Computed Tomography-Based Radiomics Model to Preoperatively Predict Microsatellite Instability Status in Colorectal Cancer: A Multicenter Study

Development and external validation of a multiparametric MRI-based radiomics model for preoperative prediction of microsatellite instability status in rectal cancer: a retrospective multicenter study

OBJECTIVES

To establish and validate a radiomics model based on multiparametric magnetic resonance imaging (MRI), and to predict microsatellite instability (MSI) status in rectal cancer patients.

METHODS

A total of 199 patients with pathologically confirmed rectal cancer were included. The MSI status was confirmed by immunohistochemistry (IHC) staining. Clinical factors and laboratory data associated with MSI status were analyzed. The imaging data of 100 patients from one of the hospitals were used as the training set. The remaining 99 patients from the other two hospitals were used as the external validation set. The regions of interest (ROIs) were delineated from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1WI (CE-T1WI) sequence to extract the radiomics features. The Tree-based approach was used for feature selection. The models were constructed based on the four single sequences and a combination of the four sequences using the random forest (RF) algorithm. The external validation set was used to verify the generalization ability of each model. The receiver operating characteristic (ROC) curves and the area under the curve (AUC) were plotted to evaluate and compare the predictive performance of each model.

RESULTS

In the four single-series models, the CE-T1WI model performed the best. The AUCs of the T1WI, T2WI, DWI, and CE-T1WI prediction models in the training set were 0.74, 0.71, 0.71, and 0.78, respectively, while in the external validation set, the corresponding AUCs were 0.67, 0.66, 0.70, and 0.77. The prediction and generalization performance of the combined model of multi-sequences was comparable to that of the CE-T1WI model and it was better than that of the remaining three single-series models, with AUC values of 0.78 and 0.78 in the training and validation sets, respectively.

CONCLUSION

The established radiomics models based on CE-T1WI or multiparametric MRI have similar predictive performance. They have the potential to predict MSI status in rectal cancer patients.

KEY POINTS

• A radiomics model for the prediction of MSI status in patients with rectal cancer was established and validated using external validation. • The models based on CE-T1WI or multiparametric MRI have better predictive performance than those based on single unenhanced sequence images. • The radiomics model has the potential to suggest MSI status in rectal cancer patients; however, it is not yet a substitute for histological confirmation.

The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review

Importance

Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity.

Highlights

We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma.

Conclusion

AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.

Facts and Hopes on the Use of Artificial Intelligence for Predictive Immunotherapy Biomarkers in Cancer

Immunotherapy by immune checkpoint inhibitors has become a standard treatment strategy for many types of solid tumors. However, the majority of patients with cancer will not respond, and predicting response to this therapy is still a challenge. Artificial intelligence (AI) methods can extract meaningful information from complex data, such as image data. In clinical routine, radiology or histopathology images are ubiquitously available. AI has been used to predict the response to immunotherapy from radiology or histopathology images, either directly or indirectly via surrogate markers. While none of these methods are currently used in clinical routine, academic and commercial developments are pointing toward potential clinical adoption in the near future. Here, we summarize the state of the art in AI-based image biomarkers for immunotherapy response based on radiology and histopathology images. We point out limitations, caveats, and pitfalls, including biases, generalizability, and explainability, which are relevant for researchers and health care providers alike, and outline key clinical use cases of this new class of predictive biomarkers.

Preoperative Prediction of Microsatellite Instability in Rectal Cancer Using Five Machine Learning Algorithms Based on Multiparametric MRI Radiomics

Objectives: To establish and verify radiomics models based on multiparametric MRI for preoperatively identifying the microsatellite instability (MSI) status of rectal cancer (RC) by comparing different machine learning algorithms. Methods: This retrospective study enrolled 383 (training set, 268; test set, 115) RC patients between January 2017 and June 2022. A total of 4148 radiomics features were extracted from multiparametric MRI, including T₂-weighted imaging, T₁-weighted imaging, apparent diffusion coefficient, and contrast-enhanced T₁-weighted imaging. The analysis of variance, correlation test, univariate logistic analysis, and a gradient-boosting decision tree were used for the dimension reduction. Logistic regression, Bayes, support vector machine (SVM), K-nearest neighbor (KNN), and tree machine learning algorithms were used to build different radiomics models. The relative standard deviation (RSD) and bootstrap method were used to quantify the stability of these five algorithms. Then, predictive performances of different models were assessed using area under curves (AUCs). The performance of the best radiomics model was evaluated using calibration and discrimination. Results: Among these 383 patients, the prevalence of MSI was 14.62% (56/383). The RSD value of logistic regression algorithm was the lowest (4.64%), followed by Bayes (5.44%) and KNN (5.45%), which was significantly better than that of SVM (19.11%) and tree (11.94%) algorithms. The radiomics model based on logistic regression algorithm performed best, with AUCs of 0.827 and 0.739 in the training and test sets, respectively. Conclusions: We developed a radiomics model based on the logistic regression algorithm, which could potentially be used to facilitate the individualized prediction of MSI status in RC patients.

Radiomics-guided checkpoint inhibitor immunotherapy for precision medicine in cancer: A review for clinicians

Immunotherapy using immune checkpoint inhibitors (ICIs) is a breakthrough in oncology development and has been applied to multiple solid tumors. However, unlike traditional cancer treatment approaches, immune checkpoint inhibitors (ICIs) initiate indirect cytotoxicity by generating inflammation, which causes enlargement of the lesion in some cases. Therefore, rather than declaring progressive disease (PD) immediately, confirmation upon follow-up radiological evaluation after four-eight weeks is suggested according to immune-related Response Evaluation Criteria in Solid Tumors (ir-RECIST). Given the difficulty for clinicians to immediately distinguish pseudoprogression from true disease progression, we need novel tools to assist in this field. Radiomics, an innovative data analysis technique that quantifies tumor characteristics through high-throughput extraction of quantitative features from images, can enable the detection of additional information from early imaging. This review will summarize the recent advances in radiomics concerning immunotherapy. Notably, we will discuss the potential of applying radiomics to differentiate pseudoprogression from PD to avoid condition exacerbation during confirmatory periods. We also review the applications of radiomics in hyperprogression, immune-related biomarkers, efficacy, and immune-related adverse events (irAEs). We found that radiomics has shown promising results in precision cancer immunotherapy with early detection in noninvasive ways.

Radiomics features based on internal and marginal areas of the tumor for the preoperative prediction of microsatellite instability status in colorectal cancer

Objectives

To explore whether the preoperative CT radiomics can predict the status of microsatellite instability (MSI) in colorectal cancer (CRC) patients and identify the region with the most stable and high-efficiency radiomics features.

Methods

This retrospective study involved 230 CRC patients with preoperative computed tomography scans and available MSI status between December 2019 and October 2021. Image segmentation and radiomic feature extraction were performed as follows. First, slices with the maximum tumor area (region of interest, ROI) were manually contoured. Subsequently, each ROI was shrunk inward by 1, 2, and 3 mm, respectively, where the remaining ROIs were considered as the internal region of the tumor (named as IROI1, IROI2, and IROI3), and the shrunk regions were considered as marginal regions of the tumor (named as MROI1, MROI2, and MROI3). Finally, radiomics features were extracted from each of the ROI. The intraclass correlation coefficient and least absolute shrinkage and selection operator method were used to choose the most reliable and relevant features of MSI status. Clinical, radiomics, and combined clinical radiomics models have been established. Calibration curve and decision curve analyses (DCA) were generated to explore the correction effect and assess the clinical applicability of the above models, respectively.

Results

In the testing cohort, the radiomics model based on IROI3 yielded the highest average area under the curve (AUC) value of 0.908, compared with the remaining radiomics models. Additionally, hypertension and N stage were considered as clinically independent factors of MSI status. The combined clinical radiomics model achieved excellent diagnostic efficacy (AUC: 0.928; sensitivity: 0.840; specificity: 0.867) in the testing cohort, as well as favorable calibration and clinical utility by calibration curve and DCA analyses.

Conclusions

The IROI3 model, which is based on a 3-mm shrink in the largest areas of the tumor, could noninvasively reflect the heterogeneity and genetic instability within the tumor. This suggests that it is an important biomarker for the preoperative prediction of MSI status. The model can extract more robust and effective radiomics features, which lays a foundation for the radiomics study of hollow organs, such as in CRC.

CT-based radiomic nomogram for preoperative prediction of DNA mismatch repair deficiency in gastric cancer

Background

DNA mismatch repair (MMR) deficiency has attracted considerable attention as a predictor of the immunotherapy efficacy of solid tumors, including gastric cancer. We aimed to develop and validate a computed tomography (CT)-based radiomic nomogram for the preoperative prediction of MMR deficiency in gastric cancer (GC).

Methods

In this retrospective analysis, 225 and 91 GC patients from two distinct hospital cohorts were included. Cohort 1 was randomly divided into a training cohort (n = 176) and an internal validation cohort (n = 76), whereas cohort 2 was considered an external validation cohort. Based on repeatable radiomic features, a radiomic signature was constructed using the least absolute shrinkage and selection operator (LASSO) regression analysis. We employed multivariable logistic regression analysis to build a radiomics-based model based on radiomic features and preoperative clinical characteristics. Furthermore, this prediction model was presented as a radiomic nomogram, which was evaluated in the training, internal validation, and external validation cohorts.

Results

The radiomic signature composed of 15 robust features showed a significant association with MMR protein status in the training, internal validation, and external validation cohorts (both P-values <0.001). A radiomic nomogram incorporating a radiomic signature and two clinical characteristics (age and CT-reported N stage) represented good discrimination in the training cohort with an AUC of 0.902 (95% CI: 0.853–0.951), in the internal validation cohort with an AUC of 0.972 (95% CI: 0.945–1.000) and in the external validation cohort with an AUC of 0.891 (95% CI: 0.825–0.958).

Conclusion

The CT-based radiomic nomogram showed good performance for preoperative prediction of MMR protein status in GC. Furthermore, this model was a noninvasive tool to predict MMR protein status and guide neoadjuvant therapy.

Detection of Microsatellite Instability in Colonoscopic Biopsies and Postal Urine Samples from Lynch Syndrome Cancer Patients Using a Multiplex PCR Assay

Identification of mismatch repair (MMR)-deficient colorectal cancers (CRCs) is recommended for Lynch syndrome (LS) screening, and supports targeting of immune checkpoint inhibitors. Microsatellite instability (MSI) analysis is commonly used to test for MMR deficiency. Testing biopsies prior to tumour resection can inform surgical and therapeutic decisions, but can be limited by DNA quantity. MSI analysis of voided urine could also provide much needed surveillance for genitourinary tract cancers in LS. Here, we reconfigure an existing molecular inversion probe-based MSI and BRAF c.1799T > A assay to a multiplex PCR (mPCR) format, and demonstrate that it can sample >140 unique molecules per marker from <1 ng of DNA and classify CRCs with 96−100% sensitivity and specificity. We also show that it can detect increased MSI within individual and composite CRC biopsies from LS patients, and within preoperative urine cell free DNA (cfDNA) from two LS patients, one with an upper tract urothelial cancer, the other an undiagnosed endometrial cancer. Approximately 60−70% of the urine cfDNAs were tumour-derived. Our results suggest that mPCR sequence-based analysis of MSI and mutation hotspots in CRC biopsies could facilitate presurgery decision making, and could enable postal-based screening for urinary tract and endometrial tumours in LS patients.

Non-invasive prediction of microsatellite instability in colorectal cancer by a genetic algorithm-enhanced artificial neural network-based CT radiomics signature

OBJECTIVE

The stratification of microsatellite instability (MSI) status assists clinicians in making treatment decisions for colorectal cancer (CRC) patients. This study aimed to establish a CT-based radiomics signature to predict MSI status in patients with CRC.

METHODS

A total of 837 CRC patients who underwent preoperative enhanced CT and had available MSI status data were recruited from two hospitals. Radiomics features were extracted from segmented tumours, and a series of data balancing and feature selection strategies were used to select MSI-related features. Finally, an MSI-related radiomics signature was constructed using a genetic algorithm-enhanced artificial neural network model. Combined and clinical models were constructed using multivariate logistic regression analyses by integrating the clinical factors with or without the signature. A Kaplan-Meier survival analysis was conducted to explore the prognostic information of the signature in patients with CRC.

RESULTS

Ten features were selected to construct a signature which showed robust performance in both the internal and external validation cohorts, with areas under the curves (AUC) of 0.788 and 0.775, respectively. The performance of the signature was comparable to that of the combined model (AUCs of 0.777 and 0.767, respectively) and it outperformed the clinical model constituting age and tumour location (AUCs of 0.768 and 0.623, respectively). Survival analysis demonstrated that the signature could stratify patients with stage II CRC according to prognosis (HR: 0.402, p = 0.029).

CONCLUSIONS

This study built a robust radiomics signature for identifying the MSI status of CRC patients, which may assist individualised treatment decisions.

KEY POINTS

• Our well-designed modelling strategies helped overcome the problem of data imbalance caused by the low incidence of MSI. • Genetic algorithm-enhanced artificial neural network-based CT radiomics signature can effectively distinguish the MSI status of CRC patients. • Kaplan-Meier survival analysis demonstrated that our signature could significantly stratify stage II CRC patients into high- and low-risk groups.

A multicenter study on the preoperative prediction of gastric cancer microsatellite instability status based on computed tomography radiomics

PURPOSE

To construct and validate a radiomics feature model based on computed tomography (CT) images and clinical characteristics to predict the microsatellite instability (MSI) status of gastric cancer patients before surgery.

METHODS

We retrospectively collected the upper abdominal or the entire abdominal-enhanced CT scans of 189 gastric cancer patients before surgery. The patients underwent postoperative gastric cancer MSI status testing, and the dates of their radiologic images and clinicopathological data were from January 2015 to August 2021. These 189 patients were divided into a training set (n = 90) and an external validation set (n = 99). The patients were divided by MSI status into the MSI-high (H) arm (30 and 33 patients in the training set and external validation set, respectively) and MSI-low/stable (L/S) arm (60 and 66 patients in the training set and external validation set, respectively). In the training set, the clinical characteristics and tumor radiologic characteristics of the patients were extracted, and the tenfold cross-validation method was used for internal validation of the training set. The external validation set was used to assess its generalized performance. A receiver-operating characteristic (ROC) curve was plotted to assess the model performance, and the area under the curve (AUC) was calculated.

RESULTS

The AUC of the radiomics model in the training set and external validation set was 0.8228 [95% confidence interval (CI) 0.7355-0.9101] and 0.7603 [95% CI 0.6625-0.8581], respectively, showing that the constructed radiomics model exhibited satisfactory generalization capabilities. The accuracy, sensitivity, and specificity of the training dataset were 0.72, 0.63, and 0.77, respectively. The accuracy, sensitivity, and specificity of the external validation dataset were 0.67, 0.79, and 0.60, respectively. Statistical analysis was carried out on the clinical data, and there was statistical significance for the tumor site and age (p < 0.05). MSI-H gastric cancer was mostly seen in the gastric antrum and older patients.

CONCLUSIONS

Radiomics markers based on CT images and clinical characteristics have the potential to be a non-invasive auxiliary diagnostic tool for preoperative assessment of gastric cancer MSI status, and they can aid in clinical decision-making and improve patient outcomes.

Multi-Omic Approaches in Colorectal Cancer beyond Genomic Data

Colorectal cancer (CRC) is one of the most frequent tumours and one of the major causes of morbidity and mortality globally. Its incidence has increased in recent years and could be linked to unhealthy dietary habits combined with environmental and hereditary factors, which can lead to genetic and epigenetic changes and induce tumour development. The model of CRC progression has always been based on a genomic, parametric, static and complex approach involving oncogenes and tumour suppressor genes. Recent advances in omics sciences have sought a paradigm shift to a multiparametric, immunological-stromal, and dynamic approach for a better understanding of carcinogenesis and tumour heterogeneity. In the present paper, we review the most important preclinical and clinical data and present recent discoveries in the field of transcriptomics, proteomics, metagenomics and radiomics in CRC disease.