File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.media.2021.102117
- Scopus: eid_2-s2.0-85108272154
- PMID: 34161914
- WOS: WOS:000681131600008
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: SSMD: Semi-Supervised medical image detection with adaptive consistency and heterogeneous perturbation
Title | SSMD: Semi-Supervised medical image detection with adaptive consistency and heterogeneous perturbation |
---|---|
Authors | |
Keywords | Lesion detection Nuclei detection Semi-Supervised learning |
Issue Date | 2021 |
Publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/media |
Citation | Medical Image Analysis, 2021, v. 72, p. article no. 102117 How to Cite? |
Abstract | Semi-Supervised classification and segmentation methods have been widely investigated in medical image analysis. Both approaches can improve the performance of fully-supervised methods with additional unlabeled data. However, as a fundamental task, semi-supervised object detection has not gained enough attention in the field of medical image analysis. In this paper, we propose a novel Semi-Supervised Medical image Detector (SSMD). The motivation behind SSMD is to provide free yet effective supervision for unlabeled data, by regularizing the predictions at each position to be consistent. To achieve the above idea, we develop a novel adaptive consistency cost function to regularize different components in the predictions. Moreover, we introduce heterogeneous perturbation strategies that work in both feature space and image space, so that the proposed detector is promising to produce powerful image representations and robust predictions. Extensive experimental results show that the proposed SSMD achieves the state-of-the-art performance at a wide range of settings. We also demonstrate the strength of each proposed module with comprehensive ablation studies. |
Persistent Identifier | http://hdl.handle.net/10722/302504 |
ISSN | 2023 Impact Factor: 10.7 2023 SCImago Journal Rankings: 4.112 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | ZHOU, HY | - |
dc.contributor.author | Wang, C | - |
dc.contributor.author | Li, H | - |
dc.contributor.author | Wang, G | - |
dc.contributor.author | Zhang, S | - |
dc.contributor.author | Li, W | - |
dc.contributor.author | Yu, Y | - |
dc.date.accessioned | 2021-09-06T03:33:15Z | - |
dc.date.available | 2021-09-06T03:33:15Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Medical Image Analysis, 2021, v. 72, p. article no. 102117 | - |
dc.identifier.issn | 1361-8415 | - |
dc.identifier.uri | http://hdl.handle.net/10722/302504 | - |
dc.description.abstract | Semi-Supervised classification and segmentation methods have been widely investigated in medical image analysis. Both approaches can improve the performance of fully-supervised methods with additional unlabeled data. However, as a fundamental task, semi-supervised object detection has not gained enough attention in the field of medical image analysis. In this paper, we propose a novel Semi-Supervised Medical image Detector (SSMD). The motivation behind SSMD is to provide free yet effective supervision for unlabeled data, by regularizing the predictions at each position to be consistent. To achieve the above idea, we develop a novel adaptive consistency cost function to regularize different components in the predictions. Moreover, we introduce heterogeneous perturbation strategies that work in both feature space and image space, so that the proposed detector is promising to produce powerful image representations and robust predictions. Extensive experimental results show that the proposed SSMD achieves the state-of-the-art performance at a wide range of settings. We also demonstrate the strength of each proposed module with comprehensive ablation studies. | - |
dc.language | eng | - |
dc.publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/media | - |
dc.relation.ispartof | Medical Image Analysis | - |
dc.subject | Lesion detection | - |
dc.subject | Nuclei detection | - |
dc.subject | Semi-Supervised learning | - |
dc.title | SSMD: Semi-Supervised medical image detection with adaptive consistency and heterogeneous perturbation | - |
dc.type | Article | - |
dc.identifier.email | Yu, Y: yzyu@cs.hku.hk | - |
dc.identifier.authority | Yu, Y=rp01415 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.media.2021.102117 | - |
dc.identifier.pmid | 34161914 | - |
dc.identifier.scopus | eid_2-s2.0-85108272154 | - |
dc.identifier.hkuros | 324828 | - |
dc.identifier.volume | 72 | - |
dc.identifier.spage | article no. 102117 | - |
dc.identifier.epage | article no. 102117 | - |
dc.identifier.isi | WOS:000681131600008 | - |
dc.publisher.place | Netherlands | - |