Pathological Diversity of Gastric Cancer from the Viewpoint of Background Condition

Abé, Hiroyuki; Ushiku, Tetsuo

doi:10.1159/000519337

Cited by 12 publications

(11 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the limitations of this study is that the deep learning models (both ESD-poorly ADC model and Biopsy-poorly ADC model) false negatively predicted poorly differentiated ADC cells (SRCC cells) in foveolar-type SRCC biopsy and ESD WSIs 3 . In early stage, SRCC cells proliferate predominantly in the proliferative zone (near the mucous neck cells) 38 were consistently false negatively predicted as poorly differentiated ADC. To predict foveolar-type SRCC precisely, we need to collect a number of foveolar-type SRCC biopsy and ESD cases for additional training or active learning 39 .…”

Section: Discussionmentioning

confidence: 99%

Weakly supervised learning for poorly differentiated adenocarcinoma classification in gastric endoscopic submucosal dissection whole slide images

Ichihara

Kanavati²

2022

Preprint

View full text Add to dashboard Cite

The endoscopic submucosal dissection (ESD) is the preferred technique for treating early gastric cancers including poorly differentiated adenocarcinoma without ulcerative findings. The histopathological classification of poorly differentiated adenocarcinoma including signet ring cell carcinoma is of pivotal importance for determining further optimum cancer treatment(s) and clinical outcomes. Because conventional diagnosis by pathologists using microscopes is time-consuming and limited in terms of human resources, it is very important to develop computer-aided techniques that can rapidly and accurately inspect large numbers of histopathological specimen whole-slide images (WSIs). Computational pathology applications which can assist pathologists in detecting and classifying gastric poorly differentiated adenocarcinoma from ESD WSIs would be of great benefit for routine histopathological diagnostic workflow. In this study, we trained the deep learning model to classify poorly differentiated adenocarcinoma in ESD WSIs by transfer and weakly supervised learning approaches. We evaluated the model on ESD, endoscopic biopsy, and surgical specimen WSI test sets, achieving and ROC-AUC up to 0.975 in gastric ESD test sets for poorly differentiated adenocarcinoma. The deep learning model developed in this study demonstrates the high promising potential of deployment in a routine practical gastric ESD histopathological diagnostic workflow as a computer-aided diagnosis system

show abstract

Section: Discussionmentioning

confidence: 99%

Weakly supervised learning for poorly differentiated adenocarcinoma classification in gastric endoscopic submucosal dissection whole slide images

Ichihara

Kanavati²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…One of the limitations of this study is that the deep learning models (both ESD-poorly ADC model and Biopsy-poorly ADC model) false negatively predicted poorly differentiated ADC cells (SRCC cells) in foveolar-type SRCC biopsy and ESD WSIs. 3 In early stage, SRCC cells proliferate predominantly in the proliferative zone (near the mucous neck cells), 47 which were consistently false negatively predicted as poorly differentiated ADC. To predict foveolar-type SRCC precisely, we need to collect a number of foveolar-type SRCC biopsy and ESD cases for additional training or active learning.…”

Section: Discussionmentioning

confidence: 99%

Weakly Supervised Learning for Poorly Differentiated Adenocarcinoma Classification in GastricEndoscopic Submucosal Dissection Whole Slide Images

Kanavati¹

2022

Technol Cancer Res Treat

View full text Add to dashboard Cite

Objective: Endoscopic submucosal dissection (ESD) is the preferred technique for treating early gastric cancers including poorly differentiated adenocarcinoma without ulcerative findings. The histopathological classification of poorly differentiated adenocarcinoma including signet ring cell carcinoma is of pivotal importance for determining further optimum cancer treatment(s) and clinical outcomes. Because conventional diagnosis by pathologists using microscopes is time-consuming and limited in terms of human resources, it is very important to develop computer-aided techniques that can rapidly and accurately inspect large number of histopathological specimen whole-slide images (WSIs). Computational pathology applications which can assist pathologists in detecting and classifying gastric poorly differentiated adenocarcinoma from ESD WSIs would be of great benefit for routine histopathological diagnostic workflow. Methods: In this study, we trained the deep learning model to classify poorly differentiated adenocarcinoma in ESD WSIs by transfer and weakly supervised learning approaches. Results: We evaluated the model on ESD, endoscopic biopsy, and surgical specimen WSI test sets, achieving and ROC-AUC up to 0.975 in gastric ESD test sets for poorly differentiated adenocarcinoma. Conclusion: The deep learning model developed in this study demonstrates the high promising potential of deployment in a routine practical gastric ESD histopathological diagnostic workflow as a computer-aided diagnosis system.

show abstract

“…Gastric cancer remains to be one of the most frequent and fatal cancers in the world, despite the reduction in risk factors such as Helicobacter pylori (1)(2)(3)(4). With the aging of the population, the incidence of gastric cancer will be increasing, and what is worse is that the early disease is hard to be discovered under usual examination; most patients are diagnosed with advanced disease (5,6).…”

Section: Introductionmentioning

confidence: 99%

A-Kinase Interacting Protein 1 Promotes Cell Invasion and Stemness via Activating HIF-1α and β-Catenin Signaling Pathways in Gastric Cancer Under Hypoxia Condition

Luo

2022

Front. Oncol.

View full text Add to dashboard Cite

BackgroundA-Kinase interacting protein 1 (AKIP1) relates to gastric cancer growth, metastasis, and prognosis, while its regulation on gastric cancer invasion and stemness under hypoxia microenvironment is not reported. Therefore, this study aimed to explore this topic to uncover AKIP1’s role in gastric cancer under hypoxia.MethodsGastric cancer cell lines AGS and MKN45 were cultured under hypoxia condition, then transfected with AKIP1 or negative control (NC) overexpression plasmid or AKIP1 or NC knockdown plasmid. Furthermore, rescue experiments were conducted by transfecting HIF-1α or β-catenin overexpression plasmid, combined with AKIP1 or NC knockdown plasmid. Afterward, cell invasion, CD133+ cell proportion, sphere number/1,000 cells, and HIF-1α and β-catenin pathways were measured.ResultsThe invasive cell count, CD133+ cell proportion, and sphere number/1,000 cells were enhanced in both AGS cells and MKN45 cells under hypoxia, and AKIP1 expression was also elevated. AKIP1 knockdown inhibited cell invasion, CD133+ cell proportion, sphere number/1,000 cells, HIF-1α, vascular endothelial growth factor (VEGF), β-catenin, and calcium-binding protein (CBP) expressions in AGS cells and MKN45 cells under hypoxia, while AKIP1 overexpression presented with the opposite effect. Then, in rescue experiments, HIF-1α overexpression and β-catenin overexpression both promoted cell invasion, CD133+ cell proportion, and sphere number/1,000 cells, which also attenuated the effect of AKIP1 knockdown on these functions in AGS cells and MKN45 cells.ConclusionAKIP1 promotes cell invasion and stemness via activating HIF-1α and β-catenin signaling pathways in gastric cancer under hypoxia condition.

show abstract

Pathological Diversity of Gastric Cancer from the Viewpoint of Background Condition

Cited by 12 publications

References 38 publications

Weakly supervised learning for poorly differentiated adenocarcinoma classification in gastric endoscopic submucosal dissection whole slide images

Weakly supervised learning for poorly differentiated adenocarcinoma classification in gastric endoscopic submucosal dissection whole slide images

Weakly Supervised Learning for Poorly Differentiated Adenocarcinoma Classification in GastricEndoscopic Submucosal Dissection Whole Slide Images

A-Kinase Interacting Protein 1 Promotes Cell Invasion and Stemness via Activating HIF-1α and β-Catenin Signaling Pathways in Gastric Cancer Under Hypoxia Condition

Contact Info

Product

Resources

About