IBRDM: An Intelligent Framework for Brain Tumor Classification Using Radiomics- and DWT-based Fusion of MRI Sequences

Brain tumors are one of the critical malignant neurological cancers with the highest number of deaths and injuries worldwide. They are categorized into two major classes, high-grade glioma (HGG) and low-grade glioma (LGG), with HGG being more aggressive and malignant, whereas LGG tumors are less aggressive, but if left untreated, they get converted to HGG. Thus, the classification of brain tumors into the corresponding grade is a crucial task, especially for making decisions related to treatment. Motivated by the importance of such critical threats to humans, we propose a novel framework for brain tumor classification using discrete wavelet transform-based fusion of MRI sequences and Radiomics feature extraction. We utilized the Brain Tumor Segmentation 2018 challenge training dataset for the performance evaluation of our approach, and we extract features from three regions of interest derived using a combination of several tumor regions. We used wrapper method-based feature selection techniques for selecting a significant set of features and utilize various machine learning classifiers, Random Forest, Decision Tree, and Extra Randomized Tree for training the model. For proper validation of our approach, we adopt the five-fold cross-validation technique. We achieved state-of-the-art performance considering several performance metrics, 〈 Acc , Sens , Spec , F1-score , MCC , AUC 〉 ≡ 〈 98.60%, 99.05%, 97.33%, 99.05%, 96.42%, 98.19% 〉, where Acc , Sens , Spec , F1-score , MCC , and AUC represents the accuracy, sensitivity, specificity, F1-score, Matthews correlation coefficient, and area-under-the-curve, respectively. We believe our proposed approach will play a crucial role in the planning of clinical treatment and guidelines before surgery.

Automatic segmentation of head and neck primary tumors on MRI using a multi-view CNN

Background Accurate segmentation of head and neck squamous cell cancer (HNSCC) is important for radiotherapy treatment planning. Manual segmentation of these tumors is time-consuming and vulnerable to inconsistencies between experts, especially in the complex head and neck region. The aim of this study is to introduce and evaluate an automatic segmentation pipeline for HNSCC using a multi-view CNN (MV-CNN). Methods The dataset included 220 patients with primary HNSCC and availability of T1-weighted, STIR and optionally contrast-enhanced T1-weighted MR images together with a manual reference segmentation of the primary tumor by an expert. A T1-weighted standard space of the head and neck region was created to register all MRI sequences to. An MV-CNN was trained with these three MRI sequences and evaluated in terms of volumetric and spatial performance in a cross-validation by measuring intra-class correlation (ICC) and dice similarity score (DSC), respectively. Results The average manual segmented primary tumor volume was 11.8±6.70 cm3 with a median [IQR] of 13.9 [3.22-15.9] cm3. The tumor volume measured by MV-CNN was 22.8±21.1 cm3 with a median [IQR] of 16.0 [8.24-31.1] cm3. Compared to the manual segmentations, the MV-CNN scored an average ICC of 0.64±0.06 and a DSC of 0.49±0.19. Improved segmentation performance was observed with increasing primary tumor volume: the smallest tumor volume group (<3 cm3) scored a DSC of 0.26±0.16 and the largest group (>15 cm3) a DSC of 0.63±0.11 (p<0.001). The automated segmentation tended to overestimate compared to the manual reference, both around the actual primary tumor and in false positively classified healthy structures and pathologically enlarged lymph nodes. Conclusion An automatic segmentation pipeline was evaluated for primary HNSCC on MRI. The MV-CNN produced reasonable segmentation results, especially on large tumors, but overestimation decreased overall performance. In further research, the focus should be on decreasing false positives and make it valuable in treatment planning.

Volumetric accuracy of different imaging modalities in acute intracerebral hemorrhage

Background Follow-up imaging in intracerebral hemorrhage is not standardized and radiologists rely on different imaging modalities to determine hematoma growth. This study assesses the volumetric accuracy of different imaging modalities (MRI, CT angiography, postcontrast CT) to measure hematoma size. Methods 28 patients with acute spontaneous intracerebral hemorrhage referred to a tertiary stroke center were retrospectively included between 2018 and 2019. Inclusion criteria were (1) spontaneous intracerebral hemorrhage (supra- or infratentorial), (2) noncontrast CT imaging performed on admission, (3) follow-up imaging (CT angiography, postcontrast CT, MRI), and (4) absence of hematoma expansion confirmed by a third cranial image within 6 days. Two independent raters manually measured hematoma volume by drawing a region of interest on axial slices of admission noncontrast CT scans as well as on follow-up imaging (CT angiography, postcontrast CT, MRI) using a semi-automated segmentation tool (Visage image viewer; version 7.1.10). Results were compared using Bland–Altman plots. Results Mean admission hematoma volume was 18.79 ± 19.86 cc. All interrater and intrarater intraclass correlation coefficients were excellent (1; IQR 0.98–1.00). In comparison to hematoma volume on admission noncontrast CT volumetric measurements were most accurate in patients who received postcontrast CT (bias of − 2.47%, SD 4.67: n = 10), while CT angiography often underestimated hemorrhage volumes (bias of 31.91%, SD 45.54; n = 20). In MRI sequences intracerebral hemorrhage volumes were overestimated in T2* (bias of − 64.37%, SD 21.65; n = 10). FLAIR (bias of 6.05%, SD 35.45; n = 13) and DWI (bias of-14.6%, SD 31.93; n = 12) over- and underestimated hemorrhagic volumes. Conclusions Volumetric measurements were most accurate in postcontrast CT while CT angiography and MRI sequences often substantially over- or underestimated hemorrhage volumes.

Perfluorocarbon Emulsion Contrast Agents: A Mini Review

Perfluorocarbon emulsions offer a variety of applications in medical imaging. The substances can be useful for most radiological imaging modalities; including, magnetic resonance imaging, ultrasonography, computed tomography, and positron emission tomography. Recently, the substance has gained much interest for theranostics, with both imaging and therapeutic potential. As MRI sequences improve and more widespread access to 19F-MRI coils become available, perfluorocarbon emulsions have great potential for new commercial imaging agents, due to high fluorine content and previous regulatory approval as antihypoxants and blood substitutes. This mini review aims to discuss the chemistry and physics of these contrast agents, in addition to highlighting some of the past, recent, and potential applications.

Can routine MRI spine T1 sequences be used for prediction of decreased bone density?

Background Bone marrow signal is ideally evaluated with magnetic resonance imaging (MRI) due to its high tissue contrast. While advanced MRI quantitative methods can be used for estimating bone density, there are no readily available parameters on routine clinical MRI sequences of the lumbar spine. Purpose To evaluate whether T1 signal intensity (SI) ratio of lumbar vertebral body (VB)/cerebrospinal fluid (CSF) may predict decreased bone density. Material and Methods A retrospective study was conducted. After use of inclusion/exclusion criteria, 36 patients who had an MRI scan of the lumbar spine and a DEXA scan performed as a part of annual health visit were selected. T1 SI of the lumbar vertebral bodies and adjacent CSF were recorded. Ratio of T1 SI of L1–L4 (VB)/CSF was calculated. The corresponding bone-density values on DEXA scan measured as g/cm2 were obtained. Pearson's r correlation statistic was used to determine the correlation between these variables. Results T1 VB/T1 CSF SI ratio was between 1.308 and 2.927 (mean = 2.028). Mean T1 SI value of vertebral bodies (L1–L4) was 264.9 and mean CSF SI value was 131.9. Bone density in g/cm2 was between 0.851 and 1.398 (mean = 1.081). Pearson correlation coefficient was r = −0.619 ( P=0.0001), which shows a negative moderate correlation between the T1 VB/T1 CSF SI ratio and bone density. Conclusion A high T1 VB/T1 CSF SI ratio on routine MRI sequences may indicate decreased bone density. This ratio may be of substantial benefit in unsuspected osteoporosis/osteopenia on routine MRI lumbar spine imaging.

HARM revisited: Etiology of subarachnoid hyperintensities in brain FLAIR MRI

Background: The hyperintense acute reperfusion marker (HARM) describes a phenomenon with a hyperintense signal in the subarachnoid space in Fluid-Attenuated Inversion Recovery (FLAIR) magnetic resonance imaging (MRI) sequences, presumably based on blood–brain barrier breakdown in acute stroke with reperfusion. However, this imaging phenomenon was described in other medical conditions. Aim: Determination of the prevalence and associated clinical findings of this phenomenon in a large sample of patients with different neurological conditions. Methods: This is retrospective, single-center, observational study of 23,948 cerebral MRIs acquired in a Neurological University Clinic over 5 years. The prevalence of HARM, the underlying diagnosis, and damage pattern were examined by chart analysis; MRI was analyzed regarding the type of acute lesions, extent of microangiopathic lesions, and whether gadolinium-based contrast agent (GBCA) was given. Results: Among the MRI data, 84 images (0.35%) from 61 patients were HARM-positive without a subarachnoid signal abnormality in any other sequence. Etiologies were heterogeneous; 35 patients had a cerebrovascular disease (CVD; 19 patients received recanalization therapy), 12 patients had an inflammatory central nervous system (CNS) disease and 14 patients had epilepsy. GBCA was applied to 64% of the patients. Conclusion: HARM was a rare radiological finding in a range of different neurological pathologies, not limited to stroke, or to previous reperfusion therapy and was not dependent on previous GBCA administration. Our data suggest that the term is too narrow in terms of the concepts of the underlying pathology. We propose to use the term FLAIR Subarachnoid Hyperintensity (“FLASH”) phenomenon which might better reflect the observation that the radiological sign can be associated with a variety of central neurological conditions without a straightforward association with therapy.

Added value of 3D-DRIVE and SWI Magnetic Resonance Imaging Sequences in Intraventricular Neurocysticercosis (IVNCC): An Institutional Experience from Northeast India

Background: Prompt diagnosis and early treatment institution are important in intraventricular neurocysticercosis(IVNCC) as compared to the parenchymal or racemose form because it is associated with a poorer patient prognosis. Intraventricular neurocysticercosis is often missed on CT scan or conventional cranial magnetic resonance imaging because of similar density or signal intensity of cysticercus lesion with cerebrospinal fluid. Thestudy aims to evaluate the added value of 3D-DRIVE and SWI MRI sequences in isolated intraventricular cysticercosis with acute neurological presentation.Methods and Materials: This retrospective study was carried out on diagnosed 10patients with isolated intraventricular neurocysticercosis(IVNCC) presented to a tertiary care hospital with an acute onset of symptoms or acute neurological deficit between June 2019 to May 2021. Relevant neurological examination, CSF analysis, a serological test of neurocysticercosis and MRI scan of the brain were performed.Result: Tenpatients of isolated intraventricular neurocysticercosis (3 males and 7 females) having 3 pediatric and7 adults were included in this study sample.The common neurological complications of the isolated intraventricular neurocysticercosis in this study are observed as obstructive hydrocephalus in 8(80%) patients and ependymitis in 7(70%) patients.IVNCC with distinctly visualized scolex (visibility score 2) identified in 2(20%) patients in T2WI, 8 (80%)patients in 3D-DRIVE and 3(30%) patients in SWI sequences. The cyst wall of IVNCC was distinctly visualized (visibility score 2) in 1(10%) patient in T2WI, 8(80%) patientsin 3D-DRIVE and 6(60%) patients in SWI sequence.Conclusion: Heavily T2-weighted steady-state and SWI sequences should be added to routine MRI sequences that helps to identify IVNCC and should be used in patients with unexplained hydrocephalus, especially in endemic regions of Neurocysticercosis.