Preoperative prediction of tumour deposits in rectal cancer by an artificial neural network-based US radiomics model

Radiomics based on T2-weighted and diffusion-weighted MR imaging for preoperative prediction of tumor deposits in rectal cancer

AIM

Preoperative diagnosis of tumor deposits (TDs) in patients with rectal cancer remains a challenge. This study aims to develop and validate a radiomics nomogram based on the combination of T2-weighted (T2WI) and diffusion-weighted MR imaging (DWI) for the preoperative identification of TDs in rectal cancer.

MATERIALS AND METHODS

A total of 199 patients with rectal cancer who underwent T2WI and DWI were retrospectively enrolled and divided into a training set (n ​= ​159) and a validation set (n ​= ​40). The total incidence of TDs was 37.2 ​% (74/199). Radiomics features were extracted from T2WI and apparent diffusion coefficient (ADC) images. A radiomics nomogram combining Rad-score (T2WI ​+ ​ADC) and clinical factors was subsequently constructed. The area under the receiver operating characteristic curve (AUC) was then calculated to evaluate the models. The nomogram is also compared to three machine learning model constructed based on no-Rad scores.

RESULTS

The Rad-score (T2WI ​+ ​ADC) achieved an AUC of 0.831 in the training and 0.859 in the validation set. The radiomics nomogram (the combined model), incorporating the Rad-score (T2WI ​+ ​ADC), MRI-reported lymph node status (mLN-status), and CA19-9, showed good discrimination of TDs with an AUC of 0.854 for the training and 0.923 for the validation set, which was superior to Random Forests, Support Vector Machines, and Deep Learning models. The combined model for predicting TDs outperformed the other three machine learning models showed an accuracy of 82.5 ​% in the validation set, with sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 66.7 ​%, 92.0 ​%, 83.3 ​%, and 82.1 ​%, respectively.

CONCLUSION

The radiomics nomogram based on Rad-score (T2WI ​+ ​ADC) and clinical factors provides a promising and effective method for the preoperative prediction of TDs in patients with rectal cancer.

T2WI-based MRI radiomics for the prediction of preoperative extranodal extension and prognosis in resectable rectal cancer

OBJECTIVE

To investigate whether T2-weighted imaging (T2WI)-based intratumoral and peritumoral radiomics can predict extranodal extension (ENE) and prognosis in patients with resectable rectal cancer.

METHODS

One hundred sixty-seven patients with resectable rectal cancer including T3T4N + cases were prospectively included. Radiomics features were extracted from intratumoral, peritumoral 3 mm, and peritumoral-mesorectal fat on T2WI images. Least absolute shrinkage and selection operator regression were used for feature selection. A radiomics signature score (Radscore) was built with logistic regression analysis. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of each Radscore. A clinical-radiomics nomogram was constructed by the most predictive radiomics signature and clinical risk factors. A prognostic model was constructed by Cox regression analysis to identify 3-year recurrence-free survival (RFS).

RESULTS

Age, cT stage, and lymph node-irregular border and/or adjacent fat invasion were identified as independent clinical risk factors to construct a clinical model. The nomogram incorporating intratumoral and peritumoral 3 mm Radscore and independent clinical risk factors achieved a better AUC than the clinical model in the training (0.799 vs. 0.736) and validation cohorts (0.723 vs. 0.667). Nomogram-based ENE (hazard ratio [HR] = 2.625, 95% CI = 1.233-5.586, p = 0.012) and extramural vascular invasion (EMVI) (HR = 2.523, 95% CI = 1.247-5.106, p = 0.010) were independent risk factors for predicting 3-year RFS. The prognostic model constructed by these two indicators showed good performance for predicting 3-year RFS in the training (AUC = 0.761) and validation cohorts (AUC = 0.710).

CONCLUSION

The nomogram incorporating intratumoral and peritumoral 3 mm Radscore and clinical risk factors could predict preoperative ENE. Combining nomogram-based ENE and MRI-reported EMVI may be useful in predicting 3-year RFS.

CRITICAL RELEVANCE STATEMENT

A clinical-radiomics nomogram could help preoperative predict ENE, and a prognostic model constructed by the nomogram-based ENE and MRI-reported EMVI could predict 3-year RFS in patients with resectable rectal cancer.

KEY POINTS

• Intratumoral and peritumoral 3 mm Radscore showed the most capability for predicting ENE. • Clinical-radiomics nomogram achieved the best predictive performance for predicting ENE. • Combining clinical-radiomics based-ENE and EMVI showed good performance for 3-year RFS.

Endoscopic Rectal Ultrasound-Based Radiomics Analysis for the Prediction of Synchronous Liver Metastasis in Patients With Primary Rectal Cancer

OBJECTIVES

To develop and validate an ultrasound-based radiomics model to predict synchronous liver metastases (SLM) in rectal cancer (RC) patients preoperatively.

METHODS

Two hundred and thirty-nine RC patients were included in this study and randomly divided into training and validation cohorts. A total of 5936 radiomics features were calculated on the basis of ultrasound images to build a radiomic model and obtain a radiomics score (Rad-score) using logistic regression. Meanwhile, clinical characteristics were collected to construct a clinical model. The radiomics-clinical model was developed and validated by integrating the radiomics features with the selected clinical characteristics. The performances of three models were evaluated and compared through their discrimination, calibration, and clinical usefulness.

RESULTS

The radiomics model was developed based on 13 radiomic features. The radiomics-clinical model, which incorporated Rad-score, CEA, and CA199, exhibited favorable discrimination and calibration with areas under the receiver operating characteristic curve (AUC) of 0.920 (95% CI: 0.874-0.965) in the training cohorts and 0.855 (95% CI: 0.759-0.951) in the validation cohorts. And the AUC of the radiomics-clinical model was 0.849 (95% CI: 0.771-0.927) for the training cohorts and 0.780 (95% CI: 0.655-0.905) for the validation cohorts, the clinical model was 0.811 (95% CI: 0.718-0.905) for the training cohorts and 0.805 (95% CI: 0.645-0.965) for the validation cohorts. Moreover, decision curve analysis (DCA) further confirmed the clinical utility of the radiomics-clinical model.

CONCLUSIONS

The radiomics-clinical model performed satisfactory predictive performance, which can help improve clinical diagnosis performance and outcome prediction for SLM in RC patients.

Predicting tumor deposits in rectal cancer: a combined deep learning model using T2-MR imaging and clinical features

BACKGROUND

Tumor deposits (TDs) are associated with poor prognosis in rectal cancer (RC). This study aims to develop and validate a deep learning (DL) model incorporating T2-MR image and clinical factors for the preoperative prediction of TDs in RC patients.

METHODS AND METHODS

A total of 327 RC patients with pathologically confirmed TDs status from January 2016 to December 2019 were retrospectively recruited, and the T2-MR images and clinical variables were collected. Patients were randomly split into a development dataset (n = 246) and an independent testing dataset (n = 81). A single-channel DL model, a multi-channel DL model, a hybrid DL model, and a clinical model were constructed. The performance of these predictive models was assessed by using receiver operating characteristics (ROC) analysis and decision curve analysis (DCA).

RESULTS

The areas under the curves (AUCs) of the clinical, single-DL, multi-DL, and hybrid-DL models were 0.734 (95% CI, 0.674-0.788), 0.710 (95% CI, 0.649-0.766), 0.767 (95% CI, 0.710-0.819), and 0.857 (95% CI, 0.807-0.898) in the development dataset. The AUC of the hybrid-DL model was significantly higher than the single-DL and multi-DL models (both p < 0.001) in the development dataset, and the single-DL model (p = 0.028) in the testing dataset. Decision curve analysis demonstrated the hybrid-DL model had higher net benefit than other models across the majority range of threshold probabilities.

CONCLUSIONS

The proposed hybrid-DL model achieved good predictive efficacy and could be used to predict tumor deposits in rectal cancer.

CRITICAL RELEVANCE STATEMENT

The proposed hybrid-DL model achieved good predictive efficacy and could be used to predict tumor deposits in rectal cancer.

KEY POINTS

• Preoperative non-invasive identification of TDs is of great clinical significance. • The combined hybrid-DL model achieved good predictive efficacy and could be used to predict tumor deposits in rectal cancer. • A preoperative nomogram provides gastroenterologist with an accurate and effective tool.

The Crying Need for a Better Response Assessment in Rectal Cancer

OPINION STATEMENT

Since total neoadjuvant treatment achieves almost 30% pathologic complete response, organ preservation has been increasingly debated for good responders after neoadjuvant treatment for patients diagnosed with rectal cancer. Two organ preservation strategies are available: a watch and wait strategy and a local excision strategy including patients with a near clinical complete response. A major issue is the selection of patients according to the initial tumor staging or the response assessment. Despite modern imaging improvement, identifying complete response remains challenging. A better selection could be possible by radiomics analyses, exploiting numerous image features to feed data characterization algorithms. The subsequent step is to include baseline and/or pre-therapeutic MRI, PET-CT, and CT radiomics added to the patients' clinicopathological data, inside machine learning (ML) prediction models, with predictive or prognostic purposes. These models could be further improved by the addition of new biomarkers such as circulating tumor biomarkers, molecular profiling, or pathological immune biomarkers.

Multiregional-based magnetic resonance imaging radiomics model for predicting tumor deposits in resectable rectal cancer

PURPOSE

To establish and validate an integrated model incorporating multiregional magnetic resonance imaging (MRI) radiomics features and clinical factors to predict tumor deposits (TDs) preoperatively in resectable rectal cancer (RC).

METHODS

This study retrospectively included 148 resectable RC patients [TDs+ (n = 45); TDs- (n = 103)] from August 2016 to August 2022, who were divided randomly into a testing cohort (n = 45) and a training cohort (n = 103). Radiomics features were extracted from the volume of interest on T2-weighted images (T2WI) and diffusion-weighted images (DWI) from pretreatment MRI. Model construction was performed after feature selection. Finally, five classification models were developed by support vector machine (SVM) algorithm to predict TDs in resectable RC using the selected clinical factor, single-regional radiomics features (extracted from primary tumor), and multiregional radiomics features (extracted from the primary tumor and mesorectal fat). Receiver-operating characteristic (ROC) curve analysis was employed to assess the discrimination performance of the five models. The AUCs of five models were compared by DeLon's test.

RESULTS

The training and testing cohorts included 31 (30.1%) and 14 (31.1%) patients with TDs, respectively. The AUCs of multiregional radiomics, single-regional radiomics, and the clinical models for predicting TDs were 0.839, 0.765, and 0.793, respectively. An integrated model incorporating multiregional radiomics features and clinical factors showed good predictive performance for predicting TDs in resectable RC (AUC, 0.931; 95% CI, 0.841-0.988), which demonstrated superiority over clinical model (P = 0.016), the single-regional radiomics model (P = 0.042), and the multiregional radiomics model (P = 0.025).

CONCLUSION

An integrated model combining multiregional MRI radiomic features and clinical factors can improve prediction performance for TDs and guide clinicians in implementing treatment plans individually for resectable RC patients.

MRI-based multiregional radiomics for preoperative prediction of tumor deposit and prognosis in resectable rectal cancer: a bicenter study

OBJECTIVE

To build T2WI-based multiregional radiomics for predicting tumor deposit (TD) and prognosis in patients with resectable rectal cancer.

MATERIALS AND METHODS

A total of 208 patients with pathologically confirmed rectal cancer from two hospitals were prospectively enrolled. Intra- and peritumoral features were extracted separately from T2WI images and the least absolute shrinkage and selection operator was used to screen the most valuable radiomics features. Clinical-radiomics nomogram was developed by radiomics signatures and the most predictive clinical parameters. Prognostic model for 3-year recurrence-free survival (RFS) was constructed using univariate and multivariate Cox analysis.

RESULTS

For TD, the area under the receiver operating characteristic curve (AUC) for intratumoral radiomics model was 0.956, 0.823, and 0.860 in the training cohort, test cohort, and external validation cohort, respectively. AUC for the peritumoral radiomics model was 0.929, 0.906, and 0.773 in the training cohort, test cohort, and external validation cohort, respectively. The AUC for combined intra- and peritumoral radiomics model was 0.976, 0.918, and 0.874 in the training cohort, test cohort, and external validation cohort, respectively. The AUC for clinical-radiomics nomogram was 0.989, 0.777, and 0.870 in the training cohort, test cohort, and external validation cohort, respectively. The prognostic model constructed by combining intra- and peritumoral radiomics signature score (radscore)-based TD and MRI-reported lymph nodes metastasis (LNM) indicated good performance for predicting 3-year RFS, with AUC of 0.824, 0.865, and 0.738 in the training cohort, test cohort and external validation cohort, respectively.

CONCLUSION

Combined intra- and peritumoral radiomics model showed good performance for predicting TD. Combining intra- and peritumoral radscore-based TD and MRI-reported LNM indicated the recurrence risk.

CLINICAL RELEVANCE STATEMENT

Combined intra- and peritumoral radiomics model could help accurately predict tumor deposits. Combining this predictive model-based tumor deposits with MRI-reported lymph node metastasis was associated with relapse risk of rectal cancer after surgery.

KEY POINTS

• Combined intra- and peritumoral radiomics model provided better diagnostic performance than that of intratumoral and peritumoral radiomics model alone for predicting TD in rectal cancer. • The predictive performance of the clinical-radiomics nomogram was not improved compared with the combined intra- and peritumoral radiomics model for predicting TD. • The prognostic model constructed by combining intra- and peritumoral radscore-based TD and MRI-reported LNM showed good performance for assessing 3-year RFS.

A different perspective on 18F-FDG PET radiomics in colorectal cancer patients: The relationship between intra & peritumoral analysis and pathological findings

OBJECTIVE

We aimed to determine the value of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) based primary tumoral and peritumoral radiomics in the prediction of tumor deposits (TDs), tumor budding (TB) and extramural venous invasion (EMVI) of colorectal cancer (CRC).

METHODS

Our retrospective study included 77 CRC patients who had preoperative 18F-FDG PET/CT between June 2020 and February 2022. A total of 131 radiomic features were extracted from primary tumors and peritumoral areas on PET/CT fusion images. The relationship between TDs, TB, EMVI and T stage in the postoperative pathology of the tumors and radiomic features was investigated. Features with a correlation coefficient (CC) less than 0.8 were analyzed by logistic regression. The area under curve (AUC) obtained from the receiver operating characteristic analysis was used to measure the model performance.

RESULTS

A model was developed from primary tumoral and peritumoral radiomics data to predict T stage (AUC 0.931), and also a predictive model was constructed from primary tumor derived radiomics to predict EMVI (AUC 0.739). Radiomic data derived from the primary tumor was obtained as a predictive prognostic factor in predicting TDs and a peritumoral feature was found to be a prognostic factor in predicting TB.

CONCLUSIONS

Intratumoral and peritumoral radiomics derived from 18F-FDG PET/CT are useful for non-invasive early prediction of pathological features that have important implications in the management of CRC.

A nomogram for preoperative differentiation of tumor deposits from lymph node metastasis in rectal cancer: A retrospective study

The objective is to develop and validate a combined model for noninvasive preoperative differentiating tumor deposits (TDs) from lymph node metastasis (LNM) in patients with rectal cancer (RC). A total of 204 patients were enrolled and randomly divided into 2 sets (training and validation set) at a ratio of 8:2. Radiomics features of tumor and peritumor fat were extracted by using Pyradiomics software from the axial T2-weighted imaging of MRI. Rad-score based on extracted Radiomics features were calculated by combination of feature selection and the machine learning method. Factors (Rad-score, laboratory test factor, clinical factor, traditional characters of tumor on MRI) with statistical significance were integrated to build a combined model. The combined model was visualized by a nomogram, and its distinguish ability, diagnostic accuracy, and clinical utility were evaluated by the receiver operating characteristic curve (ROC) analysis, calibration curve, and clinical decision curve, respectively. Carbohydrate antigen (CA) 19-9, MRI reported node stage (MRI-N stage), tumor volume (cm3), and Rad-score were all included in the combined model (odds ratio = 3.881 for Rad-score, 2.859 for CA19-9, 0.411 for MRI-N stage, and 1.055 for tumor volume). The distinguish ability of the combined model in the training and validation cohorts was area under the summary receiver operating characteristic curve (AUC) = 0.863, 95% confidence interval (CI): 0.8-0.911 and 0.815, 95% CI: 0.663-0.919, respectively. And the combined model outperformed the clinical model in both training and validation cohorts (AUC = 0.863 vs 0.749, 0.815 vs 0.627, P = .0022, .0302), outperformed the Rad-score model only in training cohorts (AUC = 0.863 vs 0.819, P = .0283). The combined model had highest net benefit and showed good diagnostic accuracy. The combined model incorporating Rad-score and clinical factors could provide a preoperative differentiation of TD from LNM and guide clinicians in making individualized treatment strategy for patients with RC.

Computed Tomography-based Radiomics Nomogram for the Preoperative Prediction of Tumor Deposits and Clinical Outcomes in Colon Cancer: a Multicenter Study

RATIONALE AND OBJECTIVES

To develop and validate a computed tomography (CT)-based radiomics nomogram for the preoperative prediction of tumor deposits (TDs) and clinical outcomes in patients with colon cancer.

MATERIALS AND METHODS

This retrospective study included 383 consecutive patients with colon cancer from two centers. Radiomics features were extracted from portal venous phase CT images. Least absolute shrinkage and selection operator regression was applied for feature selection and radiomics signature construction. The multivariate logistic regression model was used to establish a radiomics nomogram. The performance of the nomogram was assessed by using receiver operating characteristic curves, calibration curves and decision curve analysis. Kaplan‒Meier survival analysis was used to assess the difference of the overall survival (OS) in the TDs-positive and TDs-negative groups.

RESULTS

The radiomics signature was composed of 11 TDs status related features. The AUCs of the radiomics model in the training cohort, internal validation and external validation cohorts were 0.82, 0.78 and 0.78, respectively. The radiomics nomogram that incorporated the radiomics signature and clinical independent predictors (CT-N, CEA and CA199) showed good calibration and discrimination with AUCs of 0.88, 0.80 and 0.81 in the training cohort, internal validation and external validation cohorts, respectively. The radiomics nomogram-predicted high-risk groups had a worse OS than the low-risk groups (p < 0.001). The radiomics nomogram-predicted TDs was an independent preoperative predictor of OS.

CONCLUSION

The radiomics nomogram based on CT radiomics features and clinical independent predictors could effectively predict the preoperative TDs status and OS of colon cancer.

IMPORTANT FINDINGS

CT-based radiomics nomogram may be applied in the individual preoperative prediction of TDs status in colon cancer. Additionally, there was a significant difference in OS between the high-risk and low-risk groups defined by the radiomics nomogram, in which patients with high-risk TDs had a significantly worse OS, compared with those with low-risk TDs.

Artificial intelligence - based ultrasound elastography for disease evaluation - a narrative review

Ultrasound elastography (USE) provides complementary information of tissue stiffness and elasticity to conventional ultrasound imaging. It is noninvasive and free of radiation, and has become a valuable tool to improve diagnostic performance with conventional ultrasound imaging. However, the diagnostic accuracy will be reduced due to high operator-dependence and intra- and inter-observer variability in visual observations of radiologists. Artificial intelligence (AI) has great potential to perform automatic medical image analysis tasks to provide a more objective, accurate and intelligent diagnosis. More recently, the enhanced diagnostic performance of AI applied to USE have been demonstrated for various disease evaluations. This review provides an overview of the basic concepts of USE and AI techniques for clinical radiologists and then introduces the applications of AI in USE imaging that focus on the following anatomical sites: liver, breast, thyroid and other organs for lesion detection and segmentation, machine learning (ML) - assisted classification and prognosis prediction. In addition, the existing challenges and future trends of AI in USE are also discussed.

Magnetic resonance imaging radiomics modeling predicts tumor deposits and prognosis in stage T3 lymph node positive rectal cancer

PURPOSE

To develop a magnetic resonance imaging radiomics model to predict tumor deposits (TDs) and prognosis in stage T3 lymph node positive (T3N+) rectal cancer (RC).

METHODS

This retrospective study included 163 patients with pathologically confirmed T3N + RC from December 2013 to December 2015. The patients were divided into two groups for training and testing. Extracting radiomic features from MR images and selecting features using principal component analysis (PCA), then radiomic scores (rad-scores) were obtained by logistic regression analysis. Finally, a combined TDs prediction model containing rad-scores and clinical features was developed. A receiver operating characteristic (ROC) curve was used to assess the prediction performance. The overall survival (OS) rate in patients with high-risk and low-risk TDs predicted by rad-scores was validated by Kaplan-Meier survival curves.

RESULTS

Of the 163 patients included, histological TDs was diagnosed in 45 patients. The area under the curve (AUC) of the final model was 0.833 (training) and 0.844 (testing). The patients with rad-scores predicted high-risk were associated with OS. In addition, postoperative adjuvant therapy improved the OS of the high-risk TDs group (P < 0.05).

CONCLUSION

MRI-based radiomics modeling helps in the preoperative prediction of patients with TDs+ in T3N + RC and provides risk stratification for neoadjuvant therapy. In addition, the rad-scores of TDs could suggest different survival benefits of postoperative adjuvant therapy for T3N + RC patients and guide clinical treatment.

Preoperative prediction of tumor deposits in rectal cancer with clinical-magnetic resonance deep learning-based radiomic models

Background

This study aimed to establish an effective model for preoperative prediction of tumor deposits (TDs) in patients with rectal cancer (RC).

Methods

In 500 patients, radiomic features were extracted from magnetic resonance imaging (MRI) using modalities such as high-resolution T2-weighted (HRT2) imaging and diffusion-weighted imaging (DWI). Machine learning (ML)-based and deep learning (DL)-based radiomic models were developed and integrated with clinical characteristics for TD prediction. The performance of the models was assessed using the area under the curve (AUC) over five-fold cross-validation.

Results

A total of 564 radiomic features that quantified the intensity, shape, orientation, and texture of the tumor were extracted for each patient. The HRT2-ML, DWI-ML, Merged-ML, HRT2-DL, DWI-DL, and Merged-DL models demonstrated AUCs of 0.62 ± 0.02, 0.64 ± 0.08, 0.69 ± 0.04, 0.57 ± 0.06, 0.68 ± 0.03, and 0.59 ± 0.04, respectively. The clinical-ML, clinical-HRT2-ML, clinical-DWI-ML, clinical-Merged-ML, clinical-DL, clinical-HRT2-DL, clinical-DWI-DL, and clinical-Merged-DL models demonstrated AUCs of 0.81 ± 0.06, 0.79 ± 0.02, 0.81 ± 0.02, 0.83 ± 0.01, 0.81 ± 0.04, 0.83 ± 0.04, 0.90 ± 0.04, and 0.83 ± 0.05, respectively. The clinical-DWI-DL model achieved the best predictive performance (accuracy 0.84 ± 0.05, sensitivity 0.94 ± 0. 13, specificity 0.79 ± 0.04).

Conclusions

A comprehensive model combining MRI radiomic features and clinical characteristics achieved promising performance in TD prediction for RC patients. This approach has the potential to assist clinicians in preoperative stage evaluation and personalized treatment of RC patients.

Endorectal ultrasound radiomics in locally advanced rectal cancer patients: despeckling and radiotherapy response prediction using machine learning

PURPOSE

The current study aimed to evaluate the association of endorectal ultrasound (EUS) radiomics features at different denoising filters based on machine learning algorithms and to predict radiotherapy response in locally advanced rectal cancer (LARC) patients.

METHODS

The EUS images of forty-three LARC patients, as a predictive biomarker for predicting the treatment response of neoadjuvant chemoradiotherapy (NCRT), were investigated. For despeckling, the EUS images were preprocessed by traditional filters (bilateral, wiener, lee, frost, median, and wavelet filters). The rectal tumors were delineated by two readers separately, and radiomics features were extracted. The least absolute shrinkage and selection operator were used for feature selection. Classifiers including logistic regression (LR), K-nearest neighbor (KNN), support vector machine (SVM), random forest, naive Bayes, and decision tree were trained using stratified fivefold cross-validation for model development. The area under the curve (AUC) of the receiver operating characteristic curve followed by accuracy, precision, sensitivity, and specificity were obtained for model performance assessment.

RESULTS

The wavelet filter had the best results with means of AUC: 0.83, accuracy: 77.41%, precision: 82.15%, and sensitivity: 79.41%. LR and SVM by having AUC: 0.71 and 0.76; accuracy: 70.0% and 71.5%; precision: 75.0% and 73.0%; sensitivity: 69.8% and 80.2%; and specificity: 70.0% and 60.9% had the highest model's performance, respectively.

CONCLUSION

This study demonstrated that the EUS-based radiomics model could serve as pretreatment biomarkers in predicting pathologic features of rectal cancer. The wavelet filter and machine learning methods (LR and SVM) had good results on the EUS images of rectal cancer.

Ultrasound-based artificial intelligence in gastroenterology and hepatology

Artificial intelligence (AI), especially deep learning, is gaining extensive attention for its excellent performance in medical image analysis. It can automatically make a quantitative assessment of complex medical images and help doctors to make more accurate diagnoses. In recent years, AI based on ultrasound has been shown to be very helpful in diffuse liver diseases and focal liver lesions, such as analyzing the severity of nonalcoholic fatty liver and the stage of liver fibrosis, identifying benign and malignant liver lesions, predicting the microvascular invasion of hepatocellular carcinoma, curative transarterial chemoembolization effect, and prognoses after thermal ablation. Moreover, AI based on endoscopic ultrasonography has been applied in some gastrointestinal diseases, such as distinguishing gastric mesenchymal tumors, detection of pancreatic cancer and intraductal papillary mucinous neoplasms, and predicting the preoperative tumor deposits in rectal cancer. This review focused on the basic technical knowledge about AI and the clinical application of AI in ultrasound of liver and gastroenterology diseases. Lastly, we discuss the challenges and future perspectives of AI.

Radiomics for differentiating tumor deposits from lymph node metastasis in rectal cancer

BACKGROUND

Tumor deposits (TDs) are not equivalent to lymph node (LN) metastasis (LNM) but have become independent adverse prognostic factors in patients with rectal cancer (RC). Although preoperatively differentiating TDs and LNMs is helpful in designing individualized treatment strategies and achieving improved prognoses, it is a challenging task.

AIM

To establish a computed tomography (CT)-based radiomics model for preoperatively differentiating TDs from LNM in patients with RC.

METHODS

This study retrospectively enrolled 219 patients with RC [TDs⁺LNM^- (n = 89); LNM⁺ TDs^- (n = 115); TDs⁺LNM⁺ (n = 15)] from a single center between September 2016 and September 2021. Single-positive patients (i.e., TDs⁺LNM^- and LNM⁺TDs^-) were classified into the training (n = 163) and validation (n = 41) sets. We extracted numerous features from the enhanced CT (region 1: The main tumor; region 2: The largest peritumoral nodule). After deleting redundant features, three feature selection methods and three machine learning methods were used to select the best-performing classifier as the radiomics model (Rad-score). After validating Rad-score, its performance was further evaluated in the field of diagnosing double-positive patients (i.e., TDs⁺LNM⁺) by outlining all peritumoral nodules with diameter (short-axis) > 3 mm.

RESULTS

Rad-score 1 (radiomics signature of the main tumor) had an area under the curve (AUC) of 0.768 on the training dataset and 0.700 on the validation dataset. Rad-score 2 (radiomics signature of the largest peritumoral nodule) had a higher AUC (training set: 0.940; validation set: 0.918) than Rad-score 1. Clinical factors, including age, gender, location of RC, tumor markers, and radiological features of the largest peritumoral nodule, were excluded by logistic regression. Thus, the combined model was comprised of Rad-scores of 1 and 2. Considering that the combined model had similar AUCs with Rad-score 2 (P = 0.134 in the training set and 0.594 in the validation set), Rad-score 2 was used as the final model. For the diagnosis of double-positive patients in the mixed group [TDs⁺LNM⁺ (n = 15); single-positive (n = 15)], Rad-score 2 demonstrated moderate performance (sensitivity, 73.3%; specificity, 66.6%; and accuracy, 70.0%).

CONCLUSION

Radiomics analysis based on the largest peritumoral nodule can be helpful in preoperatively differentiating between TDs and LNM.

Contrast-Enhanced Ultrasound-Based Nomogram: A Potential Predictor of Individually Postoperative Early Recurrence for Patients With Combined Hepatocellular-Cholangiocarcinoma

PURPOSES

To evaluate the postsurgical prognostic implication of contrast-enhanced ultrasound (CEUS) for combined hepatocellular-cholangiocarcinoma (CHC). To build a CEUS-based early recurrence prediction classifier for CHC, in comparison with tumor-node-metastasis (TNM) staging.

METHODS

The CEUS features and clinicopathological findings of each case were analyzed, and the Liver Imaging Reporting and Data System categories were assigned. The recurrence-free survival associated factors were evaluated by Cox proportional hazard model. Incorporating the independent factors, nomograms were built to estimate the possibilities of 3-month, 6-month, and 1-year recurrence and whose prognostic value was determined by time-dependent receiver operating characteristics, calibration curves, and hazard layering efficiency validation, comparing with TNM staging system.

RESULTS

In the multivariable analysis, the levels of carbohydrate antigen 19-9, prothrombin time and total bilirubin, and tumor shape, the Liver Imaging Reporting and Data System category were independent factors for recurrence-free survival. The LR-M category showed longer recurrence-free survival than did the LR-4/5 category. The 3-month, 6-month, and 1-year area under the curves of the CEUS-clinical nomogram, clinical nomogram, and TNM staging system were 0.518, 0.552, and 0.843 versus 0.354, 0.240, and 0.624 (P = .048, .049, and .471) vs. 0.562, 0.545, and 0.843 (P = .630, .564, and .007), respectively. The calibration curves of the CEUS-clinical model at different prediction time pionts were all close to the ideal line. The CEUS-clinical model effectively stratified patients into groups of high and low risk of recurrence in both training and validation set, while the TNM staging system only works on the training set.

CONCLUSIONS

Our CEUS-clinical nomogram is a reliable early recurrence prediction tool for hepatocellular-cholangiocarcinoma and helps postoperative risk stratification.

Artificial Neural Network-Based Ultrasound Radiomics Can Predict Large-Volume Lymph Node Metastasis in Clinical N0 Papillary Thyroid Carcinoma Patients

Objective

To evaluate the ability of artificial neural network- (ANN-) based ultrasound radiomics to predict large-volume lymph node metastasis (LNM) preoperatively in clinical N0 disease (cN0) papillary thyroid carcinoma (PTC) patients.

Methods

From January 2020 to April 2021, 306 cN0 PTC patients admitted to our hospital were retrospectively reviewed and divided into a training (n = 183) cohort and a validation cohort (n = 123) in a 6 : 4 ratio. Radiomic features quantitatively extracted from ultrasound images were pruned to train one ANN-based radiomic model and three conventional machine learning-based classifiers in the training cohort. Furthermore, an integrated model using ANN was constructed for better prediction. Meanwhile, the prediction of the two models was evaluated in the papillary thyroid microcarcinoma (PTMC) and conventional papillary thyroid cancer (CPTC) subgroups.

Results

The radiomic model showed better discrimination than other classifiers for large-volume LNM in the validation cohort, with an area under the receiver operating characteristic curve (AUROC) of 0.856 and an area under the precision-recall curve (AUPR) of 0.381. The performance of the integrated model was better, with an AUROC of 0.910 and an AUPR of 0.463. According to the calibration curve and decision curve analysis, the radiomic and integrated models had good calibration and clinical usefulness. Moreover, the models had good predictive performance in the PTMC and CPTC subgroups.

Conclusion

ANN-based ultrasound radiomics could be a potential tool to predict large-volume LNM preoperatively in cN0 PTC patients.

Preoperative Survival Prediction in Intrahepatic Cholangiocarcinoma Using an Ultrasound-Based Radiographic-Radiomics Signature

OBJECTIVES

To construct a preoperative model for survival prediction in intrahepatic cholangiocarcinoma (ICC) patients using ultrasound (US) based radiographic-radiomics signatures.

METHODS

Between April 2010 and September 2015, 170 patients with ICC who underwent curative resection were retrospectively recruited. Overall survival (OS)-related radiographic signatures and radiomics signatures based on preoperative US were built and assessed through a time-dependent receiver operating characteristic curve analysis. A nomogram was developed based on the selected predictors from the radiographic-radiomics signatures and clinical and laboratory results of the training cohort (n = 127), validated in an independent testing cohort (n = 43) by the concordance index (C-index), and compared with the Tumor Node Metastasis (TNM) cancer staging system as well as the radiographic and radiomics nomograms.

RESULTS

The median areas under the curve of the radiomics signature and radiographic signature were higher than that of the TNM staging system in the testing cohort, although the values were not significantly different (0.76-0.82 versus 0.62, P = .485 and .264). The preoperative nomogram with CA 19-9, sex, ascites, radiomics signature, and radiographic signature had C-indexes of 0.72 and 0.75 in the training and testing cohorts, respectively, and it had significantly higher predictive performance than the 8th TNM staging system in the testing cohort (C-index: 0.75 versus 0.67, P = .004) and a higher C-index than the radiomics nomograms (0.75 versus 0.68, P = .044).

CONCLUSIONS

The preoperative nomogram integrated with the radiographic-radiomics signature demonstrated good predictive performance for OS in ICC and was superior to the 8th TNM staging system.

The application of apparent diffusion coefficients derived from intratumoral and peritumoral zones for assessing pathologic prognostic factors in rectal cancer

OBJECTIVE

To investigate the diagnostic performance of the apparent diffusion coefficient (ADC) derived from intratumoral and peritumoral zones for assessing pathologic prognostic factors in rectal cancer.

MATERIALS AND METHODS

One hundred forty-six patients with rectal cancer who underwent preoperative MRI were prospectively enrolled. Two radiologists independently placed free-hand regions of interest (ROIs) in the largest tumor cross section and three small ROIs on the peritumoral zone adjacent to the tumor contour. Maximum values of tumor ADC (ADC_tmax), minimum values of tumor ADC (ADC_tmin), mean values of tumor ADC (ADC_tmean), mean values of peritumor ADC (ADC_pmean), and ADC_pmean/ADC_tmean (ADC ratio) were obtained on ADC maps and correlated with prognostic factors using uni- and multivariate logistic regression, and receiver operating characteristic curve (ROC) analysis.

RESULTS

Interobserver agreement was excellent for ADC_tmax and ADC_tmean (intraclass correlation coefficient [ICC], 0.915-0.958), and were good for ADC_tmin, ADC_pmean, and ADC ratio (ICC, 0.774-0.878). The ADC ratio was significantly higher in the poor differentiation, T3-4 stage, lymph node metastasis (LNM)-positive, extranodal extension (ENE)-positive, tumor deposit (TD)-positive, and lymphovascular invasion (LVI)-positive groups than that in the well-moderate differentiation, T1-2 stage, LNM-negative, ENE-negative, TD-negative, and LVI-negative groups (p = 0.008, < 0.001, < 0.001, 0.001, < 0.001, and < 0.001, respectively). The area under the ROC curve (AUC) of the ADC ratio was the highest for assessing poor differentiation (0.700), T3-4 stage (0.707), LNM-positive (0.776), TD-positive (0.848), and LVI-positive (0.778). Both the ADC ratio (AUC = 0.677) and ADC_pmean (AUC = 0.686) showed higher diagnostic performance for assessing ENE.

CONCLUSION

The ADC ratio could provide better predictive performance for assessing preoperative prognostic factors in resectable rectal cancer.

KEY POINTS

• Both the peritumor/tumor ADC ratio and ADC_pmean are correlated with important prognostic factors of resectable rectal cancer. • Both peritumor ADC and peritumor/tumor ADC ratio had higher diagnostic performance than tumor ADC for assessment of prognostic factors in resectable rectal cancer. • Peritumor/tumor ADC ratio showed the most capability for the assessment of prognostic factors in resectable rectal cancer.

Differentiation between combined hepatocellular carcinoma and hepatocellular carcinoma: comparison of diagnostic performance between ultrasomics-based model and CEUS LI-RADS v2017

Background

The imaging findings of combined hepatocellular cholangiocarcinoma (CHC) may be similar to those of hepatocellular carcinoma (HCC). CEUS LI-RADS may not perform well in distinguishing CHC from HCC. Studies have shown that radiomics has an excellent imaging analysis ability. This study aimed to establish and confirm an ultrasomics model for differentiating CHC from HCC.

Methods

Between 2004 and 2016, we retrospectively identified 53 eligible CHC patients and randomly included 106 eligible HCC patients with a ratio of HCC:CHC = 2:1, all of whom were categorized according to Contrast-Enhanced (CE) ultrasonography (US) Liver Imaging Reporting and Data System (LI-RADS) version 2017. The model based on ultrasomics features of CE US was developed in 74 HCC and 37 CHC and confirmed in 32 HCC and 16 CHC. The diagnostic performance of the LI-RADS or ultrasomics model was assessed by the area under the curve (AUC), accuracy, sensitivity and specificity.

Results

In the entire and validation cohorts, 67.0% and 81.3% of HCC cases were correctly assigned to LR-5 or LR-TIV contiguous with LR-5, and 73.6% and 87.5% of CHC cases were assigned to LR-M correctly. Up to 33.0% of HCC and 26.4% of CHC were misclassified by CE US LI-RADS. A total of 90.6% of HCC as well as 87.5% of CHC correctly diagnosed by the ultrasomics model in the validation cohort. The AUC, accuracy, sensitivity of the ultrasomics model were higher though without significant difference than those of CE US LI-RADS in the validation cohort.

Conclusion

The proposed ultrasomics model showed higher ability though the difference was not significantly different for differentiating CHC from HCC, which may be helpful in clinical diagnosis.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00765-x.

Clinical Value of Machine Learning-Based Ultrasomics in Preoperative Differentiation Between Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma: A Multicenter Study

Objective

This study aims to explore the clinical value of machine learning-based ultrasomics in the preoperative noninvasive differentiation between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC).

Methods

The clinical data and ultrasonic images of 226 patients from three hospitals were retrospectively collected and divided into training set (n = 149), test set (n = 38), and independent validation set (n = 39). Manual segmentation of tumor lesion was performed with ITK-SNAP, the ultrasomics features were extracted by the pyradiomics, and ultrasomics signatures were generated using variance filtering and lasso regression. The prediction models for preoperative differentiation between HCC and ICC were established by using support vector machine (SVM). The performance of the three models was evaluated by the area under curve (AUC), sensitivity, specificity, and accuracy.

Results

The ultrasomics signatures extracted from the grayscale ultrasound images could successfully differentiate between HCC and ICC (p < 0.05). The combined model had a better performance than either the clinical model or the ultrasomics model. In addition to stability, the combined model also had a stronger generalization ability (p < 0.05). The AUC (along with 95% CI), sensitivity, specificity, and accuracy of the combined model on the test set and the independent validation set were 0.936 (0.806-0.989), 0.900, 0.857, 0.868, and 0.874 (0.733-0.961), 0.889, 0.867, and 0.872, respectively.

Conclusion

The ultrasomics signatures could facilitate the preoperative noninvasive differentiation between HCC and ICC. The combined model integrating ultrasomics signatures and clinical features had a higher clinical value and a stronger generalization ability.

Computed Tomography-Based Radiomics for Preoperative Prediction of Tumor Deposits in Rectal Cancer

Objective

To develop and validate a computed tomography (CT)-based radiomics model for predicting tumor deposits (TDs) preoperatively in patients with rectal cancer (RC).

Methods

This retrospective study enrolled 254 patients with pathologically confirmed RC between December 2017 and December 2019. Patients were divided into a training set (n = 203) and a validation set (n = 51). A large number of radiomics features were extracted from the portal venous phase images of CT. After selecting features with L1-based method, we established Rad-score by using the logistic regression analysis. Furthermore, a combined model incorporating Rad-score and clinical factors was developed and visualized as the nomogram. The models were evaluated by the receiver operating characteristic curve (ROC) analysis and area under the ROC curve (AUC).

Results

One hundred and seventeen of 254 patients were eventually found to be TDs⁺. Rad-score and clinical factors including carbohydrate antigen (CA) 19-9, CT-reported T stage (cT), and CT-reported peritumoral nodules (+/-) were significantly different between the TDs⁺ and TDs^- groups (all P < 0.001). These factors were all included in the combined model by the logistic regression analysis (odds ratio = 2.378 for Rad-score, 2.253 for CA19-9, 2.281 for cT, and 4.485 for peritumoral nodules). This model showed good performance to predict TDs in the training and validation cohorts (AUC = 0.830 and 0.832, respectively). Furthermore, the combined model outperformed the clinical model incorporating CA19-9, cT, and peritumoral nodules (+/-) in both training and validation cohorts for predicting TDs preoperatively (AUC = 0.773 and 0.718, P = 0.008 and 0.039).

Conclusions

The combined model incorporating Rad-score and clinical factors could provide a preoperative prediction of TDs and help clinicians guide individualized treatment for RC patients.

Radiomics as a New Frontier of Imaging for Cancer Prognosis: A Narrative Review

The evaluation of the efficacy of different therapies is of paramount importance for the patients and the clinicians in oncology, and it is usually possible by performing imaging investigations that are interpreted, taking in consideration different response evaluation criteria. In the last decade, texture analysis (TA) has been developed in order to help the radiologist to quantify and identify parameters related to tumor heterogeneity, which cannot be appreciated by the naked eye, that can be correlated with different endpoints, including cancer prognosis. The aim of this work is to analyze the impact of texture in the prediction of response and in prognosis stratification in oncology, taking into consideration different pathologies (lung cancer, breast cancer, gastric cancer, hepatic cancer, rectal cancer). Key references were derived from a PubMed query. Hand searching and clinicaltrials.gov were also used. This paper contains a narrative report and a critical discussion of radiomics approaches related to cancer prognosis in different fields of diseases.

Application of the Preoperative Assistant System Based on Machine Learning in Hepatocellular Carcinoma Resection

To conduct better research in hepatocellular carcinoma resection, this paper used 3D machine learning and logistic regression algorithm to study the preoperative assistance of patients undergoing hepatectomy. In this study, the logistic regression model was analyzed to find the influencing factors for the survival and recurrence of patients. The clinical data of 50 HCC patients who underwent extensive hepatectomy (≥4 segments of the liver) admitted to our hospital from June 2020 to December 2020 were selected to calculate the liver volume, simulated surgical resection volume, residual liver volume, surgical margin, etc. The results showed that the simulated liver volume of 50 patients was 845.2 + 285.5 mL, and the actual liver volume of 50 patients was 826.3 ± 268.1 mL, and there was no significant difference between the two groups (t = 0.425; P > 0.05). Compared with the logistic regression model, the machine learning method has a better prediction effect, but the logistic regression model has better interpretability. The analysis of the relationship between the liver tumour and hepatic vessels in practical problems has specific clinical application value for accurately evaluating the volume of liver resection and surgical margin.

A New Dawn for the Use of Artificial Intelligence in Gastroenterology, Hepatology and Pancreatology

Artificial intelligence (AI) is rapidly becoming an essential tool in the medical field as well as in daily life. Recent developments in deep learning, a subfield of AI, have brought remarkable advances in image recognition, which facilitates improvement in the early detection of cancer by endoscopy, ultrasonography, and computed tomography. In addition, AI-assisted big data analysis represents a great step forward for precision medicine. This review provides an overview of AI technology, particularly for gastroenterology, hepatology, and pancreatology, to help clinicians utilize AI in the near future.

Abnormal white matter within brain structural networks is associated with high-impulse behaviour in codeine-containing cough syrup dependent users

Codeine-containing cough syrup (CCS) is considered as one of the most popular drug of dependence among adolescents because of its inexpensiveness and easy availability. However, its relationship with neurobiological effects remains sparsely explored. Herein, we examined how high-impulse behaviours relate to changes in the brain structural networks. Forty codeine-containing cough syrup dependent (CCSD) users and age-, gender-, and number of cigarettes smoked per day -matched forty healthy control (HC) subjects underwent structural brain imaging via MRI. High-impulse behaviour was assessed using the 30-item self-rated Barratt Impulsiveness Scale (BIS-11), and structural networks were constructed using diffusion tensor imaging and AAL-90 template. Between-group topological metrics were compared using nonparametric permutations. Benjamin-Hochberg false discovery rate correction was used to correct for multiple comparisons (P < 0.05). The relationships between abnormal network metrics and clinical characteristics of CCS dependent (BIS-11 total score, CCS- dependent duration and mean dose) were examined by Spearman's correlation. Structural networks of the CCSD group demonstrated lower small-world properties than those of the HC group. Abnormal changes in nodal properties among CCSD users were located mainly in the frontal gyrus, inferior parietal lobe and olfactory cortex. NBS analysis further indicated disrupted structural connections between the frontal gyrus and multiple brain regions. There were significant correlations between abnormal nodal properties of the frontal gyrus and clinical characteristics (BIS-11 total score, CCS dependent duration and mean dose) in the CCSD group. These findings suggest that the high-impulse behavioural expression in CCS addiction is associated with widespread brain regions, particularly within those in the frontal cortex. Aberrant brain regions and disrupted connectivity of structural network may be the bases of neuropathology for underlying symptoms of high-impulse behaviours in CCSD users, which may provide a novel sight to better treat and prevent codeine dependency in adolescents.

Magnetic resonance imaging (MRI) radiomics of papillary thyroid cancer (PTC): a comparison of predictive performance of multiple classifiers modeling to identify cervical lymph node metastases before surgery

PURPOSE

To compare predictive efficiency of multiple classifiers modeling and establish a combined magnetic resonance imaging (MRI) radiomics model for identifying lymph node (LN) metastases of papillary thyroid cancer (PTC) preoperatively.

MATERIALS AND METHODS

A retrospective analysis based on the preoperative MRI scans of 109 PTC patients including 77 patients with LN metastases and 32 patients without metastases was conducted, and we divided enroll cases into trained group and validation group. Radiomics signatures were selected from fat-suppressed T2-weighted MRI images, and the optimal characteristics were confirmed by spearman correlation test, hypothesis testing and random forest methods, and then, eight predictive models were constructed by eight classifiers. The receiver operating characteristic (ROC) curves analysis were performed to demonstrate the effectiveness of the models.

RESULTS

The area under the curve (AUC) of ROC based on MRI texture diagnosed LN status by naked eye was 0.739 (sensitivity = 0.571, specificity = 0.906). Based on the 5 optimal signatures, the best AUC of MRI radiomics model by logistics regression classifier had a considerable prediction performance with AUCs 0.805 in trained group and 0.760 in validation group, respectively, and a combination of best radiomics model with visual diagnosis of MRI texture had a high AUC as 0.969 (sensitivity = 0.938, specificity = 1.000), suggesting combined model had a preferable diagnostic efficiency in evaluating LN metastases of PTC.

CONCLUSION

Our combined radiomics model with visual diagnosis could be a potentially effective strategy to preoperatively predict LN metastases in PTC patients before clinical intervention.

Automated detection and delineation of hepatocellular carcinoma on multiphasic contrast-enhanced MRI using deep learning

PURPOSE

Liver Imaging Reporting and Data System (LI-RADS) uses multiphasic contrast-enhanced imaging for hepatocellular carcinoma (HCC) diagnosis. The goal of this feasibility study was to establish a proof-of-principle concept towards automating the application of LI-RADS, using a deep learning algorithm trained to segment the liver and delineate HCCs on MRI automatically.

METHODS

In this retrospective single-center study, multiphasic contrast-enhanced MRIs using T1-weighted breath-hold sequences acquired from 2010 to 2018 were used to train a deep convolutional neural network (DCNN) with a U-Net architecture. The U-Net was trained (using 70% of all data), validated (15%) and tested (15%) on 174 patients with 231 lesions. Manual 3D segmentations of the liver and HCC were ground truth. The dice similarity coefficient (DSC) was measured between manual and DCNN methods. Postprocessing using a random forest (RF) classifier employing radiomic features and thresholding (TR) of the mean neural activation was used to reduce the average false positive rate (AFPR).

RESULTS

73 and 75% of HCCs were detected on validation and test sets, respectively, using > 0.2 DSC criterion between individual lesions and their corresponding segmentations. Validation set AFPRs were 2.81, 0.77, 0.85 for U-Net, U-Net + RF, and U-Net + TR, respectively. Combining both RF and TR with the U-Net improved the AFPR to 0.62 and 0.75 for the validation and test sets, respectively. Mean DSC between automatically detected lesions using the DCNN + RF + TR and corresponding manual segmentations was 0.64/0.68 (validation/test), and 0.91/0.91 for liver segmentations.

CONCLUSION

Our DCNN approach can segment the liver and HCCs automatically. This could enable a more workflow efficient and clinically realistic implementation of LI-RADS.

Radiomic Feature-Based Predictive Model for Microvascular Invasion in Patients With Hepatocellular Carcinoma

Objective

This study aimed to build and evaluate a radiomics feature-based model for the preoperative prediction of microvascular invasion (MVI) in patients with hepatocellular carcinoma.

Methods

A total of 145 patients were retrospectively included in the study pool, and the patients were divided randomly into two independent cohorts with a ratio of 7:3 (training cohort: n = 101, validation cohort: n = 44). For a pilot study of this predictive model another 18 patients were recruited into this study. A total of 1,231 computed tomography (CT) image features of the liver parenchyma without tumors were extracted from portal-phase CT images. A least absolute shrinkage and selection operator (LASSO) logistic regression was applied to build a radiomics score (Rad-score) model. Afterwards, a nomogram, including Rad-score as well as other clinicopathological risk factors, was established with a multivariate logistic regression model. The discrimination efficacy, calibration efficacy, and clinical utility value of the nomogram were evaluated.

Results

The Rad-score scoring model could predict MVI with the area under the curve (AUC) of 0.637 (95% CI, 0.516–0.758) in the training cohort as well as of 0.583 (95% CI, 0.395–0.770) in the validation cohort; however, the aforementioned discriminative approach could not completely outperform those existing predictors (alpha fetoprotein, neutrophilic granulocyte, and preoperative hemoglobin). The individual predictive nomogram which included the Rad-score, alpha fetoprotein, neutrophilic granulocyte, and preoperative hemoglobin showed a better discrimination efficacy with AUC of 0.865 (95% CI, 0.786–0.944), which was higher than the conventional methods’ AUCs (nomogram vs Rad-score, alpha fetoprotein, neutrophilic granulocyte, and preoperative hemoglobin at P < 0.001, P = 0.025, P < 0.001, and P = 0.001, respectively). When applied to the validation cohort, the nomogram discrimination efficacy was still outbalanced those above mentioned three remaining methods (AUC: 0.705; 95% CI, 0.537–0.874). The calibration curves of this proposed method showed a satisfying consistency in both cohorts. A prospective pilot analysis showed that the nomogram could predict MVI with an AUC of 0.844 (95% CI, 0.628–1.000).

Conclusions

The radiomics feature-based predictive model improved the preoperative prediction of MVI in HCC patients significantly. It could be a potentially valuable clinical utility.