Texture Analysis as Imaging Biomarker for recurrence in advanced cervical cancer treated with CCRT

Improving the diagnostic accuracy of small renal masses: Integration of radiomics and clear cell likelihood scores in multiparametric MRI

OBJECTIVES

Accurate diagnosis of small renal masses is crucial for treatment planning. Combining radiomics analysis with the Clear Cell Likelihood Score (ccLS) in multiparametric MRI can effectively assess malignancy risk. This study aimed to evaluate the contribution of MRI-based radiomics analysis to the diagnostic performance of the ccLS in differentiating clear cell renal carcinoma (ccRCC).

MATERIALS AND METHODS

This retrospective study included patients with cT1a renal masses who underwent preoperative MRI and nephrectomy. Radiomic features were extracted from multiparametric MRI images, including T2-weighted imaging and contrast-enhanced T1-weighted imaging sequences. Qualitative assessment was performed using the ccLS version 2.0, based on multiparametric MRI findings. The diagnostic efficacies of the ccLS, radiomic analysis, and the combination of the two methods in differentiating ccRCCs were analyzed.

RESULTS

A total of 72 small renal masses (43 ccRCC and 29 non-ccRCC) from 68 patients were evaluated. Using ccLS alone, lesions classified as ccLS ≥ 4 were identified as ccRCCs with a sensitivity of 83.3% and specificity of 73.3%. Radiomic analysis revealed significant differences between ccRCC and non-ccRCC lesions, with AUC values ranging from 0.48 to 0.87 across different features. The combined use of radiomic features and ccLS improved the differentiation of ccRCCs, achieving a sensitivity of 90.7%, specificity of 78.4%, and an AUC of 0.88. In lesions classified as ccLS 3 (equivocal), radiomic analysis alone distinguished ccRCCs with 100% sensitivity and 62.5% specificity.

CONCLUSIONS

This study's findings demonstrated that radiomics analysis successfully differentiated lesions with a ccLS 3 and that the use of radiomic analysis in combination with ccLS successfully differentiated ccRCC and non-ccRCC lesions.

A Hybrid Model-Based Clinicopathological Features and Radiomics Based on Conventional MRI for Predicting Lymph Node Metastasis and DFS in Cervical Cancer

This study aimed to improve the accuracy of the diagnosis of lymph node metastasis (LNM) and prediction of patient prognosis in cervical cancer patients using a hybrid model based on MRI and clinical aspects. We retrospectively analyzed routine MR data from 485 patients with pathologically confirmed cervical cancer from January 2014 to June 2021. The data were divided into a training cohort (N = 261), internal cohort (N = 113), and external validation cohort (n = 111). A total of 2194 features were extracted from each ROI from T2WI and CE-T1WI. The clinical model (M1) was built with clinicopathological features including squamous cell carcinoma antigen, MRI-reported LNM, maximal tumor diameter (MTD). The radiomics model (M2) was built with four radiomics features. The hybrid model (M3) was constructed with squamous cell carcinoma antigen, MRI-reported LNM, MTD which consists of M1 and four radiomics features which consist of M2. GBDT algorithms were used to create the scores of M1 (clinical-score, C-score), M2 (radiomic score, R-score), and M3 (hybrid-score, H-score). M3 showed good performance in the training cohort (AUCs, M3 vs. M1 vs. M2, 0.917 vs. 0.830 vs. 0.788), internal validation cohorts (AUCs, M3 vs. M1 vs. M2, 0.872 vs. 0.750 vs. 0.739), and external validation cohort (AUCs, M3 vs. M1 vs. M2, 0.907 vs. 0.811 vs. 0.785). In addition, higher scores were significantly associated with worse disease-free survival (DFS) in the training cohort and the internal validation cohort (C-score, P = 0.001; R-score, P = 0.002; H-score, P = 0.006). Radiomics models can accurately predict LNM status in patients with cervical cancer. The hybrid model, which incorporates clinical and radiomics features, is a novel way to enhance diagnostic performance and predict the prognosis of cervical cancer.

MRI delta radiomics during chemoradiotherapy for prognostication in locally advanced cervical cancer

BACKGROUND

Effective diagnostic tools for prompt identification of high-risk locally advanced cervical cancer (LACC) patients are needed to facilitate early, individualized treatment. The aim of this work was to assess temporal changes in tumor radiomics (delta radiomics) from T2-weighted imaging (T2WI) during concurrent chemoradiotherapy (CCRT) in LACC patients, and their association with progression-free survival (PFS). Furthermore, to develop, validate, and compare delta- and pretreatment radiomic signatures for prognostic modeling.

METHODS

A total of 110 LACC patients undergoing CCRT with MRI at baseline and mid-treatment were divided into training (cohortT: n = 73) and validation (cohortV: n = 37) cohorts. Radiomic features were extracted from tumors segmented on pre-CCRT and mid-CCRT T2WI and radiomic deltas (delta features) were computed. Two radiomic signatures for predicting PFS were constructed by least absolute shrinkage and selection operator (LASSO) Cox regression: Deltarad (from delta features) and Pre-CCRTrad (from pre-CCRT features). Prognostic performance of the radiomic signatures, 2018 International Federation of Gynecology and Obstetrics (FIGO) stage (I-IV), and baseline MRI-derived maximum tumor diameter (Tumormax: ≤2 cm; >2 and ≤ 4 cm; >4 cm) was evaluated by area under time-dependent receiver operating characteristics (tdROC) curves (AUC) in cohortT and cohortV (AUCT/AUCV). Mann-Whitney U tests assessed differences in radiomic delta features. PFS was evaluated using the Kaplan-Meier method with log-rank tests.

RESULTS

Deltarad (AUCT/AUCV: 0.74/0.79) marginally outperformed Pre-CCRTrad (0.72/0.75) for predicting 5-year PFS, and both signatures clearly surpassed that of FIGO (0.61/0.61) and Tumormax (0.58/0.65). In total, four features within Deltarad and Pre-CCRTrad significantly differed in delta feature values between progressors and non-progressors, being consistently lower in progressors (p ≤ 0.03 for all). High Deltarad and Pre-CCRTrad radiomic scores were associated with poor PFS (p ≤ 0.04 for Deltarad in cohortT/Pre-CCRTrad in both cohorts; p = 0.11 for Deltarad in cohortV).

CONCLUSIONS

Delta- and pretreatment radiomic signatures equally allow early prognostication in LACC, outperforming FIGO stage and MRI-assessed maximum tumor diameter.

Comparative Analysis of Repeatability in CT Radiomics and Dosiomics Features under Image Perturbation: A Study in Cervical Cancer Patients

This study aims to evaluate the repeatability of radiomics and dosiomics features via image perturbation of patients with cervical cancer. A total of 304 cervical cancer patients with planning CT images and dose maps were retrospectively included. Random translation, rotation, and contour randomization were applied to CT images and dose maps before radiomics feature extraction. The repeatability of radiomics and dosiomics features was assessed using intra-class correlation of coefficient (ICC). Pearson correlation coefficient (r) was adopted to quantify the correlation between the image characteristics and feature repeatability. In general, the repeatability of dosiomics features was lower compared with CT radiomics features, especially after small-sigma Laplacian-of-Gaussian (LoG) and wavelet filtering. More repeatable features (ICC > 0.9) were observed when extracted from the original, Large-sigma LoG filtered, and LLL-/LLH-wavelet filtered images. Positive correlations were found between image entropy and high-repeatable feature number in both CT and dose (r = 0.56, 0.68). Radiomics features showed higher repeatability compared to dosiomics features. These findings highlight the potential of radiomics features for robust quantitative imaging analysis in cervical cancer patients, while suggesting the need for further refinement of dosiomics approaches to enhance their repeatability.

Gynecological cancer prognosis using machine learning techniques: A systematic review of last three decades (1990–2022)

OBJECTIVE

Many Computer Aided Prognostic (CAP) systems based on machine learning techniques have been proposed in the field of oncology. The objective of this systematic review was to assess and critically appraise the methodologies and approaches used in predicting the prognosis of gynecological cancers using CAPs.

METHODS

Electronic databases were used to systematically search for studies utilizing machine learning methods in gynecological cancers. Study risk of bias (ROB) and applicability were assessed using the PROBAST tool. 139 studies met the inclusion criteria, of which 71 predicted outcomes for ovarian cancer patients, 41 predicted outcomes for cervical cancer patients, 28 predicted outcomes for uterine cancer patients, and 2 predicted outcomes for gynecological malignancies broadly.

RESULTS

Random forest (22.30 %) and support vector machine (21.58 %) classifiers were used most commonly. Use of clinicopathological, genomic and radiomic data as predictors was observed in 48.20 %, 51.08 % and 17.27 % of studies, respectively, with some studies using multiple modalities. 21.58 % of studies were externally validated. Twenty-three individual studies compared ML and non-ML methods. Study quality was highly variable and methodologies, statistical reporting and outcome measures were inconsistent, preventing generalized commentary or meta-analysis of performance outcomes.

CONCLUSION

There is significant variability in model development when prognosticating gynecological malignancies with respect to variable selection, machine learning (ML) methods and endpoint selection. This heterogeneity prevents meta-analysis and conclusions regarding the superiority of ML methods. Furthermore, PROBAST-mediated ROB and applicability analysis demonstrates concern for the translatability of existing models. This review identifies ways that this can be improved upon in future works to develop robust, clinically translatable models within this promising field.

Texture Analysis in Uterine Cervix Carcinoma: Primary Tumour and Lymph Node Assessment

The conventional magnetic resonance imaging (MRI) evaluation and staging of cervical cancer encounters several pitfalls, partially due to subjective evaluations of medical images. Fifty-six patients with histologically proven cervical malignancies (squamous cell carcinomas, n = 42; adenocarcinomas, n = 14) who underwent pre-treatment MRI examinations were retrospectively included. The lymph node status (non-metastatic lymph nodes, n = 39; metastatic lymph nodes, n = 17) was assessed using pathological and imaging findings. The texture analysis of primary tumours and lymph nodes was performed on T2-weighted images. Texture parameters with the highest ability to discriminate between the two histological types of primary tumours and metastatic and non-metastatic lymph nodes were selected based on Fisher coefficients (cut-off value > 3). The parameters' discriminative ability was tested using an k nearest neighbour (KNN) classifier, and by comparing their absolute values through an univariate and receiver operating characteristic analysis. Results: The KNN classified metastatic and non-metastatic lymph nodes with 93.75% accuracy. Ten entropy variations were able to identify metastatic lymph nodes (sensitivity: 79.17-88%; specificity: 93.48-97.83%). No parameters exceeded the cut-off value when differentiating between histopathological entities. In conclusion, texture analysis can offer a superior non-invasive characterization of lymph node status, which can improve the staging accuracy of cervical cancers.

Prognosis prediction of uterine cervical cancer using changes in the histogram and texture features of apparent diffusion coefficient during definitive chemoradiotherapy

OBJECTIVES

We investigated prospectively whether, in cervical cancer (CC) treated with concurrent chemoradiotherapy (CCRT), the Apparent diffusion coefficient (ADC) histogram and texture parameters and their change rates during treatment could predict prognosis.

METHODS

Fifty-seven CC patients treated with CCRT at our institution were included. They underwent MRI scans up to four times during the treatment course (1st, before treatment [n = 41], 2nd, at the start of image-guided brachytherapy (IGBT) [n = 41], 3rd, in the middle of IGBT [n = 27], 4th, after treatment [n = 53]). The entire tumor was manually set as the volume of interest (VOI) manually in the axial images of the ADC map by two radiologists. A total of 107 image features (morphology features 14, histogram features 18, texture features 75) were extracted from the VOI. The recurrence prediction values of the features and their change rates were evaluated by Receiver operating characteristics (ROC) analysis. The presence or absence of local and distant recurrence within two years was set as an outcome. The intraclass correlation coefficient (ICC) was also calculated.

RESULTS

The change rates in kurtosis between the 1st and 3rd, and 1st and 2nd MRIs, and the change rate in grey level co-occurrence matrix_cluster shade between the 2nd and 3rd MRIs showed particularly high predictive powers (area under the ROC curve = 0.785, 0.759, and 0.750, respectively), which exceeded the predictive abilities of the parameters obtained from pre- or post-treatment MRI only. The change rate in kurtosis between the 1st and 2nd MRIs had good reliability (ICC = 0.765).

CONCLUSIONS

The change rate in ADC kurtosis between the 1st and 2nd MRIs was the most reliable parameter, enabling us to predict prognosis early in the treatment course.

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.

Wasserstein-based texture analysis in radiomic studies

The emerging field of radiomics that transforms standard-of-care images to quantifiable scalar statistics endeavors to reveal the information hidden in these macroscopic images. The concept of texture is widely used and essential in many radiomic-based studies. Practice usually reduces spatial multidimensional texture matrices, e.g., gray-level co-occurrence matrices (GLCMs), to summary scalar features. These statistical features have been demonstrated to be strongly correlated and tend to contribute redundant information; and does not account for the spatial information hidden in the multivariate texture matrices. This study proposes a novel pipeline to deal with spatial texture features in radiomic studies. A new set of textural features that preserve the spatial information inherent in GLCMs is proposed and used for classification purposes. The set of the new features uses the Wasserstein metric from optimal mass transport theory (OMT) to quantify the spatial similarity between samples within a given label class. In particular, based on a selected subset of texture GLCMs from the training cohort, we propose new representative spatial texture features, which we incorporate into a supervised image classification pipeline. The pipeline relies on the support vector machine (SVM) algorithm along with Bayesian optimization and the Wasserstein metric. The selection of the best GLCM references is considered for each classification label and is performed during the training phase of the SVM classifier using a Bayesian optimizer. We assume that sample fitness is defined based on closeness (in the sense of the Wasserstein metric) and high correlation (Spearman's rank sense) with other samples in the same class. Moreover, the newly defined spatial texture features consist of the Wasserstein distance between the optimally selected references and the remaining samples. We assessed the performance of the proposed classification pipeline in diagnosing the coronavirus disease 2019 (COVID-19) from computed tomographic (CT) images. To evaluate the proposed spatial features' added value, we compared the performance of the proposed classification pipeline with other SVM-based classifiers that account for different texture features, namely: statistical features only, optimized spatial features using Euclidean metric, non-optimized spatial features with Wasserstein metric. The proposed technique, which accounts for the optimized spatial texture feature with Wasserstein metric, shows great potential in classifying new COVID CT images that the algorithm has not seen in the training step. The MATLAB code of the proposed classification pipeline is made available. It can be used to find the best reference samples in other data cohorts, which can then be employed to build different prediction models.

Exploring Texture Analysis to Optimize Bladder Preservation in Muscle Invasive Bladder Cancer

PURPOSE

To explore if texture analysis of Muscle Invasive Bladder Cancer (MIBC) can aid in better patient selection for bladder preservation.

METHODS

Pretreatment noncontrast CT images of 41 patients of MIBC treated with bladder preservation were included. The visible tumor was contoured on all slices by a single observer. The primary endpoint was to identify texture parameters associated with disease recurrence posttreatment. The secondary endpoints included intra and interobserver variability, single and multislice analysis, and differentiating the texture features of normal bladder and tumor. For interobserver variability of bladder tumor texture features, 3 observers contoured the visible tumor on all slices independently. Observer 1 contoured again at an interval of 1 month for intraobserver variability.

RESULTS

The median follow-up was 30 months with 12 patients having a recurrence. In the primary endpoint analysis, the mean of the pixels at Spatial Scaling Filter (SSF) 2 for the no recurrence group and recurrence group was 6.44 v 13.73 respectively (P = .031) and the same at SSF-3 was 11.95 and 22.32 respectively (P = .034). The texture features that could significantly differentiate tumor and normal bladder were mean, standard deviation and kurtosis of the pixels at SSF-2 and entropy and kurtosis of the pixels at SSF-3. Overall, there was an excellent intra and interobserver concordance in texture features. Only multislice analysis and not single-slice could differentiate recurrence and no recurrence posttreatment.

CONCLUSIONS

Texture analysis can be explored as a modality for patient selection for bladder preservation along with the established clinical parameters to improve outcomes.

Post treatment imaging in patients with local advanced cervical carcinoma

Cervical cancer (CC) is the fourth leading cause of death in women worldwide and despite the introduction of screening programs about 30% of patients presents advanced disease at diagnosis and 30-50% of them relapse in the first 5-years after treatment. According to FIGO staging system 2018, stage IB3-IVA are classified as locally advanced cervical cancer (LACC); its correct therapeutic choice remains still controversial and includes neoadjuvant chemo-radiotherapy, external beam radiotherapy, brachytherapy, hysterectomy or a combination of these modalities. In this review we focus on the most appropriated therapeutic options for LACC and imaging protocols used for its correct follow-up. We explore the imaging findings after radiotherapy and surgery and discuss the role of imaging in evaluating the response rate to treatment, selecting patients for salvage surgery and evaluating recurrence of disease. We also introduce and evaluate the advances of the emerging imaging techniques mainly represented by spectroscopy, PET-MRI, and radiomics which have improved diagnostic accuracy and are approaching to future direction.

Radiomic Analysis for Pretreatment Prediction of Recurrence Post-Radiotherapy in Cervical Squamous Cell Carcinoma Cancer

Background: The current study aims to predict the recurrence of cervical cancer patients treated with radiotherapy from radiomics features on pretreatment T1- and T2-weighted MR images. Methods: A total of 89 patients were split into model training (63 patients) and model testing (26 patients). The predictors of recurrence were selected using the least absolute shrinkage and selection operator (LASSO) regression. The machine learning used neural network classifiers. Results: Using LASSO analysis of radiomics, we found 25 features from the T1-weighted and 4 features from T2-weighted MR images, respectively. The accuracy was highest with the combination of T1- and T2-weighted MR images. The model performances with T1- or T2-weighted MR images were 86.4% or 89.4% accuracy, 74.9% or 38.1% sensitivity, 81.8% or 72.2% specificity, and 0.89 or 0.69 of the area under the curve (AUC). The model performance with the combination of T1- and T2-weighted MR images was 93.1% accuracy, 81.6% sensitivity, 88.7% specificity, and 0.94 of AUC. Conclusions: The radiomics analysis with T1- and T2-weighted MR images could highly predict the recurrence of cervix cancer after radiotherapy. The variation of the distribution and the difference in the pixel number at the peripheral and the center were important predictors.

MRI-based radiomics value for predicting the survival of patients with locally advanced cervical squamous cell cancer treated with concurrent chemoradiotherapy

BACKGROUND

To investigate the magnetic resonance imaging (MRI)-based radiomics value in predicting the survival of patients with locally advanced cervical squamous cell cancer (LACSC) treated with concurrent chemoradiotherapy (CCRT).

METHODS

A total of 185 patients (training group: n = 128; testing group: n = 57) with LACSC treated with CCRT between January 2014 and December 2018 were retrospectively enrolled in this study. A total of 400 radiomics features were extracted from T2-weighted imaging, apparent diffusion coefficient map, arterial- and delayed-phase contrast-enhanced MRI. Univariate Cox regression and least absolute shrinkage and selection operator Cox regression was applied to select radiomics features and clinical characteristics that could independently predict progression-free survival (PFS) and overall survival (OS). The predictive capability of the prediction model was evaluated using Harrell's C-index. Nomograms and calibration curves were then generated. Survival curves were generated using the Kaplan-Meier method, and the log-rank test was used for comparison.

RESULTS

The radiomics score achieved significantly better predictive performance for the estimation of PFS (C-index, 0.764 for training and 0.762 for testing) and OS (C-index, 0.793 for training and 0.750 for testing), compared with the 2018 FIGO staging system (C-index for PFS, 0.657 for training and 0.677 for testing; C-index for OS, 0.665 for training and 0.633 for testing) and clinical-predicting model (C-index for PFS, 0.731 for training and 0.725 for testing; C-index for OS, 0.708 for training and 0.693 for testing) (P < 0.05). The combined model constructed with T stage, lymph node metastasis position, and radiomics score achieved the best performance for the estimation of PFS (C-index, 0.792 for training and 0.809 for testing) and OS (C-index, 0.822 for training and 0.785 for testing), which were significantly higher than those of the radiomics score (P < 0.05).

CONCLUSIONS

The MRI-based radiomics score could provide effective information in predicting the PFS and OS in patients with LACSC treated with CCRT. The combined model (including MRI-based radiomics score and clinical characteristics) showed the best prediction performance.

The Value of Whole-Tumor Texture Analysis of ADC in Predicting the Early Recurrence of Locally Advanced Cervical Squamous Cell Cancer Treated With Concurrent Chemoradiotherapy

Objectives

To investigate the value of whole-tumor texture analysis of apparent diffusion coefficient (ADC) map in predicting the early recurrence of patients with locally advanced cervical squamous cell cancer (LACSC) treated with concurrent chemoradiotherapy (CCRT) and establish a combined prediction model including clinical variables and first-order texture features.

Methods

In total, 219 patients (training: n = 153; testing: n = 66) with stage IIB-IVA LACSC treated by CCRT between January 2014 and December 2019 were retrospectively enrolled in this study. Clinical variables and 22 first-order texture features extracted from ADC map were collected. The Mann-Whitney U test or independent sample t test, chi-square test or Fisher’s exact were used to analyze statistically significant parameters, logistic regression analysis was used for multivariate analysis, and receiver operating characteristic analysis was used to compare the diagnostic performance.

Results

In the clinical variables, T stage and lymph node metastasis (LNM) were independent risk factors, and the areas under the curve (AUCs) of the clinical model were 0.697 and 0.667 in the training and testing cohorts, the sensitivity and specificity were 48.8% and 85.5% in the training cohort, and 84.1% and 51.1% in the testing cohort, respectively. In the first-order texture features, mean absolute deviation (MAD) was the independent protective factor, with an AUC of 0.756 in the training cohort and 0.783 in the testing cohort. The sensitivity and specificity were 95.3% and 52.7% in the training cohort and 94.7% and 53.2% in the testing cohort, respectively. The combined model (MAD, T stage, and LNM) was established, it exhibited the highest AUC of 0.804 in the training cohort and 0.821 in the testing cohort, which was significantly higher than the AUC of the clinical prediction model. The sensitivity and specificity were 67.4% and 85.5% in the training cohort and 94.7% and 70.2% in the testing cohort, respectively.

Conclusions

The first-order texture features of the ADC map could be used along with clinical predictive biomarkers to predict early recurrence in patients with LACSC treated by CCRT.

Added-value of texture analysis of ADC in predicting the survival of patients with 2018 FIGO stage IIICr cervical cancer treated by concurrent chemoradiotherapy

PURPOSE

To investigate the value of texture analysis of ADC in predicting the survival of patients with 2018 International Federation of Gynecology and Obstetrics (FIGO) stage IIICr cervical squamous cell cancer (CSCC) treated with concurrent chemoradiotherapy (CCRT).

METHODS

A total of 91 patients with stage IIICr CSCC treated by CCRT between January 2014 and December 2018 were retrospectivelyenrolled in this study. Clinical variables and 21 first-order texture features extracted from ADC maps were collected. Univariate and multivariate Cox hazard regression analyses were performed to evaluate these parameters in predicting progression-free survival (PFS) and overall survival (OS). The independent variables were combined to build a prediction model and compared with the 2018 FIGO staging system. Survival curves were generated using the Kaplan-Meier method, and the log-rank test was used for comparison.

RESULTS

Mean Absolute Deviation (MAD), T stage, and the number of lymph node metastasis (LNM) were independently associated with PFS, while MAD, energy, T stage, number of LNM, and tumor grade were independently associated with OS. The C-index values of the combined models for PFS and OS, which were respectively 0.750 and 0.832, were significantly higher compared to 2018 FIGO staging system values of 0.629 and 0.630, respectively (P < 0.05).

CONCLUSIONS

The texture analysis of the ADC maps could be used along with clinical prognostic biomarkers to predict PFS and OS in patients with stage IIICr CSCC treated by CCRT.

Magnetic resonance imaging-based texture analysis for the prediction of postoperative clinical outcome in uterine cervical cancer

OBJECTIVES

Magnetic resonance imaging (MRI)-based texture analysis (MRTA) is a novel image analysis tool that offers objective information about the spatial arrangement of MRI signal intensity. We aimed to investigate the value of MRTA in predicting the postoperative clinical outcome of patients with uterine cervical cancer.

METHODS

This retrospective study included 115 patients with surgically proven cervical cancer who underwent preoperative pelvic 3T-MRI, and MRTA was performed on T2-weighted images (T2), apparent diffusion coefficient (ADC) maps, and contrast-enhanced T1-weighted images (CE-T1). Filtration histogram-based texture analysis was used to generate six first-order statistical parameters [mean intensity, standard deviation (SD), mean of positive pixels (MPP), entropy, skewness, and kurtosis] at five spatial scaling factors (SSFs, 2-6 mm) as well as from unfiltered images. Cox proportional hazard models and time-dependent receiver operating characteristic analyses were used to evaluate the associations between parameters and recurrence-free survival (RFS).

RESULTS

During a median follow-up of 36 months, tumor recurrence was found in 26 patients (22.6%). Multivariate analysis demonstrated that CE-T1 MPP and T2 kurtosis at SSF3-5, CE-T1 MPP at SSF6, and CE-T1 SD at unfiltered images were independent predictors of RFS (p < 0.05). Regarding the 2-year RFS for CE-T1 MPP and T2 kurtosis at SSF5, and CE-T1 MPP at SSF6, patients with > optimal cutoff values demonstrated significantly worse survival than those with ≤ optimal cutoff values (p < 0.05).

CONCLUSION

Preoperative MRTA may be useful for predicting postoperative outcome in patients with cervical cancer.

Differential expressions of carcinoembryonic antigen and squamous cell carcinoma antigen in patients with advanced cervical cancer undergoing chemotherapy

OBJECTIVE

Cervical cancer is a malignant tumor commonly found in women. This study was conducted to discuss the differential expression of carcinoembryonic antigen (CEA) and squamous cell carcinoma antigen (SCCA) in patients with advanced cervical cancer undergoing various chemotherapies and their effects on patient safety.

METHODS

A total of 65 patients admitted to our hospital with advanced cervical cancer were included as the study subjects and were divided into two groups based on the chemotherapy they received: control group (n = 31) and observation group (n = 34). After two cycles of systemic (IV) chemotherapy in the control group and intra-arterial infusion chemotherapy in the observation group, the two groups were compared for treatment efficacy.

RESULTS

After chemotherapy, the effective rate was 76.47% in the observation group and 48.39% in the control group (P < 0.05). The CEA and SCCA levels were reduced in the two groups, and the observation group had significantly lower levels than the control group (P < 0.05), and also in patients with CR and PR (P < 0.05).

CONCLUSION

In patients with advanced cervical cancer, intra-arterial infusion chemotherapy can improve the efficacy and short-and long-term survival, and reduce the serum VEGF level, blood flow in the tumor, metastasis, and reoccurrence.

Artificial intelligence in gynecologic cancers: Current status and future challenges - A systematic review

OBJECTIVE

Over the past years, the application of artificial intelligence (AI) in medicine has increased rapidly, especially in diagnostics, and in the near future, the role of AI in medicine will become progressively more important. In this study, we elucidated the state of AI research on gynecologic cancers.

METHODS

A search was conducted in three databases-PubMed, Web of Science, and Scopus-for research papers dated between January 2010 and December 2020. As keywords, we used "artificial intelligence," "deep learning," "machine learning," and "neural network," combined with "cervical cancer," "endometrial cancer," "uterine cancer," and "ovarian cancer." We excluded genomic and molecular research, as well as automated pap-smear diagnoses and digital colposcopy.

RESULTS

Of 1632 articles, 71 were eligible, including 34 on cervical cancer, 13 on endometrial cancer, three on uterine sarcoma, and 21 on ovarian cancer. A total of 35 studies (49%) used imaging data and 36 studies (51%) used value-based data as the input data. Magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, cytology, and hysteroscopy data were used as imaging data, and the patients' backgrounds, blood examinations, tumor markers, and indices in pathological examination were used as value-based data. The targets of prediction were definitive diagnosis and prognostic outcome, including overall survival and lymph node metastasis. The size of the dataset was relatively small because 64 studies (90%) included less than 1000 cases, and the median size was 214 cases. The models were evaluated by accuracy scores, area under the receiver operating curve (AUC), and sensitivity/specificity. Owing to the heterogeneity, a quantitative synthesis was not appropriate in this review.

CONCLUSIONS

In gynecologic oncology, more studies have been conducted on cervical cancer than on ovarian and endometrial cancers. Prognoses were mainly used in the study of cervical cancer, whereas diagnoses were primarily used for studying ovarian cancer. The proficiency of the study design for endometrial cancer and uterine sarcoma was unclear because of the small number of studies conducted. The small size of the dataset and the lack of a dataset for external validation were indicated as the challenges of the studies.

Differentiating prostate cancer from benign prostatic hyperplasia using whole-lesion histogram and texture analysis of diffusion- and T2-weighted imaging

Background

To explore the usefulness of analyzing histograms and textures of apparent diffusion coefficient (ADC) maps and T2-weighted (T2W) images to differentiate prostatic cancer (PCa) from benign prostatic hyperplasia (BPH) using histopathology as the reference.

Methods

Ninety patients with PCa and 112 patients with BPH were included in this retrospective study. Differences in whole-lesion histograms and texture parameters of ADC maps and T2W images between PCa and BPH patients were evaluated using the independent samples t-test. The diagnostic performance of ADC maps and T2W images in being able to differentiate PCa from BPH was assessed using receiver operating characteristic (ROC) curves.

Results 

The mean, median, 5^th, and 95^th percentiles of ADC values in images from PCa patients were significantly lower than those from BPH patients (p < 0.05). Significant differences were observed in the means, standard deviations, medians, kurtosis, skewness, and 5^th percentile values of T2W image between PCa and BPH patients (p < 0.05). The ADC_5th showed the largest AUC (0.906) with a sensitivity of 83.3 % and specificity of 89.3 %. The diagnostic performance of the T2W image histogram and texture analysis was moderate and had the largest AUC of 0.634 for T2W_Kurtosis with a sensitivity and specificity of 48.9% and 79.5 %, respectively. The diagnostic performance of the combined ADC_5th & T2W_Kurtosis parameters was also similar to that of the ADC_5th & ADC_{Diff−Variance}.

Conclusions

Histogram and texture parameters derived from the ADC maps and T2W images for entire prostatic lesions could be used as imaging biomarkers to differentiate PCa and BPH biologic characteristics, however, histogram parameters outperformed texture parameters in the diagnostic performance.

Radiomic Features of T2-weighted Imaging and Diffusion Kurtosis Imaging in Differentiating Clinicopathological Characteristics of Cervical Carcinoma

RATIONALE AND OBJECTIVES

Clinicopathological characteristics including histological subtypes, tumour grades and International Federation of Gynecology and Obstetrics (FIGO) stages are crucial factors in the clinical decision for cervical carcinoma (CC). The purpose of this study was to evaluate the ability of T2-weighted imaging (T2WI) and diffusion kurtosis imaging (DKI) radiomics in differentiating clinicopathological characteristics of CC.

MATERIALS AND METHODS

One hundred and seventeen histologically confirmed CC patients (mean age 56.5 ± 14.0 years) with pre-treatment magnetic resonance imaging were retrospectively reviewed. DKI was acquired with 4 b-values (0-1500 s/mm²). Volumes of interest were contoured around the tumours on T2WI and DKI. Radiomic features including shape, first-order and grey-level co-occurrence matrix with wavelet transforms were extracted. Intraclass correlation coeffient between 2 radiologists was used for features reduction. Feature selection was achieved by elastic net and minimum redundancy maximum relevance. Selected features were used to build random forest (RF) models. The performances for differentiating histological subtypes, tumour grades and FIGO stages were assessed by receiver operating characteristic analysis.

RESULTS

Area under the curves (AUCs) for T2WI-only RF models for discriminating histological subtypes, tumour grades and FIGO stages were 0.762, 0.686, and 0.719. AUCs for DWI-only models were 0.663, 0.645, and 0.868, respectively. AUCs of the combined T2WI and DKI models were 0.823, 0.790, and 0.850, respectively.

CONCLUSION

T2WI and DKI radiomic features could differentiate the clinicopathological characteristics of CC. A combined model showed excellent diagnostic discrimination for histological subtypes, while a DKI-only model presented the best performance in differentiating FIGO stages.

Prognostic value of pretreatment MRI texture features in breast cancer brain metastasis treated with Gamma Knife radiosurgery

BACKGROUND

Gamma Knife radiosurgery (GKS) was recommended for treating patients with breast cancer brain metastasis (BCBM), but predictions of the existing prognostic models for therapeutic responsiveness vary substantially.

PURPOSE

To investigate the prognostic value of pretreatment clinical, MRI radiologic, and texture features in patients with BCBM undergoing GKS.

MATERIAL AND METHODS

The data of 81 BCBMs in 44 patients were retrospectively reviewed. Progressive disease was defined as an increase of at least 20% in the longest diameter of the target lesion or the presence of new intracranial lesions on contrast-enhanced T1-weighted (CE-T1W) imaging. Radiomic features were extracted from pretreatment CE-T1W images, T2-weighted (T2W) images, and ADC maps. Cox proportional hazard analyses were performed to identify independent predictors associated with BCBM-specific progression-free survival (PFS). A nomogram was constructed and its calibration ability was assessed.

RESULTS

The cumulative BCBM-specific PFS was 52.27% at six months and 11.36% at one year, respectively. Age (hazard ratio [HR] 1.04; 95% confidence interval [CI] 1.01-1.06; P = 0.004) and CE-T1W-based kurtosis (HR 0.72; 95% CI 0.57-0.92; P = 0.008) were the independent predictors. The combination of CE-T1W-based kurtosis and age displayed a higher C-index (C-index 0.70; 95% CI 0.63-0.77) than did CE-T1W-based kurtosis (C-index 0.65; 95% CI 0.57-0.73) or age (C-index 0.63; 95% CI 0.56-0.70) alone. The nomogram based on the combinative model provided a better performance over age (P < 0.05). The calibration curves elucidated good agreement between prediction and observation for the probability of 7- and 12-month BCBM-specific PFS.

CONCLUSION

Pretreatment CE-T1W-based kurtosis combined with age could improve prognostic ability in patients with BCBM undergoing GKS.

Combination of Radiomics and Machine Learning with Diffusion-Weighted MR Imaging for Clinical Outcome Prognostication in Cervical Cancer

Objectives: To explore the potential of Radiomics alone and in combination with a diffusion-weighted derived quantitative parameter, namely the apparent diffusion co-efficient (ADC), using supervised classification algorithms in the prediction of outcomes and prognosis. Materials and Methods: Retrospective evaluation of the imaging was conducted for a study cohort of uterine cervical cancer, candidates for radical treatment with chemo radiation. ADC values were calculated from the darkest part of the tumor, both before (labeled preADC) and post treatment (labeled postADC) with chemo radiation. Post extraction of 851 Radiomics features and feature selection analysis—by taking the union of the features that had Pearson correlation >0.35 for recurrence, >0.49 for lymph node and >0.40 for metastasis—was performed to predict clinical outcomes. Results: The study enrolled 52 patients who presented with variable FIGO stages in the age range of 28–79 (Median = 53 years) with a median follow-up of 26.5 months (range: 7–76 months). Disease recurrence occurred in 12 patients (23%). Metastasis occurred in 15 patients (28%). A model generated with 24 radiomics features and preADC using a monotone multi-layer perceptron neural network to predict the recurrence yields an AUC of 0.80 and a Kappa value of 0.55 and shows that the addition of radiomics features to ADC values improves the statistical metrics by approximately 40% for AUC and approximately 223% for Kappa. Similarly, the neural network model for prediction of metastasis returns an AUC value of 0.84 and a Kappa value of 0.65, thus exceeding performance expectations by approximately 25% for AUC and approximately 140% for Kappa. There was a significant input of GLSZM features (SALGLE and LGLZE) and GLDM features (SDLGLE and DE) in correlation with clinical outcomes of recurrence and metastasis. Conclusions: The study is an effort to bridge the unmet need of translational predictive biomarkers in the stratification of uterine cervical cancer patients based on prognosis.

Radiomics in cervical and endometrial cancer

Radiomics is an emerging field of research that aims to find associations between quantitative information extracted from imaging examinations and clinical data to support the best clinical decision. In the last few years, some papers have been evaluating the role of radiomics in gynecological malignancies, mainly focusing on ovarian cancer. Nonetheless, cervical cancer is the most frequent gynecological malignancy in developing countries and endometrial cancer is the most common in western countries. The purpose of this narrative review is to give an overview of the latest published papers evaluating the role of radiomics in cervical and endometrial cancer, mostly evaluating association with tumor prognostic factors, with response to therapy and with prediction of recurrence and distant metastasis.

Radiomics Prediction of EGFR Status in Lung Cancer-Our Experience in Using Multiple Feature Extractors and The Cancer Imaging Archive Data

We investigated the performance of multiple radiomics feature extractors/software on predicting epidermal growth factor receptor mutation status in 228 patients with non–small cell lung cancer from publicly available data sets in The Cancer Imaging Archive. The imaging and clinical data were split into training (n = 105) and validation cohorts (n = 123). Two of the most cited open-source feature extractors, IBEX (1563 features) and Pyradiomics (1319 features), and our in-house software, Columbia Image Feature Extractor (CIFE) (1160 features), were used to extract radiomics features. Univariate and multivariate analyses were performed sequentially to predict EGFR mutation status using each individual feature extractor. Our univariate analysis integrated an unsupervised clustering method to identify nonredundant and informative candidate features for the creation of prediction models by multivariate analyses. In training, unsupervised clustering-based univariate analysis identified 5, 6, and 4 features from IBEX, Pyradiomics, and CIFE as candidate features, respectively. Multivariate prediction models using these features from IBEX, Pyradiomics, and CIFE yielded similar areas under the receiver operating characteristic curve of 0.68, 0.67, and 0.69. However, in validation, areas under the receiver operating characteristic curve of multivariate prediction models from IBEX, Pyradiomics, and CIFE decreased to 0.54, 0.56 and 0.64, respectively. Different feature extractors select different radiomics features, which leads to prediction models with varying performance. However, correlation between those selected features from different extractors may indicate these features measure similar imaging phenotypes associated with similar biological characteristics. Overall, attention should be paid to the generalizability of individual radiomics features and radiomics prediction models.

Association between IVIM parameters and treatment response in locally advanced squamous cell cervical cancer treated by chemoradiotherapy

OBJECTIVE

To examine the associations of intravoxel incoherent motion (IVIM) parameters with treatment response in cervical cancer following concurrent chemoradiotherapy (CCRT).

MATERIALS AND METHODS

Forty-five patients, median age of 58 years (range: 28-82), with pre-CCRT and post-CCRT MRI, were retrospectively analysed. The IVIM parameters pure diffusion coefficient (D) and perfusion fraction (f) were estimated using the full b-value distribution (BVD) as well as an optimised subsample BVD. Dice similarity coefficient (DSC) and intraclass correlation coefficient (ICC) were used to measure observer repeatability in tumour delineation at both time points. Treatment response was determined by the response evaluation criteria in solid tumour (RECIST) 1.1 between MRI examinations. Mann-Whitney U tests were used to test for significant differences in IVIM parameters between treatment response groups.

RESULTS

Pre-CCRT tumour delineation repeatability was good (DSC = 0.81) while post-CCRT delineation repeatability was moderate (DSC = 0.67). Values of D and f had good repeatability at both time points (ICC > 0.80). Pre-CCRT f estimated using the full BVD and optimised subsample BVD were found to be significantly higher in patients with partial response compared to those with stable disease or disease progression (p = 0.01 and 95% CI = -0.02-0.00 for both cases).

CONCLUSION

Pre-CCRT f was associated with treatment response in cervical cancer with good observer repeatability. Similar discriminative ability was also observed in estimated pre-CCRT f from an optimised subsample BVD.

KEY POINTS

• Pre-treatment tumour delineation and IVIM parameters had good observer repeatability. • Post-treatment tumour delineation was worse than at pre-treatment, but IVIM parameters retained good ICC. • Pre-treatment perfusion fraction estimated from all b-values and an optimised subsample of b-values were associated with treatment response.

Quantitative PET Imaging and Clinical Parameters as Predictive Factors for Patients With Cervical Carcinoma: Implications of a Prediction Model Generated Using Multi-Objective Support Vector Machine Learning

Purpose:

Quantitative features from pre-treatment positron emission tomography (PET) have been used to predict treatment outcomes for patients with cervical carcinoma. The purpose of this study is to use quantitative PET imaging features and clinical parameters to construct a multi-objective machine learning predictive model.

Materials/Methods:

Seventy-five patients with stage IB2-IVA disease treated at our institution from 2009–2012 were analyzed. Models predicting locoregional and distant failure were generated using clinical parameters (age, race, stage, histology, tumor size, nodal status) and imaging features (12 textural, 9 intensity, 8 geometric features, 2 additional imaging features) from pre-treatment PET. Model features were selected based on a multi-objective evolutionary algorithm to maximize specificity given a fixed moderately high sensitivity using support vector machine learning methods. Model 1 used clinical parameters only (C), Model 2 used imaging features only (I), and Model 3 used clinical and imaging features (C+I). Sensitivity, specificity, area under a receiver-operating characteristic curve (AUC), and p-values were compared to assess ability to predict locoregional and distant failure.

Results:

C+I had the highest performance for both locoregional failure (AUC 0.84, p < 0.01; specificity: 0.86; sensitivity: 0.79) and distant failure (AUC 0.75, p < 0.01; specificity: 0.75; sensitivity: 0.75).

Conclusions:

Based on a moderately high fixed sensitivity and optimized for specificity, the model using both clinical parameters and imaging features (C+I) had the best performance in predicting both locoregional failure and distant failure.

Diagnostic Strategies for Recurrent Cervical Cancer: A Cohort Study

Objective

The effectiveness of various strategies for the post-treatment monitoring of cervical cancer is unclear. This pilot study was conducted to explore recurrence patterns in and diagnostic strategies for patients with uterine cervical cancer who were meticulously followed using a customized monitoring plan.

Methods

The epidemiological and clinical data of patients with recurrent cervical cancer treated from March 2012 to April 2018 at a tertiary teaching hospital were retrospectively collected. The diagnostic methods and their reliability were compared across patients with various clinicopathological characteristics and were associated with survival outcomes.

Results

Two hundred sixty-four patients with recurrent cervical cancer were included in the study, among which recurrence occurred in the first three years after the last primary treatment in 214 patients (81.06%). Half of the recurrence events (50.76%) occurred only within the pelvic cavity, and most lesions (78.41%) were multiple in nature. Among all recurrent cases, approximately half were diagnosed based on clinical manifestations (n=117, 44.32%), followed by imaging examinations (n=76, 28.79%), serum tumor markers (n=34, 12.88%), physical examinations (n=33, 12.50%) and cervical cytology with or without high-risk human papillomavirus (hrHPV) testing (n=4, 1.52%). The reliability of the diagnostic methods was affected by the stage (p<0.001), primary treatment regimen (p=0.001), disease-free survival (p=0.022), recurrence site (p=0.002) and number of recurrence sites (p=0.001). Primary imaging methods (sonography and chest X-ray) were not inferior to secondary imaging methods (computed tomography, magnetic resonance imaging and positron emission tomography-computed tomography) in the detection of recurrence. The chest X-ray examination only detected three cases (1.14%) of recurrence. Patients assessed with various diagnostic strategies had similar progression-free and overall survival outcomes.

Conclusions

A meticulous evaluation of clinical manifestations might allow recurrence to be discovered in a timely manner in most patients with cervical cancer. Specific diagnostic methods for revealing recurrence were not associated with the survival outcomes.

Impact of different scanners and acquisition parameters on robustness of MR radiomics features based on women's cervix

MR Radiomics based on cervical lesions from one single scanner has achieved promising results. However, it is a challenge to achieve clinical translation. Considering multi-scanners and non-uniform scanning parameters from different centers in a real-world medical scenario, we should first identify the influence of such conditions on the robustness of MR radiomics features (RFs) based on the female cervix. In this study, 9 healthy female volunteers were enrolled and 3 kiwis were selected as references. Each of them underwent T2 weighted imaging in three different 3.0-T MR scanners with uniform acquisition parameters, and in one MR scanner with various scanning parameters. A total of 396 RFs were extracted from their images with and without decile intensity normalization. The RFs’ reproducibility was evaluated by coefficient of variation (CV) and quartile coefficient of dispersion (QCD). Representative features were selected using the hierarchical cluster analysis and their discrimination abilities were estimated by ROC analysis through retrospective comparison with the junctional zone and the outer muscular layer of healthy cervix in patients (n = 58) with leiomyoma. This study showed that only a few RFs were robust across different MR scanners and acquisition parameters based on females’ cervix, which might be improved by decile intensity normalization method.

Association between MRI histogram features and treatment response in locally advanced cervical cancer treated by chemoradiotherapy

OBJECTIVE

To examine the associations of histogram features of T2-weighted (T2W) images and apparent diffusion coefficient (ADC) with treatment response in locally advanced cervical cancer (LACC) following concurrent chemoradiotherapy (CCRT).

MATERIALS AND METHODS

Fifty-eight patients who underwent a 4-week CCRT regimen with MRI prior to treatment (pre-CCRT) and after treatment (post-CCRT) were retrospectively analysed. Histogram features were calculated from volumes of interest (VOIs) from one radiologist on T2W images and ADC maps. VOIs from two radiologists were used to assess observer repeatability in delineation and feature values at both time-points with the Dice similarity coefficient (DSC) and intraclass correlation coefficient (ICC). Treatment response was defined as a 90% reduction in tumour volume. Paired Mann-Whitney U tests were used to determine if features changed significantly between examinations. Two-sample Mann-Whitney U tests were used to identify features that were significantly different between response groups. Receiver operating characteristic (ROC) analysis was done on significantly different MRI features between treatment response groups.

RESULTS

Pre-CCRT delineation and feature repeatability were generally good (DSC > 0.700; ICC > 0.750). Post-CCRT repeatability was low (DSC < 0.700; ICC < 0.750), but ADC mean and percentiles retained good ICC scores. All features, except for T2W_Kurtosis, significantly changed between examinations. Post-CCRT ADC₅₀ was the only feature that demonstrated both good observer variability and significant differences between treatment response groups (p = 0.036) and had an AUC of 0.701 with a cut-off of 1.357 × 10^-6 mm²/s.

CONCLUSION

ADC and T2W histogram features could be used to track changes in LACC tumours undergoing CCRT. Post-CCRT ADC₅₀ was associated with treatment response with good observer repeatability.

KEY POINTS

• Pre-treatment tumour delineation and histogram feature values had good observer repeatability, while these were less repeatable at post-treatment. • MRI histogram analysis could be used to track changes in the tumour as it undergoes concurrent chemoradiotherapy. • Post-treatment median ADC was associated with treatment response and had good repeatability.

Texture Analysis of Apparent Diffusion Coefficient Maps in Cervical Carcinoma: Correlation with Histopathologic Findings and Prognosis

Purpose

To determine the feasibility of texture analysis of apparent diffusion coefficient (ADC) maps and to assess the performance of texture analysis and ADC to predict histologic grade, parametrial invasion, lymph node metastasis, International Federation of Gynecology and Obstetrics (FIGO) stage, recurrence, and recurrence-free survival (RFS) in patients with cervical carcinoma.

Materials and Methods

This retrospective study included 58 patients with cervical carcinoma who were examined with a 1.5-T MRI system and diffusion-weighted imaging with b values of 0 and 1000 sec/mm². Software with volumes of interest on ADC maps was used to extract 45 texture features, including higher-order texture features. Receiver operating characteristic (ROC) analysis was performed to compare the diagnostic performance of ADC map random forest models and of ADC values. Dunnett test, Spearman rank correlation coefficient, Kaplan-Meier analyses, log-rank test, and Cox proportional hazards regression analyses were also used for statistical analyses.

Results

The ADC map random forest models showed a significantly larger area under the ROC curve (AUC) than the AUC of ADC values for predicting high-grade cervical carcinoma (P = .0036), but not for parametrial invasion, lymph node metastasis, stages III-IV, and recurrence (P = .0602, .3176, .0924, and .5633, respectively). The random forest models predicted that the mean RFS rates were significantly shorter for high-grade cervical carcinomas, parametrial invasion, lymph node metastasis, stages III-IV, and recurrence (P = .0405, < .0001, .0344, .0001, and .0015, respectively); the random forest models for parametrial invasion and stages III-IV were more useful than ADC values (P = .0018) for predicting RFS.

Conclusion

The ADC map random forest models were more useful for noninvasively evaluating histologic grade, parametrial invasion, lymph node metastasis, FIGO stage, and recurrence and for predicting RFS in patients with cervical carcinoma than were ADC values.Keywords: Comparative Studies, Genital/Reproductive, MR-Diffusion Weighted Imaging, MR-Imaging, Neoplasms-Primary, Pathology, Pelvis, Tissue Characterization, UterusSupplemental material is available for this article.© RSNA, 2020See also the commentary by Reinhold and Nougaret in this issue.

MRI texture features differentiate clinicopathological characteristics of cervical carcinoma

OBJECTIVES

To evaluate MRI texture analysis in differentiating clinicopathological characteristics of cervical carcinoma (CC).

METHODS

Patients with newly diagnosed CC who underwent pre-treatment MRI were retrospectively reviewed. Texture analysis was performed using commercial software (TexRAD). Largest single-slice ROIs were manually drawn around the tumour on T2-weighted (T2W) images, apparent diffusion coefficient (ADC) maps and contrast-enhanced T1-weighted (T1c) images. First-order texture features were calculated and compared among histological subtypes, tumour grades, FIGO stages and nodal status using the Mann-Whitney U test. Feature selection was achieved by elastic net. Selected features from different sequences were used to build the multivariable support vector machine (SVM) models and the performances were assessed by ROC curves and AUC.

RESULTS

Ninety-five patients with FIGO stage IB~IVB were evaluated. A number of texture features from multiple sequences were significantly different among all the clinicopathological subgroups (p < 0.05). Texture features from different sequences were selected to build the SVM models. The AUCs of SVM models for discriminating histological subtypes, tumour grades, FIGO stages and nodal status were 0.841, 0.850, 0.898 and 0.879, respectively.

CONCLUSIONS

Texture features derived from multiple sequences were helpful in differentiating the clinicopathological signatures of CC. The SVM models with selected features from different sequences offered excellent diagnostic discrimination of the tumour characteristics in CC.

KEY POINTS

• First-order texture features are able to differentiate clinicopathological signatures of cervical carcinoma. • Combined texture features from different sequences can offer excellent diagnostic discrimination of the tumour characteristics in cervical carcinoma.

Differentiation of renal cell carcinoma subtypes through MRI-based radiomics analysis

OBJECTIVES

To explore whether clear cell renal cell carcinoma (ccRCC), papillary renal cell carcinoma (pRCC), and chromophobe renal cell carcinoma (cRCC) can be distinguished using radiomics features extracted from magnetic resonance (MR) images.

METHODS

Seventy-seven patients (ccRCC = 32, pRCC = 23, cRCC = 22) underwent MRI before surgery between May 2013 and August 2018 in this retrospective study. Thirty-nine radiomics features were extracted from tumor volumes on three sequences (T2WI, EN-T1WI CMP, and EN-T1WI NP). The Kruskal-Wallis test with Bonferonni correction and variance threshold were used for feature selection among the three RCC subtypes. ROC curves for the three subtypes were generated based on radiomics features. AUC, accuracy, sensitivity, and specificity for subtype differentiation are reported. Linear discriminant analysis (LDA) was used to assess the discriminative ability of these radiomics features.

RESULTS

Significant radiomics features among the three subtypes were identified, and ROC curves achieved excellent AUCs for T2WI, EN-T1WI CMP, EN-T1WI NP, and combined three MR sequences (0.631, 0.790, 0.959, and 0.959 between ccRCC and cRCC; 0.688, 0.854, 0.909, and 0.955 between pRCC and cRCC; 0.747, 0.810, 0.814, and 0.890 between ccRCC and pRCC). In addition, LDA demonstrated the three RCC subtypes were correctly classified by radiomics analysis (66.2% for EN-T1WI CMP, 71.4% for EN-T1WI NP, 55.8% for T2WI, and 71.4% for the combined three MR sequences).

CONCLUSIONS

Radiomics analysis can be used to differentiate among ccRCC, pRCC, and cRCC based on radiomics features extracted from multiple-sequence MRI and may help diagnose and treat RCC patients in the future, while further study is still needed.

KEY POINTS

• Radiomics features on multiple-sequence MRI can help differentiate the three subtypes of renal cell carcinoma (clear cell, papillary renal cell, and chromophobe renal cell carcinoma). • Radiomics features based on MRI indicate greater textural heterogeneity on ccRCCs than pRCCs and cRCCs (the highest AUCs on EN-T1WI NP are 0.814 for ccRCCs vs pRCCs and 0.959 for ccRCCs vs cRCCs, respectively). • There is a significant difference in the textural heterogeneity of radiomics features between pRCCs and cRCCs (the AUC is 0.909, 0.854, and 0.688 on EN-T1WI NP, EN-T1WI CMP, and T2WI, respectively).

Ependymoma and pilocytic astrocytoma: Differentiation using radiomics approach based on machine learning

Mandatory accurate and specific diagnosis demands have brought about increased challenges for radiologists in pediatric posterior fossa tumor prediction and prognosis. With the development of high-performance computing and machine learning technologies, radiomics provides increasing opportunities for clinical decision-making. Several studies have applied radiomics as a decision support tool in intracranial tumors differentiation. Here we seek to achieve preoperative differentiation between ependymoma (EP) and pilocytic astrocytoma (PA) using radiomics analysis method based on machine learning. A total of 135 Magnetic Resonance Imaging (MRI) slices are divided into training sets and validation sets. Three kinds of radiomics features, including Gabor transform, texture and wavelet transform based ones are used to obtain 300 multimodal features. Kruskal-Wallis test score (KWT) and support vector machines (SVM) are applied for feature selection and tumor differentiation. The performance is investigated via accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. Results show that the accuracy, sensitivity, specificity, and AUC of the selected feature set are 0.8775, 0.9292, 0.8000, and 0.8646 respectively, having no significantdifferencescomparedwiththe overall feature set. For different types of features, texture features yield the best differentiation performance and the significance analysis results are consistent with this. Our study demonstrates texture features perform better than the other features. The radiomics approach based on machine learning is efficient for pediatric posterior fossa tumors differentiation and could enhance the application of radiomics methods for assisted clinical diagnosis.

Magnetic resonance imaging features of tumor and lymph node to predict clinical outcome in node-positive cervical cancer: a retrospective analysis

Background

Current chemoradiation regimens for locally advanced cervical cancer are fairly uniform despite a profound diversity of treatment response and recurrence patterns. The wide range of treatment responses and prognoses to standardized concurrent chemoradiation highlights the need for a reliable tool to predict treatment outcomes. We investigated pretreatment magnetic resonance (MR) imaging features of primary tumor and involved lymph node for predicting clinical outcome in cervical cancer patients.

Methods

We included 93 node-positive cervical cancer patients treated with definitive chemoradiotherapy at our institution between 2006 and 2017. The median follow-up period was 38 months (range, 5–128). Primary tumor and involved lymph node were manually segmented on axial gadolinium-enhanced T1-weighted images as well as T2-weighted images and saved as 3-dimensional regions of interest (ROI). After the segmentation, imaging features related to histogram, shape, and texture were extracted from each ROI. Using these features, random survival forest (RSF) models were built to predict local control (LC), regional control (RC), distant metastasis-free survival (DMFS), and overall survival (OS) in the training dataset (n = 62). The generated models were then tested in the validation dataset (n = 31).

Results

For predicting LC, models generated from primary tumor imaging features showed better predictive performance (C-index, 0.72) than those from lymph node features (C-index, 0.62). In contrast, models from lymph nodes showed superior performance for predicting RC, DMFS, and OS compared to models of the primary tumor. According to the 3-year time-dependent receiver operating characteristic analysis of LC, RC, DMFS, and OS prediction, the respective area under the curve values for the predicted risk of the models generated from the training dataset were 0.634, 0.796, 0.733, and 0.749 in the validation dataset.

Conclusions

Our results suggest that tumor and lymph node imaging features may play complementary roles for predicting clinical outcomes in node-positive cervical cancer.

PETER PHAN: An MRI phantom for the optimisation of radiomic studies of the female pelvis

PURPOSE

To develop a phantom for methodological radiomic investigation on Magnetic Resonance (MR) images of female patients affected by pelvic cancer.

METHODS

A pelvis-shaped container was filled with a MnCl₂ solution reproducing the relaxation times (T₁, T₂) of muscle surrounding pelvic malignancies. Inserts simulating multi-textured lesions were embedded in the phantom. The relaxation times of muscle and tumour were measured on an MR scanner on healthy volunteers and patients; T₁ and T₂ of MnCl₂ solutions were evaluated with a relaxometer to find the concentrations providing a match to in vivo relaxation times. Radiomic features were extracted from the phantom inserts and the patients' lesions. Their repeatability was assessed by multiple measurements.

RESULTS

Muscle T₁ and T₂ were 1128 (806-1378) and 51 (40-65) ms, respectively. The phantom reproduced in vivo values within 13% (T₁) and 12% (T₂). T₁ and T₂ of tumour tissue were 1637 (1396-2121) and 94 (79-101) ms, respectively. The phantom insert best mimicking the tumour agreed within 7% (T₁) and 24% (T₂) with in vivo values. Out of 1034 features, 75% (95%) had interclass correlation coefficient greater than 0.9 on T₁ (T₂)-weighted images, reducing to 33% (25%) if the phantom was repositioned. The most repeatable features on phantom showed values in agreement with the features extracted from patients' lesions.

CONCLUSIONS

We developed an MR phantom with inserts mimicking both relaxation times and texture of pelvic tumours. As exemplified with repeatability assessment, such phantom is useful to investigate features robustness and optimise the radiomic workflow on pelvic MR images.

Radiomics: an Introductory Guide to What It May Foretell

PURPOSE OF REVIEW

To briefly review the radiomics concept, its applications, and challenges in oncology in the era of precision medicine.

RECENT FINDINGS

Over the last 5 years, more than 500 studies have evaluated the role of radiomics to predict tumor diagnosis, genetic pattern, tumor response to therapy, and survival in multiple cancers. This new post-processing method is aimed at extracting multiple quantitative features from the image and converting them into mineable data. Radiomics models developed have shown promising results and may play a role in the near future in the daily patient management especially to assess tumor heterogeneity acting as a whole tumor virtual biopsy. For now, radiomics is limited by its lack of standardization; future challenges will be to provide robust and reproducible metrics extracted from large multicenter databases.