Machine learning and radiomics analysis by computed tomography in colorectal liver metastases patients for RAS mutational status prediction.

PURPOSE: To assess the efficacy of machine learning and radiomics analysis by computed tomography (CT) in presurgical setting, to predict RAS mutational status in colorectal liver metastases. METHODS: Patient selection in a retrospective study was carried out from January 2018 to May 2021 considering the following inclusion criteria: patients subjected to surgical resection for liver metastases; proven pathological liver metastases; patients subjected to enhanced CT examination in the presurgical setting with a good quality of images; and RAS assessment as standard reference. A total of 851 radiomics features were extracted using the PyRadiomics Python package from the Slicer 3D image computing platform after slice-by-slice segmentation on CT portal phase by two expert radiologists of each individual liver metastasis performed first independently by the individual reader and then in consensus. Balancing technique was performed, and inter- and intraclass correlation coefficients were calculated to assess the between-observer and within-observer reproducibility of features. Receiver operating characteristics (ROC) analysis with the calculation of area under the ROC curve (AUC), sensitivity (SENS), specificity (SPEC), positive predictive value (PPV), negative predictive value (NPV) and accuracy (ACC) were assessed for each parameter. Linear and non-logistic regression model (LRM and NLRM) and different machine learning-based classifiers were considered. Moreover, features selection was performed before and after a normalized procedure using two different methods (3-sigma and z-score). RESULTS: Seventy-seven liver metastases in 28 patients with a mean age of 60 years (range 40-80 years) were analyzed. The best predictors, at univariate analysis for both normalized procedures, were original_shape_Maximum2DDiameter and wavelet_HLL_glcm_InverseVariance that reached an accuracy of 80%, an AUC ≥ 0.75, a sensitivity ≥ 80% and a specificity ≥ 70% (p value < < 0.01). However, a multivariate analysis significantly increased the accuracy in RAS prediction when a linear regression model (LRM) was used. The best performance was obtained using a LRM combining linearly 12 robust features after a z-score normalization procedure: AUC of 0.953, accuracy 98%, sensitivity 96%, specificity of 100%, PPV 100% and NPV 96% (p value < < 0.01). No statistically significant increase was obtained considering the tested machine learning both without normalization and with normalization methods. CONCLUSIONS: Normalized approach in CT radiomics analysis allows to predict RAS mutational status in colorectal liver metastases patients.

An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies.

The aim of this informative review was to investigate the application of radiomics in cancer imaging and to summarize the results of recent studies to support oncological imaging with particular attention to breast cancer, rectal cancer and primitive and secondary liver cancer. This review also aims to provide the main findings, challenges and limitations of the current methodologies. Clinical studies published in the last four years (2019-2022) were included in this review. Among the 19 studies analyzed, none assessed the differences between scanners and vendor-dependent characteristics, collected images of individuals at additional points in time, performed calibration statistics, represented a prospective study performed and registered in a study database, conducted a cost-effectiveness analysis, reported on the cost-effectiveness of the clinical application, or performed multivariable analysis with also non-radiomics features. Seven studies reached a high radiomic quality score (RQS), and seventeen earned additional points by using validation steps considering two datasets from two distinct institutes and open science and data domains (radiomics features calculated on a set of representative ROIs are open source). The potential of radiomics is increasingly establishing itself, even if there are still several aspects to be evaluated before the passage of radiomics into routine clinical practice. There are several challenges, including the need for standardization across all stages of the workflow and the potential for cross-site validation using real-world heterogeneous datasets. Moreover, multiple centers and prospective radiomics studies with more samples that add inter-scanner differences and vendor-dependent characteristics will be needed in the future, as well as the collecting of images of individuals at additional time points, the reporting of calibration statistics and the performing of prospective studies registered in a study database.

Scientific Status Quo of Small Renal Lesions: Diagnostic Assessment and Radiomics.

Background: Small renal masses (SRMs) are defined as contrast-enhanced renal lesions less than or equal to 4 cm in maximal diameter, which can be compatible with stage T1a renal cell carcinomas (RCCs). Currently, 50-61% of all renal tumors are found incidentally. Methods: The characteristics of the lesion influence the choice of the type of management, which include several methods SRM of management, including nephrectomy, partial nephrectomy, ablation, observation, and also stereotactic body radiotherapy. Typical imaging methods available for differentiating benign from malignant renal lesions include ultrasound (US), contrast-enhanced ultrasound (CEUS), computed tomography (CT), and magnetic resonance imaging (MRI). Results: Although ultrasound is the first imaging technique used to detect small renal lesions, it has several limitations. CT is the main and most widely used imaging technique for SRM characterization. The main advantages of MRI compared to CT are the better contrast resolution and tissue characterization, the use of functional imaging sequences, the possibility of performing the examination in patients allergic to iodine-containing contrast medium, and the absence of exposure to ionizing radiation. For a correct evaluation during imaging follow-up, it is necessary to use a reliable method for the assessment of renal lesions, represented by the Bosniak classification system. This classification was initially developed based on contrast-enhanced CT imaging findings, and the 2019 revision proposed the inclusion of MRI features; however, the latest classification has not yet received widespread validation. Conclusions: The use of radiomics in the evaluation of renal masses is an emerging and increasingly central field with several applications such as characterizing renal masses, distinguishing RCC subtypes, monitoring response to targeted therapeutic agents, and prognosis in a metastatic context.

Radiomics and machine learning analysis by computed tomography and magnetic resonance imaging in colorectal liver metastases prognostic assessment.

OBJECTIVE: The aim of this study was the evaluation radiomics analysis efficacy performed using computed tomography (CT) and magnetic resonance imaging in the prediction of colorectal liver metastases patterns linked to patient prognosis: tumor growth front; grade; tumor budding; mucinous type. Moreover, the prediction of liver recurrence was also evaluated. METHODS: The retrospective study included an internal and validation dataset; the first was composed by 119 liver metastases from 49 patients while the second consisted to 28 patients with single lesion. Radiomic features were extracted using PyRadiomics. Univariate and multivariate approaches including machine learning algorithms were employed. RESULTS: The best predictor to identify tumor growth was the Wavelet_HLH_glcm_MaximumProbability with an accuracy of 84% and to detect recurrence the best predictor was wavelet_HLH_ngtdm_Complexity with an accuracy of 90%, both extracted by T1-weigthed arterial phase sequence. The best predictor to detect tumor budding was the wavelet_LLH_glcm_Imc1 with an accuracy of 88% and to identify mucinous type was wavelet_LLH_glcm_JointEntropy with an accuracy of 92%, both calculated on T2-weigthed sequence. An increase statistically significant of accuracy (90%) was obtained using a linear weighted combination of 15 predictors extracted by T2-weigthed images to detect tumor front growth. An increase statistically significant of accuracy at 93% was obtained using a linear weighted combination of 11 predictors by the T1-weigthed arterial phase sequence to classify tumor budding. An increase statistically significant of accuracy at 97% was obtained using a linear weighted combination of 16 predictors extracted on CT to detect recurrence. An increase statistically significant of accuracy was obtained in the tumor budding identification considering a K-nearest neighbors and the 11 significant features extracted T1-weigthed arterial phase sequence. CONCLUSIONS: The results confirmed the Radiomics capacity to recognize clinical and histopathological prognostic features that should influence the choice of treatments in colorectal liver metastases patients to obtain a more personalized therapy.

Colorectal liver metastases patients prognostic assessment: prospects and limits of radiomics and radiogenomics.

In this narrative review, we reported un up-to-date on the role of radiomics to assess prognostic features, which can impact on the liver metastases patient treatment choice. In the liver metastases patients, the possibility to assess mutational status (RAS or MSI), the tumor growth pattern and the histological subtype (NOS or mucinous) allows a better treatment selection to avoid unnecessary therapies. However, today, the detection of these features require an invasive approach. Recently, radiomics analysis application has improved rapidly, with a consequent growing interest in the oncological field. Radiomics analysis allows the textural characteristics assessment, which are correlated to biological data. This approach is captivating since it should allow to extract biological data from the radiological images, without invasive approach, so that to reduce costs and time, avoiding any risk for the patients. Several studies showed the ability of Radiomics to identify mutational status, tumor growth pattern and histological type in colorectal liver metastases. Although, radiomics analysis in a non-invasive and repeatable way, however features as the poor standardization and generalization of clinical studies results limit the translation of this analysis into clinical practice. Clear limits are data-quality control, reproducibility, repeatability, generalizability of results, and issues related to model overfitting.

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence.

Pancreatic cancer (PC) is one of the deadliest cancers, and it is responsible for a number of deaths almost equal to its incidence. The high mortality rate is correlated with several explanations; the main one is the late disease stage at which the majority of patients are diagnosed. Since surgical resection has been recognised as the only curative treatment, a PC diagnosis at the initial stage is believed the main tool to improve survival. Therefore, patient stratification according to familial and genetic risk and the creation of screening protocol by using minimally invasive diagnostic tools would be appropriate. Pancreatic cystic neoplasms (PCNs) are subsets of lesions which deserve special management to avoid overtreatment. The current PC screening programs are based on the annual employment of magnetic resonance imaging with cholangiopancreatography sequences (MR/MRCP) and/or endoscopic ultrasonography (EUS). For patients unfit for MRI, computed tomography (CT) could be proposed, although CT results in lower detection rates, compared to MRI, for small lesions. The actual major limit is the incapacity to detect and characterize the pancreatic intraepithelial neoplasia (PanIN) by EUS and MR/MRCP. The possibility of utilizing artificial intelligence models to evaluate higher-risk patients could favour the diagnosis of these entities, although more data are needed to support the real utility of these applications in the field of screening. For these motives, it would be appropriate to realize screening programs in research settings.

Immunotherapy Assessment: A New Paradigm for Radiologists.

Immunotherapy denotes an exemplar change in an oncological setting. Despite the effective application of these treatments across a broad range of tumors, only a minority of patients have beneficial effects. The efficacy of immunotherapy is affected by several factors, including human immunity, which is strongly correlated to genetic features, such as intra-tumor heterogeneity. Classic imaging assessment, based on computed tomography (CT) or magnetic resonance imaging (MRI), which is useful for conventional treatments, has a limited role in immunotherapy. The reason is due to different patterns of response and/or progression during this kind of treatment which differs from those seen during other treatments, such as the possibility to assess the wide spectrum of immunotherapy-correlated toxic effects (ir-AEs) as soon as possible. In addition, considering the unusual response patterns, the limits of conventional response criteria and the necessity of using related immune-response criteria are clear. Radiomics analysis is a recent field of great interest in a radiological setting and recently it has grown the idea that we could identify patients who will be fit for this treatment or who will develop ir-AEs.

Preoperative localisation of nonpalpable breast lesions using magnetic markers in a tertiary cancer centre.

BACKGROUND: We retrospectively evaluated safety and performance of magnetic seed localisation of nonpalpable breast lesions. METHODS: We reviewed records of patients with nonpalpable breast lesions preoperative localised by placing magnetic Magseed® marker between February 2019 and December 2020. During surgery, Sentimag® magnetic probe was used to localise the marker and guide surgery. Safety, lesion identification and excision with tumour with free margins and re-excision rate were assessed. RESULTS: A total of 77 Magseed® devices were placed into the breasts of 73 patients, 44 under ultrasound and 33 under stereotactic guidance (4 bilateral). All devices were retrieved as were the target lesions. Magnetic marker placement was successful in all cases without any adverse event. Intraoperative identification and excision of the localised lesion were successful in 77 of 77 of cases (100%). In three cases (all of them calcifications with the seed placed under stereotactic guidance), the seed did not reach the exact target position of the biopsy clip; thus, larger excision was needed, with localisation failure attributed to incorrect clip insertion (n = 1) or to clip dislocation (n = 2). Migration of the marker was negligible in all patients. Complete excision after the initial procedure with at least 1-mm disease-free margins was obtained in 74 out of 77 (96.1%) lesions. The re-excision rate was 3 out of 77 (4%). CONCLUSIONS: Magnetic marker localisation for nonpalpable breast lesions was safe, reliable, and effective in terms of lesion identification, excision with tumour-free margins and re-excision rate.

Imaging Assessment of Interval Metastasis from Melanoma.

Interval metastasis is a particular metastatic category of metastatic localizations in the lymph nodes in patients with melanoma. Interval nodes are generally located at nonregional lymphatic stations placed along the pathway of the spread of melanoma, such as the epitrochlear lymph node station, the popliteal fossa, and the retroareolar station. Imaging techniques for evaluation of patients with interval metastasis from melanoma diseases include ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), lymphoscintigraphy (LS), and positron emission tomography (PET). A literature review was conducted through a methodical search on the Pubmed and Embase databases. The evaluation of lymph node metastases represents a critical phase in the staging and follow-up of melanoma patients. Therefore, a thorough knowledge of the imaging methods available and the interactions between the clinician and the radiologist are essential for making the correct choice for individual patients, for a better management, and to improve treatment and survival.

Multimodality Imaging Assessment of Desmoid Tumors: The Great Mime in the Era of Multidisciplinary Teams.

Desmoid tumors (DTs), also known as desmoid fibromatosis or aggressive fibromatosis, are rare, locally invasive, non-metastatic soft tissue tumors. Although histological results represent the gold standard diagnosis, imaging represents the fundamental tool for the diagnosis of these tumors. Although histological analysis represents the gold standard for diagnosis, imaging represents the fundamental tool for the diagnosis of these tumors. DTs represent a challenge for the radiologist, being able to mimic different pathological conditions. A proper diagnosis is required to establish an adequate therapeutic approach. Multimodality imaging, including ultrasound (US), computed tomography (CT) and Magnetic Resonance Imaging (MRI), should be preferred. Different imaging techniques can also guide minimally invasive treatments and monitor their effectiveness. The purpose of this review is to describe the state-of-the-art multidisciplinary imaging of DTs; and its role in patient management.

Management of cutaneous melanoma: radiologists challenging and risk assessment.

Melanoma patient remains a challenging for the radiologist, due to the difficulty related to the management of a patient more often in an advanced stage of the disease. It is necessary to determine a stratification of risk, optimizing the means, with diagnostic tools that should be optimized in relation to the type of patient, and improving knowledge. Staging and risk assessment procedures are determined by disease presentation at diagnosis. Melanoma staging is a critical tool to assist clinical decision-making and prognostic assessment. It is used for clinical trial design, eligibility, stratification, and analysis. The current standard for regional lymph nodes staging is represented by the sentinel lymph node excision biopsy procedure. For staging of distant metastases, PET-CT has the highest sensitivity and diagnostic odds ratio. Similar trend is observed during melanoma surveillance. The advent of immunotherapy, which has improved patient outcome, however, has determined new issues for radiologists, partly due to atypical response patterns, partly due to adverse reactions that must be identified as soon as possible for the correct management of the patient. The main objectives of the new ir-criteria are to standardize the assessment between different trials. However, these ir-criteria do not take into account all cases of atypical response patterns, as hyperprogression or dissociated responses. None of these criteria has actually been uniformly adopted in routine. The immune-related adverse events (irAEs) can involve various organs from head to toe. It is crucial for radiologists to know the imaging appearances of this condition, to exclude recurrent or progressive disease and for pneumonitis, since it could be potentially life-threatening toxicity, resulting in pneumonitis-related deaths in early phase trials, to allow a proper patient management.

Radiomics and machine learning analysis based on magnetic resonance imaging in the assessment of liver mucinous colorectal metastases.

PURPOSE: The purpose of this study is to evaluate the Radiomics and Machine Learning Analysis based on MRI in the assessment of Liver Mucinous Colorectal Metastases.Query METHODS: The cohort of patients included a training set (121 cases) and an external validation set (30 cases) with colorectal liver metastases with pathological proof and MRI study enrolled in this approved study retrospectively. About 851 radiomics features were extracted as median values by means of the PyRadiomics tool on volume on interest segmented manually by two expert radiologists. Univariate analysis, linear regression modelling and pattern recognition methods were used as statistical and classification procedures. RESULTS: The best results at univariate analysis were reached by the wavelet_LLH_glcm_JointEntropy extracted by T2W SPACE sequence with accuracy of 92%. Linear regression model increased the performance obtained respect to the univariate analysis. The best results were obtained by a linear regression model of 15 significant features extracted by the T2W SPACE sequence with accuracy of 94%, a sensitivity of 92% and a specificity of 95%. The best classifier among the tested pattern recognition approaches was k-nearest neighbours (KNN); however, KNN achieved lower precision than the best linear regression model. CONCLUSIONS: Radiomics metrics allow the mucinous subtype lesion characterization, in order to obtain a more personalized approach. We demonstrated that the best performance was obtained by T2-W extracted textural metrics.

Nivolumab-ipilimumab in renal cell carcinoma metastatic to the bones: A case report.

In the last recent years, the introduction in the clinical setting of treatment combinations having immune checkpoint inhibitors as the backbone has dramatically improved the outcomes of patients suffering from advanced/metastatic renal cell carcinoma (RCC). Here we report the clinical course of a patient with a rapid and bulky bone recurrence of RCC after nephrectomy, experiencing long-term benefit from nivolumab-ipilimumab administered as first-line treatment.

Complications Risk Assessment and Imaging Findings of Thermal Ablation Treatment in Liver Cancers: What the Radiologist Should Expect.

One of the major fields of application of ablation treatment is liver tumors. With respect to HCC, ablation treatments are considered as upfront treatments in patients with early-stage disease, while in colorectal liver metastases (CLM), they can be employed as an upfront treatment or in association with surgical resection. The main prognostic feature of ablation is the tumor size, since the goal of the treatment is the necrosis of all viable tumor tissue with an adequate tumor-free margin. Radiofrequency ablation (RFA) and microwave ablation (MWA) are the most employed ablation techniques. Ablation therapies in HCC and liver metastases have presented a challenge to radiologists, who need to assess response to determine complication-related treatment. Complications, defined as any unexpected variation from a procedural course, and adverse events, defined as any actual or potential injury related to the treatment, could occur either during the procedure or afterwards. To date, RFA and MWA have shown no statistically significant differences in mortality rates or major or minor complications. To reduce the rate of major complications, patient selection and risk assessment are essential. To determine the right cost-benefit ratio for the ablation method to be used, it is necessary to identify patients at high risk of infections, coagulation disorders and previous abdominal surgery interventions. Based on risk assessment, during the procedure as part of surveillance, the radiologists should pay attention to several complications, such as vascular, biliary, mechanical and infectious. Multiphase CT is an imaging tool chosen in emergency settings. The radiologist should report technical success, treatment efficacy, and complications. The complications should be assessed according to well-defined classification systems, and these complications should be categorized consistently according to severity and time of occurrence.

Analysis of a monocentric computed tomography dosimetric database using a radiation dose index monitoring software: dose levels and alerts before and after the implementation of the adaptive statistical iterative reconstruction on CT images.

OBJECTIVE: To analyze dosimetric data of a single center by a radiation dose index monitoring software evaluating quantitatively the dose reduction obtained with the implementation of the adaptive statistical iterative reconstruction (ASIR) on Computed Tomography in terms of both the value of the dose length product (DLP) and the alerts provided by the dose tool. METHODS: Dosimetric quantities were acquired using Qaelum DOSE tool (QAELUM NV, Leuven-Heverlee, Belgium). Dose data pertaining to CT examinations were performed using a General Electric Healthcare CT tomography with 64 detectors. CT dose data were collected over 4 years (January 1, 2017 to December 31, 2020) and included CT dose length product (DLP). Moreover, all CT examinations that triggered a high radiation dose (twice the median for that study description), termed alerts on Dose tool, were retrieved for the analysis. Two radiologists retrospectively assessed CT examinations in consensus for the images quality and for the causes of the alerts issued. A Chi-square test was used to assess whether there were any statistically significant differences among categorical variable while a Kruskal Wallis test was considered to assess differences statistically significant for continuous variables. RESULTS: Differences statistically significant were found for the DLP median values between the dosimetric data recorded on 2017-2018 versus 2019-2020. The differences were linked to the implementation of ASIR technique at the end of 2018 on the CT scanner. The highest percentage of alerts was reported in the CT study group "COMPLETE ABDOMEN + CHEST + HEAD" (range from 1.26% to 2.14%). A reduction year for year was relieved linked to the CT protocol optimization with a difference statistically significant. The highest percentage of alerts was linked to wrong study label/wrong study protocol selection with a range from 29 to 40%. CONCLUSIONS: Automated methods of radiation dose data collection allowed for detailed radiation dose analysis according to protocol and equipment over time. The use of CT ASIR technique could determine considerable reduction in radiation dose.

Magnetic Resonance Features of Liver Mucinous Colorectal Metastases: What the Radiologist Should Know.

Purpose: The aim of this study is to assess MRI features of mucinous liver metastases compared to non-mucinous metastases and hepatic hemangioma. Methods: A radiological archive was assessed from January 2017 to June 2021 to select patients subjected to liver resection for CRCLM and MRI in the staging phase. We selected 20 patients with hepatic hemangioma (study group B). We evaluated (a) the maximum diameter of the lesions, in millimeters, on T1-W flash 2D in phase and out phase, on axial HASTE T2-W and on portal phase axial VIBE T1 W; and (b) the signal intensity (SI) in T1-W sequences, in T2-W sequences, Diffusion-Weighted Imaging (DWI) sequences and apparent diffusion coefficient (ADC) maps so as to observe (c) the presence and the type of contrast enhancement during the contrast study. The chi-square test was employed to analyze differences in percentage values of the categorical variable, while the non-parametric Kruskal−Wallis test was used to test for statistically significant differences between the median values of the continuous variables. A p-value < 0.05 was considered statistically significant. Results: The final study population included 52 patients (33 men and 19 women) with 63 years of median age (range 37−82 years) and 157 metastases. In 35 patients, we found 118 non-mucinous type metastases (control group), and in 17 patients, we found 39 mucinous type metastases (study group A). During follow-up, recurrence occurred in 12 patients, and three exhibited mucinous types among them. In the study group, all lesions (100%) showed hypointense SI on T1-W, very high SI (similar to hepatic hemangioma) in T2-W with restricted diffusion and iso-hypointense signals in the ADC map. During the contrast study, the main significant feature is the peripheral progressive enhancement.

CT-Based Radiomics Analysis to Predict Histopathological Outcomes Following Liver Resection in Colorectal Liver Metastases.

PURPOSE: We aimed to assess the efficacy of radiomic features extracted by computed tomography (CT) in predicting histopathological outcomes following liver resection in colorectal liver metastases patients, evaluating recurrence, mutational status, histopathological characteristics (mucinous), and surgical resection margin. METHODS: This retrospectively approved study included a training set and an external validation set. The internal training set included 49 patients with a median age of 60 years and 119 liver colorectal metastases. The validation cohort consisted of 28 patients with single liver colorectal metastasis and a median age of 61 years. Radiomic features were extracted using PyRadiomics on CT portal phase. Nonparametric Kruskal-Wallis tests, intraclass correlation, receiver operating characteristic (ROC) analyses, linear regression modeling, and pattern recognition methods (support vector machine (SVM), k-nearest neighbors (KNN), artificial neural network (NNET), and decision tree (DT)) were considered. RESULTS: The median value of intraclass correlation coefficients for the features was 0.92 (range 0.87-0.96). The best performance in discriminating expansive versus infiltrative front of tumor growth was wavelet_HHL_glcm_Imc2, with an accuracy of 79%, a sensitivity of 84%, and a specificity of 67%. The best performance in discriminating expansive versus tumor budding was wavelet_LLL_firstorder_Mean, with an accuracy of 86%, a sensitivity of 91%, and a specificity of 65%. The best performance in differentiating the mucinous type of tumor was original_firstorder_RobustMeanAbsoluteDeviation, with an accuracy of 88%, a sensitivity of 42%, and a specificity of 100%. The best performance in identifying tumor recurrence was the wavelet_HLH_glcm_Idmn, with an accuracy of 85%, a sensitivity of 81%, and a specificity of 88%. The best linear regression model was obtained with the identification of recurrence considering the linear combination of the 16 significant textural metrics (accuracy of 97%, sensitivity of 94%, and specificity of 98%). The best performance for each outcome was reached using KNN as a classifier with an accuracy greater than 86% in the training and validation sets for each classification problem; the best results were obtained with the identification of tumor front growth considering the seven significant textural features (accuracy of 97%, sensitivity of 90%, and specificity of 100%). CONCLUSIONS: This study confirmed the capacity of radiomics data to identify several prognostic features that may affect the treatment choice in patients with liver metastases, in order to obtain a more personalized approach.

Contrast MR-Based Radiomics and Machine Learning Analysis to Assess Clinical Outcomes following Liver Resection in Colorectal Liver Metastases: A Preliminary Study.

PURPOSE: To assess radiomics features efficacy obtained by arterial and portal MRI phase in the prediction of clinical outcomes in the colorectal liver metastases patients, evaluating recurrence, mutational status, pathological characteristic (mucinous and tumor budding) and surgical resection margin. METHODS: This retrospective analysis was approved by the local Ethical Committee board, and radiological databases were used to select patients with colorectal liver metastases with pathological proof and MRI study in a pre-surgical setting after neoadjuvant chemotherapy. The cohort of patients included a training set (51 patients with 61 years of median age and 121 liver metastases) and an external validation set (30 patients with single lesion with 60 years of median age). For each segmented volume of interest on MRI by two expert radiologists, 851 radiomics features were extracted as median values using the PyRadiomics tool. Non-parametric Kruskal-Wallis test, intraclass correlation, receiver operating characteristic (ROC) analysis, linear regression modelling and pattern recognition methods (support vector machine (SVM), k-nearest neighbors (KNN), artificial neural network (NNET), and decision tree (DT)) were considered. RESULTS: The best predictor to discriminate expansive versus infiltrative tumor growth front was wavelet_LHH_glrlm_ShortRunLowGrayLevelEmphasis extracted on portal phase with accuracy of 82%, sensitivity of 84%, and specificity of 77%. The best predictor to discriminate tumor budding was wavelet_LLH_firstorder_10Percentile extracted on portal phase with accuracy of 92%, a sensitivity of 96%, and a specificity of 81%. The best predictor to differentiate the mucinous type of tumor was the wavelet_LLL_glcm_ClusterTendency extracted on portal phase with accuracy of 88%, a sensitivity of 38%, and a specificity of 100%. The best predictor to identify the recurrence was the wavelet_HLH_ngtdm_Complexity extracted on arterial phase with accuracy of 90%, a sensitivity of 71%, and a specificity of 95%. The best linear regression model was obtained in the identification of mucinous type considering the 13 textural significant metrics extracted by arterial phase (accuracy of 94%, sensitivity of 77% and a specificity of 99%). The best results were obtained in the identification of tumor budding with the eleven textural significant features extracted by arterial phase using a KNN (accuracy of 95%, sensitivity of 84%, and a specificity of 99%). CONCLUSIONS: Our results confirmed the capacity of radiomics to identify as biomarkers and several prognostic features that could affect the treatment choice in patients with liver metastases in order to obtain a more personalized approach.