Stromal composition predicts recurrence of early rectal cancer after local excision

Abstract

Stromal composition predicts recurrence of early rectal cancer after local excisionAims: After local excision of early rectal cancer, definitive lymph node status is not available. An alternative means for accurate assessment of recurrence risk is required to determine the most appropriate subsequent management. Currently used measures are suboptimal. We assess three measures of tumour stromal content to determine their predictive value after local excision in a well-characterised cohort of rectal cancer patients without prior radiotherapy. Methods and results: A total of 143 patients were included. Haematoxylin and eosin (H&E) sections were scanned for (i) deep neural network (DNN, a machine-learning algorithm) tumour segmentation into compartments including desmoplastic stroma and inflamed stroma; and (ii) digital assessment of tumour stromal fraction (TSR) and optical DNA ploidy analysis. 3 0 mRNA sequencing was performed to obtain gene expression data from which stromal and immune scores were calculated using the ESTI-MATE method. Full results were available for 139 samples and compared with disease-free survival. All three methods were prognostic. Most strongly predictive was a DNN-determined ratio of desmoplastic to inflamed stroma >5.41 (P < 0.0001). A ratio of ESTI-MATE stromal to immune score <1.19 was also predictive of disease-free survival (P = 0.00051), as was stromal fraction >36.5% (P = 0.037). Conclusions: The DNN-determined ratio of desmoplastic to inflamed ratio is a novel and powerful predictor of disease recurrence in locally excised early rectal cancer. It can be assessed on a single H&E section, so could be applied in routine clinical practice to improve the prognostic information available to patients and clinicians to inform the decision concerning further management.

Machine Learning of Histopathological Images Predicts Recurrences of Resected Pancreatic Ductal Adenocarcinoma With Adjuvant Treatment

“…Other factors, including fibrosis, stroma, PanIN, and fat content, did not differ significantly. However, a recent study reported that the ratio of desmoplastic to inflamed stroma is one of the clues to detect the recurrence of rectal cancer in the early stage after operation 27 . Related to this topic, a previous study reported that a low stromal area in cancer-involved regions is associated with poor prognosis, 28 although this study did not show any significant associations of stroma with outcomes and recurrences after surgery.…”

“…However, a recent study reported that the ratio of desmoplastic to inflamed stroma is one of the clues to detect the recurrence of rectal cancer in the early stage after operation. 27 Related to this topic, a previous study reported that a low stromal area in cancer-involved regions is associated with poor prognosis, 28 although this study did not show any significant associations of stroma with outcomes and recurrences after surgery. Hassid et al 29 indicated that patients with pancreatic cancer with high-grade PanIN showed a poor prognosis compared with patients with low-grade or non-PanIN.…”

Deep learning for the prediction of the chemotherapy response of metastatic colorectal cancer: comparing and combining H&E staining histopathology and infrared spectral histopathology

“…38 Jones et al have also shown, thanks to machine learning algorithms, the importance of the composition of the tumor stroma and inflammation in the evaluation of the risk of recurrence from HE sections. 39 Other studies show the important impact on the prognosis of certain markers related to inflammation, 40,41 these markers can also be linked to the TNM score for more precision. 42 We noted an interesting difference in the segmentation of the 'immune cells' class, between IR and HE images.…”

Stroma AReactive Invasion Front Areas (SARIFA): a novel histopathologic biomarker in colorectal cancer patients and its association with the luminal tumour proportion

“…There have been several studies highlighting the relevance of tumour-stroma ratio/tumour cell proportion/tumour cell density/proportion of tumour (PoT) for prognosis prediction in CRC patients: High intra-tumour stroma content measured using different methods has been shown to predict poor prognosis in several different CRC patient cohorts [9] , [10] , [11] , [12] , [13] , [14] , [15] and other tumour types. Moreover, it has been suggested that tumour stroma is actively involved in CRC development and progression, and that disruption of the tumour-stroma interaction may inhibit tumour progression and metastasis formation [16] .…”