Current Medical Imaging - Volume 17, Issue 8, 2021

Background: Variations of image segmentation techniques, particularly those used for Brain MRI segmentation, vary in complexity from basic standard Fuzzy C-means (FCM) to more complex and enhanced FCM techniques. Objective: In this paper, a comprehensive review is presented on all thirteen variations of FCM segmentation techniques. In the review process, the concentration is on the use of FCM segmentation techniques for brain tumors. Brain tumor segmentation is a vital step in the process of automatically diagnosing brain tumors. Unlike segmentation of other types of images, brain tumor segmentation is a very challenging task due to the variations in brain anatomy. The low contrast of brain images further complicates this process. Early diagnosis of brain tumors is indeed beneficial to patients, doctors, and medical providers. Results: FCM segmentation works on images obtained from magnetic resonance imaging (MRI) scanners, requiring minor modifications to hospital operations to early diagnose tumors as most, if not all, hospitals rely on MRI machines for brain imaging. Conclusion: In this paper, we critically review and summarize FCM based techniques for brain MRI segmentation.

The strategy used for the treatment of given brain cancer is critical in determining the post effects and survival. An oncological diagnosis of tumor evaluates a range of parameters such as shape, size, volume, location and neurological complexity that define the symptomatic severity. The evaluation determines a suitable treatment approach chosen from a range of options such as surgery, chemotherapy, hormone therapy, radiation therapy and other targeted therapies. Often, a combination of such therapies is applied to achieve superior results. Radiotherapy serves as a better treatment strategy because of a higher survival rate. It offers the flexibility of synergy with other treatment strategies and fewer side effects on organs at risk. This review presents a radiobiological perspective in the treatment of brain tumor. The cause, symptoms, diagnosis, treatment, post-treatment effects and the framework involved in its elimination are summarized.

Background: Magnetic Resonance Imaging (MRI) plays an important role in the field of medical diagnostic imaging as it poses non-invasive acquisition and high soft-tissue contrast. However, a huge time is needed for the MRI scanning process that results in motion artifacts, degrades image quality, misinterprets the data, and may cause discomfort to the patient. Thus, the main goal of MRI research is to accelerate data acquisition processing without affecting the quality of the image. Introduction: This paper presents a survey based on distinct conventional MRI reconstruction methodologies. In addition, a novel MRI reconstruction strategy is proposed based on weighted Compressive Sensing (CS), Penalty-aided minimization function, and Meta-heuristic optimization technique. Methods: An illustrative analysis is done concerning adapted methods, datasets used, execution tools, performance measures, and values of evaluation metrics. Moreover, the issues of existing methods and the research gaps considering conventional MRI reconstruction schemes are elaborated to obtain improved contribution for devising significant MRI reconstruction techniques. Results: The proposed method will reduce conventional aliasing artifact problems, may attain lower Mean Square Error (MSE), higher Peak Signal-to-Noise Ratio (PSNR), and Structural SIMilarity (SSIM) index. Conclusion: The issues of existing methods and the research gaps considering conventional MRI reconstruction schemes are elaborated to devising an improved significant MRI reconstruction technique.

Bone disease is the hallmark of multiple myeloma. Skeletal lesions are evaluated to establish the diagnosis, to choose the therapies and also to assess the response to treatments. Due to this, imaging procedures play a key role in the management of multiple myeloma. For decades, conventional radiography has been the standard imaging modality. Subsequently, advances in the treatment of multiple myeloma have increased the need for an accurate evaluation of skeletal disease. The introduction of new high performant imaging tools, such as whole-body lowdose computed tomography, different types of magnetic resonance imaging studies, and 18F-fluorodeoxyglucose positron emission tomography, replaced the conventional radiography. In this review, we analyze the diagnostic potentials, indications of use, and applications of the imaging tools nowadays available. Whole-body low-dose CT should be considered as the imaging modality of choice for the initial assessment of multiple myeloma lytic bone lesions. MRI is the gold-standard for the detection of bone marrow involvement, while PET/CT is the preferred technique in the assessment of response to therapy. Both MRI and PET/CT are able to provide prognostic information.

Embryologic developmental variants of the thyroid and parathyroid glands may cause cervical anomalies that are detectable in ultrasound examinations of the neck. For some of these developmental variants, molecular genetic factors have been identified. Ultrasound, as the first-line imaging procedure, has proven useful in detecting clinically relevant anatomic variants. The aim of this article was to systematically summarize the ultrasound characteristics of developmental variants of the thyroid and parathyroid glands as well as ectopic thymus and neck cysts. Quantitative measures were developed based on our findings and the respective literature. Developmental anomalies frequently manifest as cysts that can be detected by cervical ultrasound examinations. Median neck cysts are the most common congenital cervical cystic lesions, with a reported prevalence of 7% in the general population. Besides cystic malformations, developmental anomalies may appear as ectopic or dystopic tissue. Ectopic thyroid tissue is observed in the midline of the neck in most patients and has a prevalence of 1/100,000 to 1/300,000. Lingual thyroid accounts for 90% of cases of ectopic thyroid tissue. Zuckerkandl tubercles (ZTs) have been detected in 55% of all thyroid lobes. Prominent ZTs are frequently observed in thyroid lobes affected by autoimmune thyroiditis compared with normal lobes or nodular lobes (P = 0.006). The correct interpretation of the ultrasound characteristics of these variants is essential to establish the clinical diagnosis. In the preoperative assessment, the identification of these cervical anomalies via ultrasound examination is indispensable.

Objective: Automatic prediction of COVID-19 using deep convolution neural networks based pre-trained transfer models and Chest X-ray images. Methods: This research employs the advantages of computer vision and medical image analysis to develop an automated model that has the clinical potential for early detection of the disease. Using Deep Learning models, the research aims at evaluating the effectiveness and accuracy of different convolutional neural networks models in the automatic diagnosis of COVID-19 from X-ray images as compared to diagnosis performed by experts in the medical community. Results: Due to the fact that the dataset available for COVID-19 is still limited, the best model to use is the InceptionNetV3. Performance results show that the InceptionNetV3 model yielded the highest accuracy of 98.63% (with data augmentation) and 98.90% (without data augmentation) among the three models designed. However, as the dataset gets bigger, the Inception ResNetV2 and NASNetlarge will do a better job of classification. All the performed networks tend to over-fit when data augmentation is not used, this is due to the small amount of data used for training and validation. Conclusion: A deep transfer learning is proposed to detecting the COVID-19 automatically from chest X-ray by training it with X-ray images gotten from both COVID-19 patients and people with normal chest X-rays. The study is aimed at helping doctors in making decisions in their clinical practice due its high performance and effectiveness, the study also gives an insight to how transfer learning was used to automatically detect the COVID-19.

Background: Osteoarthritis (OA) is a common degenerative joint inflammation that may lead to disability. Although OA is not lethal, this disease will remarkably affect patient’s mobility and their daily lives. Detecting OA at an early stage allows for early intervention and may slow down disease progression. Introduction: Magnetic resonance imaging is a useful technique to visualize soft tissues within the knee joint. Cartilage delineation in magnetic resonance (MR) images helps in understanding the disease progressions. Convolutional neural networks (CNNs) have shown promising results in computer vision tasks, and various encoder-decoder-based segmentation neural networks are introduced in the last few years. However, the performances of such networks are unknown in the context of cartilage delineation. Methods: This study trained and compared 10 encoder-decoder-based CNNs in performing cartilage delineation from knee MR images. The knee MR images are obtained from the Osteoarthritis Initiative (OAI). The benchmarking process is to compare various CNNs based on physical specifications and segmentation performances. Results: LadderNet has the least trainable parameters with the model size of 5 MB. UNetVanilla crowned the best performances by having 0.8369, 0.9108, and 0.9097 on JSC, DSC, and MCC. Conclusion: UNetVanilla can be served as a benchmark for cartilage delineation in knee MR images, while LadderNet served as an alternative if there are hardware limitations during production.

Background: Dual-energy X-ray absorptiometry (DEXA) scanning has several disadvantages determining osteoporosis, especially for the degenerative spine. Introduction: This study aims to determine spinal osteoporosis in patients suffering from lumbar degenerative disease using computed tomography (CT). Methods: A total of 547 subjects that underwent DEXA and abdominal CT within a period of three months were examined retrospectively and separated into groups based on lumbar degenerative alteration on the CT scan. The subjects that showed degenerative severity at L1–L4, in at least two levels, were graded and placed in the degenerative group (Group D, n=350). In contrast, the other subjects constituted the control group (Group C, n=197). The Hounsfield unit (HU) of the vertebral body trabecular bone, the T-score, and bone mineral density (BMD) of L1–L4 and hips were determined from the CT images. CT-HU parameters for osteoporosis acquired from the control group were used to ascertain undiagnosed osteoporosis. Results: The CT-HU was positively correlated with T-score and lumbar BMD for both groups (P<0.001), while the L1–L4 correlation was higher in Group C than in Group D. Based on linear regression, the T-score and CT-HU for L1-L4 osteoporosis were 129, 136, 129 and 120 HU, respectively in Group C. Undiagnosed spinal osteoporosis was greater in Group D compared to the controls (44.2% vs. 9.6%, respectively) based on the CT-HU thresholds. Conclusion: Lumbar spine degeneration can augment BMD and T-score, resulting in the underestimation of lumbar osteoporosis. The osteoporosis threshold determined by CT-HU may be a valuable technique to determine undiagnosed spinal osteoporosis.

Background: Beh’s disease is a chronic multisystemic vasculitis affecting vessels of different sizes in various organs. Thoracic manifestations of the disease show a wide spectrum involving a variety of anatomic structures within the chest. However, pulmonary artery involvement is a typical manifestation of the disease that contributes significantly to mortality in patients. The study aimed to analyze CT features of thoracic manifestations, particularly pulmonary artery involvement, and to quantitatively assess bronchial arteries in Beh’s disease. Methods: Patients with Behçet’s disease who underwent CT scans for suspected thoracic involvement between 2010 and 2018 were included. CT findings of 52 patients were retrospectively analyzed for thoracic manifestations of the disease. Bronchial arteries were assessed regarding diameter in patients with/without pulmonary artery involvement. The pulmonary symptoms were noted. Results: Of the 52 patients, 67% had thoracic manifestations including pulmonary artery involvement, parenchymal changes, superior vena cava thrombosis, and intracardiac thrombus. Pulmonary artery involvement was observed in 50% of the cohort. Peripheral pulmonary arteries (77%) were the most commonly affected branches, followed by lobar (42%) and central (35%) pulmonary arteries. Other thoracic findings were significantly correlated with pulmonary artery involvement (p<0.05). Compared to patients without pulmonary artery involvement, those with pulmonary artery involvement had a higher bronchial artery diameter (p<0.05) and occurrence rate of dilated bronchial arteries. Conclusion: Involvement of peripheral pulmonary arteries is frequently encountered in Beh’s disease and it can resemble pulmonary nodules. Dilated bronchial arteries, which can be observed in cases of pulmonary artery involvement, should be considered in patients with hemoptysis.

Background: Contrast-enhanced ultrasound (CEUS) can provide more improved images of renal blood flow and much more information of both macro- and microcirculation of the kidney as compared to Doppler US. Objective: To investigate the usefulness of CEUS by analyzing differences in perfusion-related parameters among the three chronic kidney disease (CKD) subgroups and the control group. Methods: Thirty-eight patients with CKD and 21 controls who were age-matched (20−49 years) were included. Included CKD patients were stratified into three groups according to their eGFR: group I, eGFR ≥ 60 ml/min/1.73 m2 (GFR category I and II); group II, 30 ml/min/1.73 m² ≤ eGFR < 60 ml/min/1.73 m² (GFR category III); and group III, eGFR < 30 ml/min/1.73 m² (GFR category IV and V). Comparisons with the controls (eGFR > 90 ml/min/1.73 m²) were performed. Real-time and dynamic renal cortex imaging was performed using CEUS. Time-intensity curves and several bolus model quantitative perfusion parameters were created using the VueBox® quantification software. We compared the parameters among the CKD subgroups and between the CKD and control groups. Results: Eight patients were included in group I, 12 patients in group II, and 18 patients in group III. Significant differences were noted in the wash-in and wash-out rates between the CKD and control groups (p = 0.027 and p = 0.018, respectively), but not between those of the CKD subgroups. There were no significant differences of other perfusion parameters among the CKD subgroups and between the CKD and control groups. Conclusion: A few perfusion related CEUS parameters (WiR and WoR) can be used as markers of renal microvascular perfusion relating renal function. CEUS can effectively and quantitatively exhibit the renal microvascular perfusion in patients with CKD as well as normal control participants.

Objective: To compare conventional sensitivity encoding turbo spin-echo (SENSE-TSE) with compressed sensing plus SENSE turbo spin-echo (CS-TSE) in lumbar vertebrae magnetic resonance imaging (MRI). Methods: This retrospective study of lumbar vertebrae MRI included 600 patients; 300 patients received SENSE-TSE and 300 patients received CS-TSE. The SENSE acceleration factor was 1.4 for T1WI, 1.7 for T2WI, and 1.7 for PDWI. The CS total acceleration factor was 2.4, 3.6, 4.0, and 4.0 for T1WI, T2WI, PDWI sagittal, and T2WI transverse, respectively. The image quality of each MRI sequence was evaluated objectively by the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) and subjectively on a five-point scale. Two radiologists independently reviewed the MRI sequences of the 300 patients receiving CS-TSE, and their diagnostic consistency was evaluated. The degree of intervertebral foraminal stenosis and nerve root compression was assessed using the T1WI sagittal and T2WI transverse images. Results: The scan time was reduced from 7 min 28 s to 4 min 26 s with CS-TSE. The median score of nerve root image quality was 5 (p > 0.05). The diagnostic consistency using CS-TSE images between the two radiologists was high for diagnosing lumbar diseases (Κ > 0.75) and for evaluating the degree of lumbar foraminal stenosis and nerve root compression (Κ = 0.882). No differences between SENSE-TSE and CS-TSE were observed for sensitivity, specificity, positive predictive value, or negative predictive value. Conclusion: CS-TSE has the potential for diagnosing lumbar vertebrae and disc disorders.

Background: According to neuroradiological findings, empty sella seems to be deprived of pituitary tissue in sella turcica. Changing size of the pituitary volume is closely related to the occurrence of primary empty sella. The aim of the study is to determine pituitary dysfunction in patients with partial or total primary empty sella and the significance of pituitary volume measurements in these patients. Methods: This study was designed retrospectively. 67 patients (55 females, 12 males) diagnosed with primary empty sella syndrome between the years of 2015-2019 were included in the study. Patients were divided into two groups: partial (PES) and total (TES) empty sella by magnetic resonance imaging (MRI). Basal anterior pituitary and its hormones were assessed. We also included 26 healthy control subjects (19 females, 7 males) to compare the differences in pituitary volumes. Volumes were measured by using Osirix Dicom Viewer (Pixmeo SARL, Geneve, Swiss) in 3.0 Tesla scanner MRI. Results: 82.1% (n=55) of all patients were PES and the others were (n=12) TES. Hypopituitarism, known as one or more pituitary hormones deficiency, was found in 12 patients (17.9%). While 9 of them had total PES, the others had partial PES. Secondary adrenal insufficiency and gonadotropin deficiency were more prevalent in patients with TES. Mean volume measurements of patients with TES, PES and healthy subjects were 0.23±0.17, 0.35±0.15, 0.54±0.17 cm3, respectively. Except for IGF1 values (p=0.026), there was not any significant correlation found between the anterior pituitary hormones and volume measurements. Conclusion: Although volume measurement has helped in the diagnosis of pituitary empty sella (partial or total), it does not seem to have any significant correlation with pituitary secretory function.

Introduction: Carotid cavernous fistulae (CCF) are rare, and they occur when there is a communication between the internal carotid artery (ICA) and cavernous sinus. These lesions are associated with blunt or penetrating traumatic injuries of the carotid arteries. We present the first cases of cavernous dural arteriovenous fistulae (cDAVF) in the middle meningeal artery (MMA) after the treatment of direct CCF in the ICA with Willis-covered stents (WCSs). Case Presentation: Our patients comprised 22 and 50-year-old males with histories of head injuries months before admission at our facility. In both patients above, cerebral angiography revealed fistulae in the right ICA and left ICA, respectively. They were treated with WCSs via the trans-artery endovascular route. In both cases, the treatments were not in the way attempted via the MMA. Subsequently, they developed cDAVF in the middle meningeal artery (MMA), which were treated with Onyx Liquid Embolic System (Onyx HD-500) (Covidien / ev3 Neurovascular) and conservatively, respectively. Conclusion: These are the first cases in whom WCSs for the management of direct CCF resulted in cDAVF at the MMA. The WCSs inside the ICA could have resulted in the cDAVF via unknown mechanisms but not iatrogenic.

Introduction: Endovascular therapy (EVT) for intracranial arterial aneurysms is depicted with several complications. Very recently, delayed non-ischemic cerebral enhanced (NICE) lesions have been identified as a rare complication associated with EVT. This complication always stands a higher chance of being missed in asymptomatic patients. We report a case of multiple NICE lesions in a known chronic hepatitis B infection and chronic gastritis patient with left internal carotid aneurysm (ICA) treated with detachable coils. Case Presentation: A 52 years old female with left ICA was treated with detachable coils via the endovascular route. Three weeks after the operation, she presented with numbness of her right limbs which was persistent and waked her up from sleep each night. She admitted skin allergies after wearing metals except for gold and silver since childhood. MRI revealed multiple abnormal lesions in the left temporal lobe, hippocampus, insula, and parietal lobe and some perifocal edema which were consistent with the diagnosis of delayed NICE lesions. Conclusion: It is very important to report the occurrences of these lesions in literature because of their allergic origin. We advocate that allergy to metals especially those used in coating endovascular equipment should be evaluated before every EVT for intracranial aneurysms.

Introduction: Osteopetrosis is an uncommon skeletal disorder characterized by generalized sclerosis of bones due to defective osteoclast function. A wide variation in clinical severity of the disease has been observed. Radiographic features and genetic testing are commonly used to diagnose the condition. Case Presentation: In the present study, we present a case of an extremely rare, atypical and genetically- undetermined form of Osteopetrosis. Conclusion: This patient had some clinical and radiological features of craniometaphyseal dysplasia along with atypical radiological signs of osteopetrosis.