SSMD: Semi-Supervised medical image detection with adaptive consistency and heterogeneous perturbation

•We propose a semi-supervised medical image detector with a novel adaptive consistency cost function which takes into account the confidence of proposals at each spatial position.•We develop novel heterogeneous perturbation strategies that consist of two novel components: a noisy residual block for...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Medical image analysis Ročník 72; s. 102117
Hlavní autoři: Zhou, Hong-Yu, Wang, Chengdi, Li, Haofeng, Wang, Gang, Zhang, Shu, Li, Weimin, Yu, Yizhou
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier B.V 01.08.2021
Elsevier BV
Témata:
Ablation
Consistency
Cost function
Image analysis
Image classification
Image detection
Image processing
Image segmentation
Lesion detection
Medical imaging
Motivation
Nuclei detection
Object recognition
Performance enhancement
Perturbation
Predictions
Semi-Supervised learning
Nuclei detection
41A10
65D05
Semi-Supervised learning
65D17
Lesion detection
41A05
ISSN:1361-8415, 1361-8423, 1361-8423
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•We propose a semi-supervised medical image detector with a novel adaptive consistency cost function which takes into account the confidence of proposals at each spatial position.•We develop novel heterogeneous perturbation strategies that consist of two novel components: a noisy residual block for feature space, and an instance-level adversarial perturbation strategy for image space. The proposed heterogeneous perturbation strategies can improve the detection accuracy by enhancing the robustness of image features.•We experimentally verify the effectiveness of the proposed modules. The experiments suggest that the proposed detector outperforms the existing state-of-the-arts considerably. [Display omitted] 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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1361-8415
1361-8423
1361-8423
DOI:10.1016/j.media.2021.102117