Recurrent Hepatocellular Carcinoma: Patterns, Detection, Staging and Treatment

Hernandonine-mediated autophagic cell death in hepatocellular carcinoma: Interplay of p53 and YAP signaling pathways

Hepatocellular carcinoma (HCC), the primary form of liver cancer, is the third leading cause of cancer-related death globally. Hernandonine is a natural alkaloid derived from Hernandia nymphaeifolia that has been shown to exert various biological functions. In a previous study, hernandonine was shown to suppress the proliferation of several solid tumor cell lines without affecting normal human cell lines. However, little is known about the effect of hernandonine on HCC. Therefore, this study aimed to investigate the effect and mechanism of hernandonine on HCC in relation to autophagy. We found that hernandonine inhibited HCC cell growth in vitro and in vivo. In addition, hernandonine elicited autophagic cell death and DNA damage in HCC cells. RNA-seq analysis revealed that hernandonine upregulated p53 and Hippo signaling pathway-related genes in HCC cells. Small RNA interference of p53 resulted in hernandonine-induced autophagic cell death attenuation. However, inhibition of YAP sensitized HCC cells to hernandonine by increasing the autophagy induction. This is the first study to illustrate the complex involvement of p53 and YAP in the hernandonine-induced autophagic cell death in human HCC cells. Our findings provide novel evidence for the potential of hernandonine as a therapeutic agent for HCC treatment.

Lymph Node Metastasis in Gastrointestinal Carcinomas: A View from a Proteomics Perspective

Lymph node metastasis (LNM) is one of the major prognostic factors in human gastrointestinal carcinomas (GICs). The lymph node-positive patients have poorer survival than node-negative patients. LNM is directly associated with the recurrence and poor survival of patients with GICs. The early detection of LNM in patients and designing effective therapies to suppress LNM may significantly impact the survival of these patients. The rapid progress made in proteomic technologies could be successfully applied to identify molecular targets for cancers at high-throughput levels. LC-MS/MS analysis enables the identification of proteins involved in LN metastasis, which can be utilized for diagnostic and therapeutic applications. This review summarizes the studies on LN metastasis in GICs using proteomic approaches to date.

Prognostic value of CMTM6 protein in hepatocellular carcinoma involving the regulation of the immune microenvironment

There have been notable irregularities in CMTM6 expression observed in hepatocellular carcinoma (HCC), with an evident correlation between CMTM6 dysregulation and patient prognosis. The cell cycle progression came to a halt at the G2/M phase. In-depth RNA-sequencing analysis of CMTM6 knockdown Hep3B cells revealed that the most prominent effect of CMTM6 perturbation was on the expression of CXCL8, a chemokine involved in immune responses, particularly through the interleukin-17F (IL-17F) signaling pathway. By carefully examining the RNA-sequencing data obtained from CMTM6 knockdown Hep3B cells and cross-referencing it with the TCGA-LIHC database, we were able to discern that CMTM6 and programmed death-ligand 1 (PD-L1) collaboratively partake in immune regulation within T cells. Furthermore, CMTM6 exerted an influential role in modulating the infiltration of CD4+ and CD8+ T cells in the HCC microenvironment, thereby impacting the overall immune response. Our investigation found that HCC cases characterized by an elevated co-expression of CMTM6 and PD-L1, along with augmented CD4+ T cell infiltration, demonstrated comparatively longer overall and progression-free survival rates when contrasted with those displaying lower CD4+ T cell infiltration.

Salvage liver transplantation versus curative treatment for patients with recurrent hepatocellular carcinoma: A systematic review and meta-analysis

BACKGROUND

Salvage liver transplantation (SLT) is an effective treatment option for recurrent hepatocellular carcinoma (rHCC) following primary curative treatment (CUR). However, its efficacy remains controversial compared to that of CURs, including repeat liver resection (RLR) and local ablation. This meta-analysis compared the efficacy and safety of these procedures.

METHODS

A systematic literature search of the PubMed, Embase, Web of Science, and Cochrane Library databases for studies investigating SLT and CUR was performed. Outcome data, including overall and disease-free survival, tumor response, and operative and postoperative outcomes, were independently extracted and analyzed by two authors using a standardized protocol.

RESULTS

Fifteen cohort studies comprising 508 and 2050 patients with rHCC, who underwent SLT or CUR, respectively, were included. SLT achieved significantly longer overall survival than both CUR (hazard ratio [HR]: 0.56, 95 % confidence interval [CI]: 0.45-0.68; I2 = 34.6 %, p = 0.105) and RLR (HR: 0.64, 95 % CI: 0.49-0.84; I2 = 0.0 %, p = 0.639). Similar significantly better survival benefits were observed compared with CUR (HR: 0.30, 95 % CI: 0.20-0.45; I2 = 51.1 %, p = 0.038) or RLR (HR: 0.31, 95 % CI: 0.18-0.56; I2 = 65.7 %, p = 0.005) regarding disease-free survival. However, SLT resulted in a longer operative duration and hospital stay, larger amount of blood loss, higher rate of transfusion and postoperative morbidity, and slightly higher postoperative mortality than CUR.

CONCLUSION

SLT was associated with better long-term survival than CUR or RLR in patients with rHCC after primary curative treatment.

Recurrence and tumor-related death after resection of hepatocellular carcinoma in patients with metabolic syndrome

Background & Aims

Metabolic syndrome (MS) is a growing epidemic and a risk factor for the development of hepatocellular carcinoma (HCC). This study investigated the long-term outcomes of liver resection (LR) for HCC in patients with MS. Rates, timing, patterns, and treatment of recurrences were investigated, and cancer-specific survivals were assessed.

Methods

Between 2001 and 2021, data from 24 clinical centers were collected. Overall survival (OS), recurrence-free survival (RFS), and cancer-specific survival were analyzed as well as recurrence patterns and treatment. The analysis was conducted using a competing-risk framework. The trajectory of the risk of recurrence over time was applied to a competing risk analysis. For post-recurrence survival, death resulting from tumor progression was the primary endpoint, whereas deaths with recurrence relating to other causes were considered as competing events.

Results

In total, 813 patients were included in the study. Median OS was 81.4 months (range 28.1-157.0 months), and recurrence occurred in 48.3% of patients, with a median RFS of 39.8 months (range 15.7-174.7 months). Cause-specific hazard of recurrence showed a first peak 6 months (0.027), and a second peak 24 months (0.021) after surgery. The later the recurrence, the higher the chance of receiving curative intent approaches (p = 0.001). Size >5 cm, multiple tumors, microvascular invasion, and cirrhosis were independent predictors of recurrence showing a cause-specific hazard over time. RFS was associated with death for recurrence (hazard ratio: 0.985, 95% CI: 0.977-0.995; p = 0.002).

Conclusions

Patients with MS undergoing LR for HCC have good long-term survival. Recurrence occurs in 48% of patients with a double-peak incidence and time-specific hazards depending on tumor-related factors and underlying disease. The timing of recurrence significantly impacts survival. Surveillance after resection should be adjusted over time depending on risk factors.

Impact and implications

Metabolic syndrome (MS) is a growing epidemic and a significant risk factor for the development of hepatocellular carcinoma (HCC). The present study demonstrated that patients who undergo surgical resection for HCC on MS have a good long-term survival and that recurrence occurs in almost half of the cases with a double peak incidence and time-specific hazards depending on tumor-related factors and underlying liver disease. Also, the timing of recurrence significantly impacts survival. Clinicians should therefore adjust follow-up after surgery accordingly, considering timing of recurrence and specific risk factors. Also, the results of the present study might help design future trials on the use of adjuvant therapy following resection.

Immunotherapy for hepatocellular carcinoma: The next evolution in expanding access to liver transplantation

Immunotherapy has revolutionised the treatment of advanced hepatocellular carcinoma (HCC). In addition, several phase III trials of immunotherapy in combination with surgical or locoregional therapies for early-to intermediate-stage HCC have recently reported positive results, and other phase III trials in the same patient population are currently in progress. As the application of immunotherapy is shifting to include patients with earlier stages of HCC, one looming question now emerges: What is the role of immunotherapy in the pre-liver transplant population? Liver transplantation is a potentially curative therapy for HCC and confers the additional advantage of restoring a normal, healthy liver. In pre-transplant patients, immunotherapy may improve downstaging success and tumour control at the cost of some immunologic risks. These include immune-related toxicities, which are particularly relevant in a uniquely vulnerable population with chronic liver disease, and the possibility of acute rejection after transplantation. Ultimately, the goal of immunotherapy in this population will be to effectively expand access to liver transplantation while preserving pre- and post-transplant outcomes. In this review, we discuss the mechanisms supporting combination immunotherapy, summarise key recent clinical data from major immunotherapy trials, and explore how immunotherapy can be applied in the neoadjuvant setting prior to liver transplantation in selected high-risk patients.

Machine learning-based radiomic analysis and growth visualization for ablation site recurrence diagnosis in follow-up CT

OBJECTIVES

Detecting ablation site recurrence (ASR) after thermal ablation remains a challenge for radiologists due to the similarity between tumor recurrence and post-ablative changes. Radiomic analysis and machine learning methods may show additional value in addressing this challenge. The present study primarily sought to determine the efficacy of radiomic analysis in detecting ASR on follow-up computed tomography (CT) scans. The second aim was to develop a visualization tool capable of emphasizing regions of ASR between follow-up scans in individual patients.

MATERIALS AND METHODS

Lasso regression and Extreme Gradient Boosting (XGBoost) classifiers were employed for modeling radiomic features extracted from regions of interest delineated by two radiologists. A leave-one-out test (LOOT) was utilized for performance evaluation. A visualization method, creating difference heatmaps (diff-maps) between two follow-up scans, was developed to emphasize regions of growth and thereby highlighting potential ASR.

RESULTS

A total of 55 patients, including 20 with and 35 without ASR, were included in the radiomic analysis. The best performing model was achieved by Lasso regression tested with the LOOT approach, reaching an area under the curve (AUC) of 0.97 and an accuracy of 92.73%. The XGBoost classifier demonstrated better performance when trained with all extracted radiomic features than without feature selection, achieving an AUC of 0.93 and an accuracy of 89.09%. The diff-maps correctly highlighted post-ablative liver tumor recurrence in all patients.

CONCLUSIONS

Machine learning-based radiomic analysis and growth visualization proved effective in detecting ablation site recurrence on follow-up CT scans.

Modified Biejia Jianwan decoction restrains PD-L1-mediated immune evasion through the HIF-1α/STAT3/NF-κB signaling pathway

ETHNOPHARMACOLOGICAL RELEVANCE

Modified Biejia Jianwan (M-BJJW), a Traditional Chinese Medicine (TCM) decoction, has exhibited great potential in treating hepatocellular carcinoma (HCC). However, its underlying functional mechanism still remains unknown.

AIM OF THE STUDY

The study aimed to explore the anti-hepatocarcinogenic effects of M-BJJW, specifically its influence on PD-L1-mediated immune evasion in hypoxic conditions, and elucidate the related molecular mechanisms in HCC.

MATERIALS AND METHODS

To investigate the therapeutic efficacy and mechanisms underlying M-BJJW's effects on HCC, we employed a diethylnitrosamine (DEN)-induced rat model maintained for 120 days. Following model establishment, flow cytometry was utilized to assess the distribution of immune cell populations in peripheral blood, spleens, and tumor tissues after M-BJJW administration. Simultaneously, enzyme-linked immunosorbent assays (ELISA) were conducted to analyze cytokine profiles in serum samples. Immunohistochemistry was employed to determine the expression levels of crucial proteins within tumor tissues. Furthermore, HCC cells exposed to CoCl2 underwent Western blot analysis to validate the expression levels of HIF-1α, PD-L1, STAT3, and nuclear factor kappa B (NF-κB) p65. The modulatory effects of STAT3 and NF-κB p65 were investigated using specific inhibitors and activators in wild-type cell lines. High-performance liquid chromatography coupled with mass spectrometry (HPLC/MS) was utilized to identify the chemical constituents present in M-BJJW-medicated serum. The immunomodulatory properties and the anti-tumor activities of M-BJJW were evaluated by co-culturing with peripheral blood mononuclear cells (PBMC) and the CCK-8 assay. Additionally, we assessed M-BJJW's impact on hypoxia-induced alterations in HCC cell lines using immunofluorescence and Western blot assessments.

RESULTS

M-BJJW exhibited substantial therapeutic advantages by effectively alleviating pathological deterioration within the HCC microenvironment. In the DEN-induced rat model, M-BJJW administration notably reduced tumor growth. Flow cytometry analyses revealed an increased proportion of Cytotoxic T lymphocytes (CTLs) accompanied by a simultaneous decrease in regulatory T cells (Tregs). ELISA data supported a marked decrease in pro-inflammatory cytokines, including interleukin-6 (IL-6), interleukin-10 (IL-10), and tumor necrosis factor α (TNF-α). Immunohistochemistry confirmed the suppressive effect of M-BJJW on the expression of HIF-1α and PD-L1. Notably, western blotting unveiled the role of HIF-1α in regulating PD-L1 expression via the STAT3 and NF-κB signaling pathways in HCC cell lines, which was validated using activators and inhibitors of STAT3 and NF-κB. The CCK-8 assay and co-culture techniques demonstrated the anti-tumor activity of M-BJJW. Immunofluorescence and western blotting further confirmed that M-BJJW-containing serum dose-dependently inhibited HIF-1α, PD-L1, p-STAT3, and p-p65 in hypoxic HCC cell lines.

CONCLUSIONS

M-BJJW demonstrates significant therapeutic potential against HCC by influencing the hypoxic microenvironment, thereby regulating the immunosuppressive milieu. Specifically, M-BJJW modulates the HIF-1α/STAT3/NF-κB signaling pathway, leading to reduced PD-L1 expression and an elevated ratio of cytotoxic T lymphocytes (CTLs), while concurrently decreasing T regulatory cells (Tregs) and immunosuppressive factors. These synergistic effects aid in countering PD-L1-mediated immune evasion, presenting compelling pharmacological evidence supporting the clinical application of M-BJJW as a therapeutic approach for HCC.

Long-term survival analysis of ultrasound-guided percutaneous microwave ablation for hepatocellular carcinoma conforming to the Milan criteria: primary versus recurrent HCC

BACKGROUND

This study compared long-term outcomes between patients with initial hepatocellular carcinoma (IHCC) and those with recurrent HCC (RHCC) treated with microwave ablation (MWA).

METHODS

This retrospective study included 425 patients with HCCs (294 IHCCs and 131 RHCCs) within the Milan criteria who were treated with ultrasound-guided percutaneous MWA between January 2008 and November 2021. All patients with RHCC had previously undergone MWA for initial HCC. Overall survival (OS) and recurrence-free survival (RFS) rates were compared between the IHCC and RHCC groups before and after propensity score matching (PSM).

RESULTS

Before matching, the 1-, 3-, 5-, and 10-year OS rates in the IHCC group were 95.9%, 78.5%, 60.2%, and 42.5%, respectively, which were significantly higher than those in the RHCC group (93.8%, 70.0%, 42.0%, and 6.6%, respectively). This difference remained significant after PSM. However, subgroup analyses suggested that there were no significant differences in OS rates between IHCC and RHCC in patients with solitary HCC ≤3.0 cm, AFP ≤200 ng/mL, ablative margins ≥0.5 cm, or Albumin-Bilirubin (ALBI) grade 1. RFS was significantly higher in IHCC than in RHCC before and after PSM, as well as in subgroup analyses. ALBI grade (hazard ratio (HR), 2.38; 95% CI: 1.46-3.86; p < 0.001), serum AFP level (HR, 2.07; 95% CI: 1.19-3.62; p = 0.010) and ablative margins (HR, 0.18; 95% CI: 0.06-0.59; p = 0.005) were independent prognostic factors for OS of RHCC. Serum AFP(HR, 1.29; 95% CI: 1.02-1.63, p = 0.036) level was the only factor associated with RFS in RHCC.

CONCLUSIONS

MWA yielded comparable OS in IHCC and RHCC patients with solitary HCC ≤3.0 cm, AFP ≤200 ng/mL, ablative margins ≥0.5 cm, or ALBI grade 1.

From prediction to prevention: Machine learning revolutionizes hepatocellular carcinoma recurrence monitoring

In this editorial, we comment on the article by Zhang et al entitled Development of a machine learning-based model for predicting the risk of early postoperative recurrence of hepatocellular carcinoma. Hepatocellular carcinoma (HCC), which is characterized by high incidence and mortality rates, remains a major global health challenge primarily due to the critical issue of postoperative recurrence. Early recurrence, defined as recurrence that occurs within 2 years posttreatment, is linked to the hidden spread of the primary tumor and significantly impacts patient survival. Traditional predictive factors, including both patient- and treatment-related factors, have limited predictive ability with respect to HCC recurrence. The integration of machine learning algorithms is fueled by the exponential growth of computational power and has revolutionized HCC research. The study by Zhang et al demonstrated the use of a groundbreaking preoperative prediction model for early postoperative HCC recurrence. Chall-enges persist, including sample size constraints, issues with handling data, and the need for further validation and interpretability. This study emphasizes the need for collaborative efforts, multicenter studies and comparative analyses to validate and refine the model. Overcoming these challenges and exploring innovative approaches, such as multi-omics integration, will enhance personalized oncology care. This study marks a significant stride toward precise, effi-cient, and personalized oncology practices, thus offering hope for improved patient outcomes in the field of HCC treatment.

Early versus Late Recurrence of Hepatocellular Carcinoma after Microwave Ablation: Patterns, Treatments, and Post-Recurrence Survival

INTRODUCTION

Recurrence after microwave ablation (MWA) has not been extensively studied. We aimed to investigate the patterns, treatments, and survival of patients with hepatocellular carcinoma (HCC) who experienced early and late recurrence after MWA.

METHODS

This retrospective study included patients with HCC recurrence after MWA as the initial treatment from January 2008 to December 2021. Recurrence patterns, treatments, and outcomes between patients with early and late HCC recurrence were compared. Prognostic factors of post-recurrence survival (PRS) were identified by multivariable Cox regression analyses.

RESULTS

Among 222 patients, 128 developed early recurrence (≤2 years after MWA) and 94 had late recurrence (>2 years). Majority of the recurrent HCC were intrahepatic-only recurrence, within the Milan criteria, and received potentially curative treatment. No significant differences in the recurrence patterns, vascular invasion, tumor staging, post-recurrence treatments, or median PRS (35.0 vs. 33.0 months, p = 0.523) were identified between patients with early and late recurrence. Multivariable analyses suggested that multiple tumor number (hazard ratio [HR]: 1.54; 95% CI: 1.03-2.30, p = 0.038), extrahepatic recurrence (HR: 2.14, 95% CI: 1.16-3.92, p = 0.015), vascular invasion (HR: 2.37, 95% CI: 1.18-4.76, p = 0.038), and higher ALBI grade (HR: 2.18, 95% CI: 1.54-3.08, p < 0.001) were independent risk factors of worse PRS, while curative treatment after recurrence (HR: 0.59, 95% CI: 0.38-0.92, p = 0.020) was associated with better PRS.

CONCLUSIONS

No differences in recurrence patterns, post-recurrence treatments, or PRS were found between HCC patients with early and late recurrence following MWA. Tumor burden and patients' liver function reserve should be considered to decide the optimal post-recurrence treatment after MWA.

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.

Effect of multiple peritumoral regions of interest ranges based on computed tomography radiomics for the prediction of early recurrence of hepatocellular carcinoma after resection

Background

Early recurrence (ER) of hepatocellular carcinoma (HCC) is defined as recurrence that occurs within two years after resection. Our study aimed to determine the optimal peritumoral regions of interest (ROI) range by comparing the effect of multiple peritumoral radiomics ROIs on predicting ER of HCC, and to develop and validate a combined clinical-radiomics prediction model.

Methods

A total of 160 HCC patients were randomly divided into a training cohort (n=112) and a validation cohort (n=48). The intratumoral original ROI was outlined based on enhanced computed tomography images and then used as the base to sequentially extend outward 1-5 mm to form peritumoral ROI. We developed a logistic regression model to predict ER of HCC. The efficacy of different ROI prediction models was compared to determine the optimal ROI. The combined model divided the patients into a high-risk group and low-risk group.

Results

Ninety-seven (60.6%) of the patients were ER; the remaining 63 (39.4%) were not ER. The area under the curve values and 95% confidence intervals for ROI 3 were 0.867 (0.802-0.933) and 0.807 (0.682-0.931) in the training and validation cohorts, respectively, and ROI 3 was identified as the optimal ROI. Multivariate logistic regression analysis determined microvascular invasion (MVI) (P=0.037) and alpha-fetoprotein (AFP) (P=0.013) to be independent risk factors for ER. The combined clinical-radiomic model containing the radiomics score, MVI, and AFP had the optimal predictive efficacy, with area under the curve values and 95% confidence intervals of 0.903 (0.848-0.957) and 0.830 (0.709-0.952) in the training and validation cohort, respectively. Subgroup analysis showed significantly ER predicted in the high-risk group than the low-risk group (P<0.001).

Conclusions

Peritumoral radiomics 3 mm range was determined as the optimal ROI in this study. The clinical-radiomics combined models can effectively stratify high- and low-risk patients for timely clinical treatment and decision making.

Ethnic disparities in the epidemiology, treatment, and outcome of patients with hepatocellular carcinoma in the United States

There are significant ethnic disparities in incidence, tumor stage, curative therapy receipt, and survival among patients with hepatocellular carcinoma (HCC) in the US. While previous models had predicted an increasing trend in the incidence rate of HCC until 2030 in the US, recent studies have shown that HCC incidence plateaued in 2013 and then started to decline in 2015. The decreasing trend has been observed in all ethnicities except for American Indians/Alaska Natives, whose incidence rates of HCC continue to rise. Current evidence shows that African-Americans and Hispanics are two groups that are more likely to be diagnosed with late-stage HCC, and this finding has been consistent in different socioeconomic statuses of the patients. These two ethnic minority groups are also among those who are less likely to have curative therapy for early-stage HCC. Finally, advances in early diagnosis and treatment approaches have led to an improvement in HCC survival for all ethnicities; however, African-Americans continue to have the worst survival. More studies to find the causes of these disparities and interventions to eliminate them are urgently needed.

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.