Voxel-based clustered imaging by multiparameter diffusion tensor images for glioma grading

Decoding Glioblastoma Heterogeneity: Neuroimaging Meets Machine Learning

Recent advancements in neuroimaging and machine learning have significantly improved our ability to diagnose and categorize isocitrate dehydrogenase (IDH)-wildtype glioblastoma, a disease characterized by notable tumoral heterogeneity, which is crucial for effective treatment. Neuroimaging techniques, such as diffusion tensor imaging and magnetic resonance radiomics, provide noninvasive insights into tumor infiltration patterns and metabolic profiles, aiding in accurate diagnosis and prognostication. Machine learning algorithms further enhance glioblastoma characterization by identifying distinct imaging patterns and features, facilitating precise diagnoses and treatment planning. Integration of these technologies allows for the development of image-based biomarkers, potentially reducing the need for invasive biopsy procedures and enabling personalized therapy targeting specific pro-tumoral signaling pathways and resistance mechanisms. Although significant progress has been made, ongoing innovation is essential to address remaining challenges and further improve these methodologies. Future directions should focus on refining machine learning models, integrating emerging imaging techniques, and elucidating the complex interplay between imaging features and underlying molecular processes. This review highlights the pivotal role of neuroimaging and machine learning in glioblastoma research, offering invaluable noninvasive tools for diagnosis, prognosis prediction, and treatment planning, ultimately improving patient outcomes. These advances in the field promise to usher in a new era in the understanding and classification of IDH-wildtype glioblastoma.

Application of Machine Learning for Classification of Brain Tumors: A Systematic Review and Meta-Analysis

BACKGROUND

Classifying brain tumors accurately is crucial for treatment and prognosis. Machine learning (ML) shows great promise in improving tumor classification accuracy. This study evaluates ML algorithms for differentiating various brain tumor types.

METHODS

A systematic review and meta-analysis were conducted, searching PubMed, Embase, and Web of Science up to March 14, 2023. Studies that only investigated image segmentation accuracy or brain tumor detection instead of classification were excluded. We extracted binary diagnostic accuracy data, constructing contingency tables to derive sensitivity and specificity.

RESULTS

Fifty-one studies were included. The pooled area under the curve for glioblastoma versus lymphoma and low-grade versus high-grade gliomas were 0.99 (95% confidence interval [CI]: 0.98-1.00) and 0.89, respectively. The pooled sensitivity and specificity for benign versus malignant tumors were 0.90 (95% CI: 0.85-0.93) and 0.93 (95% CI: 0.90-0.95), respectively. The pooled sensitivity and specificity for low-grade versus high-grade gliomas were 0.99 (95% CI: 0.97-1.00) and 0.94, (95% CI: 0.79-0.99), respectively. Primary versus metastatic tumor identification yields sensitivity and specificity of 0.89, (95% CI: 0.83-0.93) and 0.87 (95% CI: 0.82-0.91), correspondingly. The differentiation of gliomas from pituitary tumors yielded the highest results among primary brain tumor classifications: sensitivity of 0.99 (95% CI: 0.99-1.00) and specificity of 0.99 (95% CI: 0.98-1.00).

CONCLUSIONS

ML demonstrated excellent performance in classifying brain tumor images, with near-maximum area under the curves, sensitivity, and specificity.

An effective ensemble learning approach for classification of glioma grades based on novel MRI features

The preoperative diagnosis of brain tumors is important for therapeutic planning as it contributes to the tumors' prognosis. In the last few years, the development in the field of artificial intelligence and machine learning has contributed greatly to the medical area, especially the diagnosis of the grades of brain tumors through radiological images and magnetic resonance images. Due to the complexity of tumor descriptors in medical images, assessing the accurate grade of glioma is a major challenge for physicians. We have proposed a new classification system for glioma grading by integrating novel MRI features with an ensemble learning method, called Ensemble Learning based on Adaptive Power Mean Combiner (EL-APMC). We evaluate and compare the performance of the EL-APMC algorithm with twenty-one classifier models that represent state-of-the-art machine learning algorithms. Results show that the EL-APMC algorithm achieved the best performance in terms of classification accuracy (88.73%) and F1-score (93.12%) over the MRI Brain Tumor dataset called BRATS2015. In addition, we showed that the differences in classification results among twenty-two classifier models have statistical significance. We believe that the EL-APMC algorithm is an effective method for the classification in case of small-size datasets, which are common cases in medical fields. The proposed method provides an effective system for the classification of glioma with high reliability and accurate clinical findings.

Voxel-based clustered imaging by multiparameter diffusion tensor images for predicting the grade and proliferative activity of meningioma

INTRODUCTION

Meningiomas are the most common primary central nervous system tumors. Predicting the grade and proliferative activity of meningiomas would influence therapeutic strategies. We aimed to apply the multiple parameters from preoperative diffusion tensor images for predicting meningioma grade and proliferative activity.

METHODS

Nineteen patients with low-grade meningiomas and eight with high-grade meningiomas were included. For the prediction of proliferative activity, the patients were divided into two groups: Ki-67 monoclonal antibody labeling index (MIB-1 LI) < 5% (lower MIB-1 LI group; n = 18) and MIB-1 LI ≥ 5% (higher MIB-1 LI group; n = 9). Six features, diffusion-weighted imaging, fractional anisotropy, mean, axial, and radial diffusivities, and raw T2 signal with no diffusion weighting, were extracted as multiple parameters from diffusion tensor imaging. The two-level clustering approach for a self-organizing map followed by the K-means algorithm was applied to cluster a large number of input vectors with the six features. We also validated whether the diffusion tensor-based clustered image (DTcI) was helpful for predicting preoperative meningioma grade or proliferative activity.

RESULTS

The sensitivity, specificity, accuracy, and area under the curve of receiver operating characteristic curves from the 16-class DTcIs for differentiating high- and low-grade meningiomas were 0.870, 0.901, 0.891, and 0.959, and those from the 10-class DTcIs for differentiating higher and lower MIB-1 LIs were 0.508, 0.770, 0.683, and 0.694, respectively. The log-ratio values of class numbers 13, 14, 15, and 16 were significantly higher in high-grade meningiomas than in low-grade meningiomas (p < .001). With regard to MIB-1 LIs, the log-ratio values of class numbers 8, 9, and 10 were higher in meningiomas with higher MIB-1 groups (p < .05).

CONCLUSION

The multiple diffusion tensor imaging-based parameters from the voxel-based DTcIs can help differentiate between low- and high-grade meningiomas and between lower and higher proliferative activities.

SASG-GCN: Self-Attention Similarity Guided Graph Convolutional Network for Multi-Type Lower-Grade Glioma Classification

Identifying the subtypes of low-grade glioma (LGG) can help prevent brain tumor progression and patient death. However, the complicated non-linear relationship and high dimensionality of 3D brain MRI limit the performance of machine learning methods. Therefore, it is important to develop a classification method that can overcome these limitations. This study proposes a self-attention similarity-guided graph convolutional network (SASG-GCN) that uses the constructed graphs to complete multi-classification (tumor-free (TF), WG, and TMG). In the pipeline of SASG-GCN, we use a convolutional deep belief network and a self-attention similarity-based method to construct the vertices and edges of the constructed graphs at 3D MRI level, respectively. The multi-classification experiment is performed in a two-layer GCN model. SASG-GCN is trained and evaluated on 402 3D MRI images which are produced from the TCGA-LGG dataset. Empirical tests demonstrate that SASG-GCN accurately classifies the subtypes of LGG. The accuracy of SASG-GCN achieves 93.62%, outperforming several other state-of-the-art classification methods. In-depth discussion and analysis reveal that the self-attention similarity-guided strategy improves the performance of SASG-GCN. The visualization revealed differences between different gliomas.

A Predictive Visual Analytics System for Studying Neurodegenerative Disease Based on DTI Fiber Tracts

Diffusion tensor imaging (DTI) has been used to study the effects of neurodegenerative diseases on neural pathways, which may lead to more reliable and early diagnosis of these diseases as well as a better understanding of how they affect the brain. We introduce a predictive visual analytics system for studying patient groups based on their labeled DTI fiber tract data and corresponding statistics. The system's machine-learning-augmented interface guides the user through an organized and holistic analysis space, including the statistical feature space, the physical space, and the space of patients over different groups. We use a custom machine learning pipeline to help narrow down this large analysis space and then explore it pragmatically through a range of linked visualizations. We conduct several case studies using DTI and T1-weighted images from the research database of Parkinson's Progression Markers Initiative.

AGGN: Attention-based glioma grading network with multi-scale feature extraction and multi-modal information fusion

In this paper, a magnetic resonance imaging (MRI) oriented novel attention-based glioma grading network (AGGN) is proposed. By applying the dual-domain attention mechanism, both channel and spatial information can be considered to assign weights, which benefits highlighting the key modalities and locations in the feature maps. Multi-branch convolution and pooling operations are applied in a multi-scale feature extraction module to separately obtain shallow and deep features on each modality, and a multi-modal information fusion module is adopted to sufficiently merge low-level detailed and high-level semantic features, which promotes the synergistic interaction among different modality information. The proposed AGGN is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the proposed AGGN in comparison to other advanced models, which also presents high generalization ability and strong robustness. In addition, even without the manually labeled tumor masks, AGGN can present considerable performance as other state-of-the-art algorithms, which alleviates the excessive reliance on supervised information in the end-to-end learning paradigm.

Incorporating multiple magnetic resonance diffusion models to differentiate low- and high-grade adult gliomas: a machine learning approach

BACKGROUND

Accurate grading of gliomas is a challenge in imaging diagnosis. This study aimed to evaluate the performance of a machine learning (ML) approach based on multiparametric diffusion-weighted imaging (DWI) in differentiating low- and high-grade adult gliomas.

METHODS

A model was developed from an initial cohort containing 74 patients with pathology-confirmed gliomas, who underwent 3 tesla (3T) diffusion magnetic resonance imaging (MRI) with 21 b values. In all, 112 histogram features were extracted from 16 parameters derived from seven diffusion models [monoexponential, intravoxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI), fractional order calculus (FROC), continuous-time random walk (CTRW), stretched-exponential, and statistical]. Feature selection and model training were performed using five randomly permuted five-fold cross-validations. An internal test set (15 cases of the primary dataset) and an external cohort (n=55) imaged on a different scanner were used to validate the model. The diagnostic performance of the model was compared with that of a single DWI model and DWI radiomics using accuracy, sensitivity, specificity, and the area under the curve (AUC).

RESULTS

Seven significant multiparametric DWI features (two from the stretched-exponential and FROC models, and three from the CTRW model) were selected to construct the model. The multiparametric DWI model achieved the highest AUC (0.84, versus 0.71 for the single DWI model, P<0.05), an accuracy of 0.80 in the internal test, and both AUC and accuracy of 0.76 in the external test.

CONCLUSIONS

Our multiparametric DWI model differentiated low- (LGG) from high-grade glioma (HGG) with better generalization performance than the established single DWI model. This result suggests that the application of an ML approach with multiple DWI models is feasible for the preoperative grading of gliomas.

Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading

Glioma grading plays an important role in surgical resection. We investigated the ability of different feature reduction methods in support vector machine (SVM)-based diffusion kurtosis imaging (DKI) histogram parameters to distinguish glioma grades. A total of 161 glioma patients who underwent magnetic resonance imaging (MRI) from January 2017 to January 2020 were included retrospectively. The patients were divided into low-grade (n = 61) and high-grade (n = 100) groups. Parametric DKI maps were derived, and 45 features from the DKI maps were extracted semi-automatically for analysis. Three feature selection methods [principal component analysis (PCA), recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO)] were used to establish the glioma grading model with an SVM classifier. To evaluate the performance of SVM models, the receiver operating characteristic (ROC) curves of SVM models for distinguishing glioma grades were compared with those of conventional statistical methods. The conventional ROC analysis showed that mean diffusivity (MD) variance, MD skewness and mean kurtosis (MK) C50 could effectively distinguish glioma grades, particularly MD variance. The highest classification distinguishing AUC was found using LASSO at 0.904 ± 0.069. In comparison, classification AUC by PCA was 0.866 ± 0.061, and 0.899 ± 0.079 by RFE. The SVM-PCA model with the lowest AUC among the SVM models was significantly better than the conventional ROC analysis (z = 1.947, p = 0.013). These findings demonstrate the superiority of DKI histogram parameters by LASSO analysis and SVM for distinguishing glioma grades.

A Potential Prognostic Biomarker for Glioma: Aldo-Keto Reductase Family 1 Member B1

Aldo-keto reductase family 1 member B1 (AKR1B1) plays a vital role in tumor development and is involved in the tumor immune process. However, its role in glioma cell is poorly studied. This study's aim was to assess the role of AKR1B1 in glioma through bioinformatics analysis. The AKR1B1 expression data and corresponding clinical data of glioma were collected from the Cancer Genome Atlas (TCGA) database. The R packages were used for data integration, extraction, analysis, and visualization. According to the median value of the risk score, all patients were divided into high-risk and low-risk groups to draw the Kaplan-Meier (KM) survival curves and to explore the level of immune infiltration. The expression of AKR1B1 was significantly elevated in glioma tissues compared to normal tissues (P < 0.001). The high expression of AKR1B1 was significantly associated with WHO grade (P < 0.001), IDH status (P < 0.001), 1p/19q codeletion (P < 0.001), primary therapy outcome (P = 0.004), and age (P < 0.05). Kaplan-Meier survival analysis found that OS (HR = 3.75, P < 0.001), DSS (HR = 3.85, P < 0.001), and PFI (HR = 2.76, P < 0.001) were lower in patients with glioma with high AKR1B1 expression than in the group with low AKR1B1 expression. Based on GESA, six pathways (including interferon gamma signaling, signaling by interleukins, cell cycle checkpoints, cytokine receptor interaction, cell adhesion molecules (CAMs), and cell surface interactions) at the vascular wall were identified as significantly different between the two groups. Moreover, highly expressed AKR1B1 was associated with immune cell infiltration. AKR1B1 plays a key role in glioma progression and prognosis and, therefore, serves as a potential biomarker for prediction of patients' survival.

Visualization of tumor heterogeneity and prediction of isocitrate dehydrogenase mutation status for human gliomas using multiparametric physiologic and metabolic MRI

This study aimed to differentiate isocitrate dehydrogenase (IDH) mutation status with the voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and to discover biological underpinnings of the clusters. A total of 69 patients with treatment-naïve diffuse glioma were scanned with pH-sensitive amine chemical exchange saturation transfer MRI, diffusion-weighted imaging, fluid-attenuated inversion recovery, and contrast-enhanced T1-weighted imaging at 3 T. An unsupervised two-level clustering approach was used for feature extraction from acquired images. The logarithmic ratio of the labels in each class within tumor regions was applied to a support vector machine to differentiate IDH status. The highest performance to predict IDH mutation status was found for 10-class clustering, with a mean area under the curve, accuracy, sensitivity, and specificity of 0.94, 0.91, 0.90, and 0.91, respectively. Targeted biopsies revealed that the tissues with labels 7-10 showed high expression levels of hypoxia-inducible factor 1-alpha, glucose transporter 3, and hexokinase 2, which are typical of IDH wild-type glioma, whereas those with labels 1 showed low expression of these proteins. In conclusion, A machine learning model successfully predicted the IDH mutation status of gliomas, and the resulting clusters properly reflected the metabolic status of the tumors.

Multispectral co-occurrence of wavelet coefficients for malignancy assessment of brain tumors

Brain tumor is not most common, but truculent type of cancer. Therefore, correct prediction of its aggressiveness nature at an early stage would influence the treatment strategy. Although several diagnostic methods based on different modalities exist, a pre-operative method for determining tumor malignancy state still remains as an active research area. In this regard, the paper presents a new method for the assessment of tumor grades using conventional MR sequences namely, T1, T1 with contrast enhancement, T2 and FLAIR. The proposed method for tumor gradation is mainly based on feature extraction using multiresolution image analysis and classification using support vector machine. Since the wavelet features of different tumor subregions, obtained from single MR sequence, do not carry equally important information, a wavelet fusion technique is proposed based on the texture information content of each voxel. The concept of texture gradient, used in the proposed algorithm, fuses the wavelet coefficients of the given MR sequences. The feature vector is then derived from the co-occurrence of fused wavelet coefficients. As each wavelet subband contains distinct detail information, a novel concept of multispectral co-occurrence of wavelet coefficients is introduced to capture the spatial correlation among different subbands. It enables to convey more informative features to characterize the tumor type. The effectiveness of the proposed method is analyzed, with respect to six classification performance indices, on BRATS 2012 and BRATS 2014 data sets. The classification accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under curve assessed by the ten-fold cross-validation are 91.3%, 96.8%, 66.7%, 92.4%, 88.4%, and 92.0%, respectively, on real brain MR data.

Accuracy of Machine Learning Algorithms for the Classification of Molecular Features of Gliomas on MRI: A Systematic Literature Review and Meta-Analysis

Simple Summary

Glioma prognosis and treatment are based on histopathological characteristics and molecular profile. Following the World Health Organization (WHO) guidelines (2016), the most important molecular diagnostic markers include IDH1/2-genotype and 1p/19q codeletion status, although more recent publications also include ARTX genotype and TERT- and MGMT promoter methylation. Machine learning algorithms (MLAs), however, were described to successfully determine these molecular characteristics non-invasively by using magnetic resonance imaging (MRI) data. The aim of this review and meta-analysis was to define the diagnostic accuracy of MLAs with regard to these different molecular markers. We found high accuracies of MLAs to predict each individual molecular marker, with IDH1/2-genotype being the most investigated and the most accurate. Radiogenomics could therefore be a promising tool for discriminating genetically determined gliomas in a non-invasive fashion. Although encouraging results are presented here, large-scale, prospective trials with external validation groups are warranted.

Abstract

Treatment planning and prognosis in glioma treatment are based on the classification into low- and high-grade oligodendroglioma or astrocytoma, which is mainly based on molecular characteristics (IDH1/2- and 1p/19q codeletion status). It would be of great value if this classification could be made reliably before surgery, without biopsy. Machine learning algorithms (MLAs) could play a role in achieving this by enabling glioma characterization on magnetic resonance imaging (MRI) data without invasive tissue sampling. The aim of this study is to provide a performance evaluation and meta-analysis of various MLAs for glioma characterization. Systematic literature search and meta-analysis were performed on the aggregated data, after which subgroup analyses for several target conditions were conducted. This study is registered with PROSPERO, CRD42020191033. We identified 724 studies; 60 and 17 studies were eligible to be included in the systematic review and meta-analysis, respectively. Meta-analysis showed excellent accuracy for all subgroups, with the classification of 1p/19q codeletion status scoring significantly poorer than other subgroups (AUC: 0.748, p = 0.132). There was considerable heterogeneity among some of the included studies. Although promising results were found with regard to the ability of MLA-tools to be used for the non-invasive classification of gliomas, large-scale, prospective trials with external validation are warranted in the future.

Machine learning applications to neuroimaging for glioma detection and classification: An artificial intelligence augmented systematic review

Glioma is the most common primary intraparenchymal tumor of the brain and the 5-year survival rate of high-grade glioma is poor. Magnetic resonance imaging (MRI) is essential for detecting, characterizing and monitoring brain tumors but definitive diagnosis still relies on surgical pathology. Machine learning has been applied to the analysis of MRI data in glioma research and has the potential to change clinical practice and improve patient outcomes. This systematic review synthesizes and analyzes the current state of machine learning applications to glioma MRI data and explores the use of machine learning for systematic review automation. Various datapoints were extracted from the 153 studies that met inclusion criteria and analyzed. Natural language processing (NLP) analysis involved keyword extraction, topic modeling and document classification. Machine learning has been applied to tumor grading and diagnosis, tumor segmentation, non-invasive genomic biomarker identification, detection of progression and patient survival prediction. Model performance was generally strong (AUC = 0.87 ± 0.09; sensitivity = 0.87 ± 0.10; specificity = 0.0.86 ± 0.10; precision = 0.88 ± 0.11). Convolutional neural network, support vector machine and random forest algorithms were top performers. Deep learning document classifiers yielded acceptable performance (mean 5-fold cross-validation AUC = 0.71). Machine learning tools and data resources were synthesized and summarized to facilitate future research. Machine learning has been widely applied to the processing of MRI data in glioma research and has demonstrated substantial utility. NLP and transfer learning resources enabled the successful development of a replicable method for automating the systematic review article screening process, which has potential for shortening the time from discovery to clinical application in medicine.

Differentiating IDH status in human gliomas using machine learning and multiparametric MR/PET

Background

The purpose of this study was to develop a voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and 3,4-dihydroxy-6-[¹⁸F]-fluoro-L-phenylalanine (FDOPA) positron emission tomography (PET) images using an unsupervised, two-level clustering approach followed by support vector machine in order to classify the isocitrate dehydrogenase (IDH) status of gliomas.

Methods

Sixty-two treatment-naïve glioma patients who underwent FDOPA PET and MRI were retrospectively included. Contrast enhanced T1-weighted images, T2-weighted images, fluid-attenuated inversion recovery images, apparent diffusion coefficient maps, and relative cerebral blood volume maps, and FDOPA PET images were used for voxel-wise feature extraction. An unsupervised two-level clustering approach, including a self-organizing map followed by the K-means algorithm was used, and each class label was applied to the original images. The logarithmic ratio of labels in each class within tumor regions was applied to a support vector machine to differentiate IDH mutation status. The area under the curve (AUC) of receiver operating characteristic curves, accuracy, and F1-socore were calculated and used as metrics for performance.

Results

The associations of multiparametric imaging values in each cluster were successfully visualized. Multiparametric images with 16-class clustering revealed the highest classification performance to differentiate IDH status with the AUC, accuracy, and F1-score of 0.81, 0.76, and 0.76, respectively.

Conclusions

Machine learning using an unsupervised two-level clustering approach followed by a support vector machine classified the IDH mutation status of gliomas, and visualized voxel-wise features from multiparametric MRI and FDOPA PET images. Unsupervised clustered features may improve the understanding of prioritizing multiparametric imaging for classifying IDH status.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-021-00396-5.

Identification of sarcomatoid differentiation in renal cell carcinoma by machine learning on multiparametric MRI

Sarcomatoid differentiation in RCC (sRCC) is associated with a poor prognosis, necessitating more aggressive management than RCC without sarcomatoid components (nsRCC). Since suspected renal cell carcinoma (RCC) tumors are not routinely biopsied for histologic evaluation, there is a clinical need for a non-invasive method to detect sarcomatoid differentiation pre-operatively. We utilized unsupervised self-organizing map (SOM) and supervised Learning Vector Quantizer (LVQ) machine learning to classify RCC tumors on T2-weighted, non-contrast T1-weighted fat-saturated, contrast-enhanced arterial-phase T1-weighted fat-saturated, and contrast-enhanced venous-phase T1-weighted fat-saturated MRI images. The SOM was trained on 8 nsRCC and 8 sRCC tumors, and used to compute Activation Maps for each training, validation (3 nsRCC and 3 sRCC), and test (5 nsRCC and 5 sRCC) tumor. The LVQ classifier was trained and optimized on Activation Maps from the 22 training and validation cohort tumors, and tested on Activation Maps of the 10 unseen test tumors. In this preliminary study, the SOM-LVQ model achieved a hold-out testing accuracy of 70% in the task of identifying sarcomatoid differentiation in RCC on standard multiparameter MRI (mpMRI) images. We have demonstrated a combined SOM-LVQ machine learning approach that is suitable for analysis of limited mpMRI datasets for the task of differential diagnosis.

Automated glioma grading on conventional MRI images using deep convolutional neural networks

PURPOSE

Gliomas are the most common primary tumor of the brain and are classified into grades I-IV of the World Health Organization (WHO), based on their invasively histological appearance. Gliomas grading plays an important role to determine the treatment plan and prognosis prediction. In this study we propose two novel methods for automatic, non-invasively distinguishing low-grade (Grades II and III) glioma (LGG) and high-grade (grade IV) glioma (HGG) on conventional MRI images by using deep convolutional neural networks (CNNs).

METHODS

All MRI images have been preprocessed first by rigid image registration and intensity inhomogeneity correction. Both proposed methods consist of two steps: (a) three-dimensional (3D) brain tumor segmentation based on a modification of the popular U-Net model; (b) tumor classification on segmented brain tumor. In the first method, the slice with largest area of tumor is determined and the state-of-the-art mask R-CNN model is employed for tumor grading. To improve the performance of the grading model, a two-dimensional (2D) data augmentation has been implemented to increase both the amount and the diversity of the training images. In the second method, denoted as 3DConvNet, a 3D volumetric CNNs is applied directly on bounding image regions of segmented tumor for classification, which can fully leverage the 3D spatial contextual information of volumetric image data.

RESULTS

The proposed schemes were evaluated on The Cancer Imaging Archive (TCIA) low grade glioma (LGG) data, and the Multimodal Brain Tumor Image Segmentation (BraTS) Benchmark 2018 training datasets with fivefold cross validation. All data are divided into training, validation, and test sets. Based on biopsy-proven ground truth, the performance metrics of sensitivity, specificity, and accuracy are measured on the test sets. The results are 0.935 (sensitivity), 0.972 (specificity), and 0.963 (accuracy) for the 2D Mask R-CNN based method, and 0.947 (sensitivity), 0.968 (specificity), and 0.971 (accuracy) for the 3DConvNet method, respectively. In regard to efficiency, for 3D brain tumor segmentation, the program takes around ten and a half hours for training with 300 epochs on BraTS 2018 dataset and takes only around 50 s for testing of a typical image with a size of 160 × 216 × 176. For 2D Mask R-CNN based tumor grading, the program takes around 4 h for training with around 60 000 iterations, and around 1 s for testing of a 2D slice image with size of 128 × 128. For 3DConvNet based tumor grading, the program takes around 2 h for training with 10 000 iterations, and 0.25 s for testing of a 3D cropped image with size of 64 × 64 × 64, using a DELL PRECISION Tower T7910, with two NVIDIA Titan Xp GPUs.

CONCLUSIONS

Two effective glioma grading methods on conventional MRI images using deep convolutional neural networks have been developed. Our methods are fully automated without manual specification of region-of-interests and selection of slices for model training, which are common in traditional machine learning based brain tumor grading methods. This methodology may play a crucial role in selecting effective treatment options and survival predictions without the need for surgical biopsy.

Radiogenomics correlation between MR imaging features and mRNA-based subtypes in lower-grade glioma

Background

To investigate associations between lower-grade glioma (LGG) mRNA-based subtypes (R1-R4) and MR features.

Methods

mRNA-based subtyping was obtained from the LGG dataset in The Cancer Genome Atlas (TCGA). We identified matching patients (n = 145) in The Cancer Imaging Archive (TCIA) who underwent MR imaging. The associations between mRNA-based subtypes and MR features were assessed.

Results

In the TCGA-LGG dataset, patients with the R2 subtype had the shortest median OS months (P < 0.05). The time-dependent ROC for the R2 subtype was 0.78 for survival at 12 months, 0.76 for survival at 24 months, and 0.76 for survival at 36 months. In the TCIA-LGG dataset, 41 (23.7%) R1 subtype, 40 (23.1%) R2 subtype, 19 (11.0%) R3 subtype and 45 (26.0%) R4 subtype cases were identified. Multivariate analysis revealed that enhancing margin (ill-defined, OR: 9.985; P = 0.003) and T1 + C/T2 mismatch (yes, OR: 0.091; P = 0.023) were associated with the R1 subtype (AUC: 0.708). The average accuracy of the ten-fold cross validation was 71%. Proportion of contrast-enhanced (CE) tumour (> 5%, OR: 14.733; P < 0.001) and necrosis/cystic changes (yes, OR: 0.252; P = 0.009) were associated with the R2 subtype (AUC: 0.832). The average accuracy of the ten-fold cross validation was 82%. Haemorrhage (yes, OR: 8.55; P < 0.001) was positively associated with the R3 subtype (AUC: 0.689). The average accuracy of the ten-fold cross validation was 87%. Proportion of CE tumour (> 5%, OR: 0.14; P < 0.001) was negatively associated with the R4 subtype (AUC: 0.672). The average accuracy of the ten-fold cross validation was 71%. For the prediction of the R2 subtype, the nomogram showed good discrimination and calibration. Decision curve analysis demonstrated that prediction with the R2 model was clinically useful.

Conclusions

Patients with the R2 subtype had the worst prognosis. We demonstrated that MRI features can identify distinct LGG mRNA-based molecular subtypes.

Pathologic Correlation of Cellular Imaging Using Apparent Diffusion Coefficient Quantification in Patients with Brain Metastases After Gamma Knife Radiosurgery

OBJECTIVE

To evaluate the role of apparent diffusion coefficient (ADC) in differentiating radiation necrosis (RN) from recurrent tumor after Gamma Knife radiosurgery (GKRS) for brain metastases (BMs).

METHODS

Forty-one patients with BM who underwent surgical intervention after GKRS at Cleveland Clinic (2006-2017) were included in this retrospective study. The ADC values of the growing lesions and the contralateral hemisphere were calculated using picture archiving and communication system. These values were correlated to the percentage of RN identified on pathologic evaluation of the surgical specimen.

RESULTS

The median age of the patients was 59 years (range, 25-86 years), and lung cancer (63.4%) was the most common malignancy. Median initial (pre-GKRS) target volume of the lesions was 5.4 cc (range, 0.135-45.6 cc), and median GKRS dose was 18.0 Gy. Surgical resection or biopsy was performed at a median of 176 days after GKRS. Two variables were statistically significant predictors of predominate RN (75%-100%) in the surgical specimen: 1) ADC of the lesion on the preresection magnetic resonance imaging (MRI) and 2) initial pre-GKRS target volume. ADC >1.5 × 10^-3 mm²/s within the lesion on MRI predicted significant RN on pathologic evaluation of the lesion (P < 0.05). Similarly, when the target volume before GKRS was large (>10 cc), the risk of identifying significant necrosis in the pathologic specimen was elevated (P < 0.05).

CONCLUSIONS

Our data suggest that the combination of lesion ADC on MRI prior to surgical intervention and the initial target volume can predict RN with reasonable accuracy.

Radiomics-Based Machine Learning Technology Enables Better Differentiation Between Glioblastoma and Anaplastic Oligodendroglioma

Purpose: The aim of this study was to test whether radiomics-based machine learning can enable the better differentiation between glioblastoma (GBM) and anaplastic oligodendroglioma (AO). Methods: This retrospective study involved 126 patients histologically diagnosed as GBM (n = 76) or AO (n = 50) in our institution from January 2015 to December 2018. A total number of 40 three-dimensional texture features were extracted from contrast-enhanced T1-weighted images using LIFEx package. Six diagnostic models were established with selection methods and classifiers. The optimal radiomics features were separately selected into three datasets with three feature selection methods [distance correlation, least absolute shrinkage and selection operator (LASSO), and gradient boosting decision tree (GBDT)]. Then datasets were separately adopted into linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Specificity, sensitivity, accuracy, and area under curve (AUC) of each model were calculated to evaluate their diagnostic performances. Results: The diagnostic performance of machine learning models was superior to human readers. Both classifiers showed promising ability in discrimination with AUC more than 0.900 when combined with suitable feature selection method. For LDA-based models, the AUC of models were 0.986, 0.994, and 0.970 in the testing group, respectively. For the SVM-based models, the AUC of models were 0.923, 0.817, and 0.500 in the testing group, respectively. The over-fitting model was GBDT + SVM, suggesting that this model was too volatile that unsuitable for classification. Conclusion: This study indicates radiomics-based machine learning has the potential to be utilized in clinically discriminating GBM from AO.

A Mistaken Diagnosis of Secondary Glioblastoma as Parasitosis

Background: Glioblastoma is a malignant brain tumor with poor prognosis requiring early diagnosis. Secondary glioblastoma refers to cases that progressed from low-grade glioma. Evidence shows that timely resection correlates with increased survival.

Case presentation: We describe a case of a patient with secondary glioblastoma who was mistakenly diagnosed with Angiostrongylus cantonensis infection until 7 years after disease onset. The patient presented with non-specific clinical manifestations at disease onset. A conventional magnetic resonance imaging (MRI) in the primary survey provided insufficient information, and thus failed to identify the malignancy. During follow-up, unfortunately, clinicians were misled by the patient's raw food diet, a positive serum parasite antibody and a result of low glucose metabolism on Fluorodeoxyglucose-positron emission tomography-computed tomography (FDG-PET-CT). The patient was diagnosed with parasitosis. However, his condition kept getting worse under antiparasitic treatment. Preoperative magnetic resonance spectroscopy (MRS) and diffusion tensor imaging (DTI) failed to reverse the mistaken impression. Final diagnosis was confirmed until intraoperative and postoperative pathological findings indicated glioblastoma.

Conclusion: We ascribe the incorrect diagnosis to insufficient understanding on imaging manifestations of brain neoplasm as well as clinical features of parasitosis. Thus, we review the MRI, FDG-PET-CT, MRS, and DTI data of this case according to the timeline, refer to relevant studies, and point out the pitfalls. With a long course of slowly progressing, this was a rare case of secondary glioblastoma with the absence of isocitrate dehydrogenase 1 (IDH1) gene mutation.

Assessment of Glioblastoma Response in the Era of Bevacizumab: Longstanding and Emergent Challenges in the Imaging Evaluation of Pseudoresponse

Glioblastoma is the deadliest primary malignant brain neoplasm, and despite the availability of many treatment options, its prognosis remains somber. Enhancement detected by magnetic resonance imaging (MRI) was considered the best imaging marker of tumor activity in glioblastoma for decades. However, its role as a surrogate marker of tumor viability has changed with the appearance of new treatment regimens and imaging modalities. The antiangiogenic therapy created an inflection point in the imaging assessment of glioblastoma response in clinical trials and clinical practice. Although BEV led to the improvement of enhancement, it did not necessarily mean tumor response. The decrease in the enhancement intensity represents a change in the permeability properties of the blood brain barrier, and presumably, the switch of the tumor growth pattern to an infiltrative non-enhancing phenotype. New imaging techniques for the assessment of cellularity, blood flow hemodynamics, and biochemistry have emerged to overcome this hurdle; nevertheless, designing tools to assess tumor response more accurately, and in so doing, improve the assessment of response to standard of care (SOC) therapies and to novel therapies, remains challenging.

Application of MR morphologic, diffusion tensor, and perfusion imaging in the classification of brain tumors using machine learning scheme

PURPOSE

While MRI is the modality of choice for the assessment of patients with brain tumors, differentiation between various tumors based on their imaging characteristics might be challenging due to overlapping imaging features. The purpose of this study was to apply a machine learning scheme using basic and advanced MR sequences for distinguishing different types of brain tumors.

METHODS

The study cohort included 141 patients (41 glioblastoma, 38 metastasis, 50 meningioma, and 12 primary central nervous system lymphoma). A computer-assisted classification scheme, combining morphologic MRI, perfusion MRI, and DTI metrics, was developed and used for tumor classification. The proposed multistep scheme consists of pre-processing, ROI definition, features extraction, feature selection, and classification. Feature subset selection was performed using support vector machines (SVMs). Classification performance was assessed by leave-one-out cross-validation. Given an ROI, the entire classification process was done automatically via computer and without any human intervention.

RESULTS

A binary hierarchical classification tree was chosen. In the first step, selected features were chosen for distinguishing glioblastoma from the remaining three classes, followed by separation of meningioma from metastasis and PCNSL, and then to discriminate PCNSL from metastasis. The binary SVM classification accuracy, sensitivity and specificity for glioblastoma, metastasis, meningiomas, and primary central nervous system lymphoma were 95.7, 81.6, and 91.2%; 92.7, 95.1, and 93.6%; 97, 90.8, and 58.3%; and 91.5, 90, and 96.9%, respectively.

CONCLUSION

A machine learning scheme using data from anatomical and advanced MRI sequences resulted in high-performance automatic tumor classification algorithm. Such a scheme can be integrated into clinical decision support systems to optimize tumor classification.

Radiomics based on multicontrast MRI can precisely differentiate among glioma subtypes and predict tumour-proliferative behaviour

PURPOSE

To explore the feasibility and diagnostic performance of radiomics based on anatomical, diffusion and perfusion MRI in differentiating among glioma subtypes and predicting tumour proliferation.

METHODS

220 pathology-confirmed gliomas and ten contrasts were included in the retrospective analysis. After being registered to T2FLAIR images and resampling to 1 mm³ isotropically, 431 radiomics features were extracted from each contrast map within a semi-automatic defined tumour volume. For single-contrast and the combination of all contrasts, correlations between the radiomics features and pathological biomarkers were revealed by partial correlation analysis, and multivariate models were built to identify the best predictive models with adjusted 0.632+ bootstrap AUC.

RESULTS

In univariate analysis, both non-wavelet and wavelet radiomics features were correlated significantly with tumour grade and the Ki-67 labelling index. The max R was 0.557 (p = 2.04E-14) in T₁C for tumour grade and 0.395 (p = 2.33E-07) in ADC for Ki-67. In the multivariate analysis, the combination of all-contrast radiomics features had the highest AUCs in both differentiating among glioma subtypes and predicting proliferation compared with those in single-contrast images. For low-/high-grade gliomas, the best AUC was 0.911. In differentiating among glioma subtypes, the best AUC was 0.896 for grades II-III, 0.997 for grades II-IV, and 0.881 for grades III-IV. In predicting proliferation levels, multicontrast features led to an AUC of 0.936.

CONCLUSION

Multicontrast radiomics supplies complementary information on both geometric characters and molecular biological traits, which correlated significantly with tumour grade and proliferation. Combining all-contrast radiomics models might precisely predict glioma biological behaviour, which may be attributed to presurgical personal diagnosis.

KEY POINTS

• Multicontrast MRI radiomics features are significantly correlated with tumour grade and Ki-67 LI. • Multimodality MRI provides independent but supplemental information in assessing glioma pathological behaviour. • Combined multicontrast MRI radiomics can precisely predict glioma subtypes and proliferation levels.

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.

Support Vector Machine Classification of Obsessive-Compulsive Disorder Based on Whole-Brain Volumetry and Diffusion Tensor Imaging

Magnetic resonance imaging (MRI) methods have been used to detect cerebral anatomical distinction between obsessive-compulsive disorder (OCD) patients and healthy controls (HC). Machine learning approach allows for the possibility of discriminating patients on the individual level. However, few studies have used this automatic technique based on multiple modalities to identify potential biomarkers of OCD. High-resolution structural MRI and diffusion tensor imaging (DTI) data were acquired from 48 OCD patients and 45 well-matched HC. Gray matter volume (GMV), white matter volume (WMV), fractional anisotropy (FA), and mean diffusivity (MD) were extracted as four features were examined using support vector machine (SVM). Ten brain regions of each feature contributed most to the classification were also estimated. Using different algorithms, the classifier achieved accuracies of 72.08, 61.29, 80.65, and 77.42% for GMV, WMV, FA, and MD, respectively. The most discriminative gray matter regions that contributed to the classification were mainly distributed in the orbitofronto-striatal "affective" circuit, the dorsolateral, prefronto-striatal "executive" circuit and the cerebellum. For WMV feature and the two feature sets of DTI, the shared regions contributed the most to the discrimination mainly included the uncinate fasciculus, the cingulum in the hippocampus, corticospinal tract, as well as cerebellar peduncle. Based on whole-brain volumetry and DTI images, SVM algorithm revealed high accuracies for distinguishing OCD patients from healthy subjects at the individual level. Computer-aided method is capable of providing accurate diagnostic information and might provide a new perspective for clinical diagnosis of OCD.

Analysis of DTI-Derived Tensor Metrics in Differential Diagnosis between Low-grade and High-grade Gliomas

Purpose: It is critical and difficult to accurately discriminate between high- and low-grade gliomas preoperatively. This study aimed to ascertain the role of several scalar measures in distinguishing high-grade from low-grade gliomas, especially the axial diffusivity (AD), radial diffusivity (RD), planar tensor (Cp), spherical tensor (Cs), and linear tensor (Cl) derived from diffusion tensor imaging (DTI). Materials and Methods: Fifty-three patients with pathologically confirmed brain gliomas (21 low-grade and 32 high-grade) were included. Contrast-enhanced T1-weighted images and DTI were performed in all patients. The AD, RD, Cp, Cs, and Cl values in the tumor zone, peritumoral edema zone, white matter (WM) adjacent to edema and contralateral normal-appearing white matter (NAWM) were calculated. The DTI parameters and tumor grades were statistically analyzed, and receiver operating characteristic (ROC) curve analysis was also performed. Results: The DTI metrics in the affected hemisphere showed significant differences from those in the NAWM, except for the AD values in the tumor zone and the RD values in WM adjacent to edema in the low-grade groups, as well as the Cp values in WM adjacent to edema in the high-grade groups. AD in the tumor zone as well as Cs and Cl in WM adjacent to edema revealed significant differences between the low- and high-grade gliomas. The areas under the curve (Az) of all three metrics were greater than 0.5 in distinguishing low-grade from high-grade gliomas by ROC curve analysis, and the best DTI metric was Cs in WM adjacent to edema (Az: 0.692). Conclusion: AD in the tumor zone as well as Cs and Cl in WM adjacent to edema will provide additional information to better classify gliomas and can be used as non-invasive reliable biomarkers in glioma grading.

Distinct Patterns of Cerebral Cortical Thinning in Schizophrenia: A Neuroimaging Data-Driven Approach

Schizophrenia is an etiologically and clinically heterogeneous disorder. Although neuroimaging studies have revealed brain alterations in schizophrenia, most studies have assumed that the disorder is a single entity, neglecting the diversity of alterations observed in the disorder. The current study sought to explore the distinct patterns of altered cortical thickness in patients with schizophrenia and healthy individuals using a data-driven approach. Unsupervised clustering using self-organizing maps followed by a K-means algorithm was applied to regional cortical thickness data in 108 schizophrenia patients and 121 healthy controls. After clustering, the clinical characteristics and cortical thickness patterns of each cluster were assessed. Unsupervised clustering revealed that a 6-cluster solution was the most appropriate in this sample. There was substantial overlap between the patterns of cortical thickness in schizophrenia patients and healthy controls, although the distributions of the patients and controls differed across the clusters. The patterns of altered cortical thickness in schizophrenia exhibited cluster-specific features; patients within a cluster exhibited the most extensive cortical thinning, particularly in the medial prefrontal and temporal regions, while those in other clusters exhibited reduced cortical thickness in the medial frontal region or temporal lobe. Furthermore, in the schizophrenia group, extensive cortical thinning was correlated with a higher dosage of antipsychotic medication, while preserved cortical thickness appeared to be linked to less negative symptoms. This data-driven neuroimaging approach revealed distinct patterns of cortical thinning in schizophrenia, possibly reflecting the etiological heterogeneity of the disorder.

Assessment of diffusion tensor imaging metrics in differentiating low-grade from high-grade gliomas

AIM

The aim of this article is to assess diffusion tensor imaging (DTI) metrics in differentiating low-grade from high-grade gliomas.

PATIENTS AND METHODS

A prospective study was conducted on 35 patients with gliomas who underwent DTI. Gliomas were classified into low-grade and high-grade gliomas. The fractional anisotropy (FA), mean diffusivity (MD), linear coefficient (CL), planar coefficient (CP) and spherical coefficient (CS) of the solid tumoral part and peri-tumoral regions were calculated.

RESULTS

There was significant difference (p = 0.001) in MD of the solid tumoral part of low-grade (1.78 ± 0.33 × 10(-3 )mm(2)/s) and high-grade (1.16 ± 0.22 × 10(-3 )mm(2)/s) gliomas. The selection of 1.42 × 10(-3 )mm(2)/s as a cutoff value of MD of the tumoral part was used to differentiate low-grade and high-grade gliomas; the best results were obtained with area under the curve (AUC) of 0.957 and accuracy of 91.4%. There was a significant difference in FA, MD, CP and CS of peri-tumoral regions of both groups with p values of 0.006, 0.042, 0.030 and 0.037, respectively. The cutoff values of MD, FA, CS and CP of the peri-tumoral region used to differentiate low-grade from high-grade gliomas were 1.24, 0.315, 0.726 and 0.321 with AUC of 0.694, 0.773, 0.734 and 0.724 and accuracy of 68.6%, 80.0%, 74.3% and 74.3%, respectively. The combined MD of the solid tumoral part and FA of the peri-tumoral region used to differentiate low-grade from high-grade gliomas revealed AUC of 0.974 and accuracy of 88.6%.

CONCLUSION

We conclude that the combination of MD of the solid tumoral part and FA of the peri-tumoral region is a noninvasive method to differentiate low-grade from high-grade gliomas.

Visualization of heterogeneity and regional grading of gliomas by multiple features using magnetic resonance-based clustered images

Preoperative glioma grading is important for therapeutic strategies and influences prognosis. Intratumoral heterogeneity can cause an underestimation of grading because of the sampling error in biopsies. We developed a voxel-based unsupervised clustering method with multiple magnetic resonance imaging (MRI)-derived features using a self-organizing map followed by K-means. This method produced novel magnetic resonance-based clustered images (MRcIs) that enabled the visualization of glioma grades in 36 patients. The 12-class MRcIs revealed the highest classification performance for the prediction of glioma grading (area under the receiver operating characteristic curve = 0.928; 95% confidential interval = 0.920–0.936). Furthermore, we also created 12-class MRcIs in four new patients using the previous data from the 36 patients as training data and obtained tissue sections of the classes 11 and 12, which were significantly higher in high-grade gliomas (HGGs), and those of classes 4, 5 and 9, which were not significantly different between HGGs and low-grade gliomas (LGGs), according to a MRcI-based navigational system. The tissues of classes 11 and 12 showed features of malignant glioma, whereas those of classes 4, 5 and 9 showed LGGs without anaplastic features. These results suggest that the proposed voxel-based clustering method provides new insights into preoperative regional glioma grading.

In vivo detection of atherosclerotic plaque using non-contact and label-free near-infrared hyperspectral imaging

BACKGROUND AND AIMS

Detecting detailed atherosclerotic plaques is important to reduce risk factors during surgery. However, there are few methods to evaluate them during surgery. The aim of this study was to establish an in vivo, non-contact, and label-free imaging method for identifying atherosclerotic plaque lesions from outside vessels with a diffuse-reflectance near-infrared (NIR) hyperspectral imaging (HSI) system.

METHODS

NIR spectra between 1000 and 2350 nm were measured using an NIR HSI imaging system outside the exposed abdominal aorta in five Watanabe Heritable Hyperlipidemic (WHHL) rabbits in vivo. Preprocessed data were input to a supervised machine learning algorithm called a support vector machine (SVM) to create pixel-based images that can predict atherosclerotic plaques within a vessel. The images were compared with histological findings.

RESULTS

Absorbance was significantly higher in plaques than in normal arteries at 1000-1380, 1580-1810, and 1880-2320 nm. Overall predictive performance showed a sensitivity of 0.814 ± 0.017, a specificity of 0.836 ± 0.020, and an accuracy of 0.827 ± 0.008. The area under the receiver operating characteristic curve was 0.905 (95% confidence interval = 0.904-0.906).

CONCLUSIONS

The NIR HSI system combined with a machine learning algorithm enabled accurate detection of atherosclerotic plaques within an internal vessel with high spatial resolution from outside the vessel. The findings indicate that the NIR HSI system can provide non-contact, label-free, and precise localization of atherosclerotic plaques during vascular surgery.

Assessing Detection, Discrimination, and Risk of Breast Cancer According to Anisotropy Parameters of Diffusion Tensor Imaging

BACKGROUND The aim of this study was to investigate whether the anisotropy parameters are helpful in the detection and discrimination of breast cancers, and to determine its value in predicting the risk of cancers. MATERIAL AND METHODS There were 56 patients with 56 lesions (34 malignant, 22 benign) included in the study. DTI was performed in every patient and apparent diffusion coefficient (ADC), fractional anisotropy (FA), and eigenvalues E1, E2, and E3 were measured in every lesion and the normal breast tissue. RESULTS ADC, FA, and eigenvalues of E1, E2, E3, and E1-E3 in breast cancers were all significantly lower than in normal tissue (P<0.001 for all) with mean reduction of (32 ± 17)%, (24 ± 13)%, (33 ± 19)%, (32 ± 17)%, (31 ± 18)%, and (37 ± 20)% for ADC, FA, E1, E2, E3, and E1-E3, respectively. These parameters were also statistically lower in cancers than in benign lesions (P<0.01 for all), except FA (P>0.05). ADC, E1, E2, and E3 were very similar in discriminating breast cancers and benign lesions, with area under the curve (AUC) 0.885-0.898, sensitivity 73.5-85.3%, and specificity 90.9-100%. CONCLUSIONS ADC, E1, E2, E3, and E1-E3 are much lower in breast cancers than in normal tissue and benign lesions. The reduction of ADC, E1, E2, E3, and E1-E3 of a mass in the breast is highly associated with the risk of breast cancer, but the FA has no utility in breast cancer risk prediction.