James Batten
6 Papers
James Batten is an academic researcher. The author has contributed to research in topics: Computer science & Interpolation. The author has an hindex of 1, co-authored 1 publications.
Chat about Author
Papers
•Posted Content
Detecting Outliers with Foreign Patch Interpolation.
TL;DR: This work leverages the natural variations in normal anatomy to create a range of synthetic abnormalities using the same patch region extracted from two independent samples and replaced with an interpolation between both patches.
MOOD 2020: A Public Benchmark for Out-of-Distribution Detection and Localization on Medical Images
David Zimmerer,Peter M. Full,Fabian Isensee,Paul F. Jager,Tim Adler,Jens Petersen,Gregor Köhler,Tobias Roß,Annika Reinke,Antanas Kascenas,Bjørn Sand Jensen,Alison O'Neil,Jeremy Tan,Benjamin Hou,James Batten,Huaqi Qiu,B. Kainz,Nina Shvetsova,Irina Fedulova,Dmitry V. Dylov,Baolun Yu,Jian Yang Zhai,Jingtao Hu,Runxuan Si,Sihang Zhou,Siqi Wang,Xinyang Li,Xuerun Chen,Yang Zhao,Sergio Naval Marimont,Giacomo Tarroni,Victor Saase,Lena Maier-Hein,Klaus H. Maier-Hein +33 more
TL;DR: The Medical-Out-Of-Distribution-Analysis-Challenge (MOOD) is introduced as an open, fair, and unbiased benchmark for OoD methods in the medical imaging domain and shows that performance has a strong positive correlation with the perceived difficulty, and that all algorithms show a high variance for different anomalies, making it yet hard to recommend them for clinical practice.
27
Image To Tree with Recursive Prompting
TL;DR: In this paper , a two-stage model was proposed to predict tree connectivity structure from tree-structured 3D anatomical data, which leverages the UNet and Transformer architectures and introduces an image-based prompting technique.
Vector Representations of Vessel Trees
James Batten,Michiel Schaap,Matthew Sinclair,Ying Bai,Ben Glocker +4 more
Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks
TL;DR: In this article , the authors use multiple visually-distinct synthetic anomaly learning tasks for both training and validation, which enables more robust training and generalisation, which can readily outperform state-of-the-art methods, which demonstrate on exemplars in brain MRI and chest X-rays.