ComputationalMedicine 28th Oct
Computational medicine challenges in oncology: prostate cancer
A key challenge in clinical medicine is the integration of omics data for the definition of a patient's status and for disease management. Computational medicine sees the “disease” in its complexity from the diagnosis to treatment and patients’ monitoring. The increasing availability of clinical, pathologic, bio-molecular and imaging data, together with the development of algorithms and techniques for data analysis and integrations, has recently led to significant advancement in the field of precision medicine. In this seminar, we will address two key related issues: how can we effectively use the computational tools provided by Artificial Intelligence (AI) in image triage and discuss the role of multidisciplinarity in the delicate process of "making sense of data", i.e. how to move from bench to bedside and support medical decision.
What do physicians expect from computational medicine in prostate cancer? V. Panebianco, DROP, Sapienza University of Rome
Prostate Cancer (PCa) is universally acknowledged as a complex disease, given its multi-factorial etiology involving multiple genetic and environmental factors. Prostate cancer diagnosis has evolved in the last 20 years, with MRI covering a central role in disease diagnosis and staging. Predictive factors of prostate MRI performance are the images quality control, operator expertise and patients’ selection and monitoring. Also, question marks still exist: the possibility of defining screening programs, how to deal with the large number of MR scans expected in the near future, the identification of clinical and imaging biomarkers, and the applicability of multivariate risk prediction tools to personalized prostate cancer management.
PCa management can greatly benefit from CM and AI algorithms since they provides a sound biological interpretation of data and a common language for exploring new research pathways in a rational, highly reliable and reproducible way.
How can AI help in the assessment of the quality of MRI scans? V. Guarrasi, Bioinformatics and precision medicine Group, DIAG, Sapienza University
MRI offers a wide variety of imaging techniques. A large amount of data is created per examination which needs to be checked for sufficient quality in order to derive a meaningful diagnosis. This is a manual process and therefore time- and cost-intensive. Any imaging artifacts originating from scanner hardware, signal processing, or induced by the patient may reduce the image quality and complicate the diagnosis or any image post-processing. Therefore, the assessment or the ensurance of sufficient image quality in an automated manner is of high interest. Here we propose an automated model, using Convolutional Neural Networks to understand if a Prostate MRI Scan satisfies quality standards. The models proposed, focus on the sequences most useful for future diagnostics. Differences in image acquisition techniques and protocols across institutions lead to heterogeneity in imaging quality and make it challenging to use to the full potential of the MRI scans. Manual inspection and visual quality control of each MRI scan are not feasible at a large scale. However, it is important to be able to automatically detect when a scan fails in order to avoid the inclusion of low-quality scans into subsequent analyses which could otherwise lead to incorrect conclusions. AI is expected to massively impact the radiologist’s daily life since it is well situated to become a tool that enhances accuracy and speed.
mercoledì 28 ottobre 2020, ore 15.00 - 17.00
Per partecipare al webinar, è necessario collegarsi al link della stanza virtuale meet.google.com/ppe-rbpd-xpe