitoring and control; modelling, measurement and optimal control in complex biomedical systems (epidemics spread, medical diagnostics), machine learning applications in engineering and biomedical systems.

Disclosure statement: Prof. Daniela Iacoviello and Prof. Paolo Di Giamberardino declare there is no conflict of interest.

­­All manuscripts submitted to this Article Collection will undergo a full peer-review; the Guest Advisor for this Collection will not be handling the manuscripts (unless they are an Editorial Board member).

Please review the journal scope and author submission instructions prior to submitting a manuscript.

Please contact Zhiyuan Zhang at [email protected] with any queries and discount codes regarding this Article Collection.

Please be sure to select the appropriate Article Collection from the drop-down menu in the submission system.

Instructions for AuthorsSubmit an Article