2018
DOI: 10.1186/s13000-018-0739-3
|View full text |Cite
|
Sign up to set email alerts
|

Automatic evaluation of tumor budding in immunohistochemically stained colorectal carcinomas and correlation to clinical outcome

Abstract: BackgroundTumor budding, meaning a detachment of tumor cells at the invasion front of colorectal carcinoma (CRC) into single cells or clusters (<=5 tumor cells), has been shown to correlate to an inferior clinical outcome by several independent studies. Therefore, it has been discussed as a complementary prognostic factor to the TNM staging system, and it is already included in national guidelines as an additional prognostic parameter. However, its application by manual evaluation in routine pathology is hampe… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
35
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 42 publications
(37 citation statements)
references
References 37 publications
2
35
0
Order By: Relevance
“…A second operation then is added to this phase, which is aimed at reducing the number of false positives and carried out with the help of deep learning-based algorithms. Weis et al [23] follow a similar protocol for immunohistochemistry stained TMA cores. Both authors show promising results but need further validation before implementation in daily clinical routine.…”
Section: Discussionmentioning
confidence: 99%
“…A second operation then is added to this phase, which is aimed at reducing the number of false positives and carried out with the help of deep learning-based algorithms. Weis et al [23] follow a similar protocol for immunohistochemistry stained TMA cores. Both authors show promising results but need further validation before implementation in daily clinical routine.…”
Section: Discussionmentioning
confidence: 99%
“…In colorectal carcinomas, Weis et al. [59] utilized CNN to obtain the absolute number of tumor budding based on cytokeratin‐stained WSIs and demonstrated the correlation between the number of budding hotspots and the status of lymph node. It has been reported that the kind and amount of tumor‐infiltrating immune cells are related with the sensitivity to immunotherapy and prognostic stratification for tumor patients [60, 61].…”
Section: Application Of Dl‐based Ai In Tumor Pathologymentioning
confidence: 99%
“…Deep learning for automated TB analysis. While our approach for tumour bud quantification builds on our own prior original and generic methods for IF image analysis 27,28 , Weis et al recently proposed an application specific approach to recognise TB in IHC images of colorectal carcinoma based on classification convolution neural networks 41 . We believe that the two approaches differ in both their aim and their methodology.…”
Section: Cox Regressionmentioning
confidence: 99%
“…3a.iv). In summary, while Weis et al 41 relies on colour information and heuristic rules to segment the tumour object and on deep learning for classification, we rely from the start on deep learning to segment the tumour objects and on the definition of tumour buds for their classification. Regarding the aim, we believe that utilising the explicit detection of nuclei and the explicit segmentation of tumour from stromal regions makes our approach more generic and usable in studies outwith specific tumour bud quantification.…”
Section: Cox Regressionmentioning
confidence: 99%