2016
DOI: 10.18632/oncotarget.10053
|View full text |Cite
|
Sign up to set email alerts
|

Novel histopathologic feature identified through image analysis augments stage II colorectal cancer clinical reporting

Abstract: A number of candidate histopathologic factors show promise in identifying stage II colorectal cancer (CRC) patients at a high risk of disease-specific death, however they can suffer from low reproducibility and none have replaced classical pathologic staging. We developed an image analysis algorithm which standardized the quantification of specific histopathologic features and exported a multi-parametric feature-set captured without bias. The image analysis algorithm was executed across a training set (n = 50)… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
20
0

Year Published

2018
2018
2025
2025

Publication Types

Select...
7
2
1

Relationship

4
6

Authors

Journals

citations
Cited by 22 publications
(21 citation statements)
references
References 33 publications
0
20
0
Order By: Relevance
“…Previous research has demonstrated the ability to automatically quantify CD3 + and CD8 + T cells within the TME, thereby achieving a greater level of standardization than with subjective, manual reporting (9). Similarly we have previously shown that tumor budding can be standardized through automated image analysis (12,13). Although the automatic quantification of both immune infiltrate and tumor budding has been associated with patient prognosis, they have not been studied together.…”
Section: Introductionmentioning
confidence: 96%
“…Previous research has demonstrated the ability to automatically quantify CD3 + and CD8 + T cells within the TME, thereby achieving a greater level of standardization than with subjective, manual reporting (9). Similarly we have previously shown that tumor budding can be standardized through automated image analysis (12,13). Although the automatic quantification of both immune infiltrate and tumor budding has been associated with patient prognosis, they have not been studied together.…”
Section: Introductionmentioning
confidence: 96%
“…www.nature.com/scientificreports www.nature.com/scientificreports/ Image analysis for automated TB quantification. Despite the fact that most previous studies have evaluated TB using haematoxylin and eosin (H&E), recent reports have provided meaningful information about TB and disease progression using both immunohistochemistry (IHC) [33][34][35][36] and immunofluorescence (IF) 37,38 . The use of cytokeratin-based immuno-labelling as a tumour mask clearly identifies TB even in cases that display a high density of peri-tumoural inflammatory infiltrate or reactive stromal cells.…”
Section: Discussionmentioning
confidence: 99%
“…For example, studies investigating the greatest linear extent of PDC and total area of PDC have shown early promise. 57,58 Finally, AI-based tools, such as a recently described multiplex-immunohistochemistry-based system, 59 might be leveraged to integrate the assessment of invasive front markers such as PDC, TB and DST into a single unified grading system.…”
Section: Future Directionsmentioning
confidence: 99%