Deep learning can predict lymph node status directly from histology in colorectal cancer

Kiehl, Lennard; Kuntz, Sara; Höhn, Julia; Jutzi, Tanja; Krieghoff-Henning, Eva; Kather, Jakob Nikolas; Holland‐Letz, Tim; Kopp‐Schneider, Annette; Chang‐Claude, Jenny; Brobeil, Alexander; Kalle, Christof von; Fröhling, Stefan; Alwers, Elizabeth; Brenner, Hermann; Hoffmeister, Michael; Brinker, Titus J.

doi:10.1016/j.ejca.2021.08.039

Cited by 41 publications

(32 citation statements)

References 48 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LNM is an important factor affecting the prognosis of CRC and affects therapeutic decisions (5). AJCC pN stage and LNR (12,20).…”

Section: Discussionmentioning

confidence: 99%

“…LNM is an important factor affecting the prognosis of CRC and affects therapeutic decisions ( 5 ). AJCC pN stage and LNR are both reported as prognostic factors in CRC ( 6 , 8 ), but AJCC pN stage is limited by TLNs and LNR did not consider the effect of NLNs ( 7 , 11 ).…”

Section: Discussionmentioning

confidence: 99%

“…Lymph node metastasis (LNM) is an important risk factor for the poor prognosis and strongly affects therapeutic decisions in CRC ( 5 ). The 5-year OS ranges from 70% to 90% in CRC patients with negative lymph nodes (NLNs), while it ranges from 30% to 60% in patients with positive lymph nodes (PLNs) ( 6 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prognostic value of log odds of positive lymph nodes, lymph node ratio, and N stage in patients with colorectal signet ring cell carcinoma: A retrospective cohort study

Hu¹,

Jiang²,

Wu³

et al. 2023

Front. Surg.

View full text Add to dashboard Cite

AimLittle attention has been paid in the prognosis of colorectal signet ring cell carcinoma (SRCC). This study aims to explore the predictive capacity of log odds of positive lymph nodes (LODDS), lymph node ratio (LNR), and pN stage in the prognosis of patients with colorectal SRCC.MethodsA retrospective cohort study was designed, and data were extracted from the Surveillance, Epidemiology and End Results (SEER) database. Data on demographic characteristics, clinicopathological features, and treatment were extracted. Outcomes were overall survival (OS) and cancer-specific survival (CSS). Association of LODDS, LNR, and pN stage with OS and CSS were explored using Cox proportional hazard model and Cox competing risk model, respectively, with results showing as hazard ratio and 95% confidence interval (CI). Predictive performance of LODDS, LNR, and pN stage in OS and CSS was assessed by calculating C-index.ResultsA total of 2,198 patients were included in this study. LODDS, LNR, and pN stage were associated with the OS and CSS of colorectal SRCC patients (all P < 0.05). LODDS showed a good performance in the OS (C-index: 0.704, 95% CI: 0.690–0.718), which was superior to LNR (C-index: 0.657, 95% CI: 0.643–0.671) and pN stage (C-index: 0.643, 95% CI: 0.629–0.657). The C-index of LODDS, LNR, and pN stage for CSS was 0.733 (95% CI: 0.719–0.747), 0.713 (95% CI: 0.697–0.729), and 0.667 (95% CI: 0.651–0.683), respectively.ConclusionsLODDS displayed a better predictive capacity in the OS and CSS than LNR and pN stage, indicating that LODDS may be effective to predict the prognosis of colorectal SRCC in the clinic.

show abstract

“…LNM is an important factor affecting the prognosis of CRC and affects therapeutic decisions (5). AJCC pN stage and LNR (12,20).…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Prognostic value of log odds of positive lymph nodes, lymph node ratio, and N stage in patients with colorectal signet ring cell carcinoma: A retrospective cohort study

Hu¹,

Jiang²,

Wu³

et al. 2023

Front. Surg.

View full text Add to dashboard Cite

show abstract

“…Kiehl et al developed a deep learning model from routine histological slides and/or clinical data to predict lymph node metastasis in colorectal cancer [ 42 ]. The deep learning model achieved an AUROC of 71.0%, the clinical classifier achieved an AUROC of 67.0% and a combination of the two classifiers yielded an improvement to 74.1%.…”

Section: Discussionmentioning

confidence: 99%

Deep-Learning to Predict BRCA Mutation and Survival from Digital H&E Slides of Epithelial Ovarian Cancer

Nero

Boldrini

Lenkowicz

et al. 2022

IJMS

View full text Add to dashboard Cite

BRCA 1/2 genes mutation status can already determine the therapeutic algorithm of high grade serous ovarian cancer patients. Nevertheless, its assessment is not sufficient to identify all patients with genomic instability, since BRCA 1/2 mutations are only the most well-known mechanisms of homologous recombination deficiency (HR-d) pathway, and patients displaying HR-d behave similarly to BRCA mutated patients. HRd assessment can be challenging and is progressively overcoming BRCA testing not only for prognostic information but more importantly for drugs prescriptions. However, HR testing is not already integrated in clinical practice, it is quite expensive and it is not refundable in many countries. Selecting patients who are more likely to benefit from this assessment (BRCA 1/2 WT patients) at an early stage of the diagnostic process, would allow an optimization of genomic profiling resources. In this study, we sought to explore whether somatic BRCA1/2 genes status can be predicted using computational pathology from standard hematoxylin and eosin histology. In detail, we adopted a publicly available, deep-learning-based weakly supervised method that uses attention-based learning to automatically identify sub regions of high diagnostic value to accurately classify the whole slide (CLAM). The same model was also tested for progression free survival (PFS) prediction. The model was tested on a cohort of 664 (training set: n = 464, testing set: n = 132) ovarian cancer patients, of whom 233 (35.1%) had a somatic BRCA 1/2 mutation. An area under the curve of 0.7 and 0.55 was achieved in the training and testing set respectively. The model was then further refined by manually identifying areas of interest in half of the cases. 198 images were used for training (126/72) and 87 images for validation (55/32). The model reached a zero classification error on the training set, but the performance was 0.59 in terms of validation ROC AUC, with a 0.57 validation accuracy. Finally, when applied to predict PFS, the model achieved an AUC of 0.71, with a negative predictive value of 0.69, and a positive predictive value of 0.75. Based on these analyses, we have planned further steps of development such as proving a reference classification performance, exploring the hyperparameters space for training optimization, eventually tweaking the learning algorithms and the neural networks architecture for better suiting this specific task. These actions may allow the model to improve performances for all the considered outcomes.

show abstract

“…However, the demarcation between handcrafted approaches and DL is not absolute; multiple studies have used DL systems to extract features, which are subsequently combined with handcrafted features. 10 , 11 Application-wise, ML/DL approaches can be used for two ends. First, they can recapitulate, and thus automate, the interpretation of data normally performed by human experts.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction

et al. 2022

View full text Add to dashboard Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

show abstract

Deep learning can predict lymph node status directly from histology in colorectal cancer

Cited by 41 publications

References 48 publications

Prognostic value of log odds of positive lymph nodes, lymph node ratio, and N stage in patients with colorectal signet ring cell carcinoma: A retrospective cohort study

Prognostic value of log odds of positive lymph nodes, lymph node ratio, and N stage in patients with colorectal signet ring cell carcinoma: A retrospective cohort study

Deep-Learning to Predict BRCA Mutation and Survival from Digital H&E Slides of Epithelial Ovarian Cancer

Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction

Contact Info

Product

Resources

About