A Weakly Supervised Segmentation Network Embedding Cross-scale Attention Guidance and Noise-sensitive Constraint for Detecting Tertiary Lymphoid Structures of Pancreatic Tumors

by   Bingxue Wang, et al.

The presence of tertiary lymphoid structures (TLSs) on pancreatic pathological images is an important prognostic indicator of pancreatic tumors. Therefore, TLSs detection on pancreatic pathological images plays a crucial role in diagnosis and treatment for patients with pancreatic tumors. However, fully supervised detection algorithms based on deep learning usually require a large number of manual annotations, which is time-consuming and labor-intensive. In this paper, we aim to detect the TLSs in a manner of few-shot learning by proposing a weakly supervised segmentation network. We firstly obtain the lymphocyte density maps by combining a pretrained model for nuclei segmentation and a domain adversarial network for lymphocyte nuclei recognition. Then, we establish a cross-scale attention guidance mechanism by jointly learning the coarse-scale features from the original histopathology images and fine-scale features from our designed lymphocyte density attention. A noise-sensitive constraint is introduced by an embedding signed distance function loss in the training procedure to reduce tiny prediction errors. Experimental results on two collected datasets demonstrate that our proposed method significantly outperforms the state-of-the-art segmentation-based algorithms in terms of TLSs detection accuracy. Additionally, we apply our method to study the congruent relationship between the density of TLSs and peripancreatic vascular invasion and obtain some clinically statistical results.


page 1

page 3

page 4

page 5

page 6

page 7

page 8

page 9


CTG-Net: An Efficient Cascaded Framework Driven by Terminal Guidance Mechanism for Dilated Pancreatic Duct Segmentation

Pancreatic duct dilation indicates a high risk of various pancreatic dis...

PseudoEdgeNet: Nuclei Segmentation only with Point Annotations

Nuclei segmentation is one of the important tasks for whole slide image ...

Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotations

Recently, weakly-supervised image segmentation using weak annotations li...

Weakly-Supervised Semantic Segmentation of Ships Using Thermal Imagery

The United States coastline spans 95,471 miles; a distance that cannot b...

Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss

Accurately segmenting a variety of clinically significant lesions from w...

Automated Peripancreatic Vessel Segmentation and Labeling Based on Iterative Trunk Growth and Weakly Supervised Mechanism

Peripancreatic vessel segmentation and anatomical labeling play extremel...

3D Vessel Segmentation with Limited Guidance of 2D Structure-agnostic Vessel Annotations

Delineating 3D blood vessels is essential for clinical diagnosis and tre...

Please sign up or login with your details

Forgot password? Click here to reset