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

Data scarcity is common in deep learning models for medical imagesegmentation. Previous works proposed multi-dataset learning, eithersimultaneously or via transfer learning to expand training sets. However,medical image datasets have diverse-sized images and features, and developing amodel simultaneously for multiple datasets is challenging. This work proposesFabric Image Representation Encoding Network (FIRENet), a universalarchitecture for simultaneous multi-dataset segmentation and transfer learninginvolving arbitrary numbers of dataset(s). To handle different-sized image andfeature, a 3D fabric module is used to encapsulate many multi-scalesub-architectures. An optimal combination of these sub-architectures can beimplicitly learnt to best suit the target dataset(s). For diverse-scale featureextraction, a 3D extension of atrous spatial pyramid pooling (ASPP3D) is usedin each fabric node for a fine-grained coverage of rich-scale image features.In the first experiment, FIRENet performed 3D universal bone segmentation ofmultiple musculoskeletal datasets of the human knee, shoulder and hip jointsand exhibited excellent simultaneous multi-dataset segmentation performance.When tested for transfer learning, FIRENet further exhibited excellent singledataset performance (when pre-training on a prostate dataset), as well assignificantly improved universal bone segmentation performance. The followingexperiment involves the simultaneous segmentation of the 10 MedicalSegmentation Decathlon (MSD) challenge datasets. FIRENet demonstrated goodmulti-dataset segmentation results and inter-dataset adaptability of highlydiverse image sizes. In both experiments, FIRENet's streamlined multi-datasetlearning with one unified network that requires no hyper-parameter tuning.

Generalisable 3D Fabric Architecture for Streamlined Universal Multi-Dataset Medical Image Segmentation