scholarly journals Towards Staining Independent Segmentation of Glomerulus from Histopathological Images of Kidney

2019 ◽  
Author(s):  
Robin Liu ◽  
Lu Wang ◽  
Jim He ◽  
Wenfang Chen
Keyword(s):  
Training Strategy ◽  
Supervised Training ◽  
Inaccurate Data ◽  
Biopsy Specimens ◽  
Slide Image ◽  
Digital Scanning ◽  
Histopathological Images ◽  
Localization Ability ◽  
Weakly Supervised ◽  
Microscopic Slide

AbstractThis paper introduces a detection-based framework to segment glomeruli from digital scanning image of light microscopic slide of renal biopsy specimens. The proposed method aims to better use the precise localization ability of Faster R-CNN and powerful segmentation ability of U-Net. We use a detector to localize the glomeruli from whole slide image to make the segmentation only focus on the most relevant area of the image. We explored the effectiveness of the network depth on its localization and segmentation ability in glomerular classification, and then propose to use the classification network with enhanced ability of localization and segmentation to construct and initialize a segmentation network. We also propose a weakly supervised training strategy to train the segmentation network by taking advantage of the unique morphology of the glomerulus. Both strong initialization and weakly supervised training are used to resolve the problem of insufficient and inaccurate data annotations and enhance the adaptability of the segmentation network. Experimental results demonstrate that the proposed framework is effective and robust.

scholarly journals WSF-NET: Weakly Supervised Feature-Fusion Network for Binary Segmentation in Remote Sensing Image

2018 ◽  
Vol 10 (12) ◽  
pp. 1970 ◽  
Author(s):  
Kun Fu ◽  
Wanxuan Lu ◽  
Wenhui Diao ◽  
Menglong Yan ◽  
Hao Sun ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Feature Fusion ◽  
Class Imbalance ◽  
Remote Sensing Image ◽  
Google Earth ◽  
Training Strategy ◽  
Binary Segmentation ◽  
Supervised Methods ◽  
Weakly Supervised ◽  
The Given

Binary segmentation in remote sensing aims to obtain binary prediction mask classifying each pixel in the given image. Deep learning methods have shown outstanding performance in this task. These existing methods in fully supervised manner need massive high-quality datasets with manual pixel-level annotations. However, the annotations are generally expensive and sometimes unreliable. Recently, using only image-level annotations, weakly supervised methods have proven to be effective in natural imagery, which significantly reduce the dependence on manual fine labeling. In this paper, we review existing methods and propose a novel weakly supervised binary segmentation framework, which is capable of addressing the issue of class imbalance via a balanced binary training strategy. Besides, a weakly supervised feature-fusion network (WSF-Net) is introduced to adapt to the unique characteristics of objects in remote sensing image. The experiments were implemented on two challenging remote sensing datasets: Water dataset and Cloud dataset. Water dataset is acquired by Google Earth with a resolution of 0.5 m, and Cloud dataset is acquired by Gaofen-1 satellite with a resolution of 16 m. The results demonstrate that using only image-level annotations, our method can achieve comparable results to fully supervised methods.

scholarly journals Background Suppression Network for Weakly-Supervised Temporal Action Localization

2020 ◽  
Vol 34 (07) ◽  
pp. 11320-11327 ◽  
Author(s):  
Pilhyeon Lee ◽  
Youngjung Uh ◽  
Hyeran Byun
Keyword(s):  
State Of The Art ◽  
Background Suppression ◽  
Not Given ◽  
Training Strategy ◽  
Training Stage ◽  
Action Localization ◽  
Localization Performance ◽  
Weakly Supervised ◽  
Branch Weight ◽  
Temporal Action

Weakly-supervised temporal action localization is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels: whether each video contains action frames of interest. Previous methods aggregate frame-level class scores to produce video-level prediction and learn from video-level action labels. This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately. In this paper, we design Background Suppression Network (BaS-Net) which introduces an auxiliary class for background and has a two-branch weight-sharing architecture with an asymmetrical training strategy. This enables BaS-Net to suppress activations from background frames to improve localization performance. Extensive experiments demonstrate the effectiveness of BaS-Net and its superiority over the state-of-the-art methods on the most popular benchmarks – THUMOS'14 and ActivityNet. Our code and the trained model are available at https://github.com/Pilhyeon/BaSNet-pytorch.

scholarly journals Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World

2013 ◽  
Vol 1 ◽  
pp. 193-206 ◽  
Author(s):  
Jayant Krishnamurthy ◽  
Thomas Kollar
Keyword(s):  
Language Acquisition ◽  
Natural Language ◽  
Physical Environment ◽  
Question Answering ◽  
Scene Understanding ◽  
Physical World ◽  
Training Procedure ◽  
Supervised Training ◽  
Weakly Supervised ◽  
Logical Semantics

This paper introduces Logical Semantics with Perception (LSP), a model for grounded language acquisition that learns to map natural language statements to their referents in a physical environment. For example, given an image, LSP can map the statement “blue mug on the table” to the set of image segments showing blue mugs on tables. LSP learns physical representations for both categorical (“blue,” “mug”) and relational (“on”) language, and also learns to compose these representations to produce the referents of entire statements. We further introduce a weakly supervised training procedure that estimates LSP’s parameters using annotated referents for entire statements, without annotated referents for individual words or the parse structure of the statement. We perform experiments on two applications: scene understanding and geographical question answering. We find that LSP outperforms existing, less expressive models that cannot represent relational language. We further find that weakly supervised training is competitive with fully supervised training while requiring significantly less annotation effort.

scholarly journals Prediction of BAP1 mutations in uveal melanoma patients from histology images using weakly supervised deep learning-based whole slide image analysis

2021 ◽  
Author(s):  
Garv Mehdiratta ◽  
Sharifa Sahai
Keyword(s):  
Deep Learning ◽  
Uveal Melanoma ◽  
Treatment Options ◽  
Tumor Development ◽  
Suppressor Gene ◽  
Patient Specific ◽  
Slide Image ◽  
Melanoma Patients ◽  
Weakly Supervised ◽  
Genotypic Characteristics

AbstractWhile cases of uveal melanoma are relatively rare overall, it remains the most common intraocular cancer in adults and has a 10-year fatality rate of approximately 50% in metastatic patients with no effective treatment options. Mutations in BAP1, a tumor suppressor gene, have been previously found to be associated with the onset of metastasis in uveal melanoma patients. In this study, we utilize a weakly supervised deep learning-based pipeline in order to analyze whole slide images (WSIs) of uveal melanoma patients in conjunction with slide-level labels regarding the presence of BAP1 mutations. We demonstrate that the model is able to predict relationships between BAP1 mutations and physical tumor development in patients with an optimized mean test AUC of 0.86. Our findings demonstrate that deep learning models are able to accurately predict patient-specific genotypic characteristics in uveal melanoma. Once integrated into existing non-invasive retinal scanner technologies, our model would assist healthcare professionals in understanding the specific genetic profiles of their patients and provide more personalized treatments, thus resulting in improved treatment outcomes.

Sign in / Sign up

Export Citation Format

Share Document