Radiomics model of magnetic resonance imaging for predicting pathological grading and lymph node metastases of extrahepatic cholangiocarcinoma

Preoperative prediction of high-grade osteosarcoma response to neoadjuvant therapy based on a plain CT radiomics model: A dual-center study

Objective

To develop a model combining clinical and radiomics features from CT scans for a preoperative noninvasive evaluation of Huvos grading of neoadjuvant chemotherapy in patients with HOS.

Methods

183 patients from center A and 42 from center B were categorized into training and validation sets. Features derived from radiomics were obtained from unenhanced CT scans.Following dimensionality reduction, the most optimal features were selected and utilized in creating a radiomics model through logistic regression analysis. Integrating clinical features, a composite clinical radiomics model was developed, and a nomogram was constructed. Predictive performance of the model was evaluated using ROC curves and calibration curves. Additionally, decision curve analysis was conducted to assess practical utility of nomogram in clinical settings.

Results

LASSO LR analysis was performed, and finally, three selected image omics features were obtained.Radiomics model yielded AUC values with a good diagnostic effect for both patient sets (AUCs: 0.69 and 0.68, respectively). Clinical models (including sex, age, pre-chemotherapy ALP and LDH levels, new lung metastases within 1 year after surgery, and incidence) performed well in terms of Huvos grade prediction, with an AUC of 0.74 for training set. The AUC for independent validation set stood at 0.70. Notably, the amalgamation of radiomics and clinical features exhibited commendable predictive prowess in training set, registering an AUC of 0.78. This robust performance was subsequently validated in the independent validation set, where the AUC remained high at 0.75. Calibration curves of nomogram showed that the predictions were in good agreement with actual observations.

Conclusion

Combined model can be used for Huvos grading in patients with HOS after preoperative chemotherapy, which is helpful for adjuvant treatment decisions.

Performance of radiomics in the differential diagnosis of parotid tumors: a systematic review

Purpose

A systematic review and meta-analysis were conducted to evaluate the diagnostic precision of radiomics in the differential diagnosis of parotid tumors, considering the increasing utilization of radiomics in tumor diagnosis. Although some researchers have attempted to apply radiomics in this context, there is ongoing debate regarding its accuracy.

Methods

Databases of PubMed, Cochrane, EMBASE, and Web of Science up to May 29, 2024 were systematically searched. The quality of included primary studies was assessed using the Radiomics Quality Score (RQS) checklist. The meta-analysis was performed utilizing a bivariate mixed-effects model.

Results

A total of 39 primary studies were incorporated. The machine learning model relying on MRI radiomics for diagnosis malignant tumors of the parotid gland, demonstrated a sensitivity of 0.80 [95% CI: 0.74, 0.86], SROC of 0.89 [95% CI: 0.27-0.99] in the validation set. The machine learning model based on MRI radiomics for diagnosis malignant tumors of the parotid gland, exhibited a sensitivity of 0.83[95% CI: 0.76, 0.88], SROC of 0.89 [95% CI: 0.17-1.00] in the validation set. The models also demonstrated high predictive accuracy for benign lesions.

Conclusion

There is great potential for radiomics-based models to improve the accuracy of diagnosing benign and malignant tumors of the parotid gland. To further enhance this potential, future studies should consider implementing standardized radiomics-based features, adopting more robust feature selection methods, and utilizing advanced model development tools. These measures can significantly improve the diagnostic accuracy of artificial intelligence algorithms in distinguishing between benign and malignant tumors of the parotid gland.

Systematic review registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42023434931.

Utilization of Radiomics Features Extracted From Preoperative Medical Images to Detect Metastatic Lymph Nodes in Cholangiocarcinoma and Gallbladder Cancer Patients: A Systemic Review and Meta-analysis

OBJECTIVES

This study aimed to determine the methodological quality and evaluate the diagnostic performance of radiomics features in detecting lymph node metastasis on preoperative images in patients with cholangiocarcinoma and gallbladder cancer.

METHODS

Publications between January 2005 and October 2022 were considered for inclusion. Databases such as Pubmed/Medline, Scopus, Embase, and Google Scholar were searched for relevant studies. The quality of the methodology of the manuscripts was determined using the Radiomics Quality Score and Quality Assessment of Diagnostic Accuracy Studies 2. Pooled results with corresponding 95% confidence intervals (CIs) were calculated using the DerSimonian-Liard method (random-effect model). Forest plots were used to visually represent the diagnostic profile of radiomics signature in each of the data sets pertaining to each study. Fagan plot was used to determine clinical applicability.

RESULTS

Overall sensitivity was 0.748 (95% CI, 0.703-0.789). Overall specificity was 0.795 (95% CI, 0.742-0.839). The combined negative likelihood ratio was 0.299 (95% CI, 0.266-0.350), and the positive likelihood ratio was 3.545 (95% CI, 2.850-4.409). The combined odds ratio of the studies was 12.184 (95% CI, 8.477-17.514). The overall summary receiver operating characteristics area under the curve was 0.83 (95% CI, 0.80-0.86). Three studies applied nomograms to 8 data sets and achieved a higher pooled sensitivity and specificity (0.85 [0.80-0.89] and 0.85 [0.71-0.93], respectively).

CONCLUSIONS

The pooled analysis showed that predictive models fed with radiomics features achieve good sensitivity and specificity in detecting lymph node metastasis in computed tomography and magnetic resonance imaging images. Supplementation of the models with biological correlates increased sensitivity and specificity in all data sets.

Immunotherapy and targeted therapy for cholangiocarcinoma: Artificial intelligence research in imaging

Cholangiocarcinoma (CCA) is a highly aggressive hepatobiliary malignancy, second only to hepatocellular carcinoma in prevalence. Despite surgical treatment being the recommended method to achieve a cure, it is not viable for patients with advanced CCA. Gene sequencing and artificial intelligence (AI) have recently opened up new possibilities in CCA diagnosis, treatment, and prognosis assessment. Basic research has furthered our understanding of the tumor-immunity microenvironment and revealed targeted molecular mechanisms, resulting in immunotherapy and targeted therapy being increasingly employed in the clinic. Yet, the application of these remedies in CCA is a challenging endeavor due to the varying pathological mechanisms of different CCA types and the lack of expressed immune proteins and molecular targets in some patients. AI in medical imaging has emerged as a powerful tool in this situation, as machine learning and deep learning are able to extract intricate data from CCA lesion images while assisting clinical decision making, and ultimately improving patient prognosis. This review summarized and discussed the current immunotherapy and targeted therapy related to CCA, and the research progress of AI in this field.

Radiomics and liver: Where we are and where we are headed?

Hepatic diffuse conditions and focal liver lesions represent two of the most common scenarios to face in everyday radiological clinical practice. Thanks to the advances in technology, radiology has gained a central role in the management of patients with liver disease, especially due to its high sensitivity and specificity. Since the introduction of computed tomography (CT) and magnetic resonance imaging (MRI), radiology has been considered the non-invasive reference modality to assess and characterize liver pathologies. In recent years, clinical practice has moved forward to a quantitative approach to better evaluate and manage each patient with a more fitted approach. In this setting, radiomics has gained an important role in helping radiologists and clinicians characterize hepatic pathological entities, in managing patients, and in determining prognosis. Radiomics can extract a large amount of data from radiological images, which can be associated with different liver scenarios. Thanks to its wide applications in ultrasonography (US), CT, and MRI, different studies were focused on specific aspects related to liver diseases. Even if broadly applied, radiomics has some advantages and different pitfalls. This review aims to summarize the most important and robust studies published in the field of liver radiomics, underlying their main limitations and issues, and what they can add to the current and future clinical practice and literature.

Radiomics using CT images for preoperative prediction of lymph node metastasis in perihilar cholangiocarcinoma: a multi-centric study

OBJECTIVES

To develop a CT-based radiomics model for preoperative prediction of lymph node (LN) metastasis in perihilar cholangiocarcinoma (pCCA).

METHODS

The study enrolled consecutive pCCA patients from three independent Chinese medical centers. The Boruta algorithm was applied to build the radiomics signature for the primary tumor and LN. The k-means algorithm was employed to cluster the selected LNs based on the radiomics signature LN. Support vector machines were used to construct the prediction models. The diagnostic efficiency was measured by the area under the receiver operating characteristic curve (AUC). The optimal model was evaluated in terms of calibration, clinical usefulness, and prognostic value.

RESULTS

A total of 214 patients were included in the study (mean age: 61.6 years ± 9.4; 130 male). The selected LNs were classified into two clusters, which were significantly correlated with LN metastasis in all cohorts (p < 0.001). The model incorporated the clinical risk factors, radiomics signature primary tumor, and the LN cluster obtained the best discrimination, with AUC values of 0.981 (95% CI: 0.962-1), 0.896 (95% CI: 0.810-0.982), and 0.865 (95% CI: 0.768-0.961) in the training, internal validation, and external validation cohorts, respectively. High-risk patients predicted by the optimal model had shorter overall survival than low-risk patients (median, 13.7 vs. 27.3 months, p < 0.001).

CONCLUSIONS

The study proposed a radiomics model with good performance to predict LN metastasis in pCCA. As a noninvasive preoperative prediction tool, this model may help in patient risk stratification and personalized treatment.

CLINICAL RELEVANCE STATEMENT

A CT-based radiomics model accurately predicts lymph node metastasis in perihilar cholangiocarcinoma patients. This noninvasive preoperative tool can aid in patient risk stratification and personalized treatment, potentially improving patient outcomes.

KEY POINTS

• The radiomics model based on contrast-enhanced CT is a useful tool for preoperative prediction of lymph node metastasis in perihilar cholangiocarcinoma. • Radiomics features extracted from lymph nodes show great potential for predicting lymph node metastasis. • The study is the first to identify a lymph node phenotype with a high probability of metastasis based on radiomics.

The value of an MRI-based radiomics model in predicting the survival and prognosis of patients with extrahepatic cholangiocarcinoma

OBJECTIVES

The study aimed to establish radiomics models based on magnetic resonance imaging (MRI) multiparameter images to predict the survival and prognosis of patients with extrahepatic cholangiocarcinoma (ECC).

METHODS

Seventy-eight patients with ECC confirmed by pathology were collected retrospectively. The radiomics model_a/b/c were constructed based on the 1/2/3-year survival of patients with ECC. The best texture features were selected according to postoperative survival time and ECC patient status to calculate the radiomics score (Rad-score). A cutoff value was selected, and patients were divided into high-risk and low-risk groups.

RESULTS

Model_a, model_b, and model_c were used to predict 1-, 2-, and 3-year postoperative survival rates, respectively. The area under the curve values in the training and test groups were 1.000 and 0.933 for model_a, 0.909 and 0.907 for model_b, 1.000 and 0.975 for model_c, respectively. The survival prediction model based on the Rad-score showed that the postoperative mortality risk differed significantly between risk groups (p < 0.0001).

CONCLUSIONS

The MRI radiomics model could be used to predict the survival and prognosis of patients with ECC.

Radiomics-based machine learning and deep learning to predict serosal involvement in gallbladder cancer

OBJECTIVE

Our study aimed to determine whether radiomics models based on contrast-enhanced computed tomography (CECT) have considerable ability to predict serosal involvement in gallbladder cancer (GBC) patients.

MATERIALS AND METHODS

A total of 152 patients diagnosed with GBC were retrospectively enrolled and divided into the serosal involvement group and no serosal involvement group according to paraffin pathology results. The regions of interest (ROIs) in the lesion on all CT images were drawn by two radiologists using ITK-SNAP software (version 3.8.0). A total of 412 features were extracted from the CT images of each patient. The Mann‒Whitney U test was applied to identify features with significant differences between groups. Seven machine learning algorithms and a deep learning model based on fully connected neural networks (f-CNNs) were used for radiomics model construction. The prediction efficacy of the models was evaluated using receiver operating characteristic (ROC) curve analysis.

RESULTS

Through the Mann‒Whitney U test, 75 of the 412 features extracted from the CT images of patients were significantly different between groups (P < 0.05). Among all the algorithms, logistic regression achieved the highest performance with an area under the curve (AUC) of 0.944 (sensitivity 0.889, specificity 0.8); the f-CNN deep learning model had an AUC of 0.916, and the model showed high predictive power for serosal involvement, with a sensitivity of 0.733 and a specificity of 0.801.

CONCLUSION

Radiomics models based on features derived from CECT showed convincing performances in predicting serosal involvement in GBC.

Safety and feasibility of laparoscopic radical resection for bismuth types III and IV hilar cholangiocarcinoma: a single-center experience from China

Background

Surgery represents the only cure for hilar cholangiocarcinoma (HC). However, laparoscopic radical resection remains technically challenging owing to the complex anatomy and reconstruction required during surgery. Therefore, reports on laparoscopic surgery (LS) for HC, especially for types III and IV, are limited. This study aimed to evaluate the safety and feasibility of laparoscopic radical surgery for Bismuth types III and IV HC.

Methods

The data of 16 patients who underwent LS and 9 who underwent open surgery (OS) for Bismuth types III and IV HC at Mianyang Central Hospital, School of Medicine, University of Electronic Science and Technology of China, between December 2017 and January 2022 were analyzed. Basic patient information, Bismuth-Corlette type, AJCC staging, postoperative complications, pathological findings, and follow-up results were evaluated.

Results

Sixteen patients underwent LS and 9 underwent OS for HC. According to the preoperative imaging data, there were four cases of Bismuth type IIIa, eight of type IIIb, and four of type IV in the LS group and two of type IIIa, four of type IIIb, and three of type IV in the OS group (P>0.05). There were no significant differences in age, sex, ASA score, comorbidity, preoperative percutaneous transhepatic biliary drainage rate, history of abdominal surgery, or preoperative laboratory tests between the two groups (P>0.05). Although the mean operative time and mean intraoperative blood loss were higher in the LS group than in OS group, the differences were not statistically significant (P=0.121 and P=0.115, respectively). Four patients (25%) in the LS group and two (22.2%) in the OS group experienced postoperative complications (P>0.05). No significant differences were observed in other surgical outcomes and pathologic findings between the two groups. Regarding the tumor recurrence rate, there was no difference between the groups (P>0.05) during the follow-up period (23.9 ± 13.3 months vs. 17.8 ± 12.3 months, P=0.240).

Conclusion

Laparoscopic radical resection of Bismuth types III and IV HC remains challenging, and extremely delicate surgical skills are required when performing extended hemihepatectomy followed by complex bilioenteric reconstructions. However, this procedure is generally safe and feasible for hepatobiliary surgeons with extensive laparoscopy experience.

MRI-based automatic identification and segmentation of extrahepatic cholangiocarcinoma using deep learning network

BACKGROUND

Accurate identification of extrahepatic cholangiocarcinoma (ECC) from an image is challenging because of the small size and complex background structure. Therefore, considering the limitation of manual delineation, it's necessary to develop automated identification and segmentation methods for ECC. The aim of this study was to develop a deep learning approach for automatic identification and segmentation of ECC using MRI.

METHODS

We recruited 137 ECC patients from our hospital as the main dataset (C1) and an additional 40 patients from other hospitals as the external validation set (C2). All patients underwent axial T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI). Manual delineations were performed and served as the ground truth. Next, we used 3D VB-Net to establish single-mode automatic identification and segmentation models based on T1WI (model 1), T2WI (model 2), and DWI (model 3) in the training cohort (80% of C1), and compared them with the combined model (model 4). Subsequently, the generalization capability of the best models was evaluated using the testing set (20% of C1) and the external validation set (C2). Finally, the performance of the developed models was further evaluated.

RESULTS

Model 3 showed the best identification performance in the training, testing, and external validation cohorts with success rates of 0.980, 0.786, and 0.725, respectively. Furthermore, model 3 yielded an average Dice similarity coefficient (DSC) of 0.922, 0.495, and 0.466 to segment ECC automatically in the training, testing, and external validation cohorts, respectively.

CONCLUSION

The DWI-based model performed better in automatically identifying and segmenting ECC compared to T1WI and T2WI, which may guide clinical decisions and help determine prognosis.

Lightweight neural network for smart diagnosis of cholangiocarcinoma using histopathological images

Traditional Cholangiocarcinoma detection methodology, which involves manual interpretation of histopathological images obtained after biopsy, necessitates extraordinary domain expertise and a significant level of subjectivity, resulting in several deaths due to improper or delayed detection of this cancer that develops in the bile duct lining. Automation in the diagnosis of this dreadful disease is desperately needed to allow for more effective and faster identification of the disease with a better degree of accuracy and reliability, ultimately saving countless human lives. The primary goal of this study is to develop a machine-assisted method of automation for the accurate and rapid identification of Cholangiocarcinoma utilizing histopathology images with little preprocessing. This work proposes CholangioNet, a novel lightweight neural network for detecting Cholangiocarcinoma utilizing histological RGB images. The histological RGB image dataset considered in this research work was found to have limited number of images, hence data augmentation was performed to increase the number of images. The finally obtained dataset was then subjected to minimal preprocessing procedures. These preprocessed images were then fed into the proposed lightweight CholangioNet. The performance of this proposed architecture is then compared with the performance of some of the prominent existing architectures like, VGG16, VGG19, ResNet50 and ResNet101. The Accuracy, Loss, Precision, and Sensitivity metrics are used to assess the efficiency of the proposed system. At 200 epochs, the proposed architecture achieves maximum training accuracy, precision, and recall of 99.90%, 100%, and 100%, respectively. The suggested architecture's validation accuracy, precision, and recall are 98.40%, 100%, and 100%, respectively. When compared to the performance of other AI-based models, the proposed system produced better results making it a potential AI tool for real world application.

An ultrasound-based radiomics model for survival prediction in patients with endometrial cancer

PURPOSE

To establish a nomogram integrating radiomics features based on ultrasound images and clinical parameters for predicting the prognosis of patients with endometrial cancer (EC).

MATERIALS AND METHODS

A total of 175 eligible patients with ECs were enrolled in our study between January 2011 and April 2018. They were divided into a training cohort (n = 122) and a validation cohort (n = 53). Least absolute shrinkage and selection operator (LASSO) regression were applied for selection of key features, and a radiomics score (rad-score) was calculated. Patients were stratified into high risk and low-risk groups according to the rad-score. Univariate and multivariable COX regression analysis was used to select independent clinical parameters for disease-free survival (DFS). A combined model based on radiomics features and clinical parameters was ultimately established, and the performance was quantified with respect to discrimination and calibration.

RESULTS

Nine features were selected from 1130 features using LASSO regression in the training cohort, which yielded an area under the curve (AUC) of 0.823 and 0.792 to predict DFS in the training and validation cohorts, respectively. Patients with a higher rad-score were significantly associated with worse DFS. The combined nomogram, which was composed of clinically significant variables and radiomics features, showed a calibration and favorable performance for DFS prediction (AUC 0.893 and 0.885 in the training and validation cohorts, respectively).

CONCLUSION

The combined nomogram could be used as a tool in predicting DFS and may assist individualized decision making and clinical treatment.

Machine learning radiomics to predict the early recurrence of intrahepatic cholangiocarcinoma after curative resection: A multicentre cohort study

PURPOSE

Postoperative early recurrence (ER) leads to a poor prognosis for intrahepatic cholangiocarcinoma (ICC). We aimed to develop machine learning (ML) radiomics models to predict ER in ICC after curative resection.

METHODS

Patients with ICC undergoing curative surgery from three institutions were retrospectively recruited and assigned to training and external validation cohorts. Preoperative arterial and venous phase contrast-enhanced computed tomography (CECT) images were acquired and segmented. Radiomics features were extracted and ranked through their importance. Univariate and multivariate logistic regression analysis was used to identify clinical characteristics. Various ML algorithms were used to construct radiomics-based models, and the predictive performance was evaluated by receiver operating characteristic curves, calibration curves, and decision curve analysis.

RESULTS

127 patients were included for analysis: 90 patients in the training set and 37 patients in the validation set. Ninety-two patients (72.4%) experienced recurrence, including 71 patients exhibiting ER. Male sex, microvascular invasion, TNM stage, and serum CA19-9 were identified as independent risk factors for ER, with the corresponding clinical model having a poor predictive performance (AUC of 0.685). Fifty-seven differential radiomics features were identified, and the 10 most important features were utilized for modelling. Seven ML radiomics models were developed with a mean AUC of 0.87 ± 0.02, higher than the clinical model. Furthermore, the clinical-radiomics models showed similar predictive performance to the radiomics models (AUC of 0.87 ± 0.03).

CONCLUSION

ML radiomics models based on CECT are valuable in predicting ER in ICC.

Immuno-genomic-radiomics to predict response of biliary tract cancer to camrelizumab plus GEMOX in a single-arm phase II trial

Background & Aims

Immunotherapy is an option for the treatment of advanced biliary tract cancer (BTC), although it has a low response rate. In this post hoc analysis, we investigated the predictive value of an immuno-genomic-radiomics (IGR) analysis for patients with BTC treated with camrelizumab plus gemcitabine and oxaliplatin (GEMOX) therapy.

Methods

Thirty-two patients with BTC treated with camrelizumab plus GEMOX were prospectively enrolled. The relationship between high-throughput computed tomography (CT) radiomics features with immuno-genomic expression was tested and scaled with a full correlation matrix analysis. Odds ratio (OR) of IGR expression for objective response to camrelizumab plus GEMOX was tested with logistic regression analysis. Association of IGR expression with progression-free survival (PFS) and overall survival (OS) was analysed with a Cox proportional hazard regression.

Results

CT radiomics correlated with CD8⁺ T cells (r = -0.72-0.71, p = 0.004-0.047), tumour mutation burden (TMB) (r = 0.59, p = 0.039), and ARID1A mutation (r = -0.58-0.57, p = 0.020-0.034). There was no significant correlation between radiomics and programmed cell death protein ligand 1 expression (p >0.96). Among all IGR biomarkers, only four radiomics features were independent predictors of objective response (OR = 0.09-3.81; p = 0.011-0.044). Combining independent radiomics features into an objective response prediction model achieved an area under the curve of 0.869. In a Cox analysis, radiomics signature [hazard ratio (HR) = 6.90, p <0.001], ARID1A (HR = 3.31, p = 0.013), and blood TMB (HR = 1.13, p = 0.023) were independent predictors of PFS. Radiomics signature (HR = 6.58, p <0.001) and CD8⁺ T cells (HR = 0.22, p = 0.004) were independent predictors of OS. Prognostic models integrating these features achieved concordance indexes of 0.677 and 0.681 for PFS and OS, respectively.

Conclusions

Radiomics could act as a non-invasive immuno-genomic surrogate of BTC, which could further aid in response prediction for patients with BTC treated with immunotherapy. However, multicenter and larger sample studies are required to validate these results.

Impact and implications

Immunotherapy is an alternative for the treatment of advanced BTC, whereas tumour response is heterogeneous. In a post hoc analysis of the single-arm phase II clinical trial (NCT03486678), we found that CT radiomics features were associated with the tumour microenvironment and that IGR expression was a promising marker for tumour response and long-term survival.

Clinical trial number

Post hoc analysis of NCT03486678.

EDLM: Ensemble Deep Learning Model to Detect Mutation for the Early Detection of Cholangiocarcinoma

The most common cause of mortality and disability globally right now is cholangiocarcinoma, one of the worst forms of cancer that may affect people. When cholangiocarcinoma develops, the DNA of the bile duct cells is altered. Cholangiocarcinoma claims the lives of about 7000 individuals annually. Women pass away less often than men. Asians have the greatest fatality rate. Following Whites (20%) and Asians (22%), African Americans (45%) saw the greatest increase in cholangiocarcinoma mortality between 2021 and 2022. For instance, 60-70% of cholangiocarcinoma patients have local infiltration or distant metastases, which makes them unable to receive a curative surgical procedure. Across the board, the median survival time is less than a year. Many researchers work hard to detect cholangiocarcinoma, but this is after the appearance of symptoms, which is late detection. If cholangiocarcinoma progression is detected at an earlier stage, then it will help doctors and patients in treatment. Therefore, an ensemble deep learning model (EDLM), which consists of three deep learning algorithms-long short-term model (LSTM), gated recurrent units (GRUs), and bi-directional LSTM (BLSTM)-is developed for the early identification of cholangiocarcinoma. Several tests are presented, such as a 10-fold cross-validation test (10-FCVT), an independent set test (IST), and a self-consistency test (SCT). Several statistical techniques are used to evaluate the proposed model, such as accuracy (Acc), sensitivity (Sn), specificity (Sp), and Matthew's correlation coefficient (MCC). There are 672 mutations in 45 distinct cholangiocarcinoma genes among the 516 human samples included in the proposed study. The IST has the highest Acc at 98%, outperforming all other validation approaches.

Prediction of angiogenesis in extrahepatic cholangiocarcinoma using MRI-based machine learning

Purpose

Reliable noninvasive method to preoperative prediction of extrahepatic cholangiocarcinoma (eCCA) angiogenesis are needed. This study aims to develop and validate machine learning models based on magnetic resonance imaging (MRI) for predicting vascular endothelial growth factor (VEGF) expression and the microvessel density (MVD) of eCCA.

Materials and methods

In this retrospective study from August 2011 to May 2020, eCCA patients with pathological confirmation were selected. Features were extracted from T1-weighted, T2-weighted, and diffusion-weighted images using the MaZda software. After reliability testing and feature screening, retained features were used to establish classification models for predicting VEGF expression and regression models for predicting MVD. The performance of both models was evaluated respectively using area under the curve (AUC) and Adjusted R-Squared (Adjusted R²).

Results

The machine learning models were developed in 100 patients. A total of 900 features were extracted and 77 features with intraclass correlation coefficient (ICC) < 0.75 were eliminated. Among all the combinations of data preprocessing methods and classification algorithms, Z-score standardization + logistic regression exhibited excellent ability both in the training cohort (average AUC = 0.912) and the testing cohort (average AUC = 0.884). For regression model, Z-score standardization + stochastic gradient descent-based linear regression performed well in the training cohort (average Adjusted R^2 = 0.975), and was also better than the mean model in the test cohort (average Adjusted R^2 = 0.781).

Conclusion

Two machine learning models based on MRI can accurately predict VEGF expression and the MVD of eCCA respectively.

Diagnosing malignant distal bile duct obstruction using artificial intelligence based on clinical biomarkers

Diagnosing distal bile duct obstruction remains challenging. This study aimed to examine the diagnostic ability of artificial intelligence (AI) based on clinical biomarkers in diagnosing malignant distal bile duct obstruction. A total of 206 patients with distal bile duct obstruction were included in this study. Clinical laboratory parameters were collected from the patients and evaluated using AI. All clinical parameters were input into the AI algorithm, and the AI value for malignant distal bile duct obstruction was calculated. The benign and malignant diagnostic capabilities of AI and other factors (alkaline phosphatase [ALP], intrahepatic bile duct [IHBD] diameters, and total bile duct [CBD] diameters) were compared. Benign and malignant bile duct obstruction were diagnosed in 142 and 64 patients, respectively. The median AI value of malignant distal bile duct obstruction was significantly greater than that of benign distal bile duct obstruction (0.991 vs. 0.002, p < 0.001). The area under the receiver operating characteristic curve of AI, ALP, IHBD diameter, and CBD diameter were 0.908, 0.795, 0.794, and 0.775, respectively. AI showed a sensitivity, specificity, and accuracy of 83.1%, 87.2%, and 85.9%. AI-based on clinical biomarkers could serve as an auxiliary for diagnosing malignant bile duct obstruction.

Systematic review with radiomics quality score of cholangiocarcinoma: an EuSoMII Radiomics Auditing Group Initiative

OBJECTIVES

To systematically review current research applications of radiomics in patients with cholangiocarcinoma and to assess the quality of CT and MRI radiomics studies.

METHODS

A systematic search was conducted on PubMed/Medline, Web of Science, and Scopus databases to identify original studies assessing radiomics of cholangiocarcinoma on CT and/or MRI. Three readers with different experience levels independently assessed quality of the studies using the radiomics quality score (RQS). Subgroup analyses were performed according to journal type, year of publication, quartile and impact factor (from the Journal Citation Report database), type of cholangiocarcinoma, imaging modality, and number of patients.

RESULTS

A total of 38 original studies including 6242 patients (median 134 patients) were selected. The median RQS was 9 (corresponding to 25.0% of the total RQS; IQR 1-13) for reader 1, 8 (22.2%, IQR 3-12) for reader 2, and 10 (27.8%; IQR 5-14) for reader 3. The inter-reader agreement was good with an ICC of 0.75 (95% CI 0.62-0.85) for the total RQS. All studies were retrospective and none of them had phantom assessment, imaging at multiple time points, nor performed cost-effectiveness analysis. The RQS was significantly higher in studies published in journals with impact factor > 4 (median 11 vs. 4, p = 0.048 for reader 1) and including more than 100 patients (median 11.5 vs. 0.5, p < 0.001 for reader 1).

CONCLUSIONS

Quality of radiomics studies on cholangiocarcinoma is insufficient based on the radiomics quality score. Future research should consider prospective studies with a standardized methodology, validation in multi-institutional external cohorts, and open science data.

Combination of ultrafast dynamic contrast-enhanced MRI-based radiomics and artificial neural network in assessing BI-RADS 4 breast lesions: Potential to avoid unnecessary biopsies

Objectives

To investigate whether combining radiomics extracted from ultrafast dynamic contrast-enhanced MRI (DCE-MRI) with an artificial neural network enables differentiation of MR BI-RADS 4 breast lesions and thereby avoids false-positive biopsies.

Methods

This retrospective study consecutively included patients with MR BI-RADS 4 lesions. The ultrafast imaging was performed using Differential sub-sampling with cartesian ordering (DISCO) technique and the tenth and fifteenth postcontrast DISCO images (DISCO-10 and DISCO-15) were selected for further analysis. An experienced radiologist used freely available software (FAE) to perform radiomics extraction. After principal component analysis (PCA), a multilayer perceptron artificial neural network (ANN) to distinguish between malignant and benign lesions was developed and tested using a random allocation approach. ROC analysis was performed to evaluate the diagnostic performance.

Results

173 patients (mean age 43.1 years, range 18-69 years) with 182 lesions (95 benign, 87 malignant) were included. Three types of independent principal components were obtained from the radiomics based on DISCO-10, DISCO-15, and their combination, respectively. In the testing dataset, ANN models showed excellent diagnostic performance with AUC values of 0.915-0.956. Applying the high-sensitivity cutoffs identified in the training dataset demonstrated the potential to reduce the number of unnecessary biopsies by 63.33%-83.33% at the price of one false-negative diagnosis within the testing dataset.

Conclusions

The ultrafast DCE-MRI radiomics-based machine learning model could classify MR BI-RADS category 4 lesions into benign or malignant, highlighting its potential for future application as a new tool for clinical diagnosis.

A meta-analysis of based radiomics for predicting lymph node metastasis in patients with biliary tract cancers

Background

To assess the predictive value of radiomics for preoperative lymph node metastasis (LMN) in patients with biliary tract cancers (BTCs).

Methods

PubMed, Embase, Web of Science, Cochrane Library databases, and four Chinese databases [VIP, CNKI, Wanfang, and China Biomedical Literature Database (CBM)] were searched to identify relevant studies published up to February 10, 2022. Two authors independently screened all publications for eligibility. We included studies that used histopathology as a gold standard and radiomics to evaluate the diagnostic efficacy of LNM in BTCs patients. The quality of the literature was evaluated using the Radiomics Quality Score (RQS) and the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). The diagnostic odds ratio (DOR), sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), and area under the receiver operating characteristic curve (AUC) were calculated to assess the predictive validity of radiomics for lymph node status in patients with BTCs. Spearman correlation coefficients were calculated, and Meta-regression and subgroup analyses were performed to assess the causes of heterogeneity.

Results

Seven studies were included, with 977 patients. The pooled sensitivity, specificity and AUC were 83% [95% confidence interval (CI): 77%, 88%], 78% (95% CI: 71, 84) and 0.88 (95% CI: 0.85, 0.90), respectively. The substantive heterogeneity was observed among the included studies (I ² = 80%, 95%CI: 58,100). There was no threshold effect seen. Meta-regression showed that tumor site contributed to the heterogeneity of specificity analysis (P < 0.05). Imaging methods, number of patients, combined clinical factors, tumor site, model, population, and published year all played a role in the heterogeneity of the sensitivity analysis (P < 0.05). Subgroup analysis revealed that magnetic resonance imaging (MRI) based radiomics had a higher pooled sensitivity than contrast-computed tomography (CT), whereas the result for pooled specificity was the opposite.

Conclusion

Our meta-analysis showed that radiomics provided a high level of prognostic value for preoperative LMN in BTCs patients.

Comparison of MRI and CT-based radiomics for preoperative prediction of lymph node metastasis in pancreatic ductal adenocarcinoma

Background

The preoperative prediction of lymph node metastasis (LNM) in pancreatic ductal adenocarcinoma (PDAC) is essential in prognosis and treatment strategy formulation.

Purpose

To compare the performance of computed tomography (CT) and magnetic resonance imaging (MRI) radiomics models for the preoperative prediction of LNM in PDAC.

Material and Methods

In total, 160 consecutive patients with PDAC were retrospectively included, who were divided into the training and validation sets (ratio of 8:2). Two radiologists evaluated LNM basing on morphological abnormalities. Radiomics features were extracted from T2-weighted imaging, T1-weighted imaging, and multiphase contrast enhanced MRI and multiphase CT, respectively. Overall, 1184 radiomics features were extracted from each volume of interest drawn. Only features with an intraclass correlation coefficient ≥0.75 were included. Three sequential feature selection steps—variance threshold, variance thresholding and least absolute shrinkage selection operator—were repeated 20 times with fivefold cross-validation in the training set. Two radiomics models based on multiphase CT and multiparametric MRI were built with the five most frequent features. Model performance was evaluated using the area under the curve (AUC) values.

Results

Multiparametric MRI radiomics model achieved improved AUCs (0.791 and 0.786 in the training and validation sets, respectively) than that of the CT radiomics model (0.672 and 0.655 in the training and validation sets, respectively) and of the radiologists’ assessment (0.600–0.613 and 0.560–0.587 in the training and validation sets, respectively).

Conclusion

Multiparametric MRI radiomics model may serve as a potential tool for preoperatively evaluating LNM in PDAC and had superior predictive performance to multiphase CT-based model and radiologists’ assessment.

A triple-classification for differentiating renal oncocytoma from renal cell carcinoma subtypes and CK7 expression evaluation: a radiomics analysis

Background

To investigate the value of computed tomography (CT)-based radiomics model analysis in differentiating renal oncocytoma (RO) from renal cell carcinoma subtypes (chromophobe renal cell carcinoma, clear cell carcinoma) and predicting the expression of Cytokeratin 7 (CK7).

Methods

In this retrospective study, radiomics was applied for patients with RO, chRCC and ccRCC who underwent surgery between January 2013 and December 2019 comprised the training cohort, and the testing cohort was collected between January and October 2020. The corticomedullary (CMP) and nephrographic phases (NP) were manually segmented, and radiomics texture parameters were extracted. Support vector machine was generated from CMP and NP after feature selection. Shapley additive explanations were applied to interpret the radiomics features. A radiomics signature was built using the selected features from the two phases, and the radiomics nomogram was constructed by incorporating the radiomics features and clinical factors. Receiver operating characteristic curve was calculated to evaluate the above models in the two sets. Furthermore, Rad-score was used for correlation analysis with CK7.

Results

A total of 123 patients with RO, chRCC and ccRCC were analyzed in the training cohort and 57 patients in the testing cohort. Subsequently, 396 radiomics features were selected from each phase. The radiomics features combining two phases yielded the highest area under the curve values of 0.941 and 0.935 in the training and testing sets, respectively. The Pearson’s correlation coefficient was statistically significant between Rad-score and CK7.

Conclusion

We proposed a non-invasive and individualized CT-based radiomics nomogram to differentiation among RO, chRCC and ccRCC preoperatively and predict the immunohistochemical protein expression for accurate clinical diagnosis and treatment decision.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12894-022-01099-0.

A triple-classification for the evaluation of lung nodules manifesting as pure ground-glass sign: a CT-based radiomic analysis

OBJECTIVES

To construct a noninvasive radiomics model for evaluating the pathological degree and an individualized treatment strategy for patients with the manifestation of ground glass nodules (GGNs) on CT images.

METHODS

The retrospective primary cohort investigation included patients with GGNs on CT images who underwent resection between June 2015 and June 2020. The intratumoral regions of interest were segmented semiautomatically, and radiomics features were extracted from the intratumoral and peritumoral regions. After feature selection by ANOVA, Max-Relevance and Min-Redundancy (mRMR) and Least Absolute Shrinkage and Selection Operator (Lasso) regression, a random forest (RF) model was generated. Receiver operating characteristic (ROC) analysis was calculated to evaluate each classification. Shapley additive explanations (SHAP) was applied to interpret the radiomics features.

RESULTS

In this study, 241 patients including atypical adenomatous hyperplasia (AAH) or adenocarcinoma in situ (AIS) (n = 72), minimally invasive adenocarcinoma (MIA) (n = 83) and invasive adenocarcinoma (IAC) (n = 86) were selected for radiomics analysis. Three intratumoral radiomics features and one peritumoral feature were finally identified by the triple RF classifier with an average area under the curve (AUC) of 0.960 (0.963 for AAH/AIS, 0.940 for MIA, 0.978 for IAC) in the training set and 0.944 (0.955 for AAH/AIS, 0.952 for MIA, 0.926 for IAC) in the testing set for evaluation of the GGNs.

CONCLUSION

The triple classification based on intra- and peritumoral radiomics features derived from the noncontrast CT images had satisfactory performance and may be used as a noninvasive tool for preoperative evaluation of the pure ground-glass nodules and developing of individualized treatment strategies.

Artificial intelligence using advanced imaging techniques and cholangiocarcinoma: Recent advances and future direction

While cholangiocarcinoma represents only about 3% of all gastrointestinal tumors, it has a dismal survival rate, usually because it is diagnosed at a late stage. The utilization of Artificial Intelligence (AI) in medicine in general, and in gastroenterology has made gigantic steps. However, the application of AI for biliary disease, in particular for cholangiocarcinoma, has been sub-optimal. The use of AI in combination with clinical data, cross-sectional imaging (computed tomography, magnetic resonance imaging) and endoscopy (endoscopic ultrasound and cholangioscopy) has the potential to significantly improve early diagnosis and the choice of optimal therapeutic options, leading to a transformation in the prognosis of this feared disease. In this review we summarize the current knowledge on the use of AI for the diagnosis and management of cholangiocarcinoma and point to future directions in the field.

CT-Based Radiomics Analysis for Noninvasive Prediction of Perineural Invasion of Perihilar Cholangiocarcinoma

Purpose

The study aimed to construct and evaluate a CT-Based radiomics model for noninvasive detecting perineural invasion (PNI) of perihilar cholangiocarcinoma (pCCA) preoperatively.

Materials and Methods

From February 2012 to October 2021, a total of 161 patients with pCCA who underwent resection were retrospectively enrolled in this study. Patients were allocated into the training cohort and the validation cohort according to the diagnostic time. Venous phase images of contrast-enhanced CT were used for radiomics analysis. The intraclass correlation efficient (ICC), the correlation analysis, and the least absolute shrinkage and selection operator (LASSO) regression were applied to select radiomics features and built radiomics signature. Logistic regression analyses were performed to establish a clinical model, a radiomics model, and a combined model. The performance of the predictive models was measured by area under the receiver operating characteristic curve (AUC), and pairwise ROC comparisons between models were tested using the Delong method. Finally, the model with the best performance was presented as a nomogram, and its calibration and clinical usefulness were assessed.

Results

Finally, 15 radiomics features were selected to build a radiomics signature, and three models were developed through logistic regression. In the training cohort, the combined model showed a higher predictive capability (AUC = 0.950) than the radiomics model and the clinical model (AUC: radiomics = 0.914, clinical = 0.756). However, in the validation cohort, the AUC of the radiomics model (AUC = 0.885) was significantly higher than the other two models (AUC: combined = 0.791, clinical = 0.567). After comprehensive consideration, the radiomics model was chosen to develop the nomogram. The calibration curve and decision curve analysis (DCA) suggested that the nomogram had a good consistency and clinical utility.

Conclusion

We developed a CT-based radiomics model with good performance to noninvasively predict PNI of pCCA preoperatively.

Application of 18F-FDG PET-CT Images Based Radiomics in Identifying Vertebral Multiple Myeloma and Bone Metastases

Purpose

The purpose of this study was to explore the application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) image radiomics in the identification of spine multiple myeloma (MM) and bone metastasis (BM), and whether this method could improve the classification diagnosis performance compared with traditional methods.

Methods

This retrospective study collected a total of 184 lesions from 131 patients between January 2017 and January 2021. All images were visually evaluated independently by two physicians with 20 years of experience through the double-blind method, while the maximum standardized uptake value (SUVmax) of each lesion was recorded. A total of 279 radiomics features were extracted from the region of interest (ROI) of CT and PET images of each lesion separately by manual method. After the reliability test, the least absolute shrinkage and selection operator (LASSO) regression and 10-fold cross-validation were used to perform dimensionality reduction and screening of features. Two classification models of CT and PET were derived from CT images and PET images, respectively and constructed using the multivariate logistic regression algorithm. In addition, the ComModel was constructed by combining the PET model and the conventional parameter SUVmax. The performance of the three classification diagnostic models, as well as the human experts and SUVmax, were evaluated and compared, respectively.

Results

A total of 8 and 10 features were selected from CT and PET images for the construction of radiomics models, respectively. Satisfactory performance of the three radiomics models was achieved in both the training and the validation groups (Training: AUC: CT: 0.909, PET: 0.949, ComModel: 0.973; Validation: AUC: CT: 0.897, PET: 0.929, ComModel: 0.948). Moreover, the PET model and ComModel showed significant improvement in diagnostic performance between the two groups compared to the human expert (Training: P = 0.01 and P = 0.001; Validation: P = 0.018 and P = 0.033), and no statistical difference was observed between the CT model and human experts (P = 0.187 and P = 0.229, respectively).

Conclusion

The radiomics model constructed based on 18F-FDG PET/CT images achieved satisfactory diagnostic performance for the classification of MM and bone metastases. In addition, the radiomics model showed significant improvement in diagnostic performance compared to human experts and PET conventional parameter SUVmax.

Radiomics of Biliary Tumors: A Systematic Review of Current Evidence

Biliary tumors are rare diseases with major clinical unmet needs. Standard imaging modalities provide neither a conclusive diagnosis nor robust biomarkers to drive treatment planning. In several neoplasms, texture analyses non-invasively unveiled tumor characteristics and aggressiveness. The present manuscript aims to summarize the available evidence about the role of radiomics in the management of biliary tumors. A systematic review was carried out through the most relevant databases. Original, English-language articles published before May 2021 were considered. Three main outcome measures were evaluated: prediction of pathology data; prediction of survival; and differential diagnosis. Twenty-seven studies, including a total of 3605 subjects, were identified. Mass-forming intrahepatic cholangiocarcinoma (ICC) was the subject of most studies (n = 21). Radiomics reliably predicted lymph node metastases (range, AUC = 0.729−0.900, accuracy = 0.69−0.83), tumor grading (AUC = 0.680−0.890, accuracy = 0.70−0.82), and survival (C-index = 0.673−0.889). Textural features allowed for the accurate differentiation of ICC from HCC, mixed HCC-ICC, and inflammatory masses (AUC > 0.800). For all endpoints (pathology/survival/diagnosis), the predictive/prognostic models combining radiomic and clinical data outperformed the standard clinical models. Some limitations must be acknowledged: all studies are retrospective; the analyzed imaging modalities and phases are heterogeneous; the adoption of signatures/scores limits the interpretability and applicability of results. In conclusion, radiomics may play a relevant role in the management of biliary tumors, from diagnosis to treatment planning. It provides new non-invasive biomarkers, which are complementary to the standard clinical biomarkers; however, further studies are needed for their implementation in clinical practice.

Artificial intelligence and cholangiocarcinoma: Updates and prospects

Artificial intelligence (AI) is the timeliest field of computer science and attempts to mimic cognitive function of humans to solve problems. In the era of “Big data”, there is an ever-increasing need for AI in all aspects of medicine. Cholangiocarcinoma (CCA) is the second most common primary malignancy of liver that has shown an increase in incidence in the last years. CCA has high mortality as it is diagnosed in later stages that decreases effect of surgery, chemotherapy, and other modalities. With technological advancement there is an immense amount of clinicopathologic, genetic, serologic, histologic, and radiologic data that can be assimilated together by modern AI tools for diagnosis, treatment, and prognosis of CCA. The literature shows that in almost all cases AI models have the capacity to increase accuracy in diagnosis, treatment, and prognosis of CCA. Most studies however are retrospective, and one study failed to show AI benefit in practice. There is immense potential for AI in diagnosis, treatment, and prognosis of CCA however limitations such as relative lack of studies in use by human operators in improvement of survival remains to be seen.

Single-Photon Emission Computed Tomography/Computed Tomography Image-Based Radiomics for Discriminating Vertebral Bone Metastases From Benign Bone Lesions in Patients With Tumors

Purpose: The purpose of this study was to investigate the feasibility of Single-Photon Emission Computed Tomography/Computed Tomography (SPECT/CT) image-based radiomics in differentiating bone metastases from benign bone lesions in patients with tumors. Methods: A total of 192 lesions from 132 patients (134 in the training group, 58 in the validation group) diagnosed with vertebral bone metastases or benign bone lesions were enrolled. All images were evaluated and diagnosed independently by two physicians with more than 20 years of diagnostic experience for qualitative classification, the images were imported into MaZda software in Bitmap (BMP) format for feature extraction. All radiomics features were selected by least absolute shrinkage and selection operator (LASSO) regression and 10-fold cross-validation algorithms after the process of normalization and correlation analysis. Based on these selected features, two models were established: The CT model and SPECT model (radiomics features were derived from CT and SPECT images, respectively). In addition, a combination model (ComModel) combined CT and SPECT features was developed in order to better evaluate the predictive performance of radiomics models. Subsequently, the diagnostic performance between each model was separately evaluated by a confusion matrix. Results: There were 12, 13, and 18 features contained within the CT, SPECT, and ComModel, respectively. The constructed radiomics models based on SPECT/CT images to discriminate between bone metastases and benign bone lesions not only had high diagnostic efficacy in the training group (AUC of 0.894, 0.914, 0.951 for CT model, SPECT model, and ComModel, respectively), but also performed well in the validation group (AUC; 0.844, 0.871, 0.926). The AUC value of the human experts was 0.849 and 0.839 in the training and validation groups, respectively. Furthermore, both SPECT model and ComModel show higher classification performance than human experts in the training group (P = 0.021 and P = 0.001, respectively) and the validation group (P = 0.037 and P = 0.007, respectively). All models showed better diagnostic accuracy than human experts in the training group and the validation group. Conclusion: Radiomics derived from SPECT/CT images could effectively discriminate between bone metastases and benign bone lesions. This technique may be a new non-invasive way to help prevent unnecessary delays in diagnosis and a potential contribution in disease staging and treatment planning.

A CT-based radiomics nomogram for predicting early recurrence in patients with high-grade serous ovarian cancer

PURPOSE

To develop and validate a radiomics nomogram for predicting early recurrence in high-grade serous ovarian cancer (HGSOC) patients.

MATERIALS AND METHODS

From May 2008 to December 2019, 256 eligible HGSOC patients were enrolled and divided into training (n = 179) and test cohorts (n = 77) in a 7:3 ratio. A radiomics signature (Radscore) was selected by using recursive feature elimination based on a support vector machine (SVM-RFE) and building a radiomics model for recurrence prediction. Independent clinical risk factors were generated by univariable and multivariable Cox regression analyses. A combined model was developed based on the Radscore and independent clinical risk factors and presented as a radiomics nomogram. Its performance was assessed by AUC, Kaplan-Meier survival analysis and decision curve analysis.

RESULTS

Seven radiomics features were selected. The radiomics model yielded AUCs of 0.715 (95% CI: 0.640, 0.790) and 0.717 (95% CI: 0.600, 0.834) in the training and test cohorts, respectively. The clinical model (FIGO stage and residual disease) yielded AUCs of 0.632 and 0.691 in the training and test cohorts, respectively. The combined model demonstrated AUCs of 0.749 (95% CI: 0.678, 0.821) and 0.769 (95% CI: 0.662, 0.877) in the training and test cohorts, respectively. In the combined model, PFS was significantly shorter in the high-risk group than in the low-risk group (P < 0.0001).

CONCLUSIONS

The radiomics nomogram performed well for early individualized recurrence prediction in patients with HGSOC and can also be used to differentiate high-risk patients from low-risk patients.

Deep Learning Radiomics to Predict Regional Lymph Node Staging for Hilar Cholangiocarcinoma

Background

Our aim was to establish a deep learning radiomics method to preoperatively evaluate regional lymph node (LN) staging for hilar cholangiocarcinoma (HC) patients.

Methods and Materials

Of the 179 enrolled HC patients, 90 were pathologically diagnosed with lymph node metastasis. Quantitative radiomic features and deep learning features were extracted. An LN metastasis status classifier was developed through integrating support vector machine, high-performance deep learning radiomics signature, and three clinical characteristics. An LN metastasis stratification classifier (N1 vs. N2) was also proposed with subgroup analysis.

Results

The average areas under the receiver operating characteristic curve (AUCs) of the LN metastasis status classifier reached 0.866 in the training cohort and 0.870 in the external test cohorts. Meanwhile, the LN metastasis stratification classifier performed well in predicting the risk of LN metastasis, with an average AUC of 0.946.

Conclusions

Two classifiers derived from computed tomography images performed well in predicting LN staging in HC and will be reliable evaluation tools to improve decision-making.

Histogram analysis of diffusion-weighted imaging and dynamic contrast-enhanced MRI for predicting occult lymph node metastasis in early-stage oral tongue squamous cell carcinoma

OBJECTIVES

To investigate the feasibility of whole-tumor histogram analysis of diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI for predicting occult lymph node metastasis (LNM) in early-stage oral tongue squamous cell cancer (OTSCC).

MATERIALS AND METHODS

This retrospective study included 55 early-stage OTSCC (cT1-2N0M0) patients; 34 with pathological LNM and 21 without. Eight whole-tumor histogram features were extracted from quantitative apparent diffusion coefficient (ADC) maps and two semi-quantitative DCE parametric maps (wash-in and wash-out). The clinicopathological factors and histogram features were compared between the two groups. Stepwise logistic regression was used to identify independent predictors. Receiver operating characteristic curves were generated to assess the performances of significant variables and a combined model for predicting occult LNM.

RESULTS

MRI-determined depth of invasion and ADC_entropy was significantly higher in the LNM group, with respective areas under the curve (AUCs) of 0.67 and 0.69, and accuracies of 0.73 and 0.73. ADC_10th. ADC_uniformity and wash-in_skewness were significantly lower in the LNM group, with respective AUCs of 0.68, 0.71, and 0.69, and accuracies of 0.65, 0.71, and 0.64. Histogram features from wash-out maps were not significantly associated with cervical node status. In the logistic regression analysis, ADC_10th, ADC_uniformity, and wash-in_skewness were independent predictors. The combined model yielded the best predictive performance, with an AUC of 0.87 and an accuracy of 0.82.

CONCLUSIONS

Whole-tumor histogram analysis of ADC and wash-in maps is a feasible tool for preoperative evaluation of cervical node status in early-stage OTSCC.

KEY POINTS

• Histogram analysis of parametric maps from DWI and DCE-MRI may assist the prediction of occult LNM in early-stage OTSCC. • ADC_10th, ADC_uniformity, and wash-in_skewness were independent predictors. • The combined model exhibited good predictive performance, with an accuracy of 0.82.

Prediction of Metastasis in the Axillary Lymph Nodes of Patients With Breast Cancer: A Radiomics Method Based on Contrast-Enhanced Computed Tomography

Background

The use of traditional techniques to evaluate breast cancer is restricted by the subjective nature of assessment, variation across radiologists, and limited data. Radiomics may predict axillary lymph node metastasis (ALNM) of breast cancer more accurately.

Purpose

The aim was to evaluate the diagnostic performance of a radiomics model based on ALNs themselves that used contrast-enhanced computed tomography (CECT) to detect ALNM of breast cancer.

Methods

We retrospectively enrolled 402 patients with breast cancer confirmed by pathology from January 2016 to October 2019. Three hundred and ninety-six features were extracted for all patients from axial CECT images of 825 ALNs using Artificial Intelligent Kit software (GE Medical Systems, Version V3.1.0.R). Next, the radiomics model was trained, validated, and tested for predicting ALNM in breast cancer by using a support vector machine algorithm. Finally, the performance of the radiomics model was evaluated in terms of its classification accuracy and the value of the area under the curve (AUC).

Results

The radiomics model yielded the best classification accuracy of 89.1% and the highest AUC of 0.92 (95% CI: 0.91-0.93, p=0.002) for discriminating ALNM in breast cancer in the validation cohorts. In the testing cohorts, the model also demonstrated better performance, with an accuracy of 88.5% and an AUC of 0.94 (95% CI: 0.93-0.95, p=0.005) for predicting ALNM in breast cancer.

Conclusion

The radiomics model based on CECT images can be used to predict ALNM in breast cancer and has significant potential in clinical noninvasive diagnosis and in the prediction of breast cancer metastasis.

The Development and Validation of a CT-Based Radiomics Nomogram to Preoperatively Predict Lymph Node Metastasis in High-Grade Serous Ovarian Cancer

Purpose

To develop and validate a radiomics model for predicting preoperative lymph node (LN) metastasis in high-grade serous ovarian cancer (HGSOC).

Materials and Methods

From May 2008 to January 2018, a total of 256 eligible HGSOC patients who underwent tumor resection and LN dissection were divided into a training cohort (n=179) and a test cohort (n=77) in a 7:3 ratio. A Radiomics Model was developed based on a training cohort of 179 patients. A radiomics signature (defined as the Radscore) was selected by using the random forest method. Logistics regression was used as the classifier for modeling. An Integrated Model that incorporated the Radscore and CT_reported LN status (CT_LN_report) was developed and presented as a radiomics nomogram. Its performance was determined by the area under the curve (AUC), calibration, and decision curve. The radiomics nomogram was internally tested in an independent test cohort (n=77) and a CT-LN-report negative subgroup (n=179) using the formula derived from the training cohort.

Results

The AUC value of the CT_LN_report was 0.688 (95% CI: 0.626, 0.759) in the training cohort and 0.717 (95% CI: 0.630, 0.804) in the test cohort. The Radiomics Model yielded an AUC of 0.767 (95% CI: 0.696, 0.837) in the training cohort and 0.753 (95% CI: 0.640, 0.866) in the test. The radiomics nomogram demonstrated favorable calibration and discrimination in the training cohort (AUC=0.821), test cohort (AUC=0.843), and CT-LN-report negative subgroup (AUC=0.82), outperforming the Radiomics Model and CT_LN_report alone.

Conclusions

The radiomics nomogram derived from portal phase CT images performed well in predicting LN metastasis in HGSOC and could be recommended as a new, convenient, and non-invasive method to aid in clinical decision-making.

Feasibility of magnetic resonance imaging-based radiomics features for preoperative prediction of extrahepatic cholangiocarcinoma stage

AIM

The aim of this study is to develop and test radiomics models based on magnetic resonance imaging (MRI) to preoperatively and respectively predict the T stage, perineural invasion, and microvascular invasion of extrahepatic cholangiocarcinoma (eCCA) through a non-invasive approach.

METHODS

This research included 101 eCCA patients (29-83 years; 45 females and 56 males) between August 2011 and December 2019. Radiomics features were retrospectively extracted from T1-weighted imaging, T2-weighted imaging, diffusion-weighted imaging, and apparent diffusion coefficient map using MaZda software. The region of interest was manually delineated in the largest section on four MRI images as ground truth while keeping 1-2 mm margin to tumor border, respectively. Pretreatment, dimension reduction method, and classifiers were used to establish radiomics signatures for assessing three pathological characteristics of eCCA. Finally, independent training and testing datasets were used to assess radiomics signature performance based on receiver operating characteristic curve analysis, accuracy, precision, sensitivity, and specificity.

RESULTS

This study extracted 1208 radiomics features from four MRI images of each patient. The best performing radiomics signatures for assessing the T stage, perineural invasion, and microvascular invasion were respectively produced by L1_normalization + linear discriminant analysis (LDA) + logistic regression, Box_Cox transformer + LDA + K-nearest neighbor, and L2_normalization + LDA + AdaBoost. The area under the curve values of the radiomics signatures for predicting the training and testing cohorts in each subgroup were respectively 1 and 0.962 (T stage), 1 and 1 (both perineural invasion and microvascular invasion).

CONCLUSION

These proposed radiomic models based on MR images had powerful performance and high potential in predicting T stage, perineural, and microvascular invasion of eCCA.

REPORTING GUIDELINES/RESEARCH DESIGN

Prognostic study.

Radiomics Score Combined with ACR TI-RADS in Discriminating Benign and Malignant Thyroid Nodules Based on Ultrasound Images: A Retrospective Study

This study aimed to explore the ability of combination model of ultrasound radiomics score (Rad-score) and the thyroid imaging, reporting and data system by the American College of Radiology (ACR TI-RADS) in predicting benign and malignant thyroid nodules (TNs). Up to 286 radiomics features were extracted from ultrasound images of TNs. By using the lowest probability of classification error and average correlation coefficients (POE + ACC) and the least absolute shrinkage and selection operator (LASSO), we finally selected four features to establish Rad-score (Vertl-RLNonUni, Vertl-GLevNonU, WavEnLH-s4 and WavEnHL-s5). DeLong’s test and decision curve analysis (DCA) showed that the method of combining Rad-score and ACR TI-RADS had the best performance (the area under the receiver operating characteristic curve (AUC = 0.913 (95% confidence interval (CI), 0.881–0.939) and 0.899 (95%CI, 0.840–0.942) in the training group and verification group, respectively), followed by ACR TI-RADS (AUC = 0.898 (95%CI, 0.863–0.926) and 0.870 (95%CI, 0.806–0.919) in the training group and verification group, respectively), and followed by Rad-score (AUC = 0.750 (95%CI, 0.704–0.792) and 0.750 (95%CI, 0.672–0.817) in the training group and verification group, respectively). We concluded that the ability of ultrasound Rad-score to distinguish benign and malignant TNs was not as good as that of ACR TI-RADS, and the ability of the combination model of Rad-score and ACR TI-RADS to discriminate benign and malignant TNs was better than ACR TI-RADS or Rad-score alone. Ultrasound Rad-score might play a potential role in improving the differentiation of malignant TNs from benign TNs.

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.

MRI-Based Radiomics Models for Predicting Risk Classification of Gastrointestinal Stromal Tumors

Background

We conduct a study in developing and validating four MRI-based radiomics models to preoperatively predict the risk classification of gastrointestinal stromal tumors (GISTs).

Methods

Forty-one patients (low-risk = 17, intermediate-risk = 13, high-risk = 11) underwent MRI before surgery between September 2013 and March 2019 in this retrospective study. The Kruskal–Wallis test with Bonferonni correction and variance threshold was used to select appropriate features, and the Random Forest model (three classification model) was used to select features among the high-risk, intermediate-risk, and low-risk of GISTs. The predictive performance of the models built by the Random Forest was estimated by a 5-fold cross validation (5FCV). Their performance was estimated using the receiver operating characteristic (ROC) curve, summarized as the area under the ROC curve (AUC). Area under the curve (AUC), accuracy, sensitivity, and specificity for risk classification were reported. Linear discriminant analysis (LDA) was used to assess the discriminative ability of these radiomics models.

Results

The high-risk, intermediate-risk, and low-risk of GISTs were well classified by radiomics models, the micro-average of ROC curves was 0.85, 0.81, 0.87 and 0.94 for T1WI, T2WI, ADC and combined three MR sequences. And ROC curves achieved excellent AUCs for T1WI (0.85, 0.75 and 0.82), T2WI (0.69, 0.78 and 0.78), ADC (0.85, 0.77 and 0.80) and combined three MR sequences (0.96, 0.92, 0.81) for the diagnosis of high-risk, intermediate-risk, and low-risk of GISTs, respectively. In addition, LDA demonstrated the different risk of GISTs were correctly classified by radiomics analysis (61.0% for T1WI, 70.7% for T2WI, 83.3% for ADC, and 78.9% for the combined three MR sequences).

Conclusions

Radiomics models based on a single sequence and combined three MR sequences can be a noninvasive method to evaluate the risk classification of GISTs, which may help the treatment of GISTs patients in the future.

Radiomic model for differentiating parotid pleomorphic adenoma from parotid adenolymphoma based on MRI images

Background

Distinguishing parotid pleomorphic adenoma (PPA) from parotid adenolymphoma (PA) is important for precision treatment, but there is a lack of readily available diagnostic methods. In this study, we aimed to explore the diagnostic value of radiomic signatures based on magnetic resonance imaging (MRI) for PPA and PA.

Methods

The clinical characteristic and imaging data were retrospectively collected from 252 cases (126 cases in the training cohort and 76 patients in the validation cohort) in this study. Radiomic features were extracted from MRI scans, including T1-weighted imaging (T1WI) sequences and T2-weighted imaging (T2WI) sequences. The radiomic features from three sequences (T1WI, T2WI and T1WI combined with T2WI) were selected using univariate analysis, LASSO correlation and Spearman correlation. Then, we built six quantitative radiomic models using the selected features through two machine learning methods (multivariable logistic regression, MLR, and support vector machine, SVM). The performances of the six radiomic models were assessed and the diagnostic efficacies of the ideal T1-2WI radiomic model and the clinical model were compared.

Results

The T1-2WI radiomic model using MLR showed optimal discriminatory ability (accuracy = 0.87 and 0.86, F-1 score = 0.88 and 0.86, sensitivity = 0.90 and 0.88, specificity = 0.82 and 0.80, positive predictive value = 0.86 and 0.84, negative predictive value = 0.86 and 0.84 in the training and validation cohorts, respectively) and its calibration was observed to be good (p > 0.05). The area under the curve (AUC) of the T1-2WI radiomic model was significantly better than that of the clinical model for both the training (0.95 vs. 0.67, p < 0.001) and validation (0.90 vs. 0.68, p = 0.001) cohorts.

Conclusions

The T1-2WI radiomic model in our study is complementary to the current knowledge of differential diagnosis for PPA and PA.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-021-00581-9.

Development and validation of preoperative magnetic resonance imaging-based survival predictive nomograms for patients with perihilar cholangiocarcinoma after radical resection: A pilot study

PURPOSE

We aim to develop survival predictive tools to inform clinical decision-making in perihilar cholangiocarcinoma (pCCA).

MATERIALS AND METHODS

A total of 184 patients who had curative resection and magnetic resonance imaging (MRI) examination for pCCA between January 2010 and December 2018 were enrolled. 110 patients were randomly selected for model development, while the other 74 patients for model testing. Preoperative clinical, laboratory, and imaging data were analyzed. Preoperative clinical predictors were used independently or integrated with radiomics signatures to construct different preoperative models through the multivariable Cox proportional hazards method. The nomograms were constructed to predict overall survival (OS), and the performance of which was evaluated by the discrimination ability, time-dependent receiver operating characteristic curve (ROC), calibration curve, and decision curve.

RESULTS

The clinical model (Model^clinic) was constructed based on three independent variables including preoperative CEA, cN stage, and invasion of hepatic artery in images. The model yield the best performance (Model^{clinic&AP&PVP}) was build using three independent variables, Signature^AP and Signature^PVP. In training and testing cohorts, the concordance indexes (C-indexes) of Model^clinic were 0.846 (95 % CI, 0.735-0.957) and 0.755 (95 % CI, 0.540-969), and Model^{clinic&AP&PVP} achieved C-indexes of 0.962 (95 % CI, 0.905-1) and 0.814 (95 % CI, 0.569-1). Both Model^clinic and Model^{clinic&AP&PVP} outperformed the TNM staging system. Good agreement was observed in the calibration curves, and favorable clinical utility was validated using the decision curve analysis for Model^clinic and Model^{clinic&AP&PVP}.

CONCLUSION

Two preoperative nomograms were constructed to predict 1-, 3-, and 5-years survival for individual pCCA patients, demonstrating the potential for clinical application to assist decision-making.