Imaging-Based Deep Learning for Predicting Desmoid Tumor Progression.

Desmoid tumors (DTs) are non-metastasizing and locally aggressive soft-tissue mesenchymal neoplasms. Those that become enlarged often become locally invasive and cause significant morbidity. DTs have a varied pattern of clinical presentation, with up to 50-60% not growing after diagnosis and 20-30% shrinking or even disappearing after initial progression. Enlarging tumors are considered unstable and progressive. The management of symptomatic and enlarging DTs is challenging, and primarily consists of chemotherapy. Despite wide surgical resection, DTs carry a rate of local recurrence as high as 50%. There is a consensus that contrast-enhanced magnetic resonance imaging (MRI) or, alternatively, computerized tomography (CT) is the preferred modality for monitoring DTs. Each uses Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST 1.1), which measures the largest diameter on axial, sagittal, or coronal series. This approach, however, reportedly lacks accuracy in detecting response to therapy and fails to detect tumor progression, thus calling for more sophisticated methods. The objective of this study was to detect unique features identified by deep learning that correlate with the future clinical course of the disease. Between 2006 and 2019, 51 patients (mean age 41.22 ± 15.5 years) who had a tissue diagnosis of DT were included in this retrospective single-center study. Each had undergone at least three MRI examinations (including a pretreatment baseline study), and each was followed by orthopedic oncology specialists for a median of 38.83 months (IQR 44.38). Tumor segmentations were performed on a T2 fat-suppressed treatment-naive MRI sequence, after which the segmented lesion was extracted to a three-dimensional file together with its DICOM file and run through deep learning software. The results of the algorithm were then compared to clinical data collected from the patients' medical files. There were 28 males (13 stable) and 23 females (15 stable) whose ages ranged from 19.07 to 83.33 years. The model was able to independently predict clinical progression as measured from the baseline MRI with an overall accuracy of 93% (93 ± 0.04) and ROC of 0.89 ± 0.08. Artificial intelligence may contribute to risk stratification and clinical decision-making in patients with DT by predicting which patients are likely to progress.

Automatic segmentation of femoral tumors by nnU-net.

BACKGROUND: Metastatic femoral tumors may lead to pathological fractures during daily activities. A CT-based finite element analysis of a patient's femurs was shown to assist orthopedic surgeons in making informed decisions about the risk of fracture and the need for a prophylactic fixation. Improving the accuracy of such analyses ruqires an automatic and accurate segmentation of the tumors and their automatic inclusion in the finite element model. We present herein a deep learning algorithm (nnU-Net) to automatically segment lytic tumors within the femur. METHOD: A dataset consisting of fifty CT scans of patients with manually annotated femoral tumors was created. Forty of them, chosen randomly, were used for training the nnU-Net, while the remaining ten CT scans were used for testing. The deep learning model's performance was compared to two experienced radiologists. FINDINGS: The proposed algorithm outperformed the current state-of-the-art solutions, achieving dice similarity scores of 0.67 and 0.68 on the test data when compared to two experienced radiologists, while the dice similarity score for inter-individual variability between the radiologists was 0.73. INTERPRETATION: The automatic algorithm may segment lytic femoral tumors in CT scans as accurately as experienced radiologists with similar dice similarity scores. The influence of the realistic tumors inclusion in an autonomous finite element algorithm is presented in (Rachmil et al., "The Influence of Femoral Lytic Tumors Segmentation on Autonomous Finite Element Analyses", Clinical Biomechanics, 112, paper 106192, (2024)).

Differentiating spinal pathologies by deep learning approach.

BACKGROUND CONTEXT: Spinal pathologies are diverse in nature and, excluding trauma and degenerative diseases, includes infectious, neoplastic (either extradural or intradural), and inflammatory conditions. The preoperative diagnosis is made with clinical judgment incorporating lab findings and radiological studies. When the diagnosis is uncertain, a biopsy is almost always mandatory since the treatment is dictated by the type of pathology. This is an invasive, timely, and costly process. PURPOSE: The aim of this study was to develop a deep learning (DL) algorithm, based on preoperative MRI and post-operative pathological results, to differentiate between leading spinal pathologies. STUDY DESIGN: We retrospectively collected and analyzed clinical, radiological, and pathological data of patients who underwent spinal surgery or biopsy for various spinal pathologies between 2008 and 2022 at a tertiary center. The patients were stratified according to their pathological reports (the threshold for inclusion was set to 25 patients per diagnosis). METHODS: Preoperative MRI, clinical data, and pathological results were processed by a deep learning model built on the Fast.ai framework on top of the PyTorch environment. RESULTS: A total of 231 patients diagnosed with carcinoma (80), infection (57), meningioma (52), or schwannoma (42), were included in our model. The mean overall accuracy was 0.78±0.06 for the validation, and 0.93±0.03 for the test dataset. CONCLUSION: Deep learning algorithm for differentiation between the aforementioned spinal pathologies, based solely on clinical MRI, proves as a feasible primary diagnostic modality. Larger studies should be performed to validate and improve this algorithm for clinical use. CLINICAL SIGNIFICANCE: This study provides a proof-of-concept for predicting spinal pathologies solely by MRI based DL technology, allowing for a rapid, targeted, and cost-effective work-up and subsequent treatment.

Handling Missing MRI Data in Brain Tumors Classification Tasks: Usage of Synthetic Images vs. Duplicate Images and Empty Images.

BACKGROUND: Deep-learning is widely used for lesion classification. However, in the clinic patient data often has missing images. PURPOSE: To evaluate the use of generated, duplicate and empty(black) images for replacing missing MRI data in AI brain tumor classification tasks. STUDY TYPE: Retrospective. POPULATION: 224 patients (local-dataset; low-grade-glioma (LGG) = 37, high-grade-glioma (HGG) = 187) and 335 patients (public-dataset (BraTS); LGG = 76, HGG = 259). The local-dataset was divided into training (64), validation (16), and internal-test-data (20), while the public-dataset was an independent test-set. FIELD STRENGTH/SEQUENCE: T1WI, T1WI+C, T2WI, and FLAIR images (1.5T/3.0T-MR), obtained from different suppliers. ASSESSMENT: Three image-to-image translation generative-adversarial-network (Pix2Pix-GAN) models were trained on the local-dataset, to generate T1WI, T2WI, and FLAIR images. The rating-and-preference-judgment assessment was performed by three human-readers (radiologist (MD) and two MRI-technicians). Resnet152 was used for classification, and inference was performed on both datasets, with baseline input, and with missing data replaced by 1) generated images; 2) duplication of existing images; and 3) black images. STATISTICAL TESTS: The similarity between the generated and the original images was evaluated using the peak-signal-to-noise-ratio (PSNR) and the structural-similarity-index-measure (SSIM). Classification results were evaluated using accuracy, F1-score and the Kolmogorov-Smirnov test and distance. RESULTS: For baseline-state, the classification model reached to accuracy = 0.93,0.82 on the local and public-datasets. For the missing-data methods, high similarity was obtained between the generated and the original images with mean PSNR = 35.65,32.94 and SSIM = 0.87,0.91 on the local and public-datasets; 39% of the generated-images were labeled as real images by the human-readers. The classification model using generated-images to replace missing images produced the highest results with mean accuracy = 0.91,0.82 compared to 0.85,0.79 for duplicated and 0.77,0.68 for use of black images; DATA CONCLUSION: The feasibility for inference classification model on an MRI dataset with missing images using the Pix2pix-GAN generated images, was shown. The stability and generalization ability of the model was demonstrated by producing consistent results on two independent datasets. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 5.

Model-free dynamic contrast-enhanced MRI analysis: differentiation between active tumor and necrotic tissue in patients with glioblastoma.

OBJECTIVE: Treatment response assessment in patients with high-grade gliomas (HGG) is heavily dependent on changes in lesion size on MRI. However, in conventional MRI, treatment-related changes can appear as enhancing tissue, with similar presentation to that of active tumor tissue. We propose a model-free data-driven method for differentiation between these tissues, based on dynamic contrast-enhanced (DCE) MRI. MATERIALS AND METHODS: The study included a total of 66 scans of patients with glioblastoma. Of these, 48 were acquired from 1 MRI vendor and 18 scans were acquired from a different MRI vendor and used as test data. Of the 48, 24 scans had biopsy results. Analysis included semi-automatic arterial input function (AIF) extraction, direct DCE pharmacokinetic-like feature extraction, and unsupervised clustering of the two tissue types. Validation was performed via (a) comparison to biopsy result (b) correlation to literature-based DCE curves for each tissue type, and (c) comparison to clinical outcome. RESULTS: Consistency between the model prediction and biopsy results was found in 20/24 cases. An average correlation of 82% for active tumor and 90% for treatment-related changes was found between the predicted component and population-based templates. An agreement between the predicted results and radiologist's assessment, based on RANO criteria, was found in 11/12 cases. CONCLUSION: The proposed method could serve as a non-invasive method for differentiation between lesion tissue and treatment-related changes.

Lesions to both somatic and affective pain pathways lead to decreased salience network connectivity.

Human pain is a salient stimulus composed of two main components: a sensory/somatic component, carrying peripheral nociceptive sensation via the spinothalamic tract and brainstem nuclei to the thalamus and then to sensory cortical regions, and an affective (suffering) component, where information from central thalamic nuclei is carried to the anterior insula, dorsal anterior cingulate cortex and other regions. While the sensory component processes information about stimulus location and intensity, the affective component processes information regarding pain-related expectations, motivation to reduce pain and pain unpleasantness. Unlike investigations of acute pain that are based on the introduction of real-time stimulus during brain recordings, chronic pain investigations are usually based on longitudinal and case-control studies, which are limited in their ability to infer the functional network topology of chronic pain. In the current study, we utilized the unique opportunity to target the CNS's pain pathways in two different hierarchical locations to establish causality between pain relief and specific connectivity changes seen within the salience and sensorimotor networks. We examined how lesions to the affective and somatic pain pathways affect resting-state network topology in cancer patients suffering from severe intractable pain. Two procedures have been employed: percutaneous cervical cordotomy (n = 15), hypothesized to disrupt the transmission of the sensory component of pain along the spinothalamic tract, or stereotactic cingulotomy (n = 7), which refers to bilateral intracranial ablation of an area in the dorsal anterior cingulate cortex and is known to ameliorate the affective component of pain. Both procedures led to immediate significant alleviation of experienced pain and decreased functional connectivity within the salience network. However, only the sensory procedure (cordotomy) led to decreased connectivity within the sensorimotor network. Thus, our results support the existence of two converging systems relaying experienced pain, showing that pain-related suffering can be either directly influenced by interfering with the affective pathway or indirectly influenced by interfering with the ascending spinothalamic tract.

Utilizing the TractSeg Tool for Automatic Corticospinal Tract Segmentation in Patients With Brain Pathology.

Purpose: White-matter tract segmentation in patients with brain pathology can guide surgical planning and can be used for tissue integrity assessment. Recently, TractSeg was proposed for automatic tract segmentation in healthy subjects. The aim of this study was to assess the use of TractSeg for corticospinal-tract (CST) segmentation in a large cohort of patients with brain pathology and to evaluate its consistency in repeated measurements. Methods: A total of 649 diffusion-tensor-imaging scans were included, of them: 625 patients and 24 scans from 12 healthy controls (scanned twice for consistency assessment). Manual CST labeling was performed in all cases, and by 2 raters for the healthy subjects. Segmentation results were evaluated based on the Dice score. In order to evaluate consistency in repeated measurements, volume, Fractional Anisotropy (FA), and Mean Diffusivity (MD) values were extracted and correlated for the manual versus automatic methods. Results: For the automatic CST segmentation Dice scores of 0.63 and 0.64 for the training and testing datasets were obtained. Higher consistency between measurements was detected for the automatic segmentation, with between measurements correlations of volume = 0.92/0.65, MD = 0.94/0.75 for the automatic versus manual segmentation. Conclusions: The TractSeg method enables automatic CST segmentation in patients with brain pathology. Superior measurements consistency was detected for the automatic in comparison to manual fiber segmentation, which indicates an advantage when using this method for clinical and longitudinal studies.

Neuromelanin and T2*-MRI for the assessment of genetically at-risk, prodromal, and symptomatic Parkinson's disease.

MRI was suggested as a promising method for the diagnosis and assessment of Parkinson's Disease (PD). We aimed to assess the sensitivity of neuromelanin-MRI and T2* with radiomics analysis for detecting PD, identifying individuals at risk, and evaluating genotype-related differences. Patients with PD and non-manifesting (NM) participants [NM-carriers (NMC) and NM-non-carriers (NMNC)], underwent MRI and DAT-SPECT. Imaging-based metrics included 48 neuromelanin and T2* radiomics features and DAT-SPECT specific-binding-ratios (SBR), were extracted from several brain regions. Imaging values were assessed for their correlations with age, differences between groups, and correlations with the MDS-likelihood-ratio (LR) score. Several machine learning classifiers were evaluated for group classification. A total of 127 participants were included: 46 patients with PD (62.3 ± 10.0 years) [15:LRRK2-PD, 16:GBA-PD, and 15:idiopathic-PD (iPD)], 47 NMC (51.5 ± 8.3 years) [24:LRRK2-NMC and 23:GBA-NMC], and 34 NMNC (53.5 ± 10.6 years). No significant correlations were detected between imaging parameters and age. Thirteen MRI-based parameters and radiomics features demonstrated significant differences between PD and NMNC groups. Support-Vector-Machine (SVM) classifier achieved the highest performance (AUC = 0.77). Significant correlations were detected between LR scores and two radiomic features. The classifier successfully identified two out of three NMC who converted to PD. Genotype-related differences were detected based on radiomic features. SBR values showed high sensitivity in all analyses. In conclusion, neuromelanin and T2* MRI demonstrated differences between groups and can be used for the assessment of individuals at-risk in cases when DAT-SPECT can't be performed. Combining neuromelanin and T2*-MRI provides insights into the pathophysiology underlying PD, and suggests that iron accumulation precedes neuromelanin depletion during the prodromal phase.

BV-GAN: 3D time-of-flight magnetic resonance angiography cerebrovascular vessel segmentation using adversarial CNNs.

Purpose: Cerebrovascular vessel segmentation is a key step in the detection of vessel pathology. Brain time-of-flight magnetic resonance angiography (TOF-MRA) is a main method used clinically for imaging of blood vessels using magnetic resonance imaging. This method is primarily used to detect narrowing, blockage of the arteries, and aneurysms. Despite its importance, TOF-MRA interpretation relies mostly on visual, subjective assessment performed by a neuroradiologist and is mostly based on maximum intensity projections reconstruction of the three-dimensional (3D) scan, thus reducing the acquired spatial resolution. Works tackling the central problem of automatically segmenting brain blood vessels typically suffer from memory and imbalance related issues. To address these issues, the spatial context of the segmentation consider by neural networks is typically restricted (e.g., by resolution reduction or analysis of environments of lower dimensions). Although efficient, such solutions hinder the ability of the neural networks to understand the complex 3D structures typical of the cerebrovascular system and to leverage this understanding for decision making. Approach: We propose a brain-vessels generative-adversarial-network (BV-GAN) segmentation model, that better considers connectivity and structural integrity, using prior based attention and adversarial learning techniques. Results: For evaluations, fivefold cross-validation experiments were performed on two datasets. BV-GAN demonstrates consistent improvement of up to 10% in vessel Dice score with each additive designed component to the baseline state-of-the-art models. Conclusions: Potentially, this automated 3D-approach could shorten analysis time, allow for quantitative characterization of vascular structures, and reduce the need to decrease resolution, overall improving diagnosis cerebrovascular vessel disorders.

Aberrant dopamine transporter and functional connectivity patterns in LRRK2 and GBA mutation carriers.

Non-manifesting carriers (NMCs) of Parkinson's disease (PD)-related mutations such as LRRK2 and GBA are at an increased risk for developing PD. Dopamine transporter (DaT)-spectral positron emission computed tomography is widely used for capturing functional nigrostriatal dopaminergic activity. However, it does not reflect other ongoing neuronal processes; especially in the prodromal stages of the disease. Resting-state fMRI (rs-fMRI) has been proposed as a mode for assessing functional alterations associated with PD, but its relation to dopaminergic deficiency remains unclear. We aimed to study the association between presynaptic striatal dopamine uptake and functional connectivity (FC) patterns among healthy first-degree relatives of PD patients with mutations in LRRK2 and GBA genes. N = 85 healthy first-degree subjects were enrolled and genotyped. All participants underwent DaT and rs-fMRI scans, as well as a comprehensive clinical assessment battery. Between-group differences in FC within striatal regions were investigated and compared with striatal binding ratios (SBR). N = 26 GBA-NMCs, N = 25 LRRK2-NMCs, and N = 34 age-matched nonmanifesting noncarriers (NM-NCs) were included in each study group based on genetic status. While genetically-defined groups were similar across clinical measures, LRRK2-NMCs demonstrated lower SBR in the right putamen compared with NM-NCs, and higher right putamen FC compared to GBA-NMCs. In this group, higher striatal FC was associated with increased risk for PD. The observed differential SBR and FC patterns among LRRK2-NMCs and GBA-NMCs indicate that DaTscan and FC assessments might offer a more sensitive prediction of the risk for PD in the pre-clinical stages of the disease.

Predicting EGFR mutation status by a deep learning approach in patients with non-small cell lung cancer brain metastases.

PURPOSE: Non-small cell lung cancer (NSCLC) tends to metastasize to the brain. Between 10 and 60% of NSCLCs harbor an activating mutation in the epidermal growth-factor receptor (EGFR), which may be targeted with selective EGFR inhibitors. However, due to a high discordance rate between the molecular profile of the primary tumor and the brain metastases (BMs), identifying an individual patient's EGFR status of the BMs necessitates tissue diagnosis via an invasive surgical procedure. We employed a deep learning (DL) method with the aim of noninvasive detection of the EGFR mutation status in NSCLC BM. METHODS: We retrospectively collected clinical, radiological, and pathological-molecular data of all the NSCLC patients who had been diagnosed with BMs and underwent resection of their BM during 2009-2019. The study population was then divided into two groups based upon EGFR mutational status. We further employed a DL technique to classify the two groups according to their preoperative magnetic resonance imaging features. Augmentation techniques, transfer learning approach, and post-processing of the predicted results were applied to overcome the relatively small cohort. Finally, we established the accuracy of our model in predicting EGFR mutation status of BM of NSCLC. RESULTS: Fifty-nine patients were included in the study, 16 patients harbored EGFR mutations. Our model predicted mutational status with mean accuracy of 89.8%, sensitivity of 68.7%, specificity of 97.7%, and a receiver operating characteristic curve value of 0.91 across the 5 validation datasets. CONCLUSION: DL-based noninvasive molecular characterization is feasible, has high accuracy and should be further validated in large prospective cohorts.

Whole brain and deep gray matter structure segmentation: Quantitative comparison between MPRAGE and MP2RAGE sequences.

OBJECTIVE: T1-weighted MRI images are commonly used for volumetric assessment of brain structures. Magnetization prepared 2 rapid gradient echo (MP2RAGE) sequence offers superior gray (GM) and white matter (WM) contrast. This study aimed to quantitatively assess the agreement of whole brain tissue and deep GM (DGM) volumes obtained from MP2RAGE compared to the widely used MP-RAGE sequence. METHODS: Twenty-nine healthy participants were included in this study. All subjects underwent a 3T MRI scan acquiring high-resolution 3D MP-RAGE and MP2RAGE images. Twelve participants were re-scanned after one year. The whole brain, as well as DGM segmentation, was performed using CAT12, volBrain, and FSL-FAST automatic segmentation tools based on the acquired images. Finally, contrast-to-noise ratio between WM and GM (CNRWG), the agreement between the obtained tissue volumes, as well as scan-rescan variability of both sequences were explored. RESULTS: Significantly higher CNRWG was detected in MP2RAGE vs. MP-RAGE (Mean ± SD = 0.97 ± 0.04 vs. 0.8 ± 0.1 respectively; p<0.0001). Significantly higher total brain GM, and lower cerebrospinal fluid volumes were obtained from MP2RAGE vs. MP-RAGE based on all segmentation methods (p<0.05 in all cases). Whole-brain voxel-wise comparisons revealed higher GM tissue probability in the thalamus, putamen, caudate, lingual gyrus, and precentral gyrus based on MP2RAGE compared with MP-RAGE. Moreover, significantly higher WM probability was observed in the cerebellum, corpus callosum, and frontal-and-temporal regions in MP2RAGE vs. MP-RAGE. Finally, MP2RAGE showed a higher mean percentage of change in total brain GM compared to MP-RAGE. On the other hand, MP-RAGE demonstrated a higher overtime percentage of change in WM and DGM volumes compared to MP2RAGE. CONCLUSIONS: Due to its higher CNR, MP2RAGE resulted in reproducible brain tissue segmentation, and thus is a recommended method for volumetric imaging biomarkers for the monitoring of neurological diseases.

Differentiating Small-Cell Lung Cancer From Non-Small-Cell Lung Cancer Brain Metastases Based on MRI Using Efficientnet and Transfer Learning Approach.

Differentiation between small-cell lung cancer (SCLC) from non-small-cell lung cancer (NSCLC) brain metastases is crucial due to the different clinical behaviors of the two tumor types. We propose the use of a deep learning and transfer learning approach based on conventional magnetic resonance imaging (MRI) for non-invasive classification of SCLC vs. NSCLC brain metastases. Sixty-nine patients with brain metastasis of lung cancer origin were included. Of them, 44 patients had NSCLC and 25 patients had SCLC. Classification was performed with EfficientNet architecture on crop images of lesion areas and based on post-contrast T1-weighted, T2-weighted and FLAIR imaging input data. Evaluation of the model was carried out in a 5-fold cross-validation manner, and based on accuracy, precision, recall, F1 score and area under the receiver operating characteristic curve. The best classification results were obtained with multiparametric MRI input data (T1WI+c+FLAIR+T2WI), with a mean overall accuracy of 0.90 ± 0.04, and F1 score of 0.92 ± 0.05 for NSCLC and 0.87 ± 0.08 for SCLC for the validation data and an accuracy of 0.87 ± 0.05, with an F1 score of 0.88 ± 0.05 for NSCLC and 0.85 ± 0.05 for SCLC for the test dataset. The proposed method provides an automatic noninvasive method for the classification of brain metastasis with high sensitivity and specificity for differentiation between NSCLC vs. SCLC brain metastases. It may be used as a diagnostic tool for improving decision-making in the treatment of patients with these metastases. Further studies on larger patient samples are required to validate the current results.

Automatic segmentation, classification, and follow-up of optic pathway gliomas using deep learning and fuzzy c-means clustering based on MRI.

PURPOSE: Optic pathway gliomas (OPG) are low-grade pilocytic astrocytomas accounting for 3-5% of pediatric intracranial tumors. Accurate and quantitative follow-up of OPG using magnetic resonance imaging (MRI) is crucial for therapeutic decision making, yet is challenging due to the complex shape and heterogeneous tissue pattern which characterizes these tumors. The aim of this study was to implement automatic methods for segmentation and classification of OPG and its components, based on MRI. METHODS: A total of 202 MRI scans from 29 patients with chiasmatic OPG scanned longitudinally were retrospectively collected and included in this study. Data included T2 and post-contrast T1 weighted images. The entire tumor volume and its components were manually annotated by a senior neuro-radiologist, and inter- and intra-rater variability of the entire tumor volume was assessed in a subset of scans. Automatic tumor segmentation was performed using deep-learning method with U-Net+ResNet architecture. A fivefold cross-validation scheme was used to evaluate the automatic results relative to manual segmentation. Voxel-based classification of the tumor into enhanced, non-enhanced, and cystic components was performed using fuzzy c-means clustering. RESULTS: The results of the automatic tumor segmentation were: mean dice score = 0.736 ± 0.025, precision = 0.918 ± 0.014, and recall = 0.635 ± 0.039 for the validation data, and dice score = 0.761 ± 0.011, precision = 0.794 ± 0.028, and recall = 0.742 ± 0.012 for the test data. The accuracy of the voxel-based classification of tumor components was 0.94, with precision = 0.89, 0.97, and 0.85, and recall = 1.00, 0.79, and 0.94 for the non-enhanced, enhanced, and cystic components, respectively. CONCLUSION: This study presents methods for automatic segmentation of chiasmatic OPG tumors and classification into the different components of the tumor, based on conventional MRI. Automatic quantitative longitudinal assessment of these tumors may improve radiological monitoring, facilitate early detection of disease progression and optimize therapy management.

Virtual biopsy using MRI radiomics for prediction of BRAF status in melanoma brain metastasis.

Brain metastases are common in patients with advanced melanoma and constitute a major cause of morbidity and mortality. Between 40% and 60% of melanomas harbor BRAF mutations. Selective BRAF inhibitor therapy has yielded improvement in clinical outcome; however, genetic discordance between the primary lesion and the metastatic tumor has been shown to occur. Currently, the only way to characterize the genetic landscape of a brain metastasis is by tissue sampling, which carries risks and potential complications. The aim of this study was to investigate the use of radiomics analysis for non-invasive identification of BRAF mutation in patients with melanoma brain metastases, based on conventional magnetic resonance imaging (MRI) data. We applied a machine-learning method, based on MRI radiomics features for noninvasive characterization of the BRAF status of brain metastases from melanoma (BMM) and applied it to BMM patients from two tertiary neuro-oncological centers. All patients underwent surgical resection for BMM, and their BRAF mutation status was determined as part of their oncological work-up. Their routine preoperative MRI study was used for radiomics-based analysis in which 195 features were extracted and classified according to their BRAF status via a support vector machine. The BRAF status of 53 study patients, with 54 brain metastases (25 positive, 29 negative for BRAF mutation) was predicted with mean accuracy = 0.79 ± 0.13, mean precision = 0.77 ± 0.14, mean sensitivity = 0.72 ± 0.20, mean specificity = 0.83 ± 0.11 and with a 0.78 area under the receiver operating characteristic curve for positive BRAF mutation prediction. Radiomics-based noninvasive genetic characterization is feasible and should be further verified using large prospective cohorts.

Ruminative Tendency Relates to Ventral Striatum Functionality: Evidence From Task and Resting-State fMRI.

BACKGROUND: Ruminative responding involves repetitive and passive thinking about one's negative affect. This tendency interferes with initiation of goal-directed rewarding strategies, which could alleviate depressive states. Such reward-directed response selection has been shown to be mediated by ventral striatum/nucleus accumbens (VS/NAcc) function. However, to date, no study has examined whether trait rumination relates to VS/NAcc functionality. Here, we tested whether rumination moderates VS/NAcc function both in response to reward and during a ruminative state. METHODS: Trait rumination was considered dimensionally using Rumination Response Scale (RRS) scores. Our sample (N = 80) consisted of individuals from a community sample and from patients diagnosed with major depressive disorder, providing a broad range of RRS scores. Participants underwent fMRI to assess two modes of VS/NAcc functionality: 1) in response to reward, and 2) during resting-state, as a proxy for ruminative state. We then tested for associations between RRS scores and VS/NAcc functional profiles, statistically controlling for overall depressive symptom severity. RESULTS: RRS scores correlated positively with VS/NAcc response to reward. Furthermore, we noted that higher RRS scores were associated with increased ruminative-dependent resting-state functional connectivity of the VS/NAcc with the left orbitofrontal cortex. CONCLUSIONS: These findings suggest that ruminative tendencies manifest in VS/NAcc reward- and rumination-related functions, providing support for a theoretical-clinical perspective of rumination as a habitual impairment in selection of rewarding, adaptive coping strategies.

Neuroanatomical Risk Factors for Posttraumatic Stress Disorder in Recent Trauma Survivors.

BACKGROUND: Low hippocampal volume could serve as an early risk factor for posttraumatic stress disorder (PTSD) in interaction with other brain anomalies of developmental origin. One such anomaly may well be the presence of a large cavum septum pellucidum (CSP), which has been loosely associated with PTSD. We performed a longitudinal prospective study of recent trauma survivors. We hypothesized that at 1 month after trauma exposure the relation between hippocampal volume and PTSD symptom severity will be moderated by CSP volume, and that this early interaction will account for persistent PTSD symptoms at subsequent time points. METHODS: One hundred seventy-one adults (87 women, average age 34.22 years [range, 18-65 years of age]) who were admitted to a general hospital's emergency department after a traumatic event underwent clinical assessment and structural magnetic resonance imaging within 1 month after trauma. Follow-up clinical evaluations were conducted at 6 (n = 97) and 14 (n = 78) months after trauma. Hippocampal and CSP volumes were measured automatically by FreeSurfer software and verified manually by a neuroradiologist (D.N.). RESULTS: At 1 month after trauma, CSP volume significantly moderated the relation between hippocampal volume and PTSD severity (p = .026), and this interaction further predicted symptom severity at 14 months posttrauma (p = .018). Specifically, individuals with a smaller hippocampus and larger CSP at 1 month posttrauma showed more severe symptoms at 1 and 14 months after trauma exposure. CONCLUSIONS: Our study provides evidence for an early neuroanatomical risk factors for PTSD, which could also predict the progression of the disorder in the year after trauma exposure. Such a simple-to-acquire neuroanatomical signature for PTSD could guide early management as well as long-term monitoring.

Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis.

BACKGROUND: Differentiation between glioblastoma and brain metastasis is highly important due to differing medical treatment strategies. While MRI is the modality of choice for the assessment of patients with brain tumors, differentiation between glioblastoma and solitary brain metastasis may be challenging due to their similar appearance on MRI. PURPOSE: To differentiate between glioblastoma and brain metastasis subtypes using radiomics analysis based on conventional post-contrast T1 -weighted (T1 W) MRI. STUDY TYPE: Retrospective. SUBJECTS: Data were acquired from 439 patients: 212 patients with glioblastoma and 227 patients with brain metastasis (breast, lung, and others). FIELD STRENGTH/SEQUENCE: Post-contrast 3D T1 W gradient echo images, acquired with 1.5 and 3.0 T MR systems. ASSESSMENT: Analysis included image preprocessing, segmentation of tumor area, and features extraction including: patients' clinical information, tumor location, first- and second-order statistical, morphological, wavelet features, and bag-of-features. Following dimension reduction, classification was performed using various machine-learning algorithms including support-vector machine (SVM), k-nearest neighbor, decision trees, and ensemble classifiers. STATISTICAL TESTS: For classification, the data were divided into training (80%) and testing datasets (20%). Following optimization of the classifiers, mean sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were calculated. RESULTS: For the testing dataset, the best results for differentiation of glioblastoma from brain metastasis were obtained using the SVM classifier with mean accuracy = 0.85, sensitivity = 0.86, specificity = 0.85, and AUC = 0.96. The best classification results between glioblastoma and brain metastasis subtypes were obtained using SVM classifier with mean accuracy = 0.85, 0.89, 0.75, 0.90; sensitivity = 1.00, 0.60, 0.57, 0.11; specificity = 0.76, 0.92, 0.87, 0.99; and AUC = 0.98, 0.81, 0.83, 0.57 for the glioblastoma, breast, lung, and other brain metastases, respectively. DATA CONCLUSION: Differentiation between glioblastoma and brain metastasis showed a high success rate based on postcontrast T1 W MRI. Classification between glioblastoma and brain metastasis subtypes may require additional MR sequences with other tissue contrasts. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:519-528.

Repeatability of dynamic contrast enhanced vp parameter in healthy subjects and patients with brain tumors.

PURPOSE: To study the repeatability of plasma volume (vp) extracted from dynamic-contrast-enhanced (DCE) MRI in order to define threshold values for significant longitudinal changes, and to assess changes in patients with high-grade-glioma (HGG). METHODS: Twenty eight healthy subjects, of which eleven scanned twice, were used to assess the repeatability of vp within the normal-appearing brain tissue and to define threshold values for significant changes based on least-detected-differences (LDD) of mean vp values and histogram comparisons using earth-mover's-distance (EMD). Sixteen patients with HGG were scanned longitudinally with eight patients scanned before and following bevacizumab therapy. Longitudinal changes were assessed based on defined threshold values in comparison to RANO criteria. RESULTS: The threshold values for significant changes were: LDD = 0.0024 (ml/100 ml, 21%) for mean vp and EMD = 4.14. In patients, in 20/24 comparisons, no significant longitudinal changes were detected for vp within the normal-appearing brain tissue. Concurring results were obtained between changes in lesion volume (RANO criteria) and LDD or EMD values in cases diagnosed with progressive-disease, yet in about 50% of cases diagnosed with partial-response preliminary results demonstrated significant increase in vp despite significant reductions in lesion volume. In two patients, these changes preceded progression detected at follow-up scans. In general, a good concordance was obtained between LDD and EMD. CONCLUSION: This study shows high repeatability of vp and provides threshold values for significant changes in longitudinal assessment of patients with brain tumors. Preliminary results suggest the use of vp-DCE parameter to improve assessment of therapy response in patients with high-grade-glioma.

Differentiation between vasogenic edema and infiltrative tumor in patients with high-grade gliomas using texture patch-based analysis.

BACKGROUND: High-grade gliomas (HGGs) induce both vasogenic edema and extensive infiltration of tumor cells, both of which present with similar appearance on conventional MRI. Using current radiological criteria, differentiation between these tumoral and nontumoral areas within the nonenhancing lesion area remains challenging. PURPOSE: To use radiomics patch-based analysis, based on conventional MRI, for the classification of the nonenhancing lesion area in patients with HGG into tumoral and nontumoral components. STUDY TYPE: Prospective. SUBJECTS: In all, 179 MRI scans were obtained from 102 patients: 67 patients with HGG and 35 patients with brain metastases. A subgroup of 15 patients with HGG were scanned before and following administration of bevacizumab. FIELD STRENGTH/SEQUENCE: Pre and postcontrast agent T1 -weighted-imaging (WI), T2 WI, FLAIR, diffusion-tensor-imaging (DTI), and dynamic-contrast-enhanced (DCE)-MRI at 3T. ASSESSMENT: A total of 225 histograms and gray-level-co-occurrence matrix-based features were extracted from the nonenhancing lesion area. Tumoral volumes of interest (VOIs) were defined at the peritumoral area in patients with HGG; nontumoral VOIs were defined in patients with brain metastasis. Twenty machine-learning algorithms including support-vector-machine (SVM), k-nearest neighbor, decision-trees, and ensemble classifiers were tested. The best classifier was trained on the entire labeled data, and was used to classify the entire data. STATISTICAL TESTS: Dimensional reduction was performed on the 225 features using principal component analysis. Classification results were evaluated based on the sensitivity, specificity, and accuracy of each of the 20 classifiers, first based on a training and testing dataset (80% of the labeled data) in a 5-fold manner, and next by applying the best classifier to the validation data (the remaining 20% of the labeled data). Results were additionally evaluated by assessing differences in dynamic-contrast-enhanced plasma-volume (vp ) and volume-transfer-constant (ktrans ) values between the two components using Mann-Whitney U-test/t-test. RESULTS: The best classification into tumoral and nontumoral lesion components was obtained using a linear SVM classifier, with average accuracy of 87%, sensitivity 86%, and specificity of 89% (for the training and testing data). Significantly higher vp and ktrans values (P < 0.0001) were detected in the tumoral compared to the nontumoral component. Preliminary classification results in a subgroup of patients treated with bevacizumab demonstrated a reduction mainly in the nontumoral component following administration of bevacizumab, enabling early assessment of disease progression in some patients. DATA CONCLUSION: A radiomics patch-based analysis enables classification of the nonenhancing lesion area in patients with HGG. Preliminary results were promising and the proposed method has the potential to assist in clinical decision-making and to improve therapy response assessment in patients with HGG. LEVEL OF EVIDENCE: 1 Technical Efficacy Stage 4 J. Magn. Reson. Imaging 2018.