Adaptive Elastic Loss Based on Progressive Inter-Class Association for Cervical Histology Image Segmentation

Zhu, Meng; Zhao, Zhicheng; Su, Fei; Wang, Weibao

doi:10.1109/icassp40776.2020.9053232

Cited by 2 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the pleasurable results, *Corresponding author: yfgao@zzu.edu.cn handcrafted features are not generalizable and fail to capture the inherent structures. Under the guidance of pixel-level labeled images, some methods on the basis of pure deep convolutional neural networks (DCNNs) were developed and achieved performance comparable to pathologists 7,8 . Nevertheless, the pixel-wise annotation task is quite difficult because of the subjective grading criteria and huge size of whole slide images (WSIs).…”

Section: Introductionmentioning

confidence: 99%

Weakly supervised deep learning for cervical histopathology images analysis

Shi

Xu²,

Zhang³

et al. 2022

Fourteenth International Conference on Digital Image Processing (ICDIP 2022)

View full text Add to dashboard Cite

Cervical cancer is the second most common malignancy in women, while is prevented through diagnosing and treating cervical precancerous lesions. Clinically, histopathological image analysis is recognized as the gold standard for diagnosis. However, the diagnosis of cervical precancerous lesions is challenging due to the massive size of whole slide images and subjective grading without precise quantification criteria. Most existing computer aided diagnosis approaches are patches-based, first learning patch-wise features and then aggregating these local features to infer the final prediction. Cropping pathology images into patches restrains the contextual information available to those networks, causing failing to learn clinically relevant structural representations. To address the above problems, this paper proposes a novel weakly supervised learning method called general attention network (GANet) for grading cervical precancerous lesions. A bag-of-instances pattern is introduced to overcome the limitation of the high resolution of whole slide images. Moreover, based on two transformer blocks, the proposed model is able to encode the dependencies among bags and instances that are beneficial to capture much more informative contexts, and thus produce more discriminative WSI descriptors. Finally, extensive experiments are conducted on a public cervical histology dataset and the results show that GANet achieves the state-of-the-art performance.

show abstract

Section: Introductionmentioning

confidence: 99%