SwePub
Sök i LIBRIS databas

  Utökad sökning

WFRF:(Wang Jiancong)
 

Sökning: WFRF:(Wang Jiancong) > (2023) > Deep label fusion :...

LIBRIS Formathandbok  (Information om MARC21)
FältnamnIndikatorerMetadata
00004375naa a2200433 4500
001oai:lup.lub.lu.se:53c73c19-a7bf-4469-bcac-c33fe9cfbfd2
003SwePub
008230124s2023 | |||||||||||000 ||eng|
0247 a https://lup.lub.lu.se/record/53c73c19-a7bf-4469-bcac-c33fe9cfbfd22 URI
0247 a https://doi.org/10.1016/j.media.2022.1026832 DOI
040 a (SwePub)lu
041 a engb eng
042 9 SwePub
072 7a art2 swepub-publicationtype
072 7a ref2 swepub-contenttype
1001 a Xie, Longu University of Pennsylvania4 aut
2451 0a Deep label fusion : A generalizable hybrid multi-atlas and deep convolutional neural network for medical image segmentation
264 1b Elsevier BV,c 2023
520 a Deep convolutional neural networks (DCNN) achieve very high accuracy in segmenting various anatomical structures in medical images but often suffer from relatively poor generalizability. Multi-atlas segmentation (MAS), while less accurate than DCNN in many applications, tends to generalize well to unseen datasets with different characteristics from the training dataset. Several groups have attempted to integrate the power of DCNN to learn complex data representations and the robustness of MAS to changes in image characteristics. However, these studies primarily focused on replacing individual components of MAS with DCNN models and reported marginal improvements in accuracy. In this study we describe and evaluate a 3D end-to-end hybrid MAS and DCNN segmentation pipeline, called Deep Label Fusion (DLF). The DLF pipeline consists of two main components with learnable weights, including a weighted voting subnet that mimics the MAS algorithm and a fine-tuning subnet that corrects residual segmentation errors to improve final segmentation accuracy. We evaluate DLF on five datasets that represent a diversity of anatomical structures (medial temporal lobe subregions and lumbar vertebrae) and imaging modalities (multi-modality, multi-field-strength MRI and Computational Tomography). These experiments show that DLF achieves comparable segmentation accuracy to nnU-Net (Isensee et al., 2020), the state-of-the-art DCNN pipeline, when evaluated on a dataset with similar characteristics to the training datasets, while outperforming nnU-Net on tasks that involve generalization to datasets with different characteristics (different MRI field strength or different patient population). DLF is also shown to consistently improve upon conventional MAS methods. In addition, a modality augmentation strategy tailored for multimodal imaging is proposed and demonstrated to be beneficial in improving the segmentation accuracy of learning-based methods, including DLF and DCNN, in missing data scenarios in test time as well as increasing the interpretability of the contribution of each individual modality.
650 7a TEKNIK OCH TEKNOLOGIERx Medicinteknikx Medicinsk bildbehandling0 (SwePub)206032 hsv//swe
650 7a ENGINEERING AND TECHNOLOGYx Medical Engineeringx Medical Image Processing0 (SwePub)206032 hsv//eng
653 a Deep learning
653 a Generalization
653 a Multi-atlas segmentation
653 a Multimodal image analysis
7001 a Wisse, Laura E.M.u Lund University,Lunds universitet,Diagnostisk radiologi, Lund,Sektion V,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Diagnostic Radiology, (Lund),Section V,Department of Clinical Sciences, Lund,Faculty of Medicine4 aut0 (Swepub:lu)la3343wi
7001 a Wang, Jiancongu University of Pennsylvania4 aut
7001 a Ravikumar, Sadhanau University of Pennsylvania4 aut
7001 a Khandelwal, Pulkitu University of Pennsylvania4 aut
7001 a Glenn, Trevoru University of Pennsylvania4 aut
7001 a Luther, Anicau Lund University4 aut
7001 a Lim, Sydneyu University of Pennsylvania4 aut
7001 a Wolk, David A.u University of Pennsylvania4 aut
7001 a Yushkevich, Paul A.u University of Pennsylvania4 aut
7102 a University of Pennsylvaniab Diagnostisk radiologi, Lund4 org
7730 t Medical Image Analysisd : Elsevier BVg 83q 83x 1361-8415
8564 u http://dx.doi.org/10.1016/j.media.2022.102683y FULLTEXT
8564 8u https://lup.lub.lu.se/record/53c73c19-a7bf-4469-bcac-c33fe9cfbfd2
8564 8u https://doi.org/10.1016/j.media.2022.102683

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy