English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this study, we focus on building up a model that can Segment Anything inmedical scenarios, driven by Text prompts, termed as SAT. Our maincontributions are three folds: (i) on data construction, we combine multipleknowledge sources to construct a multi-modal medical knowledge tree; Then webuild up a large-scale segmentation dataset for training, by collecting over11K 3D medical image scans from 31 segmentation datasets with carefulstandardization on both visual scans and label space; (ii) on model training,we formulate a universal segmentation model, that can be prompted by inputtingmedical terminologies in text form. We present a knowledge-enhancedrepresentation learning framework, and a series of strategies for effectivelytraining on the combination of a large number of datasets; (iii) on modelevaluation, we train a SAT-Nano with only 107M parameters, to segment 31different segmentation datasets with text prompt, resulting in 362 categories.We thoroughly evaluate the model from three aspects: averaged by body regions,averaged by classes, and average by datasets, demonstrating comparableperformance to 36 specialist nnUNets, i.e., we train nnUNet models on eachdataset/subset, resulting in 36 nnUNets with around 1000M parameters for the 31datasets. We will release all the codes, and models used in this report, i.e.,SAT-Nano. Moreover, we will offer SAT-Ultra in the near future, which istrained with model of larger size, on more diverse datasets. Webpage URL:https://zhaoziheng.github.io/MedUniSeg.

One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts