Weakly Supervised Brain Lesion Segmentation via Attentional Representation Learning

Wu, Kai; Du, Bowen; Luo, Man; Wen, Hongkai; Shen, Yiran; Feng, Jianfeng

doi:10.1007/978-3-030-32248-9_24

Cited by 31 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the lack of large-scale datasets restricts deep learning models’ full potential, researchers have adopted data augmentation as an immediate solution to the data challenges that are mentioned above. Other works have recently explored weakly-supervised learning [ 106 , 107 , 108 ] as a promising solution to address the need for fully annotated pixel-wise labels. Instead of performing pixel-level annotations, known to be tedious and time-consuming, weakly-supervised annotation uses bounding box or image-level annotations in order to signify the presence or absence of lesions in images.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning for Brain Tumor Segmentation: A Survey of State-of-the-Art

2021

View full text Add to dashboard Cite

Quantitative analysis of the brain tumors provides valuable information for understanding the tumor characteristics and treatment planning better. The accurate segmentation of lesions requires more than one image modalities with varying contrasts. As a result, manual segmentation, which is arguably the most accurate segmentation method, would be impractical for more extensive studies. Deep learning has recently emerged as a solution for quantitative analysis due to its record-shattering performance. However, medical image analysis has its unique challenges. This paper presents a review of state-of-the-art deep learning methods for brain tumor segmentation, clearly highlighting their building blocks and various strategies. We end with a critical discussion of open challenges in medical image analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning for Brain Tumor Segmentation: A Survey of State-of-the-Art

2021

View full text Add to dashboard Cite

show abstract

“…With the development of deep learning, it has evolved into cross-learning with multiple disciplines, especially the medical field. Because of lacking brain's Magnetic Resonance Imaging (MRI) and X-rays images with sufficient labels, weakly-supervised brain lesion detection [75], [76] has received attention from researchers. The purpose of weaklysupervised brain lesion detection is to give the model the SLV [57] √ √ √ ability to accurately locate lesion region and classify lesion category that helps the doctor complete the diagnosis of the disease.…”

Section: B Application Directionsmentioning

confidence: 99%

Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey

Shao¹,

Chen²,

Shao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), i.e., detecting multiple and single instances with bounding boxes in an image using image-level labels, are long-standing and challenging tasks in the CV community. With the success of deep neural networks in object detection, both WSOD and WSOL have received unprecedented attention. Hundreds of WSOD and WSOL methods and numerous techniques have been proposed in the deep learning era. To this end, in this paper, we consider WSOL is a sub-task of WSOD and provide a comprehensive survey of the recent achievements of WSOD. Specifically, we firstly describe the formulation and setting of the WSOD, including the background, challenges, basic framework. Meanwhile, we summarize and analyze all advanced techniques and training tricks for improving detection performance. Then, we introduce the widely-used datasets and evaluation metrics of WSOD. Lastly, we discuss the future directions of WSOD. We believe that these summaries can help pave a way for future research on WSOD and WSOL.

show abstract

“…These proposals are later used as pseudo-masks to train a segmentation network. More recently, image-level labels have also been leveraged to generate initial seeds, i.e., CAMs [31]- [33], which, similar to [7], serve as pseudo-masks in a later step. Knowledgedriven approaches prevail in the medical domain, where the prior-knowledge is typically integrated as an augmented loss function [8], [10], [11], [34].…”

Section: A Weakly Supervised Segmentationmentioning

confidence: 99%

Weakly supervised segmentation with cross-modality equivariant constraints

Patel¹,

Dolz²

2021

Preprint

View full text Add to dashboard Cite

Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class activation maps (CAMs), which can be generated from image-level annotations. Nevertheless, resulting maps have been demonstrated to be highly discriminant, failing to serve as optimal proxy pixel-level labels. We present a novel learning strategy that leverages self-supervision in a multi-modal image scenario to significantly enhance original CAMs. In particular, the proposed method is based on two observations. First, the learning of fully-supervised segmentation networks implicitly imposes equivariance by means of data augmentation, whereas this implicit constraint disappears on CAMs generated with image tags. And second, the commonalities between image modalities can be employed as an efficient self-supervisory signal, correcting the inconsistency shown by CAMs obtained across multiple modalities. To effectively train our model, we integrate a novel loss function that includes a within-modality and a cross-modality equivariant term to explicitly impose these constraints during training. In addition, we add a KL-divergence on the class prediction distributions to facilitate the information exchange between modalities, which, combined with the equivariant regularizers further improves the performance of our model. Exhaustive experiments on the popular multi-modal BRATS dataset demonstrate that our approach outperforms relevant recent literature under the same learning conditions.

show abstract

Weakly Supervised Brain Lesion Segmentation via Attentional Representation Learning

Cited by 31 publications

References 13 publications

Deep Learning for Brain Tumor Segmentation: A Survey of State-of-the-Art

Deep Learning for Brain Tumor Segmentation: A Survey of State-of-the-Art

Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey

Weakly supervised segmentation with cross-modality equivariant constraints

Contact Info

Product

Resources

About