Improving tumour heterogeneity MRI assessment with histograms. Br J Cancer. 2014;111:2205-2213. [PMID: 25268373 PMCID: PMC4264439 DOI: 10.1038/bjc.2014.512]

Combining Intravoxel Incoherent Motion Diffusion Weighted Imaging and Texture Analysis for a Nomogram to Predict Early Treatment Response to Concurrent Chemoradiotherapy in Cervical Cancer Patients

This study aimed to predict early treatment response to concurrent chemoradiotherapy (CCRT) by combining intravoxel incoherent motion diffusion weighted imaging (IVIM-DWI) with texture analysis (TA) for cervical cancer patients and to develop a nomogram for estimating the risk of residual tumor. Ninty-three cervical cancer patients underwent conventional MRI and IVIM-DWI before CCRT. We conducted TA using T2WI. The patients were allocated to partial response (PR) and complete response (CR) groups on the basis of posttreatment MRI. Multivariate logistic regression analysis on IVIM-DWI parameters and texture features was employed to filter the independent predictors and construct the predictive nomogram. Its discrimination and calibration performances were estimated. Multivariate analysis on the IVIM-DWI parameters showed that D and f were independent predictors (OR = 4.029 and 0.889, resp.; p < 0.05). However, the multivariate analysis on the texture features indicated that GLCM-correlation, GLRLM-LRE, and GLSZM-ZE were independent predictors (OR = 43.789, 9.774, and 23.738, resp.;p < 0.05). The combination of IVIM-DWI parameters and texture features exhibited the highest predictive performance (AUC = 0.975). The nomogram to identify the patients with high-risk residual tumors exhibited an acceptable predictive performance and stability with a C-index of 0.953. Decision curve analysis demonstrated the clinical use of the nomogram. The results demonstrate that D, f, GLCM-correlation, GLRLM-LRE, and GLSZM-ZE were independent predictors for cervical cancer. The nomogram combining IVIM-DWI parameters and texture features makes it possible to identify cervical cancer patients at a high risk of residual tumor after CCRT.

The added value of full and reduced field-of-view apparent diffusion coefficient maps for the evaluation of extramural venous invasion in rectal cancer

OBJECTIVE

To investigate the added value of the quantitative analysis of full and reduced field-of-view apparent diffusion coefficient (fADC and rADC) maps for evaluating extramural venous invasion (EMVI) in rectal cancer.

MATERIALS AND METHODS

A total of 94 rectal cancer patients who underwent direct surgical resection were enrolled in this prospective study. The EMVI status of each patient was evaluated on T2-weighted imaging. The mean values of fADC and rADC within the whole tumor were obtained, and histogram parameters were also extracted. Multivariate binary logistic regression analysis was used to analyze independent predictors of EMVI and construct combined models. Receiver operating characteristic (ROC) curves were applied to assess the diagnostic performance.

RESULTS

The energy, skewness, total energy, and kurtosis of fADC map, and the energy and total energy of rADC map were significantly different between the EMVI-positive and EMVI-negative groups (all P < 0.05). Multivariate logistic regression analysis revealed that kurtosis of fADC and circumferential percentage of tumor were independent predictors of EMVI (odds ratio 1.684 and 2.647, P = 0.020 and 0.009). These two parameters combined with subjective evaluation demonstrated the superior diagnostic performance with the area under the ROC curve, sensitivity, specificity, and accuracy of 0.841 (95% CI 0.752-0.909), 0.739, 0.803, and 0.809, respectively.

CONCLUSION

Whole-tumor histogram analysis of ADC map could potentially provide additional information to improve the diagnostic efficiency for assessing EMVI in rectal cancer, which may be beneficial for treatment decision-making.

Which Parameter Influences Local Disease-Free Survival after Radiation Therapy Due to Osteolytic Metastasis? A Retrospective Study with Pre- and Post-Radiation Therapy MRI including Diffusion-Weighted Images

Although radiation therapy (RT) plays an important role in the palliation of localized bone metastases, there is no consensus on a reliable method for evaluating treatment response. Therefore, we retrospectively evaluated the potential of magnetic resonance imaging (MRI) using apparent diffusion coefficient (ADC) maps and conventional images in whole-tumor volumetric analysis of texture features for assessing treatment response after RT. For this purpose, 28 patients who received RT for osteolytic bone metastasis and underwent both pre- and post-RT MRI were enrolled. Volumetric ADC histograms and conventional parameters were compared. Cox regression analyses were used to determine whether the change ratio in these parameters was associated with local disease progression-free survival (LDPFS). The ADC_maximum, ADC_mean, ADC_median, ADC_SD, maximum diameter, and volume of the target lesions after RT significantly increased. Change ratios of ADC_mean < 1.41, tumor diameter ≥ 1.17, and tumor volume ≥ 1.55 were significant predictors of poor LDPFS. Whole-tumor volumetric ADC analysis might be utilized for monitoring patient response to RT and potentially useful in predicting clinical outcomes.

Histogram analysis of dynamic contrast-enhanced magnetic resonance imaging in the differential diagnosis of parotid tumors

Objective

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) histograms were used to investigate whether their parameters can distinguish between benign and malignant parotid gland tumors and further differentiate tumor subgroups.

Materials and methods

A total of 117 patients (32 malignant and 85 benign) who had undergone DCE-MRI for pretreatment evaluation were retrospectively included. Histogram parameters including mean, median, entropy, skewness, kurtosis and 10th, 90th percentiles were calculated from time to peak (TTP) (s), wash in rate (WIR) (l/s), wash out rate (WOR) (l/s), and maximum relative enhancement (MRE) (%) mono-exponential models. The Mann–Whitney U test was used to compare the differences between the benign and malignant groups. The diagnostic value of each significant parameter was determined on Receiver operating characteristic (ROC) analysis. Multivariate stepwise logistic regression analysis was used to identify the independent predictors of the different tumor groups.

Results

For both the benign and malignant groups and the comparisons among the subgroups, the parameters of TTP and MRE showed better performance among the various parameters. WOR can be used as an indicator to distinguish Warthin’s tumors from other tumors. Warthin’s tumors showed significantly lower values on 10th MRE and significantly higher values on skewness TTP and 10th WOR, and the combination of 10th MRE, skewness TTP and 10th WOR showed optimal diagnostic performance (AUC, 0.971) and provided 93.12% sensitivity and 96.70% specificity. After Warthin’s tumors were removed from among the benign tumors, malignant parotid tumors showed significantly lower values on the 10th TTP (AUC, 0.847; sensitivity 90.62%; specificity 69.09%; P < 0.05) and higher values on skewness MRE (AUC, 0.777; sensitivity 71.87%; specificity 76.36%; P < 0.05).

Conclusion

DCE-MRI histogram parameters, especially TTP and MRE parameters, show promise as effective indicators for identifying and classifying parotid tumors. Entropy TTP and kurtosis MRE were found to be independent differentiating variables for malignant parotid gland tumors. The 10th WOR can be used as an indicator to distinguish Warthin’s tumors from other tumors.

Delta radiomics analysis of Magnetic Resonance guided radiotherapy imaging data can enable treatment response prediction in pancreatic cancer

Background

Magnetic Resonance Image guided Stereotactic body radiotherapy (MRgRT) is an emerging technology that is increasingly used in treatment of visceral cancers, such as pancreatic adenocarcinoma (PDAC). Given the variable response rates and short progression times of PDAC, there is an unmet clinical need for a method to assess early RT response that may allow better prescription personalization. We hypothesize that quantitative image feature analysis (radiomics) of the longitudinal MR scans acquired before and during MRgRT may be used to extract information related to early treatment response.

Methods

Histogram and texture radiomic features (n = 73) were extracted from the Gross Tumor Volume (GTV) in 0.35T MRgRT scans of 26 locally advanced and borderline resectable PDAC patients treated with 50 Gy RT in 5 fractions. Feature ratios between first (F1) and last (F5) fraction scan were correlated with progression free survival (PFS). Feature stability was assessed through region of interest (ROI) perturbation.

Results

Linear normalization of image intensity to median kidney value showed improved reproducibility of feature quantification. Histogram skewness change during treatment showed significant association with PFS (p = 0.005, HR = 2.75), offering a potential predictive biomarker of RT response. Stability analyses revealed a wide distribution of feature sensitivities to ROI delineation and was able to identify features that were robust to variability in contouring.

Conclusions

This study presents a proof-of-concept for the use of quantitative image analysis in MRgRT for treatment response prediction and providing an analysis pipeline that can be utilized in future MRgRT radiomic studies.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-021-01957-5.

Evaluation of response in patients with hepatocellular carcinoma treated with intratumoral dendritic cell vaccination using intravoxel incoherent motion (IVIM) MRI and histogram analysis

BACKGROUND

Immunotherapy of hepatocellular carcinoma (HCC) is an emerging method with promising results. Immunotherapy can have an antitumor effect without affecting tumor size, calling for functional imaging methods for response evaluation.

PURPOSE

To evaluate the response to intratumoral injections with the immune primer ilixadencel in HCCs with diffusion-weighted magnetic resonance imaging (DW-MRI) using intravoxel incoherent motion (IVIM) and histogram analysis.

MATERIAL AND METHODS

A total of 17 patients with advanced HCC were treated with intratumoral injections with ilixadencel on three occasions 2-5 weeks apart. The patients were examined with IVIM before each injection as well as approximately three months after the first injection.

RESULTS

The 10th percentile of perfusion-related parameter D* decreased significantly after the first and second intratumoral injections of ilixadencel compared to baseline (P < 0.05). There was a non-significant trend of lower median region of interest f (perfusion fraction) before injection 2 compared to baseline (P = 0.07). There were significant correlations between the 10th percentile and median of D at baseline and change in tumor size after three months (r = 0.79, P < 0.01 and r = 0.72, P < 0.05, respectively).

CONCLUSION

DW-MRI with IVIM and histogram analysis revealed significant reductions of D* early after treatment as well as an association between D at baseline and smaller tumor growth at three months. The lower percentiles (10th and 50th) were found more important. Further research is needed to confirm our preliminary findings of reduced perfusion after ilixadencel vaccinations, suggesting a treatment effect on HCC.

CT Texture analysis and CT scores for characterization of fluid collections

Background

Texture analysis derived from Computed tomography (CT) might be able to better characterize fluid collections undergoing CT-guided percutaneous drainage treatment. The present study tested, whether texture analysis can reflect microbiology results in fluid collections suspicious for septic focus.

Methods

Overall, 320 patients with 402 fluid collections were included into this retrospective study. All fluid collections underwent CT-guided drainage treatment and were microbiologically evaluated. Clinically, serologically parameters and conventional imaging findings as well as textures features were included into the analysis. A new CT score was calculated based upon imaging features alone. Established CT scores were used as a reference standard.

Results

The present score achieved a sensitivity of 0.78, a specificity of 0.69, area under curve (AUC 0.82). The present score and the score by Gnannt et al. (AUC 0.81) were both statistically better than the score by Radosa et al. (AUC 0.75). Several texture features were statistically significant between infected fluid collections and sterile fluid collections, but these features were not significantly better compared with conventional imaging findings.

Conclusions

Texture analysis is not superior to conventional imaging findings for characterizing fluid collections. A novel score was calculated based upon imaging parameters alone with similar diagnostic accuracy compared to established scores using imaging and clinical features.

Classification of MR-Detected Additional Lesions in Patients With Breast Cancer Using a Combination of Radiomics Analysis and Machine Learning

Objective

This study was conducted in order to investigate the feasibility of using radiomics analysis (RA) with machine learning algorithms based on breast magnetic resonance (MR) images for discriminating malignant from benign MR-detected additional lesions in patients with primary breast cancer.

Materials and Methods

One hundred seventy-four MR-detected additional lesions (benign, n = 86; malignancy, n = 88) from 158 patients with ipsilateral primary breast cancer from a tertiary medical center were included in this retrospective study. The entire data were randomly split to training (80%) and independent test sets (20%). In addition, 25 patients (benign, n = 21; malignancy, n = 15) from another tertiary medical center were included for the external test. Radiomics features that were extracted from three regions-of-interest (ROIs; intratumor, peritumor, combined) using fat-saturated T1-weighted images obtained by subtracting pre- from postcontrast images (SUB) and T2-weighted image (T2) were utilized to train the support vector machine for the binary classification. A decision tree method was utilized to build a classifier model using clinical imaging interpretation (CII) features assessed by radiologists. Area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, and specificity were used to compare the diagnostic performance.

Results

The RA models trained using radiomics features from the intratumor-ROI showed comparable performance to the CII model (accuracy, AUROC: 73.3%, 69.6% for the SUB RA model; 70.0%, 75.1% for the T2 RA model; 73.3%, 72.0% for the CII model). The diagnostic performance increased when the radiomics and CII features were combined to build a fusion model. The fusion model that combines the CII features and radiomics features from multiparametric MRI data demonstrated the highest performance with an accuracy of 86.7% and an AUROC of 91.1%. The external test showed a similar pattern where the fusion models demonstrated higher levels of performance compared with the RA- or CII-only models. The accuracy and AUROC of the SUB+T2 RA+CII model in the external test were 80.6% and 91.4%, respectively.

Conclusion

Our study demonstrated the feasibility of using RA with machine learning approach based on multiparametric MRI for quantitatively characterizing MR-detected additional lesions. The fusion model demonstrated an improved diagnostic performance over the models trained with either RA or CII alone.

Grading of meningioma tumors based on analyzing tumor volumetric histograms obtained from conventional MRI and apparent diffusion coefficient images

Background

Our purpose was to evaluate the application of volumetric histogram parameters obtained from conventional MRI and apparent diffusion coefficient (ADC) images for grading the meningioma tumors.

Results

Tumor volumetric histograms of preoperative MRI images from 45 patients with the diagnosis of meningioma at different grades were analyzed to find the histogram parameters. Kruskal-Wallis statistical test was used for comparison between the parameters obtained from different grades. Multi-parametric regression analysis was used to find the model and parameters with high predictive value for the classification of meningioma. Mode; standard deviation on post-contrast T1WI, T2-FLAIR, and ADC images; kurtosis on post-contrast T1WI and T2-FLAIR images; mean and several percentile values on ADC; and post-contrast T1WI images showed significant differences among different tumor grades (P < 0.05). The multi-parametric linear regression showed that the ADC histogram parameters model had a higher predictive value, with cutoff values of 0.212 (sensitivity = 79.6%, specificity = 84.3%) and 0.180 (sensitivity = 70.9%, specificity = 80.8%) for differentiating the grade I from II, and grade II from III, respectively.

Conclusions

The multi-parametric model of volumetric histogram parameters in some of the conventional MRI series (i.e., post-contrast T1WI and T2-FLAIR images) along with the ADC images are appropriate for predicting the meningioma tumors’ grade.

Whole-body diffusion-weighted MRI of normal lymph nodes: prospective apparent diffusion coefficient histogram and nodal distribution analysis in a healthy cohort

BACKGROUND

Whole body DWI (WB-DWI) enables the identification of lymph nodes for disease evaluation. However, quantitative data of benign lymph nodes across the body are lacking to allow meaningful comparison of diseased states. We evaluated apparent diffusion coefficient (ADC) histogram parameters of all visible lymph nodes in healthy volunteers on WB-DWI and compared differences in nodal ADC values between anatomical regions.

METHODS

WB-DWI was performed on a 1.5 T MR system in 20 healthy volunteers (7 female, 13 male, mean age 35 years). The b900 images were evaluated by two radiologists and all visible nodes from the neck to groin areas were segmented and individual nodal median ADC recorded. All segmented nodes in a patient were summated to generate the total nodal volume. Descriptors of the global ADC histogram, derived from individual node median ADCs, including mean, median, skewness and kurtosis were obtained for the global volume and each nodal region per patient. ADC values between nodal regions were compared using one-way ANOVA with Bonferroni post hoc tests and a p-value ≤0.05 was deemed statistically significant.

RESULTS

One thousand sixty-seven lymph nodes were analyzed. The global mean and median ADC of all lymph nodes were 1.12 ± 0.27 (10^- 3 mm²/s) and 1.09 (10^- 3 mm²/s). The average median ADC skewness was 0.25 ± 0.02 and average median ADC kurtosis was 0.34 ± 0.04. The ADC values of intrathoracic, portal and retroperitoneal nodes were significantly higher (1.53 × 10^- 3, 1.75 × 10^- 3 and 1.58 × 10^- 3 mm²/s respectively) than in other regions. Intrathoracic, portal and mesenteric nodes were relatively uncommon, accounting for only 3% of the total nodes segmented.

CONCLUSIONS

The global mean and median ADC of all lymph nodes were 1.12 ± 0.27 (10^- 3 mm²/s) and 1.09 (10^- 3 mm²/s). Intrathoracic, portal and retroperitoneal nodes display significantly higher ADCs. Normal intrathoracic, portal and mesenteric nodes are infrequently visualized on WB-DWI of healthy individuals.

TRIAL REGISTRATION

Royal Marsden Hospital committee for clinical research registration number 09/H0801/86, 19.10.2009.

CT Texture Analysis of Pulmonary Neuroendocrine Tumors-Associations with Tumor Grading and Proliferation

Texture analysis derived from computed tomography (CT) might be able to provide clinically relevant imaging biomarkers and might be associated with histopathological features in tumors. The present study sought to elucidate the possible associations between texture features derived from CT images with proliferation index Ki-67 and grading in pulmonary neuroendocrine tumors. Overall, 38 patients (n = 22 females, 58%) with a mean age of 60.8 ± 15.2 years were included into this retrospective study. The texture analysis was performed using the free available Mazda software. All tumors were histopathologically confirmed. In discrimination analysis, "S(1,1)SumEntrp" was significantly different between typical and atypical carcinoids (mean 1.74 ± 0.11 versus 1.79 ± 0.14, p = 0.007). The correlation analysis revealed a moderate positive association between Ki-67 index with the first order parameter kurtosis (r = 0.66, p = 0.001). Several other texture features were associated with the Ki-67 index, the highest correlation coefficient showed "S(4,4)InvDfMom" (r = 0.59, p = 0.004). Several texture features derived from CT were associated with the proliferation index Ki-67 and might therefore be a valuable novel biomarker in pulmonary neuroendocrine tumors. "Sumentrp" might be a promising parameter to aid in the discrimination between typical and atypical carcinoids.

Artificial Intelligence and Deep Learning of Head and Neck Cancer

Artificial intelligence (AI) algorithms, particularly deep learning, have developed to the point that they can be applied in image recognition tasks. The use of AI in medical imaging can guide radiologists to more accurate image interpretation and diagnosis in radiology. The software will provide data that we cannot extract from the images. The rapid development in computational capabilities supports the wide applications of AI in a range of cancers. Among those are its widespread applications in head and neck cancer.

The Histogram Analysis of Intravoxel Incoherent Motion-Kurtosis Model in the Diagnosis and Grading of Prostate Cancer-A Preliminary Study

Objectives

This study was conducted in order to explore the value of histogram analysis of the intravoxel incoherent motion-kurtosis (IVIM-kurtosis) model in the diagnosis and grading of prostate cancer (PCa), compared with monoexponential model (MEM).

Materials and Methods

Thirty patients were included in this study. Single-shot echo-planar imaging (SS-EPI) diffusion-weighted images (b-values of 0, 20, 50, 100, 200, 500, 1,000, 1,500, 2,000 s/mm²) were acquired. The pathologies were confirmed by in-bore MR-guided biopsy. The postprocessing and measurements were processed using the software tool Matlab R2015b for the IVIM-kurtosis model and MEM. Regions of interest (ROIs) were drawn manually. Mean values of D, D*, f, K, ADC, and their histogram parameters were acquired. The values of these parameters in PCa and benign prostatic hyperplasia (BPH)/prostatitis were compared. Receiver operating characteristic (ROC) curves were used to investigate the diagnostic efficiency. The Spearman test was used to evaluate the correlation of these parameters and Gleason scores (GS) of PCa.

Results

For the IVIM-kurtosis model, D (mean, 10th, 25th, 50th, 75th, 90th), D* (90th), and f (10th) were significantly lower in PCa than in BPH/prostatitis, while D (skewness), D* (kurtosis), and K (mean, 75th, 90th) were significantly higher in PCa than in BPH/prostatitis. For MEM, ADC (mean, 10th, 25th, 50th, 75th, 90th) was significantly lower in PCa than in BPH/prostatitis. The area under the ROC curve (AUC) of the IVIM-kurtosis model was higher than MEM, without significant differences (z = 1.761, P = 0.0783). D (mean, 50th, 75th, 90th), D* (mean, 10th, 25th, 50th, 75th), and f (skewness, kurtosis) correlated negatively with GS, while D (kurtosis), D* (skewness, kurtosis), f (mean, 75th, 90th), and K (mean, 75th, 90th) correlated positively with GS. The histogram parameters of ADC did not show correlations with GS.

Conclusion

The IVIM-kurtosis model has potential value in the differential diagnosis of PCa and BPH/prostatitis. IVIM-kurtosis histogram analysis may provide more information in the grading of PCa than MEM.

Virtual Contrast-enhanced Magnetic Resonance Images Synthesis for Patients With Nasopharyngeal Carcinoma Using Multimodality-guided Synergistic Neural Network

PURPOSE

To investigate a novel deep-learning network that synthesizes virtual contrast-enhanced T1-weighted (vceT1w) magnetic resonance images (MRI) from multimodality contrast-free MRI for patients with nasopharyngeal carcinoma (NPC).

METHODS AND MATERIALS

This article presents a retrospective analysis of multiparametric MRI, with and without contrast enhancement by gadolinium-based contrast agents (GBCAs), obtained from 64 biopsy-proven cases of NPC treated at Hong Kong Queen Elizabeth Hospital. A multimodality-guided synergistic neural network (MMgSN-Net) was developed to leverage complementary information between contrast-free T1-weighted and T2-weighted MRI for vceT1w MRI synthesis. Thirty-five patients were randomly selected for model training, whereas 29 patients were selected for model testing. The synthetic images generated from MMgSN-Net were quantitatively evaluated against real GBCA-enhanced T1-weighted MRI using a series of statistical evaluating metrics, which include mean absolute error (MAE), mean squared error (MSE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Qualitative visual assessment between the real and synthetic MRI was also performed. Effectiveness of our MMgSN-Net was compared with 3 state-of-the-art deep-learning networks, including U-Net, CycleGAN, and Hi-Net, both quantitatively and qualitatively. Furthermore, a Turing test was performed by 7 board-certified radiation oncologists from 4 hospitals for assessing authenticity of the synthesized vceT1w MRI against the real GBCA-enhanced T1-weighted MRI.

RESULTS

Results from the quantitative evaluations demonstrated that our MMgSN-Net outperformed U-Net, CycleGAN and Hi-Net, yielding the top-ranked scores in averaged MAE (44.50 ± 13.01), MSE (9193.22 ± 5405.00), SSIM (0.887 ± 0.042), and PSNR (33.17 ± 2.14). Furthermore, the mean accuracy of the 7 readers in the Turing tests was determined to be 49.43%, equivalent to random guessing (ie, 50%) in distinguishing between real GBCA-enhanced T1-weighted and synthetic vceT1w MRI. Qualitative evaluation indicated that MMgSN-Net gave the best approximation to the ground-truth images, particularly in visualization of tumor-to-muscle interface and the intratumor texture information.

CONCLUSIONS

Our MMgSN-Net was capable of synthesizing highly realistic vceT1w MRI that outperformed the 3 comparable state-of-the-art networks.

The history of magnetic resonance imaging and its reflections in Acta Radiologica

The first reports in Acta Radiologica on magnetic resonance imaging (MRI) were published in 1984, four years after the first commercial MR scanners became available. For the first two years, all MR papers originated from the USA. Nordic contributions started in 1986, and until 2020, authors from 44 different countries have published MR papers in Acta Radiologica. Papers on MRI have constituted, on average, 30%-40% of all published original articles in Acta Radiologica, with a high of 49% in 2019. The MR papers published since 1984 document tremendous progress in several areas such as magnet and coil design, motion compensation techniques, faster image acquisitions, new image contrast, contrast-enhanced MRI, functional MRI, and image analysis. In this historical review, all of these aspects of MRI are discussed and related to Acta Radiologica papers.

Tangent functional canonical correlation analysis for densities and shapes, with applications to multimodal imaging data

It is quite common for functional data arising from imaging data to assume values in infinite-dimensional manifolds. Uncovering associations between two or more such nonlinear functional data extracted from the same object across medical imaging modalities can assist development of personalized treatment strategies. We propose a method for canonical correlation analysis between paired probability densities or shapes of closed planar curves, routinely used in biomedical studies, which combines a convenient linearization and dimension reduction of the data using tangent space coordinates. Leveraging the fact that the corresponding manifolds are submanifolds of unit Hilbert spheres, we describe how finite-dimensional representations of the functional data objects can be easily computed, which then facilitates use of standard multivariate canonical correlation analysis methods. We further construct and visualize canonical variate directions directly on the space of densities or shapes. Utility of the method is demonstrated through numerical simulations and performance on a magnetic resonance imaging dataset of glioblastoma multiforme brain tumors.

Progress of MRI Radiomics in Hepatocellular Carcinoma

Background

Hepatocellular carcinoma (HCC) is the sixth most common cancer in the world and the third leading cause of cancer-related death. Although the diagnostic scheme of HCC is currently undergoing refinement, the prognosis of HCC is still not satisfactory. In addition to certain factors, such as tumor size and number and vascular invasion displayed on traditional imaging, some histopathological features and gene expression parameters are also important for the prognosis of HCC patients. However, most parameters are based on postoperative pathological examinations, which cannot help with preoperative decision-making. As a new field, radiomics extracts high-throughput imaging data from different types of images to build models and predict clinical outcomes noninvasively before surgery, rendering it a powerful aid for making personalized treatment decisions preoperatively.

Objective

This study reviewed the workflow of radiomics and the research progress on magnetic resonance imaging (MRI) radiomics in the diagnosis and treatment of HCC.

Methods

A literature review was conducted by searching PubMed for search of relevant peer-reviewed articles published from May 2017 to June 2021.The search keywords included HCC, MRI, radiomics, deep learning, artificial intelligence, machine learning, neural network, texture analysis, diagnosis, histopathology, microvascular invasion, surgical resection, radiofrequency, recurrence, relapse, transarterial chemoembolization, targeted therapy, immunotherapy, therapeutic response, and prognosis.

Results

Radiomics features on MRI can be used as biomarkers to determine the differential diagnosis, histological grade, microvascular invasion status, gene expression status, local and systemic therapeutic responses, and prognosis of HCC patients.

Conclusion

Radiomics is a promising new imaging method. MRI radiomics has high application value in the diagnosis and treatment of HCC.

Systematic review: radiomics for the diagnosis and prognosis of hepatocellular carcinoma

BACKGROUND

Advances in imaging technology have the potential to transform the early diagnosis and treatment of hepatocellular carcinoma (HCC) through quantitative image analysis. Computational "radiomic" techniques extract biomarker information from images which can be used to improve diagnosis and predict tumour biology.

AIMS

To perform a systematic review on radiomic features in HCC diagnosis and prognosis, with a focus on reporting metrics and methodologic standardisation.

METHODS

We performed a systematic review of all full-text articles published from inception through December 1, 2019. Standardised data extraction and quality assessment metrics were applied to all studies.

RESULTS

A total of 54 studies were included for analysis. Radiomic features demonstrated good discriminatory performance to differentiate HCC from other solid lesions (c-statistics 0.66-0.95), and to predict microvascular invasion (c-statistic 0.76-0.92), early recurrence after hepatectomy (c-statistics 0.71-0.86), and prognosis after locoregional or systemic therapies (c-statistics 0.74-0.81). Common stratifying features for diagnostic and prognostic radiomic tools included analyses of imaging skewness, analysis of the peritumoural region, and feature extraction from the arterial imaging phase. The overall quality of the included studies was low, with common deficiencies in both internal and external validation, standardised imaging segmentation, and lack of comparison to a gold standard.

CONCLUSIONS

Quantitative image analysis demonstrates promise as a non-invasive biomarker to improve HCC diagnosis and management. However, standardisation of protocols and outcome measurement, sharing of algorithms and analytic methods, and external validation are necessary prior to widespread application of radiomics to HCC diagnosis and prognosis in clinical practice.

The Value of Magnetic Resonance Imaging Histograms in the Preoperative Differential Diagnosis of Endometrial Stromal Sarcoma and Degenerative Hysteromyoma

Objective: The present study aimed to explore the application value of magnetic resonance imaging (MRI) histograms with multiple sequences in the preoperative differential diagnosis of endometrial stromal sarcoma (ESS) and degenerative hysteromyoma (DH).

Methods: The clinical and preoperative MRI data of 20 patients with pathologically confirmed ESS and 24 patients with pathologically confirmed DH were retrospectively analyzed, forming the two study groups. Mazda software was used to select the MRI layer with the largest tumor diameter in T2WI, the apparent diffusion coefficient (ADC), and enhanced T1WI (T₁CE) images. The region of interest (ROI) was outlined for gray-scale histogram analysis. Nine parameters—the mean, variance, kurtosis, skewness, 1st percentile, 10th percentile, 50th percentile, 90th percentile, and 99th percentile—were obtained for intergroup analysis, and the receiver operating curves (ROCs) were plotted to analyze the differential diagnostic efficacy for each parameter.

Results: In the T2WI histogram, the differences between the two groups in seven of the parameters (mean, skewness, 1st percentile, 10th percentile, 50th percentile, 90th percentile, and 99th percentile) were statistically significant (P < 0.05). In the ADC histogram, the differences between the two groups in three of the parameters (skewness, 10th percentile, and 50th percentile) were statistically significant (P < 0.05). In the T₁CE histogram, no significant differences were found between the two groups in any of the parameters (all P > 0.05). Of the nine parameters, the 50th percentile was found to have the best diagnostic efficacy. In the T2WI histogram, ROC curve analysis of the 50th percentile yielded the best area under the ROC curve (AUC; 0.742), sensitivity of 70%, and specificity of 83.3%. In the ADC histogram, ROC curve analysis of the 50th percentile yielded the best area under the ROC curve (AUC; 0.783), sensitivity of 81%, and specificity of 76.9%.

Conclusion: The parameters of the mean, 10th percentile and 50th percentile in the T2WI histogram have good diagnostic efficacy, providing new methods and ideas for clinical diagnosis.

Application of first-order feature analysis of DWI-ADC in rare malignant mesenchymal tumours of the maxillofacial region

BACKGROUND

To research the first-order features of apparent diffusion coefficient (ADC) values on diffusion-weighted magnetic resonance imaging (DWI) in maxillofacial malignant mesenchymal tumours.

METHODS

The clinical data of 12 patients with rare malignant mesenchymal tumours of the maxillofacial region (6 cases of sarcoma and 6 cases of lymphoma) treated in the hospital from May 2018 to June 2020 and were confirmed by postoperative pathology were retrospectively analyzed. The patients were all examined by 1.5T magnetic resonance imaging. PyRadiomics were used to extract radiomics imaging first-order features. Group differences in quantitative variables were examined using independent-samples t-tests.

RESULTS

The voxels number of ADC_mean and ADC_median of sarcoma tissues were 44.9124 and 44.2064, respectively, significantly higher than those in lymphoma tissues (ADC_mean (- 68.8379) and ADC_median (- 74.0045)), the difference considered statistically significant, so do the ADC_kurt and ADC_skew.

CONCLUSIONS

The statistical difference of ADC_mean and ADC_median is significant, it is consistent with the outcome of the manual measurement of the ADC mean value of the most significant cross-section of twelve cases of lymphoma. Development of tumour volume based on the ADC parameter map of DWI demonstrates that the first-order ADC radiomics features analysis can provide new imaging markers for the differentiation of maxillofacial sarcoma and lymphoma. Therefore, first-order ADC features of ADC_kurt combined ADC_skew may improve the diagnosis level.

Characterizing Fibrosis and Inflammation in a Partial Bile Duct Ligation Mouse Model by Multiparametric Magnetic Resonance Imaging

Background

Partial bile duct ligation (PBDL) model is a reliable cholestatic fibrosis experimental model that showed complex histopathological changes. Magnetic resonance imaging (MRI) features of PBDL have not been well characterized.

Purpose

To investigate the potential of MRI parameters in assessing fibrosis in PBDL and explore the relationships between MRI and pathological features.

Animal Model

Established PBDL models.

Population

Fifty‐four mice were randomly divided into four timepoints PBDL groups and one sham group.

Field Strength/Sequence

3.0 T; MRI sequences included T1‐weighted fast spin‐echo (FSE), T2‐weighted single shot FSE, variable flip angle T1 mapping, multi‐echo SE T2 mapping, multi‐echo gradient‐echo T2* mapping, and multi‐b‐value diffusion‐weighted imaging.

Assessment

MRI examination was performed at the corresponding timepoints after surgery. Native T1, ΔT1 (T1native‐T1post), T2, T2*, apparent diffusion coefficient (ADC) values, histogram parameters (skewness and kurtosis), intravoxel incoherent motion parameters (f, D, and D^*) within the entire ligated (PBDL), non‐ligated liver (PBDL), and whole liver (sham) were obtained. Fibrosis and inflammation were assessed in Masson and H&E staining slices using the Metavir and activity scoring system.

Statistical Tests

One‐way ANOVA, Spearman's rank correlation, and receiver operating characteristic curves were performed. P < 0.05 was considered statistically significant.

Results

Fibrosis and inflammation were finally staged as F3 and A3 in ligated livers but were not observed in non‐ligated or sham livers. Ligated livers displayed significantly elevated native T1, ΔT1, T2, and reduced ADC and T2^* than other livers. Spearman's correlation showed better correlation with inflammation (r = 0.809) than fibrosis (r = 0.635) in T2 and both ΔT1 and ADC showed stronger correlation with fibrosis (r = 0.704 and r = −0.718) than inflammation (r = 0.564 and r = −0.550). Area under the curve (AUC) for ΔT1 performed the highest (0.896). When combined with all relative parameters, AUC increased to 0.956.

Data Conclusion

Multiparametric MRI can evaluate and differentiate pathological changes in PBDL. ΔT1 and ADC better correlated with fibrosis while T2 stronger with inflammation.

Level of Evidence

1

Technical Efficacy

Stage 2

Whole-lesion ADC histogram analysis versus single-slice ADC measurement for the differentiation of benign and malignant soft tissue tumors

PURPOSE

To evaluate and compare the diagnostic performances of whole-lesion apparent diffusion coefficient (ADC) histogram analysis and single-slice ADC measurement in the differentiation of benign and malignant soft tissue tumors.

METHODS

Fifty-three patients (mean age: 48.5 ± 21.4) with soft tissue tumors (27 benign and 26 malignant) were evaluated with diffusion-weighted MRI. Whole-lesion ADC histogram parameters (mean, median, 10^th percentile, 90^th percentile, minimum, maximum, range, mean absolute deviation, interquartile range, kurtosis, skewness, root mean squared, variance and inhomogeneity) of the lesions were measured using the whole solid tumor volume region of interest (ROI). In other sessions, five ROIs were manually drawn on the tumor slices, and mean ADC and minimum ADC of the measurements were calculated. Diagnostic accuracies of the two methods were assessed and compared.

RESULTS

Mean, median, minimum, 10^th percentile, 90^th percentile, range, root mean squared and inhomogeneity of ADC histogram analysis, and mean ADC and minimum ADC of single-slice ADC measurement were significantly different between malignant and benign lesions (p < 0.001 - p = 0.002). Among the ADC histogram parameters, 10^th percentile had the highest diagnostic performance (AUC = 0.825) followed by mean (AUC = 0.792) and median (AUC = 0.789). For the single-slice ADC measurement, the AUC of mean ADC and minimum ADC were 0.842 and 0.786, respectively. Mean ADC of single-slice measurement had a similar diagnostic performance with the 10^th percentile, mean, and median of ADC histogram analysis (p = 0.070-1.000).

CONCLUSIONS

Both whole-lesion ADC histogram analysis and single-slice ADC measurement can differentiate benign and malignant soft tissue tumors with similar diagnostic performances.

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.

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.

Performances of Whole Tumor Texture Analysis Based on MRI: Predicting Preoperative T Stage of Rectal Carcinomas

Objective

To determine whether there is a correlation between texture features extracted from high-resolution T2-weighted imaging (HR-T2WI) or apparent diffusion coefficient (ADC) maps and the preoperative T stage (stages T1–2 versus T3–4) in rectal carcinomas.

Materials and Methods

One hundred and fifty four patients with rectal carcinomas who underwent preoperative HR-T2WI and diffusion-weighted imaging were enrolled. Patients were divided into training (n = 89) and validation (n = 65) cohorts. 3D Slicer was used to segment the entire volume of interest for whole tumors based on HR-T2WI and ADC maps. The least absolute shrinkage and selection operator (LASSO) was performed to select feature. The significantly difference was tested by the independent sample t-test and Mann-Whitney U test. The support vector machine (SVM) model was used to develop classification models. The correlation between features and T stage was assessed by Spearman’s correlation analysis. Multivariate logistic regression analysis was performed to identify independent predictors of tumor invasion. The performance of classifiers was evaluated by the receiver operating characteristic (ROC) curves.

Results

The wavelet HHH NGTDM strength (R_S = -0.364, P < 0.001) from HR-T2WI was an independent predictor of stage T3–4 tumors. The shape maximum 2D diameter column (R_S = 0.431, P < 0.001), log σ = 5.0 mm 3D first-order maximum (R_S = 0.276, P = 0.009), and log σ = 5.0 mm 3D first-order interquartile range (R_S = -0.229, P = 0.032) from ADC maps were independent predictors. In training cohorts, the classification models from HR-T2WI, ADC maps and the combination of two achieved the area under the ROC curves (AUCs) of 0.877, 0.902 and 0.941, with the accuracy of 79.78%, 89.86% and 89.89%, respectively. In validation cohorts, the three models achieved AUCs of 0.845, 0.881 and 0.910, with the accuracy of 78.46%, 83.08% and 87.69%, respectively.

Conclusions

Texture analysis based on ADC maps shows more potential than HR-T2WI in identifying preoperative T stage in rectal carcinomas. The combined application of HR-T2WI and ADC maps may help to improve the accuracy of preoperative diagnosis of rectal cancer invasion.

Tumor habitat analysis by magnetic resonance imaging distinguishes tumor progression from radiation necrosis in brain metastases after stereotactic radiosurgery

OBJECTIVES

The identification of viable tumor after stereotactic radiosurgery (SRS) is important for future targeted therapy. This study aimed to determine whether tumor habitat on structural and physiologic MRI can distinguish viable tumor from radiation necrosis of brain metastases after SRS.

METHOD

Multiparametric contrast-enhanced T1- and T2-weighted imaging, apparent diffusion coefficient (ADC), and cerebral blood volume (CBV) were obtained from 52 patients with 69 metastases, showing enlarging enhancing masses after SRS. Voxel-wise clustering identified three structural MRI habitats (enhancing, solid low-enhancing, and nonviable) and three physiologic MRI habitats (hypervascular cellular, hypovascular cellular, and nonviable). Habitat-based predictors for viable tumor or radiation necrosis were identified by logistic regression. Performance was validated using the area under the curve (AUC) of the receiver operating characteristics curve in an independent dataset with 24 patients.

RESULTS

None of the physiologic MRI habitats was indicative of viable tumor. Viable tumor was predicted by a high-volume fraction of solid low-enhancing habitat (low T2-weighted and low CE-T1-weighted values; odds ratio [OR] 1.74, p <.001) and a low-volume fraction of nonviable tissue habitat (high T2-weighted and low CE-T1-weighted values; OR 0.55, p <.001). Combined structural MRI habitats yielded good discriminatory ability in both development (AUC 0.85, 95% confidence interval [CI]: 0.77-0.94) and validation sets (AUC 0.86, 95% CI:0.70-0.99), outperforming single ADC (AUC 0.64) and CBV (AUC 0.58) values. The site of progression matched with the solid low-enhancing habitat (72%, 8/11).

CONCLUSION

Solid low-enhancing and nonviable tissue habitats on structural MRI can help to localize viable tumor in patients with brain metastases after SRS.

KEY POINTS

• Structural MRI habitats helped to differentiate viable tumor from radiation necrosis. • Solid low-enhancing habitat was most helpful to find viable tumor. • Providing spatial information, the site of progression matched with solid low-enhancing habitat.

Differentiation of soft-tissue lymphoma from undifferentiated sarcoma: apparent diffusion coefficient histogram analysis

BACKGROUND

Making the preoperative diagnosis of soft-tissue lymphoma is important because the treatments for lymphoma and sarcoma are different.

PURPOSE

To determine the reliability and accuracy of single-slice and whole-tumor apparent diffusion coefficient (ADC) histogram analysis when differentiating soft-tissue lymphoma from undifferentiated sarcoma.

MATERIAL AND METHODS

Patients with confirmed soft-tissue lymphoma or undifferentiated sarcoma who underwent 3-T magnetic resonance imaging (MRI), including diffusion-weighted imaging, were included. Single-slice and whole-tumor ADC histogram analyses were performed using software. Mean, standard deviation (SD), 5th and 95th percentiles, skewness, and kurtosis were compared between groups, and a receiver operating characteristic curve with area under the curve (AUC) was obtained.

RESULTS

Thirteen patients with soft-tissue lymphoma and 12 patients with undifferentiated sarcoma were included. ADC histogram analysis of single-slice and whole-tumor, mean, SD, and 5th and 95th percentiles was significantly lower in lymphoma than in undifferentiated sarcoma. Whole-tumor analysis kurtosis was significantly higher in lymphoma than in undifferentiated sarcoma. All AUCs were high in single-slice and whole-tumor analysis: 0.987 vs. 1.000 in mean; 0.821 vs. 0.782 in SD; 0.949 vs. 0.949 in 5th percentile; and 1.000 vs. 1.000 in 95th percentile without significant difference. AUC of kurtosis in whole-tumor ADC histogram analysis was 0.750.

CONCLUSION

Single-slice and whole-tumor ADC histogram analysis seems to be reliable and accurate for differentiating soft-tissue lymphoma from undifferentiated sarcoma.

Histogram models based on intravoxel incoherent motion diffusion-weighted imaging to predict nodal staging of rectal cancer

PURPOSE

To develop a model based on histogram parameters derived from intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) for predicting the nodal staging of rectal cancer (RC).

MATERIAL AND METHODS

A total of 95 RC patients who underwent direct surgical resection were enrolled in this prospective study. The nodal staging on conventional magnetic resonance imaging (MRI) was evaluated according to the short axis diameter and morphological characteristics. Histogram parameters were extracted from apparent diffusion coefficient (ADC), true diffusion coefficient (D), pseudo-diffusion coefficient (D*), and perfusion fraction (f) maps. Multivariate binary logistic regression analysis was conducted to establish models for predicting nodal staging among all patients and those underestimated on conventional MRI.

RESULTS

The combined model based on multiple maps demonstrated superior diagnostic performance to single map models, with an area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.959, 94.3%, 88.3%, and 90.5%, respectively. The AUC of the combined model was significantly higher than that of the conventional nodal staging (P < 0.001). Additionally, 85.0% of the underestimated patients had suspicious lymph nodes with 5-8 mm short-axis diameter. The histogram model for these subgroups of patients showed good diagnostic efficacy with an AUC, sensitivity, specificity, and accuracy of 0.890, 100%, 75%, and 80.5%.

CONCLUSION

The histogram model based on IVIM-DWI could improve the diagnostic performance of nodal staging of RC. In addition, histogram parameters of IVIM-DWI may help to reduce the uncertainty of nodal staging in underestimated patients on conventional MRI.

Radiomics Analysis of Multi-Sequence MR Images For Predicting Microsatellite Instability Status Preoperatively in Rectal Cancer

Background

Immunotherapy, adjuvant chemotherapy, and prognosis of colorectal cancer are associated with MSI. Biopsy pathology cannot fully reflect the MSI status and heterogeneity of rectal cancer.

Purpose

To develop a radiomic-based model to preoperatively predict MSI status in rectal cancer on MRI.

Assessment

The patients were divided into two cohorts (training and testing) at a 7:3 ratio. Radiomics features, including intensity, texture, and shape, were extracted from the segmented volumes of interest based on T2-weighted and ADC imaging.

Statistical Tests

Independent sample t test, Mann-Whitney test, the chi-squared test, Receiver operating characteristic curves, calibration curves, decision curve analysis and multi-variate logistic regression analysis

Results

The radiomics models were significantly associated with MSI status. The T2-based model showed an area under the curve of 0.870 with 95% CI: 0.794–0.945 (accuracy, 0.845; specificity, 0.714; sensitivity, 0.976) in training set and 0.895 with 95% CI, 0.777–1.000 (accuracy, 0.778; specificity, 0.887; sensitivity, 0.772) in testing set. The ADC-based model had an AUC of 0.790 with 95% CI: 0.794–0.945 (accuracy, 0.774; specificity, 0.714; sensitivity, 0.976) in training set and 0.796 with 95% CI, 0.777–1.000 (accuracy, 0.778; specificity, 0.889; sensitivity, 0.772) in testing set. The combined model integrating T2 and ADC features showed an AUC of 0.908 with 95% CI: 0.845–0.971 (accuracy, 0.857; specificity, 0.762; sensitivity, 0.952) in training set and 0.926 with 95% CI: 0.813-1.000 (accuracy, 0.852; specificity, 1.000; sensitivity, 0.778) in testing set. Calibration curve showed that the combined score had a good calibration degree, and the decision curve demonstrated that the combined score was of benefit for clinical use.

Data Conclusion

Radiomics analysis of T2W and ADC images showed significant relevance in the prediction of microsatellite status, and the accuracy of combined model of ADC and T2W features was better than either alone.

Radiomic machine learning for predicting prognostic biomarkers and molecular subtypes of breast cancer using tumor heterogeneity and angiogenesis properties on MRI

OBJECTIVES

To investigate machine learning approaches for radiomics-based prediction of prognostic biomarkers and molecular subtypes of breast cancer using quantification of tumor heterogeneity and angiogenesis properties on magnetic resonance imaging (MRI).

METHODS

This prospective study examined 291 invasive cancers in 288 patients who underwent breast MRI at 3 T before treatment between May 2017 and July 2019. Texture and perfusion analyses were performed and a total of 160 parameters for each cancer were extracted. Relationships between MRI parameters and prognostic biomarkers were analyzed using five machine learning algorithms. Each model was built using only texture features, only perfusion features, or both. Model performance was compared using the area under the receiver-operating characteristic curve (AUC) and the DeLong method, and the importance of MRI parameters in prediction was derived.

RESULTS

Texture parameters were associated with the status of hormone receptors, human epidermal growth factor receptor 2, and Ki67, tumor size, grade, and molecular subtypes (p < 0.002). Perfusion parameters were associated with the status of hormone receptors and Ki67, grade, and molecular subtypes (p < 0.003). The random forest model integrating texture and perfusion parameters showed the highest performance (AUC = 0.75). The performance of the random forest model was the best with a special scale filter of 0 (AUC = 0.80). The important parameters for prediction were texture irregularity (entropy) and relative extracellular extravascular space (V_e).

CONCLUSIONS

Radiomic machine learning that integrates tumor heterogeneity and angiogenesis properties on MRI has the potential to noninvasively predict prognostic factors of breast cancer.

KEY POINTS

• Machine learning, integrating tumor heterogeneity and angiogenesis properties on MRI, can be applied to predict prognostic biomarkers and molecular subtypes in breast cancer. • The random forest model showed the best predictive performance among the five machine learning models (logistic regression, decision tree, naïve Bayes, random forest, and artificial neural network). • The most important MRI parameters for predicting prognostic factors in breast cancer were texture irregularity (entropy) among texture parameters and relative extracellular extravascular space (V_e) among perfusion parameters.

3D quantitative analysis of diffusion-weighted imaging for predicting the malignant potential of intraductal papillary mucinous neoplasms of the pancreas

Purpose

To investigate the predictors of intraductal papillary mucinous neoplasms of the pancreas (IPMNs) with high-grade dysplasia, using 2-dimensional (2D) analysis and 3-dimensional (3D) volume-of-interest-based apparent diffusion coefficient (ADC) histogram analysis.

Material and methods

The data of 45 patients with histopathologically confirmed IPMNs with high-grade or low-grade dysplasia were retrospectively assessed. The 2D analysis included lesion-to-spinal cord signal intensity ratio (LSR), minimum ADC value (ADC_min), and mean ADC value (ADC_mean). The 3D analysis included the overall mean (ADC_{overall mean}), mean of the bottom 10^th percentile (ADC_mean0-10), mean of the bottom 10-25^th percentile (ADC_mean10-25), mean of the bottom 25-50^th percentile (ADC_mean25-50), skewness (ADC_skewness), kurtosis (ADC_kurtosis), and entropy (ADC_entropy). Diagnostic performance was compared by analysing the area under the receiver operating characteristic curve (AUC). Inter-rater reliability was assessed by blinded evaluation using the intraclass correlation coefficient.

Results

There were 16 and 29 IPMNs with high- and low-grade dysplasia, respectively. The LSR, ADC_{overall mean}, ADC_mean0-10, ADC_mean10-25, ADC_mean25-50, and ADC_entropy showed significant between-group differences (AUC = 72-93%; p < 0.05). Inter-rater reliability assessment showed almost perfect agreement for LSR and substantial agreement for ADC_{overall mean} and ADC_entropy. Multivariate logistic regression showed that ADCoverall mean and ADCentropy were significant independent predictors of malignancy (p < 0.05), with diagnostic accuracies of 80% and 73%, respectively.

Conclusion

ADC_{overall mean} and ADC_entropy from 3D analysis may assist in predicting IPMNs with high-grade dysplasia.

Correlation between 18F-FDG PET/CT and diffusion-weighted MRI parameters in head and neck squamous cell carcinoma at baseline and after chemo-radiotherapy. A retrospective single institutional study

OBJECTIVES

The relationship between glucose metabolism and tumor cellularity before chemo-radiotherapy in patients with head and neck squamous cell carcinoma (SCC) has never been compared with that of patients evaluated after treatment. This retrospective study analyzed the correlation between glucose metabolism parameters expressed by standardized uptake value (SUV) derived from 18F-fluorodeoxyglucose (18F-FDG) PET/CT and cellularity tumor parameters expressed by apparent diffusion coefficients (ADC) derived from diffusion-weighted (DW) MRI in untreated and treated patients with head and neck SCC.

METHODS

In 19 patients with no previous exposure to any treatment and 17 different chemo-radiotreated patients with head and neck SCC, we correlated the semi-quantitative uptake values (SUVmax, SUVpeak, and SUVmean) with the ADC functional parameters (ADCmin, ADCmean) including the standard deviation of ADC values (ADCsd).

RESULTS

No significant correlation was found between glucose metabolism parameters and ADCmin or ADCmean in untreated and treated patient groups. However, in untreated patients, significant inverse correlations were found between ADCsd and SUVmax (P = 0.039, r = -0.476), SUVpeak (P = 0.003, r = -0.652) and SUVmean (P = 0.039, r = -0.477). Analyses after chemo-radiotherapy in 17 patients showed no significant correlation between glucose metabolism parameters and DW MRI values, excluding a persistent significant (but lower intensity) inverse correlation between SUVpeak and ADCsd (P = 0.033, r = -0.519).

CONCLUSIONS

The demonstrated relationships suggest complex interactions especially between metabolic activity and heterogeneity of tumoral tissue, which might play a complementary role in the assessment of head and neck SCC.

TRIAL DATE OF REGISTRATION AND REGISTRATION NUMBER

Our retrospective study was registered on April 9th, 2020 by the Ethics Committee of the Coordinating Center "Area Vasta Nord Ovest" (CEAVNO) with Registration Number CEAVNO09042020.

Preoperative histogram parameters of dynamic contrast-enhanced MRI as a potential imaging biomarker for assessing the expression of Ki-67 in prostate cancer

Purpose

To investigate whether preoperative histogram parameters of dynamic contrast‐enhanced MRI (DCE‐MRI) can assess the expression of Ki‐67 in prostate cancer (PCa).

Materials and methods

A consecutive series of 76 patients with pathology‐proven PCa who underwent routine DCE‐MRI scans were retrospectively recruited. Quantitative parameters including the volume transfer constant (K^trans), rate contrast (K_ep), extracellular‐extravascular volume fraction (V_e), and plasma volume (V_p) by outlining the three‐dimensional volume of interest (VOI) of all lesions were processed. Then, the histogram analyses of these quantitative parameters were performed. The Spearman rank correlation analysis was used to evaluate the correlation of these parameters and Ki‐67 expression of PCa. Receiver operating characteristic (ROC) curve analysis was adopted to evaluate the efficacy of these quantitative histogram parameters in identifying high Ki‐67 expression from low Ki‐67 expression of PCa.

Results

Eighty‐eight PCa lesions were enrolled in this study, including 31 lesions with high Ki‐67 expression and 57 lesions with low Ki‐67 expression. The median, mean, 75th percentile, and 90th percentile derived from K^trans and K_ep had a moderately positive correlation with Ki‐67 expression (r = 0.361–0.450, p < 0.05), in which both the median and mean of K^trans had the highest positive correlation (r = 0.450, p < 0.05). The diagnostic efficacy of the K^trans median, mean, 75th percentile, and 90th percentile, along with the K_ep‐based median and mean was assessed by the ROC curve. The area under the curve (AUC) of the mean for K^trans was the highest (0.826). When the cut‐off of the mean for K^trans was ≥0.47/min, its Youden index, sensitivity, and specificity were 0.625, 0.871, and 0.754, respectively. The AUC of the median of K_ep was the lowest (0.772).

Conclusion

The histogram of DCE‐MRI quantitative parameters is correlated with Ki‐67 expression, which has the potential to noninvasively assess the expression of Ki‐67 with patients of PCa.

Pseudo Test-Retest Evaluation of Millimeter-Resolution Whole-Brain Dynamic Contrast-enhanced MRI in Patients with High-Grade Glioma

Background

Advances in sub-Nyquist–sampled dynamic contrast-enhanced (DCE) MRI enable monitoring of brain tumors with millimeter resolution and whole-brain coverage. Such undersampled quantitative methods need careful characterization regarding achievable test-retest reproducibility.

Purpose

To demonstrate a fully automated high-resolution whole-brain DCE MRI pipeline with 30-fold sparse undersampling and estimate its reproducibility on the basis of reference regions of stable tissue types during multiple posttreatment time points by using longitudinal clinical images of high-grade glioma.

Materials and Methods

Two methods for sub-Nyquist–sampled DCE MRI were extended with automatic estimation of vascular input functions. Continuously acquired three-dimensional k-space data with ramped-up flip angles were partitioned to yield high-resolution, whole-brain tracer kinetic parameter maps with matched precontrast-agent T1 and M₀ maps. Reproducibility was estimated in a retrospective study in participants with high-grade glioma, who underwent three consecutive standard-of-care examinations between December 2016 and April 2019. Coefficients of variation and reproducibility coefficients were reported for histogram statistics of the tracer kinetic parameters plasma volume fraction and volume transfer constant (K^trans) on five healthy tissue types.

Results

The images from 13 participants (mean age ± standard deviation, 61 years ± 10; nine women) with high-grade glioma were evaluated. In healthy tissues, the protocol achieved a coefficient of variation less than 57% for median K^trans, if K^trans was estimated consecutively. The maximum reproducibility coefficient for median K^trans was estimated to be at 0.06 min^–1 for large or low-enhancing tissues and to be as high as 0.48 min^–1 in smaller or strongly enhancing tissues.

Conclusion

A fully automated, sparsely sampled DCE MRI reconstruction with patient-specific vascular input function offered high spatial and temporal resolution and whole-brain coverage; in healthy tissues, the protocol estimated median volume transfer constant with maximum reproducibility coefficient of 0.06 min^–1 in large, low-enhancing tissue regions and maximum reproducibility coefficient of less than 0.48 min^–1 in smaller or more strongly enhancing tissue regions.

Published under a CC BY 4.0 license.

Online supplemental material is available for this article.

See also the editorial by Lenkinski in this issue.

Texture Analysis of Fractional Water Content Images Acquired during PET/MRI: Initial Evidence for an Association with Total Lesion Glycolysis, Survival and Gene Mutation Profile in Primary Colorectal Cancer

To assess the capability of fractional water content (FWC) texture analysis (TA) to generate biologically relevant information from routine PET/MRI acquisitions for colorectal cancer (CRC) patients. Thirty consecutive primary CRC patients (mean age 63.9, range 42-83 years) prospectively underwent FDG-PET/MRI. FWC tumor parametric images generated from Dixon MR sequences underwent TA using commercially available research software (TexRAD). Data analysis comprised (1) identification of functional imaging correlates for texture features (TF) with low inter-observer variability (intraclass correlation coefficient: ICC > 0.75), (2) evaluation of prognostic performance for FWC-TF, and (3) correlation of prognostic imaging signatures with gene mutation (GM) profile. Of 32 FWC-TF with ICC > 0.75, 18 correlated with total lesion glycolysis (TLG, highest: rs = -0.547, p = 0.002). Using optimized cut-off values, five MR FWC-TF identified a good prognostic group with zero mortality (lowest: p = 0.017). For the most statistically significant prognostic marker, favorable prognosis was significantly associated with a higher number of GM per patient (medians: 7 vs. 1.5, p = 0.009). FWC-TA derived from routine PET/MRI Dixon acquisitions shows good inter-operator agreement, generates biological relevant information related to TLG, GM count, and provides prognostic information that can unlock new clinical applications for CRC patients.

Histogram parameters derived from T1 and T2 weighted images correlate with tumor infiltrating lymphocytes and tumor-stroma ratio in head and neck squamous cell cancer

PURPOSE

The present study used histogram analysis values derived from T1- and T2- weighted (w) images to elucidate possible associations with Tumor-infiltrating lymphocytes (TIL) and Vimentin expression in head and neck squamous cell cancer (HNSCC).

MATERIALS AND METHODS

Overall, 28 patients (n = 8 female patient, 28.6%) with primary HNSCC of different localizations were involved in the study. Magnetic resonance imaging (MRI) was obtained on a 3 T MRI. The images were analyzed with a whole lesion measurement using a histogram approach. TIL- and vimentin-expression was calculated on biopsy samples before any form of treatment.

RESULTS

Several T1-derived parameters correlated with the expression of TIL within the stroma compartment: mean (r = 0.42, p = 0.025), p10 (r = 0.50, p = 0.007), p25 (r = 0.42, p = 0.025), median (r = 0.39, p = 0.036), and mode (r = 0.39, p = 0.04). No T2-derived parameter correlated with the TIL within the stroma compartment. Several T2-derived parameters correlated with the expression of TIL within the tumor compartment: mean (r = -0.52, p = 0.004), max (r = -0.43, p = 0.02), p10 (r = -0.38, p = 0.04), p25 (r = -0.53, p = 0.004), p75 (r = -0.52, p = 0.004), p90 (r = -0.48, p = 0.009), median (r = -0.52, p = 0.004), mode (r = -0.40, p = 0.03). Kurtosis derived from T2w images had significant higher values in tumor-rich tumors, compared to stroma-rich tumors, (mean 5.5 ± 0.5 versus 4.2 ± 1.2, p = 0.028).

CONCLUSIONS

Histogram analysis parameters derived from T1w and T2w images might be able to reflect tumor compartments and TIL expression in HNSCC.

Identification of Tumor-Specific MRI Biomarkers Using Machine Learning (ML)

The identification of reliable and non-invasive oncology biomarkers remains a main priority in healthcare. There are only a few biomarkers that have been approved as diagnostic for cancer. The most frequently used cancer biomarkers are derived from either biological materials or imaging data. Most cancer biomarkers suffer from a lack of high specificity. However, the latest advancements in machine learning (ML) and artificial intelligence (AI) have enabled the identification of highly predictive, disease-specific biomarkers. Such biomarkers can be used to diagnose cancer patients, to predict cancer prognosis, or even to predict treatment efficacy. Herein, we provide a summary of the current status of developing and applying Magnetic resonance imaging (MRI) biomarkers in cancer care. We focus on all aspects of MRI biomarkers, starting from MRI data collection, preprocessing and machine learning methods, and ending with summarizing the types of existing biomarkers and their clinical applications in different cancer types.

Low conductivity on electrical properties tomography demonstrates unique tumor habitats indicating progression in glioblastoma

OBJECTIVES

Tissue conductivity measurements made with electrical properties tomography (EPT) can be used to define temporal changes in tissue habitats on longitudinal multiparametric MRI. We aimed to demonstrate the added insights for identifying tumor habitats obtained by including EPT with diffusion- and perfusion-weighted MRI, and to evaluate the use of these tumor habitats for determining tumor treatment response in post-treatment glioblastoma.

METHODS

Tumor habitats were developed from EPT, diffusion-weighted, and perfusion-weighted MRI in 60 patients with glioblastoma who underwent concurrent chemoradiotherapy. Voxels from EPT, apparent diffusion coefficient (ADC), and cerebral blood volume (CBV) maps were clustered into habitats, and each habitat was serially examined to assess its temporal change. The usefulness of temporal changes in tumor habitats for diagnosing tumor progression and treatment-related change was investigated using logistic regression. The performance of significant predictors was measured using the area under the curve (AUC) from receiver-operating-characteristics analysis with 1000-fold bootstrapping.

RESULTS

Five tumor habitats were identified, and of these, the hypervascular cellular habitat (odds ratio [OR] 5.45; 95% CI, 1.75-31.42; p = .02), hypovascular low conductivity habitat (OR 2.00; 95% CI, 1.45-3.05; p < .001), and hypovascular intermediate habitat (OR 1.57; 95% CI, 1.18-2.30; p = .006) were predictive of tumor progression. Low EPT and low CBV reflected a unique hypovascular low conductivity habitat that showed the highest diagnostic performance (AUC 0.86; 95% CI, 0.76-0.96). The combined habitats showed high performance (AUC 0.90; 95% CI, 0.82-0.98) in the differentiation of tumor progression from treatment-related change.

CONCLUSION

EPT reveals low conductivity habitats that can improve the diagnosis of tumor progression in post-treatment glioblastoma.

KEY POINTS

• Electrical properties tomography (EPT) demonstrated lower conductivity in tumor progression than in treatment-related change. • EPT allowed identification of a unique hypovascular low conductivity habitat when combined with cerebral blood volume mapping. • Tumor habitats with a hypovascular low conductivity habitat, hypervascular cellular habitat, and hypovascular intermediate habitat yielded high diagnostic performance for diagnosing tumor progression.

Correlation between quantitative perfusion histogram parameters of DCE-MRI and PTEN, P-Akt and m-TOR in different pathological types of lung cancer

Background

To explore if the quantitative perfusion histogram parameters of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) correlates with the expression of PTEN, P-Akt and m-TOR protein in lung cancer.

Methods

Thirty‐three patients with 33 lesions who had been diagnosed with lung cancer were enrolled in this study. They were divided into three groups: squamous cell carcinoma (SCC, 15 cases), adenocarcinoma (AC, 12 cases) and small cell lung cancer (SCLC, 6 cases). Preoperative imaging (conventional imaging and DCE-MRI) was performed on all patients. The Exchange model was used to measure the phar- macokinetic parameters, including K^trans, V_p, K_ep, V_e and F_p, and then the histogram parameters meanvalue, skewness, kurtosis, uniformity, energy, entropy, quantile of above five parameters were analyzed. The expression of PTEN, P-Akt and m-TOR were assessed by immunohistochemistry. Spearman correlation analysis was used to compare the correlation between the quantitative perfusion histogram parameters and the expression of PTEN, P-Akt and m-TOR in different pathological subtypes of lung cancer.

Results

The expression of m-TOR (P = 0.013) and P-Akt (P = 0.002) in AC was significantly higher than those in SCC. V_p (uniformity) in SCC group, K^trans (uniformity), V_e (kurtosis, Q10, Q25) in AC group, F_p (skewness, kurtosis, energy), V_e (Q75, Q90, Q95) in SCLC group was positively correlated with PTEN, and F_p (entropy) in the SCLC group was negatively correlated with PTEN (P < 0.05); K_ep (Q5, Q10) in the SCLC group was positively correlated with P-Akt, and K_ep (energy) in the SCLC group was negatively correlated with P-Akt (P < 0.05); K_ep (Q5) in SCC group and V_p (meanvalue, Q75, Q90, Q95) in SCLC group was positively correlated with m-TOR, and V_e (meanvalue) in SCC group was negatively correlated with m-TOR (P < 0.05).

Conclusions

The quantitative perfusion histogram parameters of DCE-MRI was correlated with the expression of PTEN, P-Akt and m-TOR in different pathological types of lung cancer, which may be used to indirectly evaluate the activation status of PI3K/Akt/mTOR signal pathway gene in lung cancer, and provide important reference for clinical treatment.

Diffusion weighted imaging in high-grade gliomas: A histogram-based analysis of apparent diffusion coefficient profile

Purpose

Glioblastoma and anaplastic astrocytoma represent the most commonly encountered high-grade-glioma (HGG) in adults. Although both neoplasms are very distinct entities in context of epidemiology, clinical course and prognosis, their appearance in conventional magnetic resonance imaging (MRI) is very similar. In search for additional information aiding the distinction of potentially confusable neoplasms, histogram analysis of apparent diffusion coefficient (ADC) maps recently proved to be auxiliary in a number of entities. Therefore, our present exploratory retrospective study investigated whether ADC histogram profile parameters differ significantly between anaplastic astrocytoma and glioblastoma, reflect the proliferation index Ki-67, or are associated with the prognostic relevant MGMT (methylguanine-DNA methyl-transferase) promotor methylation status.

Methods

Pre-surgical ADC volumes of 56 HGG patients were analyzed by histogram-profiling. Association between extracted histogram parameters and neuropathology including WHO-grade, Ki-67 expression and MGMT promotor methylation status was investigated due to comparative and correlative statistics.

Results

Grade IV gliomas were more heterogeneous than grade III tumors. More specifically, ADCmin and the lowest percentile ADCp10 were significantly lower, whereas ADCmax, ADC standard deviation and Skewness were significantly higher in the glioblastoma group. ADCmin, ADCmax, ADC standard deviation, Kurtosis and Entropy of ADC histogram were significantly correlated with Ki-67 expression. No significant difference could be revealed by comparison of ADC histogram parameters between MGMT promotor methylated and unmethylated HGG.

Conclusions

ADC histogram parameters differ significantly between glioblastoma and anaplastic astrocytoma and show distinct associations with the proliferative activity in both HGG. Our results suggest ADC histogram profiling as promising biomarker for differentiation of both, however, further studies with prospective multicenter design are wanted to confirm and further elaborate this hypothesis.

Multi-parametric magnetic resonance imaging assessment of whole tumour heterogeneity for chemoradiotherapy response prediction in rectal cancer

Background and purpose

Prediction of chemoradiotherapy response (CRT) in locally advanced rectal cancer would enable stratification of management. The purpose was to prospectively evaluate multi-parametric magnetic resonance imaging (MRI) assessment of tumour heterogeneity combining diffusion weighted imaging (DWI) and dynamic contrast enhanced (DCE) MRI for the prediction of CRT response in locally advanced rectal cancer.

Materials and methods

Patients with Stage II or III rectal adenocarcinoma undergoing neoadjuvant CRT and surgery underwent MRI (DWI and DCE) before, during (week 3), and after CRT (1 week before surgery). Patients with histopathology tumour regression grade (TRG) 0-1 were classified as responders, and TRG 2-3 were classified as non-responders. A whole tumour voxel-wise technique was used to produce apparent diffusion coefficient (ADC) and K^trans (Tofts model) histograms derived from DWI and DCE-MRI, respectively. Logistic regression was used to predict response status for ADC and K^trans quantiles.

Results

Thirty-three patients were included in this analysis; 16 responders, and 17 non-responders. On heterogeneity analysis, odds of being a responder were significantly higher after CRT (before surgery) for higher ADC 75th (p = 0.049) and ADC 90th (p = 0.034) percentile values. The K^trans quantiles were lower in non-responders than responders before and during CRT, and higher after CRT although no significant association with response status was observed (p ≥ 0.10).

Conclusions

DWI-MRI after CRT (before surgery) incorporating a histogram analysis of whole tumour heterogeneity was predictive of CRT response in patients with locally advanced rectal cancer. DCE-MRI did not add value in response prediction.

Clinical trial registration

Australian New Zealand Clinical Trials Registry (ANZCTR) number ACTRN12616001690448.

An analysis of Ki-67 expression in stage 1 invasive ductal breast carcinoma using apparent diffusion coefficient histograms

Background

To investigate the value of apparent diffusion coefficient (ADC) histograms in differentiating Ki-67 expression in T1 stage invasive ductal breast carcinoma (IDC).

Methods

The records of 111 patients with pathologically confirmed T1 stage IDC who underwent magnetic resonance imaging prior to surgery were retrospectively reviewed. The expression of Ki-67 in tumor tissue samples from the patients was assessed using immunohistochemical (IHC) staining, with a cut-off value of 25% for high Ki-67 labeling index (LI). ADC images of the maximum lay of tumors were selected, and the region of interest (ROI) of each lay was delineated using the MaZda software and analyzed by histogram. The correlations between the histogram characteristic parameters and the Ki-67 LI were investigated. Additionally, the histogram characteristic parameters of the high Ki-67 group (n=54) and the low Ki-67 group (n=57) were statistically analyzed to determine the characteristic parameters with significant difference. Receiver operator characteristic (ROC) analyses were further performed for the significant parameters.

Results

The mean value, and the 1st, 10th, 50th, 90th, and 99th percentiles were found to be negatively correlated with the expression of Ki-67 (all P values <0.001), with a correlation coefficient of -0.624, -0.749, -0.717, -0.621, -0.500, and -0.410, respectively. In the high Ki-67 group, the mean value, and the 1st, 10th, 50th, 90th, and 99th percentiles extracted by the histogram were significantly lower (all P values <0.05) than that of the low Ki-67 group, with areas under the ROC curves ranging from 0.717-0.856. However, the variance, skewness, and kurtosis did not differ between the two groups (all P values >0.05).

Conclusions

Histogram-derived parameters for ADC images can serve as a reliable tool in the prediction of Ki-67 proliferation status in patients with T1 stage IDC. Among the significant ADC histogram values, the 1st and 10th percentiles showed the best predictive values.

Value of Apparent Diffusion Coefficient Histogram Analysis in the Differential Diagnosis of Nasopharyngeal Lymphoma and Nasopharyngeal Carcinoma Based on Readout-Segmented Diffusion-Weighted Imaging

Background

This study aims to explore the utility of whole-lesion apparent diffusion coefficient (ADC) histogram analysis for differentiating nasopharyngeal lymphoma (NPL) from nasopharyngeal carcinoma (NPC) following readout-segmented echo-planar diffusion-weighted imaging (RESOLVE sequence).

Methods

Thirty-eight patients with NPL and 62 patients with NPC, who received routine head-and-neck MRI and RESOLVE (b-value: 0 and 1,000 s/mm²) examinations, were retrospectively evaluated as derivation cohort (February 2015 to August 2018); another 23 patients were analyzed as validation cohort (September 2018 to December 2019). The RESOLVE data were obtained from the MAGNETOM Skyra 3T MR system (Siemens Healthcare, Erlangen, Germany). Fifteen parameters derived from the whole-lesion histogram analysis (ADC_mean, variance, skewness, kurtosis, ADC₁, ADC₁₀, ADC₂₀, ADC₃₀, ADC₄₀, ADC₅₀, ADC₆₀, ADC₇₀, ADC₈₀, ADC₉₀, and ADC₉₉) were calculated for each patient. Then, statistical analyses were performed between the two groups to determine the statistical significance of each histogram parameter. A receiver operating characteristic curve (ROC) analysis was conducted to assess the diagnostic performance of each histogram parameter for distinguishing NPL from NPC and further tested in the validation cohort; calibration of the selected parameter was tested with Hosmer-Lemeshow test.

Results

NPL exhibited significantly lower ADC_mean, variance, ADC₁, ADC₁₀, ADC₂₀, ADC₃₀, ADC₄₀, ADC₅₀, ADC₆₀, ADC₇₀, ADC₈₀, ADC₉₀ and ADC₉₉, when compared to NPC (all, P < 0.05), while no significant differences were found on skewness and kurtosis. Furthermore, ADC₉₉ revealed the highest diagnostic efficiency, followed by ADC₁₀ and ADC₂₀. Optimal diagnostic performance (AUC = 0.790, sensitivity = 91.9%, and specificity = 63.2%) could be achieved when setting ADC₉₉ = 1,485.0 × 10^-6 mm²/s as the threshold value. The predictive performance was maintained in the validation cohort (AUC = 0.817, sensitivity = 94.6%, and specificity = 56.2%).

Conclusion

Whole-lesion ADC histograms based on RESOLVE are effective in differentiating NPC from NPL.

Heterogeneity analysis of MRI T2 maps for measurement of early tumor response to radiotherapy

External beam radiotherapy (XRT) is a widely used cancer treatment, yet responses vary dramatically among patients. These differences are not accounted for in clinical practice, partly due to a lack of sensitive early response biomarkers. We hypothesize that quantitative magnetic resonance imaging (MRI) measures reflecting tumor heterogeneity can provide a sensitive and robust biomarker of early XRT response. MRI T2 mapping was performed every 72 hours following 10 Gy dose XRT in two models of pancreatic cancer propagated in the hind limb of mice. Interquartile range (IQR) of tumor T2 was presented as a potential biomarker of radiotherapy response compared with tumor growth kinetics, and biological validation was performed through quantitative histology analysis. Quantification of tumor T2 IQR showed sensitivity for detection of XRT-induced tumor changes 72 hours after treatment, outperforming T2-weighted and diffusion-weighted MRI, with very good robustness. Histological comparison revealed that T2 IQR provides a measure of spatial heterogeneity in tumor cell density, related to radiation-induced necrosis. Early IQR changes were found to correlate to subsequent tumor volume changes, indicating promise for treatment response prediction. Our preclinical findings indicate that spatial heterogeneity analysis of T2 MRI can provide a translatable method for early radiotherapy response assessment. We propose that the method may in future be applied for personalization of radiotherapy through adaptive treatment paradigms.

A simulation study of cell size and volume fraction mapping for tissue with two underlying cell populations using diffusion-weighted MRI

PURPOSE

To propose a method for voxel-wise estimation of cell radii and volume fractions of two cell populations when they coexist in the same MR voxel using the combination of diffusion-weighted MRI and microstructural modeling.

METHOD

Microstructure models were investigated using diffusion data simulated with the matrix method for a range of microstructures mimicking tumor tissue with two cell populations, using acquisition parameters available on preclinical scanners. The effect of noise was investigated for a subset of these microstructures. The accuracy and precision of the estimated radii and volume fractions for large and small cells R l , R s , v i n , l , v i n , s were evaluated by comparing the estimates to their true values. The stability of model fitting was characterized by the percentage of accepted fits.

RESULTS

The estimation accuracy and precision, and thus the ability to robustly distinguish the two cell populations, depended on the microstructural properties and SNR. For a SNR of 50, a minimum difference of 3 μm between the radius of the large and small cell populations was required for differentiation. Proposed modifications to the two cell population microstructure model, including constrained fits, improved the stability of fits.

CONCLUSIONS

This proof-of-concept study proposed a diffusion MRI-based method for voxel-wise estimation of cell radii and volume fractions of two cell populations when they coexist in the same MR voxel. The ability to reliably characterize tissue with two cell populations opens exciting avenues of potential applications in both tumor diagnosis and treatment monitoring.

Diagnostic accuracy of MRI textural analysis in the classification of breast tumors

OBJECTIVE

To investigate whether textural analysis (TA) of MRI heterogeneity may play a role in the clinical assessment and classification of breast tumors.

MATERIALS AND METHODS

For this retrospective study, patients with breast masses ≥1 cm on contrast-enhanced MRI were obtained in 69 women (mean age: 51 years; range 21-78 years) with 77 masses (38 benign, 39 malignant) from 2006 to 2018. The selected single slice sagittal peak post-contrast T1-weighted image was analyzed with commercially available TA software [TexRAD Ltd., UK]. Eight histogram TA parameters were evaluated at various spatial scaling factors (SSF) including mean pixel intensity, standard deviation of the pixel histogram (SD), entropy, mean of the positive pixels (MPP), skewness, kurtosis, sigma, and Tx_sigma. Additional statistical tests were used to determine their predictiveness.

RESULTS

Entropy showed a significant difference between benign and malignant tumors at all textural scales (p < 0.0001) and kurtosis was significant at SSF = 0-5 (p = 0.0026-0.0241). The single best predictor was entropy at SSF = 4 with AUC = 0.80, giving a sensitivity of 95% and specificity of 53%. An AUC of 0.91 was found using a model combining entropy with sigma, which yielded better performance with a sensitivity of 92% and specificity of 79%.

CONCLUSION

TA of breast masses has the potential to assist radiologists in categorizing tumors as benign or malignant on MRI. Measurements of entropy, kurtosis, and entropy combined with sigma may provide the best predictability.

Noninvasive Assessment of O(6)-Methylguanine-DNA Methyltransferase Promoter Methylation Status in World Health Organization Grade II-IV Glioma Using Histogram Analysis of Inflow-Based Vascular-Space-Occupancy Combined with Structural Magnetic Resonance Imaging

BACKGROUND

O(6)-methylguanine-DNA methyltransferase (MGMT) promoter methylation is an important prognostic factor for gliomas and is associated with tumor angiogenesis. Arteriolar cerebral blood volume (CBVa) obtained from inflow-based vascular-space-occupancy (iVASO) magnetic resonance imaging (MRI) is assumed to be an indicator of tumor microvasculature. Its preoperative predictive ability for MGMT promoter methylation remains unclear.

PURPOSE

To investigate the role of iVASO-CBVa histogram features in determining MGMT promoter methylation status of grade II-IV gliomas.

STUDY TYPE

Retrospective SUBJECTS: Forty-six patients consisting of 20 MGMT methylated and 26 unmethylated gliomas.

FIELD STRENGTH/SEQUENCE

3.0 T magnetic resonance images containing iVASO MRI, T₁ -weighted image (T₁ WI), T₂ -weighted image, T₂ -weighted fluid attenuated inversion recovery image images, and enhanced T₁ WI.

ASSESSMENT

Sixteen structural imaging features were visually evaluated on structural MRI and 14 CBVa histogram features were extracted from iVASO-CBVa maps.

STATISTICAL TESTS

Imaging features were screened and ranked using Fisher's exact test, Mann-Whitney U-test, and randomforest algorithm. Features with higher importance were selected to develop logistic regression models to determine MGMT methylation status. Receiver operating characteristics (ROC) curve with the area under the curve (AUC) and leave-one-out cross-validation (LOOCV) were used to assess effectiveness and stability.

RESULTS

The top two CBVa histogram features were root mean squared (RMS) and variance. The top two structural imaging features were contrast-enhancing component of the tumor (CET) location and tumor location. Both the CBVa model of RMS and variance (ROC, AUC = 0.867; LOOCV, AUC = 0.819) and the model of structural features (ROC, AUC = 0.882; LOOCV, AUC = 0.802) accurately identified MGMT methylation. The fusion model of CBVa RMS and CET location improved diagnostic performance (ROC, AUC = 0.931; LOOCV, AUC =0.906). DATA CONCLUSION: iVASO-CBVa has potential in evaluating MGMT methylation status in grade II-IV gliomas.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 2.

Spatiotemporal habitats from multiparametric physiologic MRI distinguish tumor progression from treatment-related change in post-treatment glioblastoma

OBJECTIVES

We aimed to develop multiparametric physiologic MRI-based spatial habitats and to evaluate whether temporal changes in these habitats help to distinguish tumor progression from treatment-related change in post-treatment glioblastoma.

METHODS

This retrospective, single-institution study included patients with glioblastoma treated by concurrent chemoradiotherapy who had newly developed or enlarging, measurable contrast-enhancing mass. Contrast-enhancing mass was divided into three spatial habitats by K-means clustering of voxel-wise ADC and CBV values. Temporal changes of these habitats between two consecutive examinations prior to the diagnosis of tumor progression or treatment-related change were assessed. Predictors were selected using logistic regression and the performance was measured with an area under the receiver operating characteristics curve (AUC). Spatiotemporal habitats were further analyzed for correlation with the site of tumor progression.

RESULTS

There were 75 patients (mean, 58 years; range, 26-81 years; 43 men) with 48 cases of tumor progression and 39 cases of treatment-related change including 12 patient overlaps at different time points. Three spatial habitats of hypervascular cellular, hypovascular cellular, and nonviable tissue were identified. Increase in the hypervascular cellular (OR 4.55, p = .002) and hypovascular cellular habitat (OR 1.22, p < .001) was predictive of tumor progression. Combination of spatiotemporal habitats yielded a high diagnostic performance with an AUC of 0.89 (95% CI, 0.87-0.92). An increase in hypovascular cellular habitat predicted the site of tumor progression in 84% [21/25] of cases with tumor progression.

CONCLUSIONS

Temporal changes in spatial habitats derived from multiparametric physiologic MRI provided diagnostic value in distinguishing tumor progression from treatment-related change and predicted site of tumor progression in post-treatment glioblastoma.

KEY POINTS

• In post-treatment glioblastoma, three spatial habitats of hypervascular cellular, hypovascular cellular, and nonviable tissue were identified, and an increase in the hypervascular cellular (OR 4.55, p = .002) and hypovascular cellular habitat (OR 1.22, p < .001) was predictive of tumor progression. • Combination of spatiotemporal habitats yielded a high diagnostic performance with an AUC of 0.89 (95% CI, 0.87-0.92). • An increase in hypovascular cellular habitat predicted the site of tumor progression in 84% (21/25) of cases with tumor progression.