COVID-19 and myocarditis: a brief review.

Cardiovascular complications (especially myocarditis) related to COVID-19 viral infection are not well understood, nor do they possess a well recognized diagnostic protocol as most of our information regarding this issue was derived from case reports. In this article we extract data from all published case reports in the second half of 2020 to summarize the theories of pathogenesis and explore the value of each diagnostic test including clinical, lab, ECG, ECHO, cardiac MRI and endomyocardial biopsy. These tests provide information that explain the mechanism of development of myocarditis that further paves the way for better management.

Texture and shape analysis of diffusion-weighted imaging for thyroid nodules classification using machine learning.

PURPOSE: To assess whether the integration between (a) functional imaging features that will be extracted from diffusion-weighted imaging (DWI); and (b) shape and texture imaging features as well as volumetric features that will be extracted from T2-weighted magnetic resonance imaging (MRI) can noninvasively improve the diagnostic accuracy of thyroid nodules classification. PATIENTS AND METHODS: In a retrospective study of 55 patients with pathologically proven thyroid nodules, T2-weighted and diffusion-weighted MRI scans of the thyroid gland were acquired. Spatial maps of the apparent diffusion coefficient (ADC) were reconstructed in all cases. To quantify the nodules' morphology, we used spherical harmonics as a new parametric shape descriptor to describe the complexity of the thyroid nodules in addition to traditional volumetric descriptors (e.g., tumor volume and cuboidal volume). To capture the inhomogeneity of the texture of the thyroid nodules, we used the histogram-based statistics (e.g., kurtosis, entropy, skewness, etc.) of the T2-weighted signal. To achieve the main goal of this paper, a fusion system using an artificial neural network (NN) is proposed to integrate both the functional imaging features (ADC) with the structural morphology and texture features. This framework has been tested on 55 patients (20 patients with malignant nodules and 35 patients with benign nodules), using leave-one-subject-out (LOSO) for training/testing validation tests. RESULTS: The functionality, morphology, and texture imaging features were estimated for 55 patients. The accuracy of the computer-aided diagnosis (CAD) system steadily improved as we integrate the proposed imaging features. The fusion system combining all biomarkers achieved a sensitivity, specificity, positive predictive value, negative predictive value, F1-score, and accuracy of 92.9 % $92.9\%$ (confidence interval [CI]: 78.9 % -- 99.5 % $78.9\%\text{--}99.5\%$ ), 95.8 % $95.8\%$ (CI: 87.4 % -- 99.7 % $87.4\%\text{--}99.7\%$ ), 93 % $93\%$ (CI: 80.7 % -- 99.5 % $80.7\%\text{--}99.5\%$ ), 96 % $96\%$ (CI: 88.8 % -- 99.7 % $88.8\%\text{--}99.7\%$ ), 92.8 % $92.8\%$ (CI: 83.5 % -- 98.5 % $83.5\%\text{--}98.5\%$ ), and 95.5 % $95.5\%$ (CI: 88.8 % -- 99.2 % $88.8\%\text{--}99.2\%$ ), respectively, using the LOSO cross-validation approach. CONCLUSION: The results demonstrated in this paper show the promise that integrating the functional features with morphology as well as texture features by using the current state-of-the-art machine learning approaches will be extremely useful for identifying thyroid nodules as well as diagnosing their malignancy.

Diffusion Tensor Imaging in Characterization of Mediastinal Lymphadenopathy.

OBJECTIVE: To determine the efficacy of diffusion-weighted MRI (DWI) and diffusion tensor imaging (DTI) in the characterization of mediastinal lymphadenopathy and the differentiation between malignant and benign lymph nodes (LNs). METHODS: a retrospective evaluation of 58 patients with mediastinal lymphadenopathy that underwent DWI and DTI with calculation of apparent diffusion coefficient (ADC), fractional anisotropy (FA), and mean diffusivity (MD) values of LNs. Final diagnosis was made by the histopathology and proved metastatic (n = 21), lymphomatous (n = 14), granulomatous (n = 11) and reactive (n = 12) LNs. RESULTS: Malignant mediastinal LNs had remarkably lower ADC and MD; (p = 0.001) and higher FA; (p = 0.001) than in benign LNs. The threshold of ADC, MD, and FA at (1.48, 1.32 × 10-3 mm2/s), (1.31, 1.33 × 10-3 mm2/s), (0.62, 0.52) to differentiate malignant from benign LNs has AUC of (0.89, 0.94), (0.96, 0.95), (0.72, 0.82), accuracy of (87%, 86%), (89%, 86%), (70%, 72%) by both observers respectively. The threshold of ADC, MD, and FA at (1.47, 1.32 × 10-3 mm2/s), (1.31, 1.3 × 10-3 mm2/s), (0.62, 0.67) used to differentiate metastatic from reactive LNs revealed AUC of (0.90, 0.94), (0.96, 0.96), (0.73, 0.77), accuracy of (87%, 81%), (87%, 81%), (72%, 66%) by both observers respectively. The mean ADC and MD values of metastatic LNs were statistically significant (p = 0.001) and (p = 0.002, 0.02) respectively when compared with that of lymphoma. The threshold of ADC, and MD (0.94, 0.97 × 10-3 mm2/s) and (0.87, 0.91 × 10-3 mm2/s) used to differentiates metastatic from lymphomatous nodes revealed AUC of (0.90, 0.91), (0.81, 0.74), an accuracy of (85%, 91%), (71%, 71%), by both observers respectively. The inter-class correlation between two observers for all nodes for ADC, MD and FA was r= 0.931, 0.956 and 0.885 respectively. CONCLUSION: Using ADC, MD, and FA can help in the characterization of mediastinal lymphadenopathy noninvasively.

Posttreatment Magnetic Resonance Imaging Surveillance of Head and Neck Cancers.

Treatment strategies and recommended surveillance imaging differ for head and neck cancers depending on subsite and neoplasm type, and pose confusion for referring physicians and interpreting radiologists. The superior soft tissue resolution offered by magnetic resonance imaging is most useful in the surveillance of cancers with high propensities for intraorbital, intracranial, or perineural disease spread, which most commonly include those arising from the sinonasal cavities, nasopharynx, orbits, salivary glands, and the skin. This article discusses recommended surveillance protocoling and reviews treatment approaches, common posttreatment changes, and pearls for identifying disease recurrence in a subsite-based approach.

Role of MR Imaging in Head and Neck Squamous Cell Carcinoma.

Routine and advanced MR imaging sequences are used for locoregional spread, nodal, and distant staging of head and neck squamous cell carcinoma, aids treatment planning, predicts treatment response, differentiates recurrence for postradiation changes, and monitors patients after chemoradiotherapy.

Preimaging and Postimaging of Graft and Flap in Head and Neck Reconstruction.

Head and neck reconstructive surgical techniques are complex; now the microvascular free tissue transfer is the most frequently used. The postreconstruction imaging interpretation is challenging due to the altered anatomy and flap variability. We aim to improve radiologists' knowledge with diverse methods of flap reconstruction for an accurate appreciation of their expected cross-sectional imaging appearance and early detection of tumor recurrence and other complication.

MR Imaging of Salivary Gland Tumors.

Neoplasms of the salivary glands are characterized by their marked histologic diversity giving them nonspecific imaging findings. MR imaging is the best imaging modality to evaluate salivary gland tumors. Multiparametric MR imaging combines conventional imaging features, diffusion-weighted imaging, and perfusion imaging to help distinguish benign and low-grade neoplasms from malignant tumors; however, a biopsy is often needed to establish a definitive histopathologic diagnosis. An awareness of potential imaging pitfalls is important to prevent mistakes in salivary neoplasm imaging.

Update on MR Imaging of Soft Tissue Tumors of Head and Neck.

This article reviews soft tissue tumors of the head and neck following the 2020 revision of WHO Classification of Soft Tissue and Bone Tumours. Common soft tissue tumors in the head and neck and tumors are discussed, along with newly added entities to the classification system. Salient clinical and imaging features that may allow for improved diagnostic accuracy or to narrow the imaging differential diagnosis are covered. Advanced imaging techniques are discussed, with a focus on diffusion-weighted and dynamic contrast imaging and their potential to help characterize soft tissue tumors and aid in distinguishing malignant from benign tumors.

MR Imaging of Vascular Malformations and Tumors of Head and Neck.

Soft tissue vascular anomalies show a wide heterogeneity of clinical manifestations and imaging features. MR imaging has an important role in the diagnosis and management of vascular lesions of the head and neck. MR angiography is mandatory in cases of arteriovenous and combined malformations to assess the high-flow nature/component of the lesions and plan therapy. Infantile hemangiomas can be differentiated from congenital hemangiomas by clinical course. Reactive vascular tumors have nonspecific features similar to infantile hemangiomas. Locally malignant and malignant vascular tumors have irregular borders, infiltration of different tissue planes, and lower apparent diffusion coefficient values than benign vascular tumors.

MR imaging of Oral Cavity and Oropharyngeal Cancer.

MR imaging is the modality of choice in the evaluation of oral cavity and oropharyngeal cancer. Routine postcontrast MR imaging is important for the accurate localization and characterization of the locoregional extension of oral cavity and oropharyngeal cancers. The anatomy of the oral cavity and oropharynx is complex; accurate interpretation is vital for description of the extension of the masses. Understanding the new changes in the eighth edition of the American Joint Committee on Cancer staging system. MR imaging is the imaging modality of choice for detection of perineural spread.

Artificial Intelligence and Deep Learning of Head and Neck Cancer.

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

Magnetic Resonance Imaging of Perineural Spread of Head and Neck Cancer.

Perineural tumor spread (PNTS) is one of the important methods of tumoral spread in head and neck cancers. It consists of a complex process that entails the production of certain chemicals or the production of certain cell receptors. Histologic type and primary tumor site play an important role in PNTS. Any nerve could be affected; however, the trigeminal and facial nerves are the most involved nerves. Magnetic resonance imaging and computed tomography detect the primary and secondary signs of PNTS. Functional imaging such as diffusion-weighted imaging and hybrid imaging act as problem-solving techniques.

Clinical applications of artificial intelligence and radiomics in neuro-oncology imaging.

This article is a comprehensive review of the basic background, technique, and clinical applications of artificial intelligence (AI) and radiomics in the field of neuro-oncology. A variety of AI and radiomics utilized conventional and advanced techniques to differentiate brain tumors from non-neoplastic lesions such as inflammatory and demyelinating brain lesions. It is used in the diagnosis of gliomas and discrimination of gliomas from lymphomas and metastasis. Also, semiautomated and automated tumor segmentation has been developed for radiotherapy planning and follow-up. It has a role in the grading, prediction of treatment response, and prognosis of gliomas. Radiogenomics allowed the connection of the imaging phenotype of the tumor to its molecular environment. In addition, AI is applied for the assessment of extra-axial brain tumors and pediatric tumors with high performance in tumor detection, classification, and stratification of patient's prognoses.

A Comprehensive Computer-Assisted Diagnosis System for Early Assessment of Renal Cancer Tumors.

Renal cell carcinoma (RCC) is the most common and a highly aggressive type of malignant renal tumor. In this manuscript, we aim to identify and integrate the optimal discriminating morphological, textural, and functional features that best describe the malignancy status of a given renal tumor. The integrated discriminating features may lead to the development of a novel comprehensive renal cancer computer-assisted diagnosis (RC-CAD) system with the ability to discriminate between benign and malignant renal tumors and specify the malignancy subtypes for optimal medical management. Informed consent was obtained from a total of 140 biopsy-proven patients to participate in the study (male = 72 and female = 68, age range = 15 to 87 years). There were 70 patients who had RCC (40 clear cell RCC (ccRCC), 30 nonclear cell RCC (nccRCC)), while the other 70 had benign angiomyolipoma tumors. Contrast-enhanced computed tomography (CE-CT) images were acquired, and renal tumors were segmented for all patients to allow the extraction of discriminating imaging features. The RC-CAD system incorporates the following major steps: (i) applying a new parametric spherical harmonic technique to estimate the morphological features, (ii) modeling a novel angular invariant gray-level co-occurrence matrix to estimate the textural features, and (iii) constructing wash-in/wash-out slopes to estimate the functional features by quantifying enhancement variations across different CE-CT phases. These features were subsequently combined and processed using a two-stage multilayer perceptron artificial neural network (MLP-ANN) classifier to classify the renal tumor as benign or malignant and identify the malignancy subtype as well. Using the combined features and a leave-one-subject-out cross-validation approach, the developed RC-CAD system achieved a sensitivity of 95.3%±2.0%, a specificity of 99.9%±0.4%, and Dice similarity coefficient of 0.98±0.01 in differentiating malignant from benign tumors, as well as an overall accuracy of 89.6%±5.0% in discriminating ccRCC from nccRCC. The diagnostic abilities of the developed RC-CAD system were further validated using a randomly stratified 10-fold cross-validation approach. The obtained results using the proposed MLP-ANN classification model outperformed other machine learning classifiers (e.g., support vector machine, random forests, relational functional gradient boosting, etc.). Hence, integrating morphological, textural, and functional features enhances the diagnostic performance, making the proposal a reliable noninvasive diagnostic tool for renal tumors.

Novel MRI-Based CAD System for Early Detection of Thyroid Cancer Using Multi-Input CNN.

Early detection of thyroid nodules can greatly contribute to the prediction of cancer burdening and the steering of personalized management. We propose a novel multimodal MRI-based computer-aided diagnosis (CAD) system that differentiates malignant from benign thyroid nodules. The proposed CAD is based on a novel convolutional neural network (CNN)-based texture learning architecture. The main contribution of our system is three-fold. Firstly, our system is the first of its kind to combine T2-weighted MRI and apparent diffusion coefficient (ADC) maps using a CNN to model thyroid cancer. Secondly, it learns independent texture features for each input, giving it more advanced capabilities to simultaneously extract complex texture patterns from both modalities. Finally, the proposed system uses multiple channels for each input to combine multiple scans collected into the deep learning process using different values of the configurable diffusion gradient coefficient. Accordingly, the proposed system would enable the learning of more advanced radiomics with an additional advantage of visualizing the texture patterns after learning. We evaluated the proposed system using data collected from a cohort of 49 patients with pathologically proven thyroid nodules. The accuracy of the proposed system has also been compared against recent CNN models as well as multiple machine learning (ML) frameworks that use hand-crafted features. Our system achieved the highest performance among all compared methods with a diagnostic accuracy of 0.87, specificity of 0.97, and sensitivity of 0.69. The results suggest that texture features extracted using deep learning can contribute to the protocols of cancer diagnosis and treatment and can lead to the advancement of precision medicine.

Bone-related disorders of the jaw: A clinico-radiological diagnostic algorithm.

Bone-related disorders of the jaw (BRDJ) include a spectrum of non-neoplastic and neoplastic lesions of the maxillofacial region that have been recently classified into fibro-osseous lesions, giant cell lesions and osseous tumours. The histopathological features of BRDJ can be similar and overlie each other. Imaging is important in order to reach a specific diagnosis. However, the appearance of BRDJ on imaging is non-specific in some cases. Computed tomography (CT) and magnetic resonance imaging (MRI) are used for accurate localisation, characterisation of the tumour matrix, delineation of the lesion extension and establishment of the relation of BRDJ to the surrounding structures. Imaging is usually done to detect the relationship with the adjacent surrounding vital structures and to diagnose aggressive forms, malignant transformation and associated syndromes. The correlation of the demographic findings, the location and the clinical presentations with the imaging features are important for the diagnosis of BRDJ. The proposed clinico-radiological diagnostic algorithm with CT and MRI helps a specific diagnosis to be reached in some cases.

Differentiation malignant from benign parotid tumors in children with diffusion-weighted MR imaging.

PURPOSE: To differentiate pediatric solid malignant from the benign parotid tumors with diffusion-weighted MR imaging (DWI). MATERIALS AND METHODS: A retrospective study comprising 38 children with parotid tumors (21 boys and 17 girls aged from 2 months to 17 years) was conducted using (DWI) of the parotid gland. Apparent diffusion coefficient (ADC) maps were generated. The ADC value of the parotid tumors was calculated. RESULTS: The mean ADC value of malignant parotid tumors (1.08 ± 0.1, 1.04 ± 0.1 × 10-3mm2/s) was significantly lower [P = 0.001] than that of benign lesions (1.69 ± 0.2, 1.72 ± 0.3 × 10-3mm2/s). A threshold of ADC of 1.40, 1.33 × 10-3mm2/s was used for differentiating malignant parotid tumors from benign lesions and led to the best results of the area under the curve of 0.940, 0.929, accuracy of 86, 89%, sensitivity of 94, 94%, specificity of 80, 85%, negative predictive value of 94.1, 94.4%, and positive predictive value of 81, 85%. There was insignificant difference in ADC values of malignant lesions (P = 0.23, 0.30) as well as within benign lesions (P = 0.25, 0.08). CONCLUSION: DWI is an innovative anticipating imaging technique that can be used in the differentiation of pediatric solid malignant parotid tumors from benign lesions.

Arterial spin labeling and diffusion-weighted MR imaging: Utility in differentiating idiopathic orbital inflammatory pseudotumor from orbital lymphoma.

PURPOSE: To assess arterial spin-labeling (ASL) and diffusion-weighted imaging (DWI) and in combination for differentiating between idiopathic orbital inflammatory pseudotumor (IOIP) and orbital lymphoma. MATERIAL AND METHODS: A retrospective study was done on 37 untreated patients with orbital masses, suspected to be IOIP or orbital lymphoma that underwent ASL and DWI of the orbit. Quantitative measurement of tumor blood flow (TBF) and apparent diffusion coefficient (ADC) of the orbital lesion was done. RESULTS: There was a significant difference (P = 0.001) in TBF between patients with IOIP (n = 21) (38.1 ± 6.2, 40.3 ± 7.1 ml/100 g/min) and orbital lymphoma (n = 16) (55.5 ± 7.1, 56.8 ± 7.9 ml/100 g/min) for both observers respectively. Thresholds of TBF used for differentiating IOIP from orbital lymphoma were 48, 46 ml/100 g/min revealed area under the curve (AUC) of (0.958 and 0.921), and accuracy of (86% and 83%) for both observers respectively. There was a significant difference (P = 0.001) in ADC between patients with IOIP (1.04 ± 0.19, 1.12 ± 0.23 × 10-3 mm2/s) and orbital lymphoma (0.69 ± 0.10, 0.72 ± 0.11 × 10-3 mm2/s) for both observers respectively. Thresholds of ADC used for differentiating IOIP from orbital lymphoma were 0.84 and 0.86 × 10-3 mm2/s with AUC of (0.933 and 0.920), and accuracy of 89% and 90% for both observers respectively. The combined TBF and ADC used for differentiating IOIP from orbital lymphoma had AUC of (0.973 and 0.970) and accuracy of (91% and 89%) for both observers respectively. CONCLUSION: TBF and ADC alone and in combination are useful for differentiating IOIP from orbital lymphoma.

Peripheral Nerve Sheath Tumors of Head and Neck: Imaging-Based Review of World Health Organization Classification.

We aim to review the imaging appearance of peripheral nerve sheath tumors (PNSTs) of head and neck according to updated fourth edition of World Health Organization classification. Peripheral nerve sheath tumor can be sporadic or associated with neurofibromatosis type 1, neurofibromatosis type 2, and schwannomatosis. Schwannoma is the most common benign PNST that can be intracranial or extracranial and appears heterogeneous reflecting its histologic composition. Melanotic schwannoma is a different entity with high prediction of malignancy; it shows hypointense signal on T2-weighted image. Neurofibroma can present by localized, plexiform, or diffuse lesion. It usually appears homogeneous or shows a characteristic target sign. Perineurioma can be intraneural seen with the nerve fiber or extraneural appearing as a mass. Solitary circumscribed neuroma and neurothekeoma commonly present as dermal lesions. Nerve sheath myxoma may exhibit high signal on T1 weighted image. Benign triton tumors can be central, aggressive lesion, or peripheral nonaggressive lesion. Granular cell tumor shows hypointense signal on T2 weighted image. Neuroglial heterotopia most commonly occurs in the nasal cavity. Ectopic meningioma arises from ectopic arachnoid cells in the neck. In hybrid PNST, combined histological features of benign PNST occur in the same lesion. Malignant PNSTs are rare with an aggressive pattern. Computed tomography and magnetic resonance imaging are complementary studies to determine the location and extent of the tumor. Advanced magnetic resonance sequences, namely, diffusion-weighted imaging and dynamic contrast enhancement, can help in differentiation of benign from malignant PNST.

Assessment of Diffusion Tensor Imaging Parameters of Hepatic Parenchyma for Differentiation of Biliary Atresia from Alagille Syndrome.

OBJECTIVE: To assess diffusion tensor imaging (DTI) parameters of the hepatic parenchyma for the differentiation of biliary atresia (BA) from Alagille syndrome (ALGS). MATERIALS AND METHODS: This study included 32 infants with BA and 12 infants with ALGS groups who had undergone DTI. Fractional anisotropy (FA) and mean diffusivity (MD) of the liver were calculated twice by two separate readers and hepatic tissue was biopsied. Statistical analyses were performed to determine the mean values of the two groups. The optimum cut-off values for DTI differentiation of BA and ALGS were calculated by receiver operating characteristic (ROC) analysis. RESULTS: The mean hepatic MD of BA (1.56 ± 0.20 and 1.63 ± 0.2 × 10-3 mm²/s) was significantly lower than that of ALGS (1.84 ± 0.04 and 1.79 ± 0.03 × 10-3 mm²/s) for both readers (r = 0.8, p = 0.001). Hepatic MD values of 1.77 and 1.79 × 10-3 mm²/s as a threshold for differentiating BA from ALGS showed accuracies of 82 and 79% and area under the curves (AUCs) of 0.90 and 0.91 for both readers, respectively. The mean hepatic FA of BA (0.34 ± 0.04 and 0.36 ± 0.04) was significantly higher (p = 0.01, 0.02) than that of ALGS (0.30 ± 0.06 and 0.31 ± 0.05) for both readers (r = 0.80, p = 0.001). FA values of 0.30 and 0.28 as a threshold for differentiating BA from ALGS showed accuracies of 75% and 82% and AUCs of 0.69 and 0.68 for both readers, respectively. CONCLUSION: Hepatic DTI parameters are promising quantitative imaging parameters for the detection of hepatic parenchymal changes in BA and ALGS and may be an additional noninvasive imaging tool for the differentiation of BA from ALGS.