CT texture analysis for the prediction of KRAS mutation status in colorectal cancer via a machine learning approach. Eur J Radiol. 2019;118:38-43. [PMID: 31439256 DOI: 10.1016/j.ejrad.2019.06.028]

Prediction of KRAS gene mutations in colorectal cancer using a CT-based radiomic model

Background

Determining the KRAS gene mutation status in colorectal cancer (CRC) before surgery is highly important for an individualized clinical treatment. This study aimed to explore the clinical value of radiomics models based on CT images in predicting the KRAS mutation status in patients with CRC.

Methods

A total of 201 CRC patients who underwent surgery and pathology examinations from March 2022 to January 2025 were included. They were randomly allocated to a training group (160 patients) or a testing group (41 patients) at a ratio of 8:2. All patients underwent plain CT and contrast-enhanced examinations before surgery. The 3D segmentation of the tumour was manually delineated by two radiologists who were unaware of the pathological results and KRAS gene detection outcomes. The PyRadiomics package in Python was used to extract 2,264 radiomic features from each ROI. After dimensionality reduction, machine learning methods such as extremely randomized trees (ERT), random forest (RF), XGBoost, Bagging, and CatBoost were used for model construction. The performance of the models was compared using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. The Delong test was employed to assess the differences between the various models.

Results

After feature selection, the top 8 features with the highest mutual information scores were extracted to construct a prediction model. The Delong test revealed that the XGBoost model, which is based on CT images from the vein phase, performed the best, with AUC values of 0.90 and 0.81 in the training and test sets, respectively. The calibration curve indicated a high consistency between the actual and predicted probabilities of the samples. The decision curve analysis results revealed that the XGBoost model exhibited the highest net clinical benefit among all the models.

Conclusion

In this study, a highly accurate radiomics model was developed for KRAS gene mutation status prediction in patients with CRC before surgery. This technique avoids the potential risks of tumour rupture and dissemination during biopsy and can serve as a powerful tool to assist doctors in developing personalized and precise targeted treatments for colorectal cancer, which highly important in clinical work.

From Images to Genes: Radiogenomics Based on Artificial Intelligence to Achieve Non-Invasive Precision Medicine in Cancer Patients

With the increasing demand for precision medicine in cancer patients, radiogenomics emerges as a promising frontier. Radiogenomics is originally defined as a methodology for associating gene expression information from high-throughput technologies with imaging phenotypes. However, with advancements in medical imaging, high-throughput omics technologies, and artificial intelligence, both the concept and application of radiogenomics have significantly broadened. In this review, the history of radiogenomics is enumerated, related omics technologies, the five basic workflows and their applications across tumors, the role of AI in radiogenomics, the opportunities and challenges from tumor heterogeneity, and the applications of radiogenomics in tumor immune microenvironment. The application of radiogenomics in positron emission tomography and the role of radiogenomics in multi-omics studies is also discussed. Finally, the challenges faced by clinical transformation, along with future trends in this field is discussed.

A multicenter study: predicting KRAS mutation and prognosis in colorectal cancer through a CT-based radiomics nomogram

PURPOSE

To establish a CT-based radiomics nomogram for preoperative prediction of KRAS mutation and prognostic stratification in colorectal cancer (CRC) patients.

METHODS

In a retrospective analysis, 408 patients with confirmed CRC were included, comprising 168 cases in the training set, 111 cases in the internal validation set, and 129 cases in the external validation set. Radiomics features extracted from the primary tumors were meticulously screened to identify those closely associated with KRAS mutation. Subsequently, a radiomics nomogram was constructed by integrating these radiomics features with clinically significant parameters. The diagnostic performance was assessed through the area under the receiver operating characteristic curve (AUC). Lastly, the prognostic significance of the nomogram was explored, and Kaplan-Meier analysis was employed to depict survival curves for the high-risk and low-risk groups.

RESULTS

A radiomics model was constructed using 19 radiomics features significantly associated with KRAS mutation. Furthermore, a nomogram was developed by integrating these radiomics features with two clinically significant parameters (age, tumor location). The nomogram achieved AUCs of 0.834, 0.813, and 0.811 in the training set, internal validation set, and external validation set, respectively. Additionally, the nomogram effectively stratified patients into high-risk (KRAS mutation) and low-risk (KRAS wild-type) groups, demonstrating a significant difference in overall survival (P < 0.001). Patients categorized in the high-risk group exhibited inferior overall survival in contrast to those classified in the low-risk group.

CONCLUSIONS

The CT-based radiomics nomogram demonstrates the capability to effectively predict KRAS mutation in CRC patients and stratify their prognosis preoperatively.

Using tumor habitat-derived radiomic analysis during pretreatment 18F-FDG PET for predicting KRAS/NRAS/BRAF mutations in colorectal cancer

BACKGROUND

To investigate the association between Kirsten rat sarcoma viral oncogene homolog (KRAS) / neuroblastoma rat sarcoma viral oncogene homolog (NRAS) /v-raf murine sarcoma viral oncogene homolog B (BRAF) mutations and the tumor habitat-derived radiomic features obtained during pretreatment 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) in patients with colorectal cancer (CRC).

METHODS

We retrospectively enrolled 62 patients with CRC who had undergone 18F-FDG PET/computed tomography from January 2017 to July 2022 before the initiation of therapy. The patients were randomly split into training and validation cohorts with a ratio of 6:4. The whole tumor region radiomic features, habitat-derived radiomic features, and metabolic parameters were extracted from 18F-FDG PET images. After reducing the feature dimension and selecting meaningful features, we constructed a hierarchical model of KRAS/NRAS/BRAF mutations by using the support vector machine. The convergence of the model was evaluated by using learning curve, and its performance was assessed based on the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis. The SHapley Additive exPlanation was used to interpret the contributions of various features to predictions of the model.

RESULTS

The model constructed by using habitat-derived radiomic features had adequate predictive power with respect to KRAS/NRAS/BRAF mutations, with an AUC of 0.759 (95% CI: 0.585-0.909) on the training cohort and that of 0.701 (95% CI: 0.468-0.916) on the validation cohort. The model exhibited good convergence, suitable calibration, and clinical application value. The results of the SHapley Additive explanation showed that the peritumoral habitat and a high_metabolism habitat had the greatest impact on predictions of the model. No meaningful whole tumor region radiomic features or metabolic parameters were retained during feature selection.

CONCLUSION

The habitat-derived radiomic features were found to be helpful in stratifying the status of KRAS/NRAS/BRAF in CRC patients. The approach proposed here has significant implications for adjuvant treatment decisions in patients with CRC, and needs to be further validated on a larger prospective cohort.

Application of artificial intelligence in colorectal cancer screening by colonoscopy: Future prospects (Review)

Colorectal cancer (CRC) has become a severe global health concern, with the third‑high incidence and second‑high mortality rate of all cancers. The burden of CRC is expected to surge to 60% by 2030. Fortunately, effective early evidence‑based screening could significantly reduce the incidence and mortality of CRC. Colonoscopy is the core screening method for CRC with high popularity and accuracy. Yet, the accuracy of colonoscopy in CRC screening is related to the experience and state of operating physicians. It is challenging to maintain the high CRC diagnostic rate of colonoscopy. Artificial intelligence (AI)‑assisted colonoscopy will compensate for the above shortcomings and improve the accuracy, efficiency, and quality of colonoscopy screening. The unique advantages of AI, such as the continuous advancement of high‑performance computing capabilities and innovative deep‑learning architectures, which hugely impact the control of colorectal cancer morbidity and mortality expectancy, highlight its role in colonoscopy screening.

CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study

Colorectal cancer (CRC) is one of the most common types of cancer worldwide. The KRAS mutation is present in 30-50% of CRC patients. This mutation confers resistance to treatment with anti-EGFR therapy. This article aims at proving that computer tomography (CT)-based radiomics can predict the KRAS mutation in CRC patients. The piece is a retrospective study with 56 CRC patients from the Hospital of Santiago de Compostela, Spain. All patients had a confirmatory pathological analysis of the KRAS status. Radiomics features were obtained using an abdominal contrast enhancement CT (CECT) before applying any treatments. We used several classifiers, including AdaBoost, neural network, decision tree, support vector machine, and random forest, to predict the presence or absence of KRAS mutation. The most reliable prediction was achieved using the AdaBoost ensemble on clinical patient data, with a kappa and accuracy of 53.7% and 76.8%, respectively. The sensitivity and specificity were 73.3% and 80.8%. Using texture descriptors, the best accuracy and kappa were 73.2% and 46%, respectively, with sensitivity and specificity of 76.7% and 69.2%, also showing a correlation between texture patterns on CT images and KRAS mutation. Radiomics could help manage CRC patients, and in the future, it could have a crucial role in diagnosing CRC patients ahead of invasive methods.

KRAS mutation status between left- and right-sided colorectal cancer: are there any differences in computed tomography?

PURPOSE

To investigate the differences in clinicopathological and imaging features according to KRAS mutation status in left- and right-sided colorectal cancer.

METHOD

A total of 157 patients with pathologically proven colorectal cancer and preoperative contrast-enhanced multidetector CT examinations were enrolled. According to the tumor location and KRAS status, they were divided into two groups: the left-sided colorectal cancer (LCC) group (wild type, mutant type) and the right-sided colorectal cancer (RCC) group (wild type, mutant type). Clinicopathological and imaging features were recorded in each group. The imaging observation indicators included short axis diameter (SAD), longitudinal tumor length (LTL), tumor shape, pericolic fat stranding, bowel stenosis, intratumoral low-density range, enhancement pattern, and bowel obstruction. Univariate and multivariate logistic regression analyses were performed to compare the difference in KRAS mutation status between groups.

RESULTS

In the LCC group, SAD, tumor shape, degree of pericolic fat stranding, and bowel obstruction were significant indicators for predicting KRAS status (P < 0.05). In the RCC group, CA19-9, SAD, and intratumoral low-density range were significant indicators for predicting KRAS status (P < 0.05.). The area under the curve (AUC) of the combination image indicators in the LCC group was 0.802 [cutoff point 0.372, 95% confidence interval (CI) 0.718-0.888, sensitivity 85.4%, specificity 72.0%]. The AUC in the RCC group was 0.828 (cutoff point 0.647, 95% CI 0.726-0.931, sensitivity 79.5%, specificity 75.0%).

CONCLUSION

The CT imaging features associated with KRAS mutation status in the LCC and RCC groups were different. The combination of tumor location and imaging features can help to further improve the predictive value of KRAS status.

Contrast-Enhanced CT Texture Analysis in Colon Cancer: Correlation with Genetic Markers

Background: The purpose of the study was to determine whether contrast-enhanced CT texture features relate to, and can predict, the presence of specific genetic mutations involved in CRC carcinogenesis. Materials and methods: This retrospective study analyzed the pre-operative CT in the venous phase of patients with CRC, who underwent testing for mutations in the KRAS, NRAS, BRAF, and MSI genes. Using a specific software based on CT images of each patient, for each slice including the tumor a region of interest was manually drawn along the margin, obtaining the volume of interest. A total of 56 texture parameters were extracted that were compared between the wild-type gene group and the mutated gene group. A p-value of <0.05 was considered statistically significant. Results: The study included 47 patients with stage III-IV CRC. Statistically significant differences between the MSS group and the MSI group were found in four parameters: GLRLM RLNU (area under the curve (AUC) 0.72, sensitivity (SE) 77.8%, specificity (SP) 65.8%), GLZLM SZHGE (AUC 0.79, SE 88.9%, SP 65.8%), GLZLM GLNU (AUC 0.74, SE 88.9%, SP 60.5%), and GLZLM ZLNU (AUC 0.77, SE 88.9%, SP 65.8%). Conclusions: The findings support the potential role of the CT texture analysis in detecting MSI in CRC based on pre-treatment CT scans.

Clinical management of metastatic colorectal cancer in the era of precision medicine

Colorectal cancer (CRC) represents approximately 10% of all cancers and is the second most common cause of cancer deaths. Initial clinical presentation as metastatic CRC (mCRC) occurs in approximately 20% of patients. Moreover, up to 50% of patients with localized disease eventually develop metastases. Appropriate clinical management of these patients is still a challenging medical issue. Major efforts have been made to unveil the molecular landscape of mCRC. This has resulted in the identification of several druggable tumor molecular targets with the aim of developing personalized treatments for each patient. This review summarizes the improvements in the clinical management of patients with mCRC in the emerging era of precision medicine. In fact, molecular stratification, on which the current treatment algorithm for mCRC is based, although it does not completely represent the complexity of this disease, has been the first significant step toward clinically informative genetic profiling for implementing more effective therapeutic approaches. This has resulted in a clinically relevant increase in mCRC disease control and patient survival. The next steps in the clinical management of mCRC will be to integrate the comprehensive knowledge of tumor gene alterations, of tumor and microenvironment gene and protein expression profiling, of host immune competence as well as the application of the resulting dynamic changes to a precision medicine-based continuum of care for each patient. This approach could result in the identification of individual prognostic and predictive parameters, which could help the clinician in choosing the most appropriate therapeutic program(s) throughout the entire disease journey for each patient with mCRC. CA Cancer J Clin. 2022;72:000-000.

Radiomics-Guided Precision Medicine Approaches for Colorectal Cancer

The concept of precision oncology entails molecular profiling of tumors to guide therapeutic interventions. Genomic testing through next-generation sequencing (NGS) molecular analysis provides the basis of such highly targeted therapeutics in oncology. As radiomic analysis delivers an array of structural and functional imaging-based biomarkers that depict these molecular mechanisms and correlate with key genetic alterations related to cancers. There is an opportunity to synergize these two big-data approaches to determine the molecular guidance for precision therapeutics. Colorectal cancer is one such disease whose therapeutic management is being guided by genetic and genomic analyses. We review the rationale and utility of radiomics as a combinative strategy for these approaches in the management of colorectal cancer.

Predicting Kirsten Rat Sarcoma Virus Gene Mutation Status in Patients With Colorectal Cancer by Radiomics Models Based on Multiphasic CT

OBJECTIVE

To develop and validate radiomics models based on multiphasic CT in predicting Kirsten rat sarcoma virus (KRAS) gene mutation status in patients with colorectal cancer (CRC).

MATERIALS AND METHODS

A total of 231 patients with pathologically confirmed CRC were retrospectively enrolled and randomly divided into training(n=184) and test groups(n=47) in a ratio of 4:1. A total of 1316 quantitative radiomics features were extracted from non-contrast phase (NCP), arterial-phase (AP) and venous-phase (VP) CT for each patient. Four steps were applied for feature selection including Spearman correlation analysis, variance threshold, least absolute contraction and selection operator, and multivariate stepwise regression analysis. Clinical and pathological characteristics were also assessed. Subsequently, three classification methods, logistic regression (LR), support vector machine (SVM) and random tree (RT) algorithm, were applied to develop seven groups of prediction models (NCP, AP, VP, AP+VP, AP+VP+NCP, AP&VP, AP&VP&NCP) for KRAS mutation prediction. The performance of these models was evaluated by receiver operating characteristics curve (ROC) analysis.

RESULTS

Among the three groups of single-phase models, the AP model, developed by LR algorithm, showed the best prediction performance with an AUC value of 0.811 (95% CI:0.685-0.938) in the test cohort. Compared with the single-phase models, the dual-phase (AP+VP) model with the LR algorithm showed better prediction performance (AUC=0.826, 95% CI:0.700-0.952). The performance of multiphasic (AP+VP+NCP) model with the LR algorithm (AUC=0.811, 95%CI: 0.679-0.944) is comparable to the model with the SVM algorithm (AUC=0.811, 95%CI: 0.695-0.918) in the test cohort, but the sensitivity, specificity, and accuracy of the multiphasic (AP+VP+NCP) model with the LR algorithm were 0.810, 0.808, 0.809 respectively, which were highest among these seven groups of prediction models in the test cohort.

CONCLUSION

The CT radiomics models have the potential to predict KRAS mutation in patients with CRC; different phases may affect the predictive efficacy of radiomics model, of which arterial-phase CT is more informative. The combination of multiphasic CT images can further improve the performance of radiomics model.

A comprehensive texture feature analysis framework of renal cell carcinoma: pathological, prognostic, and genomic evaluation based on CT images

OBJECTIVES

We tried to realize accurate pathological classification, assessment of prognosis, and genomic molecular typing of renal cell carcinoma by CT texture feature analysis. To determine whether CT texture features can perform accurate pathological classification and evaluation of prognosis and genomic characteristics in renal cell carcinoma.

METHODS

Patients with renal cell carcinoma from five open-source cohorts were analyzed retrospectively in this study. These data were randomly split to train and test machine learning algorithms to segment the lesion, predict the histological subtype, tumor stage, and pathological grade. Dice coefficient and performance metrics such as accuracy and AUC were calculated to evaluate the segmentation and classification model. Quantitative decomposition of the predictive model was conducted to explore the contribution of each feature. Besides, survival analysis and the statistical correlation between CT texture features, pathological, and genomic signatures were investigated.

RESULTS

A total of 569 enhanced CT images of 443 patients (mean age 59.4, 278 males) were included in the analysis. In the segmentation task, the mean dice coefficient was 0.96 for the kidney and 0.88 for the cancer region. For classification of histologic subtype, tumor stage, and pathological grade, the model was on a par with radiologists and the AUC was 0.83 [Formula: see text] 0.1, 0.80 [Formula: see text] 0.1, and 0.77 [Formula: see text] 0.1 at 95% confidence intervals, respectively. Moreover, specific quantitative CT features related to clinical prognosis were identified. A strong statistical correlation (R² = 0.83) between the feature crosses and genomic characteristics was shown. The structural equation modeling confirmed significant associations between CT features, pathological (β =  - 0.75), and molecular subtype (β =  - 0.30).

CONCLUSIONS

The framework illustrates high performance in the pathological classification of renal cell carcinoma. Prognosis and genomic characteristics can be inferred by quantitative image analysis.

KEY POINTS

• The analytical framework exhibits high-performance pathological classification of renal cell carcinoma and is on a par with human radiologists. • Quantitative decomposition of the predictive model shows that specific texture features contribute to histologic subtype and tumor stage classification. • Structural equation modeling shows the associations of genomic characteristics to CT texture features. Overall survival and molecular characteristics can be inferred by quantitative CT texture analysis in renal cell carcinoma.

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.

Combined model based on enhanced CT texture features in liver metastasis prediction of high-risk gastrointestinal stromal tumors

PURPOSE

To investigate the use of the combined model based on clinical and enhanced CT texture features for predicting the liver metastasis of high-risk gastrointestinal stromal tumors (GISTs).

METHODS

This retrospective study was conducted including 204 patients with pathologically confirmed high-risk GISTs from the Zhejiang Cancer Hospital from January 2015 to June 2021, and 76 cases of them were diagnosed with simultaneous liver metastasis. We randomly divided the cohort into a training cohort (n = 142) and a validation cohort (n = 62) with a ratio of 7:3. All volumes of interest (VOIs) of the high-risk GISTs were manually segmented on the portal venous phase CT images using the ITK-SNAP software. The least absolute shrinkage and selection operator (Lasso) algorithm was performed to determine the most valuable features from a total of 110 texture features extracted by the A-K software to reflect the texture information of the given VOIs. Texture-based predictive model was built from the selected texture features. Independent clinical risk factors were identified through univariate logistic analysis. Then, the texture-based model incorporated the clinical predictors to develop a combined model by multivariate logistic regression. Receiver operating characteristic curve, calibration curve, and decision curve analysis were utilized to analyze the discrimination capacity and clinical application value of the predictive models.

RESULTS

The nine optimal texture features were remained after the reduction of dimension using Lasso method. Another four clinical parameters (BMI, location, gastrointestinal bleeding, and CA125 level) were included in the clinical-based predictive model. Finally, with the combination of remaining texture and clinical features, a multivariate logistic regression classifier was built to predict the liver metastasis potential of high-risk GISTs. The remarkable classification performance of the combined model for the prediction of liver metastasis in the subjects with high-risk GISTs was obtained with area under curve (AUC) = 0.919, sensitivity = 83.9%, specificity = 89.7%, and accuracy = 84.9% in our validation group.

CONCLUSION

The texture-based radiomic signature derived from the portal venous phase CT images could predict liver metastasis of high-risk GISTs in a non-invasive way. Integrating additional clinical variables into the model further leads to an improvement of liver metastasis risk prediction.

Clinical Significance and Prognostic Value of the Maximum Standardized Uptake Value of 18F-Flurodeoxyglucose Positron Emission Tomography-Computed Tomography in Colorectal Cancer

Background

The role of ¹⁸F-flurodeoxyglucose (¹⁸F-FDG) positron emission tomography–computed tomography (PET/CT) in colorectal cancer (CRC) remains unclear. This study aimed to explore the association of the maximum standardized uptake value (SUVmax), a parameter of ¹⁸F-FDG PET/CT, with KRAS mutation, the Ki-67 index, and survival in patients with CRC.

Methods

Data of 66 patients with CRC who underwent ¹⁸F-FDG PET/CT was retrospectively collected in our center. The clinical significance of the SUVmax in CRC and the association of the SUVmax with KRAS mutation and the Ki-67 index were determined. A meta-analysis was conducted by a systematic search of PubMed, Web of Science, and CNKI databases, and the data from published articles were combined with that of our study. The association of the SUVmax with KRAS mutation and the Ki-67 index was determined using the odds ratio to estimate the pooled results. The hazard ratio was used to quantitatively evaluate the prognosis of the SUVmax in CRC.

Results

By analyzing the data of 66 patients with CRC, the SUVmax was found not to be related to the tumor-node-metastasis stage, clinical stage, sex, and KRAS mutation but was related to the tumor location and nerve invasion. The SUVmax had no significant correlation with the tumor biomarkers and the Ki-67 index. Data of 17 studies indicated that the SUVmax was significantly increased in the mutated type compared with the wild type of KRAS in CRC; four studies showed that there was no remarkable difference between patients with a high and low Ki-67 index score regarding the SUVmax. Twelve studies revealed that the SUVmax had no significant association with overall survival and disease-free survival in CRC patients.

Conclusions

Based on the combined data, this study demonstrated that the SUVmax of ¹⁸F-FDG PET/CT was different between colon and rectal cancers and associated with KRAS mutation but not the Ki-67 index; there was no significant association between the SUVmax and survival of patients with CRC.

Reproducibility and Repeatability of CBCT-Derived Radiomics Features

PURPOSE

This study was conducted in order to determine the reproducibility and repeatability of cone-beam computed tomography (CBCT) radiomics features.

METHODS

The first-, second-, and fifth-day CBCT images from 10 head and neck (H&N) cancer patients and 10 pelvic cancer patients were retrospectively collected for this study. Eighteen common radiomics features were extracted from the longitudinal CBCT images using two radiomics packages. The reproducibility of CBCT-derived radiomics features was assessed using the first-day image as input and compared across the two software packages. The site-specific intraclass correlation coefficient (ICC) was used to quantitatively assess the agreement between packages. The repeatability of CBCT-based radiomics features was evaluated by comparing the following days of CBCT to the first-day image and quantified using site-specific concordance correlation coefficient (CCC). Furthermore, the correlation with volume for all the features was assessed with linear regression and R 2 as correlation parameters.

RESULTS

The first-order histogram-based features such as skewness and entropy showed good agreement computed in either software package (ICCs ≥ 0.80), while the kurtosis measurements were consistent in H&N patients between the two software tools but not in pelvic cases. The ICCs for GLCM-based features showed good agreement (ICCs ≥ 0.80) between packages in both H&N and pelvic groups except for the GLCM-correction. The GLRLM-based texture features were overall less consistent as calculated by the two different software packages compared with the GLCM-based features. The CCC values of all first-order and second-order GLCM features (except GLCM-energy) were all above 0.80 from the 2-day part test-retest set, while the CCC values all dropped below the cutoff after 5-day treatment scans. All first-order histogram-based and GLCM-texture-based features were not highly correlated with volume, while two GLRLM features, in both H&N and pelvic cohorts, showed R 2 ≥0.8, meaning a high correlation with volume.

CONCLUSION

The reproducibility and repeatability of CBCT-based radiomics features were assessed and compared for the first time on both H&N and pelvic sites. There were overlaps of stable features in both disease sites, yet the overall stability of radiomics features may be disease-/protocol-specific and a function of time between scans.

Comparable Performance of Deep Learning-Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer

Radiomic features extracted from segmented tumor regions have shown great power in gene mutation prediction, while deep learning–based (DL-based) segmentation helps to address the inherent limitations of manual segmentation. We therefore investigated whether deep learning–based segmentation is feasible in predicting KRAS/NRAS/BRAF mutations of rectal cancer using MR-based radiomics. In this study, we proposed DL-based segmentation models with 3D V-net architecture. One hundred and eight patients’ images (T2WI and DWI) were collected for training, and another 94 patients’ images were collected for validation. We evaluated the DL-based segmentation manner and compared it with the manual-based segmentation manner through comparing the gene prediction performance of six radiomics-based models on the test set. The performance of the DL-based segmentation was evaluated by Dice coefficients, which are 0.878 ± 0.214 and 0.955 ± 0.055 for T2WI and DWI, respectively. The performance of the radiomics-based model in gene prediction based on DL-segmented VOI was evaluated by AUCs (0.714 for T2WI, 0.816 for DWI, and 0.887 for T2WI+DWI), which were comparable to that of corresponding manual-based VOI (0.637 for T2WI, P=0.188; 0.872 for DWI, P=0.181; and 0.906 for T2WI+DWI, P=0.676). The results showed that 3D V-Net architecture could conduct reliable rectal cancer segmentation on T2WI and DWI images. All-relevant radiomics-based models presented similar performances in KRAS/NRAS/BRAF prediction between the two segmentation manners.

Emerging applications of radiomics in rectal cancer: State of the art and future perspectives

Rectal cancer (RC) is the third most commonly diagnosed cancer and has a high risk of mortality, although overall survival rates have improved. Preoperative assessments and predictions, including risk stratification, responses to therapy, long-term clinical outcomes, and gene mutation status, are crucial to guide the optimization of personalized treatment strategies. Radiomics is a novel approach that enables the evaluation of the heterogeneity and biological behavior of tumors by quantitative extraction of features from medical imaging. As these extracted features cannot be captured by visual inspection, the field holds significant promise. Recent studies have proved the rapid development of radiomics and validated its diagnostic and predictive efficacy. Nonetheless, existing radiomics research on RC is highly heterogeneous due to challenges in workflow standardization and limitations of objective cohort conditions. Here, we present a summary of existing research based on computed tomography and magnetic resonance imaging. We highlight the most salient issues in the field of radiomics and analyze the most urgent problems that require resolution. Our review provides a cutting-edge view of the use of radiomics to detect and evaluate RC, and will benefit researchers dedicated to using this state-of-the-art technology in the era of precision medicine.

Advances in radiological staging of colorectal cancer

The role of imaging in clinically staging colorectal cancer has grown substantially in the 21^st century with more widespread availability of multi-row detector computed tomography (CT), high-resolution magnetic resonance imaging (MRI) with diffusion weighted imaging (DWI), and integrated positron-emission tomography (PET)/CT. In contrast to staging many other cancers, increasing colorectal cancer stage does not highly correlate with survival. As has been the case previously, clinical practice incorporates advances in staging and it is used to guide therapy before adoption into international staging guidelines. Emerging imaging techniques show promise to become part of future staging standards.

Radiomics signature of brain metastasis: prediction of EGFR mutation status

OBJECTIVES

To predict epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma using MR-based radiomics signature of brain metastasis and explore the optimal MR sequence for prediction.

METHODS

Data from 52 patients with brain metastasis from lung adenocarcinoma (28 with mutant EGFR, 24 with wild-type EGFR) were retrospectively reviewed. Contrast-enhanced T1-weighted imaging (T1-CE), T2 fluid-attenuated inversion recovery (T2-FLAIR), T2WI, and DWI sequences were selected for radiomics features extraction. A total of 438 radiomics features were extracted from each MR sequence. All sequences were randomly divided into training and validation cohorts. The least absolute shrinkage selection operator was used to select informative features, a radiomics signature was built with the logistic regression model of the training cohort, and the radiomics signature performance was evaluated using the validation cohort and an independent testing data set.

RESULTS

The radiomics signature built on 9 selected features showed good discrimination in both the training and validation cohorts for T2-FLAIR. The radiomics signature of T2-FLAIR yielded an AUC of 0.987, a classification accuracy of 0.991, sensitivity of 1.000, and specificity of 0.980 in the validation cohort. The AUC was 0.871 in the independent testing data set. The AUCs of our radiomics signature to differentiate exon 19 and exon 21 mutations were 0.529, 0.580, 0.645, and 0.406 for T1-CE, T2-FLAIR, T2WI, and DWI, respectively.

CONCLUSIONS

We developed a T2-FLAIR radiomics signature that can be used as a noninvasive auxiliary tool for predicting EGFR mutation status in lung adenocarcinoma, which is helpful to guide therapeutic strategies.

KEY POINTS

• MR-based radiomics signature of brain metastasis may help predict EGFR mutation status in lung adenocarcinoma, especially using T2-FLAIR. • Nine radiomics features extracted from T2-FLAIR sequence strongly correlate with EGFR mutation status. • Radiomics features reflect tumor heterogeneity through potential changes in tissue morphology caused by EGFR mutation.

Radiomics in Oncology, Part 1: Technical Principles and Gastrointestinal Application in CT and MRI

Simple Summary

Part I is an overview aimed to investigate some technical principles and the main fields of radiomic application in gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy in gastrointestinal cancers, describing mostly the results for each pre-eminent tumor. In particular, this paper provides a general description of the main radiomic drawbacks and future challenges, which limit radiomic application in clinical setting as routine. Further investigations need to standardize and validate the Radiomics as a helpful tool in management of oncologic patients. In that context, Radiomics has been playing a relevant role and could be considered as a future imaging landscape.

Abstract

Radiomics has been playing a pivotal role in oncological translational imaging, particularly in cancer diagnosis, prediction prognosis, and therapy response assessment. Recently, promising results were achieved in management of cancer patients by extracting mineable high-dimensional data from medical images, supporting clinicians in decision-making process in the new era of target therapy and personalized medicine. Radiomics could provide quantitative data, extracted from medical images, that could reflect microenvironmental tumor heterogeneity, which might be a useful information for treatment tailoring. Thus, it could be helpful to overcome the main limitations of traditional tumor biopsy, often affected by bias in tumor sampling, lack of repeatability and possible procedure complications. This quantitative approach has been widely investigated as a non-invasive and an objective imaging biomarker in cancer patients; however, it is not applied as a clinical routine due to several limitations related to lack of standardization and validation of images acquisition protocols, features segmentation, extraction, processing, and data analysis. This field is in continuous evolution in each type of cancer, and results support the idea that in the future Radiomics might be a reliable application in oncologic imaging. The first part of this review aimed to describe some radiomic technical principles and clinical applications to gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy.

Challenges and opportunities for artificial intelligence in oncological imaging

Imaging plays a key role in oncology, including the diagnosis and detection of cancer, determining clinical management, assessing treatment response, and complications of treatment or disease. The current use of clinical oncology is predominantly qualitative in nature with some relatively crude size-based measurements of tumours for assessment of disease progression or treatment response; however, it is increasingly understood that there may be significantly more information about oncological disease that can be obtained from imaging that is not currently utilized. Artificial intelligence (AI) has the potential to harness quantitative techniques to improve oncological imaging. These may include improving the efficiency or accuracy of traditional roles of imaging such as diagnosis or detection. These may also include new roles for imaging such as risk-stratifying patients for different types of therapy or determining biological tumour subtypes. This review article outlines several major areas in oncological imaging where there may be opportunities for AI technology. These include (1) screening and detection of cancer, (2) diagnosis and risk stratification, (3) tumour segmentation, (4) precision oncology, and (5) predicting prognosis and assessing treatment response. This review will also address some of the potential barriers to AI research in oncological imaging.

Radiogenomics in Colorectal Cancer

Simple Summary

Colorectal carcinoma is characterized by intratumoral heterogeneity that can be assessed by radiogenomics. Radiomics, high-throughput quantitative data extracted from medical imaging, combined with molecular analysis, through genomic and transcriptomic data, is expected to lead to significant advances in personalized medicine. However, a radiogenomics approach in colorectal cancer is still in its early stages and many problems remain to be solved. Here we review the progress and challenges in this field at its current stage, as well as future developments.

Abstract

The steady improvement of high-throughput technologies greatly facilitates the implementation of personalized precision medicine. Characterization of tumor heterogeneity through image-derived features—radiomics and genetic profile modifications—genomics, is a rapidly evolving field known as radiogenomics. Various radiogenomics studies have been dedicated to colorectal cancer so far, highlighting the potential of these approaches to enhance clinical decision-making. In this review, a general outline of colorectal radiogenomics literature is provided, discussing the current limitations and suggested further developments.

Artificial intelligence in gastrointestinal cancer: Recent advances and future perspectives

Artificial intelligence (AI) using machine or deep learning algorithms is attracting increasing attention because of its more accurate image recognition ability and prediction performance than human-aid analyses. The application of AI models to gastrointestinal (GI) clinical oncology has been investigated for the past decade. AI has the capacity to automatically detect and diagnose GI tumors with similar diagnostic accuracy to expert clinicians. AI may also predict malignant potential, such as tumor histology, metastasis, patient survival, resistance to cancer treatments and the molecular biology of tumors, through image analyses of radiological or pathological imaging data using complex deep learning models beyond human cognition. The introduction of AI-assisted diagnostic systems into clinical settings is expected in the near future. However, limitations associated with the evaluation of GI tumors by AI models have yet to be resolved. Recent studies on AI-assisted diagnostic models of gastric and colorectal cancers in the endoscopic, pathological, and radiological fields were herein reviewed. The limitations and future perspectives for the application of AI systems in clinical settings have also been discussed. With the establishment of a multidisciplinary team containing AI experts in each medical institution and prospective studies, AI-assisted medical systems will become a promising tool for GI cancer.

Radiogenomics of neuroblastoma in pediatric patients: CT-based radiomics signature in predicting MYCN amplification

OBJECTIVES

To construct a CT-based radiomics signature and assess its performance in predicting MYCN amplification (MNA) in pediatric patients with neuroblastoma.

METHODS

Seventy-eight pediatric patients with neuroblastoma were recruited (55 in training cohort and 23 in test cohort). Radiomics features were extracted automatically from the region of interest (ROI) manually delineated on the three-phase computed tomography (CT) images. Selected radiomics features were retained to construct radiomics signature and a radiomics score (rad-score) was calculated by using the radiomics signature-based formula. A clinical model was established with clinical factors, including clinicopathological data, and CT image features. A combined nomogram was developed with the incorporation of a radiomics signature and clinical factors. The predictive performance was assessed by receiver operating characteristics curve (ROC) analysis and decision curve analysis (DCA).

RESULTS

The radiomics signature was constructed using 7 selected radiomics features. The clinical radiomics nomogram, which was based on the radiomics signature and two clinical factors, showed superior predictive performance compared with the clinical model alone (area under the curve (AUC) in the training cohort: 0.95 vs. 0.82, the test cohort: 0.91 vs. 0.70). The clinical utility of clinical radiomics nomogram was confirmed by DCA.

CONCLUSIONS

This proposed CT-based radiomics signature was able to predict MNA. Combining the radiomics signature with clinical factors outperformed using clinical model alone for MNA prediction.

KEY POINTS

• A CT-based radiomics signature has the ability to predict MYCN amplification (MNA) in neuroblastoma. • Both pre- and post-contrast CT images are valuable in predicting MNA. • Associating the radiomics signature with clinical factors improved the predictive performance of MNA, compared with clinical model alone.

Radiogenomics for predicting p53 status, PD-L1 expression, and prognosis with machine learning in pancreatic cancer

BACKGROUND

Radiogenomics is an emerging field that integrates "Radiomics" and "Genomics". In the current study, we aimed to predict the genetic information of pancreatic tumours in a simple, inexpensive, and non-invasive manner, using cancer imaging analysis and radiogenomics. We focused on p53 mutations, which are highly implicated in pancreatic ductal adenocarcinoma (PDAC), and PD-L1, a biomarker for immune checkpoint inhibitor-based therapies.

METHODS

Overall, 107 patients diagnosed with PDAC were retrospectively examined. The relationship between p53 mutations as well as PD-L1 abnormal expression and clinicopathological factors was investigated using immunohistochemistry. Imaging features (IFs) were extracted from CT scans and were used to create prediction models of p53 and PD-L1 status.

RESULTS

We found that p53 and PD-L1 are significant independent prognostic factors (P = 0.008, 0.013, respectively). The area under the curve for p53 and PD-L1 predictive models was 0.795 and 0.683, respectively. Radiogenomics-predicted p53 mutations were significantly associated with poor prognosis (P = 0.015), whereas the predicted abnormal expression of PD-L1 was not significant (P = 0.096).

CONCLUSIONS

Radiogenomics could predict p53 mutations and in turn the prognosis of PDAC patients. Hence, prediction of genetic information using radiogenomic analysis may aid in the development of precision medicine.

Cancer genotypes prediction and associations analysis from imaging phenotypes: a survey on radiogenomics

In this paper, we present a survey on the progress of radiogenomics research, which predicts cancer genotypes from imaging phenotypes and investigates the associations between them. First, we present an overview of the popular technology modalities for obtaining diagnostic medical images. Second, we summarize recently used methodologies for radiogenomics analysis, including statistical analysis, radiomics and deep learning. And then, we give a survey on the recent research based on several types of cancers. Finally, we discuss these studies and propose possible future research directions. In conclusion, we have identified strong correlations between cancer genotypes and imaging phenotypes. In addition, with the rapid growth of medical data, deep learning models show great application potential for radiogenomics.

Preoperative prediction of perineural invasion and KRAS mutation in colon cancer using machine learning

PURPOSE

Preoperative prediction of perineural invasion (PNI) and Kirsten RAS (KRAS) mutation in colon cancer is critical for treatment planning and patient management. We developed machine learning models for diagnosis of PNI and KRAS mutation in colon cancer patients by interpreting preoperative CT.

METHODS

This retrospective study included 207 patients who received surgical resection in our institution. The underlying tumor characteristics were described by analyzing CT image texture quantitatively. The key radiomics features were determined with similarity analysis followed by RELIEFF method among 306 CT imaging features. Eight kernel-based support vector machines classifiers were constructed using individual (II, III, or IV) or multi-stage (II + III + IV) patient cohorts for predicting PNI and KRAS mutation. The model performances were evaluated using accuracy, receiver operating curve, and decision curve analyses.

RESULTS

Multi-stage classifiers obtained AUC of 0.793 and 0.862 for detecting PNI and KRAS mutation for test cohort. Moreover, individual-stage classifiers demonstrated significantly improved diagnostic performance at all stages (II_AUC: [0.86; 0.99], III_AUC: [0.99; 0.99], and IV_AUC: [1.00; 1.00], respectively, for PNI and KRAS mutation in test cohort). Besides, stage II tumor is better described with coarse texture features while more detailed features are required for better characterization of advanced-stage tumors (III and IV) for diagnoses of PNI or KRAS mutation.

CONCLUSION

Machine learning models developed using preoperative CT data can predict PNI and KRAS mutation in colon cancer patients with satisfactory performance. Individual-stage models better-characterized the relationship between CT features and PNI or KRAS mutation than multi-stage models and demonstrated good prediction scores.