Cambridge MedAI Seminar Series

Add to your list(s) Download to your calendar using vCal

• Dr. Agnieszka Słowik, Microsoft Research Cambridge and Mariana Lindo, Critical Techworks
• Monday 27 November 2023, 10:00-11:00
• Jeffrey Cheah Biomedical Centre, Puddicombe Way, Cambridge CB2 0AW.

If you have a question about this talk, please contact Ines Machado.

The Cancer Research UK Cambridge Centre and the Department of Radiology at Addenbrooke’s are pleased to announce a seminar series on Artificial Intelligence (AI) in Medicine, which aims to provide a comprehensive overview of the latest developments in this rapidly evolving field. As AI continues to revolutionize healthcare, we believe it is essential to explore its potential and discuss the challenges and opportunities it presents.

The seminar series will feature prominent experts in the field who will share their research and insights on a range of topics, including AI applications in disease diagnosis, drug discovery, and patient care. Each seminar will involve two talks, followed by an interactive discussion with coffee and pastries! We hope that this seminar series will be a valuable platform for researchers, practitioners and students to learn about the latest trends and explore collaborations in the exciting field of AI in Medicine.

The next seminar will be held on the 27th of November 2023, 10am at the Jeffrey Cheah Biomedical Centre (Main Lecture Theatre), University of Cambridge and will feature two talks:

Title: “Turn and face the strange: Out-of-distribution generalisation in machine learning” – Dr. Agnieszka Słowik, Microsoft Research Cambridge

Agnieszka Słowik is a Postdoctoral Researcher working on R&D in robust and responsible AI at Microsoft Research Cambridge. Prior to joining Microsoft, she did her PhD in out-of-distribution generalisation in machine learning at University of Cambridge. During her PhD, she did several research internships at Mila, Meta AI and Microsoft Research, and published at top machine learning venues, such as AISTATS and AAAI .

Abstract: When applied to a new data distribution, machine learning algorithms have been shown to deteriorate. Distribution shifts are caused by spurious correlations that hold at training time but not at test time, changes to the domain, as well as under- and over-representation of certain populations in training data. In this talk, I present two studies in the setting of learning from multiple data sources. In the first study, On Distributionally Robust Optimization and Data Rebalancing, multiple data sources are used to minimise the error on the most challenging data source. In the second study, Linear unit-tests for invariance discovery, I present a set of ‘unit tests’ that validate whether a given algorithm ignores spurious, unstable features that are unlikely to hold in the future, while learning the features that hold across all sources of training data. I conclude with a discussion of potential applications of this research to AI in medicine.

Title: “Development of a Natural Language Processing Multilingual Model for Summarizing Radiology Reports” – Mariana Lindo, Critical Techworks

Mariana Lindo is a Biomedical Engineer specialized in Medical Informatics. She obtained her degree and master’s degree at the University of Minho in Braga, Portugal. During her academic career, she had the opportunity to participate in projects related to AI and health, including the Scientific Talent Grant in Artificial Intelligence awarded by the Calouste Gulbenkian Foundation, where she was able to develop a model based on Generative Adversarial Networks for the generation of X-ray images of difficult-to-detect rib fractures. She also had the opportunity to complete an internship at the Institute for Artificial Intelligence in Medicine in Essen, Germany, as part of the ERASMUS + program, where she focused on developing her dissertation and learned a lot from the institute’s research team. She is currently working as a Data Mastermind at Critical Techworks, a company responsible for the development and construction of BMW vehicles software.

Abstract: The impression section of a radiology report summarizes important radiology findings and plays a critical role in communicating these findings to physicians. However, the preparation of these summaries is time-consuming and error-prone for radiologists. Recently, numerous models for radiology report summarization have been developed. Nevertheless, there is currently no model that can summarize these reports in multiple languages. Such a model could greatly improve future research and the development of Deep Learning models that incorporate data from patients with different ethnic backgrounds. In this study, the generation of radiology impressions in different languages was automated by fine-tuning a model, publicly available, based on a multilingual text-to-text Transformer to summarize findings available in English, Portuguese, and German radiology reports. In a blind test, two board-certified radiologists indicated that for at least 70% of the system-generated summaries, the quality matched or exceeded the corresponding human-written summaries, suggesting substantial clinical reliability. Furthermore, this study showed that the multilingual model outperformed other models that specialized in summarizing radiology reports in only one language, as well as models that were not specifically designed for summarizing radiology reports, such as ChatGPT.

This is a hybrid event so you can also join via Zoom:

https://zoom.us/j/99050467573?pwd=UE5OdFdTSFdZeUtIcU1DbXpmdlNGZz09

Meeting ID: 990 5046 7573 and Passcode: 617729

We look forward to your participation! If you are interested in getting involved and presenting your work, please email Ines Machado at im549@cam.ac.uk

This talk is part of the Cambridge MedAI Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• CCC talks for website
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge MedAI Seminar Series
• Cambridge talks
• Chris Davis' list
• Interested Talks
• Interested Talks
• Jeffrey Cheah Biomedical Centre, Puddicombe Way, Cambridge CB2 0AW
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.