As part of the German Congress of Radiology 2020, a webcast with Dr. David Jean Winkel took place on the topic of “Artificial Intelligence in clinical practice, today and tomorrow”.
Dr. David Jean Winkel from the University Hospital Basel reports on the current status of the use of AI in prostate MRI, talks about the advantages of AI in automatic image acquisition and reporting and ventures an outlook on the future of AI as part of preventive patient care.
In doing so, he addresses the applications of AI in the diagnosis and management of prostate cancer.
The presentation is divided into two parts:
- AI solutions that are already being or can be applied in routine clinical practice: A focus will be placed on Prostate Dot Engine¹, which enables automated image acquisition. Based on this automated image acquisition, Dr. Winkel will present ‘Prostate AI’¹, a software for detection and classification of PI-RADS lesions in prostate MRI examinations.
- Automatically or semi-automatically generated information as input for promising AI solutions of the future: presented here are the ‘AI Pathway Companion’ and a vision for the management of prostate cancer of tomorrow also in terms of patient management.
Today, there is a certain need for reproducible and robust workflows for image acquisition, optimised and fast sequence design and, possibly based on this, automatic detection and classification of tumours with report generation. These parts act as independent for themselves, but are strictly interconnected, as reproducible high image quality is a prerequisite for optimal AI-based analysis.
The ‘Prostate Dot Engine’¹ is suitable for this through, for example, automatic detection of the contour of the prostate with subsequent volumetry of the gland, anatomical landmark recognition using AI and then planning of the ‘Field of View’ and automatic positioning of the image acquisition planes with the ulterior motive of reducing the variability of the image quality.
Gain insights on the importance of improved image acquisition in radiological workflows and watch the recording of the presentation with English subtitles here.
¹ This product is under development and not commercially available. Its future availability cannot be ensured.