Development of a Novel Multiparametric MRI Radiomic Nomogram for Preoperative Evaluation of Early Recurrence in Resectable Pancreatic Cancer

Preoperative CA19‑9 level and dual time point FDG‑PET/CT as strong biological indicators of borderline resectability in pancreatic cancer: A retrospective study

Tumor resectability, which is increasingly determined based on preoperative chemotherapy, is critical in determining the best treatment for pancreatic cancers. The present study evaluated the usefulness of serum carbohydrate antigen 19-9 (CA19-9) and the preoperative 8F-fluorodeoxyglucose positron emission tomography/computed tomography standardized uptake value (SUV) percentage change (SUVmax%=[(SUVmax2-SUVmax1)/SUVmax1] ×100, where SUVmax1 and SUVmax2 represent the initial and delayed phases, respectively) as biological factors indicative of tumor resectability. The present study included patients with resectable pancreatic cancer who underwent complete surgical resection, for whom both CA19-9 and SUVmax% were documented using cut-off values of 500 U/ml and 24.25%, respectively. Patients were classified as follows: i) High CA19-9 and SUVmax%: both CA19-9 and SUVmax% were elevated; ii) high CA19-9 or SUVmax%: either CA19-9 or SUVmax% were elevated; or iii) low CA19-9 and SUVmax%: neither value met the cut-off. Relapse-free survival (RFS) and overall survival (OS) were calculated, for which univariate and multivariate analyses were performed. Of the 86 patients included, 39 were classified as high CA19-9 or SUVmax% and 12 as high CA19-9 and SUVmax%, with the former group having a significantly worse RFS (vs. low CA19-9 and SUVmax%; P<0.001; vs. high CA19-9 or SUVmax%; P=0.011) and OS (vs. low CA19-9 and SUVmax%, P=0.002; vs. high CA19-9 or SUVmax%, P<0.001). Therefore, high CA19-9 and SUVmax% was an independent predictor of worse RFS (P<0.001) and OS (P=0.003). In conclusion, CA19-9 and SUVmax% can be utilized as biological indicators of resectability.

Association between programmed cell death ligand-1 expression in patients with cervical cancer and apparent diffusion coefficient values: a promising tool for patient´s immunotherapy selection

OBJECTIVE

To investigate the associations between apparent diffusion coefficient (ADC) values extracted from three different region of interest (ROI) position approaches and programmed cell death ligand-1 (PD-L1) expression, and evaluate the performance of the nomogram established based on ADC values and clinicopathological parameters in predicting PD-L1 expression in cervical cancer (CC) patients.

METHODS

Through retrospective recruitment, a training cohort of 683 CC patients was created, and a validation cohort of 332 CC patients was prospectively recruited. ROIs were delineated using three different methods to measure the mean ADC (ADCmean), single-section ADC (ADCss), and the minimum ADC of tumors (ADCmin). Logistic regression was employed to identify independent factors related to PD-L1 expression. A nomogram was drawn based on ADC values combined with clinicopathological features, its discrimination and calibration performances were estimated using the area under the curve (AUC) of receiver operating characteristic and calibration curve. The clinical benefits were evaluated by decision curve analysis.

RESULTS

The ADCmin independently correlated with PD-L1 expression. The nomogram constructed with ADCmin and other independent clinicopathological-related factors: FIGO staging, pathological grade, parametrial invasion, and lymph node status demonstrated excellent diagnostic performance (AUC = 0.912 and 0.903, respectively), good calibration capacities, and greater net benefits compared to the clinicopathological model in both the training and validation cohorts.

CONCLUSION

ADCmin independently correlated PD-L1 expression, and the nomogram established with ADCmin and clinicopathological independent prognostic factors had a strong predictive performance for PD-L1 expression, thereby serving as a promising tool for selecting cases eligible for immunotherapy.

CLINICAL RELEVANCE STATEMENT

The minimum ADC can serve as a reliable imaging biomarker related to PD-L1 expression; the established nomogram combines the minimum ADC and clinicopathological factors that can assist clinical immunotherapy decisions.

Uncovering the clinicopathological features of early recurrence after surgical resection of pancreatic cancer

To identify risk factors and biomarker for early recurrence in patients diagnosed with pancreatic cancer who undergo curative resection. Early recurrence after curative resection of pancreatic cancer is an obstacle to long-term survival. We retrospectively reviewed 162 patients diagnosed with pancreatic cancer who underwent curative resection. Early recurrence was defined as recurrence within 12 months of surgery. We selected S100A2 as a biomarker and investigated its expression using immunohistochemistry. Of the total, 79.6% (n = 129) of patients received adjuvant chemotherapy after surgery and 117 (72.2%) experienced recurrence, of which 73 (45.1%) experience early recurrence. In multivariate analysis, age < 60 years, presence of lymph node metastasis, and no adjuvant chemotherapy were significantly associated with early recurrence (all P < 0.05). The proportion of patients with high S100A2 expression (H-score > 5) was significantly lower in the early recurrence group (41.5% vs. 63.3%, P = 0.020). The cumulative incidence rate of early recurrence was higher in patients with an S100A2 H-score < 5 (41.5% vs. 63.3%, P = 0.012). The median overall survival of patients with higher S100A2 expression was longer than those with lower S100A2 expression (median 30.1 months vs. 24.2 months, P = 0.003). High-risk factors for early recurrence after surgery for pancreatic cancer include young age, lymph node metastasis, and no adjuvant therapy. Neoadjuvant treatment or intensive adjuvant therapy after surgery may improve the prognosis of patients with high-risk signatures. In patients who receive adjuvant therapy, high S100A2 expression is a good predictor.

Preoperative evaluating early recurrence in resectable pancreatic ductal adenocarcinoma by using CT radiomics

OBJECTIVE

To investigate the feasibility of a radiomics model based on contrast-enhanced CT for preoperatively predicting early recurrence after curative resection in patients with resectable pancreatic ductal adenocarcinoma (PDAC).

METHODS

One hundred and eighty-six patients with resectable PDAC who underwent curative resection were included and allocated to training set (131 patients) and validation set (55 patients). Radiomics features were extracted from arterial phase and portal venous phase images. The Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) regression were used for feature selection and radiomics signature construction. The radiomics model based on radiomics signature and clinical features was developed by the multivariate logistic regression analysis. Performance of the radiomics model was investigated by the area under the receiver operating characteristic (ROC) curve.

RESULTS

The radiomics signature, consisting of three arterial phase and three venous phase features, showed optimal prediction performance for early recurrence in both training (AUC = 0.73) and validation sets (AUC = 0.66). Multivariate logistic analysis identified the radiomics signature (OR, 2.58; 95% CI 2.36-3.17; p = 0.002) and clinical stage (OR, 1.60; 95% CI 1.15-2.30; p = 0.007) as independent predictors. The AUC values for risk evaluation of early recurrence using the radiomics model incorporating clinical stage were 0.80 (training set) and 0.75 (validation set).

CONCLUSION

The radiomics-based model integrating with clinical stage can predict early recurrence after upfront surgery in patients with resectable PDAC.

MRI-based radiomics signature: a potential imaging biomarker for prediction of microvascular invasion in combined hepatocellular-cholangiocarcinoma

PURPOSE

To investigate the potential of radiomics analysis of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in preoperatively predicting microvascular invasion (MVI) in patients with combined hepatocellular-cholangiocarcinoma (cHCC-CC) before surgery.

METHODS

A cohort of 91 patients with histologically confirmed cHCC-CC who underwent preoperative liver DCE-MRI were enrolled and divided into a training cohort (27 MVI-positive and 37 MVI-negative) and a validation cohort (11 MVI-positive and 16 MVI-negative). Clinical characteristics and MR features of the patients were evaluated. Radiomics features were extracted from DCE-MRI, and a radiomics signature was built using the least absolute shrinkage and selection operator (LASSO) algorithm in the training cohort. Prediction performance of the developed radiomics signature was evaluated by utilizing the receiver operating characteristic (ROC) analysis.

RESULTS

Larger tumor size and higher Radscore were associated with the presence of MVI in the training cohort (p = 0.026 and < 0.001, respectively), and theses findings were also confirmed in the validation cohort (p = 0.040 and 0.001, respectively). The developed radiomics signature, composed of 4 stable radiomics features, showed high prediction performance in both the training cohort (AUC = 0.866, 95% CI 0.757-0.938, p < 0.001) and validation cohort (AUC = 0.841, 95% CI 0.650-0.952, p < 0.001).

CONCLUSIONS

The radiomics signature developed from DCE-MRI can be a reliable imaging biomarker to preoperatively predict MVI in cHCC-CC.

Radiomics analysis with three-dimensional and two-dimensional segmentation to predict survival outcomes in pancreatic cancer

BACKGROUND

Radiomics can assess prognostic factors in several types of tumors, but considering its prognostic ability in pancreatic cancer has been lacking.

AIM

To evaluate the performance of two different radiomics software in assessing survival outcomes in pancreatic cancer patients.

METHODS

We retrospectively reviewed pretreatment contrast-enhanced dual-energy computed tomography images from 48 patients with biopsy-confirmed pancreatic ductal adenocarcinoma who later underwent neoadjuvant chemoradiation and surgery. Tumors were segmented using TexRad software for 2-dimensional (2D) analysis and MIM software for 3D analysis, followed by radiomic feature extraction. Cox proportional hazard modeling correlated texture features with overall survival (OS) and progression-free survival (PFS). Cox regression was used to detect differences in OS related to pretreatment tumor size and residual tumor following treatment. The Wilcoxon test was used to show the relationship between tumor volume and the percent of residual tumor. Kaplan-Meier analysis was used to compare survival in patients with different tumor densities in Hounsfield units for both 2D and 3D analysis.

RESULTS

3D analysis showed that higher mean tumor density [hazard ratio (HR) = 0.971, P = 0.041)] and higher median tumor density (HR = 0.970, P = 0.037) correlated with better OS. 2D analysis showed that higher mean tumor density (HR = 0.963, P = 0.014) and higher mean positive pixels (HR = 0.962, P = 0.014) correlated with better OS; higher skewness (HR = 3.067, P = 0.008) and higher kurtosis (HR = 1.176, P = 0.029) correlated with worse OS. Higher entropy correlated with better PFS (HR = 0.056, P = 0.036). Models determined that patients with increased tumor size greater than 1.35 cm were likely to have a higher percentage of residual tumors of over 10%.

CONCLUSION

Several radiomics features can be used as prognostic tools for pancreatic cancer. However, results vary between 2D and 3D analyses. Mean tumor density was the only variable that could reliably predict OS, irrespective of the analysis used.

Dynamic contrast-enhanced magnetic resonance imaging radiomics analysis based on intratumoral subregions for predicting luminal and nonluminal breast cancer

Background

Breast cancer is a heterogeneous disease with different morphological and biological characteristics. The molecular subtypes of breast cancer are closely related to the treatment and prognosis of patients. In order to predict the luminal type of breast cancer in a noninvasive manner, our study developed and validated a radiomics nomogram combining clinical factors with a radiomics score based on the features of the intratumoral subregion to distinguish between luminal and nonluminal breast cancer.

Methods

From January 2018 to January 2020, 153 women with clinically and pathologically diagnosed breast cancer with an average age of 50.08 years were retrospectively analyzed. Using a semiautomatic segmentation method, the whole tumor was divided into 3 subregions on the basis of the time required for the contrast agent to reach its peak; 540 features were extracted from 3 subregions and the whole tumor region. Subsequently, 2 machine learning classifiers were developed. The least absolute shrinkage and selection operator method was used for feature selection and radiomics score (Rad-score) construction. Moreover, multivariable logistic regression analysis was applied to select independent factors from the Rad-score and clinical factors to establish a prediction model in the form of a nomogram. The performance of the nomogram was evaluated through calibration, discrimination, and clinical usefulness.

Results

The prediction performance of texture features from the rapid subregion was the best in the 3 intratumoral subregions, and the area under the receiver operating characteristic curve (AUC) values in the training and validation cohort were 0.805 (95% CI: 0.719-0.892) and 0.737 (95% CI: 0.581-0.893), respectively. The Rad-score, consisting of 5 features from the rapid subregion, was associated with the luminal type of breast cancer (P=0.001 and P=0.035 in the training and validation cohorts, respectively). The predictors included in the personalized prediction nomogram included Rad-score, human epidermal growth factor receptor 2 (HER2) status, and tumor histological grade. The nomogram showed good discrimination, with an area under the receiver operating characteristic curve in the training and validation cohorts of 0.830 (95% CI: 0.746-0.896) and 0.879 (95% CI: 0.748-0.957), respectively. The calibration curve of the 2 cohorts and decision curve analysis demonstrated that the nomogram had good calibration and clinical usefulness.

Conclusions

We proposed a nomogram model that combined clinical factors and Rad-score, which showed good performance in predicting the luminal type of breast cancer.

Development and validation of a radiomics model of magnetic resonance for predicting liver metastasis in resectable pancreatic ductal adenocarcinoma patients

BACKGROUND

Nearly one fourth of patients with pancreatic ductal adenocarcinoma (PDAC) occur to liver metastasis after surgery, and liver metastasis is a risk factor for prognosis for those patients with surgery therapy. However, there is no effective way to predict liver metastasis post-operation.

METHOD

Clinical data and preoperative magnetic resonance imaging (MRI) of PDAC patients diagnosed between July 2010 and July 2020 were retrospectively collected from three hospital centers in China. The significant MRI radiomics features or clinicopathological characteristics were used to establish a model to predict liver metastasis in the development and validation cohort.

RESULTS

A total of 204 PDAC patients from three hospital centers were divided randomly (7:3) into development and validation cohort. Due to poor predictive value of clinical features, MRI radiomics model had similar receiver operating characteristics curve (ROC) value to clinical-radiomics combing model in development cohort (0.878 vs. 0.880, p = 0.897) but better ROC in validation dataset (0.815 vs. 0.732, p = 0.022). Radiomics model got a sensitivity of 0.872/0.750 and a specificity of 0.760/0.822 to predict liver metastasis in development and validation cohort, respectively. Among 54 patients randomly selected with post-operation specimens, fibrosis markers (α-smooth muscle actin) staining was shown to promote radiomics model with ROC value from 0.772 to 0.923 (p = 0.049) to predict liver metastasis.

CONCLUSION

This study developed and validated an MRI-based radiomics model and showed a good performance in predicting liver metastasis in resectable PDAC patients.

Automated segmentation of craniopharyngioma on MR images using U-Net-based deep convolutional neural network

OBJECTIVES

To develop a U-Net-based deep learning model for automated segmentation of craniopharyngioma.

METHODS

A total number of 264 patients diagnosed with craniopharyngiomas were included in this research. Pre-treatment MRIs were collected, annotated, and used as ground truth to learn and evaluate the deep learning model. Thirty-eight patients from another institution were used for independently external testing. The proposed segmentation model was constructed based on a U-Net architecture. Dice similarity coefficients (DSCs), Hausdorff distance of 95% percentile (95HD), Jaccard value, true positive rate (TPR), and false positive rate (FPR) of each case were calculated. One-way ANOVA analysis was used to investigate if the model performance was associated with the radiological characteristics of tumors.

RESULTS

The proposed model showed a good performance in segmentation with average DSCs of 0.840, Jaccard of 0.734, TPR of 0.820, FPR of 0.000, and 95HD of 3.669 mm. It performed feasibly in the independent external test set, with average DSCs of 0.816, Jaccard of 0.704, TPR of 0.765, FPR of 0.000, and 95HD of 4.201 mm. Also, one-way ANOVA suggested the performance was not statistically associated with radiological characteristics, including predominantly composition (p = 0.370), lobulated shape (p = 0.353), compressed or enclosed ICA (p = 0.809), and cavernous sinus invasion (p = 0.283).

CONCLUSIONS

The proposed deep learning model shows promising results for the automated segmentation of craniopharyngioma.

KEY POINTS

• The segmentation model based on U-Net showed good performance in segmentation of craniopharyngioma. • The proposed model showed good performance regardless of the radiological characteristics of craniopharyngioma. • The model achieved feasibility in the independent external dataset obtained from another center.

Branch duct-intraductal papillary mucinous neoplasms (BD-IPMNs): an MRI-based radiomic model to determine the malignant degeneration potential

BACKGROUND

Branch duct-intraductal papillary mucinous neoplasms (BD-IPMNs) are the most common pancreatic cystic tumors and have a low risk of malignant transformation. Features able to early identify high-risk BD-IPMNs are lacking, and guidelines currently rely on the occurrence of worrisome features (WF) and high-risk stigmata (HRS).

AIM

In our study, we aimed to use a magnetic resonance imaging (MRI) radiomic model to identify features linked to a higher risk of malignant degeneration, and whether these appear before the occurrence of WF and HRS.

METHODS

We retrospectively evaluated adult patients with a known BD-IPMN who had had at least two contrast-enhanced MRI studies at our center and a 24-month minimum follow-up time. MRI acquisition protocol for the two examinations included pre- and post-contrast phases and diffusion-weighted imaging (DWI)/apparent diffusion coefficient (ADC) map. Patients were divided into two groups according to the development of WF or HRS at the end of the follow-up (Group 0 = no WF or HRS; Group 1 = WF or HRS). We segmented the MRI images and quantitative features were extracted and compared between the two groups. Features that showed significant differences (SF) were then included in a LASSO regression method to build a radiomic-based predictive model.

RESULTS

We included 50 patients: 31 in Group 0 and 19 in Group 1. No patients in this cohort developed HRS. At baseline, 47, 67, 38, and 68 SF were identified for pre-contrast T1-weighted (T1-W) sequence, post-contrast T1-W sequence, T2-weighted (T2- W) sequence, and ADC map, respectively. At the end of follow-up, we found 69, 78, 53, and 91 SF, respectively. The radiomic-based predictive model identified 16 SF: more particularly, 5 SF for pre-contrast T1-W sequence, 6 for post-contrast T1-W sequence, 3 for T2-W sequence, and 2 for ADC.

CONCLUSION

We identified radiomic features that correlate significantly with WF in patients with BD-IPMNs undergoing contrast-enhanced MRI. Our MRI-based radiomic model can predict the occurrence of WF.

Deep Learning Provides a New Magnetic Resonance Imaging-Based Prognostic Biomarker for Recurrence Prediction in High-Grade Serous Ovarian Cancer

This study aims to use a deep learning method to develop a signature extract from preoperative magnetic resonance imaging (MRI) and to evaluate its ability as a non-invasive recurrence risk prognostic marker in patients with advanced high-grade serous ovarian cancer (HGSOC). Our study comprises a total of 185 patients with pathologically confirmed HGSOC. A total of 185 patients were randomly assigned in a 5:3:2 ratio to a training cohort (n = 92), validation cohort 1 (n = 56), and validation cohort 2 (n = 37). We built a new deep learning network from 3839 preoperative MRI images (T2-weighted images and diffusion-weighted images) to extract HGSOC prognostic indicators. Following that, a fusion model including clinical and deep learning features is developed to predict patients' individual recurrence risk and 3-year recurrence likelihood. In the two validation cohorts, the consistency index of the fusion model was higher than both the deep learning model and the clinical feature model (0.752, 0.813 vs. 0.625, 0.600 vs. 0.505, 0.501). Among the three models, the fusion model had a higher AUC than either the deep learning model or the clinical model in validation cohorts 1 or 2 (AUC = was 0.986, 0.961 vs. 0.706, 0.676/0.506, 0.506). Using the DeLong method, the difference between them was statistically significant (p < 0.05). The Kaplan-Meier analysis distinguished two patient groups with high and low recurrence risk (p = 0.0008 and 0.0035, respectively). Deep learning may be a low-cost, non-invasive method for predicting risk for advanced HGSOC recurrence. Deep learning based on multi-sequence MRI serves as a prognostic biomarker for advanced HGSOC, which provides a preoperative model for predicting recurrence in HGSOC. Additionally, using the fusion model as a new prognostic analysis means that can use MRI data can be used without the need to follow-up the prognostic biomarker.

Pathological Diagnosis of Adult Craniopharyngioma on MR Images: An Automated End-to-End Approach Based on Deep Neural Networks Requiring No Manual Segmentation

PURPOSE

The goal of this study was to develop end-to-end convolutional neural network (CNN) models that can noninvasively discriminate papillary craniopharyngioma (PCP) from adamantinomatous craniopharyngioma (ACP) on MR images requiring no manual segmentation.

MATERIALS AND METHODS

A total of 97 patients diagnosed with ACP or PCP were included. Pretreatment contrast-enhanced T1-weighted images were collected and used as the input of the CNNs. Six models were established based on six networks, including VGG16, ResNet18, ResNet50, ResNet101, DenseNet121, and DenseNet169. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were used to assess the performances of these deep neural networks. A five-fold cross-validation was applied to evaluate the performances of the models.

RESULTS

The six networks yielded feasible performances, with area under the receiver operating characteristic curves (AUCs) of at least 0.78 for classification. The model based on Resnet50 achieved the highest AUC of 0.838 ± 0.062, with an accuracy of 0.757 ± 0.052, a sensitivity of 0.608 ± 0.198, and a specificity of 0.845 ± 0.034, respectively. Moreover, the results also indicated that the CNN method had a competitive performance compared to the radiomics-based method, which required manual segmentation for feature extraction and further feature selection.

CONCLUSIONS

MRI-based deep neural networks can noninvasively differentiate ACP from PCP to facilitate the personalized assessment of craniopharyngiomas.

Multiregional Radiomic Signatures Based on Functional Parametric Maps from DCE-MRI for Preoperative Identification of Estrogen Receptor and Progesterone Receptor Status in Breast Cancer

Radiomics based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has been used for breast estrogen receptor (ER) and progesterone receptor (PR) status evaluation. However, the radiomic features of peritumoral regions were not thoroughly analyzed. This study aimed to establish and validate the multiregional radiomic signatures (RSs) for the preoperative identification of the ER and PR status in breast cancer. A total of 443 patients with breast cancer were divided into training (n = 356) and validation (n = 87) sets. Radiomic features were extracted from intra- and peritumoral regions on six functional parametric maps from DCE-MRI. A two-sample t-test, least absolute shrinkage and selection operator regression, and stepwise were used for feature selections. Three RSs for predicting the ER and PR status were constructed using a logistic regression model based on selected intratumoral, peritumoral, and combined intra- and peritumoral radiomic features. The area under the receiver operator characteristic curve (AUC) was used to assess the discriminative performance of three RSs. The AUCs of intra- and peritumoral RSs for identifying the ER status were 0.828/0.791 and 0.755/0.733 in the training and validation sets, respectively. For predicting the PR status, intra- and peritumoral RSs resulted in AUCs of 0.816/0.749 and 0.806/0.708 in the training and validation sets, respectively. Multiregional RSs achieved the best AUCs among three RSs for evaluating the ER (0.851 and 0.833) and PR (0.848 and 0.763) status. In conclusion, multiregional RSs based on functional parametric maps from DCE-MRI showed promising results for preoperatively evaluating the ER and PR status in breast cancer patients. Further studies using a larger cohort from multiple centers are necessary to confirm the reliability of the established models before clinical application.

The Application Value of MRI T 2 ∗ WI Radiomics Nomogram in Discriminating Hepatocellular Carcinoma from Intrahepatic Cholangiocarcinoma

Objective. To establish and validate an MRI T $2^{\ast }$ WI-based radiomics nomogram model and to discriminate hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (ICCA). Methods. 174 patients were retrospectively collected, who were diagnosed with primary hepatic carcinoma by surgery or puncture pathology and received preoperative MRI scans including T $2^{\ast }$ WI scans. There were 113 cases of HCC and 61 cases of mass-type ICCA. T $2^{\ast }$ WI was used for feature extraction, the extent of the lesions was manually outlined at the largest lesions layer of the T $2^{\ast }$ WI, and the feature dimension reduction was performed by the mRMR and LASSO to obtain the optimal feature set. The radiomics features and clinical risk factors were combined to establish the radiomics nomogram model. In both training and validation groups, calibration curves and ROC curves were applied to validate the efficacy of the established model. Finally, calibration curves were applied to assess the degree of fitting and DCA to assess the clinical utility of the established model. Results. The radiomics model had the AUC of 0.90 (95% CI, 0.85–0.96) and 0.91 (95% CI, 0.83–0.99) in the training and validation groups, respectively; the AUC of the radiomics nomogram was 0.97 (95% CI, 0.94–0.99) in the training group and 0.95 (95% CI, 0.95–0.99) in the validation group. DCA suggested the clinical application value of the nomogram model. Conclusion. Radiomics nomogram model based on MRI T $2^{\ast }$ WI scan without enhancement can be used to discriminate HCC from ICCA.

Imaging of Pancreatic Ductal Adenocarcinoma: An Update on Recent Advances

Pancreatic ductal carcinoma (PDAC) is one of the leading causes of cancer-related death worldwide. Computed tomography (CT) remains the primary imaging modality for diagnosis of PDAC. However, CT has limitations for early pancreatic tumor detection and tumor characterization so that it is currently challenged by magnetic resonance imaging. More recently, a particular attention has been given to radiomics for the characterization of pancreatic lesions using extraction and analysis of quantitative imaging features. In addition, radiomics has currently many applications that are developed in conjunction with artificial intelligence (AI) with the aim of better characterizing pancreatic lesions and providing a more precise assessment of tumor burden. This review article sums up recent advances in imaging of PDAC in the field of image/data acquisition, tumor detection, tumor characterization, treatment response evaluation, and preoperative planning. In addition, current applications of radiomics and AI in the field of PDAC are discussed.

Pancreatic cancer, radiomics and artificial intelligence

Patients with pancreatic ductal adenocarcinoma (PDAC) are generally classified into four categories based on contrast-enhanced CT at diagnosis: resectable, borderline resectable, unresectable, and metastatic disease. In the initial grading and staging of PDAC, structured radiological templates are useful but limited, as there is a need to define the aggressiveness and microscopic disease stage of these tumours to ensure adequate treatment allocation. Quantitative imaging analysis allows radiomics and dynamic imaging features to provide information of clinical outcomes, and to construct clinical models based on radiomics signatures or imaging phenotypes. These quantitative features may be used as prognostic and predictive biomarkers in clinical decision-making, enabling personalised management of advanced PDAC. Deep learning and convolutional neural networks also provide high level bioinformatics tools that can help define features associated with a given aspect of PDAC biology and aggressiveness, paving the way to define outcomes based on these features. Thus, the prediction of tumour phenotype, treatment response and patient prognosis may be feasible by using such comprehensive and integrated radiomics models. Despite these promising results, quantitative imaging is not ready for clinical implementation in PDAC. Limitations include the instability of metrics and lack of external validation. Large properly annotated datasets, including relevant semantic features (demographics, blood markers, genomics), image harmonisation, robust radiomics analysis, clinically significant tasks as outputs, comparisons with gold-standards (such as TNM or pretreatment classifications) and fully independent validation cohorts, will be required for the development of trustworthy radiomics and artificial intelligence solutions to predict PDAC aggressiveness in a clinical setting.

Update on quantitative radiomics of pancreatic tumors

Radiomics is a newer approach for analyzing radiological images obtained from conventional imaging modalities such as computed tomography, magnetic resonance imaging, endoscopic ultrasonography, and positron emission tomography. Radiomics involves extracting quantitative data from the images and assessing them to identify diagnostic or prognostic features such as tumor grade, resectability, tumor response to neoadjuvant therapy, and survival. The purpose of this review is to discuss the basic principles of radiomics and provide an overview of the current clinical applications of radiomics in the field of pancreatic tumors.

Development and validation of a clinicoradiomic nomogram to assess the HER2 status of patients with invasive ductal carcinoma

Background

The determination of HER2 expression status contributes significantly to HER2-targeted therapy in breast carcinoma. However, an economical, efficient, and non-invasive assessment of HER2 is lacking. We aimed to develop a clinicoradiomic nomogram based on radiomics scores extracted from multiparametric MRI (mpMRI, including ADC-map, T2W1, DCE-T1WI) and clinical risk factors to assess HER2 status.

Methods

We retrospectively collected 214 patients with pathologically confirmed invasive ductal carcinoma between January 2018 to March 2021 from Fudan University Shanghai Cancer Center, and randomly divided this cohort into training set (n = 128, 42 HER2-positive and 86 HER2-negative cases) and validation set (n = 86, 28 HER2-positive and 58 HER2-negative cases) at a ratio of 6:4. The original and transformed pretherapy mpMRI images were treated by semi-automated segmentation and manual modification on the DeepWise scientific research platform v1.6 (http://keyan.deepwise.com/), then radiomics feature extraction was implemented with PyRadiomics library. Recursive feature elimination (RFE) based on logistic regression (LR) and LASSO regression were adpoted to identify optimal features before modeling. LR, Linear Discriminant Analysis (LDA), support vector machine (SVM), random forest (RF), naive Bayesian (NB) and XGBoost (XGB) algorithms were used to construct the radiomics signatures. Independent clinical predictors were identified through univariate logistic analysis (age, tumor location, ki-67 index, histological grade, and lymph node metastasis). Then, the radiomics signature with the best diagnostic performance (Rad score) was further combined with significant clinical risk factors to develop a clinicoradiomic model (nomogram) using multivariate logistic regression. The discriminative power of the constructed models were evaluated by AUC, DeLong test, calibration curve, and decision curve analysis (DCA).

Results

70 (32.71%) of the enrolled 214 cases were HER2-positive, while 144 (67.29%) were HER2-negative. Eleven best radiomics features were retained to develop 6 radiomcis classifiers in which RF classifier showed the highest AUC of 0.887 (95%CI: 0.827–0.947) in the training set and acheived the AUC of 0.840 (95%CI: 0.758–0.922) in the validation set. A nomogram that incorporated the Rad score with two selected clinical factors (Ki-67 index and histological grade) was constructed and yielded better discrimination compared with Rad score (p = 0.374, Delong test), with an AUC of 0.945 (95%CI: 0.904–0.987) in the training set and 0.868 (95%CI: 0.789–0.948; p = 0.123) in the validation set. Moreover, calibration with the p-value of 0.732 using Hosmer–Lemeshow test demonstrated good agreement, and the DCA verified the benefits of the nomogram.

Conclusion

Post largescale validation, the clinicoradiomic nomogram may have the potential to be used as a non-invasive tool for determination of HER2 expression status in clinical HER2-targeted therapy prediction.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-09967-6.

Efficient Prediction of Ki-67 Proliferation Index in Meningiomas on MRI: From Traditional Radiological Findings to a Machine Learning Approach

Background/aim This study aimed to explore the value of radiological and radiomic features retrieved from magnetic resonance imaging in the prediction of a Ki-67 proliferative index in meningioma patients using a machine learning model. Methods This multicenter, retrospective study included 371 patients collected from two centers. The Ki-67 expression was classified into low-expressed and high-expressed groups with a threshold of 5%. Clinical features and radiological features were collected and analyzed by using univariate and multivariate statistical analyses. Radiomic features were extracted from contrast-enhanced images, followed by three independent feature selections. Six predictive models were constructed with different combinations of features by using linear discriminant analysis (LDA) classifier. Results The multivariate analysis suggested that the presence of intratumoral necrosis (p = 0.032) and maximum diameter (p < 0.001) were independently correlated with a high Ki-67 status. The predictive models showed good performance with AUC of 0.837, accuracy of 0.810, sensitivity of 0.857, and specificity of 0.771 in the internal test and with AUC of 0.700, accuracy of 0.557, sensitivity of 0.314, and specificity of 0.885 in the external test. Conclusion The results of this study suggest that the predictive model can efficiently predict the Ki-67 index of meningioma patients to facilitate the therapeutic management.

Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging

Simple Summary

Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest cancers worldwide, associated with a 98% loss of life expectancy and a 30% increase in disability-adjusted life years. Image-based artificial intelligence (AI) can help improve outcomes for PDAC given that current clinical guidelines are non-uniform and lack evidence-based consensus. However, research on image-based AI for PDAC is too scattered and lacking in sufficient quality to be incorporated into clinical workflows. In this review, an international, multi-disciplinary team of the world’s leading experts in pancreatic cancer breaks down the patient pathway and pinpoints the current clinical touchpoints in each stage. The available PDAC imaging AI literature addressing each pathway stage is then rigorously analyzed, and current performance and pitfalls are identified in a comprehensive overview. Finally, the future research agenda for clinically relevant, image-driven AI in PDAC is proposed.

Abstract

Pancreatic ductal adenocarcinoma (PDAC), estimated to become the second leading cause of cancer deaths in western societies by 2030, was flagged as a neglected cancer by the European Commission and the United States Congress. Due to lack of investment in research and development, combined with a complex and aggressive tumour biology, PDAC overall survival has not significantly improved the past decades. Cross-sectional imaging and histopathology play a crucial role throughout the patient pathway. However, current clinical guidelines for diagnostic workup, patient stratification, treatment response assessment, and follow-up are non-uniform and lack evidence-based consensus. Artificial Intelligence (AI) can leverage multimodal data to improve patient outcomes, but PDAC AI research is too scattered and lacking in quality to be incorporated into clinical workflows. This review describes the patient pathway and derives touchpoints for image-based AI research in collaboration with a multi-disciplinary, multi-institutional expert panel. The literature exploring AI to address these touchpoints is thoroughly retrieved and analysed to identify the existing trends and knowledge gaps. The results show absence of multi-institutional, well-curated datasets, an essential building block for robust AI applications. Furthermore, most research is unimodal, does not use state-of-the-art AI techniques, and lacks reliable ground truth. Based on this, the future research agenda for clinically relevant, image-driven AI in PDAC is proposed.

Preoperative Prediction of Lymph Node Metastasis of Pancreatic Ductal Adenocarcinoma Based on a Radiomics Nomogram of Dual-Parametric MRI Imaging

Purpose

This study aims to uncover and validate an MRI-based radiomics nomogram for detecting lymph node metastasis (LNM) in pancreatic ductal adenocarcinoma (PDAC) patients prior to surgery.

Materials and Methods

We retrospectively collected 141 patients with pathologically confirmed PDAC who underwent preoperative T2-weighted imaging (T2WI) and portal venous phase (PVP) contrast-enhanced T1-weighted imaging (T1WI) scans between January 2017 and December 2021. The patients were randomly divided into training (n = 98) and validation (n = 43) cohorts at a ratio of 7:3. For each sequence, 1037 radiomics features were extracted and analyzed. After applying the gradient-boosting decision tree (GBDT), the key MRI radiomics features were selected. Three radiomics scores (rad-score 1 for PVP, rad-score 2 for T2WI, and rad-score 3 for T2WI combined with PVP) were calculated. Rad-score 3 and clinical independent risk factors were combined to construct a nomogram for the prediction of LNM of PDAC by multivariable logistic regression analysis. The predictive performances of the rad-scores and the nomogram were assessed by the area under the operating characteristic curve (AUC), and the clinical utility of the radiomics nomogram was assessed by decision curve analysis (DCA).

Results

Six radiomics features of T2WI, eight radiomics features of PVP and ten radiomics features of T2WI combined with PVP were found to be associated with LNM. Multivariate logistic regression analysis showed that rad-score 3 and MRI-reported LN status were independent predictors. In the training and validation cohorts, the AUCs of rad-score 1, rad-score 2 and rad-score 3 were 0.769 and 0.751, 0.807 and 0.784, and 0.834 and 0.807, respectively. The predictive value of rad-score 3 was similar to that of rad-score 1 and rad-score 2 in both the training and validation cohorts (P &gt; 0.05). The radiomics nomogram constructed by rad-score 3 and MRI-reported LN status showed encouraging clinical benefit, with an AUC of 0.845 for the training cohort and 0.816 for the validation cohort.

Conclusions

The radiomics nomogram derived from the rad-score based on MRI features and MRI-reported lymph status showed outstanding performance for the preoperative prediction of LNM of PDAC.

Multi-Sequence MR-Based Radiomics Signature for Predicting Early Recurrence in Solitary Hepatocellular Carcinoma ≤5 cm

Purpose

To investigate the value of radiomics features derived from preoperative multi-sequence MR images for predicting early recurrence (ER) in patients with solitary hepatocellular carcinoma (HCC) ≤5 cm.

Methods

One hundred and ninety HCC patients were enrolled and allocated to training and validation sets (n = 133:57). The clinical–radiological model was established by significant clinical risk characteristics and qualitative imaging features. The radiomics model was constructed using the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm in the training set. The combined model was formed by integrating the clinical–radiological risk factors and selected radiomics features. The predictive performance was assessed by the area under the receiver operating characteristic curve (AUC).

Results

Arterial peritumoral hyperenhancement, non-smooth tumor margin, satellite nodules, cirrhosis, serosal invasion, and albumin showed a significant correlation with ER. The AUC of the clinical–radiological model was 0.77 (95% CI: 0.69–0.85) and 0.76 (95% CI: 0.64–0.88) in the training and validation sets, respectively. The radiomics model constructed using 12 radiomics features selected by LASSO regression had an AUC of 0.85 (95% CI: 0.79–0.91) and 0.84 (95% CI: 0.73–0.95) in the training and validation sets, respectively. The combined model further improved the prediction performance compared with the clinical–radiological model, increasing AUC to 0.90 (95% CI: 0.85–0.95) in the training set and 0.88 (95% CI: 0.80–0.97) in the validation set (p < 0.001 and p = 0.012, respectively). The calibration curve fits well with the standard curve.

Conclusions

The predictive model incorporated the clinical–radiological risk factors and radiomics features that could adequately predict the individualized ER risk in patients with solitary HCC ≤5 cm.

A novel preoperative MRI-based radiomics nomogram outperforms traditional models for prognostic prediction in pancreatic ductal adenocarcinoma

To develop an efficient prognostic model based on preoperative magnetic resonance imaging (MRI) radiomics for patients with pancreatic ductal adenocarcinoma (PDAC), the preoperative MRI data of PDAC patients in two independent centers (defined as development cohort and validation cohort, respectively) were collected retrospectively, and the radiomics features of tumors were then extracted. Based on the optimal radiomics features which were significantly related to overall survival (OS) and progression-free survival (PFS), the score of radiomics signature (Rad-score) was calculated, and its predictive efficiency was evaluated according to the area under receiver operator characteristic curve (AUC). Subsequently, the clinical-radiomics nomogram which incorporated the Rad-score and clinical parameters was developed, and its discrimination, consistency and application value were tested by calibration curve, concordance index (C-index) and decision curve analysis (DCA). Moreover, the predictive value of the clinical-radiomics nomogram was compared with traditional prognostic models. A total of 196 eligible PDAC patients were enrolled in this study. The AUC value of Rad-score for OS and PFS in development cohort was 0.724 and 0.781, respectively, and the value of Rad-score was negatively correlated with PDAC's prognosis. Moreover, the developed clinical-radiomics nomogram showed great consistency with the C-index for OS and PFS in development cohort was 0.814 and 0.767, respectively. In addition, the DCA demonstrated that the developed nomogram displayed better clinical predictive usefulness than traditional prognostic models. We concluded that the preoperative MRI-based radiomics signature was significantly related to the poor prognosis of PDAC patients, and the developed clinical-radiomics nomogram showed better predictive ability, it might be used for individualized prognostic assessment of preoperative patients with PDAC.

Using Quantitative Imaging for Personalized Medicine in Pancreatic Cancer: A Review of Radiomics and Deep Learning Applications

Simple Summary

With a five-year survival rate of only 3% for the majority of patients, pancreatic cancer is a global healthcare challenge. Radiomics and deep learning, two novel quantitative imaging methods that treat medical images as minable data instead of just pictures, have shown promise in advancing personalized management of pancreatic cancer through diagnosing precursor diseases, early detection, accurate diagnosis, and treatment personalization. Radiomics and deep learning methods aim to collect hidden information in medical images that is missed by conventional radiology practices through expanding the data search and comparing information across different patients. Both methods have been studied and applied in pancreatic cancer. In this review, we focus on the current progress of these two methods in pancreatic cancer and provide a comprehensive narrative review on the topic. With better regulation, enhanced workflow, and larger prospective patient datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through personalized precision medicine.

Abstract

As the most lethal major cancer, pancreatic cancer is a global healthcare challenge. Personalized medicine utilizing cutting-edge multi-omics data holds potential for major breakthroughs in tackling this critical problem. Radiomics and deep learning, two trendy quantitative imaging methods that take advantage of data science and modern medical imaging, have shown increasing promise in advancing the precision management of pancreatic cancer via diagnosing of precursor diseases, early detection, accurate diagnosis, and treatment personalization and optimization. Radiomics employs manually-crafted features, while deep learning applies computer-generated automatic features. These two methods aim to mine hidden information in medical images that is missed by conventional radiology and gain insights by systematically comparing the quantitative image information across different patients in order to characterize unique imaging phenotypes. Both methods have been studied and applied in various pancreatic cancer clinical applications. In this review, we begin with an introduction to the clinical problems and the technology. After providing technical overviews of the two methods, this review focuses on the current progress of clinical applications in precancerous lesion diagnosis, pancreatic cancer detection and diagnosis, prognosis prediction, treatment stratification, and radiogenomics. The limitations of current studies and methods are discussed, along with future directions. With better standardization and optimization of the workflow from image acquisition to analysis and with larger and especially prospective high-quality datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through big data-based high-precision personalization.

Development and Validation of Noninvasive MRI-Based Signature for Preoperative Prediction of Early Recurrence in Perihilar Cholangiocarcinoma

BACKGROUND

Cholangiocarcinoma is a type of hepatobiliary tumor. For perihilar cholangiocarcinoma (pCCA), patients who experience early recurrence (ER) have a poor prognosis. Preoperative accurate prediction of postoperative ER can avoid unnecessary operation; however, prediction is challenging.

PURPOSE

To develop a novel signature based on clinical and/or MRI radiomics features of pCCA to preoperatively predict ER.

STUDY TYPE

Retrospective.

POPULATION

One hundred eighty-four patients (median age, 61.0 years; interquartile range: 53.0-66.8 years) including 115 men and 69 women.

FIELD STRENGTH/SEQUENCE

A 1.5 T; volumetric interpolated breath-hold examination (VIBE) sequence.

ASSESSMENT

The models were developed from the training set (128 patients) and validated in a separate testing set (56 patients). The contrast-enhanced arterial and portal vein phase MR images of hepatobiliary system were used for extracting radiomics features. The correlation analysis, least absolute shrinkage and selection operator (LASSO) logistic regression (LR), backward stepwise LR were mainly used for radiomics feature selection and modeling (Model^radiomic ). The univariate and multivariate backward stepwise LR were used for preoperative clinical predictors selection and modeling (Model^clinic ). The radiomics and preoperative clinical predictors were combined by multivariate LR method to construct clinic-radiomics nomogram (Model^combine ).

STATISTICAL TESTS

Chi-squared (χ² ) test or Fisher's exact test, Mann-Whitney U-test or t-test, Delong test. Two tailed P < 0.05 was considered statistically significant.

RESULTS

Based on the comparison of area under the curves (AUC) using Delong test, Model^clinic and Model^combine had significantly better performance than Model^radiomic and tumor-node-metastasis (TNM) system in training set. In the testing set, both Model^clinic and Model^combine had significantly better performance than TNM system, whereas only Model^combine was significantly superior to Model^radiomic . However, the AUC values were not significantly different between Model^clinic and Model^combine (P = 0.156 for training set and P = 0.439 for testing set).

DATA CONCLUSION

A noninvasive model combining the MRI-based radiomics signature and clinical variables is potential to preoperatively predict ER for pCCA.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 4.

Magnetic Resonance Imaging Radiomics-Based Nomogram From Primary Tumor for Pretreatment Prediction of Peripancreatic Lymph Node Metastasis in Pancreatic Ductal Adenocarcinoma: A Multicenter Study

BACKGROUND

Determining the absence or presence of peripancreatic lymph nodal metastasis (PLNM) is important to the pathologic staging, prognostication, and guidance of treatment in pancreatic ductal adenocarcinoma (PDAC) patients. Computed tomography and MRI had a poor sensitivity and diagnostic accuracy in the assessment of PLNM.

PURPOSES

To develop and validate a 3 T MRI primary tumor radiomics-based nomogram from multicenter datasets for pretreatment prediction of the PLNM in PDAC patients.

STUDY TYPE

Retrospective.

SUBJECTS

A total of 251 patients (156 men and 95 women; mean age, 60.85 ± 8.23 years) with histologically confirmed pancreatic ductal adenocarcinoma from three hospitals.

FIELD STRENGTH AND SEQUENCES

A 3.0 T and fat-suppressed T1-weighted imaging.

ASSESSMENT

Quantitative imaging features were extracted from fat-suppressed T1-weighted (FS T1WI) images at the arterial phase.

STATISTICAL TESTS

Normally distributed data were compared by using t-tests, while the Mann-Whitney U test was used to evaluate non-normally distributed data. The diagnostic performances of the preoperative and postoperative nomograms were assessed in the external validation cohort with the area under receiver operating characteristics curve (AUC), calibration curve, and decision curve analysis (DCA). AUCs were compared with the De Long test. A p value below 0.05 was considered to be statistically significant.

RESULTS

The AUCs of magnetic resonance imaging (MRI) Rad-score were 0.868 (95% confidence level [CI]: 0.613-0.852) and 0.772 (95% CI: 0.659-0.879) in the training and internal validation cohort, respectively. The preoperative and postoperative nomograms could accurately predict PLNM in the training cohort (AUC = 0.909 and 0.851) and were validated in both the internal and external cohorts (AUC = 0.835 and 0.805, 0.808 and 0.733, respectively). DCA indicated that the two novel nomograms are of similar clinical usefulness.

DATA CONCLUSION

Pre-/postoperative nomograms and the constructed radiomics signature from primary tumor based on FS T1WI of arterial phase could serve as a potential tool to predict PLNM in patients with PDAC. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

DCE-MRI based radiomics nomogram for preoperatively differentiating combined hepatocellular-cholangiocarcinoma from mass-forming intrahepatic cholangiocarcinoma

OBJECTIVE

To establish a radiomics nomogram based on dynamic contrast-enhanced (DCE) MR images to preoperatively differentiate combined hepatocellular-cholangiocarcinoma (cHCC-CC) from mass-forming intrahepatic cholangiocarcinoma (IMCC).

METHODS

A total of 151 training cohort patients (45 cHCC-CC and 106 IMCC) and 65 validation cohort patients (19 cHCC-CC and 46 IMCC) were enrolled. Findings of clinical characteristics and MR features were analyzed. Radiomics features were extracted from the DCE-MR images. A radiomics signature was built based on radiomics features by the least absolute shrinkage and selection operator algorithm. Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and construct a clinical model. The radiomics signature and significant clinicoradiological variables were then incorporated into the radiomics nomogram by multivariate logistic regression analysis. Performance of the radiomics nomogram, radiomics signature, and clinical model was assessed by receiver operating characteristic and area under the curve (AUC) was compared.

RESULTS

Eleven radiomics features were selected to develop the radiomics signature. The radiomics nomogram integrating the alpha fetoprotein, background liver disease (cirrhosis or chronic hepatitis), and radiomics signature showed favorable calibration and discrimination performance with an AUC value of 0.945 in training cohort and 0.897 in validation cohort. The AUCs for the radiomics signature and clinical model were 0.848 and 0.856 in training cohort and 0.792 and 0.809 in validation cohort, respectively. The radiomics nomogram outperformed both the radiomics signature and clinical model alone (p < 0.05).

CONCLUSION

The radiomics nomogram based on DCE-MRI may provide an effective and noninvasive tool to differentiate cHCC-CC from IMCC, which could help guide treatment strategies.

KEY POINTS

• The radiomics signature based on dynamic contrast-enhanced magnetic resonance imaging is useful to preoperatively differentiate cHCC-CC from IMCC. • The radiomics nomogram showed the best performance in both training and validation cohorts for differentiating cHCC-CC from IMCC.

Development and validation of a novel model incorporating MRI-based radiomics signature with clinical biomarkers for distinguishing pancreatic carcinoma from mass-forming chronic pancreatitis

•

A novel model incorporating multiparametric MRI-based radiomic signature with clinically independent risk factors can greatly improve the non-invasive diagnostic accuracy in differentiating PC from MFCP.

•

The nomogram integrating rad-score and clinically independent risk factors had a better diagnostic performance than the mp-MRI and clinical models.

•

The mixed model may aid in formulating treatment strategies and help to avoid unnecessary surgical operations for doctors.

Purpose

It is difficult to make a clear differential diagnosis of pancreatic carcinoma (PC) and mass-forming chronic pancreatitis (MFCP) via conventional examinations. We aimed to develop a novel model incorporating an MRI-based radiomics signature with clinical biomarkers for distinguishing the two lesions.

Methods

A total of 102 patients were retrospectively enrolled and randomly divided into the training and validation cohorts. Radiomics features were extracted from four different sequences. Individual imaging modality radiomics signature, multiparametric MRI (mp-MRI) radiomics signature, and a final mixed model based on mp-MRI and clinically independent risk factors were established to discriminate between PC and MFCP. The diagnostic performance of each model and model discrimination were assessed in both the training and validation cohorts.

Results

ADC had the best predictive performance among the four individual radiomics models, but there were no significant differences between the pairs of models (all p > 0.05). Six potential radiomics features were finally selected from the 960 texture features to formulate the radiomics score (rad-score) of the mp-MRI model. In addition, the boxplot results of the distributions of rad-scores identified the rad-score as an independent predictive factor for the differentiation of PC and MFCP (p< 0.001). Notably, the nomogram integrating rad-score and clinically independent risk factors had a better diagnostic performance than the mp-MRI and clinical models. These results were further confirmed by the validation group.

Conclusion

The mixed model was developed and preliminarily validated to distinguish PC from MFCP, which may benefit the formulation of treatment strategies and nonsurgical procedures.

Preoperative prediction of microvascular invasion in hepatocellular carcinoma: a radiomic nomogram based on MRI

AIM

To develop a reliable model to predict microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) by combining a large number of clinical and imaging examinations, especially the radiomic features of magnetic resonance imaging (MRI).

MATERIALS AND METHODS

Three hundred and one consecutive patients from two centres were enrolled. Least absolute shrinkage and selection operator (LASSO) regression was used to shrink the feature size, and logistic regression was used to construct a predictive radiomic signature. The ability of the nomogram to discriminate MVI in patients with HCC was evaluated using area under the curve (AUC) of receiver operating characteristics (ROC), accuracy, and calibration curves.

RESULTS

The radiomic signature showed a significant association with MVI (p<0.001 for all data sets). Other useful predictors of MVI included non-smooth tumour margin, internal arteries, and the alpha-fetoprotein (AFP) level. The nomogram demonstrated a strong prognostic capability in the training set and both validation sets, providing AUCs of 0.914 (95% confidence interval [CI] 0.853-0.956), 0.872 (95% CI: 0.757-0.946), and 0.881 (95% CI: 0.806-0.934), respectively.

CONCLUSIONS

The preoperative radiomic nomogram, incorporating clinical risk factors and a radiomic signature, could predict MVI in patients with HCC. The MRI-based radiomic-clinical model predicted the MVI of HCC effectively and was more efficient compared with the radiomic model or clinical model alone.

Development and Validation of a Radiomics Model Based on 18F-FDG PET of Primary Gastric Cancer for Predicting Peritoneal Metastasis

Objectives

The aim of this study was to develop a preoperative positron emission tomography (PET)-based radiomics model for predicting peritoneal metastasis (PM) of gastric cancer (GC).

Methods

In this study, a total of 355 patients (109PM+, 246PM-) who underwent preoperative fluorine-18-fludeoxyglucose (¹⁸F-FDG) PET images were retrospectively analyzed. According to a 7:3 ratio, patients were randomly divided into a training set and a validation set. Radiomics features and metabolic parameters data were extracted from PET images. The radiomics features were selected by logistic regression after using maximum relevance and minimum redundancy (mRMR) and the least shrinkage and selection operator (LASSO) method. The radiomics models were based on the rest of these features. The performance of the models was determined by their discrimination, calibration, and clinical usefulness in the training and validation sets.

Results

After dimensionality reduction, 12 radiomics feature parameters were obtained to construct radiomics signatures. According to the results of the multivariate logistic regression analysis, only carbohydrate antigen 125 (CA125), maximum standardized uptake value (SUVmax), and the radiomics signature showed statistically significant differences between patients (P<0.05). A radiomics model was developed based on the logistic analyses with an AUC of 0.86 in the training cohort and 0.87 in the validation cohort. The clinical prediction model based on CA125 and SUVmax was 0.76 in the training set and 0.69 in the validation set. The comprehensive model, which contained a rad-score and the clinical factor (CA125) as well as the metabolic parameter (SUVmax), showed promising performance with an AUC of 0.90 in the training cohort and 0.88 in the validation cohort, respectively. The calibration curve showed the actual rate of the nomogram-predicted probability of peritoneal metastasis. Decision curve analysis (DCA) also demonstrated the good clinical utility of the radiomics nomogram.

Conclusions

The comprehensive model based on the rad-score and other factors (SUVmax, CA125) can provide a novel tool for predicting peritoneal metastasis of gastric cancer patients preoperatively.

Radiomics Nomogram Based on Radiomics Score from Multiregional Diffusion-Weighted MRI and Clinical Factors for Evaluating HER-2 2+ Status of Breast Cancer

This study aimed to establish and validate a radiomics nomogram using the radiomics score (rad-score) based on multiregional diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) features combined with clinical factors for evaluating HER-2 2+ status of breast cancer. A total of 223 patients were retrospectively included. Radiomic features were extracted from multiregional DWI and ADC images. Based on the intratumoral, peritumoral, and combined regions, three rad-scores were calculated using the logistic regression model. Independent parameters were selected among clinical factors and combined rad-score (com-rad-score) using multivariate logistic analysis and used to construct a radiomics nomogram. The performance of the nomogram was evaluated using calibration, discrimination, and clinical usefulness. The areas under the receiver operator characteristic curve (AUCs) of intratumoral and peritumoral rad-scores were 0.824/0.763 and 0.794/0.731 in the training and validation cohorts, respectively. Com-rad-score achieved the highest AUC (0.860/0.790) among three rad-scores. ER status and com-rad-score were selected to establish the nomogram, which yielded good discrimination (AUC: 0.883/0.848) and calibration. Decision curve analysis demonstrated the clinical value of the nomogram in the validation cohort. In conclusion, radiomics nomogram, including clinical factors and com-rad-score, showed favorable performance for evaluating HER-2 2+ status in breast cancer.

Radiomics Is Effective for Distinguishing Coronavirus Disease 2019 Pneumonia From Influenza Virus Pneumonia

Objectives: To develop and validate a radiomics model for distinguishing coronavirus disease 2019 (COVID-19) pneumonia from influenza virus pneumonia.

Materials and Methods: A radiomics model was developed on the basis of 56 patients with COVID-19 pneumonia and 90 patients with influenza virus pneumonia in this retrospective study. Radiomics features were extracted from CT images. The radiomics features were reduced by the Max-Relevance and Min-Redundancy algorithm and the least absolute shrinkage and selection operator method. The radiomics model was built using the multivariate backward stepwise logistic regression. A nomogram of the radiomics model was established, and the decision curve showed the clinical usefulness of the radiomics nomogram.

Results: The radiomics features, consisting of nine selected features, were significantly different between COVID-19 pneumonia and influenza virus pneumonia in both training and validation data sets. The receiver operator characteristic curve of the radiomics model showed good discrimination in the training sample [area under the receiver operating characteristic curve (AUC), 0.909; 95% confidence interval (CI), 0.859–0.958] and in the validation sample (AUC, 0.911; 95% CI, 0.753–1.000). The nomogram was established and had good calibration. Decision curve analysis showed that the radiomics nomogram was clinically useful.

Conclusions: The radiomics model has good performance for distinguishing COVID-19 pneumonia from influenza virus pneumonia and may aid in the diagnosis of COVID-19 pneumonia.

Predicting early recurrence for resected pancreatic ductal adenocarcinoma: a multicenter retrospective study in China

A precise classification of early recurrence (ER) after radical surgery of pancreatic ductal adenocarcinoma (PDAC) has not been standardized. We aim to develop an optimal cut-off based on scientific evidence to distinguish early and late recurrence (LR) for PDAC after radical surgery and develop a predictive model for ER of PDAC. The best threshold for recurrence-free survival (RFS) was assessed with a minimum P-value method, and patients were categorized into ER and LR groups. We used a logistic regression model to assess potential risk factors for ER and develop a predictive model for ER risk. The best threshold between high-risk and intermediate-high-risk groups was identified by using the receiver operating characteristic curve. Among 3,279 patients included, 1,234 (37.6%) experienced ER. The RFS of 9 months is the optimal threshold to distinguish ER and LR. Univariable and multivariable analysis identified four preoperative risk factors for ER, including larger tumor maximal diameter on computed tomography (CT), enlarged lymph nodes on CT, carbohydrate antigen (CA) 125 > 35 U/ml, and CA19-9 > 235 U/ml. The concordance index (C-index) for the predictive model in the training cohort and the validation cohort was 0.651 (95% confidence interval (CI): 0.624-0.678), and 0.636 (95% CI: 0.593-0.679), respectively, showing promising predictive ability. The high-risk group had a score above 203, and the corresponding risk of ER for this group was 56.7%. An RFS of 9 months is the best threshold to distinguish ER and LR. The model can accurately predict the risk of ER in PDAC after radical resection, and risk grouping can predict the patients who could benefit from upfront surgery.

Machine Learning-Based Multiparametric Magnetic Resonance Imaging Radiomic Model for Discrimination of Pathological Subtypes of Craniopharyngioma

BACKGROUND

Preoperative, noninvasive discrimination of the craniopharyngioma subtypes is important because it influences the treatment strategy.

PURPOSE

To develop a radiomic model based on multiparametric magnetic resonance imaging for noninvasive discrimination of pathological subtypes of craniopharyngioma.

STUDY TYPE

Retrospective.

POPULATION

A total of 164 patients from two medical centers were enrolled in this study. Patients from the first medical center were divided into a training cohort (N = 99) and an internal validation cohort (N = 33). Patients from the second medical center were used as the external independent validation cohort (N = 32).

FIELD STRENGTH/SEQUENCE

Axial T₁ -weighted (T₁ -w), T₂ -weighted (T₂ -w), contrast-enhanced T₁ -weighted (CET₁ -w) on 3.0 T or 1.5 T magnetic resonance scanners.

ASSESSMENT

Pathological subtypes (squamous papillary craniopharyngioma and adamantinomatous craniopharyngioma) were confirmed by surgery and hematoxylin and eosin staining. Optimal radiomic feature selection was performed by SelectKBest, the least absolute shrinkage and selection operator algorithm, and support vector machine (SVM) with a recursive feature elimination algorithm. Models based on each sequence or combinations of sequences were built using a SVM classifier and used to differentiate pathological subtypes of craniopharyngioma in the training cohort, internal validation, and external validation cohorts.

STATISTICAL TESTS

The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic performance of the radiomic models.

RESULTS

Seven texture features, three from T₁ -w, two from T₂ -w, and two from CET₁ -w, were selected and used to construct the radiomic model. The AUC values of the radiomic model were 0.899, 0.810, and 0.920 in the training cohort, internal and external validation cohorts, respectively. The AUC values of the clinicoradiological model were 0.677, 0.655, and 0.671 in the training cohort, internal and external validation cohorts, respectively.

DATA CONCLUSION

The model based on radiomic features from T₁ -w, T₂ -w, and CET₁ -w has a high discriminatory ability for pathological subtypes of craniopharyngioma.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: 2.

Survival prediction after upfront surgery in patients with pancreatic ductal adenocarcinoma: Radiomic, clinic-pathologic and body composition analysis

OBJECTIVE

To investigate the value of radiomic features at contrast-enhanced CT integrated with clinic-pathologic features and body composition measures for predicting survival after upfront surgery in patients with pancreatic ductal adenocarcinoma (PDAC).

METHODS

Two hundred and ninety-nine patients with PDAC who underwent surgical resection were included and allocated to training set (210 patients) and validation set (89 patients). The radiomics signature for predicting survival was constructed by using the least absolute shrinkage and selection operator Cox regression. Multivariable Cox regression analysis was used to construct a radiomics model based on radiomics signature, clinic-pathologic features and body composition measures. A clinical model without radiomics signature was also developed. Model performance was analyzed by Harrell's concordance index (C-index) and time-independent receiver operating characteristic (ROC) analysis. The Kaplan-Meier (KM) method was used for survival analysis.

RESULTS

Five independent variables were selected for the radiomics model: radiomics signature, carbohydrate antigen 19-9, skeletal muscle index, histologic grade and postoperative chemotherapy. The radiomics-based model provided better predictive performance (C-index = 0.73; all p < 0.05) than the clinical model without radiomics signature and American Joint Committee on Cancer (AJCC) TNM staging system. Patients were stratified as high-risk and low-risk group by the radiomics model. The KM analysis showed a significant difference between two groups (p < 0.05).

CONCLUSION

The radiovdmics-based model integrating with clinic-pathologic features and body composition measures could predict survival after surgical resection in PDAC patients.

Detection of Immunotherapeutic Response in a Transgenic Mouse Model of Pancreatic Ductal Adenocarcinoma Using Multiparametric MRI Radiomics: A Preliminary Investigation

RATIONALE AND OBJECTIVES

To develop classification and regression models interpreting tumor characteristics obtained from structural (T1w and T2w) magnetic resonance imaging (MRI) data for early detection of dendritic cell (DC) vaccine treatment effects and prediction of long-term outcomes for LSL-Kras^G12D; LSL-Trp53^R172H; Pdx-1-Cre (KPC) transgenic mice model of pancreatic ductal adenocarcinoma.

MATERIALS AND METHODS

Eight mice were treated with DC vaccine for 3 weeks while eight KPC mice were used as untreated control subjects. The reproducibility of the computed 264 features was evaluated using the intraclass correlation coefficient. Key variables were determined using a three-step feature selection approach. Support vector machines classifiers were generated to differentiate treatment-related changes on tumor tissue following first- and third weeks of the DC vaccine therapy. The multivariable regression models were generated to predict overall survival (OS) and histological tumor markers of KPC mice using quantitative features.

RESULTS

The quantitative features computed from T1w MRI data have better reproducibility than T2w MRI features. The KPC mice in treatment and control groups were differentiated with a longitudinally increasing accuracy (first- and third weeks: 87.5% and 93.75%). The linear regression model generated with five features of T1w MRI data predicted OS with a root-mean-squared error (RMSE) <6 days. The proposed multivariate regression models predicted histological tumor markers with relative error <2.5% for fibrosis percentage (RMSE: 0.414), CK19⁺ area (RMSE: 0.027), and Ki67⁺ cells (RMSE: 0.190).

CONCLUSION

Our results demonstrated that proposed models generated with quantitative MRI features can be used to detect early treatment-related changes in tumor tissue and predict OS of KPC mice following DC vaccination.

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

Simple Summary

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

Abstract

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

A Novel Validated Recurrence Stratification System Based on 18F-FDG PET/CT Radiomics to Guide Surveillance After Resection of Pancreatic Cancer

objective

Despite the heterogeneous biology of pancreatic cancer, similar surveillance schemas have been used. Identifying the high recurrence risk population and conducting prompt intervention may improve prognosis and prolong overall survival.

Methods

One hundred fifty-six resectable pancreatic cancer patients who had undergone ¹⁸F-FDG PET/CT from January 2013 to December 2018 were retrospectively reviewed. The patients were categorized into a training cohort (n = 109) and a validation cohort (n = 47). LIFEx software was used to extract radiomic features from PET/CT. The risk stratification system was based on predictive factors for recurrence, and the index of prediction accuracy was used to reflect both the discrimination and calibration.

Results

Overall, seven risk factors comprising the rad-score and clinical variables that were significantly correlated with relapse were incorporated into the final risk stratification system. The 1-year recurrence-free survival differed significantly among the low-, intermediate-, and high-risk groups (85.5, 24.0, and 9.1%, respectively; p < 0.0001). The C-index of the risk stratification system in the development cohort was 0.890 (95% CI, 0.835-0.945).

Conclusion

The ¹⁸F-FDG PET/CT-based radiomic features and clinicopathological factors demonstrated good performance in predicting recurrence after pancreatectomy in pancreatic cancer patients, providing a strong recommendation for an adequate adjuvant therapy course in all patients. The high-risk recurrence population should proceed with closer follow-up in a clinical setting.

[Factors affecting survival prognosis of advanced gastric cancer and establishment of a nomogram predictive model]

OBJECTIVE

To explore the factors affecting the survival of patients with advanced gastric cancer and establish a reliable predictive model of the patients' survival outcomes.

OBJECTIVE

We retrospectively collected the clinical data from patients with advanced gastric cancer treated in our department between January, 2015 and December, 2019. Univariate survival analysis was carried out using Kaplan-Meier method followed by multivariate Cox regression analysis to identify the factors associated with the survival outcomes of the patients. The R package was used to generate the survival rates, and a nomogram was established based on the results of multivariate analysis. The calibration curves and C-index were calculated to determine the predictive and discriminatory power of the model. The performance of the nomogram model for predicting the survival outcomes of the patients was evaluated using receiver- operating characteristic (ROC) curve analysis and decision curve analysis (DCA).

OBJECTIVE

Univariate analysis showed that the number of metastatic sites, the number of treatment lines received, disease control rate (DCR) and progression-free survival (PFS) time following first-line treatment, and surgical treatment in first-line treatment were significantly correlated with the survival time of the patients (P < 0.05). Multivariate Cox regression analysis showed that surgical treatment, number of treatment lines, PFS time following first-line treatment and peritoneal metastasis, as independent prognostic factors, were significantly correlated with the patients' survival (P < 0.05). The C-index of the nomogram was 0.785 (95%CI: 0.744-0.826) for overall survival of the patients. The calibration curves showed that the actual survival rate of the patients was consistent with the predicted survival rate. The time-dependent AUC and DCA demonstrated that the nomogram had a good performance for predicting the survival outcomes of patients with advanced gastric cancer.

OBJECTIVE

Peritoneal metastasis is associated with s shorter overall survival time of patients with advanced gastric cancer, while a PFS time following first-line treatment of more than 7.0 months and third-line and posterior-line treatments are related with a longer survival time. Systematic treatment including elective surgery can improve the survival outcomes of the patients. The nomogram we established provides a reliable prognostic model for evaluating the prognosis of patients with advanced gastric cancer.

Application of Functional Magnetic Resonance Imaging in the Diagnosis of Parkinson's Disease: A Histogram Analysis

This study aimed to investigate the value of amplitude of low-frequency fluctuation (ALFF)-based histogram analysis in the diagnosis of Parkinson's disease (PD) and to investigate the regions of the most important discriminative features and their contribution to classification discrimination. Patients with PD (n = 59) and healthy controls (HCs; n = 41) were identified and divided into a primary set (80 cases, including 48 patients with PD and 32 HCs) and a validation set (20 cases, including 11 patients with PD and nine HCs). The Automated Anatomical Labeling (AAL) 116 atlas was used to extract the histogram features of the regions of interest in the brain. Machine learning methods were used in the primary set for data dimensionality reduction, feature selection, model construction, and model performance evaluation. The model performance was further validated in the validation set. After feature data dimension reduction and feature selection, 23 of a total of 1,276 features were entered in the model. The brain regions of the selected features included the frontal, temporal, parietal, occipital, and limbic lobes, as well as the cerebellum and the thalamus. In the primary set, the area under the curve (AUC) of the model was 0.974, the sensitivity was 93.8%, the specificity was 90.6%, and the accuracy was 93.8%. In the validation set, the AUC, sensitivity, specificity, and accuracy were 0.980, 90.9%, 88.9%, and 90.0%, respectively. ALFF-based histogram analysis can be used to classify patients with PD and HCs and to effectively identify abnormal brain function regions in PD patients.

Radiomics Based on T2-Weighted Imaging and Apparent Diffusion Coefficient Images for Preoperative Evaluation of Lymph Node Metastasis in Rectal Cancer Patients

Purpose

To develop and validate a radiomics nomogram based on T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) features for the preoperative prediction of lymph node (LN) metastasis in rectal cancer patients.

Materials and Methods

One hundred and sixty-two patients with rectal cancer confirmed by pathology were retrospectively analyzed, who underwent T2WI and DWI sequences. The data sets were divided into training (n = 97) and validation (n = 65) cohorts. For each case, a total of 2,752 radiomic features were extracted from T2WI, and ADC images derived from diffusion-weighted imaging. A two-sample t-test was used for prefiltering. The least absolute shrinkage selection operator method was used for feature selection. Three radiomics scores (rad-scores) (rad-score 1 for T2WI, rad-score 2 for ADC, and rad-score 3 for the combination of both) were calculated using the support vector machine classifier. Multivariable logistic regression analysis was then used to construct a radiomics nomogram combining rad-score 3 and independent risk factors. The performances of three rad-scores and the nomogram were evaluated using the area under the receiver operating characteristic curve (AUC). Decision curve analysis (DCA) was used to assess the clinical usefulness of the radiomics nomogram.

Results

The AUCs of the rad-score 1 and rad-score 2 were 0.805, 0.749 and 0.828, 0.770 in the training and validation cohorts, respectively. The rad-score 3 achieved an AUC of 0.879 in the training cohort and an AUC of 0.822 in the validation cohort. The radiomics nomogram, incorporating the rad-score 3, age, and LN size, showed good discrimination with the AUC of 0.937 for the training cohort and 0.884 for the validation cohort. DCA confirmed that the radiomics nomogram had clinical utility.

Conclusions

The radiomics nomogram, incorporating rad-score based on features from the T2WI and ADC images, and clinical factors, has favorable predictive performance for preoperative prediction of LN metastasis in patients with rectal cancer.

Artificial intelligence for early detection of pancreatic adenocarcinoma: The future is promising

Pancreatic ductal adenocarcinoma (PDAC) is a worldwide public health concern. Despite extensive research efforts toward improving diagnosis and treatment, the 5-year survival rate at best is approximately 15%. This dismal figure can be attributed to a variety of factors including lack of adequate screening methods, late symptom onset, and treatment resistance. Pancreatic ductal adenocarcinoma remains a grim diagnosis with a high mortality rate and a significant psy-chological burden for patients and their families. In recent years artificial intelligence (AI) has permeated the medical field at an accelerated pace, bringing potential new tools that carry the promise of improving diagnosis and treatment of a variety of diseases. In this review we will summarize the landscape of AI in diagnosis and treatment of PDAC.

Diagnostic Value of Conventional PET Parameters and Radiomic Features Extracted from 18F-FDG-PET/CT for Histologic Subtype Classification and Characterization of Lung Neuroendocrine Neoplasms

Aim: To evaluate if conventional Positron emission tomography (PET) parameters and radiomic features (RFs) extracted by 18F-FDG-PET/CT can differentiate among different histological subtypes of lung neuroendocrine neoplasms (Lu-NENs). Methods: Forty-four naïve-treatment patients on whom 18F-FDG-PET/CT was performed for histologically confirmed Lu-NEN (n = 46) were retrospectively included. Manual segmentation was performed by two operators allowing for extraction of four conventional PET parameters (SUVmax, SUVmean, metabolic tumor volume (MTV), and total lesion glycolysis (TLG)) and 41 RFs. Lu-NENs were classified into two groups: lung neuroendocrine tumors (Lu-NETs) vs. lung neuroendocrine carcinomas (Lu-NECs). Lu-NETs were classified according to histological subtypes (typical (TC)/atypical carcinoid (AC)), Ki67-level, and TNM staging. The least absolute shrink age and selection operator (LASSO) method was used to select the most predictive RFs for classification and Pearson correlation analysis was performed between conventional PET parameters and selected RFs. Results: PET parameters, in particular, SUVmax (area under the curve (AUC) = 0.91; cut-off = 5.16) were higher in Lu-NECs vs. Lu-NETs (p < 0.001). Among RFs, HISTO_Entropy_log10 was the most predictive (AUC = 0.90), but correlated with SUVmax/SUVmean (r = 0.95/r = 0.94, respectively). No statistical differences were found between conventional PET parameters and RFs (p > 0.05) and TC vs. AC classification. Conventional PET parameters were correlated with N+ status in Lu-NETs. Conclusion: In our study, conventional PET parameters were able to distinguish Lu-NECs from Lu-NETs, but not TC from AC. RFs did not provide additional information.

Radiomics signature on dynamic contrast-enhanced MR images: a potential imaging biomarker for prediction of microvascular invasion in mass-forming intrahepatic cholangiocarcinoma

OBJECTIVE

To develop a radiomics signature based on dynamic contrast-enhanced (DCE) MR images for preoperative prediction of microvascular invasion (MVI) in patients with mass-forming intrahepatic cholangiocarcinoma (IMCC).

METHODS

One hundred twenty-six patients with surgically resected single IMCC (34 MVI-positive and 92 MVI-negative) were enrolled and allocated to training and validation cohorts (7:3 ratio). Findings of clinical characteristics and MR features were analyzed. A radiomics signature was built on the basis of reproducible features by using the least absolute shrinkage and selection operator (LASSO) regression algorithm in the training cohort. The prediction performance of radiomics signature was evaluated by receiver operating characteristics curve (ROC) analysis. Internal validation was performed on an independent cohort containing 38 patients.

RESULTS

Larger tumor size and higher radiomics score were positively correlated with MVI in both training cohort (p < 0.001, < 0.001, respectively) and validation cohort (p = 0.008, 0.001, respectively). The radiomics signature, consisting of seven wavelet features, showed optimal prediction performance in both training (AUC = 0.873) and validation cohorts (AUC = 0.850).

CONCLUSION

A radiomics signature derived from DCE-MRI of the liver can be a reliable imaging biomarker for predicting MVI of IMCC, which could aid in tailoring treatment strategies.

KEY POINTS

• The radiomics signature based on dynamic contrast-enhanced magnetic resonance imaging can be a useful tool to preoperatively predict MVI of IMCC. • Larger tumor size is positively correlated with MVI of IMCC.

Diffusion kurtosis imaging to evaluate the effect and mechanism of tetramethylpyrazine on cognitive impairment induced by lipopolysaccharide in rats

Using diffusion kurtosis imaging (DKI) to evaluate the brain changes, the therapeutic effect and mechanism of tetramethylpyrazine in rats with dementia induced by lipopolysaccharide. Thirty-six male Sprague-Dawley rats were randomly divided into control group and five groups pretreated with sham operation, lipopolysaccharide(150ug) and three doses of tetramethylpyrazine(5, 10, and 20 mg/mL respectively). The Morris water maze test was used to evaluate cognitive ability. DKI and histology were performed. Low-dose of tetramethylpyrazine pretreated rats showed lower escape latency(6th day: 15.92seconds(s) vs. 5.11 s, P = 0.001), spent more time in the target quadrant(15.67 s vs. 29.83 s, P = 0.009) and crossed the platform area more frequently(3.50 vs. 9.17, P = 0.001) than rats in the LPS-treated group. Compared to sham group, the fractional anisotropy (FA), axial diffusion (Da), mean kurtosis (MK), and axial kurtosis (Ka) values in the cortex of lipopolysaccharide group were lower (P = 0.021,0.003,0.003,0.001,respectively).The MK, Ka, Kr, and FA values in the hippocampus of the lipopolysaccharide group were higher (P = 0.01, 0.026,0.007,0.003,respectively),while MD and Da values were lower (P = 0.045,0.044, respectively). Tetramethylpyrazine-pretreated rats showed higher values of FA, MD, Da, MK, and Ka in the cortex, lower MK, Ka, Kr, and FA values and higher MD,Da values in the hippocampus than the lipopolysaccharide group. Histologically, prominent inflammatory cells infiltration in the brain parenchyma of lipopolysaccharide group were observed, while groups pretreated using tetramethylpyrazine were alleviated. Tetramethylpyrazine can improve cognitive dysfunction induced by lipopolysaccharide. DKI can sensitively detect microstructure integrity of brain parenchyma in a non-invasive manner.

Delta Radiomics Analysis for Local Control Prediction in Pancreatic Cancer Patients Treated Using Magnetic Resonance Guided Radiotherapy

The aim of this study is to investigate the role of Delta Radiomics analysis in the prediction of one-year local control (1yLC) in patients affected by locally advanced pancreatic cancer (LAPC) and treated using Magnetic Resonance guided Radiotherapy (MRgRT). A total of 35 patients from two institutions were enrolled: A 0.35 Tesla T2*/T1 MR image was acquired for each case during simulation and on each treatment fraction. Physical dose was converted in biologically effective dose (BED) to compensate for different radiotherapy schemes. Delta Radiomics analysis was performed considering the gross tumour volume (GTV) delineated on MR images acquired at BED of 20, 40, and 60 Gy. The performance of the delta features in predicting 1yLC was investigated in terms of Wilcoxon Mann-Whitney test and area under receiver operating characteristic (ROC) curve (AUC). The most significant feature in predicting 1yLC was the variation of cluster shade calculated at BED = 40 Gy, with a p-value of 0.005 and an AUC of 0.78 (0.61-0.94). Delta Radiomics analysis on low-field MR images might play a promising role in 1yLC prediction for LAPC patients: further studies including an external validation dataset and a larger cohort of patients are recommended to confirm the validity of this preliminary experience.

Radiomics Analysis Based on Multiparametric MRI for Predicting Early Recurrence in Hepatocellular Carcinoma After Partial Hepatectomy

BACKGROUND

Preoperative prediction of early recurrence (ER) of hepatocellular carcinoma (HCC) plays a critical role in individualized risk stratification and further treatment guidance.

PURPOSE

To investigate the role of radiomics analysis based on multiparametric MRI (mpMRI) for predicting ER in HCC after partial hepatectomy.

STUDY TYPE

Retrospective.

POPULATION

In all, 113 HCC patients (ER, n = 58 vs. non-ER, n = 55), divided into training (n = 78) and validation (n = 35) cohorts.

FIELD STRENGTH/SEQUENCE

1.5T or 3.0T, gradient-recalled-echo in-phase T₁ -weighted imaging (I-T₁ WI) and opposed-phase T₁ WI (O-T₁ WI), fast spin-echo T₂ -weighted imaging (T₂ WI), spin-echo planar diffusion-weighted imaging (DWI), and gradient-recalled-echo contrast-enhanced MRI (CE-MRI).

ASSESSMENT

In all, 1146 radiomics features were extracted from each image sequence, and radiomics models based on each sequence and their combination were established via multivariate logistic regression analysis. The clinicopathologic-radiologic (CPR) model and the combined model integrating the radiomics score with the CPR risk factors were constructed. A nomogram based on the combined model was established.

STATISTICAL TESTS

Receiver operating characteristic (ROC) curve analysis was used to evaluate the discriminative performance of each model. The potential clinical usefulness was evaluated by decision curve analysis (DCA).

RESULTS

The radiomics model based on I-T₁ WI, O-T₁ WI, T₂ WI, and CE-MRI sequences presented the best performance among all radiomics models with an area under the ROC curve (AUC) of 0.771 (95% confidence interval (CI): 0.598-0.894) in the validation cohort. The combined nomogram (AUC: 0.873; 95% CI: 0.756-0.989) outperformed the radiomics model and the CPR model (AUC: 0.742; 95% CI: 0.577-0.907). DCA demonstrated that the combined nomogram was clinically useful.

DATA CONCLUSION

The mpMRI-based radiomics analysis has potential to predict ER of HCC patients after hepatectomy, which could enhance risk stratification and provide support for individualized treatment planning.

EVIDENCE LEVEL

4.

TECHNICAL EFFICACY

Stage 4.

Pancreas image mining: a systematic review of radiomics

OBJECTIVES

To systematically review published studies on the use of radiomics of the pancreas.

METHODS

The search was conducted in the MEDLINE database. Human studies that investigated the applications of radiomics in diseases of the pancreas were included. The radiomics quality score was calculated for each included study.

RESULTS

A total of 72 studies encompassing 8863 participants were included. Of them, 66 investigated focal pancreatic lesions (pancreatic cancer, precancerous lesions, or benign lesions); 4, pancreatitis; and 2, diabetes mellitus. The principal applications of radiomics were differential diagnosis between various types of focal pancreatic lesions (n = 19), classification of pancreatic diseases (n = 23), and prediction of prognosis or treatment response (n = 30). Second-order texture features were most useful for the purpose of differential diagnosis of diseases of the pancreas (with 100% of studies investigating them found a statistically significant feature), whereas filtered image features were most useful for the purpose of classification of diseases of the pancreas and prediction of diseases of the pancreas (with 100% of studies investigating them found a statistically significant feature). The median radiomics quality score of the included studies was 28%, with the interquartile range of 22% to 36%. The radiomics quality score was significantly correlated with the number of extracted radiomics features (r = 0.52, p < 0.001) and the study sample size (r = 0.34, p = 0.003).

CONCLUSIONS

Radiomics of the pancreas holds promise as a quantitative imaging biomarker of both focal pancreatic lesions and diffuse changes of the pancreas. The usefulness of radiomics features may vary depending on the purpose of their application. Standardisation of image acquisition protocols and image pre-processing is warranted prior to considering the use of radiomics of the pancreas in routine clinical practice.

KEY POINTS

• Methodologically sound studies on radiomics of the pancreas are characterised by a large sample size and a large number of extracted features. • Optimisation of the radiomics pipeline will increase the clinical utility of mineable pancreas imaging data. • Radiomics of the pancreas is a promising personalised medicine tool in diseases of the pancreas.