Rectifying Supporting Regions With Mixed and Active Supervision for Rib Fracture Recognition

Huang, Yalin; Liu, Weiping; Wang, Xiuying; Fang, Qu; Wang, Renzhen; Wang, Yi; Chen, Huai; Chen, Hao; Meng, Deyu; Wang, Lisheng

doi:10.1109/tmi.2020.3006138

Cited by 29 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, focus was given to semi and weak supervision learning [15], [17]- [20], either rely on pixel-level or image-level annotations, combined with unlabeled images. The most relevant research to our framework is from [1]- [3], in which the same model with both segmentation and classification output branch is jointly trained on two types of data. Our framework is different from theirs because the end-to-end classification training with entire image input is difficult due to massive size of whole slide images.…”

Section: A Mixed Supervision Learningmentioning

confidence: 99%

“…Pixel-level experiment is conducted based on source code of Mahendra Khened et al [53]. This generalized pathology processing framework is the 5th in Camelyon17 Challenge 1 [16], 4th in DigestPath2019 2 [15] and 3rd in PAIP challenge 3 . It uses all of existing pixellevel fine-grained labels to train patch segmentation model and image-level labels to train whole slide image classification model, without extracting hidden pixel-level pseudo labels.…”

Section: A Experimental Settingmentioning

confidence: 99%

“…Mixed supervision learning on various levels of annotations has shown its effectiveness in various machine learning applications [1]- [3] . However, in the context of computational pathology, this is still a challenging problem, as the highresolution of whole slide images makes it unattainable to conduct end-to-end training of deep learning models using existing weak or mixed supervision learning methods [1], [2], [4]- [12].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hybrid Supervision Learning for Pathology Whole Slide Image Classification

Li¹,

Chen²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Weak supervision learning on classification labels has demonstrated high performance in various tasks. When a few pixel-level fine annotations are also affordable, it is natural to leverage both of the pixel-level (e.g., segmentation) and image level (e.g., classification) annotation to further improve the performance. In computational pathology, however, such weak or mixed supervision learning is still a challenging task, since the high resolution of whole slide images makes it unattainable to perform endto-end training of classification models. An alternative approach is to analyze such data by patch-base model training, i.e., using self-supervised learning to generate pixellevel pseudo labels for patches. However, such methods usually have model drifting issues, i.e., hard to converge, because the noise accumulates during the self-training process. To handle those problems, we propose a mixed supervision learning framework for super high-resolution images to effectively utilize their various labels (e.g., sufficient image-level coarse annotations and a few pixel-level fine labels). During the patch training stage, this framework can make use of coarse image-level labels to refine selfsupervised learning and generate high-quality pixel-level pseudo labels. A comprehensive strategy is proposed to suppress pixel-level false positives and false negatives. Three real-world datasets with very large number of images (i.e., more than 10,000 whole slide images) and various types of labels are used to evaluate the effectiveness of mixed supervision learning. We reduced the false positive rate by around one third compared to state of the art while retaining 100% sensitivity, in the task of image-level classification.

show abstract

Section: A Mixed Supervision Learningmentioning

confidence: 99%

Section: A Experimental Settingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Supervision Learning for Pathology Whole Slide Image Classification

Li¹,

Chen²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Specifically, to obtain varied views of the lesions for the input disentanglement, the first step of our model is to locate the lesion regions. Previous works [18]- [20] highly rely on segmentation labels or bounding boxes for further feature disentanglement. Unfortunately, such substantial annotations of lesions are far more expensive and unavailable in our dataset, where merely category labels are accessible.…”

Section: Introductionmentioning

confidence: 99%

CDNet: Contrastive Disentangled Network for Fine-Grained Image Categorization of Ocular B-Scan Ultrasound

Dan¹,

Li²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Precise and rapid categorization of images in the Bscan ultrasound modality is vital for diagnosing ocular diseases. Nevertheless, distinguishing various diseases in ultrasound still challenges experienced ophthalmologists. Thus a novel contrastive disentangled network (CDNet) is developed in this work, aiming to tackle the fine-grained image categorization (FGIC) challenges of ocular abnormalities in ultrasound images, including intraocular tumor (IOT), retinal detachment (RD), posterior scleral staphyloma (PSS), and vitreous hemorrhage (VH). Three essential components of CDNet are the weaklysupervised lesion localization module (WSLL), contrastive multizoom (CMZ) strategy, and hyperspherical contrastive disentangled loss (HCD-Loss), respectively. These components facilitate feature disentanglement for fine-grained recognition in both the input and output aspects. The proposed CDNet is validated on our ZJU Ocular Ultrasound Dataset (ZJUOUSD), consisting of 5213 samples. Furthermore, the generalization ability of CDNet is validated on two public and widely-used chest X-ray FGIC benchmarks. Quantitative and qualitative results demonstrate the efficacy of our proposed CDNet, which achieves state-ofthe-art performance in the FGIC task. Code is available at: https://github.com/ZeroOneGame/CDNet-for-OUS-FGIC.

show abstract

“…This situation especially exists for chest X-rays (CXR) as the world's commonest medical image. Apart from many unlabeled data, CXR datasets often have image-level annotations that can be easily obtained by text mining from the numerous radiological reports [26,9], while lesion-level annotations (e.g., bounding boxes) are scarce [7,27]. Therefore, efficiently leveraging available annotations to develop thoracic disease detection algorithms has significant practical value.…”

Section: Introductionmentioning

confidence: 99%

OXnet: Omni-supervised Thoracic Disease Detection from Chest X-rays

Luo,

Chen,

Zhou

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Chest X-ray (CXR) is the most typical medical image worldwide to examine various thoracic diseases. Automatically localizing lesions from CXR is a promising way to alleviate radiologists' daily reading burden. However, CXR datasets often have numerous image-level annotations and scarce lesion-level annotations, and more often, without annotations. Thus far, unifying different supervision granularities to develop thoracic disease detection algorithms has not been comprehensively addressed. In this paper, we present OXnet, the first deep omnisupervised thoracic disease detection network to our best knowledge that uses as much available supervision as possible for CXR diagnosis. Besides fully supervised learning, to enable learning from weakly-annotated data, we guide the information from a global classification branch to the lesion localization branch by a dual attention alignment module. To further enhance global information learning, we impose intra-class compactness and inter-class separability with a global prototype alignment module. For unsupervised data learning, we extend the focal loss to be its soft form to distill knowledge from a teacher model. Extensive experiments show the proposed OXnet outperforms competitive methods with significant margins. Further, we investigate omni-supervision under various annotation granularities and corroborate OXnet is a promising choice to mitigate the plight of annotation shortage for medical image diagnosis. 2

show abstract

Rectifying Supporting Regions With Mixed and Active Supervision for Rib Fracture Recognition

Cited by 29 publications

References 27 publications

Hybrid Supervision Learning for Pathology Whole Slide Image Classification

Hybrid Supervision Learning for Pathology Whole Slide Image Classification

CDNet: Contrastive Disentangled Network for Fine-Grained Image Categorization of Ocular B-Scan Ultrasound

OXnet: Omni-supervised Thoracic Disease Detection from Chest X-rays

Contact Info

Product

Resources

About