The utility of MRI histogram and texture analysis for the prediction of histological diagnosis in head and neck malignancies

Histogram analysis of intravoxel incoherent motion imaging: Correlation with molecular prognostic factors and combined subtypes of breast cancer

PURPOSE

To look for links between diffusion and IVIM parameters and different molecular subtypes and prognostic factors through histogram analysis.

MATERIALS AND METHODS

A total of 139 patients with breast cancer who had pre-operative MRI examinations were enrolled in this retrospective study. Histograms of the diffusion and IVIM parameters were analyzed for the whole tumor, and an association was investigated between the parameters and the different molecular prognostic factors and subtypes using the nonparametric test, Spearman's rank correlation, and receiver operating characteristic (ROC) curve.

RESULTS

The histogram metrics of the diffusion and IVIM parameters were significantly different for molecular prognostic factors such as human epidermal receptor factor-2 (HER2), progesterone receptor, estrogen receptor, and ki-67. All histogram metrics displayed a poor correlation with all groups (r = -0.28-0.29). There were significant differences in the histogram metrics for the Luminal B-HER2 (-) vs. HER2-positive (non-luminal) subtypes in the mean and 10th percentile D, with the area under the curves (AUCs) of 0.742 and 0.700, respectively, and for the Luminal A and HER2-positive (non-luminal) subtypes in the 90th percentile and entropy of D*, with AUCs of 0.769 and 0.727, respectively.

CONCLUSION

The histogram metrics of IVIM parameters exhibited links with breast cancer prognosis factors and combined subtypes.

Radiomics-Based Machine Learning Classification Strategy for Characterization of Hepatocellular Carcinoma on Contrast-Enhanced Ultrasound in High-Risk Patients with LI-RADS Category M Nodules

Objective  Accurate differentiation within the LI-RADS category M (LR-M) between hepatocellular carcinoma (HCC) and non-HCC malignancies (mainly intrahepatic cholangiocarcinoma [CCA] and combined hepatocellular and cholangiocarcinoma [cHCC-CCA]) is an area of active investigation. We aimed to use radiomics-based machine learning classification strategy for differentiating HCC from CCA and cHCC-CCA on contrast-enhanced ultrasound (CEUS) images in high-risk patients with LR-M nodules. Methods  A total of 159 high-risk patients with LR-M nodules (69 HCC and 90 CCA/cHCC-CCA) who underwent CEUS within 1 month before pathologic confirmation from January 2006 to December 2019 were retrospectively included (111 patients for training set and 48 for test set). The training set was used to build models, while the test set was used to compare models. For each observation, six CEUS images captured at predetermined time points (T1, peak enhancement after contrast injection; T2, 30 seconds; T3, 45 seconds; T4, 60 seconds; T5, 1-2 minutes; and T6, 2-3 minutes) were collected for tumor segmentation and selection of radiomics features, which included seven types of features: first-order statistics, shape (2D), gray-level co-occurrence matrix, gray-level size zone matrix, gray-level run length matrix, neighboring gray tone difference matrix, and gray-level dependence matrix. Clinical data and key radiomics features were employed to develop the clinical model, radiomics signature (RS), and combined RS-clinical (RS-C) model. The RS and RS-C model were built using the machine learning framework. The diagnostic performance of these three models was calculated and compared. Results  Alpha-fetoprotein (AFP), CA19-9, enhancement pattern, and time of washout were included as independent factors for clinical model (all p  < 0.05). Both the RS and RS-C model performed better than the clinical model in the test set (area under the curve [AUC] of 0.698 [0.571-0.812] for clinical model, 0.903 [0.830-0.970] for RS, and 0.912 [0.838-0.977] for the RS-C model; both p  < 0.05). Conclusions  Radiomics-based machine learning classifiers may be competent for differentiating HCC from CCA and cHCC-CCA in high-risk patients with LR-M nodules.

Synthetic MRI and diffusion-weighted imaging for differentiating nasopharyngeal lymphoma from nasopharyngeal carcinoma: combination with morphological features

OBJECTIVES

To investigate the feasibility of synthetic MRI (syMRI), diffusion-weighted imaging (DWI), and their combination with morphological features for differentiating nasopharyngeal lymphoma (NPL) from nasopharyngeal carcinoma (NPC).

METHODS

Sixty-nine patients with nasopharyngeal tumours (NPL, n = 22; NPC, n = 47) who underwent syMRI and DWI were retrospectively enrolled between October 2020 and May 2022. syMRI and DWI quantitative parameters (T1, T2, PD, ADC) and morphological features were obtained. Diagnostic performance was assessed by independent sample t-test, chi-square test, logistic regression analysis, receiver operating characteristic curve (ROC), and DeLong test.

RESULTS

NPL has significantly lower T2, PD, and ADC values compared to NPC (all P < .05), whereas no significant difference was found in T1 value between these two entities (P > .05). The morphological features of tumour type, skull-base involvement, Waldeyer ring involvement, and lymph nodes involvement region were significantly different between NPL and NPC (all P < .05). The syMRI (T2 + PD) model has better diagnostic efficacy, with AUC, sensitivity, specificity, and accuracy of 0.875, 77.27%, 89.36%, and 85.51%. Compared with syMRI model, syMRI + Morph (PD + Waldeyer ring involvement + lymph nodes involvement region), syMRI + DWI (T2 + PD + ADC), and syMRI + DWI + Morph (PD + ADC + skull-base involvement + Waldeyer ring involvement) models can further improve the diagnostic efficiency (all P < .05). Furthermore, syMRI + DWI + Morph model has excellent diagnostic performance, with AUC, sensitivity, specificity, and accuracy of 0.986, 95.47%, 97.87%, and 97.10%, respectively.

CONCLUSION

syMRI and DWI quantitative parameters were helpful in discriminating NPL from NPC. syMRI + DWI + Morph model has the excellent diagnostic efficiency in differentiating these two entities.

ADVANCES IN KNOWLEDGE

syMRI + DWI + morphological feature method can differentiate NPL from NPC with excellent diagnostic performance.

Predicting Response to Exclusive Combined Radio-Chemotherapy in Naso-Oropharyngeal Cancer: The Role of Texture Analysis

The aim of this work is to identify MRI texture features able to predict the response to radio-chemotherapy (RT-CHT) in patients with naso-oropharyngeal carcinoma (NPC-OPC) before treatment in order to help clinical decision making. Textural features were derived from ADC maps and post-gadolinium T1-images on a single MRI machine for 37 patients with NPC-OPC. Patients were divided into two groups (responders/non-responders) according to results from MRI scans and 18F-FDG-PET/CT performed at follow-up 3-4 and 12 months after therapy and biopsy. Pre-RT-CHT lesions were segmented, and radiomic features were extracted. A non-parametric Mann-Whitney test was performed. A p-value < 0.05 was considered significant. Receiver operating characteristic curves and area-under-the-curve values were generated; a 95% confidence interval (CI) was reported. A radiomic model was constructed using the LASSO algorithm. After feature selection on MRI T1 post-contrast sequences, six features were statistically significant: gldm_DependenceEntropy and DependenceNonUniformity, glrlm_RunEntropy and RunLengthNonUniformity, and glszm_SizeZoneNonUniformity and ZoneEntropy, with significant cut-off values between responder and non-responder group. With the LASSO algorithm, the radiomic model showed an AUC of 0.89 and 95% CI: 0.78-0.99. In ADC, five features were selected with an AUC of 0.84 and 95% CI: 0.68-1. Texture analysis on post-gadolinium T1-images and ADC maps could potentially predict response to therapy in patients with NPC-OPC who will undergo exclusive treatment with RT-CHT, being, therefore, a useful tool in therapeutical-clinical decision making.

Imaging of human papilloma virus (HPV) related oropharynx tumour: what we know to date

The tumours of head and neck district are around 3% of all malignancies and squamous cell carcinoma is the most frequent histotype, with rapid increase during the last two decades because of the increment of the infection due to human papilloma virus (HPV). Even if the gold standard for the diagnosis is histological examination, including the detection of viral DNA and transcription products, imaging plays a fundamental role in the detection and staging of HPV + tumours, in order to assess the primary tumour, to establish the extent of disease and for follow-up. The main diagnostic tools are Computed Tomography (CT), Positron Emission Tomography-Computed Tomography (PET-CT) and Magnetic Resonance Imaging (MRI), but also Ultrasound (US) and the use of innovative techniques such as Radiomics have an important role. Aim of our review is to illustrate the main imaging features of HPV + tumours of the oropharynx, in US, CT and MRI imaging. In particular, we will outline the main limitations and strengths of the various imaging techniques, the main uses in the diagnosis, staging and follow-up of disease and the fundamental differential diagnoses of this type of tumour. Finally, we will focus on the innovative technique of texture analysis, which is increasingly gaining importance as a diagnostic tool in aid of the radiologist.

Evaluating the Gray Level Co-Occurrence Matrix-Based Texture Features of Magnetic Resonance Images for Glioblastoma Multiform Patients' Treatment Response Assessment

Background

Medical images of cancer patients are usually evaluated qualitatively by clinical specialists which makes the accuracy of the diagnosis subjective and related to the skills of clinicians. Quantitative methods based on the textural feature analysis may be useful to facilitate such evaluations. This study aimed to analyze the gray level co-occurrence matrix (GLCM)-based texture features extracted from T1-axial magnetic resonance (MR) images of glioblastoma multiform (GBM) patients to determine the distinctive features specific to treatment response or disease progression.

Methods

20 GLCM-based texture features, in addition to mean, standard deviation, entropy, RMS, kurtosis, and skewness were extracted from step I MR images (obtained 72 h after surgery) and step II MR images (obtained three months later). Responded and not responded patients to treatment were classified manually based on the radiological evaluation of step II images. Extracted texture features from Step I and Step II images were analyzed to determine the distinctive features for each group of responsive or progressive diseases. MATLAB 2020 was applied to feature extraction. SPSS version 26 was used for the statistical analysis. P value < 0.05 was considered statistically significant.

Results

Despite no statistically significant differences between Step I texture features for two considered groups, almost all step II extracted GLCM-based texture features in addition to entropy M and skewness were significantly different between responsive and progressive disease groups.

Conclusions

GLCM-based texture features extracted from MR images of GBM patients can be used with automatic algorithms for the expeditious prediction or interpretation of response to the treatment quantitatively besides qualitative evaluations.

Artificial Intelligence in Neuroradiology: A Review of Current Topics and Competition Challenges

There is an expanding body of literature that describes the application of deep learning and other machine learning and artificial intelligence methods with potential relevance to neuroradiology practice. In this article, we performed a literature review to identify recent developments on the topics of artificial intelligence in neuroradiology, with particular emphasis on large datasets and large-scale algorithm assessments, such as those used in imaging AI competition challenges. Numerous applications relevant to ischemic stroke, intracranial hemorrhage, brain tumors, demyelinating disease, and neurodegenerative/neurocognitive disorders were discussed. The potential applications of these methods to spinal fractures, scoliosis grading, head and neck oncology, and vascular imaging were also reviewed. The AI applications examined perform a variety of tasks, including localization, segmentation, longitudinal monitoring, diagnostic classification, and prognostication. While research on this topic is ongoing, several applications have been cleared for clinical use and have the potential to augment the accuracy or efficiency of neuroradiologists.

Magnetic resonance imaging in naso-oropharyngeal carcinoma: role of texture analysis in the assessment of response to radiochemotherapy, a preliminary study

OBJECTIVE

Identifying MRI texture parameters able to distinguish inflammation, fibrosis, and residual cancer in patients with naso-oropharynx carcinoma after radiochemotherapy (RT-CHT).

MATERIAL AND METHODS

In this single-centre, observational, retrospective study, texture analysis was performed on ADC maps and post-gadolinium T1 images of patients with histological diagnosis of naso-oropharyngeal carcinoma treated with RT-CHT. An initial cohort of 99 patients was selected; 57 of them were later excluded. The final cohort of 42 patients was divided into 3 groups (inflammation, fibrosis, and residual cancer) according to MRI, 18F-FDG-PET/CT performed 3-4 months after RT-CHT, and biopsy. Pre-RT-CHT lesions and the corresponding anatomic area post-RT-CHT were segmented with 3D slicer software from which 107 textural features were derived. T-Student and Wilcoxon signed-rank tests were performed, and features with p-value < 0.01 were considered statistically significant. Cut-off values-obtained by ROC curves-to discriminate post-RT-CHT non-tumoural changes from residual cancer were calculated for the parameters statistically associated to the diseased status at follow-up.

RESULTS

Two features-Energy and Grey Level Non-Uniformity-were statistically significant on T1 images in the comparison between 'positive' (residual cancer) and 'negative' patients (inflammation and fibrosis). Energy was also found to be statistically significant in both patients with fibrosis and residual cancer. Grey Level Non-Uniformity was significant in the differentiation between residual cancer and inflammation. Five features were statistically significant on ADC maps in the differentiation between 'positive' and 'negative' patients. The reduction in values of such features between pre- and post-RT-CHT was correlated with a good response to therapy.

CONCLUSIONS

Texture analysis on post-gadolinium T1 images and ADC maps can differentiate residual cancer from fibrosis and inflammation in early follow-up of naso-oropharyngeal carcinoma treated with RT-CHT.

Influence of maternal psychological distress during COVID-19 pandemic on placental morphometry and texture

The Coronavirus Disease 2019 (COVID-19) pandemic has been accompanied by increased prenatal maternal distress (PMD). PMD is associated with adverse pregnancy outcomes which may be mediated by the placenta. However, the potential impact of the pandemic on in vivo placental development remains unknown. To examine the impact of the pandemic and PMD on in vivo structural placental development using advanced magnetic resonance imaging (MRI), acquired anatomic images of the placenta from 63 pregnant women without known COVID-19 exposure during the pandemic and 165 pre-pandemic controls. Measures of placental morphometry and texture were extracted. PMD was determined from validated questionnaires. Generalized estimating equations were utilized to compare differences in PMD placental features between COVID-era and pre-pandemic cohorts. Maternal stress and depression scores were significantly higher in the pandemic cohort. Placental volume, thickness, gray level kurtosis, skewness and run length non-uniformity were increased in the pandemic cohort, while placental elongation, mean gray level and long run emphasis were decreased. PMD was a mediator of the association between pandemic status and placental features. Altered in vivo placental structure during the pandemic suggests an underappreciated link between disturbances in maternal environment and perturbed placental development. The long-term impact on offspring is currently under investigation.

Differential diagnosis of parotid gland tumors using apparent diffusion coefficient, texture features, and their combination

OBJECTIVES

Warthin's tumors (WT) and pleomorphic adenomas (PA) are the commonest parotid gland tumors; however, their differentiation remains difficult. This study aimed to investigate the utility of the apparent diffusion coefficient (ADC) value, texture features, and their combination for the differential diagnosis of parotid gland tumors.

METHODS

Patients who underwent magnetic resonance imaging (MRI) between April 2008 and March 2021 for parotid gland tumors were included and divided into two groups according to the tumor type: WT and PA. The tumor types were used as predictor variables, while the ADC value, texture features, and their combination were the outcome variables. Texture features were measured on short tau inversion recovery (STIR) images and selected using the Fisher's coefficient method and probability of error, and average correlation coefficients. The Mann-Whitney U-test was used to analyze bivariate statistics. Receiver operating characteristic curve analysis was used to assess the ability of the ADC value, texture features, and their combination to distinguishing between the two tumor types.

RESULTS

A total of 22 patients were included, 11 in each group. The ADC value, 10 texture features, and their combination were significantly different between the two groups (p < .001). Moreover, all three variables had high area under the curve values of 0.93-0.96.

CONCLUSION

The ADC value, texture features, and their combination demonstrated good diagnostic ability to distinguish between WTs and PAs. This method may be used to aid the differential diagnosis of parotid gland tumors, thereby promoting timely and adequate treatment.

Magnetic resonance image texture analysis of the lateral pterygoid muscle in patients with rheumatoid arthritis: a preliminary report

OBJECTIVES

Magnetic resonance imaging (MRI) is useful for assessing temporomandibular disorders (TMDs). However, few studies have attempted texture analysis of the lateral pterygoid muscle in patients with rheumatoid arthritis (RA). This study aims to investigate the usefulness of MRI texture analysis of the lateral pterygoid muscle of patients with RA of the temporomandibular joint (TMJ).

METHODS

We analyzed the data from 36 patients (18 non-RA patients and 18 RA patients) who complained of pain and underwent MRI between April 2008 and August 2021. From the MRI scans of these patients, 279 radiomics features were extracted using STIR image data of the ROIs on the lateral pterygoid muscle of patients with RA and analyzed using MaZda ver. 3.3. Seven gray-level co-occurrence matrix features (Sum entropy, Sum variance) were picked up using the Fisher coefficient, for comparison between the RA and non-RA groups. Data analysis was performed using the Mann-Whitney U test A P value of < 0.05 was considered as statistically significant.

RESULTS

All seven lateral pterygoid muscle radiomic features indicated significant differences between the non-RA and RA groups (P < 0.05).

CONCLUSION

MRI texture analysis shows potential for application in radiomics diagnosis of RA in TMJ.

Whole-tumor radiomics analysis of T2-weighted imaging in differentiating neuroblastoma from ganglioneuroblastoma/ganglioneuroma in children: an exploratory study

PURPOSE

To examine the potential of whole-tumor radiomics analysis of T2-weighted imaging (T2WI) in differentiating neuroblastoma (NB) from ganglioneuroblastoma/ganglioneuroma (GNB/GN) in children.

MATERIALS AND METHODS

This study included 102 children with peripheral neuroblastic tumors, comprising 47 NB patients and 55 GNB/GN patients, which were randomly divided into a training group (n = 72) and a test group (n = 30). Radiomics features were extracted from T2WI images, and feature dimensionality reduction was applied. Linear discriminant analysis was used to construct radiomics models, and one-standard error role combined with leave-one-out cross-validation was used to choose the optimal radiomics model with the least predictive error. Subsequently, the patient age at initial diagnosis and the selected radiomics features were incorporated to construct a combined model. The receiver operator characteristic (ROC) curve, decision curve analysis (DCA) and clinical impact curve (CIC) were applied to evaluate the diagnostic performance and clinical utility of the models.

RESULTS

Fifteen radiomics features were eventually chosen to construct the optimal radiomics model. The area under the curve (AUC) of the radiomics model in the training group and test group was 0.940 [95% confidence interval (CI) 0.886, 0.995] and 0.799 (95%CI 0.632, 0.966), respectively. The combined model, which incorporated patient age and radiomics features, achieved an AUC of 0.963 (95%CI 0.925, 1.000) in the training group and 0.871 (95%CI 0.744, 0.997) in the test group. DCA and CIC demonstrated that the radiomics model and combined model could provide benefits at various thresholds, with the combined model being superior to the radiomics model.

CONCLUSION

Radiomics features derived from T2WI, in combination with the age of the patient at initial diagnosis, may offer a quantitative method for distinguishing NB from GNB/GN, thus aiding in the pathological differentiation of peripheral neuroblastic tumors in children.

Machine learning-based CT radiomics model to discriminate the primary and secondary intracranial hemorrhage

It is challenging to distinguish between primary and secondary intracranial hemorrhage (ICH) purely by imaging data, and the two forms of ICHs are treated differently. This study aims to evaluate the potential of CT-based machine learning to identify the etiology of ICHs and compare the effectiveness of two regions of interest (ROI) sketching methods. A total of 1702 radiomic features were extracted from the CT brain images of 238 patients with acute ICH. We used the Select K Best method, least absolute shrinkage, and selection operator logistic regression to select the most discriminable features with a support vector machine to build a classifier model. Then, a ten-fold cross-validation strategy was employed to evaluate the performance of the classifier. From all quantitative CT-based imaging features obtained by two sketch methods, eighteen features were selected respectively. The radiomics model outperformed radiologists in distinguishing between primary and secondary ICH in both the volume of interest and the three-layer ROI sketches. As a result, a machine learning-based CT radiomics model can improve the accuracy of identifying primary and secondary ICH. A three-layer ROI sketch can identify primary versus secondary ICH based on the CT radiomics method.

Histogram analysis of synthetic magnetic resonance imaging: Correlations with histopathological factors in head and neck squamous cell carcinoma

PURPOSE

To analyse the association between histogram parameters derived from synthetic MRI (SyMRI) and different histopathological factors in head and neck squamous cell carcinoma (HNSCC).

METHOD

Sixty-one patients with histologically proven primary HNSCC were prospectively enrolled. The correlations between histogram parameters of SyMRI (T1, T2 and proton density (PD) maps) and histopathological factors were analysed using Spearman analysis. The Mann-Whitney U test or Student's t test was utilized to differentiate histological grades and human papillomavirus (HPV) status. The ROC curves and leave-one-out cross-validation (LOOCV) were used to evaluate the differentiation performance. Bootstrapping was applied to avoid overfitting.

RESULTS

Several histogram parameters were associated with histological grade: T1 map (r = 0.291) and PD map (r = 0.294 - 0.382/-0.343), and PD_75th Percentile showed the highest differentiation performance (AUC: 0.721 (ROC) and 0.719 (LOOCV)). Moderately negative correlations were found between p16 status and the histogram parameters: T1 map (r = -0.587 - -0.390), T2 map (r = -0.649 - -0.357) and PD map (r = -0.537 - -0.338). In differentiating HPV infection, Entropy was the most discriminative parameter in each map and T2_Entropy showed the highest diagnostic performance (AUC: 0.851 [ROC] and 0.851 [LOOCV]). Additionally, several histogram parameters were correlated with Ki-67 (r = -0.379/-0.397), epidermal growth factor receptor (EGFR) (r = 0.318/0.322) status and p53 (r = 0.452 - 0.665/-0.607) status.

CONCLUSIONS

Histogram parameters derived from SyMRI may serve as a potential biomarker for discriminating relevant histopathological features, including histological differentiation grade, HPV infection, Ki-67, EGFR and p53 statuses.

Radiomics-Based Machine Learning Model for Predicting Overall and Progression-Free Survival in Rare Cancer: A Case Study for Primary CNS Lymphoma Patients

Primary Central Nervous System Lymphoma (PCNSL) is an aggressive neoplasm with a poor prognosis. Although therapeutic progresses have significantly improved Overall Survival (OS), a number of patients do not respond to HD–MTX-based chemotherapy (15–25%) or experience relapse (25–50%) after an initial response. The reasons underlying this poor response to therapy are unknown. Thus, there is an urgent need to develop improved predictive models for PCNSL. In this study, we investigated whether radiomics features can improve outcome prediction in patients with PCNSL. A total of 80 patients diagnosed with PCNSL were enrolled. A patient sub-group, with complete Magnetic Resonance Imaging (MRI) series, were selected for the stratification analysis. Following radiomics feature extraction and selection, different Machine Learning (ML) models were tested for OS and Progression-free Survival (PFS) prediction. To assess the stability of the selected features, images from 23 patients scanned at three different time points were used to compute the Interclass Correlation Coefficient (ICC) and to evaluate the reproducibility of each feature for both original and normalized images. Features extracted from Z-score normalized images were significantly more stable than those extracted from non-normalized images with an improvement of about 38% on average (p-value < 10−12). The area under the ROC curve (AUC) showed that radiomics-based prediction overcame prediction based on current clinical prognostic factors with an improvement of 23% for OS and 50% for PFS, respectively. These results indicate that radiomics features extracted from normalized MR images can improve prognosis stratification of PCNSL patients and pave the way for further study on its potential role to drive treatment choice.

Diagnostic efficacy of apparent diffusion coefficient, texture features, and their combination for differential diagnosis of odontogenic cysts and tumors

OBJECTIVE

This study assessed the diagnostic efficacy of apparent diffusion coefficient (ADC), texture features, and their combination for the differential diagnosis of odontogenic cysts and tumors with cyst-like features.

STUDY DESIGN

In total, 14 dentigerous cysts (DCs), 12 odontogenic keratocysts (OKCs), and 6 unicystic ameloblastomas (UABs) were used as predictor variables in 32 outpatients who underwent magnetic resonance imaging. The outcome variables were ADC, texture features, and their combination for each lesion. Texture features including histogram and gray-level co-occurrence matrix (GLCM) were measured on ADC maps. Ten features were selected by using the Fisher coefficient method. The Kruskal-Wallis test and post hoc Mann-Whitney test with Bonferroni adjustment were used to analyze trivariate statistics. Statistical significance was established at P < .05. Receiver operating characteristic analysis was used to evaluate the diagnostic effect of ADC, texture features, and their combination in distinguishing the lesions from each other.

RESULTS

Apparent diffusion coefficient, 1 histogram feature, 9 GLCM features, and their combination demonstrated significant differences between DC, OKC, and UAB (P ≤ .01). Receiver operating characteristic analysis revealed a high area under the curve of .95 to 1.00 for ADC, 10 texture features, and their combination. Sensitivity, specificity, and accuracy ranged from .86 to 1.00.

CONCLUSIONS

Apparent diffusion coefficient and texture features, alone or in combination, can be clinically important in facilitating the distinction between these odontogenic lesions.

Efficacy of magnetic resonance imaging texture features of the lateral pterygoid muscle in distinguishing rheumatoid arthritis and osteoarthritis of the temporomandibular joint

OBJECTIVES

The aim of this study was to assess whether magnetic resonance imaging (MRI) texture features of the lateral pterygoid muscle can distinguish between rheumatoid arthritis (RA) and osteoarthritis (OA) of the temporomandibular joint (TMJ).

METHODS

The authors extracted 279 texture features from 36 patients with RA and OA from the region of interest set for the lateral pterygoid muscle on short tau inversion recovery (STIR) images using MaZda Ver.3.3. A total of 10 texture features were selected using Fisher's coefficients, as well as probability of error and average correlation coefficients. Data observed to have a non-normal distribution using the Kolmogorov-Smirnov test were compared using the Mann-Whitney U-test. Receiver operating characteristic (ROC) curves were used to assess the ability of the 10 texture features to distinguish RA and OA of the TMJ.

RESULTS

A total of 10 features (5 Correlation, 3 Run Length Nonuniformity, 1 Sigma, and 1 Teta) were selected from 279 texture features. These texture features revealed significant differences between the RA and OA groups (p < 0.01). The sensitivity, specificity, accuracy, and area under the ROC curve of the texture features for distinguishing RA from OA were 0.78-0.94, 0.89-1.0, 0.86-0.92, and 0.89-0.95, respectively.

CONCLUSION

MRI texture analysis of the lateral pterygoid muscle may be useful for distinguishing between RA and OA of the TMJ.

Synthetic MRI in differentiating benign from metastatic retropharyngeal lymph node: combination with diffusion-weighted imaging

OBJECTIVES

This study aimed to evaluate the synthetic MRI (syMRI), its combination with diffusion-weighted imaging (DWI), and morphological features for discriminating benign from metastatic retropharyngeal lymph nodes (RLNs).

METHODS

Fifty-eight patients with a total of 63 RLNs (21 benign and 42 metastatic) were enrolled. The mean and standard deviation of syMRI-derived relaxometry parameters (T1, T2, PD; T1_SD, T2_SD, PD_SD) were obtained from two different regions of interest (namely, partial-lesion and full-lesion ROI). The parameters derived from benign and metastatic RLNs were compared using Student's t or chi-square tests. Logistic regression analysis was used to construct a multi-parameter model of syMRI, syMRI + DWI, and syMRI + DWI + morphological features. Areas under the curve (AUC) were compared using the DeLong test to determine the best diagnostic approach.

RESULTS

Benign RLNs had significantly higher T1, T2, PD, and T1_SD values compared with metastatic RLNs in both partial-lesion and full-lesion ROI (all p < 0.05). The T1_SD obtained from full-lesion ROI showed the best diagnostic performance among all syMRI-derived single parameters. The AUC of combined syMRI multiple parameters (T1, T2, PD, T1_SD) were higher than those of any single parameter from syMRI. The combination of synthetic MRI and DWI can improve the AUC regardless of ROI delineation. Furthermore, the combination of synthetic MRI, DWI-derived quantitative parameters, and morphological features can significantly improve the overall diagnostic performance.

CONCLUSIONS

The value of syMRI has been validated in differential diagnosis of benign and metastatic RLNs, and syMRI + DWI + morphological features can further improve the diagnostic efficiency for discriminating these two entities.

KEY POINTS

• Synthetic MRI was useful in differential diagnosis of benign and metastatic RLNs. • The combination of syMRI, DWI, and morphological features can significantly improve the diagnostic efficiency.

Texture analysis of conventional magnetic resonance imaging and diffusion-weighted imaging for distinguishing sinonasal non-Hodgkin's lymphoma from squamous cell carcinoma

PURPOSE

To evaluate the value of texture analysis (TA) of conventional magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) in the differential diagnosis between sinonasal non-Hodgkin's lymphoma (NHL) and squamous cell carcinoma (SCC).

METHODS

Forty-two patients with sinonasal SCC and 30 patients with NHL were retrospectively enrolled. TAs were performed on T2-weighted image (T2WI), apparent diffusion coefficient (ADC) and contrast-enhanced T1-weighted image (T1WI). Texture parameters, including mean value, skewness, kurtosis, entropy and uniformity were obtained and compared between sinonasal SCC and NHL groups. Receiver-operating characteristic (ROC) curves and logistic regression analyses were used to evaluate the diagnostic value and identify the independent TA parameters.

RESULTS

The mean value and entropy of ADC, and mean value of contrast-enhanced T1WI were significantly lower in the sinonasal NHL group than those in the SCC group (all P < 0.05). ROC analysis indicated that the entropy of ADC had the best diagnostic performance (AUC 0.832; Sensitivity 0.95; Specificity 0.67; Cutoff value 6.522). Logistic regression analysis showed that the entropy of ADC (P = 0.002, OR = 26.990) was the independent parameter for differentiating sinonasal NHL from SCC.

CONCLUSION

TA parameters of conventional MRI and DWI, particularly the entropy value of ADC, might be useful in the differentiating diagnosis between sinonasal NHL and SCC.

Quantitative texture analysis based on dynamic contrast enhanced MRI for differential diagnosis between primary thymic lymphoma from thymic carcinoma

To evaluate the value of texture analysis based on dynamic contrast enhanced MRI (DCE-MRI) in the differential diagnosis of thymic carcinoma and thymic lymphoma. Sixty-nine patients with pathologically confirmed (thymic carcinoma, n = 32; thymic lymphoma, n = 37) were enrolled in this retrospective study. Ktrans, Kep and Ve maps were automatically generated, and texture features were extracted, including mean, median, 5th/95th percentile, skewness, kurtosis, diff-variance, diff-entropy, contrast and entropy. The differences in parameters between the two groups were compared and the diagnostic efficacy was calculated. The Ktrans-related significant features yielded an area under the curve (AUC) of 0.769 (sensitivity 90.6%, specificity 51.4%) for the differentiation between thymic carcinoma and thymic lymphoma. The Kep-related significant features yielded an AUC of 0.780 (sensitivity 87.5%, specificity 62.2%). The Ve-related significant features yielded an AUC of 0.807 (sensitivity 75.0%, specificity 78.4%). The combination of DCE-MRI textural features yielded an AUC of 0.962 (sensitivity 93.8%, specificity 89.2%). Five parameters were screened out, including age, Ktrans-entropy, Kep-entropy, Ve-entropy, and Ve-P95. The combination of these five parameters yielded the best discrimination efficiency (AUC of 0.943, 93.7% sensitivity, 81.1% specificity). Texture analysis of DCE-MRI may be helpful to distinguish thymic carcinoma from thymic lymphoma.

Head and neck cancer N-glycome traits are cell line and HPV status–dependent

Glycosylation is the most common post-translational modification of proteins, and glycosylation changes at cell surfaces are frequently associated with malignant epithelia including head and neck squamous cell carcinoma (HNSCC). In HNSCC, 5-year survival remains poor, averaging around 50% globally: this is partly related to late diagnosis. Specific protein glycosylation signatures on malignant keratinocytes have promise as diagnostic and prognostic biomarkers and as therapeutic targets. Nevertheless, HNSCC-specific glycome is to date largely unknown. Herein, we tested six established HNSCC cell lines to capture the qualitative and semi-quantitative N-glycome using porous graphitized carbon liquid chromatography coupled to electrospray ionisation tandem mass spectrometry. Oligomannose-type N-glycans were the predominant features in all HNSCC cell lines analysed (57.5–70%). The levels of sialylated N-glycans showed considerable cell line-dependent differences ranging from 24 to 35%. Importantly, α2-6 linked sialylated N-glycans were dominant across most HNSCC cell lines except in SCC-9 cells where similar levels of α2-6 and α2-3 sialylated N-glycans were observed. Furthermore, we found that HPV-positive cell lines contained higher levels of phosphorylated oligomannose N-glycans, which hint towards an upregulation of lysosomal pathways. Almost all fucose-type N-glycans carried core-fucose residues with just minor levels (< 4%) of Lewis-type fucosylation identified. We also observed paucimannose-type N-glycans (2–5.5%), though in low levels. Finally, we identified oligomannose N-glycans carrying core-fucose residues and confirmed their structure by tandem mass spectrometry. This first systematic mapping of the N-glycome revealed diverse and specific glycosylation features in HNSCC, paving the way for further studies aimed at assessing their possible diagnostic relevance.

Diagnostic utility of magnetic resonance imaging texture analysis in suppurative osteomyelitis of the mandible

PURPOSE

This study aimed to determine the diagnostic utility of magnetic resonance imaging (MRI) texture analysis for evaluating mandibular suppurative osteomyelitis (OM).

MATERIALS AND METHODS

In this retrospective cohort study, we analyzed the records of 50 patients with and without OM who underwent MRI between April 2019 and March 2021. The presence or absence of OM served as a predictor variable. The outcome variables were the texture features of the region of interest, which were analyzed. Quantitative parameters based on histogram features (90th percentile) and gray-level co-occurrence matrix (GLCM) features (Sum Averg) were calculated using short-tau inversion-recovery data with a region of interest. These six features out of 279 parameters were selected using Fisher, probability of error, and average correlation coefficient methods in MaZda. For the analysis of trivariate statistics, the post-Mann-Whitney test of the Kruskal-Wallis test with Bonferroni adjustment was used, and the p value was set to 0.05. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic effect of texture function to distinguish between acute and chronic diseases.

RESULTS

One histogram feature and five GLCM features showed differences among the non-OM patients, acute OM patients, and chronic OM patients (p < 0.05). The ROC analysis revealed a high area under the curve ranging from 0.91 to 0.96 for six texture features.

CONCLUSION

The six texture features of the mandibular bone marrow demonstrated differences among patients without and with acute and chronic OM. MRI texture analysis may facilitate accurate assessment of the mandibular OM stage.

Image quality and whole-lesion histogram and texture analysis of diffusion-weighted imaging of breast MRI based on advanced ZOOMit and simultaneous multislice readout-segmented echo-planar imaging

Objectives

To investigate the image quality and diagnostic capability a of whole-lesion histogram and texture analysis of advanced ZOOMit (A-ZOOMit) and simultaneous multislice readout-segmented echo-planar imaging (SMS-RS-EPI) to differentiate benign from malignant breast lesions.

Study design

From February 2020 to October 2020, diffusion-weighted imaging (DWI) using SMS-RS-EPI and A-ZOOMit were performed on 167 patients. Three breast radiologists independently ranked the image datasets. The inter-/intracorrelation coefficients (ICCs) of mean image quality scores and lesion conspicuity scores were calculated between these three readers. Histogram and texture features were extracted from the apparent diffusion coefficient (ADC) maps, respectively, based on a WL analysis. Student’s t-tests, one-way ANOVAs, Mann–Whitney U tests, and receiver operating characteristic curves were used for statistical analysis.

Results

The overall image quality scores and lesion conspicuity scores for A-ZOOMit and SMS-RS-EPI showed statistically significant differences (4.92 ± 0.27 vs. 3.92 ± 0.42 and 4.93 ± 0.29 vs. 3.87 ± 0.47, p < 0.0001). The ICCs for the image quality and lesion conspicuity scores had good agreements among the three readers (all ICCs >0.75). To differentiate benign and malignant breast lesions, the entropy of ADC_A-Zoomit had the highest area (0.78) under the ROC curve.

Conclusions

A-ZOOMit achieved higher image quality and lesion conspicuity than SMS-RS-EPI. Entropy based on A-ZOOMit is recommended for differentiating benign from malignant breast lesions.

Comparison of the Classification Results Accuracy for CT Soft Tissue and Bone Reconstructions in Detecting the Porosity of a Spongy Tissue

The aim of the study was to compare the accuracy of the classification pertaining to the results of two types of soft tissue and bone reconstructions of the spinal CT in detecting the porosity of L1 vertebral body spongy tissue. The dataset for each type of reconstruction (high-resolution bone reconstruction and soft tissue reconstruction) included 400 sponge tissue images from 50 healthy patients and 50 patients with osteoporosis. Texture feature descriptors were calculated based on the statistical analysis of the grey image histogram, autoregression model, and wavelet transform. The data dimensional reduction was applied by feature selection using nine methods representing various approaches (filter, wrapper, and embedded methods). Eleven methods were used to build the classifier models. In the learning process, hyperparametric optimization based on the grid search method was applied. On this basis, the most effective model and the optimal subset of features for each selection method used were determined. In the case of bone reconstruction images, four models achieved a maximum accuracy of 92%, one of which had the highest sensitivity of 95%, with a specificity of 89%. For soft tissue reconstruction images, five models achieved the highest testing accuracy of 95%, whereas the other quality indices (TPR and TNR) were also equal to 95%. The research showed that the images derived from soft tissue reconstruction allow for obtaining more accurate values of texture parameters, which increases the accuracy of the classification and offers better possibilities for diagnosing osteoporosis.

The utility of diffusion-weighted T2 mapping for the prediction of histological tumor grade in patients with head and neck squamous cell carcinoma

Background

In head and neck cancers, histopathological information is important for the determination of the tumor characteristics and for predicting the prognosis. The aim of this study was to assess the utility of diffusion-weighted T2 (DW-T2) mapping for the evaluation of tumor histological grade in patients with head and neck squamous cell carcinoma (SCC).

Methods

The cases of 41 patients with head and neck SCC (21 well/moderately and 17 poorly differentiated SCC) were retrospectively analyzed. All patients received MR scanning using a 3-Tesla MR unit. The conventional T2 value, DW-T2 value, ratio of DW-T2 value to conventional T2 value, and apparent diffusion coefficient (ADC) were calculated using signal information from the DW-T2 mapping sequence with a manually placed region of interest (ROI).

Results

ADC values in the poorly differentiated SCC group were significantly lower than those in the moderately/well differentiated SCC group (P<0.05). The ratio of DW-T2 value to conventional T2 value was also significantly different between poorly and moderately/well differentiated SCC groups (P<0.01). Receiver operating characteristic (ROC) curve analysis of ADC values showed a sensitivity of 0.76, specificity of 0.67, positive predictive value (PPV) of 0.62, negative predictive value (NPV) of 0.8, accuracy of 0.71 and area under the curve (AUC) of 0.73, whereas the ROC curve analysis of the ratio of DW-T2 value to conventional T2 value showed a sensitivity of 0.76, specificity of 0.83, PPV of 0.76, NPV of 0.83, accuracy of 0.8 and AUC of 0.82.

Conclusions

DW-T2 mapping might be useful as supportive information for the determination of tumor histological grade in patients with head and neck SCC.

Amide proton transfer imaging for the determination of human papillomavirus status in patients with oropharyngeal squamous cell carcinoma

The aim of this study was to investigate the utility of amide proton transfer (APT) imaging for the determination of human papillomavirus (HPV) status in patients with oropharyngeal squamous cell carcinoma (SCC). Thirty-one patients with oropharyngeal SCC were retrospectively evaluated. All patients underwent amide proton transfer imaging using a 3T magnetic resonance (MR) unit. Patients were divided into HPV-positive and -negative groups depending on the pathological findings in their primary tumor. In APT imaging, the primary tumor was delineated with a polygonal region of interest (ROI). Signal information in the ROI was used to calculate the mean, standard deviation (SD) and coefficient of variant (CV) of the APT signals (APT mean, APT SD, and APT CV, respectively). The value of APT CV in the HPV-positive group (0.43 ± 0.04) was significantly lower than that in the HPV-negative group (0.48 ± 0.04) (P = .01). There was no significant difference in APT mean (P = .82) or APT SD (P = .13) between the HPV-positive and -negative groups. Receiver operating characteristic (ROC) curve analysis of APT CV had a sensitivity of 0.75, specificity of 0.8, positive predictive value of 0.75, negative predictive value of 0.8, accuracy of 0.77 and area under the curve (AUC) of 0.8. The APT signal in the HPV-negative group was considered heterogeneous compared to the HPV-positive group. This information might be useful for the determination of HPV status in patients with oropharyngeal SCC.

MRI whole-lesion texture analysis on ADC maps for the prognostic assessment of ischemic stroke

Background

This study aims is to explore whether it is feasible to use magnetic resonance texture analysis (MRTA) in order to distinguish favorable from unfavorable function outcomes and determine the prognostic factors associated with favorable outcomes of stroke.

Methods

The retrospective study included 103 consecutive patients who confirmed unilateral anterior circulation subacute ischemic stroke by computed tomography angiography between January 2018 and September 2019. Patients were divided into favorable outcome (modified Rankin scale, mRS ≤ 2) and unfavorable outcome (mRS > 2) groups according to mRS scores at day 90. Two radiologists manually segmented the infarction lesions based on diffusion-weighted imaging and transferred the images to corresponding apparent diffusion coefficient (ADC) maps in order to extract texture features. The prediction models including clinical characteristics and texture features were built using multiple logistic regression. A univariate analysis was conducted to assess the performance of the mean ADC value of the infarction lesion. A Delong’s test was used to compare the predictive performance of models through the receiver operating characteristic curve.

Results

The mean ADC performance was moderate [AUC = 0.60, 95% confidence interval (CI) 0.49–0.71]. The texture feature model of the ADC map (tADC), contained seven texture features, and presented good prediction performance (AUC = 0.83, 95%CI 0.75–0.91). The energy obtained after wavelet transform, and the kurtosis and skewness obtained after Laplacian of Gaussian transformation were identified as independent prognostic factors for the favorable stroke outcomes. In addition, the combination of the tADC model and clinical characteristics (hypertension, diabetes mellitus, smoking, and atrial fibrillation) exhibited a subtly better performance (AUC = 0.86, 95%CI 0.79–0.93; P > 0.05, Delong’s).

Conclusion

The models based on MRTA on ADC maps are useful to evaluate the clinical function outcomes in patients with unilateral anterior circulation ischemic stroke. Energy obtained after wavelet transform, kurtosis obtained after Laplacian of Gaussian transform, and skewness obtained after Laplacian of Gaussian transform were identified as independent prognostic factors for favorable stroke outcomes.

Apparent Diffusion Coefficient-Based Radiomic Nomogram in Sinonasal Squamous Cell Carcinoma: A Preliminary Study on Histological Grade Evaluation

PURPOSE

The aim of the study was to develop and validate a nomogram model combining radiomic features and clinical characteristics to preoperatively differentiate between low- and high-grade sinonasal squamous cell carcinomas.

MATERIAL AND METHODS

A total of 174 patients who underwent diffusion-weighted imaging were included in this study. The patients were allocated to the training and testing cohorts randomly at a ratio of 6:4. The least absolute shrinkage and selection operator regression was applied for feature selection and radiomic signature (radscore) construction. Multivariable logistic regression analysis was applied to identify independent predictors. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC), the calibration curve, decision curve analysis, and the clinical impact curve.

RESULTS

The radscore included 9 selected radiomic features. The radscore and clinical stage were independent predictors. The nomogram showed better performance (training cohort: AUC, 0.92; 95% confidence interval, 0.85-0.96; testing cohort: AUC, 0.91; 95% CI, 0.82-0.97) than either the radscore or the clinical stage in both the training and test cohorts (P < 0.050). The nomogram demonstrated good calibration and clinical usefulness.

CONCLUSIONS

The apparent diffusion coefficient-based radiomic nomogram model could be useful in differentiating between low- and high-grade sinonasal squamous cell carcinomas.

Diagnostic accuracy of quantitative susceptibility mapping in multiple system atrophy: The impact of echo time and the potential of histogram analysis

•

We performed histogram analysis on χ maps at different TEs on MSA patients and HC.

•

We found altered χ distribution in Pu, SN, GP, CN for MSAp and in SN, DN for MSAc.

•

QSM diagnostic accuracy is TE-dependent and is enhanced at short TEs.

•

Short TEs capture rapidly-decaying contributions of high χ sources.

•

Histogram features detect χ spatial heterogeneities improving diagnostic accuracy.

The non-invasive quantification of iron stores via Quantitative Susceptibility Mapping (QSM) could play an important role in the diagnosis and the differential diagnosis of atypical Parkinsonisms. However, the susceptibility (χ) values measured via QSM depend on echo time (TE). This effect relates to the microstructural organization within the voxel, whose composition can be altered by the disease. Moreover, pathological iron deposition in a brain area may not be spatially uniform, and conventional Region of Interest (ROI)-based analysis may fail in detecting alterations. Therefore, in this work we evaluated the impact of echo time on the diagnostic accuracy of QSM on a population of patients with Multiple System Atrophy (MSA) of either Parkinsonian (MSAp) or cerebellar (MSAc) phenotypes. In addition, we tested the potential of histogram analysis to improve QSM classification accuracy.

We enrolled 32 patients (19 MSAp and 13 MSAc) and 16 healthy controls, who underwent a 7T MRI session including a gradient-recalled multi-echo sequence for χ mapping. Nine histogram features were extracted from the χ maps computed for each TE in atlas-based ROIs covering deep brain nuclei, and compared among groups.

Alterations of susceptibility distribution were found in the Putamen, Substantia Nigra, Globus Pallidus and Caudate Nucleus for MSAp and in the Substantia Nigra and Dentate Nucleus for MSAc. Increased iron deposition was observed in a larger number of ROIs for the two shortest TEs and the standard deviation, the 75^th and the 90^th percentile were the most informative features yielding excellent diagnostic accuracy with area under the ROC curve > 0.9.

In conclusion, short TEs may enhance QSM diagnostic performances, as they can capture variations in rapidly-decaying contributions of high χ sources. The analysis of histogram features allowed to reveal fine heterogeneities in the spatial distribution of susceptibility alteration, otherwise undetected by a simple evaluation of ROI χ mean values.

Texture Analysis of Fat-Suppressed T2-Weighted Magnetic Resonance Imaging and Use of Machine Learning to Discriminate Nasal and Paranasal Sinus Small Round Malignant Cell Tumors

Objective

We used texture analysis and machine learning (ML) to classify small round cell malignant tumors (SRCMTs) and Non-SRCMTs of nasal and paranasal sinus on fat-suppressed T2 weighted imaging (Fs-T2WI).

Materials

Preoperative MRI scans of 164 patients from 1 January 2018 to 1 January 2021 diagnosed with SRCMTs and Non-SRCMTs were included in this study. A total of 271 features were extracted from each regions of interest. Datasets were randomly divided into two sets, including a training set (∼70%) and a test set (∼30%). The Pearson correlation coefficient (PCC) and principal component analysis (PCA) methods were performed to reduce dimensions, and the Analysis of Variance (ANOVA), Kruskal-Wallis (KW), and Recursive Feature Elimination (RFE) and Relief were performed for feature selections. Classifications were performed using 10 ML classifiers. Results were evaluated using a leave one out cross-validation analysis.

Results

We compared the AUC of all pipelines on the validation dataset with FeAture Explorer (FAE) software. The pipeline using a PCC dimension reduction, relief feature selection, and gaussian process (GP) classifier yielded the highest area under the curve (AUC) using 15 features. When the “one-standard error” rule was used, FAE also produced a simpler model with 13 features, including S(5,-5)SumAverg, S(3,0)InvDfMom, Skewness, WavEnHL_s-3, Horzl_GlevNonU, Horzl_RLNonUni, 135dr_GlevNonU, WavEnLL_s-3, Teta4, Teta2, S(5,5)DifVarnc, Perc.01%, and WavEnLH_s-2. The AUCs of the training/validation/test datasets were 1.000/0.965/0.979, and the accuracies, sensitivities, and specificities were 0.890, 0.880, and 0.920, respectively. The best algorithm was GP whose AUCs of the training/validation/test datasets by the two-dimensional reduction methods and four feature selection methods were greater than approximately 0.800. Especially, the AUCs of different datasets were greater than approximately 0.900 using the PCC, RFE/Relief, and GP algorithms.

Conclusions

We demonstrated the feasibility of combining artificial intelligence and the radiomics from Fs-T2WI to differentially diagnose SRCMTs and Non-SRCMTs. This non-invasive approach could be very promising in clinical oncology.

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.

Prediction of the degree of pathological differentiation in tongue squamous cell carcinoma based on radiomics analysis of magnetic resonance images

Background

Tongue squamous cell carcinoma (TSCC) is one of the most difficult malignancies to control. It displays particular and aggressive behaviour even at an early stage. The purpose of this paper is to explore the value of radiomics based on magnetic resonance fat-suppressed T2-weighted images in predicting the degree of pathological differentiation of TSCC.

Methods

Retrospective analysis of 127 patients with TSCC who were randomly divided into a primary cohort and a test cohort, including well-differentiated, moderately differentiated and poorly differentiated. The tumour regions were manually labelled in fat-suppressed T2-weighted imaging (FS-T2WI), and PyRadiomics was used to extract radiomics features. The radiomics features were then selected by the least absolute shrinkage and selection operator (LASSO) method. The model was established by the logistic regression classifier using a 5-fold cross-validation method, applied to all data and evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity.

Results

In total, 1132 features were extracted, and seven features were selected for modelling. The AUC in the logistic regression model for well-differentiated TSCC was 0.90 with specificity and precision values of 0.92 and 0.78, respectively, and the sensitivity for poorly differentiated TSCC was 0.74.

Conclusions

The MRI-based radiomics signature could discriminate between well-differentiated, moderately differentiated and poorly differentiated TSCC and might be used as a biomarker for preoperative grading.

Texture Analysis and its Applications in Biomedical Imaging: A Survey

Texture analysis describes a variety of image analysis techniques that quantify the variation in intensity and pattern. This paper provides an overview of several texture analysis approaches addressing the rationale supporting them, their advantages, drawbacks, and applications. This surveys emphasis is in collecting and categorising over five decades of active research on texture analysis. Brief descriptions of different approaches are presented along with application examples. From a broad range of texture analysis applications, this surveys final focus is on biomedical image analysis. An up-to-date list of biological tissues and organs in which disorders produce texture changes that may be used to spot disease onset and progression is provided. Finally, the role of texture analysis methods as biomarkers of disease is summarised.

Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint

Brain tumor image classification is an important part of medical image processing. It assists doctors to make accurate diagnosis and treatment plans. Magnetic resonance (MR) imaging is one of the main imaging tools to study brain tissue. In this article, we propose a brain tumor MR image classification method using convolutional dictionary learning with local constraint (CDLLC). Our method integrates the multi-layer dictionary learning into a convolutional neural network (CNN) structure to explore the discriminative information. Encoding a vector on a dictionary can be considered as multiple projections into new spaces, and the obtained coding vector is sparse. Meanwhile, in order to preserve the geometric structure of data and utilize the supervised information, we construct the local constraint of atoms through a supervised k-nearest neighbor graph, so that the discrimination of the obtained dictionary is strong. To solve the proposed problem, an efficient iterative optimization scheme is designed. In the experiment, two clinically relevant multi-class classification tasks on the Cheng and REMBRANDT datasets are designed. The evaluation results demonstrate that our method is effective for brain tumor MR image classification, and it could outperform other comparisons.

Preoperative T2-weighted MR imaging texture analysis of gastric cancer: prediction of TNM stages

PURPOSE

To explore the capability of algorithms to build multivariate models integrating morphological and texture features derived from preoperative T₂-weighted magnetic resonance (MR) images of gastric cancer (GC) to evaluate tumor- (T), node- (N), and metastasis- (M) stages.

METHODS

A total of 80 patients at our hospital who underwent abdominal MR imaging and were diagnosed with GC from December 2011 to November 2016 were retrospectively included. Texture features were calculated using T₂-weighted images with a manual region of interest. Morphological characteristics were also evaluated. Classifiers and regression analyses were used to build multivariate models. Receiver operating characteristic (ROC) curve analysis was performed to assess diagnostic efficacy.

RESULTS

There were 8, 10, and 3 texture parameters that showed significant differences in GCs at different overall (I-II vs. III-IV), T (1-2 vs. 3-4), and N (- vs. +) stages (all p < 0.05), respectively. Mild thickening was more common in stages I-II, T1-2, and N- GCs (all p < 0.05). An irregular outer contour was more commonly observed in stages III-IV (p = 0.001) and T3-4 (p = 0.001) GCs. T3-4 and N+ GCs tended to be thickening type lesions (p = 0.005 and 0.032, respectively). The multivariate models using the naive bayes algorithm showed the highest diagnostic efficacy in predicting T and N stages (area under the ROC curves [AUC] = 0.900 and 0.863, respectively), and the model based on regression analysis had the best predictive performance in overall staging (AUC = 0.839).

CONCLUSION

Multivariate models combining morphological characteristics with texture parameters based on machine learning algorithms were able to improve diagnostic efficacy in predicting the overall, T, and N stages of GCs.

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.

Utility of CT texture analysis to differentiate olfactory neuroblastoma from sinonasal squamous cell carcinoma

The purpose of this study was to examine differences in texture features between olfactory neuroblastoma (ONB) and sinonasal squamous cell carcinoma (SCC) on contrast-enhanced CT (CECT) images, and to evaluate the predictive accuracy of texture analysis compared to radiologists’ interpretations. Forty-three patients with pathologically-diagnosed primary nasal and paranasal tumor (17 ONB and 26 SCC) were included. We extracted 42 texture features from tumor regions on CECT images obtained before treatment. In univariate analysis, each texture features were compared, with adjustment for multiple comparisons. In multivariate analysis, the elastic net was used to select useful texture features and to construct a texture-based prediction model with leave-one-out cross-validation. The prediction accuracy was compared with two radiologists’ visual interpretations. In univariate analysis, significant differences were observed for 28 of 42 texture features between ONB and SCC, with areas under the receiver operating characteristic curve between 0.68 and 0.91 (median: 0.80). In multivariate analysis, the elastic net model selected 18 texture features that contributed to differentiation. It tended to show slightly higher predictive accuracy than radiologists’ interpretations (86% and 74%, respectively; P = 0.096). In conclusion, several texture features contributed to differentiation of ONB from SCC, and the texture-based prediction model was considered useful.

Heterogeneity Measurement of Cardiac Tissues Leveraging Uncertainty Information from Image Segmentation

Identifying arrhythmia substrates and quantifying their heterogeneity has great potential to provide critical guidance for radio frequency ablation. However, quantitative analysis of heterogeneity on cardiac optical coherence tomography (OCT) images is lacking. In this paper, we conduct the first study on quantifying cardiac tissue heterogeneity from human OCT images. Our proposed method applies a dropout-based Monte Carlo sampling technique to measure the model uncertainty. The heterogeneity information is extracted by decoupling the intra/inter-tissue heterogeneity and tissue boundary uncertainty from the uncertainty measurement. We empirically demonstrate that our model can highlight the subtle features from OCT images, and the heterogeneity information extracted is positively correlated with the tissue heterogeneity information from corresponding histology images.

Texture analysis of routine T2 weighted fat-saturated images can identify head and neck paragangliomas - A pilot study

PURPOSE

To evaluate the role of the first and second-order texture parameters obtained from T2-weighted fat-saturated DIXON images in differentiating paragangliomas from other neck masses, and to develop a statistical model to classify them.

METHOD

We retrospectively evaluated 38 paragangliomas, 18 nerve-sheath tumours and 14 other miscellaneous neck lesions obtained from an IRB approved study conducted between January 2016 and June 2019; using a composite gold standard of histopathology, cytology and DOTANOC PET CT (A total of 70 lesions in 63 patients). Fat-suppressed T2weighted-DIXON axial images were used. First and second-order texture-parameters were calculated from the original and filtered images. Feature selection using F-statistics and collinearity analysis provided 14 texture parameters for further analysis. Mann-Whitney-U test was used to compare between the groups and p-values were adjusted for multiple comparisons. ROC curve analysis was used to obtain optimal cut-offs.

RESULTS

A total of ten texture features were found to be significantly different between paragangliomas and non-paraganglioma lesions. Minimum from the histogram of grey levels was lower in paragangliomas with a cut off of ≤113.462 obtaining 62.9 % sensitivity and 77.27 % specificity in differentiating paragangliomas from non-paragangliomas. Logistic regression model was trained (n-49) using forward feature selection, which when evaluated on the validation set(n-21)- obtained an AUC of 0.855(95 %CI, 0.633 to 0.968) with a positive likelihood ratio of 4.545 (95 %CI, 1.298-15.923) in differentiating paragangliomas from non-paragangliomas.

CONCLUSION

Texture analysis of a routine imaging sequence can identify paragangliomas with high accuracy. Further development of texture analysis would enable better imaging workflow, resource utilisation and imaging cost reductions.

Discrimination between pituitary adenoma and craniopharyngioma using MRI-based image features and texture features

PURPOSE

To investigate differences between pituitary adenoma and craniopharyngioma on magnetic resonance imaging (MRI) with image features and three-dimensional texture features.

MATERIALS AND METHODS

A total of 126 patients diagnosed with pituitary adenoma (N = 63) or craniopharyngioma (N = 63) were enrolled. Qualitative magnetic resonance (MR) image features and texture features of tumors were extracted from preoperative MRI and evaluated using chi-square test or Mann-Whitney U test. Binary logistic regression analyses were performed to assess their abilities as independent diagnostic predictors, and ROC analyses were conducted to evaluate the diagnostic value of significant features. Mann-Whitney U test and ROC analyses were performed to explore the relationship between MR image features and texture features.

RESULTS

Five MR image features were suggested to be significantly different between pituitary adenoma and craniopharyngioma. Three texture features from contrast-enhanced T1WI (HISTO-Skewness, GLCM-Contrast and GLCM-Energy), two texture features from T2WI (HISTO-Skewness and GLCM-Contrast) showed significant differences between two types of tumors. Logistic regression analyses suggested GLCM-Energy from contrast-enhanced T1WI, HISTO-Skewness and GLCM-Contrast from T2WI could be taken as independent predictors. Moreover, HISTO-Skewness and GLCM-Contrast from T2WI were found to be significantly related to cystic change.

CONCLUSION

MR image features and texture features were associated with each other, and both types of features represented feasible diagnostic value in discrimination between pituitary adenoma and craniopharyngioma.

Quantitative Histogram Analysis on Intracranial Atherosclerotic Plaques: A High-Resolution Magnetic Resonance Imaging Study

BACKGROUND AND PURPOSE

Intracranial atherosclerosis is one of the main causes of stroke, and high-resolution magnetic resonance imaging provides useful imaging biomarkers related to the risk of ischemic events. This study aims to evaluate differences in histogram features between culprit and nonculprit intracranial atherosclerosis using high-resolution magnetic resonance imaging.

METHODS

Two hundred forty-seven patients with intracranial atherosclerosis who underwent high-resolution magnetic resonance imaging sequentially between January 2015 and December 2016 were recruited. Quantitative features, including stenosis, plaque burden, minimum luminal area, intraplaque hemorrhage, enhancement ratio, and dispersion of signal intensity (coefficient of variation), were analyzed based on T2-, T1-, and contrast-enhanced T1-weighted images. Step-wise regression analysis was used to identify key determinates differentiating culprit and nonculprit plaques and to calculate the odds ratios (ORs) with 95% CIs.

RESULTS

In total, 190 plaques were identified, of which 88 plaques (37 culprit and 51 nonculprit) were located in the middle cerebral artery and 102 (57 culprit and 45 nonculprit) in the basilar artery. Nearly 90% of culprit lesions had a degree of luminal stenosis of <70%. Multiple logistic regression analyses showed that intraplaque hemorrhage (OR, 16.294 [95% CI, 1.043-254.632]; P=0.047), minimum luminal area (OR, 1.468 [95% CI, 1.032-2.087]; P=0.033), and coefficient of variation (OR, 13.425 [95% CI, 3.987-45.204]; P<0.001) were 3 significant features in defining culprit plaques in middle cerebral artery. The enhancement ratio (OR, 9.476 [95% CI, 1.256-71.464]; P=0.029), intraplaque hemorrhage (OR, 2.847 [95% CI, 0.971-10.203]; P=0.046), and coefficient of variation (OR, 10.068 [95% CI, 2.820-21.343]; P<0.001) were significantly associated with plaque type in basilar artery. Coefficient of variation was a strong independent predictor in defining plaque type for both middle cerebral artery and basilar artery with sensitivity, specificity, and accuracy being 0.79, 0.80, and 0.80, respectively.

CONCLUSIONS

Features characterized by high-resolution magnetic resonance imaging provided complementary values over luminal stenosis in defined lesion type for intracranial atherosclerosis; the dispersion of signal intensity in histogram analysis was a particularly effective predictive parameter.

MRI-Based Texture Features as Potential Prognostic Biomarkers in Anaplastic Astrocytoma Patients Undergoing Surgical Treatment

Objectives. The purpose of this study was to investigate whether texture features from magnetic resonance imaging (MRI) were associated with the overall survival (OS) of anaplastic astrocytoma (AA) patients undergoing surgical treatment. Methods. A total of 51 qualified patients who were diagnosed with AA and underwent surgical interventions in our institution were enrolled in this retrospective study. Patients were followed up for at least 30 months or until death. Texture features derived from histogram-based matrix (HISTO) and grey-level co-occurrence matrix (GLCM) were extracted from preoperative contrast-enhanced T1-weighted images. Each texture feature was dichotomized based on its optimal cutoff value calculated by receiver operating characteristics curve analysis. Kaplan–Meier analysis and log rank test were conducted to compare the 30-month OS between the dichotomized subgroups. Multivariate Cox regression analysis was performed to determine independent prognostic factors. Results. Three HISTO-derived features (HISTO-Energy, HISTO-Entropy, and HISTO-Skewness) and five GLCM-derived features (GLCM-Contrast, GLCM-Energy, GLCM-Entropy, GLCM-Homogeneity, and GLCM-Dissimilarity) were found to be significantly correlated with 30-month OS. Moreover, GLCM-Homogeneity (p=0.001, hazard ratio = 6.351) was suggested to be the independent predictor of the patient survival. Conclusion. MRI-based texture features have the potential to be applied as prognostic biomarkers in AA patients undergoing surgical treatment.

MRI texture analysis in acromegaly and its role in predicting response to somatostatin receptor ligands

PURPOSE

Given the paucity of reliable predictors of tumor recurrence, progression, or response to somatostatin receptor ligand (SRL) therapy in acromegaly, we attempted to determine whether preoperative MR image texture was predictive of these clinical outcomes. We also determined whether image texture could differentiate somatotroph adenomas from non-functioning pituitary adenomas (NFPAs).

METHODS

We performed a retrospective study of patients with acromegaly due to a macroadenoma who underwent transsphenoidal surgery at our institution between 2007 and 2015. Clinical data were extracted from electronic medical records. MRI texture analysis was performed on preoperative non-enhanced T1-weighted images using ImageJ (NIH). Logistic and Cox models were used to determine if image texture parameters predicted outcomes.

RESULTS

Eighty-nine patients had texture parameters measured, which were compared to that of NFPAs, while 64 of these patients had follow-up and were included in the remainder of analyses. Minimum pixel intensity, skewness, and kurtosis were significantly different in somatotroph adenomas versus NFPAs (area under the receiver operating characteristic curve, 0.7771, for kurtosis). Furthermore, those with a maximum pixel intensity above the median had an increased odds of IGF-I normalization on SRL therapy (OR 5.96, 95% CI 1.33-26.66), which persisted after adjusting for several potential predictors of response. Image texture did not predict tumor recurrence or progression.

CONCLUSION

Our data suggest that MRI texture analysis can distinguish NFPAs from somatotroph macroadenomas with good diagnostic accuracy and can predict normalization of IGF-I with SRL therapy.

Current status and quality of radiomics studies in lymphoma: a systematic review

OBJECTIVES

To perform a systematic review regarding the developments in the field of radiomics in lymphoma. To evaluate the quality of included articles by the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), the phases classification criteria for image mining studies, and the radiomics quality scoring (RQS) tool.

METHODS

We searched for eligible articles in the MEDLINE/PubMed and EMBASE databases using the terms "radiomics", "texture" and "lymphoma". The included studies were divided into two categories: diagnosis-, therapy response- and outcome-related studies. The diagnosis-related studies were evaluated using the QUADAS-2; all studies were evaluated using the phases classification criteria for image mining studies and the RQS tool by two reviewers.

RESULTS

Forty-five studies were included; thirteen papers (28.9%) focused on the differential diagnosis of primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM). Thirty-two (71.1%) studies were classified as discovery science according to the phase classification criteria for image mining studies. The mean RQS score of all studies was 14.2% (ranging from 0.0 to 40.3%), and 23 studies (51.1%) were given a score of < 10%.

CONCLUSION

The radiomics features could serve as diagnostic and prognostic indicators in lymphoma. However, the current conclusions should be interpreted with caution due to the suboptimal quality of the studies. In order to introduce radiomics into lymphoma clinical settings, the lesion segmentation and selection, the influence of the pathological pattern and the extraction of multiple modalities and multiple time points features need to be further studied.

KEY POINTS

• The radiomics approach may provide useful information for diagnosis, prediction of the therapy response, and outcome of lymphoma. • The quality of published radiomics studies in lymphoma has been suboptimal to date. • More studies are needed to examine lesion selection and segmentation, the influence of pathological patterns, and the extraction of multiple modalities and multiple time point features.

Multicenter evaluation of MRI-based radiomic features: A phantom study

INTRODUCTION

This work describes the development of a novel radiomics phantom designed for magnetic resonance imaging (MRI) that can be used in a multicenter setting. The purpose of this study is to assess the stability and reproducibility of MRI-based radiomic features using this phantom across different MRI scanners.

METHODS & MATERIALS

A set of phantoms were three-dimensional (3D) printed using MRI visible materials. One set of phantoms were imaged on seven MRI scanners and one was imaged on one MRI scanner. Radiomics analysis of the phantoms, which included first-order features, shape and texture features was performed. Intraclass correlation coefficient (ICC) was used to assess the stability of radiomic features across eight scanners and the reproducibility of two printed models on one scanner. Coefficient of variation (COV) was used to assess the reproducibility of radiomics measurements in the phantom on a single scanner.

RESULTS

The phantom models provide sufficient signal-to-noise and contrast in all the tumor models permitting robust automatic segmentation. During a 12-month period of monitoring, the phantom material was stable with T1 and T2 of 150.7 ± 6.7 ms and 56.1 ± 3.9 ms, respectively. Of all the radiomic features computed, 34 of 69 had COV < 10%. Features from first-order statistics were the most robust in stability across the eight scanners with eight of 12 (67%) having high stability. About 29 of 50 (58%) texture features had high stability and no shape features had high stability features across the eight scanners.

CONCLUSION

A novel MRI radiomics phantom has been developed to assess the reproducibility and stability of MRI-based radiomic features across multiple institutions. The variation in radiomic feature stability demonstrates the need for caution when interpreting these features for clinical studies.

Prediction of the human papillomavirus status in patients with oropharyngeal squamous cell carcinoma by FDG-PET imaging dataset using deep learning analysis: A hypothesis-generating study

PURPOSE

To assess the diagnostic accuracy of imaging-based deep learning analysis to differentiate between human papillomavirus (HPV) positive and negative oropharyngeal squamous cell carcinomas (OPSCCs) using FDG-PET images.

METHODS

One hundred and twenty patients with OPSCC who underwent pretreatment FDG-PET/CT were included and divided into the training 90 patients and validation 30 patients cohorts. In the training session, 2160 FDG-PET images were analyzed after data augmentation process by a deep learning technique to create a diagnostic model to discriminate between HPV-positive and HPV-negative OPSCCs. Validation cohort data were subsequently analyzed for confirmation of diagnostic accuracy in determining HPV status by the deep learning-based diagnosis model. In addition, two radiologists evaluated the validation cohort image-data to determine the HPV status based on each tumor's imaging findings.

RESULTS

In deep learning analysis with training session, the diagnostic model using training dataset was successfully created. In the validation session, the deep learning diagnostic model revealed sensitivity of 0.83, specificity of 0.83, positive predictive value of 0.88, negative predictive value of 0.77, and diagnostic accuracy of 0.83, while the visual assessment by two radiologists revealed 0.78, 0.5, 0.7, 0.6, and 0.67 (reader 1), and 0.56, 0.67, 0.71, 0.5, and 0.6 (reader 2), respectively. Chi square test showed a significant difference between deep learning- and radiologist-based diagnostic accuracy (reader 1: P = 0.016, reader 2: P = 0.008).

CONCLUSIONS

Deep learning diagnostic model with FDG-PET imaging data can be useful as one of supportive tools to determine the HPV status in patients with OPSCC.

Ability of Radiomics in Differentiation of Anaplastic Oligodendroglioma From Atypical Low-Grade Oligodendroglioma Using Machine-Learning Approach

Objectives: To investigate the ability of radiomics features from MRI in differentiating anaplastic oligodendroglioma (AO) from atypical low-grade oligodendroglioma using machine-learning algorithms.

Methods: A total number of 101 qualified patients (50 participants with AO and 51 with atypical low-grade oligodendroglioma) were enrolled in this retrospective, single-center study. Forty radiomics features of tumor images derived from six matrices were extracted from contrast-enhanced T1-weighted (T1C) images and fluid-attenuation inversion recovery (FLAIR) images. Three selection methods were performed to select the optimal features for classifiers, including distance correlation, least absolute shrinkage and selection operator (LASSO), and gradient boosting decision tree (GBDT). Then three machine-learning classifiers were adopted to generate discriminative models, including linear discriminant analysis, support vector machine, and random forest (RF). Receiver operating characteristic analysis was conducted to evaluate the discriminative performance of each model.

Results: Nine predictive models were established based on radiomics features from T1C images and FLAIR images. All of the classifiers represented feasible ability in differentiation, with AUC more than 0.840 when combined with suitable selection method. For models based on T1C images, the combination of LASSO and RF classifier represented the highest AUC of 0.904 in the validation group. For models based on FLAIR images, the combination of GBDT and RF classifier showed the highest AUC of 0.861 in the validation group.

Conclusion: Radiomics-based machine-learning approach could potentially serve as a feasible method in distinguishing AO from atypical low-grade oligodendroglioma.

Differentiation of Pituitary Adenoma from Rathke Cleft Cyst: Combining MR Image Features with Texture Features

Objectives

To differentiate pituitary adenoma from Rathke cleft cyst in magnetic resonance (MR) scan by combing MR image features with texture features.

Methods

A total number of 133 patients were included in this study, 83 with pituitary adenoma and 50 with Rathke cleft cyst. Qualitative MR image features and quantitative texture features were evaluated by using the chi-square tests or Mann–Whitney U test. Binary logistic regression analysis was conducted to investigate their ability as independent predictors. ROC analysis was conducted subsequently on the independent predictors to assess their practical value in discrimination and was used to investigate the association between two types of features.

Results

Signal intensity on the contrast-enhanced image was found to be the only significantly different MR image feature between the two lesions. Two texture features from the contrast-enhanced images (Histo-Skewness and GLCM-Correlation) were found to be the independent predictors in discrimination, of which AUC values were 0.80 and 0.75, respectively. Besides, the above two texture features (Histo-Skewness and GLCM-Contrast) were suggested to be associated with signal intensity on the contrast-enhanced image.

Conclusion

Signal intensity on the contrast-enhanced image was the most significant MR image feature in differentiation between pituitary adenoma and Rathke cleft cyst, and texture features also showed promising and practical ability in discrimination. Moreover, two types of features could be coordinated with each other.

The Diagnostic Value of MRI-Based Texture Analysis in Discrimination of Tumors Located in Posterior Fossa: A Preliminary Study

Objectives

To investigate the diagnostic value of MRI-based texture analysis in discriminating common posterior fossa tumors, including medulloblastoma, brain metastatic tumor, and hemangioblastoma.

Methods

A total number of 185 patients were enrolled in the current study: 63 of them were diagnosed with medulloblastoma, 56 were diagnosed with brain metastatic tumor, and 66 were diagnosed with hemangioblastoma. Texture features were extracted from contrast-enhanced T1-weighted (T1C) images and fluid-attenuation inversion recovery (FLAIR) images within two matrixes. Mann–Whitney U test was conducted to identify whether texture features were significantly different among subtypes of tumors. Logistic regression analysis was performed to assess if they could be taken as independent predictors and to establish the integrated models. Receiver operating characteristic analysis was conducted to evaluate their performances in discrimination.

Results

There were texture features from both T1C images and FLAIR images found to be significantly different among the three types of tumors. The integrated model represented that the promising diagnostic performance of texture analysis depended on a series of features rather than a single feature. Moreover, the predictive model that combined texture features and clinical feature implied feasible performance in prediction with an accuracy of 0.80.

Conclusion

MRI-based texture analysis could potentially be served as a radiological method in discrimination of common tumors located in posterior fossa.

CT-Based Radiomics Signature for the Preoperative Discrimination Between Head and Neck Squamous Cell Carcinoma Grades

Background: Radiomics has been widely used to non-invasively mine quantitative information from medical images and could potentially predict tumor phenotypes. Pathologic grade is considered a predictive prognostic factor for head and neck squamous cell carcinoma (HNSCC) patients. A preoperative histological assessment can be important in the clinical management of patients. We applied radiomics analysis to devise non-invasive biomarkers and accurately differentiate between well-differentiated (WD) and moderately differentiated (MD) and poorly differentiated (PD) HNSCC.

Methods: This study involved 206 consecutive HNSCC patients (training cohort: n = 137; testing cohort: n = 69). In total, we extracted 670 radiomics features from contrast-enhanced computed tomography (CT) images. Radiomics signatures were constructed with a kernel principal component analysis (KPCA), random forest classifier and a variance-threshold (VT) selection. The associations between the radiomics signatures and HNSCC histological grades were investigated. A clinical model and combined model were also constructed. Areas under the receiver operating characteristic curves (AUCs) were applied to evaluate the performances of the three models.

Results: In total, 670 features were selected by the KPCA and random forest methods from the CT images. The radiomics signatures had a good performance in discriminating between the two cohorts of HNSCC grades, with an AUC of 0.96 and an accuracy of 0.92. The specificity, accuracy, sensitivity, positive predictive value (PPV), and negative predictive value (NPV) of the abovementioned method with a VT selection for determining HNSCC grades were 0.83, 0.92, 0.96, 0.94, and 0.91, respectively; without VT, the corresponding results were 0.70, 0.83, 0.88, 0.80, and 0.84. The differences in accuracy, sensitivity and NPV were significant between these approaches (p < 0.05). The AUCs with VT and without VT were 0.96 and 0.89, respectively (p < 0.05). Compared to the combined model and the radiomics signatures, The clinical model had a worse performance, and the differences were significant (p < 0.05). The combined model had the best performance, but the difference between the combined model and the radiomics signature weren't significant (p > 0.05).

Conclusions: The CT-based radiomics signature could discriminate between WD and MD and PD HNSCC and might serve as a biomarker for preoperative grading.