ADC-derived spatial features can accurately classify adnexal lesions

Automated Prediction of Early Recurrence in Advanced Sinonasal Squamous Cell Carcinoma With Deep Learning and Multi-parametric MRI-based Radiomics Nomogram

RATIONALE AND OBJECTIVES

Preoperative prediction of the recurrence risk in patients with advanced sinonasal squamous cell carcinoma (SNSCC) is critical for individualized treatment. To evaluate the predictive ability of radiomics signature (RS) based on deep learning and multiparametric MRI for the risk of 2-year recurrence in advanced SNSCC.

MATERIALS AND METHODS

Preoperative MRI datasets were retrospectively collected from 265 SNSCC patients (145 recurrences) who underwent preoperative MRI, including T2-weighted (T2W), contrast-enhanced T1-weighted (T1c) sequences and diffusion-weighted (DW). All patients were divided into 165 training cohort and 70 test cohort. A deep learning segmentation model based on VB-Net was used to segment regions of interest (ROIs) for preoperative MRI and radiomics features were extracted from automatically segmented ROIs. Least absolute shrinkage and selection operator (LASSO) and logistic regression (LR) were applied for feature selection and radiomics score construction. Combined with meaningful clinicopathological predictors, a nomogram was developed and its performance was evaluated. In addition, X-title software was used to divide patients into high-risk or low-risk early relapse (ER) subgroups. Recurrence-free survival probability (RFS) was assessed for each subgroup.

RESULTS

The radiomics score, T stage, histological grade and Ki-67 predictors were independent predictors. The segmentation models of T2WI, T1c, and apparent diffusion coefficient (ADC) sequences achieved Dice coefficients of 0.720, 0.727, and 0.756, respectively, in the test cohort. RS-T2, RS-T1c and RS-ADC were derived from single-parameter MRI. RS-Combined (combined with T2WI, T1c, and ADC features) was derived from multiparametric MRI and reached area under curve (AUC) and accuracy of 0.854 (0.749-0.927) and 74.3% (0.624-0.840), respectively, in the test cohort. The calibration curve and decision curve analysis (DCA) illustrate its value in clinical practice. Kaplan-Meier analysis showed that the 2-year RFS rate for low-risk patients was significantly greater than that for high-risk patients in both the training and testing cohorts (p < 0.001).

CONCLUSION

Automated nomograms based on multi-sequence MRI help to predict ER in SNSCC patients preoperatively.

Quantification of Multi-Parametric Magnetic Resonance Imaging Based on Radiomics Analysis for Differentiation of Benign and Malignant Lesions of Prostate

Background

The most common cancer (non-cutaneous) malignancy among men is prostate cancer. Management of prostate cancer, including staging and treatment, playing an important role in decreasing mortality rates. Among all current diagnostic tools, multiparametric MRI (mp-MRI) has shown high potential in localizing and staging prostate cancer. Quantification of mp-MRI helps to decrease the dependency of diagnosis on readers' opinions.

Objective

The aim of this research is to set a method based on quantification of mp-MRI images for discrimination between benign and malignant prostatic lesions with fusion-guided MR imaging/transrectal ultrasonography biopsy as a pathology validation reference.

Material and Methods

It is an analytical research that 27 patients underwent the mp-MRI examination, including T1- and T2- weighted and diffusion weighted imaging (DWI). Quantification was done by calculating radiomic features from mp-MRI images. Receiver-operating-characteristic curve was done for each feature to evaluate the discriminatory capacity and linear discriminant analysis (LDA) and leave-one-out cross-validation for feature filtering to estimate the sensitivity, specificity and accuracy of the benign and malignant lesion differentiation process is used.

Results

An accuracy, sensitivity and specificity of 92.6%, 95.2% and 83.3%, respectively, were achieved from a subset of radiomics features obtained from T2-weighted images and apparent diffusion coefficient (ADC) maps for distinguishing benign and malignant prostate lesions.

Conclusion

Quantification of mp-MRI (T2-weighted images and ADC-maps) based on radiomics feature has potential to distinguish benign with appropriate accuracy from malignant prostate lesions. This technique is helpful in preventing needless biopsies in patients and provides an assisted diagnosis for classifications of prostate lesions.

A case of paraovarian tumor of borderline malignancy with decrease of apparent diffusion coefficient value and marked 18F-fluorodeoxyglucose accumulation

Para-ovarian cysts are occasionally encountered in clinical practice; however, malignant tumors derived from them are rare. Due to its rarity, the characteristic imaging findings of para-ovarian tumors with borderline malignancy (PTBM) are largely unknown. Herein, we report a case of PTBM, along with imaging findings. A 37-year-old woman came to our department with a suspected malignant adnexal tumor. Pelvic contrast-enhanced magnetic resonance imaging (MRI) revealed a solid part within the cystic tumor with a decrease in the apparent diffusion coefficient (ADC) value (1.16 × 10-3 mm2/s). We also performed Positron Emission Tomography-MRI and showed a strong accumulation of 18F-fluorodeoxyglucose (FDG) in the solid part (SUVmax = 14.8). In addition, the tumor appeared to develop independently of the ovary. Because tumor was derived from para-ovarian cyst, we suspected PTBM preoperatively and planned fertility sparing treatment. Pathological examination revealed a serous borderline tumor and PTBM was confirmed. PTBM can have unique imaging characteristics, including a low ADC value and high FDG accumulation. When a tumor appears to develop from para-ovarian cysts, borderline malignancy can be suspected, even if imaging findings suggest malignant potential.

Radiomic Analysis of Multi-parametric MR Images (MRI) for Classification of Parotid Tumors

Background

Characterization of parotid tumors before surgery using multi-parametric magnetic resonance imaging (MRI) scans can support clinical decision making about the best-suited therapeutic strategy for each patient.

Objective

This study aims to differentiate benign from malignant parotid tumors through radiomics analysis of multi-parametric MR images, incorporating T2-w images with ADC-map and parametric maps generated from Dynamic Contrast Enhanced MRI (DCE-MRI).

Material and Methods

MRI scans of 31 patients with histopathologically-confirmed parotid gland tumors (23 benign, 8 malignant) were included in this retrospective study. For DCE-MRI, semi-quantitative analysis, Tofts pharmacokinetic (PK) modeling, and five-parameter sigmoid modeling were performed and parametric maps were generated. For each patient, borders of the tumors were delineated on whole tumor slices of T2-w image, ADC-map, and the late-enhancement dynamic series of DCE-MRI, creating regions-of-interest (ROIs). Radiomic analysis was performed for the specified ROIs.

Results

Among the DCE-MRI-derived parametric maps, wash-in rate (WIR) and PK-derived K^trans parameters surpassed the accuracy of other parameters based on support vector machine (SVM) classifier. Radiomics analysis of ADC-map outperformed the T2-w and DCE-MRI techniques using the simpler classifier, suggestive of its inherently high sensitivity and specificity. Radiomics analysis of the combination of T2-w image, ADC-map, and DCE-MRI parametric maps resulted in accuracy of 100% with both classifiers with fewer numbers of selected texture features than individual images.

Conclusion

In conclusion, radiomics analysis is a reliable quantitative approach for discrimination of parotid tumors and can be employed as a computer-aided approach for pre-operative diagnosis and treatment planning of the patients.

Diffusion-Weighted Magnetic Resonance Imaging in Ovarian Cancer: Exploiting Strengths and Understanding Limitations

Detection, characterization, staging, and response assessment are key steps in the imaging pathway of ovarian cancer. The most common type, high grade serous ovarian cancer, often presents late, so that accurate disease staging and response assessment are required through imaging in order to improve patient management. Currently, computerized tomography (CT) is the most common method for these tasks, but due to its poor soft-tissue contrast, it is unable to quantify early response within lesions before shrinkage is observed by size criteria. Therefore, quantifiable techniques, such as diffusion-weighted magnetic resonance imaging (DW-MRI), which generates high contrast between tumor and healthy tissue, are increasingly being explored. This article discusses the basis of diffusion-weighted contrast and the technical issues that must be addressed in order to achieve optimal implementation and robust quantifiable diffusion-weighted metrics in the abdomen and pelvis. The role of DW-MRI in characterizing adnexal masses in order to distinguish benign from malignant disease, and to differentiate borderline from frankly invasive malignancy is discussed, emphasizing the importance of morphological imaging over diffusion-weighted metrics in this regard. Its key role in disease staging and predicting resectability in comparison to CT is addressed, including its valuable use as a biomarker for following response within individual lesions, where early changes in the apparent diffusion coefficient in peritoneal metastases may be detected. Finally, the task of implementing DW-MRI into clinical trials in order to validate this biomarker for clinical use are discussed, along with the trials that include it within their protocols.

Machine Learning Using Multiparametric Magnetic Resonance Imaging Radiomic Feature Analysis to Predict Ki-67 in World Health Organization Grade I Meningiomas

BACKGROUND

Although World Health Organization (WHO) grade I meningiomas are considered "benign" tumors, an elevated Ki-67 is one crucial factor that has been shown to influence tumor behavior and clinical outcomes. The ability to preoperatively discern Ki-67 would confer the ability to guide surgical strategy.

OBJECTIVE

In this study, we develop a machine learning (ML) algorithm using radiomic feature analysis to predict Ki-67 in WHO grade I meningiomas.

METHODS

A retrospective analysis was performed for a cohort of 306 patients who underwent surgical resection of WHO grade I meningiomas. Preoperative magnetic resonance imaging was used to perform radiomic feature extraction followed by ML modeling using least absolute shrinkage and selection operator wrapped with support vector machine through nested cross-validation on a discovery cohort (n = 230), to stratify tumors based on Ki-67 <5% and ≥5%. The final model was independently tested on a replication cohort (n = 76).

RESULTS

An area under the receiver operating curve (AUC) of 0.84 (95% CI: 0.78-0.90) with a sensitivity of 84.1% and specificity of 73.3% was achieved in the discovery cohort. When this model was applied to the replication cohort, a similar high performance was achieved, with an AUC of 0.83 (95% CI: 0.73-0.94), sensitivity and specificity of 82.6% and 85.5%, respectively. The model demonstrated similar efficacy when applied to skull base and nonskull base tumors.

CONCLUSION

Our proposed radiomic feature analysis can be used to stratify WHO grade I meningiomas based on Ki-67 with excellent accuracy and can be applied to skull base and nonskull base tumors with similar performance achieved.

Radiomic nomogram based on MRI to predict grade of branching type intraductal papillary mucinous neoplasms of the pancreas: a multicenter study

Background

Accurate diagnosis of high-grade branching type intraductal papillary mucinous neoplasms (BD-IPMNs) is challenging in clinical setting. We aimed to construct and validate a nomogram combining clinical characteristics and radiomic features for the preoperative prediction of low and high-grade in BD-IPMNs.

Methods

Two hundred and two patients from three medical centers were enrolled. The high-grade BD-IPMN group comprised patients with high-grade dysplasia and invasive carcinoma in BD-IPMN (n = 50). The training cohort comprised patients from the first medical center (n = 103), and the external independent validation cohorts comprised patients from the second and third medical centers (n = 48 and 51). Within 3 months prior to surgery, all patients were subjected to magnetic resonance examination. The volume of interest was delineated on T1-weighted (T1-w) imaging, T2-weighted (T2-w) imaging, and contrast-enhanced T1-weighted (CET1-w) imaging, respectively, on each tumor slice. Quantitative image features were extracted using MITK software (G.E.). The Mann-Whitney U test or independent-sample t-test, and LASSO regression, were applied for data dimension reduction, after which a radiomic signature was constructed for grade assessment. Based on the training cohort, we developed a combined nomogram model incorporating clinical variables and the radiomic signature. Decision curve analysis (DCA), a receiver operating characteristic curve (ROC), a calibration curve, and the area under the ROC curve (AUC) were used to evaluate the utility of the constructed model based on the external independent validation cohorts.

Results

To predict tumor grade, we developed a nine-feature-combined radiomic signature. For the radiomic signature, the AUC values of high-grade disease were 0.836 in the training cohort, 0.811 in external validation cohort 1, and 0.822 in external validation cohort 2. The CA19–9 level and main pancreatic duct size were identified as independent parameters of high-grade of BD-IPMNs using multivariate logistic regression analysis. The CA19–9 level and main pancreatic duct size were then used to construct the radiomic nomogram. Using the radiomic nomogram, the high-grade disease-associated AUC values were 0.903 (training cohort), 0.884 (external validation cohort 1), and 0.876 (external validation cohort 2). The clinical utility of the developed nomogram was verified using the calibration curve and DCA.

Conclusions

The developed radiomic nomogram model could effectively distinguish high-grade patients with BD-IPMNs preoperatively. This preoperative identification might improve treatment methods and promote personalized therapy in patients with BD-IPMNs.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-021-00395-6.

Development of a Novel Multiparametric MRI Radiomic Nomogram for Preoperative Evaluation of Early Recurrence in Resectable Pancreatic Cancer

Background

In pancreatic cancer, methods to predict early recurrence (ER) and identify patients at increased risk of relapse are urgently required.

Purpose

To develop a radiomic nomogram based on MR radiomics to stratify patients preoperatively and potentially improve clinical practice.

Study Type

Retrospective.

Population

We enrolled 303 patients from two medical centers. Patients with a disease‐free survival ≤12 months were assigned as the ER group (n = 130). Patients from the first medical center were divided into a training cohort (n = 123) and an internal validation cohort (n = 54). Patients from the second medical center were used as the external independent validation cohort (n = 126).

Field Strength/Sequence

3.0T axial T₁‐weighted (T₁‐w), T₂‐weighted (T₂‐w), contrast‐enhanced T₁‐weighted (CET₁‐w).

Assessment

ER was confirmed via imaging studies as MRI or CT. Risk factors, including clinical stage, CA19‐9, and radiomic‐related features of ER were assessed. In addition, to determine the intra‐ and interobserver reproducibility of radiomic features extraction, the intra‐ and interclass correlation coefficients (ICC) were calculated.

Statistical Tests

The area under the receiver‐operator characteristic (ROC) curve (AUC) was used to evaluate the predictive accuracy of the radiomic signature in both the training and test groups. The results of decision curve analysis (DCA) indicated that the radiomic nomogram achieved the most net benefit.

Results

The AUC values of ER evaluation for the radiomics signature were 0.80 (training cohort), 0.81 (internal validation cohort), and 0.78 (external validation cohort). Multivariate logistic analysis identified the radiomic signature, CA19‐9 level, and clinical stage as independent parameters of ER. A radiomic nomogram was then developed incorporating the CA19‐9 level and clinical stage. The AUC values for ER risk evaluation using the radiomic nomogram were 0.87 (training cohort), 0.88 (internal validation cohort), and 0.85 (external validation cohort).

Data Conclusion

The radiomic nomogram can effectively evaluate ER risks in patients with resectable pancreatic cancer preoperatively, which could potentially improve treatment strategies and facilitate personalized therapy in pancreatic cancer.

Level of Evidence: 4

Technical Efficacy: Stage 4

J. Magn. Reson. Imaging 2020;52:231–245.

Accuracy of diffusion-weighted imaging-magnetic resonance in differentiating functional from non-functional pituitary macro-adenoma and classification of tumor consistency

PURPOSE

The purpose of this study was to determine the accuracy of selected first or second-order histogram features in differentiation of functional types of pituitary macro-adenomas.

MATERIALS AND METHODS

Diffusion-weighted imaging magnetic resonance imaging was performed on 32 patients (age mean±standard deviation = 43.09 ± 11.02 years; min = 22 and max = 65 years) with pituitary macro-adenoma (10 with functional and 22 with non-functional tumors). Histograms of apparent diffusion coefficient were generated from regions of interest and selected first or second-order histogram features were extracted. Collagen contents of the surgically resected tumors were examined histochemically using Masson trichromatic staining and graded as containing <1%, 1-3%, and >3% of collagen.

RESULTS

Among selected first or second-order histogram features, uniformity ( p = 0.02), 75th percentile ( p = 0.03), and tumor smoothness ( p = 0.02) were significantly different between functional and non-functional tumors. Tumor smoothness > 5.7 × 10^-9 (area under the curve = 0.75; 0.56-0.89) had 70% (95% confidence interval = 34.8-93.3%) sensitivity and 33.33% (95% confidence interval = 14.6-57.0%) specificity for diagnosis of functional tumors. Uniformity ≤179.271 had a sensitivity of 60% (95% confidence interval = 26.2-87.8%) and specificity of 90.48% (95% confidence interval = 69.6-98.8%) with area under the curve = 0.76; 0.57-0.89. The 75th percentile >0.7 had a sensitivity of 80% (95% confidence interval = 44.4-97.5%) and specificity of 66.67% (95% confidence interval = 43.0-85.4%) for categorizing tumors to functional and non-functional types (area under the curve = 0.74; 0.55-0.88). Using these cut-offs, smoothness and uniformity are suggested as negative predictive indices (non-functional tumors) whereas 75th percentile is more applicable for diagnosis of functional tumors.

CONCLUSION

First or second-order histogram features could be helpful in differentiating functional vs non-functional pituitary macro-adenoma tumors.

Characterization of active and infiltrative tumorous subregions from normal tissue in brain gliomas using multiparametric MRI

BACKGROUND

Targeted localized biopsies and treatments for diffuse gliomas rely on accurate identification of tissue subregions, for which current MRI techniques lack specificity.

PURPOSE

To explore the complementary and competitive roles of a variety of conventional and quantitative MRI methods for distinguishing subregions of brain gliomas.

STUDY TYPE

Prospective.

POPULATION

Fifty-one tissue specimens were collected using image-guided localized biopsy surgery from 10 patients with newly diagnosed gliomas.

FIELD STRENGTH/SEQUENCE

Conventional and quantitative MR images consisting of pre- and postcontrast T1 w, T2 w, T2 -FLAIR, T2 -relaxometry, DWI, DTI, IVIM, and DSC-MRI were acquired preoperatively at 3T.

ASSESSMENT

Biopsy specimens were histopathologically attributed to glioma tissue subregion categories of active tumor (AT), infiltrative edema (IE), and normal tissue (NT) subregions. For each tissue sample, a feature vector comprising 15 MRI-based parameters was derived from preoperative images and assessed by a machine learning algorithm to determine the best multiparametric feature combination for characterizing the tissue subregions.

STATISTICAL TESTS

For discrimination of AT, IE, and NT subregions, a one-way analysis of variance (ANOVA) test and for pairwise tissue subregion differentiation, Tukey honest significant difference, and Games-Howell tests were applied (P < 0.05). Cross-validated feature selection and classification methods were implemented for identification of accurate multiparametric MRI parameter combination.

RESULTS

After exclusion of 17 tissue specimens, 34 samples (AT = 6, IE = 20, and NT = 8) were considered for analysis. Highest accuracies and statistically significant differences for discrimination of IE from NT and AT from NT were observed for diffusion-based parameters (AUCs >90%), and the perfusion-derived parameter as the most accurate feature in distinguishing IE from AT. A combination of "CBV, MD, T2 _ISO, FLAIR" parameters showed high diagnostic performance for identification of the three subregions (AUC ∼90%).

DATA CONCLUSION

Integration of a few quantitative along with conventional MRI parameters may provide a potential multiparametric imaging biomarker for predicting the histopathologically proven glioma tissue subregions.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;48:938-950.