Integrative Analysis of Histopathological Images and Genomic Data Predicts Metastasis for Colorectal Cancer
Approved Research ID: 73860
Approval date: August 31st 2021
The purpose of this study is to develop an automated prognostic model that could predict patient's metastastic risk for patient stratification, using a combination of quantitative image features and genes.
Histopathologic images confer important information for diagnosis, staging, and prognosis for cancers and are being used extensively by pathologists in clinical practice. With the recent availability of digital whole-slide images, automated computational histopathologic image analysis systems have shown great promise in diagnosis and the discovery of new biomarkers for cancers. In comparison with human inspection, computerized image analysis has great potential to improve efficiency, accuracy, and consistency. Besides histopathologic images, molecular characteristics, such as genetic alterations and geneexpression signatures, are also widely adopted for predicting clinical outcomes for cancers. Therefore, an interesting scientific question is the relationship between morphologic and genomic features while an important translational question is if the integration of these two types of features can lead to more accurate prediction of patient outcome.
To study these issues, matched histopathologic images and genomic datasets for cancers are needed.
Currently, clinicians make important treatment decisions through nodal status evaluation based only on limited radiological examinations, such as ultrasound and computed tomography, and on manual evaluations of a few histological features via light microscopy. However, qualitative evaluation of pathological features exclusively (such as histologic type, depth of tumor invasion, and tumor grades) is insufficient for predicting the presence of lymph node metastasis (LNM) in patients with colorectal cancer.
Public health impact:
The accurate and fast assessment of locoregional and/or distant metastases in patients with early CRC using derived model enable to determine whether these patients should undergo additional surgical resections or be needed surveillance regularly.