The role of radiomics in hepato-bilio-pancreatic surgery: a literature review

The role


INTRODUCTION
Hepato-bilio-pancreatic (HBP) surgery comprises demanding and complex procedures, the planning of which requires highly specific radiological skills for diagnosis, staging, and evaluation of treatment response.The interpretation of imaging results, in view of the clinical findings, relies heavily on the training and experience of the radiologist; as such, the conventional process of image interpretation has limited diagnostic accuracy and reproducibility.Moreover, radiological images contain a large amount of information that is invisible even to an experienced human eye.
Radiomics is an advanced computational analysis of biomedical images, including ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET), that aims to obtain an objective, detailed, and multidimensional characterization of biological tissues through the extraction of numerical features by converting images into mineable data.Radiomics features numerically describe and quantify the spatial distribution and relationships between the voxels that compose a "black and white" image, which ultimately reflect the underlying physiopathology of the tissue under study [1] .Although the clinical role of radiologists in patients' care remains a cornerstone of cancer imaging, the addition of radiomics features to the visual assessment of an imaging examination may improve the diagnostic performance of radiologists, the reproducibility of the results, and the patients' outcomes by identifying adverse pathological features, predicting disease recurrence and survival, and improving the evaluation of treatment response, which are extremely important for HBP surgery.Previous reports revealed that radiomics is a promising tool to improve the non-invasive characterization and preoperative staging of HBP neoplasms [1] .Nevertheless, each individual step in the process of radiomics has technical challenges that result in a significant translational gap between research and clinical practice.
The aim of this paper was to review the current role of radiomics in HBP surgery by analyzing systematic reviews, meta-analyses and the most relevant published series.

RADIOMICS: WORKFLOW, POTENTIAL AND LIMITATIONS
The most important field of application of radiomics is oncological imaging.The underlying hypothesis is that radiomics features parallelize the heterogeneity that characterizes tumor histology, allowing deep exploration of tumor microenvironment and intra-and inter-tumoral heterogeneity, which are ultimately related to the biological and genomic characteristics [2] .The workflow of radiomics consists of several steps [3] : (1) acquisition of standardized, high-quality radiological images; (2) accurate segmentation of the tumor mass with delineation of a volume of interest (VOI); (3) extraction of reproducible, non-redundant and uncorrelated radiomics features; (4) integration of radiomics features with pathological and clinical data; (5) construction of a database for data mining.
Each of these steps is a potential source of bias that may affect the quality, robustness and reproducibility of the results.Given that a single voxel can influence the radiomics features, differences in the equipment, for example, the magnetic field strength in MRI and the number of detectors in CT, and the image acquisition protocols lead to relevant discrepancies between studies.
Segmentation, defined as the delineation of the tumor mass relative to adjacent structures, is one of the most important sources of variability.Manual tumor segmentation is time-consuming and limited by human capabilities, but also has the advantage of being controlled in real time by the human eye; on the other hand, automatic tumor segmentation is fast and highly standardizable, but lacks the ability to iteratively understand whether data are being acquired correctly; finally, semi-automatic tumor segmentation seems to be the most effective method because it combines the advantages of computer technology with the control of the human eye [3] .Radiomic feature extraction is a poorly standardized process, given the multitude of software applications that work differently to convert voxels to numerical data; furthermore, post-processing of biomedical images can be done with several different modeling algorithms.Both these aspects increase the heterogeneity between studies.Finally, large, shared databases for data mining would be essential to validate the results of single studies by interrogating separate populations of patients and to obtain study cohorts with sufficient size for statistical power.
Radiomic research initially used manual tumor segmentation and conventional statistical tests, such as the Fisher's or Wilcoxon tests, to select radiomics features; more complex statistical analyses, such as the least absolute shrinkage and selection operator (LASSO), were then used to select predictive features.Although this approach is easy to perform even by operators without specific experience in image processing and statistical analysis, it is time-consuming and its application is limited to small populations.The current research trend relies on machine learning (ML) methods, as they allow for a higher level of automation compared to the traditional workflow, providing faster segmentation and feature extraction as well as advantages in terms of reproducibility.Despite these benefits, ML-based radiomics are limited by the high correlation to the quality of the input data (i.e., the accuracy of the segmentation and the size of the training population); therefore, large datasets are necessary to identify robust features.
Researchers' interest in radiomics has exploded in recent years, and thousands of studies on several different settings have been published.As a decade of radiomics research is approaching, it is time for a critical review of what results have been achieved and what has been translated into clinical practice.The Radiomics Quality Score (RQS) was developed to evaluate the methodological quality of a radiomic study [4] .The RQS consists of 16 criteria, with a score of 36 (or 100%) indicating excellent study quality [Table 1].A recent study [5] reported a median RQS of 21% among 44 systematic reviews on radiomics, suggesting that the quality in this research field needs to be increased as it is currently unsatisfactory regardless of the topic.

METHODS
A search of the MEDLINE database was performed to identify meta-analysis and systematic reviews relevant to detection, characterization and differential diagnosis, identification of adverse pathological features, and prediction of prognosis of hepato-bilio-pancreatic neoplasms using radiomics.The following terms were searched: "(liver OR hepatic) AND (radiomics OR histogram analysis)", "pancreas AND (radiomics OR histogram analysis)", "(hepatocellular carcinoma OR hepatocarcinoma) AND (radiomics OR histogram analysis)", "cholangiocarcinoma AND (radiomics OR histogram analysis)", "liver metastases AND (radiomics OR histogram analysis)", "pancreatic adenocarcinoma AND (radiomics OR histogram analysis)", "pancreatic neuroendocrine AND (radiomics OR histogram analysis)", "intraductal papillary mucinous neoplasm AND (radiomics OR histogram analysis)".A total of 38 meta-analyses and systematic reviews were retrieved; the search was further expanded by reviewing the reference list of the selected articles in order to identify relevant papers in terms of sample size, originality, methodology and importance of the results.Full-text articles in English, reporting on US, CT, and MRI, published by 15th May 2023, were considered.Studies were excluded if they were not conducted in humans or if they evaluated other imaging techniques such as PET-CT or endoscopic US.Seventy-one studies met the eligibility criteria and were included in this literature review.The results of the meta-analysis and systematic reviews that reported pooled data diagnostic values are summarized in Table 2; the studies analyzed are described in the following paragraphs.

HEPATOCELLULAR CARCINOMA
Hepatocellular carcinoma (HCC) is usually diagnosed and monitored by imaging; therefore, it is a good candidate for radiomic analysis.Several studies have been published regarding the identification, diagnosis, and prediction of adverse pathological features, and prognosis in HCC patients.

Diagnosis
Transabdominal US, alone or in combination with serum markers, is the backbone for surveillance and early identification of HCC in high-risk subjects [6,7] , as it has a sensitivity of 94% for detecting HCC before it becomes clinically apparent; however, US has a lower sensitivity (63%) for detecting early-stage HCC [8] .
There are several reasons for this, including tumor location, size, and echogenicity, as well as patient-related factors that limit US exploration, such as poor cooperation, obesity, and marked steatosis, which are relevant given the increasing prevalence of non-alcoholic fatty liver disease (NAFLD).Enhancing the AUC 0.680-0.890,Acc 0.70-0.82diagnostic capability of US for early identification of HCC would be highly beneficial from a clinical point of view.Radiomics has a potential role in this regard, although the evidence is very scarce: one single study by Yao et al. explored radiomic analysis in 177 subjects with a liver lesion who underwent B-mode US, shear wave elastography, and shear wave viscosity imaging; 2,560 features were extracted and five radiomic models were constructed to differentiate between benign and malignant lesions and to diagnose HCC [9] .The areas under the curve (AUCs) were 0.94 for differentiation between benign and malignant lesions and 0.97 for classification of the malignant subtype.Although CT and MR are frequently performed after an initial insufficient US examination of the liver, their role in screening has not been investigated, as both are unsuitable due to radiation burden and high cost, respectively.Nine of the 54 studies included in the systematic review by Harding-Theobald et al. examined aspects of HCC diagnosis based on radiomics analysis, but most of them focused on the differentiation between hemangiomas from HCC, which is a simple task for trained Radiologists; moreover, these studies were of low methodological quality, with a RQS ranging from 5 to 10 [10] .Dankerl et al. trained a computer-aided diagnosis (CAD) system based on CT texture analysis in 372 patients with 2,325 liver lesions [11] .The diagnostic performance of the CAD system for differentiation between benign and malignant lesions and between cysts, hemangiomas, and metastases was high, with AUCs of 94.5% for lesion type and 91.4% for lesion histology; overall, the CAD system performed better than three radiologists blinded to clinical information and with access only to CT images.Using the European Association for the Study of the Liver (EASL) guidelines, Mokrane et al. retrospectively examined 178 patients with cirrhosis with radiologically indeterminate, biopsy-proven liver nodules [12] .142 and 36 patients were randomly chosen for discovery and validation cohorts, respectively.Nodules were segmented on CT images, and 13,920 features were extracted.The radiomic signature was trained, calibrated, and validated using machine learning for differentiation between HCC and non-HCC nodules: a single radiomics feature had an AUC of 0.70 and 0.66 in the two cohorts.Laino et al. reviewed 11 studies on automatic classification of liver nodules using the Liver Imaging Reporting and Data System (LI-RADS) criteria: all studies demonstrated that radiomics performs well in the classification of liver nodules, sometimes better than human evaluation, reaching an AUC of 0.98 either on CT or MR [13] .

Prognostic stratification
Prognostic stratification is the most challenging and fascinating application of radiomics.This can be obtained either by correlating radiomics features to known adverse pathological features or by directly comparing radiomics features to overall survival (OS) and recurrence-free survival (RFS).Tumor grade has a role in determining the prognosis of HCC patients, as disease recurrence and metastasis are more likely to develop in high-grade HCCs [14] .Mao et al. [15] and Wu et al. [16] reported high AUC values for combined clinical and radiomics models for HCC grading prediction (0.801 and 0.800, respectively).Microvascular invasion (MVI) has an impact on survival outcomes and disease recurrence.Studies conducted on the role of radiomics in predicting MVI reported AUC values ranging from 0.76 to 0.94 [10,[17][18][19][20] , with MR-based studies having the highest diagnostic value in predicting MVI.Another negative prognostic factor in HCC is vessels encapsulated tumor clusters (VETC), which are histologically defined as the presence of vessels marked with CD34 completely encapsulating neoplastic clusters.Yu et al. developed a predictive model based on contrast-enhanced MR images obtained after gadolinium ethoxy benzylic diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) injection, with AUC of 0.972 for preoperative prediction of VETC [21] .Finally, HCCs expressing biliary-specific markers such as CK19 have a higher rate of nodal metastasis and worse prognosis after surgery [22] .Wang et al. developed a radiomics-based model derived from MR images with sensitivity and specificity values of 0.818 and 0.974 in the training cohort and 0.769 and 0.818 in the validation cohort [23] .Disease recurrence after surgery negatively affects patients' prognosis.According to 17 studies included in the meta-analysis by Harding-Theobald et al., radiomic models can predict early recurrence after surgery, with AUCs ranging from 0.71 to 0.86 [10] .The radiomics model developed by Ji et al. to predict early disease recurrence outperformed non-radiomics models and commonly used staging systems in terms of predictive performance (C-index ≥ 0.77) and prediction error (integrated Brier score ≤ 0.14) [24] .The most advanced applications of radiomics incorporate immuno-molecular and genomic characteristics of HCC, which may aid in treatment stratification.Hectors et al. reported that qualitative and quantitative radiomics features were significantly correlated with several immunohistochemical markers such as CD3, CD68, CD31, PD-L1, PD1 and CTLA4 [25] .

Response to treatment
Several radiological criteria have been proposed to assess treatment response in HCC patients, such as Response Evaluation Criteria In Solid Tumors (RECIST) and modified RECIST (mRECIST).Radiomics might enable a standardized, early and comprehensive evaluation of treatment response, with implications for patient management.Most studies were applied to patients who underwent loco-regional treatments for HCC [10] .Kim et al. demonstrated that post-TACE OS could be predicted with a hazard ratio (HR) of 19.8 by combining clinical (Child-Pugh score, alphafetoprotein, and tumor size) and radiomics features (surface area-to-volume ratio, kurtosis, median, size zone variability) [26] .Other studies reported similar results, indicating that radiomics features extracted from pre-treatment imaging were able to predict treatment response after TACE [27] .Histogram analysis of apparent diffusion coefficient (ADC) maps seems to predict TACE response, as reported by Wu et al. [28] and Shaghaghi et al. [29] .Yang et al. [30] developed a radiomics score composed of four features that independently affected recurrence after ablation at 1, 2, and 3 years with AUCs of 0.79/0.72,0.72/0.61,and 0.71/0.64 in the train and validation groups, respectively.

Diagnosis
Liu et al. aimed to differentiate combined HCC-CC from iCC and HCC using MRI and CT radiomics features [32] .MRI-based radiomics features were the best for differentiation of HCC-CC from non-HCC-CC (AUC = 0.77).Zhou et al. aimed to differentiate HCC-CC from mass-forming iCC by extracting radiomics features from contrast-enhanced MR images: a radiomics nomogram including alpha-fetoprotein, coexistent liver disease, and radiomics signature had an AUC value of 0.945 in the training cohort and 0.897 in the validation cohort [33] .

Staging
Even using high-end preoperative imaging, understaging is a problem, as a substantial proportion of patients with cholangiocarcinoma (CC) have occult metastases detected only on resection specimens or through early recurrence after resection.Moreover, positive resection margins are not uncommon.For these reasons, preoperative risk stratification should be as precise as possible to better stratify patients' prognoses.Ji et al. developed a radiomics signature with significant association with nodal metastases in a cohort of 155 patients (test cohort = 103 patients; validation cohort = 52 patients); by adding CA 19.9 levels to the radiomics signature, the model had AUC of 0.846 and 0.892 in the two cohorts, respectively [34] .Chu et al. included 203 iCC patients from two centers [35] .Clinical and CT-derived radiomics features were selected to develop two models predictive of unbeneficial surgery (i.e., with macroscopic residual tumor or definitely unresectable).The radiomic model had higher AUC than the clinical model (0.804 vs. 0.590; P = 0.043) and reached 84.6% sensitivity and 77.1% specificity values.In the study by Qin et al., 274 patients who underwent contrast-enhanced CT and resection were divided into training (n = 167), internal validation (n = 70) and external validation (n = 37) cohorts [36] .18,120 radiomics features and 48 clinical and radiologic characteristics were analyzed.A model based on tumor differentiation, nodal metastasis, preoperative CA 19.9 level, tumor enhancement, the "shrink score" (i.e., features extracted from a ROI comprising 50% of the entire tumor area on arterial, portal and delayed contrast phases) had an AUC of 0.883 and performed better than clinical and radiomic models (AUCs 0.792-0.805);the model had an accuracy of 0.826, which was higher than AJCC 8th [37] , MSKCC [38] , and Gazzaniga [39] staging systems (AUCs, 0.641, 0.617, and 0.581, respectively).

Prediction of prognosis
Some studies have been published concerning the possibility of predicting the prognosis of patients with CC..A combination of three wavelets and one 3D feature were able to discriminate immunophenotyping (AUC = 0.919).

Treatment selection and response to treatment
The radiomic feature Wavelet-HLH_firstorder_Median was associated with OS, with a C-index of 0.70.CT texture analysis can quantify vascularization and homogeneity of iCC, providing useful information in identifying optimal candidates for trans-arterial radioembolization (TARE), as reported by Mosconi et al.:  in this study, analysis was retrospectively performed in 55 pre-TARE CT scans; iCCs showing objective response after TARE had a higher mean histogram values (P < 0.001), GLCM homogeneity (P = 0.005) and GLCM correlation (P = 0.030), and lower kurtosis (P = 0.043), Grey-level co-occurrence matrix (GLCM) contrast (P = 0.004), and GLCM dissimilarity (P = 0.005) at the pre-TARE CT scan [42] .

LIVER METASTASES
Radiomics is a promising method to predict disease recurrence and survival and improve personalized treatment in patients with liver metastases (LM), according to three systematic reviews [43][44][45] .A very important issue was reported by Kelahan et al., as inter-reader reproducibility of CT radiomics features demonstrated tumor-size dependence, and this could explain result variability among the studies [46] .

Prediction of Kirsten Rat Sarcoma Virus gene (KRAS) status
Kirsten Rat Sarcoma Virus gene (KRAS) mutation is associated with worse prognosis; on the other hand, KRAS inhibitors are more and more commonly used for the treatment of metastatic colorectal cancer.
Predicting KRAS status with non-invasive methods would be, therefore, clinically useful.A meta-analysis by Jia et al. reported on the prediction of the KRAS status in patients with colorectal LM, with pooled sensitivity, specificity and AUC values of 0.80/0.78,0.80/0.84and 0.87/0.86 in the training and validation cohorts, respectively [45] .

Response to treatment
Early and accurate response evaluation in patients with LM would be of importance given the availability of several different treatment modalities, and several studies [47][48][49][50] reported a significant association between radiomics features and response to chemotherapy and targeted therapies.

PANCREATIC NEOPLASMS
The potential usefulness of radiomics in preoperative staging and prediction of histological findings and clinical outcomes was reported by three systematic reviews and meta-analyses; these studies highlighted the low quality of most radiomics studies conducted so far.Abunahel et al. included 72 studies encompassing 8,863 participants; 66 studies investigated focal pancreatic lesions [51] .Overall, second-order features were the most useful for lesion characterization, while filtered image features were most useful for classification and prognosis predictions.The median RQS of studies included was 28%, and it was significantly correlated both with the amount of features (r = 0.52, P < 0.001) and the size of the study population (r = 0.34, P = 0.003).The meta-analysis by Gao et al. evaluated 23 studies [52] .Two of them showed better prognosis prediction performance of radiomics compared to TNM staging; 9 studies demonstrated a significant correlation between entropy, a radiomic feature describing the uncertainty or randomness in the image values, and OS (mean HR = 1.66).Staal et al. included 45 studies on pancreatic neuroendocrine neoplasms (pNENs) [53] .The mean RQS of the studies was 18%.In most studies, radiomics features could predict tumor grade or differentiate pNENs from other lesions with AUCs = 0.74-0.96and 0.80-0.99,respectively; one study developed a predictive model for disease recurrence (AUC = 0.77).

Early detection of pancreatic cancer
Despite improvements in the multidisciplinary treatment approach to patients with pancreatic ductal adenocarcinoma (PDAC), the prognosis of this disease remains very poor, as PDAC is frequently diagnosed at an advanced stage.The goal of screening and surveillance programs is to detect and treat stage I PDAC and cancer precursor lesions as intraductal papillary mucinous neoplasms (IPMNs) with high-grade dysplasia [54] .Even though encouraging results were described by two studies [55,56] , a meta-analysis by Chhoda et al. reported a significant proportion of PDACs diagnosed at a late stage during follow-up, which limits the survival benefit of surveillance [57] .Although no studies have been conducted in this regard, AI and radiomics could theoretically play a role, as they can automatically differentiate between cancer and normal pancreas, as reported by Chu et al.: in this study, 427 features were extracted from CT images; overall, the accuracy of the binary random forest classification was 99.2%, with an AUC of 99.9%, a sensitivity of 100% and a specificity of 98.5%; a major limitation of this study is that the mean tumor size was 4.1 cm, which usually corresponds to a non resectable disease [58] .Two studies by Qureshi et al. [59] and Javed et al. [60] identified several features that may be predictive of PDAC development extracted from pre-diagnostic CT scans in PDAC patients: the predictive model had an accuracy of 86%-89.3%, a sensitivity of 86% and a specificity of 93%; unfortunately, these results were based on a very limited study population and needed further validation.The most robust study on early automated detection of PDAC was published by Mukherjee et al.: they used a radiomics-based machine learning model to detect PDAC before the clinical diagnosis based on volumetric segmentation of the pancreas performed on pre-diagnostic CT scans in 155 PDAC patients and 265 normal subjects [61] .A supporting vector machine model had high sensitivity (95.5%), specificity (90.3%),AUC (0.98), and accuracy (92.2%) for the classification of CT into prediagnostic versus normal.The paradigm for early detection of cancer in IPMN is based on "worrisome features" and "high-risk stigmata".Accurate prediction of the malignant potential of IPMN is of great importance.Nevertheless, studies on AI/radiomic applications in identifying "malignant" IPMNs comprised very small study populations.The largest were proposed by Jeon et al. [62] and Chakraborty et al. [63] , who reported that radiomics features improve the performance of MR and CT for predicting malignant IPMNs.Circulating micro RNAs (miRNAs) may be diagnostic biomarkers of incidentally detected IPMNs and predictors of their histological classification: a study by Permuth et al. suggested that the combination of radiomics features with the miRNA genomic classifier (MGC) had an AUC = 0.92 and sensitivity (83%), specificity (89%), PPV (88%), and NPV (85%) for prediction of IPMN malignancy [64] .

Differential diagnosis
Radiomics is a promising tool to improve the characterization of focal pancreatic lesions.Zhang et al. developed CT and radiomics nomograms for the differentiation between mass-forming pancreatitis (MFP) and PDAC in patients with chronic pancreatitis (CP) [65] .138 patients with histopathologically diagnosed MFCP or PDAC were retrospectively analyzed.Both models had good performance in differentiating between the two entities in the training (AUC = 0.87/0.91)and validation (AUC = 0.94) cohorts.A radiomics-based computer-aided diagnosis scheme proposed by Wei et al. had AUC = 0.767, sensitivity = 0.686, and specificity = 0.709 for preoperative diagnosis of cystic neoplasms [66] .

Prediction of prognosis
Tumor grade is a major prognostic factor for pancreatic neoplasms.Chang et al. [67] and Tikhonova et al. [68] reported significant differences in radiomics signatures between PDAC of different grades, with AUC ranging from 0.66 to 0.77.Tumor grade is even more important from a prognostic point of view for pNENs.Gu et al. included 138 patients with pathologically confirmed pNENs (training cohort, 104 patients; validation cohort, 34 patients) [69] .A nomogram integrating tumor margin status and a radiomic signature derived from CT images showed strong discrimination with AUCs of 0.974 and 0.902 in the training and validation cohort, respectively.
Several studies conducted a radiomic analysis to predict features with a negative prognostic role of pNENs.
In particular, a study [70] retrospectively analyzed the MR histogram features of 42 patients with pNEN: ADCentropy was higher in G2-3 tumors with AUC = 0.757, sensitivity and specificity of 83.3% and 61.1%, while kurtosis was higher in pNENs with vascular infiltration, lymph node and liver metastases (P = 0.008, 0.021 and 0.008; AUC = 0.820, 0.709 and 0.820).Mori et al. evaluated radiomics features extracted from unenhanced CT images and reported AUCs of 0.81/0.81for the radiomic and clinic-radiological model for metastases and 0.67/0.72 and 0.68/0.70 for tumor grade [71] .Transcriptional classifiers are key prognostic factors of PDAC.Salinas-Miranda et al. [72] developed a radiomics score that was significantly associated (coefficient = 0.31) with the four PDAC subtypes (squamous, pancreatic progenitor, immunogenic, and aberrantly differentiated endocrine exocrine) classified by Bailey et al. [73] through gene expression analysis.Preoperative staging of pancreatic neoplasms includes the evaluation of vascular involvement, node and distant metastases.Rigiroli et al. developed a 5-feature model with AUC = 0.71 for preoperative assessment of superior mesenteric artery involvement by PDAC [74] .Bian et al. developed a radiomic score that was linked to the possibility of nodal metastasis [75] .Finally, a study that comprised 220 patients [76] developed a logistic regression model composed of eight variables that had sensitivity, specificity, PPV, NPV and AUC of 58.6%, 91.3%, 75.9%, 82.5%, and 0.850 for prediction of simultaneous liver metastases in PDAC patients.
Early recurrence after surgery is not uncommon in PDAC patients.Although the reasons for this have not been defined with certainty, the availability of a non-invasive biomarker would be clinically useful in patients with resectable PDAC to avoid unbeneficial surgery.Tang et al. analyzed 303 PDAC patients; the AUC values for prediction of early recurrence of radiomics signatures were 0.80, 0.81, and 0.78 in the training, inner validation, and outer validation cohorts, respectively; the AUC values for early recurrence were 0.87, 0.88, and 0.85 in the training, internal validation, and external validation cohorts [77] .A study aimed to correlate conventional and radiomics MR features with the risk and the time to metastases after surgical resection in patients with resected PDAC [78] ; 120 patients were included.ADC skewness had a significant impact on the risk of metastases, with HR = 5.22 (P < 0.001): the time to metastases was significantly shorter (11.7 vs. 30.8months, P < 0.001) in patients with an ADC skewness value greater than 0.23.Two studies [79,80] reported the association between radiomics features and adverse pathological features, including margin and nodal status, tumor grade, lymphovascular and perineural invasion.Several studies reported the correlation between radiomics features and clinical outcomes in terms of RFS and OS [81][82][83][84] .Few data are available on the potential usefulness of radiomics to assess treatment response.Borhani et al. [85] and Kim et al. [86] reported that textural features extracted from CT could be used as biomarkers predictive of the histologic response, the DFS and the OS after neoadjuvant chemotherapy.Cozzi et al. [87] developed a clinical-radiomic signature which was significantly associated with OS in PDAC patients treated with stereotactic body radiation therapy (SBRT) in training and validation cohorts (P = 0.01 and 0.05; concordance index 0.73 and 0.75, respectively).

CONCLUSION
Radiomics is a promising tool to improve the non-invasive characterization and the preoperative staging of HBP neoplasms, while the results concerning the prediction of patients' clinical outcomes are still limited.Despite these promising results, radiomics is a young discipline and its application is still at the stage of research.There are several reasons for that, including technical complexity in image analysis, issues in study design, and lack of standards for image acquisition and validating results.Technical issues in image analysis and data extraction can be addressed easily through the collaboration between radiologists, computer scientists and physicists.A possible solution to poor reproducibility would be to establish precise benchmarks for radiomics studies, including acquisition protocols, and to develop guidelines for results reporting.Finally, data sharing is a relevant issue, as it includes images and a significant amount of personal information.A possible solution to overcome cultural, administrative, and regulatory issues is the creation of centralized data repositories with anonymized data, wherein access can be limited to institutional review board-approved users.

Table 1 . Items composing the radiomics quality score and relative points [4] RQS checkpoints Criteria Points
RQS: Radiomics quality score.