<i>CCR</i> 20th Anniversary Commentary: Molecular Pathology of <i>ALK</i>-Rearranged Lung Tumors

Iafrate, A. John

doi:10.1158/1078-0432.ccr-14-3130

Cited by 3 publications

(2 citation statements)

References 20 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results indicate that our model successfully identifies regions with signet ring cells (Fig- ures 8a and d), a histological feature commonly associated with ALK-rearranged adenocarcinoma 27,28 . Additionally, the model detects regions with a solid growth pattern (Figures 8b and c), which has been previously linked to ALK-rearrangement in other studies 26,29 .…”

Section: Multiple Instance Mnistsupporting

confidence: 64%

Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio

Wang,

Xu,

Zhao

et al. 2023

Preprint

View full text Add to dashboard Cite

Histopathology image analysis plays a crucial role in cancer diagnosis. However, training a clinically applicable segmentation algorithm requires pathologists to engage in labour-intensive labelling. In contrast, weakly supervised learning methods, which only require coarse-grained labels at the image level, can significantly reduce the labeling efforts. Unfortunately, while these methods perform reasonably well in slide-level prediction, their ability to locate cancerous regions, which is essential for many clinical applications, remains unsatisfactory. Previously, we proposed CAMEL, which achieves comparable results to those of fully supervised baselines in pixel-level segmentation. However, CAMEL requires 1,280×1,280 image-level binary annotations for positive WSIs. Here, we present CAMEL2, by introducing a threshold of the cancerous ratio for positive bags, it allows us to better utilize the information, consequently enabling us to scale up the image-level setting from 1,280×1,280 to 5,120×5,120 while maintaining the accuracy. Our results with various datasets, demonstrate that CAMEL2, with the help of 5,120×5,120 image-level binary annotations, which are easy to annotate, achieves comparable performance to that of a fully supervised baseline in both instance- and slide-level classifications.

show abstract

Section: Multiple Instance Mnistsupporting

confidence: 64%

Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio

Wang,

Xu,

Zhao

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…ALK rearrangements were apparently confined to a subset of peritoneal mesotheliomas and not detected in pleural mesotheliomas in this and other studies (9,21,23). ALK, located on chromosome 2p23, is a pivotal therapeutic target with the use of the small-molecule tyrosine-kinase inhibitor in patients with non-small-cell lung cancers, lymphomas, and other rare soft tissue tumors with ALK rearrangements (24,25). Identification of ALK rearrangement suggests that a subset of patients with peritoneal mesothelioma may be identified by immunohistochemistry for ALK and considered for tyrosine-kinase inhibitor therapy.…”

Section: Alk Rearrangements In Peritoneal Mesotheliomasupporting

confidence: 50%

Novel insights and recent discoveries on the genetics and pathogenesis of malignant mesothelioma

Hung

Chirieac

2018

J. Thorac. Dis.

View full text Add to dashboard Cite

CAMEL2: Enhancing Weakly Supervised Learning for Histopathology Images by Incorporating the Significance Ratio

Xu,

Wang,

Zhao

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

Histopathology image analysis plays a crucial role in cancer diagnosis. However, training a clinically applicable segmentation algorithm requires pathologists to engage in labor‐intensive labeling. In contrast, weakly supervised learning methods, which only require coarse‐grained labels at the image level, can significantly reduce the labeling efforts. Unfortunately, while these methods perform reasonably well in slide‐level prediction, their ability to locate cancerous regions, which is essential for many clinical applications, remains unsatisfactory. Previously, CAMEL is proposed, which achieves comparable results to those of fully supervised baselines in pixel‐level segmentation. However, CAMEL requires 1280 × 1280 image‐level binary annotations for positive WSIs. Here, CAMEL2 is presented, by introducing a threshold of the cancerous ratio for positive bags, it allows one to better utilize the information, consequently enabling us to scale up the image‐level setting from 1280 × 1280 to 5120 × 5120 while maintaining accuracy. The results with various datasets demonstrate that CAMEL2, with the help of 5120 × 5120 image‐level binary annotations, which are easy to annotate, achieves comparable performance to that of a fully supervised baseline in both instance‐ and slide‐level classifications.

show abstract

CCR 20th Anniversary Commentary: Molecular Pathology of ALK-Rearranged Lung Tumors

Cited by 3 publications

References 20 publications

Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio

Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio

Novel insights and recent discoveries on the genetics and pathogenesis of malignant mesothelioma

CAMEL2: Enhancing Weakly Supervised Learning for Histopathology Images by Incorporating the Significance Ratio

Contact Info

Product

Resources

About