Negative Pseudo Labeling Using Class Proportion for Semantic Segmentation in Pathology

Tokunaga, Hiroki; Iwana, Brian Kenji; Teramoto, Yuki; Yoshizawa, Akihiko; Bise, Ryoma

doi:10.1007/978-3-030-58555-6_26

Cited by 19 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Negative Learning aims at decreasing the risk of incorrect information by lowering the probability of negative samples [24,25,34,39], but those negative samples are selected with high confidence. In other words, these methods still utilizes pixels with reliable predictions.…”

Section: Related Workmentioning

confidence: 99%

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Wang¹,

Wang²,

Shen³

et al. 2022

Preprint

View full text Add to dashboard Cite

The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability. We argue that every pixel matters to the model training, even its prediction is ambiguous. Intuitively, an unreliable prediction may get confused among the top classes (i.e., those with the highest probabilities), however, it should be confident about the pixel not belonging to the remaining classes. Hence, such a pixel can be convincingly treated as a negative sample to those most unlikely categories. Based on this insight, we develop an effective pipeline to make sufficient use of unlabeled data. Concretely, we separate reliable and unreliable pixels via the entropy of predictions, push each unreliable pixel to a category-wise queue that consists of negative samples, and manage to train the model with all candidate pixels. Considering the training evolution, where the prediction becomes more and more accurate, we adaptively adjust the threshold for the reliable-unreliable partition. Experimental results on various benchmarks and training settings demonstrate the superiority of our approach over the stateof-the-art alternatives. 1

show abstract

Section: Related Workmentioning

confidence: 99%

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Wang¹,

Wang²,

Shen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Various point-based models [61]- [64] have proven the effectiveness on the nuclei segmentation task. Some recent works [65], [66] utilized the proportion of the tissue as the labels.…”

Section: Annotation Efficient Approachesmentioning

confidence: 99%

WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma

Han¹,

Pan²,

Yan³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…They first used a semisupervised model to detect the center points of all the nuclei, and then designed a weakly supervised model for nuclei segmentation. Tokunaga et al [66] leveraged the proportion of the tissue subtypes to generate pseudo labels. Zhang et al [67] used foreground proportion as the weak labels and then combine FCN and graph convolutional networks (FGNet) for automatic tissue segmentation.…”

Section: B Reducing Annotation Efforts For Medical Image Segmentationmentioning

confidence: 99%

Multi-Layer Pseudo-Supervision for Histopathology Tissue Semantic Segmentation using Patch-level Classification Labels

Han¹,

Lin²,

Mai³

et al. 2021

Preprint

View full text Add to dashboard Cite

Tissue-level semantic segmentation is a vital step in computational pathology. Fully-supervised models have already achieved outstanding performance with dense pixel-level annotations. However, drawing such labels on the giga-pixel whole slide images is extremely expensive and time-consuming. In this paper, we use only patch-level classification labels to achieve tissue semantic segmentation on histopathology images, finally reducing the annotation efforts. We proposed a two-step model including a classification and a segmentation phases. In the classification phase, we proposed a CAM-based model to generate pseudo masks by patch-level labels. In the segmentation phase, we achieved tissue semantic segmentation by our proposed Multi-Layer Pseudo-Supervision. Several technical novelties have been proposed to reduce the information gap between pixellevel and patch-level annotations. As a part of this paper, we introduced a new weakly-supervised semantic segmentation (WSSS) dataset for lung adenocarcinoma (LUAD-HistoSeg). We conducted several experiments to evaluate our proposed model on two datasets. Our proposed model outperforms two state-ofthe-art WSSS approaches. Note that we can achieve comparable quantitative and qualitative results with the fully-supervised model, with only around a 2% gap for MIoU and FwIoU. By comparing with manual labeling, our model can greatly save

show abstract

Negative Pseudo Labeling Using Class Proportion for Semantic Segmentation in Pathology

Cited by 19 publications

References 27 publications

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma

Multi-Layer Pseudo-Supervision for Histopathology Tissue Semantic Segmentation using Patch-level Classification Labels

Contact Info

Product

Resources

About