Constrained Deep Weak Supervision for Histopathology Image Segmentation

Jia, Zhang; Huang, Xingyi; Chang, Eric; Xu, Yan

doi:10.1109/tmi.2017.2724070

Cited by 221 publications

(166 citation statements)

References 41 publications

Supporting

Mentioning

165

Contrasting

Unclassified

Order By: Relevance

“…To relieve the demand for theses fine-grained labels, people have proposed many weakly supervised learning algorithms only requiring coarse-grained labels at the imagelevel [13,25,26]. However, due to the lack of sufficient supervision information, the accuracy is much lower than their fully supervised counterparts.…”

Section: Tainmentioning

confidence: 99%

CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation

Gang

Song

Sun³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

126

View full text Add to dashboard Cite

Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive and time-consuming labeling at the pixel level. In this research, we propose CAMEL, a weakly supervised learning framework for histopathology image segmentation using only image-level labels. Using multiple instance learning (MIL)-based label enrichment, CAMEL splits the image into latticed instances and automatically generates instance-level labels. After label enrichment, the instance-level labels are further assigned to the corresponding pixels, producing the approximate pixellevel labels and making fully supervised training of segmentation models possible. CAMEL achieves comparable performance with the fully supervised approaches in both instance-level classification and pixel-level segmentation on CAMELYON16 and a colorectal adenoma dataset. Moreover, the generality of the automatic labeling methodology may benefit future weakly supervised learning studies for histopathology image analysis.

show abstract

Section: Tainmentioning

confidence: 99%

CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation

Gang

Song

Sun³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

126

View full text Add to dashboard Cite

show abstract

“…The WSI texture is examined for the detection of these compulsory class differences. Several studies have been proposed to detect similar fluctuations in the tissue and H&E stained region linkages . These studies have some deficiencies for a complete decision‐making system, such as the fact that cell centers are not identified and the differences among cells are not emphasized, although they are quite satisfactory for tissue detection.…”

Section: Cell‐type Based Semantic Segmentationmentioning

confidence: 99%

Cell‐type based semantic segmentation of histopathological images using deep convolutional neural networks

Öztürk

Akdemïr

2019

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Histopathological whole‐slide image (WSI) analysis is still one of the most important ways to identify regions of cancer risk. For cancer in which early diagnosis is vital, pathologists are at the center of the decision‐making process. Thanks to the widespread use of digital pathology and the development of artificial intelligence methods, automatic histopathological image analysis methods help pathologists in their decision‐making process. In this process, rather than producing labels for whole‐slide image patches, semantic segmentation is very useful, which facilitates the pathologists’ interpretation. In this study, automatic semantic segmentation based on cell type is proposed for the first time in the literature using novel deep convolutional networks structure (DCNN). We presents semantic information on four classes, including white areas in the whole‐slide image, tissue without cells, tissue with normal cells and tissue with cancerous cells. This visual information presented to the pathologist is an easy‐to‐understand picture of the status of the cells and their implications for the spread of cancerous cells. A new DCNN architecture is created, inspired by the residual network and deconvolution network architecture. Our network is trained end‐to‐end manner with histopathological image patches for cell structures to be more discriminative. The proposed method not only produces more successful results than other state‐of‐art semantic segmentation algorithms with 9.2% training error and 88.89% F‐score for test, but also has the most important advantage in that it has the ability to generate automatic information about the cancer and also provides information that pathologists can quickly interpret.

show abstract

“…Thus, any modeling approach needs to be time and memory efficient whilst extracting as much information as possible out of the image. The popular approach adopted to deal with this has been to formulate HIA as a Multiple Instance Learning (MIL) problem: instead of treating images as a single instance, we instead assume it represents a bag of instances [6], [27], [28]. This consists in dividing the histopathology slides into small high resolution patches, sampling randomly from these patches and applying patch level CNNs.…”

Section: Departments Of Medicine and Biomedical Data Science Stanformentioning

confidence: 99%

Deep Recurrent Attention Models for Histopathological Image Analysis

Momeni

Thibault

Gevaert

2018

Preprint

View full text Add to dashboard Cite

Histopathology defines the gold standard in oncology. Automatic analysis of pathology images could thus have a significant impact on diagnoses, prognoses and treatment decisions for cancer patients. Recently, convolutional neural networks (CNNs) have shown strong performance in computational histopathology tasks. However, given it remains intractable to process pathology slides in their entirety, CNNs have traditionally performed inference on small individual patches extracted from the image. This often requires a significant amount of computation and can result in ignoring potentially relevant spatial and contextual information. Being able to process larger input patches and locating discriminatory regions more efficiently could help improve both computational and task specific performance. Inspired by the recent success of Deep Recurrent Attention Models (DRAMs) in image recognition tasks, we propose a novel attention-based architecture for classification in histopathology. Similar to CNNs, DRAMs have a degree of translation invariance built-in, but the amount of computation performed can be controlled independently from the input image size. The model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant areas of large input patches. We evaluate our model on histological and molecular subtype classification tasks for the glioma cohorts of The Cancer Genome Atlas (TCGA). Our results suggest that the DRAM has comparable performance to state-of-the-art CNNs despite only processing a select number of patches.

show abstract

Constrained Deep Weak Supervision for Histopathology Image Segmentation

Cited by 221 publications

References 41 publications

CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation

CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation

Cell‐type based semantic segmentation of histopathological images using deep convolutional neural networks

Deep Recurrent Attention Models for Histopathological Image Analysis

Contact Info

Product

Resources

About