Hist-Immune signature: a prognostic factor in colorectal cancer using immunohistochemical slide image analysis

Automated deep learning-based assessment of tumour-infiltrating lymphocyte density determines prognosis in colorectal cancer

BACKGROUND

The presence of tumour-infiltrating lymphocytes (TILs) is a well-established prognostic biomarker across multiple cancer types, with higher TIL counts being associated with lower recurrence rates and improved patient survival. We aimed to examine whether an automated intraepithelial TIL (iTIL) assessment could stratify patients by risk, with the ability to generalise across independent patient cohorts, using routine H&E slides of colorectal cancer (CRC). To our knowledge, no other existing fully automated iTIL system has demonstrated this capability.

METHODS

An automated method employing deep neural networks was developed to enumerate iTILs in H&E slides of CRC. The method was applied to a Stage III discovery cohort (n = 353) to identify an optimal threshold of 17 iTILs per-mm2 tumour for stratifying relapse-free survival. Using this threshold, patients from two independent Stage II-III validation cohorts (n = 1070, n = 885) were classified as "TIL-High" or "TIL-Low".

RESULTS

Significant stratification was observed in terms of overall survival for a combined validation cohort univariate (HR 1.67, 95%CI 1.39-2.00; p < 0.001) and multivariate (HR 1.37, 95%CI 1.13-1.66; p = 0.001) analysis. Our iTIL classifier was an independent prognostic factor within proficient DNA mismatch repair (pMMR) Stage II CRC cases with clinical high-risk features. Of these, those classified as TIL-High had outcomes similar to pMMR clinical low risk cases, and those classified TIL-Low had significantly poorer outcomes (univariate HR 2.38, 95%CI 1.57-3.61; p < 0.001, multivariate HR 2.17, 95%CI 1.42-3.33; p < 0.001).

CONCLUSIONS

Our deep learning method is the first fully automated system to stratify patient outcome by analysing TILs in H&E slides of CRC, that has shown generalisation capabilities across multiple independent cohorts.

Pathological-Features-Modified TNM Staging System Improves Prognostic Accuracy for Rectal Cancer

BACKGROUND

Variations in survival outcomes are observed in the eighth edition of the American Joint Committee on Cancer TNM staging system.

OBJECTIVE

Machine learning ensemble methods were used to develop and evaluate the effectiveness of a pathological-features-modified TNM staging system in predicting survival for patients with rectal cancer by use of commonly reported pathological features, such as histological grade, tumor deposits, and perineural invasion, to improve the prognostic accuracy.

DESIGN

This was a retrospective population-based study.

SETTINGS

Data were assessed from the database of the Surveillance, Epidemiology, and End Results Program.

PATIENTS

The study cohort comprised 14,468 patients with rectal cancer diagnosed between 2010 and 2015. The development cohort included those who underwent surgery as the primary treatment, whereas patients who received neoadjuvant therapy were assigned to the validation cohort.

MAIN OUTCOME MEASURES

The primary outcome measures included cumulative rectal cancer survival, adjusted HRs, and both calibration and discrimination statistics to evaluate model performance and internal validation.

RESULTS

Multivariable Cox regression analysis identified all 3 pathological features as prognostic factors, after which patients were categorized into 4 pathological groups based on the number of pathological features (ie, 0, 1, 2, and 3). Distinct survival differences were observed among the groups, especially with patients with stage III rectal cancer. The proposed pathological-features-modified TNM staging outperformed the TNM staging in both the development and validation cohorts.

LIMITATIONS

Retrospective in design and lack of external validation.

CONCLUSIONS

The proposed pathological-features-modified TNM staging could complement the current TNM staging by improving the accuracy of survival estimation of patients with rectal cancer. See Video Abstract .

EL SISTEMA DE ESTADIFICACIN TNM CON CARACTERSTICAS PATOLGICAS MODIFICADO MEJORA LA PRECISIN DEL PRONSTICO DEL CNCER DE RECTO

ANTECEDENTES:Se observan variaciones en los resultados de supervivencia en el sistema de estadificación TNM del Comité Conjunto Americano del Cáncer 8º ediciónOBJETIVO:Se utilizaron métodos conjuntos de aprendizaje automático para desarrollar y evaluar la eficacia de un sistema de estadificación con características patológicas modificadas de tumores, ganglios y metástasis para predecir la supervivencia de pacientes con cáncer de recto, utilizando algunas características patológicas comúnmente informadas, como el grado histológico, depósitos tumorales e invasión perineural, para mejorar la precisión del pronóstico.DISEÑO:Este fue un estudio retrospectivo de base poblacional.ENTERNO CLINICO:Se recuperaron y evaluaron datos de la base de datos de Vigilancia, Epidemiología y Resultados Finales.PACIENTES:La cohorte del estudio estuvo compuesta por 14,468 pacientes con cáncer de recto diagnosticados entre 2010 y 2015. La cohorte de desarrollo incluyó a aquellos que se sometieron a cirugía como tratamiento primario, mientras que los pacientes que recibieron terapia neoadyuvante fueron asignados a la cohorte de validación.PRINCIPALES MEDIDAS DE RESULTADO:Las medidas de resultado primarias incluyeron supervivencia acumulada del cáncer de recto, índices de riesgo ajustados y estadísticas de calibración y discriminación para evaluar el rendimiento del modelo y la validación interna.RESULTADOS:El análisis de regresión multivariable de Cox identificó las tres características patológicas como factores pronósticos, después de lo cual los pacientes se clasificaron en cuatro grupos patológicos según el número de características patológicas (es decir, 0, 1, 2 y 3). Se observaron distintas diferencias en la supervivencia entre los grupos, especialmente en los pacientes en estadio III. La estadificación propuesta con características patológicas modificadas de tumores-ganglios-metástasis superó a la estadificación TNM tanto en las cohortes de desarrollo como en las de validación.LIMITACIONES:Diseño retrospectivo y falta de validación externa.CONCLUSIONES:La estadificación propuesta con características patológicas modificadas de tumores-ganglios-metástasis podría complementar la estadificación TNM actual al mejorar la precisión de la estimación de supervivencia de los pacientes con cáncer de recto. (Traducción- Dr. Francisco M. Abarca-Rendon ).

Desmoplastic Reaction Associates with Prognosis and Adjuvant Chemotherapy Response in Colorectal Cancer: A Multicenter Retrospective Study

Desmoplastic reaction (DR) is one of many tumor-host interactions and is associated with the overall survival (OS) of patients with colorectal cancer. However, the clinical significance of DR requires further study in large multicenter cohorts and its predictive value in adjuvant chemotherapy (ACT) response remains unclear. Here, a total of 2,225 patients with colorectal cancer from five independent institutions were divided into primary (N = 1,012 from two centers) and validation (N = 1,213 from three centers) cohorts. DR was classified as immature, middle, or mature depending on the presence of myxoid stroma and hyalinized collagen bundles at the invasive front of the primary tumor. OS among different subgroups were compared, and the correlations of DR type with tumor-infiltrating lymphocytes (TILs) within stroma, tumor stroma ratio (TSR), and Stroma AReactive Invasion Front Areas (SARIFA) were also analyzed. In the primary cohort, patients with mature DR had the highest 5-year survival rate. These findings were confirmed in validation cohort. In addition, for stage II colorectal cancer, patients classified as non-mature DR would benefit from ACT compared with surgery alone. Furthermore, immature and middle DR were more associated with high TSR, less distribution of TILs within stroma and positive SARIFA compared with mature. Taken together, these data suggest that DR is a robust-independent prognostic factor for patients with colorectal cancer. For patients with stage II colorectal cancer, non-mature DR could be a potential marker for recognizing high-risk patients who may benefit from ACT.

Significance

DR has the potential to identify patients with high-risk colorectal cancer and predict the efficacy of adjuvant chemotherapy in patients with stage II colorectal cancer. Our findings support reporting DR types as additional pathologic parameters in clinical practice for more precise risk stratification.

Development and Validation of an Immune-Based Prognostic Risk Score for Patients With Resected Non-Small Cell Lung Cancer

Background

Despite the well-known role of immunoscore, as a prognostic tool, that appeared to be superior to tumor–node–metastasis (TNM) staging system, no prognostic scoring system based on immunohistochemistry (IHC) staining digital image analysis has been established in non-small cell lung cancer (NSCLC). Hence, we aimed to develop and validate an immune-based prognostic risk score (IMPRS) that could markedly improve individualized prediction of postsurgical survival in patients with resected NSCLC.

Methods

In this retrospective study, complete resection of NSCLC (stage I–IIIA) was performed for two independent patient cohorts (discovery cohort, n=168; validation cohort, n=115). Initially, paraffin-embedded resected specimens were stained by immunohistochemistry (IHC) of three immune cell types (CD3+, CD4+, and CD8+ T cells), and a total of 5,580 IHC-immune features were extracted from IHC digital images for each patient by using fully automated pipeline. Then, an IHC-immune signature was constructed with selected features using the LASSO Cox analysis, and the association of signature with patients’ overall survival (OS) was analyzed by Kaplan–Meier method. Finally, IMPRS was established by incorporating IHC-immune signature and independent clinicopathological variables in multivariable Cox regression analysis. Furthermore, an external validation cohort was included to validate this prognostic risk score.

Results

Eight key IHC-immune features were selected for the construction of IHC-immune signature, which showed significant associations with OS in all cohorts [discovery: hazard ratio (HR)=11.518, 95%CI, 5.444–24.368; validation: HR=2.664, 95%CI, 1.029–6.896]. Multivariate analyses revealed IHC-immune signature as an independent prognostic factor, and age, T stage, and N stage were also identified and entered into IMPRS (all p&lt;0.001). IMPRS had good discrimination ability for predicting OS (C-index, 0.869; 95%CI, 0.861–0.877), confirmed using external validation cohort (0.731, 0.717–0.745). Interestingly, IMPRS had better prognostic value than clinicopathological-based model and TNM staging system termed as C-index (clinicopathological-based model: 0.674; TNM staging: 0.646, all p&lt;0.05). More importantly, decision curve analysis showed that IMPRS had adequate performance for predicting OS in resected NSCLC patients.

Conclusions

Our findings indicate that the IMPRS that we constructed can provide more accurate prognosis for individual prediction of OS for patients with resected NSCLC, which can help in guiding personalized therapy and improving outcomes for patients.

Deep learning quantified mucus-tumor ratio predicting survival of patients with colorectal cancer using whole-slide images

Background

In colorectal cancer (CRC), mucinous adenocarcinoma differs from other adenocarcinomas in gene-phenotype, morphology, and prognosis. However, mucinous components are present in a large number of adenocarcinomas, and the prognostic value of mucus proportion has not been investigated. Artificial intelligence provides a way to quantify mucus proportion on whole-slide images (WSIs) accurately. We aimed to quantify mucus proportion by deep learning and further investigate its prognostic value in two CRC patient cohorts.

Methods

Deep learning was used to segment WSIs stained with hematoxylin and eosin. Mucus-tumor ratio (MTR) was defined as the proportion of mucinous component in the tumor area. A training cohort (N = 419) and a validation cohort (N = 315) were used to evaluate the prognostic value of MTR. Survival analysis was performed using the Cox proportional hazard model.

Result

Patients were stratified to mucus-low and mucus-high groups, with 24.1% as the threshold. In the training cohort, patients with mucus-high had unfavorable outcomes (hazard ratio for high vs. low 1.88, 95% confidence interval 1.18-2.99, P = 0.008), with 5-year overall survival rates of 54.8% and 73.7% in mucus-high and mucus-low groups, respectively. The results were confirmed in the validation cohort (2.09, 1.21-3.60, 0.008; 62.8% vs. 79.8%). The prognostic value of MTR was maintained in multivariate analysis for both cohorts.

Conclusion

The deep learning quantified MTR was an independent prognostic factor in CRC. With the advantages of advanced efficiency and high consistency, our method is suitable for clinical application and promotes precision medicine development.