Daniel Coelho de Castro

Daniel Coelho de Castro

Auto-generated profile, based on publicly available information

Daniel Coelho de Castro

Microsoft Health Futures, Cambridge, UK

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 July 2020 in Nature Communications
Verified
Journal Article
Open access
PDF file
DCDaniel C. Castro
Daniel C. Castro
IWIan Walker
Ian Walker
BGBen Glocker
Ben Glocker
Causal reasoning can shed new light on the major challenges in machine learning for medical imaging: scarcity of high-quality annotated data and mismatch between the development dataset and the target environment. A causal perspective on these issues allows decisions about data collection, annotation, preprocessing, and learning strategies to be made and scrutinized more transparently, while providing a detailed categorisation of potential biases and mitigation techniques. Along with worked clinical examples, we highlight the importance of establishing the causal relationship between images and their annotations, and offer step-by-step recommendations for future studies.

29 October 2022
Verified
Book Chapter
Closed access
PDF file
BBBenedikt Boecking
Benedikt Boecking
NUNaoto Usuyama
Naoto Usuyama
SBShruthi Bannur
Shruthi Bannur
DCDaniel C. Castro
Daniel C. Castro
ASAnton Schwaighofer
Anton Schwaighofer
OOOzan Oktay
Ozan Oktay

13 January 2025 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
FPFernando Pérez-García
Fernando Pérez-García
HSHarshita Sharma
Harshita Sharma
SBSam Bond-Taylor
Sam Bond-Taylor
KBKenza Bouzid
Kenza Bouzid
VSValentina Salvatelli
Valentina Salvatelli
OOOzan Oktay
Ozan Oktay

15 February 2024 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
CJCharles Jones
Charles Jones
DCDaniel C. Castro
Daniel C. Castro
FRFabio De Sousa Ribeiro
Fabio De Sousa Ribeiro
OOOzan Oktay
Ozan Oktay
MMMelissa McCradden
Melissa McCradden
BGBen Glocker
Ben Glocker

11 May 2024
Verified
Conference Paper
Open access
NYNur Yildirim
Nur Yildirim
HRHannah Richardson
Hannah Richardson
MWMaria Teodora Wetscherek
Maria Teodora Wetscherek
JBJunaid Bajwa
Junaid Bajwa
JJJoseph Jacob
Joseph Jacob
Anja ThiemeAnja Thieme
Anja Thieme
Recent advances in AI combine large language models (LLMs) with vision encoders that bring forward unprecedented technical capabilities to leverage for a wide range of healthcare applications. Focusing on the domain of radiology, vision-language models (VLMs) achieve good performance results for tasks such as generating radiology findings based on a patient’s medical image, or answering visual questions (e.g., “Where are the nodules in this chest X-ray?”). However, the clinical utility of potential applications of these capabilities is currently underexplored. We engaged in an iterative, multidisciplinary design process to envision clinically relevant VLM interactions, and co-designed four VLM use concepts: Draft Report Generation, Augmented Report Review, Visual Search and Querying, and Patient Imaging History Highlights. We studied these concepts with 13 radiologists and clinicians who assessed the VLM concepts as valuable, yet articulated many design considerations. Reflecting on our findings, we discuss implications for integrating VLM capabilities in radiology, and for healthcare AI more generally.

26 June 2025 in NEJM AI
Verified
Journal Article
Closed access
DCDaniel Coelho de Castro
Daniel Coelho de Castro
ABAurelia Bustos
Aurelia Bustos
SBShruthi Bannur
Shruthi Bannur
SHStephanie L. Hyland
Stephanie L. Hyland
KBKenza Bouzid
Kenza Bouzid
Antonio PertusaAntonio Pertusa
Antonio Pertusa