MRI features and texture analysis for the early prediction of therapeutic response to neoadjuvant chemoradiotherapy and tumor recurrence of locally advanced rectal cancer. Eur Radiol. 2020;30:4201-4211. [PMID: 32270317 DOI: 10.1007/s00330-020-06835-4]

Machine learning-based response assessment in patients with rectal cancer after neoadjuvant chemoradiotherapy: radiomics analysis for assessing tumor regression grade using T2-weighted magnetic resonance images

PURPOSE

This study aimed to assess tumor regression grade (TRG) in patients with rectal cancer after neoadjuvant chemoradiotherapy (NCRT) through a machine learning-based radiomics analysis using baseline T2-weighted magnetic resonance (MR) images.

MATERIALS AND METHODS

In total, 148 patients with locally advanced rectal cancer(T2-4 or N+) who underwent MR imaging at baseline and after chemoradiotherapy between January 2010 and May 2021 were included. A region of interest for each tumor mass was drawn by a radiologist on oblique axial T2-weighted images, and main features were selected using principal component analysis after dimension reduction among 116 radiomics and three clinical features. Among eight learning models that were used for prediction model development, the model showing best performance was selected. Treatment responses were classified as either good or poor based on the MR-assessed TRG (mrTRG) and pathologic TRG (pTRG). The model performance was assessed using the area under the receiver operating curve (AUROC) to classify the response group.

RESULTS

Approximately 49% of the patients were in the good response (GR) group based on mrTRG (73/148) and 26.9% based on pTRG (28/104). The AUCs of clinical data, radiomics models, and combined radiomics with clinical data model for predicting mrTRG were 0.80 (95% confidence interval [CI] 0.73, 0.87), 0.74 (95% CI 0.66, 0.81), and 0.75(95% CI 0.68, 0.82), and those for predicting pTRG was 0.62 (95% CI 0.52, 0.71), 0.74 (95% CI 0.65, 0.82), and 0.79 (95% CI 0.71, 0.87).

CONCLUSION

Radiomics combined with clinical data model using baseline T2-weighted MR images demonstrated feasible diagnostic performance in predicting both MR-assessed and pathologic treatment response in patients with rectal cancer after NCRT.

Non-contrast-enhanced magnetic resonance urography for measuring split kidney function in pediatric patients with hydronephrosis: comparison with renal scintigraphy

BACKGROUND

Split kidney function (SKF) is critical for treatment decision in pediatric patients with hydronephrosis and is commonly measured using renal scintigraphy (RS). Non-contrast-enhanced magnetic resonance urography (NCE-MRU) is increasingly used in clinical practice. This study aimed to investigate the feasibility of using NCE-MRU as an alternative to estimate SKF in pediatric patients with hydronephrosis, compared to RS.

METHODS

Seventy-five pediatric patients with hydronephrosis were included in this retrospective study. All patients underwent NCE-MRU and RS within 2 weeks. Kidney parenchyma volume (KPV) and texture analysis parameters were obtained from T2-weighted (T2WI) in NCE-MRU. The calculated split KPV (SKPV) percent and texture analysis parameters percent of left kidney were compared with the RS-determined SKF.

RESULTS

SKPV showed a significant positive correlation with SKF (r = 0.88, p < 0.001), while inhomogeneity was negatively correlated with SKF (r =  - 0.68, p < 0.001). The uncorrected and corrected prediction models of SKF were established using simple and multiple linear regression. Bland-Altman plots demonstrated good agreement of both predictive models. The residual sum of squares of the corrected prediction model was lower than that of the uncorrected model (0.283 vs. 0.314) but not statistically significant (p = 0.662). Subgroup analysis based on different MR machines showed correlation coefficients of 0.85, 0.95, and 0.94 between SKF and SKPV for three different scanners, respectively (p < 0.05 for all).

CONCLUSIONS

NCE-MRU can be used as an alternative method for estimating SKF in pediatric patients with hydronephrosis when comparing with RS. Specifically, SKPV proves to be a simple and universally applicable indicator for predicting SKF.

Improved Cervical Lymph Node Characterization among Patients with Head and Neck Squamous Cell Carcinoma Using MR Texture Analysis Compared to Traditional FDG-PET/MR Features Alone

Accurate differentiation of benign and malignant cervical lymph nodes is important for prognosis and treatment planning in patients with head and neck squamous cell carcinoma. We evaluated the diagnostic performance of magnetic resonance image (MRI) texture analysis and traditional 18F-deoxyglucose positron emission tomography (FDG-PET) features. This retrospective study included 21 patients with head and neck squamous cell carcinoma. We used texture analysis of MRI and FDG-PET features to evaluate 109 histologically confirmed cervical lymph nodes (41 metastatic, 68 benign). Predictive models were evaluated using area under the curve (AUC). Significant differences were observed between benign and malignant cervical lymph nodes for 36 of 41 texture features (p < 0.05). A combination of 22 MRI texture features discriminated benign and malignant nodal disease with AUC, sensitivity, and specificity of 0.952, 92.7%, and 86.7%, which was comparable to maximum short-axis diameter, lymph node morphology, and maximum standard uptake value (SUVmax). The addition of MRI texture features to traditional FDG-PET features differentiated these groups with the greatest AUC, sensitivity, and specificity (0.989, 97.5%, and 94.1%). The addition of the MRI texture feature to lymph node morphology improved nodal assessment specificity from 70.6% to 88.2% among FDG-PET indeterminate lymph nodes. Texture features are useful for differentiating benign and malignant cervical lymph nodes in patients with head and neck squamous cell carcinoma. Lymph node morphology and SUVmax remain accurate tools. Specificity is improved by the addition of MRI texture features among FDG-PET indeterminate lymph nodes. This approach is useful for differentiating benign and malignant cervical lymph nodes.

Radiomics and Machine Learning for prediction of two-year disease-specific mortality and KRAS mutation status in metastatic colorectal cancer

PURPOSE

Colorectal cancer is usually accompanied by liver metastases. The prediction of patient evolution is essential for the choice of the appropriate therapy. The aim of this study is to develop and evaluate machine learning models to predict KRAS gene mutations and 2-year disease-specific mortality from medical images.

METHODS

Clinical and follow-up information was collected from patients with metastatic colorectal cancer who had undergone computed tomography prior to liver resection. The dominant liver lesion was segmented in each scan and radiomic features were extracted from the volumes of interest. The 65% of the cases were employed to perform feature selection and to train machine learning algorithms through cross-validation. The best performing models were assembled and evaluated in the remaining cases of the cohort.

RESULTS

For the mortality model development, 101 cases were used as training set (64 alive, 37 deceased) and 35 as test set (22 alive, 13 deceased); while for KRAS mutation models, 55 cases were used for training (31 wild-type, 24 mutated) and 30 for testing (17 wild-type, 13 mutated). The ensemble of top performing models resulted in an area under the receiver operating characteristic curve of 0.878 for mortality and 0.905 for KRAS prediction.

CONCLUSIONS

Predicting the prognosis of patients with metastatic colorectal cancer is useful for making timely decisions about the best treatment options. This study presents a noninvasive method based on quantitative analysis of baseline images to identify factors influencing patient outcomes, with the aim of incorporating these tools as support systems.

Infliximab response associates with radiologic findings in bio-naïve Crohn's disease

OBJECTIVES

Since a reliable model for predicting infliximab (IFX) benefits in bio-naïve Crohn's disease (CD) is still lacking, we constructed a magnetic resonance enterography (MRE)-based model to predict the risk of loss of response to IFX in bio-naïve patients with CD.

METHODS

This retrospective multicenter study enrolled 188 bio-naïve patients with CD who underwent MRE before IFX therapy. Therapeutic outcomes were determined based on clinical symptoms and endoscopic findings within 52 weeks. The areas of bowel wall segmentation were decided by two experienced radiologists in consensus. Texture features were extracted using the least absolute shrinkage and selection operator, and a radiomic model was built using multivariate logistic regression. The model performance was validated by receiver operating characteristic, calibration curve, and decision curve analysis.

RESULTS

The area under the curve of radiomic model was 0.88 (95% confidence interval: 0.82-0.95), and the model provided clinical net benefit in identifying the loss of response to IFX and exhibited remarkable robustness among centers, scanners, and disease characteristics. The high-risk patients defined by the radiomic model were more likely to develop IFX nonresponse than low-risk patients (all p < 0.05).

CONCLUSIONS

This novel pretreatment MRE-based model could act as an effective tool for the early estimation of loss of response to IFX in bio-naïve patients with CD.

KEY POINTS

• Magnetic resonance enterography model guides infliximab therapy in Crohn's disease. • The model presented significant discrimination and provided net clinical benefit. • Model divided patients into low- and high-risk groups for infliximab failure.

Risk factors for the recurrence of cervical cancer using MR-based T1 mapping: A pilot study

Objectives

This study aimed to identify risk factors for recurrence in patients with cervical cancer (CC) through quantitative T1 mapping.

Methods

A cohort of 107 patients histopathologically diagnosed with CC at our institution between May 2018 and April 2021 was categorized into surgical and non-surgical groups. Patients in each group were further divided into recurrence and non-recurrence subgroups depending on whether they showed recurrence or metastasis within 3 years of treatment. The longitudinal relaxation time (native T1) and apparent diffusion coefficient (ADC) value of the tumor were calculated. The differences between native T1 and ADC values of the recurrence and non-recurrence subgroups were analyzed, and receiver operating characteristic (ROC) curves were drawn for parameters with statistical differences. Logistic regression was performed for analysis of significant factors affecting CC recurrence. Recurrence-free survival rates were estimated by Kaplan–Meier analysis and compared using the log-rank test.

Results

Thirteen and 10 patients in the surgical and non-surgical groups, respectively, showed recurrence after treatment. There were significant differences in native T1 values between the recurrence and non-recurrence subgroups in the surgical and non-surgical groups (P&lt;0.05); however, there was no difference in ADC values (P&gt;0.05). The areas under the ROC curve of native T1 values for discriminating recurrence of CC after surgical and non-surgical treatment were 0.742 and 0.780, respectively. Logistic regression analysis indicated that native T1 values were risk factors for tumor recurrence in the surgical and non-surgical groups (P=0.004 and 0.040, respectively). Compared with cut-offs, recurrence-free survival curves of patients with higher native T1 values of the two groups were significantly different from those with lower ones (P=0.000 and 0.016, respectively).

Conclusion

Quantitative T1 mapping could help identify CC patients with a high risk of recurrence, supplementing information on tumor prognosis other than clinicopathological features and providing the basis for individualized treatment and follow-up schemes.

Post-Surgical Imaging Assessment in Rectal Cancer: Normal Findings and Complications

Rectal cancer (RC) is one of the deadliest malignancies worldwide. Surgery is the most common treatment for RC, performed in 63.2% of patients. The type of surgical approach chosen aims to achieve maximum residual function with the lowest risk of recurrence. The selection is made by a multidisciplinary team that assesses the characteristics of the patient and the tumor. Total mesorectal excision (TME), including both low anterior resection (LAR) and abdominoperineal resection (APR), is still the standard of care for RC. Radical surgery is burdened by a 31% rate of major complications (Clavien-Dindo grade 3-4), such as anastomotic leaks and a risk of a permanent stoma. In recent years, less-invasive techniques, such as local excision, have been tested. These additional procedures could mitigate the morbidity of rectal resection, while providing acceptable oncologic results. The "watch and wait" approach is not a globally accepted model of care but encouraging results on selected groups of patients make it a promising strategy. In this plethora of treatments, the radiologist is called upon to distinguish a physiological from a pathological postoperative finding. The aim of this narrative review is to identify the main post-surgical complications and the most effective imaging techniques.

Value of pre-treatment 18F-FDG PET/CT radiomics in predicting the prognosis of stage III-IV colorectal cancer

Background and purpose

To investigate the value of radiomics features extracted from pre-treatment ¹⁸F-FDG PET/CT in predicting the outcomes of stage III-IV colorectal cancer (CRC), which may assist in clinical management strategies and precise treatment of stage III-IV CRC.

Materials and methods

124 patients with pathologically confirmed stage III-IV CRC who underwent pre-treatment ¹⁸F-FDG PET/CT scans were enrolled in this study. The least absolute shrinkage and selection operator Cox regression (LASSO-Cox) was used to select radiomics features, and the radiomics scores (Rad-scores) were calculated to build radiomics models. The performance of radiomics models was represented by the concordance index (C-index) and compared with clinical models and complex model. The bootstrap resampling method was used to create validation sets. Additionally, nomograms were developed based on complex models.

Results

The C-indices of the radiomics model for predicting PFS and OS were 0.712 (95%CI: 0.680-0.744) and 0.758 (0.728-0.789), respectively. In the clinical model, these values were 0.690 (0.664-0.0.717) and 0.738 (0.709-0.767), respectively. However, in the complex model were 0.734 (0.705-0.762) and 0.780 (0.754-0.807), respectively. The Kaplan-Meier curves demonstrated that the radiomics model could effectively separate patients with stage III-IV stage CRC into high- and low-risk groups (p < 0.001). Multivariate Cox regression analysis confirmed the independent prognostic value of Rad-scores.

Conclusion

Pre-treatment ¹⁸F-FDG PET/CT radiomics features can stratify the risk of patients with stage III-IV CRC and accurately predict their outcomes. These findings could be clinically valuable for precision treatment and management decisions in stage III-IV CRC.

Exploratory analysis of radiomic as prognostic biomarkers in 18F-FDG PET/CT scan in uterine cervical cancer

Objective

To evaluate the performance of 18F-fluorodeoxyglucose positron emission tomography (¹⁸F-FDG PET/CT) radiomic features to predict overall survival (OS) in patients with locally advanced uterine cervical carcinoma.

Methods

Longitudinal and retrospective study that evaluated 50 patients with cervical epidermoid carcinoma (clinical stage IB2 to IVA according to FIGO). Segmentation of the 18F-FDG PET/CT tumors was performed using the LIFEx software, generating the radiomic features. We used the Mann-Whitney test to select radiomic features associated with the clinical outcome (death), excluding the features highly correlated with each other with Spearman correlation. Subsequently, ROC curves and a Kaplan-Meier analysis were performed. A p-value < 0.05 were considered significant.

Results

The median follow-up was 23.5 months and longer than 24 months in all surviving patients. Independent predictors for OS were found-SUVpeak with an AUC of 0.74, sensitivity of 77.8%, and specificity of 72.7% (p = 0.006); and the textural feature gray-level run-length matrix GLRLM_LRLGE, with AUC of 0.74, sensitivity of 72.2%, and specificity of 81.8% (p = 0.005). When we used the derived cut-off points from these ROC curves (12.76 for SUVpeak and 0.001 for GLRLM_LRLGE) in a Kaplan-Meier analysis, we can see two different groups (one with an overall survival probability of approximately 90% and the other with 30%). These biomarkers are independent of FIGO staging.

Conclusion

By radiomic ¹⁸F-FDG PET/CT data analysis, SUVpeak and GLRLM_LRLGE textural feature presented the best performance to predict OS in patients with cervical cancer undergoing chemo-radiotherapy and brachytherapy.

Textural Analysis as a Predictive Biomarker in Rectal Cancer

Colorectal cancer (CRC) is a common deadly cancer. Early detection and accurate staging of CRC enhance good prognosis and better treatment outcomes. Rectal cancer staging is the cornerstone for selecting the best treatment approach. The standard gold method for rectal cancer staging is pelvic MRI. After staging, combining surgery and chemoradiation is the standard management aiming for a curative outcome. Textural analysis (TA) is a radiomic process that quantifies lesions' heterogenicity by measuring pixel distribution in digital imaging. MRI textural analysis (MRTA) of rectal cancer images is growing in current literature as a future predictor of outcomes of rectal cancer management, such as pathological response to neoadjuvant chemoradiotherapy (NCRT), survival, and tumour recurrence. MRTA techniques could validate alternative approaches in rectal cancer treatment, such as the wait-and-watch (W&W) approach in pathologically complete responders (pCR) following NCRT. We consider this a significant step towards implementing precision management in rectal cancer. In this narrative review, we summarize the current knowledge regarding the potential role of TA in rectal cancer management in predicting the prognosis and clinical outcomes, as well as aim to delineate the challenges which obstruct the implementing of this new modality in clinical practice.

Application of Radiomics in Predicting Treatment Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer: Strategies and Challenges

Neoadjuvant chemoradiotherapy (nCRT) followed by total mesorectal excision is the standard treatment for locally advanced rectal cancer (LARC). A noninvasive preoperative prediction method should greatly assist in the evaluation of response to nCRT and for the development of a personalized strategy for patients with LARC. Assessment of nCRT relies on imaging and radiomics can extract valuable quantitative data from medical images. In this review, we examined the status of radiomic application for assessing response to nCRT in patients with LARC and indicated a potential direction for future research.

Value of texture analysis based on dynamic contrast-enhanced magnetic resonance imaging in preoperative assessment of extramural venous invasion in rectal cancer

Objective

Accurate preoperative assessment of extramural vascular invasion (EMVI) is critical for the treatment and prognosis of rectal cancer. The aim of our research was to develop an assessment model by texture analysis for preoperative prediction of EMVI.

Materials and methods

This study enrolled 44 rectal patients as train cohort, 7 patients as validation cohort and 18 patients as test cohort. A total of 236 texture features from DCE MR imaging quantitative parameters were extracted for each patient (59 features of Ktrans, Kep, Ve and Vp), and key features were selected by least absolute shrinkage and selection operator regression (LASSO). Finally, clinical independent risk factors, conventional MRI assessment, and T-score were incorporated to construct an assessment model using multivariable logistic regression.

Results

The T-score calculated using the 4 selected key features were significantly correlated with EMVI (p < 0.010). The area under the receiver operating characteristic curve (AUC) was 0.797 for discriminating between EMVI-positive and EMVI-negative patients with a sensitivity of 88.2% and specificity of 70.4%. The conventional MRI assessment of EMVI had a sensitivity of 23.53% and a specificity of 96.30%. The assessment model showed a greatly improved performance with an AUC of 0.954 (sensitivity, 88.2%; specificity, 92.6%) in train cohort, 0.833 (sensitivity, 66.7%; specificity, 100%) in validation cohort and 0.877 in test cohort, respectively.

Conclusions

The assessment model showed an excellent performance in preoperative assessment of EMVI. It demonstrates strong potential for improving the accuracy of EMVI assessment and provide a reliable basis for individualized treatment decisions.

Application of preoperative CT texture analysis in papillary gastric adenocarcinoma

Background

This study aimed to analyze the ability of computed tomography (CT) texture analysis to discriminate papillary gastric adenocarcinoma (PGC) and to explore the diagnostic efficacy of multivariate models integrating clinical information and CT texture parameters for discriminating PGCs.

Methods

This retrospective study included 20 patients with PGC and 80 patients with tubular adenocarcinoma (TAC). The clinical data and CT texture parameters based on the arterial phase (AP) and venous phase (VP) of all patients were collected and analyzed. Two CT signatures based on the AP and VP were built with the optimum features selected by the least absolute shrinkage and selection operator method. The performance of CT signatures was tested by regression analysis. Multivariate models based on regression analysis and the support vector machine (SVM) algorithm were established. The diagnostic performance of the established nomogram based on regression analysis was evaluated by receiver operating characteristic curve analysis.

Results

Thirty-two and fifteen CT texture parameters extracted from AP and VP CT images, respectively, differed significantly between PGCs and TACs (all p < 0.05). The diagnostic performance of CT signatures based on the AP and VP achieved AUCs of 0.873 and 0.859 in distinguishing PGCs. Multivariate models that integrated two CT signatures and age based on regression analysis and the SVM algorithm showed favorable performance in preoperatively predicting PGCs (AUC = 0.922 and 0.914, respectively).

Conclusion

CT texture analysis based multivariate models could preoperatively predict PGCs with satisfactory diagnostic efficacy.

Treatment planning computed tomography radiomics for predicting treatment outcomes and haematological toxicities in locally advanced cervical cancer treated with radiotherapy: A retrospective cohort study

OBJECTIVE

We evaluated whether radiomic features extracted from planning computed tomography (CT) scans predict clinical end points in patients with locally advanced cervical cancer (LACC) undergoing intensity-modulated radiation therapy and brachytherapy.

DESIGN

A retrospective cohort study.

SETTING

Xiangya Hospital of Central South University, Changsha, Hunan, China.

POPULATION

Two hundred and fifty-seven LACC patients who were treated with intensity-modulated radiotherapy from 2014 to 2017.

METHODS

Patients were allocated into the training/validation sets (3:1 ratio) using proportional random sampling, resulting in the same proportion of groups in the two sets. We extracted 254 radiomic features from each of the gross target volume, pelvis and sacral vertebrae. The sequentially backward elimination support vector machine algorithm was used for feature selection and end point prediction.

MAIN OUTCOMES AND MEASURES

Clinical end points include tumour complete response (CR), 5-year overall survival (OS), anaemia, and leucopenia.

RESULTS

A combination of ten clinicopathological parameters and 34 radiomic features performed best for predicting CR (validation balanced accuracy: 80.8%). The validation balanced accuracy of 54 radiomic features was 85.8% for OS, and their scores can stratify patients into the low-risk and high-risk groups (5-year OS: 95.5% versus 36.4%, p < 0.001). The clinical and radiomic models were also predictive of anaemia and leucopenia (validation balanced accuracies: 71.0% and 69.9%).

CONCLUSION

This study demonstrated that combining clinicopathological parameters with CT-based radiomics may have value for predicting clinical end points in LACC. If validated, this model may guide therapeutic strategy to optimise the effectiveness and minimise toxicity or treatment for LACC.

Radiomics for Detection of the EGFR Mutation in Liver Metastatic NSCLC

RATIONALE AND OBJECTIVES

The research aims to investigate whether MRI radiomics on hepatic metastasis from primary nonsmall cell lung cancer (NSCLC) can be used to differentiate patients with epidermal growth factor receptor (EGFR) mutations from those with EGFR wild-type, and develop a prediction model based on combination of primary tumor and the metastasis.

MATERIALS AND METHODS

A total of 130 patients were enrolled between Aug. 2017 and Dec. 2021, all pathologically confirmed harboring hepatic metastasis from primary NSCLC. The pyradiomics was used to extract radiomics features from intra- and peritumoral areas of both primary tumor and metastasis. The least absolute shrinkage and selection operator (LASSO) regression was applied to identify most predictive features and to develop radiomics signatures (RSs) for prediction of the EGFR mutation status. The receiver operating characteristic (ROC) curve analysis was performed to assess the prediction capability of the developed RSs.

RESULTS

A RS-Primary and a RS-Metastasis were derived from the primary tumor and metastasis, respectively. The RS-Combine by combination of the primary tumor and metastasis achieved the highest prediction performance in the training (AUCs, RS-Primary vs. RS-Metastasis vs. RS-Combine, 0.826 vs. 0.821 vs. 0.908) and testing (AUCs, RS-Primary vs. RS-Metastasis vs. RS-Combine, 0.760 vs. 0.791 vs. 0.884) set. The smoking status showed significant difference between EGFR mutant and wild-type groups (p < 0.05) in the training set.

CONCLUSION

The study indicates that hepatic metastasis-based radiomics can be used to detect the EGFR mutation. The developed multiorgan combined radiomics signature may be helpful to guide individual treatment strategies for patients with metastatic NSCLC.

Combining Clinicopathology, IVIM-DWI and Texture Parameters for a Nomogram to Predict Treatment Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer Patients

Objectives

This study aimed to create a nomogram for the risk prediction of neoadjuvant chemoradiotherapy (nCRT) resistance in locally advanced rectal cancer (LARC).

Methods

Clinical data in this retrospective study were collected from a total of 135 LARC patients admitted to our hospital from June 2016 to December 2020. After screening by inclusion and exclusion criteria, 62 patients were included in the study. Texture analysis (TA) was performed on T2WI and DWI images. Patients were divided into response group (CR+PR) and no-response group (SD+PD) according to efficacy assessment. Multivariate analysis was performed on clinicopathology, IVIM-DWI and texture parameters for screening of independent predictors. A nomogram was created and model fit and clinical net benefit were assessed.

Results

Multivariate analysis of clinicopathology parameters showed that the differentiation and T stage were independent predictors (OR values were 14.516 and 11.589, resp.; P<0.05). Multivariate analysis of IVIM-DWI and texture parameters showed that f value and Rads-score were independent predictors (OR values were 0.855, 2.790, resp.; P<0.05). In this study, clinicopathology together with IVIM-DWI and texture parameters showed the best predictive efficacy (AUC=0.979). The nomogram showed good predictive performance and stability in identifying high-risk LARC patients who are resistant to nCRT (C-index=0.979). Decision curve analyses showed that the nomogram had the best clinical net benefit. Ten-fold cross-validation results showed that the average AUC value was 0.967, and the average C-index was 0.966.

Conclusions

The nomogram combining the differentiation, T stage, f value and Rads-score can effectively estimate the risk of nCRT resistance in patients with LARC.

Interobserver variability in MRI measurements of mesorectal invasion depth in rectal cancer

PROPOSE

To assess the interobserver variability in MRI measurements of mesorectal invasion depth (MID) in rectal adenocarcinomas primarily staged as T3, by determining the level of interobserver agreement in the differentiation of individual T3 substages and of T3a-b vs. T3c-d disease, between readers with different levels of expertise.

METHODS

A retrospective analysis of 60 patients classified by MRI as having T3 rectal cancers was performed. Each patient underwent MR examination in a 1.5 T machine and the standard imaging protocol included a high-resolution axial T2-weighted sequence in which the measurements were determined by independent radiologists (readers A and B, with 15 years and 1 year of experience, respectively). The rectum was further divided into quadrants and each reader selected the quadrant where the measurement was taken. The patients were grouped according to the MID (T3a < 1 mm; T3b 1-5 mm; T3c > 5-15 mm; T3d > 15 mm) and the interobserver reliability was tested using Cohen's kappa.

RESULTS

Population included 40 males and 20 females with a median age of 65.9 years. Interobserver agreement on individual substage differentiation (T3 a, b, c and d) was moderate (K = 0.428) and in the quadrant evaluation the level of agreement was also moderate (K = 0.414). Nevertheless, the interobserver reliability for the differentiation between stages T3a-b vs. T3c-d was substantial (K = 0.697).

CONCLUSIONS

There is no considerable interobserver variability when distinguishing T3a-b from T3c-d tumors, regardless of the quadrant where the MID is measured. Therefore, assessment of MID, for that purpose, is a reproducible MR parameter, irrespectively of the readers' experience.

The feasibility of MRI-based radiomics model in presurgical evaluation of tumor budding in locally advanced rectal cancer

PURPOSE

To build and validate a magnetic resonance imaging-based radiomics model to preoperatively evaluate tumor budding (TB) in locally advanced rectal cancer (LARC).

METHODS

Pathologically confirmed LARC cases submitted to preoperative rectal MRI in two distinct hospitals were enrolled in this retrospective study and assigned to cohort 1 (training set, n = 77; test set, n = 51) and cohort 2 (validation set, n = 96). Radiomics features were obtained from multiple sequences, comprising high-resolution T2, contrast-enhanced T1, and diffusion-weighted imaging (T2WI, CE-T1WI, and DWI, respectively). The least absolute shrinkage and selection operator (LASSO) was utilized to select the optimal features from T2WI, CE-T1WI, DWI, and the combination of multi-sequences, respectively. A support vector machine (SVM) classifier was utilized to construct various radiomics models for discriminating the TB grades. Receiver operating characteristic curve analysis and decision curve analysis (DCA) were carried out to determine the diagnostic value.

RESULTS

Five optimal features associated with TB grade were determined from combined multi-sequence data. Accordingly, a radiomics model based on combined multi-sequences had an area under the curve of 0.796, with an accuracy of 81.2% in the validation set, showing a better performance in comparison with other models in both cohorts (p < 0.05). DCA exhibited a clinical benefit for this radiomics model.

CONCLUSION

The novel MRI-based radiomics model combining multiple sequences is an effective and non-invasive approach for evaluating TB grade preoperatively in patients with LARC.

Predicting pathologic complete response in locally advanced rectal cancer patients after neoadjuvant therapy: a machine learning model using XGBoost

PURPOSE

Watch and wait strategy is a safe and effective alternative to surgery in patients with locally advanced rectal cancer (LARC) who have achieved pathological complete response (pCR) after neoadjuvant therapy (NAT); present restaging methods do not meet clinical needs. This study aimed to construct a machine learning (ML) model to predict pCR preoperatively.

METHODS

LARC patients who received NAT were included to generate an extreme gradient boosting-based ML model to predict pCR. The group was divided into a training set and a tuning set at a 7:3 ratio. The SHapley Additive exPlanations value was used to quantify feature importance. The ML model was compared with a nomogram model developed using independent risk factors identified by conventional multivariate logistic regression analysis.

RESULTS

Compared with the nomogram model, our ML model improved the area under the receiver operating characteristics from 0.72 to 0.95, sensitivity from 43 to 82.2%, and specificity from 87.1 to 91.6% in the training set, the same trend applied to the tuning set. Neoadjuvant radiotherapy, preoperative carbohydrate antigen 125 (CA125), CA199, carcinoembryonic antigen level, and depth of tumor invasion were significant in predicting pCR in both models.

CONCLUSION

Our ML model is a potential alternative to the existing assessment tools to conduct triage treatment for patients and provides reference for clinicians in tailoring individual treatment: the watch and wait strategy is used to avoid surgical trauma in pCR patients, and non-pCR patients receive surgical treatment to avoid missing the optimal operation time window.

Multiparametric MRI-based Radiomics approaches on predicting response to neoadjuvant chemoradiotherapy (nCRT) in patients with rectal cancer

PURPOSE

To investigate the value of multiparametric MRI-based radiomics on predicting response to nCRT in patients with rectal cancer.

METHODS

This study enrolled 193 patients with pathologically confirmed LARC who received nCRT treatment between Apr. 2014 and Jun. 2018. All patients underwent baseline T1-weighted (T1W), T2-weighted (T2W) and T2-weighted fat-suppression (T2FS) MRI scans before neoadjuvant chemoradiotherapy. Radiomics features were extracted and selected from the MRI data to establish the radiomics signature. Important clinical predictors were identified by Mann-Whitney U test and Chi-square test. The nomogram integrating the radiomics signature and important clinical predictors was constructed using multivariate logistic regression. Prediction capabilities of each model were assessed with receiver operating characteristic (ROC) curve analysis. Performance of the nomogram was evaluated by its calibration and potential clinical usefulness.

RESULTS

For the prediction of good response (GR) and pathologic complete response (pCR), the developed radiomics signature comprising 10 and 7 features, respectively, were significantly associated with the therapeutic response to nCRT. The nomogram incorporating the radiomics signature and important clinical predictors (CEA and CA19-9 for predicting GR; CEA, posttreatment length and posttreatment thickness for predicting pCR) achieved favorable prediction efficacy, with AUCs of 0.918 (95% confidence interval [CI]: 0.867-0.971, Sen = 0.972, Spe = 0.828) and 0.944 (95% CI: 0.891-0.997, Sen = 0.943, Spe = 0.828) in the training and validation cohort for predicting GR, respectively; with AUCs of 0.959 (95% CI: 0.927-0.991, Sen = 1.000, Spe = 0.833) and 0.912 (95% CI: 0.843-0.982, Sen = 1.000, Spe = 0.815) in the training and validation cohort for predicting pCR, respectively. Decision curve analysis confirmed potential clinical usefulness of our nomogram.

CONCLUSIONS

This study demonstrated that the MRI-based radiomics nomogram is predictive of response to nCRT and can be considered as a promising tool for facilitating treatment decision-making for patients with LARC.

MRI-Based Grading of Clear Cell Renal Cell Carcinoma Using a Machine Learning Classifier

Objective

To develop a machine learning (ML)-based classifier for discriminating between low-grade (ISUP I-II) and high-grade (ISUP III-IV) clear cell renal cell carcinomas (ccRCCs) using MRI textures.

Materials and Methods

We retrospectively evaluated a total of 99 patients (with 61 low-grade and 38 high-grade ccRCCs), who were randomly divided into a training set (n = 70) and a validation set (n = 29). Regions of interest (ROIs) of all tumors were manually drawn three times by a radiologist at the maximum lesion level of the cross-sectional CMP sequence images. The quantitative texture analysis software, MaZda, was used to extract texture features, including histograms, co-occurrence matrixes, run-length matrixes, gradient models, and autoregressive models. Reproducibility of the texture features was assessed with the intra-class correlation coefficient (ICC). Features were chosen based on their importance coefficients in a random forest model, while the multi-layer perceptron algorithm was used to build a classifier on the training set, which was later evaluated with the validation set.

Results

The ICCs of 257 texture features were equal to or higher than 0.80 (0.828–0.998. Six features, namely Kurtosis, 135dr_RLNonUni, Horzl_GLevNonU, 135dr_GLevNonU, S(4,4)Entropy, and S(0,5)SumEntrp, were chosen to develop the multi-layer perceptron classifier. A three-layer perceptron model, which has 229 nodes in the hidden layer, was trained on the training set. The accuracy of the model was 95.7% with the training set and 86.2% with the validation set. The areas under the receiver operating curves were 0.997 and 0.758 for the training and validation sets, respectively.

Conclusions

A machine learning-based grading model was developed that can aid in the clinical diagnosis of clear cell renal cell carcinoma using MRI images.

Textural differences based on apparent diffusion coefficient maps for discriminating pT3 subclasses of rectal adenocarcinoma

BACKGROUND

The accuracy of discriminating pT3a from pT3b-c rectal cancer using high-resolution magnetic resonance imaging (MRI) remains unsatisfactory, although texture analysis (TA) could improve such discrimination.

AIM

To investigate the value of TA on apparent diffusion coefficient (ADC) maps in differentiating pT3a rectal adenocarcinomas from pT3b-c tumors.

METHODS

This was a case-control study of 59 patients with pT3 rectal adenocarcinoma, who underwent diffusion-weighted imaging (DWI) between October 2016 and December 2018. The inclusion criteria were: (1) Proven pT3 rectal adenocarcinoma; (2) Primary MRI including high-resolution T2-weighted image (T2WI) and DWI; and (3) Availability of pathological reports for surgical specimens. The exclusion criteria were: (1) Poor image quality; (2) Preoperative chemoradiation therapy; and (3) A different pathological type. First-order (ADC values, skewness, kurtosis, and uniformity) and second-order (energy, entropy, inertia, and correlation) texture features were derived from whole-lesion ADC maps. Receiver operating characteristic curves were used to determine the diagnostic value for pT3b-c tumors.

RESULTS

The final study population consisted of 59 patients (34 men and 25 women), with a median age of 66 years (range, 41-85 years). Thirty patients had pT3a, 24 had pT3b, and five had pT3c. Among the ADC first-order textural differences between pT3a and pT3b-c rectal adenocarcinomas, only skewness was significantly lower in the pT3a tumors than in pT3b-c tumors. Among the ADC second-order textural differences, energy and entropy were significantly different between pT3a and pT3b-c rectal adenocarcinomas. For differentiating pT3a rectal adenocarcinomas from pT3b-c tumors, the areas under the curves (AUCs) of skewness, energy, and entropy were 0.686, 0.657, and 0.747, respectively. Logistic regression analysis of all three features yielded a greater AUC (0.775) in differentiating pT3a rectal adenocarcinomas from pT3b-c tumors (69.0% sensitivity and 83.3% specificity).

CONCLUSION

TA features derived from ADC maps might potentially differentiate pT3a rectal adenocarcinomas from pT3b-c tumors.

Machine learning model development for quantitative analysis of CT heterogeneity in canine hepatic masses may predict histologic malignancy

Tumor heterogeneity is a well-established marker of biologically aggressive neoplastic processes and is associated with local recurrence and distant metastasis. Quantitative analysis of CT textural features is an indirect measure of tumor heterogeneity and therefore may help predict malignant disease. The purpose of this retrospective, secondary analysis study was to quantitatively evaluate CT heterogeneity in dogs with histologically confirmed liver masses to build a predictive model for malignancy. Forty dogs with liver tumors and corresponding histopathologic evaluation from a previous prospective study were included. Triphasic image acquisition was standardized across dogs and whole liver and liver mass were contoured on each precontrast and delayed postcontrast dataset. First-order and second-order indices were extracted from contoured regions. Univariate analysis identified potentially significant indices that were subsequently used for top-down model construction. Multiple quadratic discriminatory models were constructed and tested, including individual models using both postcontrast and precontrast whole liver or liver mass volumes. The best performing model utilized the CT features voxel volume and uniformity from postcontrast mass contours; this model had an accuracy of 0.90, sensitivity of 0.67, specificity of 1.0, positive predictive value of 1.0, negative predictive value of 0.88, and precision of 1.0. Heterogeneity indices extracted from delayed postcontrast CT hepatic mass contours were more informative about tumor type compared to indices from whole liver contours, or from precontrast hepatic mass and whole liver contours. Results demonstrate that CT radiomic feature analysis may hold clinical utility as a noninvasive method of predicting hepatic malignancy and may influence diagnostic or therapeutic approaches.

Radiomics in the Setting of Neoadjuvant Radiotherapy: A New Approach for Tailored Treatment

Simple Summary

This review based on a literature search aims at showing the impact of Texture Analysis in the prediction of response to neoadjuvant radiotherapy and/or chemoradiotherapy. The manuscript explores radiomics approaches in different fields of neoadjuvant radiotherapy, including esophageal cancer, lung cancer, sarcoma and rectal cancer in order to shed a light in the setting of neoadjuvant radiotherapy that can be used to tailor the best subsequent therapeutical strategy.

Abstract

Introduction: Neoadjuvant radiotherapy is currently used mainly in locally advanced rectal cancer and sarcoma and in a subset of non-small cell lung cancer and esophageal cancer, whereas in other diseases it is under investigation. The evaluation of the efficacy of the induction strategy is made possible by performing imaging investigations before and after the neoadjuvant therapy and is usually challenging. In the last decade, texture analysis (TA) has been developed to help the radiologist to quantify and identify the parameters related to tumor heterogeneity, which cannot be appreciated by the naked eye. The aim of this narrative is to review the impact of TA on the prediction of response to neoadjuvant radiotherapy and or chemoradiotherapy. Materials and Methods: Key references were derived from a PubMed query. Hand searching and ClinicalTrials.gov were also used. Results: This paper contains a narrative report and a critical discussion of radiomics approaches in different fields of neoadjuvant radiotherapy, including esophageal cancer, lung cancer, sarcoma, and rectal cancer. Conclusions: Radiomics can shed a light on the setting of neoadjuvant therapies that can be used to tailor subsequent approaches or even to avoid surgery in the future. At the same, these results need to be validated in prospective and multicenter trials.

Contrast-enhanced CT radiomics features to predict recurrence of locally advanced oesophageal squamous cell cancer within 2 years after trimodal therapy: A case-control study

Radiomics transforms the medical images into high-dimensional quantitative features and provides potential information about tumor phenotypes and heterogeneity. We conducted a retrospective analysis to explore and validate radiomics model based on contrast-enhanced computed tomography (CECT) to predict recurrence of locally advanced oesophageal squamous cell cancer (SCC) within 2 years after trimodal therapy. This study collected CECT and clinical data of consecutive 220 patients with pathology-confirmed locally advanced oesophageal SCC (154 in the training cohort and 66 in the validation cohort). Univariate statistical test and the least absolute shrinkage and selection operator method were performed to select the optimal radiomics features. Logistic regression was conducted to build radiomics model, clinical model, and combined model of both the radiomics and clinical features. Predictive performance was judged by the area under receiver operating characteristics curve (AUC), accuracy, and F1-score in the training and validation cohorts. Ten optimal radiomics features and/or 7 clinical features were selected to build radiomics model, clinical model, and the combined model. The integrated model of radiomics and clinical features was superior to radiomics model or clinical model in predicting recurrence of locally advanced oesophageal SCC within 2 years in the training (AUC: 0.879 vs 0.815 or 0.763; accuracy: 0.844 vs 0.773 or 0.740; and F1-score: 0.886 vs 0.839 or 0.815, respectively) and validation (AUC: 0.857 vs 0.720 or 0.750; accuracy: 0.788 vs 0.700 or 0.697; and F1-score: 0.851 vs 0.800 or 0.787, respectively) cohorts. The combined model of radiomics and clinical features shows better performance than the radiomics or clinical model to predict the recurrence of locally advanced oesophageal SCC within 2 years after trimodal therapy.

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.

Predicting Treatment Response to Neoadjuvant Chemoradiotherapy in Rectal Mucinous Adenocarcinoma Using an MRI-Based Radiomics Nomogram

Objective

To build and validate an MRI-based radiomics nomogram to predict the therapeutic response to neoadjuvant chemoradiotherapy (nCRT) in rectal mucinous adenocarcinoma (RMAC).

Methods

Totally, 92 individuals with pathologically confirmed RMAC administered surgical resection upon nCRT in two different centers were assessed retrospectively (training set, n = 52, validation set, n = 40). Rectal MRI was performed pre-nCRT. Radiomics parameters were obtained from high-resolution T2-weighted images and selected to construct a radiomics signature. Then, radiomics nomogram construction integrated patient variables and the radiomics signature. The resulting radiomics nomogram was utilized to assess the tumor regression grade (TRG). Diagnostic performance was determined by generating receiver operating characteristic (ROC) curves and decision curve analysis (DCA).

Results

Six optimal features related to TRG were obtained to construct a radiomics signature. The nomogram combining the radiomics signature with age and mucin deposit outperformed the radiomics signature alone in the training (AUC, 0.950 vs 0.843, p < 0.05) and validation (AUC, 0.868 vs 0.719, p < 0.05) cohorts. DCA demonstrated a clinical utility for the radiomics nomogram model.

Conclusions

The established quantitative MRI-based radiomics nomogram is effective in predicting treatment response to neoadjuvant therapy in patients with RMAC.

Evaluating treatment response to neoadjuvant chemoradiotherapy in rectal cancer using various MRI-based radiomics models

Background

To validate and compare various MRI-based radiomics models to evaluate treatment response to neoadjuvant chemoradiotherapy (nCRT) of rectal cancer.

Methods

A total of 80 patients with locally advanced rectal cancer (LARC) who underwent surgical resection after nCRT were enrolled retrospectively. Rectal MR images were scanned pre- and post-nCRT. The radiomics features were extracted from T2-weighted images, then reduced separately by least absolute shrinkage and selection operator (LASSO) and principal component analysis (PCA). Four classifiers of Logistic Regression, Random Forest (RF), Decision Tree and K-nearest neighbor (KNN) models were constructed to assess the tumor regression grade (TRG) and pathologic complete response (pCR), respectively. The diagnostic performances of models were determined with leave-one-out cross-validation by generating receiver operating characteristic curves and decision curve analysis.

Results

Three features related to the TRG and 11 features related to the pCR were obtained by LASSO. Top five principal components representing a cumulative contribution of 80% to overall features were selected by PCA. For TRG, the area under the curve (AUC) of RF model was 0.943 for LASSO and 0.930 for PCA, higher than other models (P < 0.05 for both). As for pCR, the AUCs of KNN for LASSO and PCA were 0.945 and 0.712, higher than other models (P < 0.05 for both). The DCA showed that LASSO algorithm was clinically superior to PCA.

Conclusion

MRI-based radiomics models demonstrated good performance for evaluating the treatment response of LARC after nCRT and LASSO algorithm yielded more clinical benefit.

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.