Academic Journal
Advantages of transformer and its application for medical image segmentation: a survey.
| Τίτλος: | Advantages of transformer and its application for medical image segmentation: a survey. |
|---|---|
| Συγγραφείς: | Pu Q; School of Information Engineering, Minzu University of China, Beijing, 100081, China., Xi Z; School of Information Engineering, Minzu University of China, Beijing, 100081, China.; CAS Key Laboratory for Biomedical Effects of Nanomaterials and Nanosafety Institute of High Energy Physics, Chinese Academy of Sciences, Beijing, 100049, China., Yin S; School of Information Engineering, Minzu University of China, Beijing, 100081, China., Zhao Z; The Fourth Medical Center of PLA General Hospital, Beijing, 100039, China., Zhao L; CAS Key Laboratory for Biomedical Effects of Nanomaterials and Nanosafety Institute of High Energy Physics, Chinese Academy of Sciences, Beijing, 100049, China. linazhao@ihep.ac.cn. |
| Πηγή: | Biomedical engineering online [Biomed Eng Online] 2024 Feb 03; Vol. 23 (1), pp. 14. Date of Electronic Publication: 2024 Feb 03. |
| Τύπος έκδοσης: | Journal Article; Review |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: BioMed Central Country of Publication: England NLM ID: 101147518 Publication Model: Electronic Cited Medium: Internet ISSN: 1475-925X (Electronic) Linking ISSN: 1475925X NLM ISO Abbreviation: Biomed Eng Online Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central, [2002- |
| Ιατρικοί όροι (MeSH): | Natural Language Processing* , Neural Networks, Computer*, Technology ; Image Processing, Computer-Assisted |
| Περίληψη: | Purpose: Convolution operator-based neural networks have shown great success in medical image segmentation over the past decade. The U-shaped network with a codec structure is one of the most widely used models. Transformer, a technology used in natural language processing, can capture long-distance dependencies and has been applied in Vision Transformer to achieve state-of-the-art performance on image classification tasks. Recently, researchers have extended transformer to medical image segmentation tasks, resulting in good models. Methods: This review comprises publications selected through a Web of Science search. We focused on papers published since 2018 that applied the transformer architecture to medical image segmentation. We conducted a systematic analysis of these studies and summarized the results. Results: To better comprehend the benefits of convolutional neural networks and transformers, the construction of the codec and transformer modules is first explained. Second, the medical image segmentation model based on transformer is summarized. The typically used assessment markers for medical image segmentation tasks are then listed. Finally, a large number of medical segmentation datasets are described. Conclusion: Even if there is a pure transformer model without any convolution operator, the sample size of medical picture segmentation still restricts the growth of the transformer, even though it can be relieved by a pretraining model. More often than not, researchers are still designing models using transformer and convolution operators. (© 2024. The Author(s).) |
| References: | Radiother Oncol. 2021 Jul;160:175-184. (PMID: 33961914) IEEE Trans Med Imaging. 2019 Feb;38(2):448-459. (PMID: 30716022) Conf Proc IEEE Eng Med Biol Soc. 2005;2005:6492-5. (PMID: 17281756) Int J Biomed Imaging. 2013;2013:154860. (PMID: 24416040) Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018). 2018 Sep;11045:3-11. (PMID: 32613207) Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:3565-3568. (PMID: 34892009) IEEE Trans Med Imaging. 2017 Jul;36(7):1550-1560. (PMID: 28287963) Med Image Anal. 2023 Feb;84:102680. (PMID: 36481607) Comput Biol Med. 2019 Jun;109:218-225. (PMID: 31078126) Br J Ophthalmol. 2010 May;94(5):643-7. (PMID: 20447967) IEEE Trans Med Imaging. 2000 Mar;19(3):203-10. (PMID: 10875704) Biomed Eng Online. 2023 Sep 25;22(1):96. (PMID: 37749595) IEEE Trans Med Imaging. 2019 Oct;38(10):2281-2292. (PMID: 30843824) IEEE Trans Med Imaging. 2004 Apr;23(4):501-9. (PMID: 15084075) BMC Med Imaging. 2023 Sep 15;23(1):129. (PMID: 37715137) Front Bioeng Biotechnol. 2020 Dec 23;8:605132. (PMID: 33425871) Nat Methods. 2019 Dec;16(12):1247-1253. (PMID: 31636459) Neural Netw. 2020 Jan;121:74-87. (PMID: 31536901) Nat Commun. 2022 Jul 15;13(1):4128. (PMID: 35840566) Sensors (Basel). 2023 May 12;23(10):. (PMID: 37430601) Med Image Anal. 2017 Jan;35:489-502. (PMID: 27614792) IEEE Trans Pattern Anal Mach Intell. 2017 Apr;39(4):640-651. (PMID: 27244717) Nat Methods. 2021 Feb;18(2):203-211. (PMID: 33288961) Int J Comput Assist Radiol Surg. 2024 Feb;19(2):273-281. (PMID: 37796413) Med Image Anal. 2014 Feb;18(2):359-73. (PMID: 24418598) Biomed Eng Online. 2021 Sep 23;20(1):94. (PMID: 34556141) Science. 2006 Jul 28;313(5786):504-7. (PMID: 16873662) Comput Methods Biomech Biomed Engin. 2014;17(8):888-904. (PMID: 22994296) J Neurooncol. 2017 May;133(1):27-35. (PMID: 28470431) Comput Methods Programs Biomed. 2012 Oct;108(1):407-33. (PMID: 22525589) Comput Methods Biomech Biomed Engin. 2010;13(2):235-46. (PMID: 19657801) IEEE Trans Med Imaging. 2018 Nov;37(11):2514-2525. (PMID: 29994302) Med Image Anal. 2024 Jan;91:103000. (PMID: 37883822) Biomed Eng Online. 2023 Jul 21;22(1):74. (PMID: 37479991) Comput Biol Med. 2022 Nov;150:105954. (PMID: 36122443) |
| Grant Information: | 2020YFA0710700 National Key Research and Development Program of China; 2021YFA1200904 National Key Research and Development Program of China; 12375326 National Natural Science Foundation of China; 31971311 National Natural Science Foundation of China; E35457U2 Innovation Program for IHEP |
| Contributed Indexing: | Keywords: Codec; Deep learning; Medical image; Segmentation; Transformer |
| Entry Date(s): | Date Created: 20240203 Date Completed: 20240205 Latest Revision: 20240206 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC10838005 |
| DOI: | 10.1186/s12938-024-01212-4 |
| PMID: | 38310297 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!