BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Cambridge MedAI Seminar - April 2025 - Daniel Kreuter and Dr Ander
  Biguri
DTSTART:20250425T104500Z
DTEND:20250425T120000Z
UID:TALK230251@talks.cam.ac.uk
CONTACT:Hannah Clayton
DESCRIPTION:Sign up on Eventbrite: https://medai_april2025.eventbrite.co.u
 k\n\nJoin us for the *Cambridge AI in Medicine Seminar Series*\, hosted by
  the *Cancer Research UK Cambridge Centre* and the *Department of Radiolog
 y at Addenbrooke’s*. This series brings together leading experts to expl
 ore cutting-edge AI applications in healthcare—from disease diagnosis to
  drug discovery. It’s a unique opportunity for researchers\, practitione
 rs\, and students to stay at the forefront of AI innovations and engage in
  discussions shaping the future of AI in healthcare.\n\nThis month’s sem
 inar will be held on *Friday 25 April 2025\, 12-1pm at the Jeffrey Cheah B
 iomedical Centre (Main Lecture Theatre)\, University of Cambridge* and *st
 reamed online via Zoom*. A light lunch from Aromi will be served from 11:4
 5. The event will feature the following talks:\n\n*_Unlocking Hidden Poten
 tial: Federated Machine Learning on Blood Count Data Enables Accurate Iron
  Deficiency Detection in Blood Donors_ - Daniel Kreuter\, PhD Student\, De
 partment of Applied Mathematics and Theoretical Physics\, University of Ca
 mbridge*\n\nDaniel is a PhD student in the BloodCounts! project\, focusing
  on building algorithms for advanced full blood count analysis to extract 
 additional clinical information from the world's most common medical test.
  His research aims to improve healthcare decision-making through more effi
 cient use of existing data. He is in his final year and is supervised by P
 rof Carola-Bibiane Schönlieb from the Applied Mathematics department and 
 Prof Willem Ouwehand from the department of Haematology. Before coming to 
 Cambridge\, Daniel studied physics at the Technische Universität Darmstad
 t in Germany. His Master's thesis project focused on replacing costly lase
 r-plasma interaction simulations with a much faster neural network model\,
  reducing computation time from 4 hours to a few milliseconds.\n\n*Abstrac
 t:* The full blood count is the world's most common medical laboratory tes
 t\, with 3.6 billion tests performed annually worldwide. Despite this ubiq
 uity\, the rich single-cell flow cytometry data generated by haematology a
 nalysers to calculate standard parameters like haemoglobin and cell counts
  is routinely discarded. Our research demonstrates how AI models can extra
 ct this hidden value\, transforming a routine test into a powerful screeni
 ng tool for iron deficiency in blood donors—with no additional testing r
 equired. Iron deficiency remains a major challenge in blood donation progr
 ams\, affecting donor health and donation efficiency. By applying advanced
  machine learning to previously unused data dimensions within standard blo
 od counts\, we achieve significantly improved detection accuracy compared 
 to conventional parameters. Furthermore\, we show that federated learning 
 enables this approach to scale and generalise across multiple centres whil
 e preserving data privacy. This work exemplifies how AI can enhance existi
 ng medical infrastructure\, extracting new clinical value from already-col
 lected data to improve donor health.\n\n*_Reconstructing extremely low dos
 e CT images using machine learning_ - Dr Ander Biguri\, Senior Research As
 sociate\, Department of Applied Mathematics and Theoretical Physics\, Univ
 ersity of Cambridge*\n\nAnder Biguri received his Ph.D. in Electrical Engi
 neering from the University of Bath in 2018\, for his work on 4D Computed 
 Tomography for radiotherapy. Since\, he has held research positions at Uni
 versity of Southampton\, University College London and lastly University o
 f Cambridge. His research lies in the intersection of inverse problems and
  their applications in real-case scenarios\, such as Positron Emission Tom
 ography or various computed tomography modalities. He is best known for th
 e development of the TIGRE toolbox for applied tomography applications.\n\
 n*Abstract:* ML models can be used to denoise medical images\, however whe
 n doing this we don't use information from the measurements. You can inste
 ad add machine learning to the image formation/reconstruction process\, en
 suring high quality images that still match the measured data from medical
  scanners. In this talk we will briefly see different ways of adding machi
 ne learning to these mathematical processes and discuss the challenges sti
 ll needed to be tackled to make the application of such methods a clinical
  reality.\n\n\nThis is a hybrid event so you can also join via Zoom:\n\nht
 tps://zoom.us/j/99050467573?pwd=UE5OdFdTSFdZeUtIcU1DbXpmdlNGZz09\n\nMeetin
 g ID: 990 5046 7573 and Passcode: 617729\n\nWe look forward to your partic
 ipation! If you are interested in getting involved and presenting your wor
 k\, please email Ines Machado at im549@cam.ac.uk\n\nFor more information a
 bout this seminar series\, see: https://www.integratedcancermedicine.org/r
 esearch/cambridge-medai-seminar-series/
LOCATION:Jeffrey Cheah Biomedical Centre (Main Lecture Theatre)\, Universi
 ty of Cambridge
END:VEVENT
END:VCALENDAR