Deep learning-based morphological feature analysis and the prognostic association study in colon adenocarcinoma histopathological images

Abstract

Colorectal cancer (CRC) is now the third most common malignancy to cause mortality worldwide, and its prognosis is of great importance. Recent CRC prognostic prediction studies mainly focused on biomarkers, radiometric images, and end-to-end deep learning methods, while only a few works paid attention to exploring the relationship between the quantitative morphological features of patients' tissue slides and their prognosis. However, existing few works in this area suffered from the drawback of choosing the cells randomly from the whole slides, which contain the non-tumor region that lakes information about prognosis. In addition, the existing works, which tried to demonstrate their biological interpretability using patients' transcriptome data, failed to show the biological meaning closely related to cancer. In this study, we proposed and evaluated a prognostic model using morphological features of cells in the tumor region. The features were first extracted by the software CellProfiler from the tumor region selected by Eff-Unet deep learning model. Features from different regions were then averaged for each patient as their representative, and the Lasso-Cox model was used to select the prognosis-related features. The prognostic prediction model was at last constructed using the selected prognosis-related features and was evaluated through KM estimate and cross-validation. In terms of biological meaning, Gene Ontology (GO) enrichment analysis of the expressed genes that correlated with the prognostically significant features was performed to show the biological interpretability of our model.With the help of tumor segmentation, our model achieved better statistical significance and better biological interpretability compared to the results without tumor segmentation. Statistically, the Kaplan Meier (KM) estimate of our model showed that the model using features in the tumor region has a higher C-index, a lower p-value, and a better performance on cross-validation than the model without tumor segmentation. In addition, revealing the pathway of the immune escape and the spread of the tumor, the model with tumor segmentation demonstrated a biological meaning much more related to cancer immunobiology than the model without tumor segmentation. Our prognostic prediction model using quantitive morphological features from tumor regions was almost as good as the TNM tumor staging system as they had a close C-index, and our model can be combined with the TNM tumor stage system to make a better prognostic prediction. And to the best of our knowledge, the biological mechanisms in our study were the most relevant to the immune mechanism of cancer compared to the previous studies.

Digital Pathology: A Comprehensive Review of Open-Source Histological Segmentation Software

“…Colorectal cancer (CRC) still represents a cause of death worldwide, in which early detection and grade identification represent an opportunity to improve overall survival [13,138,139]. Early diagnosis is supported by the exploitation of specific biomarkers associated with radiological imaging analyses.…”

“…Early diagnosis is supported by the exploitation of specific biomarkers associated with radiological imaging analyses. Thus, several authors have proposed prognostic prediction models through tumor segmentation, which has reported a more significant analysis than the model without tumor segmentation [139,140]. Relevant studies have been carried out, employing CellProfiler and QuPath for the nuclei classification of colorectal cancer slides, showing promising results [52].…”

Nextflow pipeline for Visium and H&E data from patient-derived xenograft samples

“…Manual detailed assessment of the WSI image is a laborious process, and machine learning tools can help to quantify morphological features on WSI. 17 , 18 …”

Transformer with Convolution and Graph-Node co-embedding: An accurate and interpretable vision backbone for predicting gene expressions from local histopathological image

“…For biomedical images, some morphological features extracted from the pathological images are also believed to be related to the clinical outcomes of patients [11]. Emerging technologies and approaches have brought new opportunities to generate more accurate gene expression [12], mutation [13], and cell type annotations [14] at a single cell [15] or spatial resolution [16], which also brings the urgent need for linking molecular features and biomedical images.…”