Magnetic Resonance Imaging-Based Radiomics Models to Predict Early Extrapancreatic Necrosis in Acute Pancreatitis

Application of radiomics in acute and severe non-neoplastic diseases: A literature review

Radiomics involves the integration of computer technology, big data analysis, and clinical medicine. Currently, there have been initial advancements in the fields of acute cerebrovascular disease and cardiovascular disease. The objective of radiomics is to extract quantitative features from medical images for analysis to predict the risk or treatment outcome, help in differential diagnosis, and guide clinical decisions and management. Radiomics applied research has reached a more advanced stage yet encounters several obstacles, including the need for standardization of radiomics features and alignment with treatment requirements for acute and severe illnesses. Future research should aim to seamlessly incorporate radiomics with various disciplines, leverage big data and artificial intelligence advancements, cater to the requirements of acute and critical medicine, and enhance the effectiveness of technological innovation and application in diagnosing and treating acute and critical illnesses.

Integrating CT-based radiomics and clinical features to better predict the prognosis of acute pancreatitis

OBJECTIVES

To develop and validate the performance of CT-based radiomics models for predicting the prognosis of acute pancreatitis.

METHODS

All 344 patients (51 ± 15 years, 171 men) in a first episode of acute pancreatitis (AP) were retrospectively enrolled and randomly divided into training (n = 206), validation (n = 69), and test (n = 69) sets with the ratio of 6:2:2. The patients were dichotomized into good and poor prognosis subgroups based on follow-up CT and clinical data. The radiomics features were extracted from contrast-enhanced CT. Logistic regression analysis was applied to analyze clinical-radiological features for developing clinical and radiomics-derived models. The predictive performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA).

RESULTS

Eight pancreatic and six peripancreatic radiomics features were identified after reduction and selection. In the training set, the AUCs of clinical, pancreatic, peripancreatic, radiomics, and combined models were 0.859, 0.800, 0.823, 0.852, and 0.899, respectively. In the validation set, the AUCs were 0.848, 0.720, 0.746, 0.773, and 0.877, respectively. The combined model exhibited the highest AUC among radiomics-based models (pancreatic, peripancreatic, and radiomics models) in both the training (0.899) and validation (0.877) sets (all p < 0.05). Further, the AUC of the combined model was 0.735 in the test set. The calibration curve and DCA indicated the combined model had favorable predictive performance.

CONCLUSIONS

CT-based radiomics incorporating clinical features was superior to other models in predicting AP prognosis, which may offer additional information for AP patients at higher risk of developing poor prognosis.

CRITICAL RELEVANCE STATEMENT

Integrating CT radiomics-based analysis of pancreatic and peripancreatic features with clinical risk factors enhances the assessment of AP prognosis, allowing for optimal clinical decision-making in individuals at risk of severe AP.

KEY POINTS

Radiomics analysis provides help to accurately assess acute pancreatitis (AP). CT radiomics-based models are superior to the clinical model in the prediction of AP prognosis. A CT radiomics-based nomogram integrated with clinical features allows a more comprehensive assessment of AP prognosis.

Radiomics models of contrast-enhanced computed tomography for predicting the activity and prognosis of acute pancreatitis

BACKGROUND

The modified pancreatitis activity scoring system (mPASS) was proposed to assess the activity of acute pancreatitis (AP) while it doesn't include indicators that directly reflect pathophysiology processes and imaging characteristics.

OBJECTIVES

To determine the threshold of admission mPASS and investigate radiomics and laboratory parameters to construct a model to predict the activity of AP.

METHODS

AP inpatients at institution 1 were randomly divided into training and validation groups based on a 5:5 ratio. AP inpatients at Institution 2 were served as test group. The cutoff value of admission mPASS scores in predicting severe AP was selected to divide patients into high and low level of disease activity group. LASSO was used in screening features. Multivariable logistic regression was used to develop radiomics model. Meaningful laboratory parameters were used to construct combined model.

RESULTS

There were 234 (48 years ± 10, 155 men) and 101 (48 years ± 11, 69 men) patients in two institutions. The threshold of admission mPASS score was 112.5 in severe AP prediction. The AUC of the radiomics model was 0.79, 0.72, and 0.76 and that of the combined model incorporating rad-score and white blood cell were 0.84, 0.77, and 0.80 in three groups for activity prediction. The AUC of the combined model in predicting disease without remission was 0.74.

CONCLUSIONS

The threshold of admission mPASS was 112.5 in predicting severe AP. The model based on CECT radiomics has the ability to predict AP activity. Its ability to predict disease without remission is comparable to mPASS.

CRITICAL RELEVANCE STATEMENT

This work is the first attempt to assess the activity of acute pancreatitis using contrast-enhanced CT radiomics and laboratory parameters. The model provides a new method to predict the activity and prognosis of AP, which could contribute to further management.

KEY POINTS

Radiomics features and laboratory parameters are associated with the activity of acute pancreatitis. The combined model provides a new method to predict the activity and prognosis of AP. The ability of the combined model is comparable to the modified Pancreatitis Activity Scoring System.

Radiomics-Based Machine Learning Model for Diagnosis of Acute Pancreatitis Using Computed Tomography

In the early diagnostic workup of acute pancreatitis (AP), the role of contrast-enhanced CT is to establish the diagnosis in uncertain cases, assess severity, and detect potential complications like necrosis, fluid collections, bleeding or portal vein thrombosis. The value of texture analysis/radiomics of medical images has rapidly increased during the past decade, and the main focus has been on oncological imaging and tumor classification. Previous studies assessed the value of radiomics for differentiating between malignancies and inflammatory diseases of the pancreas as well as for prediction of AP severity. The aim of our study was to evaluate an automatic machine learning model for AP detection using radiomics analysis. Patients with abdominal pain and contrast-enhanced CT of the abdomen in an emergency setting were retrospectively included in this single-center study. The pancreas was automatically segmented using TotalSegmentator and radiomics features were extracted using PyRadiomics. We performed unsupervised hierarchical clustering and applied the random-forest based Boruta model to select the most important radiomics features. Important features and lipase levels were included in a logistic regression model with AP as the dependent variable. The model was established in a training cohort using fivefold cross-validation and applied to the test cohort (80/20 split). From a total of 1012 patients, 137 patients with AP and 138 patients without AP were included in the final study cohort. Feature selection confirmed 28 important features (mainly shape and first-order features) for the differentiation between AP and controls. The logistic regression model showed excellent diagnostic accuracy of radiomics features for the detection of AP, with an area under the curve (AUC) of 0.932. Using lipase levels only, an AUC of 0.946 was observed. Using both radiomics features and lipase levels, we showed an excellent AUC of 0.933 for the detection of AP. Automated segmentation of the pancreas and consecutive radiomics analysis almost achieved the high diagnostic accuracy of lipase levels, a well-established predictor of AP, and might be considered an additional diagnostic tool in unclear cases. This study provides scientific evidence that automated image analysis of the pancreas achieves comparable diagnostic accuracy to lipase levels and might therefore be used in the future in the rapidly growing era of AI-based image analysis.

Evaluation of Inflammatory Infiltration in the Retroperitoneal Space of Acute Pancreatitis Using Computer Tomography and Its Correlation with Clinical Severity

This paper investigates the correlation between the degree and severity of CT inflammatory infiltration in the retroperitoneal space of acute pancreatitis (AP). A total of 113 patients were included based on diagnostic criteria. The general data of the patients and the relationship between the computed tomography severity index (CTSI) and pleural effusion (PE), involvement, degree of inflammatory infiltration of retroperitoneal space (RPS), number of peripancreatic effusion sites, and degree of pancreatic necrosis on contrast-enhanced CT at different times were studied. The results showed that the mean age of onset in females was later than that in males; 62 cases involved RPS to varying degrees, with a positive rate of 54.9% (62/113), and the total involvement rates of only the anterior pararenal space (APS); both APS and perirenal space (PS); and APS, PS, and posterior pararenal space (PPS) were 46.9% (53/113), 53.1% (60/113), and 17.7% (20/113), respectively. The degree of inflammatory infiltration in the RPS worsened with the increase in CTSI score; the incidence of PE was higher in the group greater than 48 hours than in the group less than 48 hours; necrosis >50% grade was predominant (43.2%) 5 to 6 days after onset, with a higher detection rate than other time periods (P < 0.05). Thus, when the PPS was involved, the patient's condition can be treated as severe acute pancreatitis (SAP); the higher the degree of inflammatory infiltration in the retroperitoneum, the higher the severity of AP. Enhanced CT examination 5 to 6 days after onset in patients with AP revealed the greatest extent of pancreatic necrosis.

Radiomics: Status quo and future challenges

Noninvasive imaging (computed tomography, magnetic resonance imaging, endoscopic ultrasonography, and positron emission tomography) as an important part of the clinical workflow in the clinic, but it still provides limited information for diagnosis, treatment effect evaluation and prognosis prediction. In addition, judgment and diagnoses made by experts are usually based on multiple years of experience and subjective impression which lead to variable results in the same case. With accumulation of medical imaging data, radiomics emerges as a relatively new approach for analysis. Via artificial intelligence techniques, high-throughput quantitative data which is invisible to the naked eyes extracted from original images can be used in the process of patients’ management. Several studies have evaluated radiomics combined with clinical factors, pathological, or genetic information would assist in the diagnosis, particularly in the prediction of biological characteristics, risk of recurrence, and survival with encouraging results. In various clinical settings, there are limitations and challenges needing to be overcome before transformation. Therefore, we summarize the concepts and method of radiomics including image acquisition, region of interest segmentation, feature extraction and model development. We also set forth the current applications of radiomics in clinical routine. At last, the limitations and related deficiencies of radiomics are pointed out to direct the future opportunities and development.

A systematic review of radiomics in pancreatitis: applying the evidence level rating tool for promoting clinical transferability

Background

Multiple tools have been applied to radiomics evaluation, while evidence rating tools for this field are still lacking. This study aims to assess the quality of pancreatitis radiomics research and test the feasibility of the evidence level rating tool.

Results

Thirty studies were included after a systematic search of pancreatitis radiomics studies until February 28, 2022, via five databases. Twenty-four studies employed radiomics for diagnostic purposes. The mean ± standard deviation of the adherence rate was 38.3 ± 13.3%, 61.3 ± 11.9%, and 37.1 ± 27.2% for the Radiomics Quality Score (RQS), the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist, and the Image Biomarker Standardization Initiative (IBSI) guideline for preprocessing steps, respectively. The median (range) of RQS was 7.0 (− 3.0 to 18.0). The risk of bias and application concerns were mainly related to the index test according to the modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. The meta-analysis on differential diagnosis of autoimmune pancreatitis versus pancreatic cancer by CT and mass-forming pancreatitis versus pancreatic cancer by MRI showed diagnostic odds ratios (95% confidence intervals) of, respectively, 189.63 (79.65–451.48) and 135.70 (36.17–509.13), both rated as weak evidence mainly due to the insufficient sample size.

Conclusions

More research on prognosis of acute pancreatitis is encouraged. The current pancreatitis radiomics studies have insufficient quality and share common scientific disadvantages. The evidence level rating is feasible and necessary for bringing the field of radiomics from preclinical research area to clinical stage.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-022-01279-4.

Automated Machine Learning for the Early Prediction of the Severity of Acute Pancreatitis in Hospitals

Background

Machine learning (ML) algorithms are widely applied in building models of medicine due to their powerful studying and generalizing ability. This study aims to explore different ML models for early identification of severe acute pancreatitis (SAP) among patients hospitalized for acute pancreatitis.

Methods

This retrospective study enrolled patients with acute pancreatitis (AP) from multiple centers. Data from the First Affiliated Hospital and Changshu No. 1 Hospital of Soochow University were adopted for training and internal validation, and data from the Second Affiliated Hospital of Soochow University were adopted for external validation from January 2017 to December 2021. The diagnosis of AP and SAP was based on the 2012 revised Atlanta classification of acute pancreatitis. Models were built using traditional logistic regression (LR) and automated machine learning (AutoML) analysis with five types of algorithms. The performance of models was evaluated by the receiver operating characteristic (ROC) curve, the calibration curve, and the decision curve analysis (DCA) based on LR and feature importance, SHapley Additive exPlanation (SHAP) Plot, and Local Interpretable Model Agnostic Explanation (LIME) based on AutoML.

Results

A total of 1,012 patients were included in this study to develop the AutoML models in the training/validation dataset. An independent dataset of 212 patients was used to test the models. The model developed by the gradient boost machine (GBM) outperformed other models with an area under the ROC curve (AUC) of 0.937 in the validation set and an AUC of 0.945 in the test set. Furthermore, the GBM model achieved the highest sensitivity value of 0.583 among these AutoML models. The model developed by eXtreme Gradient Boosting (XGBoost) achieved the highest specificity value of 0.980 and the highest accuracy of 0.958 in the test set.

Conclusions

The AutoML model based on the GBM algorithm for early prediction of SAP showed evident clinical practicability.

Radiomics and Its Applications and Progress in Pancreatitis: A Current State of the Art Review

Radiomics involves high-throughput extraction and analysis of quantitative information from medical images. Since it was proposed in 2012, there are some publications on the application of radiomics for (1) predicting recurrent acute pancreatitis (RAP), clinical severity of acute pancreatitis (AP), and extrapancreatic necrosis in AP; (2) differentiating mass-forming chronic pancreatitis (MFCP) from pancreatic ductal adenocarcinoma (PDAC), focal autoimmune pancreatitis (AIP) from PDAC, and functional abdominal pain (functional gastrointestinal diseases) from RAP and chronic pancreatitis (CP); and (3) identifying CP and normal pancreas, and CP risk factors and complications. In this review, we aim to systematically summarize the applications and progress of radiomics in pancreatitis and it associated situations, so as to provide reference for related research.