Whole liver CT texture analysis to predict the development of colorectal liver metastases-A multicentre study

Prediction of liver metastasis and recommended optimal follow-up nursing in rectal cancer

We aimed to analyze and investigate the clinical factors that influence the occurrence of liver metastasis in locally advanced rectal cancer patients, with an attempt to assist patients in devising the optimal imaging-based follow-up nursing. Between June 2011 and May 2021, patients with rectal cancer at our hospital were retrospectively analyzed. A random survival forest model was developed to predict the probability of liver metastasis and provide a practical risk-based approach to surveillance. The results indicated that age, perineural invasion, and tumor deposit were significant factors associated with the liver metastasis and survival. The liver metastasis risk of the low-risk group was higher at 6-21 months, with a peak occurrence time in the 15th month. The liver metastasis risk of the high-risk group was higher at 0-24 months, with a peak occurrence time in the 8th month. In general, our clinical model could predict liver metastasis in rectal cancer patients. It provides a visualization tool that can aid physicians and nurses in making clinical decisions, by detecting the probability of liver metastasis.

Artificial Intelligence to Early Predict Liver Metastases in Patients with Colorectal Cancer: Current Status and Future Prospectives

BACKGROUND

Artificial Intelligence (AI)-based analysis represents an evolving medical field. In the last few decades, several studies have reported the diagnostic efficiency of AI applied to Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) to early detect liver metastases (LM), mainly from colorectal cancer. Despite the increase in information and the development of different procedures in several radiological fields, an accurate method of predicting LM has not yet been found. This review aims to compare the diagnostic efficiency of different AI methods in the literature according to accuracy, sensibility, precision, and recall to identify early LM.

METHODS

A narrative review of the literature was conducted on PubMed. A total of 336 studies were screened.

RESULTS

We selected 17 studies from 2012 to 2022. In total, 14,475 patients were included, and more than 95% were affected by colorectal cancer. The most frequently used imaging tool to early detect LM was found to be CT (58%), while MRI was used in three cases. Four different AI analyses were used: deep learning, radiomics, machine learning, and fuzzy systems in seven (41.18%), five (29.41%), four (23.53%), and one (5.88%) cases, respectively. Four studies achieved an accuracy of more than 90% after MRI and CT scan acquisition, while just two reported a recall rate ≥90% (one method using MRI and CT and one CT).

CONCLUSIONS

Routinely acquired radiological images could be used for AI-based analysis to early detect LM. Simultaneous use of radiomics and machine learning analysis applied to MRI or CT images should be an effective method considering the better results achieved in the clinical scenario.

The prognostic value of radiomic features in liver-limited metastatic colorectal cancer patients from the TRIBE2 study

Aims: Evaluating the prognostic role of radiomic features in liver-limited metastatic colorectal cancer treated with first-line therapy at baseline and best response among patients undergoing resection. Patients & methods: Among patients enrolled in TRIBE2 (NCT02339116), the association of clinical and radiomic data, extracted by SOPHiA-DDM™ with progression-free and overall survival (OS) in the overall population and with disease-free survival/postresection OS in those undergoing resection was investigated. Results: Among 98 patients, radiomic parameters improved the prediction accuracy of our model for OS (area under the curve: 0.83; sensitivity: 0.85; specificity: 0.73; accuracy: 0.78), but not progression-free survival. Of 46 resected patients, small-distance high gray-level emphasis was associated with shorter disease-free survival and high gray-level zone emphasis/higher kurtosis with shorter postresection OS. Conclusion: Radiomic features should be implemented as tools of outcome prediction for liver-limited metastatic colorectal cancer.

Radiomics based on preoperative rectal cancer MRI to predict the metachronous liver metastasis

PURPOSE

At present, there are few effective method to predict metachronous liver metastasis (MLM) from rectal cancer. We aim to investigate the efficacy of radiomics based on multiparametric MRI of first diagnosed rectal cancer in predicting MLM from rectal cancer.

METHODS

From 301 consecutive histopathologically confirmed rectal cancer patients, 130 patients who have no distant metastasis detected at the time of diagnosis were enrolled and divided into MLM group (n = 49) and non-MLM group (n = 81) according to whether liver metastasis be detected later than 6 month after the first diagnosis of rectal cancer within 3 years' follow-up. The 130 patients were divided into a training set (n = 91) and a testing set (n = 39) at a ratio of 7:3 by stratified sampling using SPSS 24.0 software. The DWI model, HD T₂WI model, and DWI + HD T₂WI model were constructed respectively. The best performing model was selected and combined with the screened clinical features (including non-radiomics MRI features) to construct a fusion model. The testing set was used to evaluate the performance of the models, and the area under the curve (AUC) of receiver operating characteristics (ROC) was calculated for both the training set and the testing set.

RESULTS

The AUC of the DWI + HD T₂WI model in the testing set was higher than that of the DWI or the HD T₂ model alone with statistically significance (P < 0.05). The screened clinical features were extramural vascular invasion (EMVI), T and N stages in MRI (_mrT, _mrN), and the distance from the lower edge of the tumor to the anal verge. The AUC of the fusion model in the testing set was 0.911. Decision curves and nomogram also showed that the fusion model had excellent clinical performance.

CONCLUSION

The fusion model of primary rectal cancer MRI based radiomics combing clinical features can effectively predict MLM from rectal cancer, which may assist clinicians in formulating individualized monitoring and treatment plans.

Deep learning-based assessment of body composition and liver tumour burden for survival modelling in advanced colorectal cancer

BACKGROUND

Personalized therapy planning remains a significant challenge in advanced colorectal cancer care, despite extensive research on prognostic and predictive markers. A strong correlation of sarcopenia or overall body composition and survival has been described. Here, we explore whether automated assessment of body composition and liver metastases from standard of care CT images can add to clinical parameters in personalized survival risk prognostication.

METHODS

We retrospectively analysed clinical imaging data from 85 patients (50.6% female, mean age 58.9 SD 12.2 years) with colorectal cancer and synchronous liver metastases. Pretrained deep learning models were used to assess body composition and liver metastasis geometry from abdominal CT images before the initiation of systemic treatment. Abdominal muscle-to-bone ratio (MBR) was calculated by dividing abdominal muscle volume by abdominal bone volume. MBR was compared with body mass index (BMI), abdominal muscle volume, and abdominal muscle volume divided by height squared. Differences in overall survival based on body composition and liver metastasis parameters were compared using Kaplan-Meier survival curves. Results were correlated with clinical and biomarker data to develop a machine learning model for survival risk prognostication.

RESULTS

The MBR, unlike abdominal muscle volume or BMI, was significantly associated with overall survival (HR 0.39, 95% CI: 0.19-0.80, P = 0.009). The MBR (P = 0.022), liver metastasis surface area (P = 0.01) and primary tumour sidedness (P = 0.007) were independently associated with overall survival in multivariate analysis. Body composition parameters did not correlate with KRAS mutational status or primary tumour sidedness. A prediction model based on MBR, liver metastasis surface area and primary tumour sidedness achieved a concordance index of 0.69.

CONCLUSIONS

Automated segmentation enables to extract prognostic parameters from routine imaging data for personalized survival modelling in advanced colorectal cancer patients.

Role of radiomics in the diagnosis and treatment of gastrointestinal cancer

Gastrointestinal cancer (GIC) has high morbidity and mortality as one of the main causes of cancer death. Preoperative risk stratification is critical to guide patient management, but traditional imaging studies have difficulty predicting its biological behavior. The emerging field of radiomics allows the conversion of potential pathophysiological information in existing medical images that cannot be visually recognized into high-dimensional quantitative image features. Tumor lesion characterization, therapeutic response evaluation, and survival prediction can be achieved by analyzing the relationships between these features and clinical and genetic data. In recent years, the clinical application of radiomics to GIC has increased dramatically. In this editorial, we describe the latest progress in the application of radiomics to GIC and discuss the value of its potential clinical applications, as well as its limitations and future directions.

Whole-liver enhanced CT radiomics analysis to predict metachronous liver metastases after rectal cancer surgery

Background

To develop a radiomics model based on pretreatment whole-liver portal venous phase (PVP) contrast-enhanced CT (CE-CT) images for predicting metachronous liver metastases (MLM) within 24 months after rectal cancer (RC) surgery.

Methods

This study retrospectively analyzed 112 RC patients without preoperative liver metastases who underwent rectal surgery between January 2015 and December 2017 at our institution. Volume of interest (VOI) segmentation of the whole-liver was performed on the PVP CE-CT images. All 1316 radiomics features were extracted automatically. The maximum-relevance and minimum-redundancy and least absolute shrinkage and selection operator methods were used for features selection and radiomics signature constructing. Three models based on radiomics features (radiomics model), clinical features (clinical model), and radiomics combined with clinical features (combined model) were built by multivariable logistic regression analysis. Receiver operating characteristic (ROC) curves were used to assess the diagnostic performance of models, and calibration curve and the decision curve analysis were performed to evaluate the clinical application value.

Results

In total, 52 patients in the MLM group and 60 patients in the non-MLM group were enrolled in this study. The radscore was built using 16 selected features and the corresponding coefficients. Both the radiomics model and the combined model showed higher diagnostic performance than clinical model (AUCs of training set: radiomics model 0.84 (95% CI, 0.76–0.93), clinical model 0.65 (95% CI, 0.55–0.75), combined model 0.85 (95% CI, 0.77–0.94); AUCs of validation set: radiomics model 0.84 (95% CI, 0.70–0.98), clinical model 0.58 (95% CI, 0.40–0.76), combined model 0.85 (95% CI, 0.71–0.99)). The calibration curves showed great consistency between the predicted value and actual event probability. The DCA showed that both the radiomics and combined models could add a net benefit on a large scale.

Conclusions

The radiomics model based on preoperative whole-liver PVP CE-CT could predict MLM within 24 months after RC surgery. Clinical features could not significantly improve the prediction efficiency of the radiomics model.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-022-00485-z.

Association of CT-Based Delta Radiomics Biomarker With Progression-Free Survival in Patients With Colorectal Liver Metastases Undergo Chemotherapy

Predicting the prognosis of patients in advance is conducive to providing personalized treatment for patients. Our aim was to predict the therapeutic efficacy and progression free survival (PFS) of patients with liver metastasis of colorectal cancer according to the changes of computed tomography (CT) radiomics before and after chemotherapy.

Methods

This retrospective study included 139 patients (397 lesions) with colorectal liver metastases who underwent neoadjuvant chemotherapy from April 2015 to April 2020. We divided the lesions into training cohort and testing cohort with a ratio of 7:3. Two - dimensional region of interest (ROI) was obtained by manually delineating the largest layers of each metastasis lesion. The expanded ROI (3 mm and 5 mm) were also included in the study to characterize microenvironment around tumor. For each of the ROI, 1,316 radiomics features were extracted from delineated plain scan, arterial, and venous phase CT images before and after neoadjuvant chemotherapy. Delta radiomics features were constructed by subtracting the radiomics features after treatment from the radiomics features before treatment. Univariate Cox regression and the Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression were applied in the training cohort to select the valuable features. Based on clinical characteristics and radiomics features, 7 Cox proportional-hazards model were constructed to predict the PFS of patients. C-index value and Kaplan Meier (KM) analysis were used to evaluate the efficacy of predicting PFS of these models. Moreover, the prediction performance of one-year PFS was also evaluated by area under the curve (AUC).

Results

Compared with the PreRad (Radiomics form pre-treatment CT images; C-index [95% confidence interval (CI)] in testing cohort: 0.614(0.552-0.675) and PostRad models (Radiomics form post-treatment CT images; 0.642(0.578-0.707), the delta model has better PFS prediction performance (Delta radiomics; 0.688(0.627-0.749). By incorporating clinical characteristics, CombDeltaRad obtains the best performance in both training cohort [C-index (95% CI): 0.802(0.772-0.832)] and the testing cohort (0.744(0.686-0.803). For 1-year PFS prediction, CombDeltaRad model obtained the best performance with AUC (95% CI) of 0.871(0.828-0.914) and 0.745 (0.651-0.838) in training cohort and testing cohort, respectively.

Conclusion

CT radiomics features have the potential to predict PFS in patients with colorectal cancer and liver metastasis who undergo neoadjuvant chemotherapy. By combining pre-treatment radiomics features, post-treatment radiomics features, and clinical characteristics better prediction results can be achieved.

Assessment of Primary Colorectal Cancer CT Radiomics to Predict Metachronous Liver Metastasis

Objectives

To establish and validate a machine learning-based CT radiomics model to predict metachronous liver metastasis (MLM) in patients with colorectal cancer.

Methods

In total, 323 patients were retrospectively recruited from two independent institutions to develop and evaluate the CT radiomics model. Then, 1288 radiomics features were extracted to decode the imaging phenotypes of colorectal cancer on CT images. The optimal radiomics features were selected using a recursive feature elimination selector configured by a support vector machine. To reduce the bias caused by an unbalanced dataset, the synthetic minority oversampling technique was applied to resample the minority samples in the datasets. Then, both radiomics and clinical features were used to train the multilayer perceptron classifier to develop two classification models. Finally, a score-level fusion model was developed to further improve the model performance.

Results

The area under the curve (AUC) was 0.78 ± 0.07 for the tumour feature model and 0.79 ± 0.08 for the clinical feature model. The fusion model achieved the best performance, with AUCs of 0.79 ± 0.08 and 0.72 ± 0.07 in the internal and external validation cohorts.

Conclusions

Radiomics models based on baseline colorectal contrast-enhanced CT have high potential for MLM prediction. The fusion model combining radiomics and clinical features can provide valuable biomarkers to identify patients with a high risk of colorectal liver metastases.

Early Diagnosis of Liver Metastases from Colorectal Cancer through CT Radiomics and Formal Methods: A Pilot Study

BACKGROUND

Liver metastases are a leading cause of cancer-associated deaths in patients affected by colorectal cancer (CRC). The multidisciplinary strategy to treat CRC is more effective when the radiological diagnosis is accurate and early. Despite the evolving technologies in radiological accuracy, the radiological diagnosis of Colorectal Cancer Liver Metastases (CRCLM) is still a key point. The aim of our study was to define a new patient representation different by Artificial Intelligence models, using Formal Methods (FMs), to help clinicians to predict the presence of liver metastasis when still undetectable using the standard protocols.

METHODS

We retrospectively reviewed from 2013 to 2020 the CT scan of nine patients affected by CRC who would develop liver lesions within 4 months and 8 years. Seven patients developed liver metastases after primary staging before any liver surgery, and two patients were enrolled after R0 liver resection. Twenty-one patients were enrolled as the case control group (CCG). Regions of Interest (ROIs) were identified through manual segmentation on the medical images including only liver parenchyma and eventual benign lesions, avoiding major vessels and biliary ducts. Our predictive model was built based on formally verified radiomic features.

RESULTS

The precision of our methods is 100%, scheduling patients as positive only if they will be affected by CRCLM, showing a 93.3% overall accuracy. Recall was 77.8%.

CONCLUSION

FMs can provide an effective early detection of CRCLM before clinical diagnosis only through non-invasive radiomic features even in very heterogeneous and small clinical samples.

CT radiomics models are unable to predict new liver metastasis after successful thermal ablation of colorectal liver metastases

BACKGROUND

Patients with colorectal liver metastases (CRLM) who undergo thermal ablation are at risk of developing new CRLM after ablation. Identification of these patients might enable individualized treatment.

PURPOSE

To investigate whether an existing machine-learning model with radiomics features based on pre-ablation computed tomography (CT) images of patients with colorectal cancer can predict development of new CRLM.

MATERIAL AND METHODS

In total, 94 patients with CRLM who were treated with thermal ablation were analyzed. Radiomics features were extracted from the healthy liver parenchyma of CT images in the portal venous phase, before thermal ablation. First, a previously developed radiomics model (Original model) was applied to the entire cohort to predict new CRLM after 6 and 24 months of follow-up. Next, new machine-learning models were developed (Radiomics, Clinical, and Combined), based on radiomics features, clinical features, or a combination of both.

RESULTS

The external validation of the Original model reached an area under the curve (AUC) of 0.57 (95% confidence interval [CI]=0.56-0.58) and 0.52 (95% CI=0.51-0.53) for 6 and 24 months of follow-up. The new predictive radiomics models yielded a higher performance at 6 months compared to 24 months. For the prediction of CRLM at 6 months, the Combined model had slightly better performance (AUC=0.60; 95% CI=0.59-0.61) compared to the Radiomics and Clinical models (AUC=0.55-0.57), while all three models had a low performance for the prediction at 24 months (AUC=0.52-0.53).

CONCLUSION

Both the Original and newly developed radiomics models were unable to predict new CLRM based on healthy liver parenchyma in patients who will undergo ablation for CRLM.

Distinguishing pure histopathological growth patterns of colorectal liver metastases on CT using deep learning and radiomics: a pilot study

Histopathological growth patterns (HGPs) are independent prognosticators for colorectal liver metastases (CRLM). Currently, HGPs are determined postoperatively. In this study, we evaluated radiomics for preoperative prediction of HGPs on computed tomography (CT), and its robustness to segmentation and acquisition variations. Patients with pure HGPs [i.e. 100% desmoplastic (dHGP) or 100% replacement (rHGP)] and a CT-scan who were surgically treated at the Erasmus MC between 2003-2015 were included retrospectively. Each lesion was segmented by three clinicians and a convolutional neural network (CNN). A prediction model was created using 564 radiomics features and a combination of machine learning approaches by training on the clinician's and testing on the unseen CNN segmentations. The intra-class correlation coefficient (ICC) was used to select features robust to segmentation variations; ComBat was used to harmonize for acquisition variations. Evaluation was performed through a 100 × random-split cross-validation. The study included 93 CRLM in 76 patients (48% dHGP; 52% rHGP). Despite substantial differences between the segmentations of the three clinicians and the CNN, the radiomics model had a mean area under the curve of 0.69. ICC-based feature selection or ComBat yielded no improvement. Concluding, the combination of a CNN for segmentation and radiomics for classification has potential for automatically distinguishing dHGPs from rHGP, and is robust to segmentation and acquisition variations. Pending further optimization, including extension to mixed HGPs, our model may serve as a preoperative addition to postoperative HGP assessment, enabling further exploitation of HGPs as a biomarker.

Development and validation of a radiomics nomogram to discriminate advanced pancreatic cancer with liver metastases or other metastatic patterns

BACKGROUND

Patients with advanced pancreatic cancer (APC) and liver metastases have much poorer prognoses than patients with other metastatic patterns.

OBJECTIVE

This study aimed to develop and validate a radiomics model to discriminate patients with pancreatic cancer and liver metastases from those with other metastatic patterns.

METHODS

We evaluated 77 patients who had APC and performed texture analysis on the region of interest. 58 patients and 19 patients were allocated randomly into the training and validation cohorts with almost the same proportion of liver metastases. An independentsamples t-test was used for feature selection in the training cohort. Random forest classifier was used to construct models based on these features and a radiomics signature (RS) was derived. A nomogram was constructed based on RS and CA19-9, and was validated with calibration plot and decision curve. The prognostic value of RS was evaluated by Kaplan-Meier methods.

RESULTS

The constructed nomogram demonstrated good discrimination in the training (AUC = 0.93) and validation (AUC = 0.81) cohorts. In both cohorts, patients with RS > 0.61 had much poorer overall survival than patients with RS < 0.61.

CONCLUSIONS

This study presents a radiomics nomogram incorporating RS and CA19-9 to discriminate patients who have APC with liver metastases from patients with other metastatic patterns.

Emerging applications of radiomics in rectal cancer: State of the art and future perspectives

Rectal cancer (RC) is the third most commonly diagnosed cancer and has a high risk of mortality, although overall survival rates have improved. Preoperative assessments and predictions, including risk stratification, responses to therapy, long-term clinical outcomes, and gene mutation status, are crucial to guide the optimization of personalized treatment strategies. Radiomics is a novel approach that enables the evaluation of the heterogeneity and biological behavior of tumors by quantitative extraction of features from medical imaging. As these extracted features cannot be captured by visual inspection, the field holds significant promise. Recent studies have proved the rapid development of radiomics and validated its diagnostic and predictive efficacy. Nonetheless, existing radiomics research on RC is highly heterogeneous due to challenges in workflow standardization and limitations of objective cohort conditions. Here, we present a summary of existing research based on computed tomography and magnetic resonance imaging. We highlight the most salient issues in the field of radiomics and analyze the most urgent problems that require resolution. Our review provides a cutting-edge view of the use of radiomics to detect and evaluate RC, and will benefit researchers dedicated to using this state-of-the-art technology in the era of precision medicine.

Machine learning-based analysis of CT radiomics model for prediction of colorectal metachronous liver metastases

PURPOSE

Early identification of patients at risk of developing colorectal liver metastases can help personalizing treatment and improve oncological outcome. The aim of this study was to investigate in patients with colorectal cancer (CRC) whether a machine learning-based radiomics model can predict the occurrence of metachronous metastases.

METHODS

In this multicentre study, the primary staging portal venous phase CT of 91 CRC patients were retrospectively analysed. Two groups were assessed: patients without liver metastases at primary staging, or during follow-up of ≥ 24 months (n = 67) and patients without liver metastases at primary staging but developed metachronous liver metastases < 24 months after primary staging (n = 24). After liver parenchyma segmentation, 1767 radiomics features were extracted for each patient. Three predictive models were constructed based on (1) radiomics features, (2) clinical features and (3) a combination of clinical and radiomics features. Stability of features across hospitals was assessed by the Kruskal-Wallis test and inter-correlated features were removed if their correlation coefficient was higher than 0.9. Bayesian-optimized random forest with wrapper feature selection was used for prediction models.

RESULTS

The three predictive models that included radiomics features, clinical features and a combination of radiomics with clinical features resulted in an AUC in the validation cohort of 86% (95%CI 85-87%), 71% (95%CI 69-72%) and 86% (95% CI 85-87%), respectively.

CONCLUSION

A machine learning-based radiomics analysis of routine clinical CT imaging at primary staging can provide valuable biomarkers to identify patients at high risk for developing colorectal liver metastases.

Radiomics for the Prediction of Treatment Outcome and Survival in Patients With Colorectal Cancer: A Systematic Review

Prediction of outcome in patients with colorectal cancer (CRC) is challenging as a result of lack of a robust biomarker and heterogeneity between and within tumors. The aim of this review was to assess the current possibilities and limitations of radiomics (on computed tomography [CT], magnetic resonance imaging [MRI], and positron emission tomography [PET]) for the prediction of treatment outcome and long-term outcome in CRC. Medline/PubMed was searched up to August 2020 for studies that used radiomics for the prediction of response to treatment and survival in patients with CRC (based on pretreatment imaging). The Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool and Radiomics Quality Score (RQS) were used for quality assessment. A total of 76 studies met the inclusion criteria and were included for further analysis. Radiomics analyses were performed on MRI in 41 studies, on CT in 30 studies, and on ¹⁸F-FDG-PET/CT in 10 studies. Heterogeneous results were reported regarding radiomics methods and included features. High-quality studies (n = 13), consisting mainly of MRI-based radiomics to predict response in rectal cancer, were able to predict response with good performance. Radiomics literature in CRC is highly heterogeneous, but it nonetheless holds promise for the prediction of outcome. The most evidence is available for MRI-based radiomics in rectal cancer. Future radiomics research in CRC should focus on independent validation of existing models rather than on developing new models.

Contrast-Enhanced CT-based Textural Parameters as Potential Prognostic Factors of Survival for Colorectal Cancer Patients Receiving Targeted Therapy

PURPOSE

This study was designed to estimate the clinical significance of the contrast-enhanced computed tomography (CT) textural features for prediction of survival in colorectal cancer (CRC) patients receiving targeted therapy (bevacizumab and cetuximab).

PROCEDURES

The LifeX software was used to extract the textural parameters of the tumor lesions in the contrast-enhanced CT. We used the least absolute shrinkage and selection operator (LASSO) Cox regression and random forest method to screen the non-redundant radiomic features and constructed the CT imaging score. Univariate and multivariate analyses through the Cox proportional hazards model were performed to assess the prognostic clinical factor. Based on the result of multivariate analysis and CT imaging score, combined nomogram model was constructed to predict the overall survival (OS) of patients. Decision curves analysis was employed to evaluate the performance of the combined model and clinical model.

RESULTS

After comparative analysis of the area under curve of the receiver operating characteristic (ROC) curve, we chose the result of random forest model as CT imaging score. Considering the clinical practice and the result of analysis, age, surgery, and lactate dehydrogenase (LDH) level have been introduced into clinical model. Based on the result of analysis and the CT imaging score, we constructed the nomogram combined model. C-index and calibration curve verified the goodness of fit and discrimination of the combined model. Decision curve analysis (DCA) demonstrated that the combined model showed the better net benefit for a 3-year OS than clinical model.

CONCLUSIONS

In conclusion, the study provides preliminary evidences that several radiomic parameters of tumor lesions derived from CT images were prognostic factors and predictive markers for CRC patients who are candidates for targeted therapy (bevacizumab and cetuximab).

Applicability of radiomics in interstitial lung disease associated with systemic sclerosis: proof of concept

Objective

To retrospectively evaluate if texture-based radiomics features are able to detect interstitial lung disease (ILD) and to distinguish between the different disease stages in patients with systemic sclerosis (SSc) in comparison with mere visual analysis of high-resolution computed tomography (HRCT).

Methods

Sixty patients (46 females, median age 56 years) with SSc who underwent HRCT of the thorax were retrospectively analyzed. Visual analysis was performed by two radiologists for the presence of ILD features. Gender, age, and pulmonary function (GAP) stage was calculated from clinical data (gender, age, pulmonary function test). Data augmentation was performed and the balanced dataset was split into a training (70%) and a testing dataset (30%). For selecting variables that allow classification of the GAP stage, single and multiple logistic regression models were fitted and compared by using the Akaike information criterion (AIC). Diagnostic accuracy was evaluated from the area under the curve (AUC) from receiver operating characteristic (ROC) analyses, and diagnostic sensitivity and specificity were calculated.

Results

Values for some radiomics features were significantly lower (p < 0.05) and those of other radiomics features were significantly higher (p = 0.001) in patients with GAP2 compared with those in patients with GAP1. The combination of two specific radiomics features in a multivariable model resulted in the lowest AIC of 10.73 with an AUC of 0.96, 84% sensitivity, and 99% specificity. Visual assessment of fibrosis was inferior in predicting individual GAP stages (AUC 0.86; 83% sensitivity; 74% specificity).

Conclusion

The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features indicating severity of SSc-ILD on HRCT, which are not recognized by visual analysis.

Key Points

• Radiomics features can predict GAP stage with a sensitivity of 84% and a specificity of almost 100%.

• Extent of fibrosis on HRCT and a combined model of different visual HRCT-ILD features perform worse in predicting GAP stage.

• The correlation of radiomics with GAP stage, but not with the visually defined features of ILD-HRCT, implies that radiomics might capture features on HRCT, which are not recognized by visual analysis.

Electronic supplementary material

The online version of this article (10.1007/s00330-020-07293-8) contains supplementary material, which is available to authorized users.

The relevance of CT-based geometric and radiomics analysis of whole liver tumor burden to predict survival of patients with metastatic colorectal cancer

OBJECTIVES

To investigate the prediction of 1-year survival (1-YS) in patients with metastatic colorectal cancer with use of a systematic comparative analysis of quantitative imaging biomarkers (QIBs) based on the geometric and radiomics analysis of whole liver tumor burden (WLTB) in comparison to predictions based on the tumor burden score (TBS), WLTB volume alone, and a clinical model.

METHODS

A total of 103 patients (mean age: 61.0 ± 11.2 years) with colorectal liver metastases were analyzed in this retrospective study. Automatic segmentations of WLTB from baseline contrast-enhanced CT images were used. Established biomarkers as well as a standard radiomics model building were used to derive 3 prognostic models. The benefits of a geometric metastatic spread (GMS) model, the Aerts radiomics prior model of the WLTB, and the performance of TBS and WLTB volume alone were assessed. All models were analyzed in both statistical and predictive machine learning settings in terms of AUC.

RESULTS

TBS showed the best discriminative performance in a statistical setting to discriminate 1-YS (AUC = 0.70, CI: [0.56, 0.90]). For the machine learning-based prediction for unseen patients, both a model of the GMS of WLTB (0.73, CI: [0.60, 0.84]) and the Aerts radiomics prior model (0.76, CI: [0.65, 0.86]) applied on the WLTB showed a numerically higher predictive performance than TBS (0.68, CI: [0.54, 0.79]), radiomics (0.65, CI: [0.55, 0.78]), WLTB volume alone (0.53, CI: [0.40. 0.66]), or the clinical model (0.56, CI: [0.43, 0.67]).

CONCLUSIONS

The imaging-based GMS model may be a first step towards a more fine-grained machine learning extension of the TBS concept for risk stratification in mCRC patients without the vulnerability to technical variance of radiomics.

KEY POINTS

• CT-based geometric distribution and radiomics analysis of whole liver tumor burden in metastatic colorectal cancer patients yield prognostic information. • Differences in survival are possibly attributable to the spatial distribution of metastatic lesions and the geometric metastatic spread analysis of all liver metastases may serve as robust imaging biomarker invariant to technical variation. • Imaging-based prediction models outperform clinical models for 1-year survival prediction in metastatic colorectal cancer patients with liver metastases.

Current state of the art imaging approaches for colorectal liver metastasis

One of the most common cancers worldwide, colorectal cancer (CRC) has been associated with significant morbidity and mortality and therefore represents an enormous burden to the health care system. Recent advances in CRC treatments have provided patients with primary and metastatic CRC a better long-term prognosis. The presence of synchronous or metachronous metastasis has been associated, however, with worse survival. The most common site of metastatic disease is the liver. A variety of treatment modalities aimed at targeting colorectal liver metastases (CRLM) has been demonstrated to improve the prognosis of these patients. Loco-regional approaches such as surgical resection and tumor ablation (operative and percutaneous) can provide patients with a chance at long-term disease control and even cure in select populations. Patient selection is important in defining the most suitable treatment option for CRLM in order to provide the best possible survival benefit while avoiding unnecessary interventions and adverse events. Medical imaging plays a crucial role in evaluating the characteristics of CRLMs and disease resectability. Size of tumors, proximity to adjacent anatomical structures, and volume of the unaffected liver are among the most important imaging parameters to determine the suitability of patients for surgical management or other appropriate treatment approaches. We herein provide a comprehensive overview of current-state-of-the-art imaging in the management of CRLM, including staging, treatment planning, response and survival assessment, and post-treatment surveillance. Computed tomography (CT) scan and magnetic resonance imaging (MRI) are two most commonly used techniques, which can be used solely or in combination with functional imaging modalities such as positron emission tomography (PET) and diffusion weighted imaging (DWI). Providing up-to-date evidence on advantages and disadvantages of imaging modalities and tumor assessment criteria, the current review offers a practice guide to assist providers in choosing the most suitable imaging approach for patients with CRLM.

A clinical-radiomic model for improved prognostication of surgical candidates with colorectal liver metastases

BACKGROUND AND OBJECTIVES

Colorectal cancer with liver metastases is potentially curable with surgical resection however clinical prognostic factors can insufficiently stratify patients. This study aims to assess whether radiomic features are prognostic and can inform clinical decision making.

METHODS

This single-site retrospective study included 102 patients who underwent colorectal liver metastases resection with preoperative computed tomography (CT), magnetic resonance imaging (MRI) with gadoxetic acid (EOB) and clinical covariates. A lasso-regularized multivariate Cox proportional hazards model was applied to 114 features (10 clinical, 104 radiomic) to determine association with disease-free survival (DFS). A prognostic index was derived using the significant Cox regression coefficients and their corresponding input features and a threshold was determined to classify patients into high- and low-risk groups, and DFS compared using log-rank tests.

RESULTS

Four covariates were significantly associated with DFS; bilobar disease (hazard ratio [HR]= 1.56; P = .0043), complete pathological response (HR= 0.67; P = .025), minimum pixel value (HR= 1.66; P = .00016), and small area emphasis (HR= 0.62; P = .0013) from the EOB-MRI data. Radiomic CT features were not prognostic. The prognostic index strongly stratified high- and low-risk prognostic groups (HR = 0.31; P = .00068).

CONCLUSION

Radiomic MRI features provided meaningful prognostic information above clinical covariates alone. This merits further validation for potential clinical implementation to inform management.

Application of computerized 3D-CT texture analysis of pancreas for the assessment of patients with diabetes

Objective

To evaluate the role of computerized 3D CT texture analysis of the pancreas as quantitative parameters for assessing diabetes.

Methods

Among 2,493 patients with diabetes, 39 with type 2 diabetes (T2D) and 12 with type 1 diabetes (T1D) who underwent CT using two selected CT scanners, were enrolled. We compared these patients with age-, body mass index- (BMI), and CT scanner-matched normal subjects. Computerized texture analysis for entire pancreas was performed by extracting 17 variable features. A multivariate logistic regression analysis was performed to identify the predictive factors for diabetes. A receiver operator characteristic (ROC) curve was constructed to determine the optimal cut off values for statistically significant variables.

Results

In diabetes, mean attenuation, standard deviation, variance, entropy, homogeneity, surface area, sphericity, discrete compactness, gray-level co-occurrence matrix (GLCM) contrast, and GLCM entropy showed significant differences (P < .05). Multivariate analysis revealed that a higher variance (adjusted OR, 1.002; P = .005), sphericity (adjusted OR, 1.649×10⁴; P = .048), GLCM entropy (adjusted OR, 1.057×10⁵; P = .032), and lower GLCM contrast (adjusted OR, 0.997; P < .001) were significant variables. The mean AUCs for each feature were 0.654, 0.689, 0.620, and 0.613, respectively (P < .05). In subgroup analysis, only larger surface area (adjusted OR, 1.000; P = .025) was a significant predictor for T2D.

Conclusions

Computerized 3D CT texture analysis of the pancreas could be helpful for predicting diabetes. A higher variance, sphericity, GLCM entropy, and a lower GLCM contrast were the significant predictors for diabetes.

Machine Learning-based Analysis of Rectal Cancer MRI Radiomics for Prediction of Metachronous Liver Metastasis

RATIONALE AND OBJECTIVES

To use machine learning-based magnetic resonance imaging radiomics to predict metachronous liver metastases (MLM) in patients with rectal cancer.

MATERIALS AND METHODS

This study retrospectively analyzed 108 patients with rectal cancer (54 in MLM group and 54 in nonmetastases group). Feature selection were performed in the radiomic feature sets extracted from images of T2-weighted image (T2WI) and venous phase (VP) sequence respectively, and the combining feature set with 2058 radiomic features incorporating two sequences with the least absolute shrinkage and selection operator method. Five-fold cross-validation and two machine learning algorithms (support vector machine [SVM]; logistic regression [LR]) were utilized for predictive model constructing. The diagnostic performance of the models was evaluated by receiver operating characteristic curves with indicators of accuracy, sensitivity, specificity and area under the curve, and compared by DeLong test.

RESULTS

Five, 8, and 22 optimal features were selected from 1029 T2WI, 1029 VP, and 2058 combining features, respectively. Four-group models were constructed using the five T2WI features (Model_T2), the 8 VP features (Model_VP), the combined 13 optimal features (Model_combined), and the 22 optimal features selected from 2058 features (Model_optimal). In Model_VP, the LR was superior to the SVM algorithm (P = 0.0303). The Model_optimal using LR algorithm showed the best prediction performance (P = 0.0019-0.0081) with accuracy, sensitivity, specificity, and area under the curve of 0.80, 0.83, 0.76, and 0.87, respectively.

CONCLUSION

Radiomics models based on baseline rectal magnetic resonance imaging has high potential for MLM prediction, especially the Model_optimal using LR algorithm. Moreover, except for Model_VP, the LR was not superior to the SVM algorithm for model construction.

[Computed tomography and/or magnetic resonance imaging of the liver : How, why, what for?]

CLINICAL PROBLEM

Colorectal metastases are the most common malignant liver lesions. Imaging of the liver in patients with colorectal carcinoma is performed for early detection of liver metastases (CRLM) at the time of initial tumor diagnosis, for monitoring and follow-up in order to exclude or diagnose metachronous metastases.

STANDARD RADIOLOGICAL METHODS

Radiological imaging includes primarily multislice computed tomography (CT) and magnetic resonance imaging (MRI), which play an important role regarding therapeutic management and assessment of prognosis.

PERFORMANCE, ACHIEVEMENTS

Contrast-enhanced CT is broadly available and allows for rapid image acquisition including the possibility for complete tumor staging. MRI, on the other hand, is characterized by very good soft tissue contrast and has-especially with the use of diffusion-weighted imaging and administration of liver-specific contrast agents-the highest sensitivity for detection of metastases smaller than 1 cm.

PRACTICAL RECOMMENDATIONS

The choice of imaging in daily routine is often dependent on availability and clinical question. Frequently, e.g. for assessment of resectability (extent of metastases, anatomic relation of lesions to critical structures), both modalities may be implemented in combination.

Evaluation of texture analysis for the differential diagnosis of focal nodular hyperplasia from hepatocellular adenoma on contrast-enhanced CT images

PURPOSE

To explore the value of CT texture analysis (CTTA) for differentiation of focal nodular hyperplasia (FNH) from hepatocellular adenoma (HCA) on contrast-enhanced CT (CECT).

METHODS

This is a retrospective, IRB-approved study conducted in a single institution. A search of the medical records between 2008 and 2017 revealed 48 patients with 70 HCA and 50 patients with 62 FNH. All lesions were histologically proven and with available pre-operative CECT imaging. Hepatic arterial phase (HAP) and portal venous phase (PVP) were used for CTTA. Textural features were extracted using a commercially available research software (TexRAD). The differences between textural parameters of FNH and HCA were assessed using the Mann-Whitney U test and the AUROC were calculated. CTTA parameters showing significant difference in rank sum test were used for binary logistic regression analysis. A p value < 0.05 was considered statistically significant.

RESULTS

On HAP images, mean, mpp, and skewness were significantly higher in FNH than in HCA on unfiltered images (p ≤ 0.007); SD, entropy, and mpp on filtered analysis (p ≤ 0.006). On PVP, mean, mpp, and skewness in FNH were significantly different from HCA (p ≤ 0.001) on unfiltered images, while entropy and kurtosis were significantly higher in FNH on filtered images (p ≤ 0.018). The multivariate logistic regression analysis indicated that the mean, mpp, and entropy of medium-level and coarse-level filtered images on HAP were independent predictors for the diagnosis of HCA and a model based on all these parameters showed the largest AUROC (0.824).

CONCLUSIONS

Multiple explored CTTA parameters are significantly different between FNH and HCA on CECT.

Texture analysis of myocardial infarction in CT: Comparison with visual analysis and impact of iterative reconstruction

OBJECTIVES

To compare texture analysis (TA) with subjective visual diagnosis of myocardial infarction (MI) in cardiac computed tomography (CT) and to evaluate the impact of iterative reconstruction (IR).

METHODS

Ten patients (4 women, mean age 68 ± 11 years) with confirmed chronic MI and 20 controls (8 women, mean age 52 ± 11 years) with no cardiac abnormality underwent contrast-enhanced cardiac CT with the same protocol. Images were reconstructed with filtered back projection (FBP) and with advanced modeled IR at strength levels 3-5. Subjective diagnosis of MI was made by three independent, blinded readers with different experience levels. Classification of MI was performed using machine learning-based decision tree models for the entire data set and after splitting into training and test data to avoid overfitting.

RESULTS

Subjective visual analysis for diagnosis of MI showed excellent intrareader (kappa: 0.93) but poor interreader agreement (kappa: 0.3), with variable performance at different image reconstructions. TA showed high performance for all image reconstructions (correct classifications: 94%-97%, areas under the curve: 0.94-0.99). After splitting into training and test data, overall lower performances were observed, with best results for IR at level 5 (correct classifications: 73%, area under the curve: 0.65).

CONCLUSIONS

As compared with subjective, nonreliable visual analysis of inexperienced readers, TA enables objective and reproducible diagnosis of chronic MI in cardiac CT with higher accuracy. IR has a considerable impact on both subjective and objective image analysis.

Whole-volume vs. segmental CT texture analysis of the liver to assess metachronous colorectal liver metastases

PURPOSE

It is unclear whether changes in liver texture in patients with colorectal cancer are caused by diffuse (e.g., perfusional) changes throughout the liver or rather based on focal changes (e.g., presence of occult metastases). The aim of this study is to compare a whole-liver approach to a segmental (Couinaud) approach for measuring the CT texture at the time of primary staging in patients who later develop metachronous metastases and evaluate whether assessing CT texture on a segmental level is of added benefit.

METHODS

46 Patients were included: 27 patients without metastases (follow-up >2 years) and 19 patients who developed metachronous metastases within 24 months after diagnosis. Volumes of interest covering the whole liver were drawn on primary staging portal-phase CT. In addition, each liver segment was delineated separately. Mean gray-level intensity, entropy (E), and uniformity (U) were derived with different filters (σ0.5-2.5). Patients/segments without metastases and patients/segments that later developed metachronous metastases were compared using independent samples t tests.

RESULTS

Absolute differences in entropy and uniformity between the group without metastases and the group with metachronous metastases group were consistently smaller for the segmental approach compared to the whole-liver approach. No statistically significant differences were found in the texture measurements between both groups.

CONCLUSIONS

In this small patient cohort, we could not demonstrate a clear predictive value to identify patients at risk of developing metachronous metastases within 2 years. Segmental CT texture analysis of the liver probably has no additional benefit over whole-liver texture analysis.