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

The value of machine learning based on CT radiomics in the preoperative identification of peripheral nerve invasion in colorectal cancer: a two-center study

BACKGROUND

We aimed to explore the application value of various machine learning (ML) algorithms based on multicenter CT radiomics in identifying peripheral nerve invasion (PNI) of colorectal cancer (CRC).

METHODS

A total of 268 patients with colorectal cancer who underwent CT examination in two hospitals from January 2016 to December 2022 were considered. Imaging and clinicopathological data were collected through the Picture Archiving and Communication System (PACS). The Feature Explorer software (FAE) was used to identify the peripheral nerve invasion of colorectal patients in center 1, and the best feature selection and classification channels were selected. Finally, the best feature selection and classifier pipeline were verified in center 2.

RESULTS

The six-feature models using RFE feature selection and GP classifier had the highest AUC values, which were 0.610, 0.699, and 0.640, respectively. FAE generated a more concise model based on one feature (wavelet-HLL-glszm-LargeAreaHighGrayLevelEmphasis) and achieved AUC values of 0.614 and 0.663 on the validation and test sets, respectively, using the "one standard error" rule. Using ANOVA feature selection, the GP classifier had the best AUC value in a one-feature model, with AUC values of 0.611, 0.663, and 0.643 on the validation, internal test, and external test sets, respectively. Similarly, when using the "one standard error" rule, the model based on one feature (wave-let-HLL-glszm-LargeAreaHighGrayLevelEmphasis) achieved AUC values of 0.614 and 0.663 on the validation and test sets, respectively.

CONCLUSIONS

Combining artificial intelligence and radiomics features is a promising approach for identifying peripheral nerve invasion in colorectal cancer. This innovative technique holds significant potential for clinical medicine, offering broader application prospects in the field.

CRITICAL RELEVANCE STATEMENT

The multi-channel ML method based on CT radiomics has a simple operation process and can be used to assist in the clinical screening of patients with CRC accompanied by PNI.

KEY POINTS

• Multi-channel ML in the identification of peripheral nerve invasion in CRC. • Multi-channel ML method based on CT-radiomics can detect the PNI of CRC. • Early preoperative identification of PNI in CRC is helpful to improve the formulation of treatment strategies and the prognosis of patients.

Preoperative assessment of grade, T stage, and lymph node involvement: machine learning-based CT texture analysis in colon cancer

PURPOSE

To investigate whether texture analysis of primary colonic mass in preoperative abdominal computed tomography (CT) scans of patients diagnosed with colon cancer could predict tumor grade, T stage, and lymph node involvement using machine learning (ML) algorithms.

MATERIALS AND METHODS

This retrospective study included 73 patients diagnosed with colon cancer. Texture features were extracted from contrast-enhanced CT images using LifeX software. First, feature reduction was performed by two radiologists through reproducibility analysis. Using the analysis of variance method, the parameters that best predicted lymph node involvement, grade, and T stage were determined. The predictive performance of these parameters was assessed using Orange software with the k-nearest neighbor (kNN), random forest, gradient boosting, and neural network models, and their area under the curve values were calculated.

RESULTS

There was excellent reproducibility between the two radiologists in terms of 49 of the 58 texture parameters that were subsequently subject to further analysis. Considering all four ML algorithms, the mean AUC and accuracy ranges were 0.557-0.800 and 47-76%, respectively, for the prediction of lymph node involvement; 0.666-0.846 and 68-77%, respectively, for the prediction of grade; and 0.768-0.962 and 81-88%, respectively, for the prediction of T stage. The best performance was achieved with the random forest model in the prediction of LN involvement, the kNN model for the prediction of grade, and the gradient boosting model for the prediction of T stage.

CONCLUSION

The results of this study suggest that the texture analysis of preoperative CT scans obtained for staging purposes in colon cancer can predict the presence of advanced-stage tumors, high tumor grade, and lymph node involvement with moderate specificity and sensitivity rates when evaluated using ML models.

Prognostic DNA mutation and mRNA expression analysis of perineural invasion in oral squamous cell carcinoma

This study analyzed oral squamous cell carcinoma (OSCC) genomes and transcriptomes in relation to perineural invasion (PNI) and prognosis using Cancer Genome Atlas data and validated these results with GSE41613 data. Gene set enrichment analysis (GSEA), gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes were conducted. We identified 22 DNA mutations associated with both overall survival (OS) and PNI. Among them, TGFBR1 and RPS6KA4 mRNAs were overexpressed, while TYRO3 and GPR137 mRNAs were underexpressed in PNI patients. Among the 141 mRNA genes associated with both OS and PNI, we found overlap with PNI-related DNA mutations, including ZNF43, TEX10, TPSD1, and PSD3. In GSE41613 data, TGFBR1, RPS6KA4, TYRO3, GPR137, TEX10 and TPSD1 mRNAs were expressed differently according to the prognosis. The 22 DNA-mutated genes clustered into nervous system development, regulation of DNA-templated transcription, and transforming growth factor beta binding. GSEA analysis of mRNAs revealed upregulation of hallmarks epithelial mesenchymal transition (EMT), TNFα signaling via NF-κB, and IL2 STAT5 signaling. EMT upregulation aligned with the TGFBR1 DNA mutation, supporting its significance in PNI. These findings suggest a potential role of PNI genes in the prognosis of OSCC, providing insights for diagnosis and treatment of OSCC.

Artificial Intelligence Applications in the Treatment of Colorectal Cancer: A Narrative Review

Colorectal cancer is the third most prevalent cancer worldwide, and its treatment has been a demanding clinical problem. Beyond traditional surgical therapy and chemotherapy, newly revealed molecular mechanisms diversify therapeutic approaches for colorectal cancer. However, the selection of personalized treatment among multiple treatment options has become another challenge in the era of precision medicine. Artificial intelligence has recently been increasingly investigated in the treatment of colorectal cancer. This narrative review mainly discusses the applications of artificial intelligence in the treatment of colorectal cancer patients. A comprehensive literature search was conducted in MEDLINE, EMBASE, and Web of Science to identify relevant papers, resulting in 49 articles being included. The results showed that, based on different categories of data, artificial intelligence can predict treatment outcomes and essential guidance information of traditional and novel therapies, thus enabling individualized treatment strategy selection for colorectal cancer patients. Some frequently implemented machine learning algorithms and deep learning frameworks have also been employed for long-term prognosis prediction in patients with colorectal cancer. Overall, artificial intelligence shows encouraging results in treatment strategy selection and prognosis evaluation for colorectal cancer patients.

Development and validation of a combined nomogram for predicting perineural invasion status in rectal cancer via computed tomography-based radiomics

AIM

This study aimed to create and validate a clinic-radiomics nomogram based on computed tomography (CT) imaging for predicting preoperative perineural invasion (PNI) of rectal cancer (RC).

MATERIAL AND METHODS

This study enrolled 303 patients with RC who were divided into training (n = 242) and test datasets (n = 61) in an 8:2 ratio with all their clinical outcomes. A total of 3,296 radiomic features were extracted from CT images. Five machine learning (ML) models (logistic regression (LR)/K-nearest neighbor (KNN)/multilayer perceptron (MLP)/support vector machine (SVM)/light gradient boosting machine (LightGBM)) were developed using radiomic features derived from the arterial and venous phase images, and the model with the best diagnostic performance was selected. By combining the radiomics and clinical signatures, a fused nomogram model was constructed.

RESULTS

After using the Mann-Whitney U-test and least absolute shrinkage and selection operator (LASSO) to remove redundant features, the MLP model proved to be the most efficient among the five ML models. The fusion nomogram based on MLP prediction probability further improves the ability to predict the PNI status. The area under the curve (AUC) of the training and test sets was 0.883 and 0.889, respectively, which were higher than those of the clinical (training set, AUC = 0.710; test set, AUC = 0.762) and radiomic models (training set, AUC = 0.840; test set, AUC = 0.834).

CONCLUSIONS

The clinical-radiomics combined nomogram model based on enhanced CT images efficiently predicted the PNI status of patients with RC.

CT-based radiomics nomogram for the preoperative prediction of microsatellite instability and clinical outcomes in colorectal cancer: a multicentre study

AIM

To develop and validate a computed tomography (CT)-based radiomics nomogram for preoperative prediction of microsatellite instability (MSI) status and clinical outcomes in colorectal cancer (CRC) patients.

MATERIALS AND METHODS

This retrospective study enrolled 497 CRC patients from three centres. Least absolute shrinkage and selection operator regression was utilised for feature selection and constructing the radiomics signature. Univariate and multivariate logistic regression analyses were employed to identify significant clinical variables. The radiomics nomogram was constructed by integrating the radiomics signature and the identified clinical variables. The performance of the nomogram was evaluated through receiver operating characteristic curves, calibration curves, and decision curve analysis. Kaplan-Meier analysis was performed to investigate the prognostic value of the nomogram.

RESULTS

The radiomics signature comprised 10 radiomics features associated with MSI status. The nomogram, integrating the radiomics signature and independent predictors (age, location, and thickness), demonstrated favourable calibration and discrimination, achieving areas under the receiver operating characteristic (ROC) curves (AUCs) of 0.89 (95% confidence interval [CI]: 0.83-0.95), 0.87 (95% CI: 0.79-0.95), 0.88 (95% CI: 0.81-0.96), and 0.86 (95% CI: 0.78-0.93) in the training cohort, internal validation cohort, and two external validation cohorts, respectively. The nomogram exhibited superior performance compared to the clinical model (p<0.05). Additionally, survival analysis demonstrated that the nomogram successfully stratified stage II CRC patients based on prognosis (hazard ratio [HR]: 0.357, p=0.022).

CONCLUSION

The radiomics nomogram demonstrated promising performance in predicting MSI status and stratifying the prognosis of patients with CRC.

Correlation between KRAS Mutation and CTLA-4 mRNA Expression in Circulating Tumour Cells: Clinical Implications in Colorectal Cancer

Combination strategies of KRAS inhibition with immunotherapy in treating advanced or recurrent colorectal carcinoma (CRC) may need to be assessed in circulating tumour cells (CTCs) to achieve better clinical outcomes. This study aimed to investigate the genomic variations of KRAS in CTCs and matched CRC tissues and compared mRNA expression of KRAS and CTLA-4 between wild-type and KRAS-mutated CTCs and CRC tissues. Clinicopathological correlations were also compared. Six known mutations of KRAS were identified at both codon 12 and codon 13 (c.35G>T/G12V, c.35G>A7/G12D, c.35G>C/G12A, c.34G>A/G12S, c.38G>C/G13A, and c.38G>A/G13D). Three CTC samples harboured the identified mutations (16.7%; 3/18), while fifteen matched primary tumour tissues (65.2%, 15/23) showed the mutations. CTCs harbouring the KRAS variant were different from matched CRC tissue. All the mutations were heterozygous. Though insignificant, CTLA-4 mRNA expression was higher in patients carrying KRAS mutations. Patients harbouring KRAS mutations in CTCs were more likely to have poorly differentiated tumours (p = 0.039) and with lymph node metastasis (p = 0.027) and perineural invasion (p = 0.014). KRAS mutations in CTCs were also significantly correlated with overall pathological stages (p = 0.027). These findings imply the genetic basis of KRAS with immunotherapeutic target molecules based on a real-time platform. This study also suggests the highly heterogeneous nature of cancer cells, which may facilitate the assessment of clonal dynamics across a single patient's disease.

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.

Preoperative prediction of microvascular invasion and perineural invasion in pancreatic ductal adenocarcinoma with 18F-FDG PET/CT radiomics analysis

AIM

To develop and validate a predictive model based on 2-[¹⁸F]-fluoro-2-deoxy-d-glucose (¹⁸F-FDG) positron-emission tomography (PET)/computed tomography (CT) radiomics features and clinicopathological parameters to preoperatively identify microvascular invasion (MVI) and perineural invasion (PNI), which are important predictors of poor prognosis in patients with pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS

Preoperative ¹⁸F-FDG PET/CT images and clinicopathological parameters of 170 patients in PDAC were collected retrospectively. The whole tumour and its peritumoural variants (tumour dilated with 3, 5, and 10 mm pixels) were applied to add tumour periphery information. A feature-selection algorithm was employed to mine mono-modality and fused feature subsets, then conducted binary classification using gradient boosted decision trees.

RESULTS

For MVI prediction, the model performed best on a fused subset of ¹⁸F-FDG PET/CT radiomics features and two clinicopathological parameters, with an area under the receiver operating characteristic curve (AUC) of 83.08%, accuracy of 78.82%, recall of 75.08%, precision of 75.5%, and F1-score of 74.59%. For PNI prediction, the model achieved best prediction results only on the subset of PET/CT radiomics features, with AUC of 94%, accuracy of 89.33%, recall of 90%, precision of 87.81%, and F1 score of 88.35%. In both models, 3 mm dilation on the tumour volume produced the best results.

CONCLUSIONS

The radiomics predictors from preoperative ¹⁸F-FDG PET/CT imaging exhibited instructive predictive efficacy in the identification of MVI and PNI status preoperatively in PDAC. Peritumoural information was shown to assist in MVI and PNI predictions.

Repeatability of radiomics studies in colorectal cancer: a systematic review

BACKGROUND

Recently, radiomics has been widely used in colorectal cancer, but many variable factors affect the repeatability of radiomics research. This review aims to analyze the repeatability of radiomics studies in colorectal cancer and to evaluate the current status of radiomics in the field of colorectal cancer.

METHODS

The included studies in this review by searching from the PubMed and Embase databases. Then each study in our review was evaluated using the Radiomics Quality Score (RQS). We analyzed the factors that may affect the repeatability in the radiomics workflow and discussed the repeatability of the included studies.

RESULTS

A total of 188 studies was included in this review, of which only two (2/188, 1.06%) studies controlled the influence of individual factors. In addition, the median score of RQS was 11 (out of 36), range-1 to 27.

CONCLUSIONS

The RQS score was moderately low, and most studies did not consider the repeatability of radiomics features, especially in terms of Intra-individual, scanners, and scanning parameters. To improve the generalization of the radiomics model, it is necessary to further control the variable factors of repeatability.

Current status and quality of radiomic studies for predicting KRAS mutations in colorectal cancer patients: A systematic review and meta‑analysis

PURPOSE

The purpose of this study was to evaluate the methodological quality of radiomics-based studies for noninvasive, preoperative prediction of Kirsten rat sarcoma (KRAS) mutations in patients with colorectal cancer; furthermore, we systematically evaluate the diagnostic accuracy of predicting models.

METHODS

We systematically searched PubMed, Embase, Cochrane Library and Web of Science databases up to 20 April 2022 for eligible studies. The methodological quality of included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) and Radiomics Quality Score (RQS) tools. A meta-analysis of studies on the prediction of KRAS status in colorectal cancer patients was performed.

RESULT

Twenty-nine studies were identified in the systematic review, including three studies on the prediction of KRAS status in colorectal cancer liver metastases. All studies had an average RQS score of 9.55 (26.5% of the total score), ranging from 3 to 17. Most studies demonstrated a low or unclear risk of bias in the domains of QUADAS-2. Nineteen studies were included in the meta-analysis, mostly imaged with magnetic resonance imaging (MRI), followed by computed tomography (CT), positron emission tomography-CT (PET/CT). With pooled sensitivity, specificity and area under the curve (AUC) of the training cohorts were 0.80(95% confidence interval(CI), 0.75-0.84), 0.80(95% CI, 0.74-0.85) and 0.87(95% CI, 0.84-0.90),respectively. The pooled sensitivity, specificity, and AUC for the validation cohorts (13 studies) were 0.78(95% CI, 0.71-0.84), 0.84(95% CI, 0.74-0.90), and 0.86(95% CI, 0.83-0.89), respectively.

CONCLUSION

Radiomics is a potential noninvasive technology that has a moderate preoperative diagnosis and prediction effect on KRAS mutations. However, it has not been implemented as a clinical decision-making tool. Future researchers should pay more attention to the methodological quality of the study and further externally validate the model using multicenter datasets.

The clinical implications and molecular features of intrahepatic cholangiocarcinoma with perineural invasion

BACKGROUND

Perineural invasion (PNI) is associated with metastasis in malignancies, including intrahepatic cholangiocarcinoma (ICC), and is correlated with poor prognosis.

METHODS

The study included three large cohorts: ZS-ICC and TMA cohorts from our team, MSK cohort from a public database, and a small cohort named cohort 4. Prognostic implications of PNI were investigated in MSK cohort and TMA cohort. PNI-related genomic and transcriptomic profiles were analyzed in MSK and ZS-ICC cohorts. GO, KEGG, and ssGSEA analyses were performed. Immunohistochemistry was used to investigate the relationship between PNI and markers of neurons, hydrolases, and immune cells. The efficacy of adjuvant therapy in ICC patients with PNI was also assessed.

RESULTS

A total of 30.6% and 20.7% ICC patients had PNI in MSK and TMA cohorts respectively. Patients with PNI presented with malignant phenotypes such as high CA19-9, the large bile duct type, lymph node invasion, and shortened overall survival (OS) and relapse-free survival (RFS). Nerves involved in PNI positively express tyrosine hydroxylase (TH), a marker of sympathetic nerves. Patients with PNI showed high mutation frequency of KRAS and an immune suppressive metastasis prone niche of decreased NK cell, increased neutrophil, and elevated PD-L1, CD80, and CD86 expression. Patients with PNI had an extended OS after adjuvant therapy with TEGIO, GEMOX, or capecitabine.

CONCLUSION

Our study deciphered the genomic features and the immune suppressive metastasis-prone niche in ICC with PNI. Patients with PNI showed a poor prognosis after surgery but a good response to adjuvant chemotherapy.

Computed tomography-based radiomics nomogram for the preoperative prediction of perineural invasion in colorectal cancer: a multicentre study

PURPOSE

To develop and validate a computed tomography (CT) radiomics nomogram from multicentre datasets for preoperative prediction of perineural invasion (PNI) in colorectal cancer.

METHODS

A total of 299 patients with histologically confirmed colorectal cancer from three hospitals were enrolled in this retrospective study. Radiomic features were extracted from the whole tumour volume. The least absolute shrinkage and selection operator logistic regression was applied for feature selection and radiomics signature construction. Finally, a radiomics nomogram combining the radiomics score and clinical predictors was established. The receiver operating characteristic curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the radiomics nomogram in the training cohort, internal validation and external validation cohorts.

RESULTS

Twelve radiomics features extracted from the whole tumour volume were used to construct the radiomics model. The area under the curve (AUC) values of the radiomics model in the training cohort, internal validation cohort, external validation cohort 1, and external validation cohort 2 were 0.82 (0.75-0.90), 0.77 (0.62-0.92), 0.71 (0.56-0.85), and 0.73 (0.60-0.85), respectively. The nomogram, which combined the radiomics score with T category and N category by CT, yielded better performance in the training cohort (AUC = 0.88), internal validation cohort (AUC = 0.80), external validation cohort 1 (AUC = 0.75), and external validation cohort 2 (AUC = 0.76). DCA confirmed the clinical utility of the nomogram.

CONCLUSIONS

The CT-based radiomics nomogram has the potential to accurately predict PNI in patients with 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&amp;VP, AP&amp;VP&amp;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.

What Genetics Can Do for Oncological Imaging: A Systematic Review of the Genetic Validation Data Used in Radiomics Studies

(1) Background: Radiogenomics is motivated by the concept that biomedical images contain information that reflects underlying pathophysiology. This review focused on papers that used genetics to validate their radiomics models and outcomes and assess their contribution to this emerging field. (2) Methods: All original research with the words radiomics and genomics in English and performed in humans up to 31 January 2022, were identified on Medline and Embase. The quality of the studies was assessed with Radiomic Quality Score (RQS) and the Cochrane recommendation for diagnostic accuracy study Quality Assessment 2. (3) Results: 45 studies were included in our systematic review, and more than 50% were published in the last two years. The studies had a mean RQS of 12, and the studied tumors were very diverse. Up to 83% investigated the prognosis as the main outcome, with the rest focusing on response to treatment and risk assessment. Most applied either transcriptomics (54%) and/or genetics (35%) for genetic validation. (4) Conclusions: There is enough evidence to state that new science has emerged, focusing on establishing an association between radiological features and genomic/molecular expression to explain underlying disease mechanisms and enhance prognostic, risk assessment, and treatment response radiomics models in cancer patients.

Preoperative prediction of KRAS mutation status in colorectal cancer using a CT-based radiomics nomogram

OBJECTIVE

This study aimed to develop a model to predict KRAS mutations in colorectal cancer according to radiomic signatures based on CT and clinical risk factors.

METHODS

This retrospective study included 172 patients with colorectal cancer. All patients were randomized at a 7:3 ratio into a training cohort (n = 121, 38.8% positive for KRAS mutation) and a validation cohort (n = 51, 39.2% positive for KRAS mutation). Radiomics features were extracted from single-slice and full-volume regions of interest on the portal-venous CT images. The least absolute shrinkage and selection operator (LASSO) algorithm was adopted to construct a radiomics signature, and logistic regression was applied to select the significant variables to develop the clinical-radiomics model. The predictive performance was evaluated by receiver operating characteristic curve (ROC) analysis, calibration curve analysis, and decision curve analysis (DCA).

RESULTS

1018 radiomics features were extracted from single-slice and full-volume ROIs. Eight features were retained to construct 2D (two-dimensional, 2D) radiomics model. Similarly, eight features were retained to construct 3D (three-dimensional, 3D) radiomics model. The area under the curve (AUC) values of the test cohort were 0.75 and 0.84, respectively. Delong test showed that the integrated nomogram (AUC = 0.92 in the test cohort) had better clinical predictive efficiency than 2D radiomics (p-value < 0.05) model and 3D radiomics model (p-value < 0.05).

CONCLUSION

The 2D and 3D radiomics models can both predict KRAS mutations. And, the integrated nomogram can be better applied to predict KRAS mutation status in colorectal cancer.

ADVANCES IN KNOWLEDGE

CT-based radiomics showed satisfactory diagnostic significance for the KRAS status in colorectal cancer, the clinical-combined model may be applied in the individual pre-operative prediction of KRAS mutation.

Preoperative Prediction of Perineural Invasion Status of Rectal Cancer Based on Radiomics Nomogram of Multiparametric Magnetic Resonance Imaging

Objectives

To compare the predictive performance of different radiomics signatures from multiparametric magnetic resonance imaging (mpMRI), including four sequences when used individually or combined, and to establish and validate an optimal nomogram for predicting perineural invasion (PNI) in rectal cancer (RC) patients.

Methods

Our retrospective study included 279 RC patients without preoperative antitumor therapy (194 in the training dataset and 85 in the test dataset) who underwent preoperative mpMRI scan between January 2017 and January 2021. Among them, 72 cases were PNI-positive. Then, clinical and radiological variables were collected, including carcinoembryonic antigen (CEA), radiological tumour stage (T_1-4), lymph node stage (N_0-2) and so on. Quantitative radiomics features were extracted and selected from oblique axial T₂-weighted imaging (T₂WI), T₁-weighted imaging (T₁WI), apparent diffusion coefficient (ADC), and enhanced T₁WI (T₁CE) sequences. The clinical model was constructed by integrating the final selected clinical and radiological variables. The radiomics signatures included four single-sequence signatures and one fusion signature were built using the respective remaining optimized features. And the nomogram was constructed based on the independent predictors by using multivariable logistic regression. The area under curve (AUC), DeLong test, calibration curve, and decision curve analysis (DCA) were used to evaluate the performance.

Results

Ultimately, 20 radiomics features were retained from the four sequences—T₁WI (n = 4), T₂WI (n = 5), ADC (n = 5), and T₁CE (n = 6)—to construct four single-sequence radiomics signatures and one fusion radiomics signature. The fusion radiomics signature performed better than four single-sequence radiomics signatures and clinical model (AUCs of 0.835 and 0.773 vs. 0.680-0.737 and 0.666-0.709 in the training and test datasets, respectively). The nomogram constructed by incorporating CEA, tumour stage and rad-score performed best, with AUCs of 0.869 and 0.864 in the training and test datasets, respectively. Delong test showed that the nomogram was significantly different from the clinical model and four single-sequence radiomics signatures (P < 0.05). Moreover, calibration curves demonstrated good agreement, and DCA highlighted benefits of the nomogram.

Conclusions

The comprehensive nomogram can preoperatively and noninvasively predict PNI status, provide a convenient and practical tool for treatment strategy, and help optimize individualized clinical decision-making in RC patients.

The value of 18F-FDG PET/CT-based radiomics in predicting perineural invasion and outcome in non-metastatic colorectal cancer

PURPOSE

Perineural invasion (PNI) has been recognized as an important prognosis factor in patients with colorectal cancer (CRC). The purpose of this retrospective study was to investigate the value of ¹⁸F-FDG PET/CT-based radiomics integrating clinical information, PET/CT features, and metabolic parameters for preoperatively predicting PNI and outcome in non-metastatic CRC and establish an easy-to-use nomogram.

METHODS

A total of 131 patients with non-metastatic CRC who undergo PET/CT scan were retrospectively enrolled. Univariate analysis was used to compare the differences between PNI-present and PNI-absent groups. Multivariate logistic regression was performed to select the independent predictors for PNI status. Akaike information criterion (AIC) was used to select the best prediction models for PNI status. CT radiomics signatures (RSs) and PET-RSs were selected by maximum relevance minimum redundancy (mRMR) and the least absolute shrinkage and selection operator algorithm (LASSO) regression and radiomics scores (Rad-scores) were calculated for each patient. The prediction models with or without Rad-score were established. According to the nomogram, nomogram scores (Nomo-scores) were calculated for each patient. The performance of different models was assessed with the area under the curve (AUC), specificity, and sensitivity. The clinical usefulness was assessed by decision curve (DCA). Multivariate Cox regression was used to selected independent predictors of progression-free survival (PFS).

RESULTS

Among all the clinical information, PET/CT features, and metabolic parameters, CEA, lymph node metastatic on PET/CT (N stage), and total lesion glycolysis (TLG) were independent predictors for PNI (p < 0.05). Six CT-RSs and 12 PET-RSs were selected as the most valuable factors to predict PNI. The Rad-score calculated with these RSs was significantly different between PNI-present and PNI-absent groups (p < 0.001). The AUC of the constructed model was 0.90 (95%CI: 0.83-0.97) in the training cohort and 0.80 (95%CI: 0.65-0.95) in the test cohort. The nomogram's predicting sensitivity was 0.84 and the specificity was 0.83 in the training cohort. The clinical model's predicting sensitivity and specificity were 0.66 and 0.85 in the training cohort, respectively. Besides, DCA showed that patients with non-metastatic CRC could get more benefit with our model. The results also indicated that N stage, PNI status, and the Nomo-score were independent predictors of PFS in patients with non-metastatic CRC.

CONCLUSION

The nomogram, integrating clinical data, PET/CT features, metabolic parameters, and radiomics, performs well in predicting PNI status and is associated with the outcome in patients with non-metastatic CRC.

Machine Learning Algorithms for Predicting Surgical Outcomes after Colorectal Surgery: A Systematic Review

BACKGROUND

Machine learning (ML) has been introduced in various fields of healthcare. In colorectal surgery, the role of ML has yet to be reported. In this systematic review, an overview of machine learning models predicting surgical outcomes after colorectal surgery is provided.

METHODS

Databases PubMed, EMBASE, Cochrane, and Web of Science were searched for studies using machine learning models for patients undergoing colorectal surgery. To be eligible for inclusion, studies needed to apply machine learning models for patients undergoing colorectal surgery. Absence of machine learning or colorectal surgery or studies reporting on reviews, children, study abstracts were excluded. The Probast risk of bias tool was used to evaluate the methodological quality of machine learning models.

RESULTS

A total of 1821 studies were analysed, resulting in the inclusion of 31 articles. A vast proportion of ML algorithms have been used to predict the course of disease and response to neoadjuvant chemoradiotherapy. Radiomics have been applied most frequently, along with predictive accuracies up to 91%. However, most studies included a retrospective study design without external validation or calibration.

CONCLUSIONS

Machine learning models have shown promising potential in predicting surgical outcomes after colorectal surgery. However, large-scale data is warranted to bridge the gap between calibration and external validation. Clinical implementation is needed to demonstrate the contribution of ML within daily practice.

AI in spotting high-risk characteristics of medical imaging and molecular pathology

Medical imaging provides a comprehensive perspective and rich information for disease diagnosis. Combined with artificial intelligence technology, medical imaging can be further mined for detailed pathological information. Many studies have shown that the macroscopic imaging characteristics of tumors are closely related to microscopic gene, protein and molecular changes. In order to explore the function of artificial intelligence algorithms in in-depth analysis of medical imaging information, this paper reviews the articles published in recent years from three perspectives: medical imaging analysis method, clinical applications and the development of medical imaging in the direction of pathological molecular prediction. We believe that AI-aided medical imaging analysis will be extensively contributing to precise and efficient clinical decision.

A multitask dual-stream attention network for the identification of KRAS mutation in colorectal cancer

PURPOSE

It is of great significance to accurately identify the KRAS gene mutation status for patients in tumor prognosis and personalized treatment. Although the computer-aided diagnosis system based on deep learning has gotten all-round development, its performance still cannot meet the current clinical application requirements due to the inherent limitations of small-scale medical image data set and inaccurate lesion feature extraction. Therefore, our aim is to propose a deep learning model based on T2 MRI of colorectal cancer (CRC) patients to identify whether KRAS gene is mutated.

METHODS

In this research, a multitask attentive model is proposed to identify KRAS gene mutations in patients, which is mainly composed of a segmentation subnetwork and an identification subnetwork. Specifically, at first, the features extracted by the encoder of segmentation model are used as guidance information to guide the two attention modules in the identification network for precise activation of the lesion area. Then the original image of the lesion and the segmentation result are concatenated for feature extraction. Finally, features extracted from the second step are combined with features activated by the attention modules to identify the gene mutation status. In this process, we introduce the interlayer loss function to encourage the similarity of the two subnetwork parameters and ensure that the key features are fully extracted to alleviate the overfitting problem caused by small data set to some extent.

RESULTS

The proposed identification model is benchmarked primarily using 15-fold cross validation. Three hundred and eighty-two images from 36 clinical cases were used to test the model. For the identification of KRAS mutation status, the average accuracy is 89.95 ± 1.23%, the average sensitivity is 89.29 ± 1.79%, the average specificity is 90.53 ± 2.45%, and the average area under the curve (AUC) is 95.73 ± 0.52%. For segmentation of lesions, the average dice is 88.11 ± 0.86%.

CONCLUSIONS

We developed a novel deep learning-based model to identify the KRAS status in CRC. We demonstrated the excellent properties of the proposed identification through comparison with ground truth gene mutation status of 36 clinical cases. And all these results show that the novel method has great potential for clinical application.