|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM355229803 |
| 003 |
DE-627 |
| 005 |
20231226063917.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3234002
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1184.xml
|
| 035 |
|
|
|a (DE-627)NLM355229803
|
| 035 |
|
|
|a (NLM)37018263
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhou, Hong-Yu
|e verfasserin
|4 aut
|
| 245 |
1 |
2 |
|a A Unified Visual Information Preservation Framework for Self-supervised Pre-Training in Medical Image Analysis
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 07.06.2023
|
| 500 |
|
|
|a Date Revised 20.06.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a Recent advances in self-supervised learning (SSL) in computer vision are primarily comparative, whose goal is to preserve invariant and discriminative semantics in latent representations by comparing siamese image views. However, the preserved high-level semantics do not contain enough local information, which is vital in medical image analysis (e.g., image-based diagnosis and tumor segmentation). To mitigate the locality problem of comparative SSL, we propose to incorporate the task of pixel restoration for explicitly encoding more pixel-level information into high-level semantics. We also address the preservation of scale information, a powerful tool in aiding image understanding but has not drawn much attention in SSL. The resulting framework can be formulated as a multi-task optimization problem on the feature pyramid. Specifically, we conduct multi-scale pixel restoration and siamese feature comparison in the pyramid. In addition, we propose non-skip U-Net to build the feature pyramid and develop sub-crop to replace multi-crop in 3D medical imaging. The proposed unified SSL framework (PCRLv2) surpasses its self-supervised counterparts on various tasks, including brain tumor segmentation (BraTS 2018), chest pathology identification (ChestX-ray, CheXpert), pulmonary nodule detection (LUNA), and abdominal organ segmentation (LiTS), sometimes outperforming them by large margins with limited annotations. Codes and models are available at https://github.com/RL4M/PCRLv2
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Lu, Chixiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Chen, Chaoqi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Sibei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yu, Yizhou
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 7 vom: 03. Juli, Seite 8020-8035
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:7
|g day:03
|g month:07
|g pages:8020-8035
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3234002
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 7
|b 03
|c 07
|h 8020-8035
|