Weakly Supervised Learning For Cell Recognition In Immunohistochemical Cytoplasm Staining Images

Zhang, Shichuan; Zhu, Chenglu; Li, Honglin; Cai, Jiatong; Yang, Lin

doi:10.1109/isbi52829.2022.9761625

Cited by 4 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quantitative comparison results are listed by cell detection and classification as Table .1 shows. In comparison with the model proposed by Zhang et al [17] that performs best among previous cell recognition studies, our model improves the F1 score by 5.68 percent point in cell detection and 5.23 percent point in cell classification, respectively. In addition, the average inference time of the proposed model is nearly 23 times shorter than that of [17], which demonstrates its higher practicality as quantitative TPS calculation requires a wide range of cell recognition with hundreds of patches cropped from a whole-slide image.…”

Section: Resultsmentioning

confidence: 64%

See 1 more Smart Citation

End-to-end cell recognition by point annotation

Shui¹,

Zhang²,

Zhu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Reliable quantitative analysis of immunohistochemical staining images requires accurate and robust cell detection and classification. Recent weakly-supervised methods usually estimate probability density maps for cell recognition. However, in dense cell scenarios, their performance can be limited by pre-and post-processing as it is impossible to find a universal parameter setting. In this paper, we introduce an end-to-end framework that applies direct regression and classification for preset anchor points. Specifically, we propose a pyramidal feature aggregation strategy to combine low-level features and high-level semantics simultaneously, which provides accurate cell recognition for our purely point-based model. In addition, an optimized cost function is designed to adapt our multi-task learning framework by matching ground truth and predicted points. The experimental results demonstrate the superior accuracy and efficiency of the proposed method, which reveals the high potentiality in assisting pathologist assessments.

show abstract

Section: Resultsmentioning

confidence: 64%

“…Multi-task Learning. The success of some previous studies [2,17] of cell recognition shows the advantage of the multi-task strategy in weakly supervised learning. Thus a similar structure is introduced in our recognition framework.…”

Section: Methodsmentioning

confidence: 91%

End-to-end cell recognition by point annotation

Shui¹,

Zhang²,

Zhu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…PCD aims to localize and classify cells in a pathology image, with each cell represented by a class-aware point. Mainstream PCD methods (Abousamra et al 2021;Cai et al 2021;Zhang et al 2022;Ryu et al 2023) operate similarly with density map-based crowd localization approaches but regress multiple density maps, each corresponding to a distinct cell type. Recently, (Shui et al 2022) introduces the advanced P2PNet to perform PCD in an end-to-end manner.…”

Section: Point-based Cell Detectionmentioning

confidence: 99%

“…To reduce the annotation cost while maintaining sufficient clinical support, point-based cell detection (PCD) has emerged as a promising and rapidly evolving frontier in computational pathology (Zhou et al 2018;Huang et al 2020;Abousamra et al 2021;Cai et al 2021;Zhang et al 2022;Ryu et al 2023). The goal of PCD is to predict a 2D point set that represents the coordinates and classes of cells present in an input image.…”

Section: Introductionmentioning

confidence: 99%

DPA-P2PNet: Deformable Proposal-Aware P2PNet for Accurate Point-Based Cell Detection

Shui,

Zheng,

Zhu

et al. 2024

AAAI

View full text Add to dashboard Cite

Point-based cell detection (PCD), which pursues high-performance cell sensing under low-cost data annotation, has garnered increased attention in computational pathology community. Unlike mainstream PCD methods that rely on intermediate density map representations, the Point-to-Point network (P2PNet) has recently emerged as an end-to-end solution for PCD, demonstrating impressive cell detection accuracy and efficiency. Nevertheless, P2PNet is limited to decoding from a single-level feature map due to the scale-agnostic property of point proposals, which is insufficient to leverage multi-scale information. Moreover, the spatial distribution of pre-set point proposals is biased from that of cells, leading to inaccurate cell localization. To lift these limitations, we present DPA-P2PNet in this work. The proposed method directly extracts multi-scale features for decoding according to the coordinates of point proposals on hierarchical feature maps. On this basis, we further devise deformable point proposals to mitigate the positional bias between proposals and potential cells to promote cell localization. Inspired by practical pathological diagnosis that usually combines high-level tissue structure and low-level cell morphology for accurate cell classification, we propose a multi-field-of-view (mFoV) variant of DPA-P2PNet to accommodate additional large FoV images with tissue information as model input. Finally, we execute the first self-supervised pre-training on immunohistochemistry histopathology image data and evaluate the suitability of four representative self-supervised methods on the PCD task. Experimental results on three benchmarks and a large-scale and real-world interval dataset demonstrate the superiority of our proposed models over the state-of-the-art counterparts. Codes and pre-trained weights are available at https://github.com/windygoo/DPA-P2PNet.

show abstract