Diagnostic variability in the histopathological assessment of advanced colorectal adenomas and early colorectal cancer in a screening population

Smits, Lisanne J H; Vink‐Börger, Elisa; Lijnschoten, Gesina van; Focke-Snieders, Isabelle; Post, Rachel S. van der; Tuynman, Jurriaan B.; Grieken, Nicole C.T. van; Nagtegaal, Irıs D.

doi:10.1111/his.14601

Cited by 27 publications

(37 citation statements)

References 23 publications

(90 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, a diagnosis of adenocarcinoma was changed to high grade dysplasia with pseudoinvasion in two cases. 7 Interobserver agreement was found to be better between panel members than between the panels and the referrers. 6,7 This is similar to previous studies and presumably reflects the greater levels of experience in the assessment of these polyps by panel members, who will be specialist gastrointestinal pathologists.…”

mentioning

confidence: 91%

“…7 Interobserver agreement was found to be better between panel members than between the panels and the referrers. 6,7 This is similar to previous studies and presumably reflects the greater levels of experience in the assessment of these polyps by panel members, who will be specialist gastrointestinal pathologists. 10 The English panel was set up with three members in order to maximize the chance of creating an opinion that is at least a consensus based on a 2:1 majority.…”

mentioning

confidence: 91%

“…However, Smits et al estimated that the discrepancies observed between their panel and referring pathologists had potential clinical consequences in 15% of adenomas and 32% of adenocarcinomas (to the nearest whole percent). 7 In conclusion, the studies by Bateman et al and Smits et al illustrate the value of expert opinion in bowel cancer screening-derived histopathology and highlight the utility of pathology panels for achieving consensus in difficult cases. 6,7 Conflicts of interest None.…”

mentioning

confidence: 91%

“…In this issue, Bateman et al and Smits et al assess inter-observer variability between expert pathology panels and referring pathologistsand between panel memberswithin bowel cancer screening programmes in England and the Netherlands respectively. 6,7 Both of these referral panels were created as a source of support for bowel cancer screening programme pathologists. Bateman et al describe their clinical experience in real time over a 4-year period in which almost all referrals to their panel (the 'Expert Board') were related to the differential diagnosis between epithelial misplacement and stage pT1 adenocarcinoma.…”

mentioning

confidence: 99%

“…6 Similarly, the Dutch panel comprised five members, three of whom reviewed each case. 7 There is great variability in the threshold for referring cases for expert opinion. Bateman et al found that 25% of their panel workload was derived from just over 7% of the 193 pathologists who referred cases during the 4-year study period.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Expert opinion in bowel cancer screening pathology

Bateman

2022

Histopathology

View full text Add to dashboard Cite

mentioning

confidence: 91%

mentioning

confidence: 91%

mentioning

confidence: 91%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Expert opinion in bowel cancer screening pathology

Bateman

2022

Histopathology

View full text Add to dashboard Cite

Augmented histopathology: Enhancing colon cancer detection through deep learning and ensemble techniques

Gowthamy,

Ramesh

2024

Microscopy Res & Technique

View full text Add to dashboard Cite

Colon cancer poses a significant threat to human life with a high global mortality rate. Early and accurate detection is crucial for improving treatment quality and the survival rate. This paper presents a comprehensive approach to enhance colon cancer detection and classification. The histopathological images are gathered from the CRC‐VAL‐HE‐7K dataset. The images undergo preprocessing to improve quality, followed by augmentation to increase dataset size and enhance model generalization. A deep learning based transformer model is designed for efficient feature extraction and enhancing classification by incorporating a convolutional neural network (CNN). A cross‐transformation model captures long‐range dependencies between regions, and an attention mechanism assigns weights to highlight crucial features. To boost classification accuracy, a Siamese network distinguishes colon cancer tissue classes based on probabilities. Optimization algorithms fine‐tune model parameters, categorizing colon cancer tissues into different classes. The multi‐class classification performance is evaluated in the experimental evaluation, which demonstrates that the proposed model provided highest accuracy rate of 98.84%. In this research article, the proposed method achieved better performance in all analyses by comparing with other existing methods.Research Highlights Deep learning‐based techniques are proposed. DL methods are used to enhance colon cancer detection and classification. CRC‐VAL‐HE‐7K dataset is utilized to enhance image quality. Hybrid particle swarm optimization (PSO) and dwarf mongoose optimization (DMO) are used. The deep learning models are tuned by implementing the PSO‐DMO algorithm.

show abstract

Long-term oncological outcomes after local excision of T1 rectal cancer

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background A growing proportion of patients with early rectal cancer is treated by local excision only. The aim of this study was to evaluate long-term oncological outcomes and the impact of local recurrence on overall survival for surgical local excision in pT1 rectal cancer. Methods Patients who only underwent local excision for pT1 rectal cancer between 1997 and 2014 in two Dutch tertiary referral hospitals were included in this retrospective cohort study. The primary outcome was the local recurrence rate. Secondary outcomes were distant recurrence, overall survival and the impact of local recurrence on overall survival. Results A total of 150 patients (mean age 68.5 ± 10.7 years, 57.3% males) were included in the study. Median length of follow-up was 58.9 months (range 6–176 months). Local recurrence occurred in 22.7% (n = 34) of the patients, with a median time to local recurrence of 11.1 months (range 2.3–82.6 months). The vast majority of local recurrences were located in the lumen. Five-year overall survival was 82.0%, and landmark analyses showed that local recurrence significantly impacted overall survival at 6 and 36 months of follow-up (6 months, p = 0.034, 36 months, p = 0.036). Conclusions Local recurrence rates after local excision of early rectal cancer can be substantial and may impact overall survival. Therefore, clinical decision-making should be based on patient- and tumour characteristics and should incorporate patient preferences.

show abstract

Diagnostic variability in the histopathological assessment of advanced colorectal adenomas and early colorectal cancer in a screening population

Cited by 27 publications

References 23 publications

Expert opinion in bowel cancer screening pathology

Expert opinion in bowel cancer screening pathology

Augmented histopathology: Enhancing colon cancer detection through deep learning and ensemble techniques

Long-term oncological outcomes after local excision of T1 rectal cancer

Contact Info

Product

Resources

About