Current Medical Imaging - Volume 14, Issue 3, 2018

Background: Toxic and metabolic encephalopathies are easily misinterpreted or overlooked in daily neuroimaging practices. Aims: This review aims to summarize the imaging features of a number of acquired metabolic and toxic encephalopathies. Discussion: These conditions are not diagnosed easily. Imaging is very important in terms of diagnosis, assessment of treatment response and prediction of prognosis. Therefore, it is important for radiologists to know the imaging features of relatively frequent acquired metabolic and toxic encephalopathies. Conclusion: Integration of clinical information with the MRI findings can help physicians in diagnosis and treatment of the underlying disease.

The radiation exposure to cardiac tissues often result in severe form of cardiac injuries whose underlying mechanisms are not well understood till date. The most obvious choice to determine the extent of radiation-induced damages in cardiac tissues is via imaging. We searched the electronic database PubMed for pre-clinical as well as clinical reports pertaining to the importance of imaging modalities during radiation induced cardiac toxicity. It was observed clearly that various imaging modalities are now available for the above purpose and each having different pros and cons. Imaging modality offers non-invasive ways for the visualization of radiation induced toxic changes. The potential effects of radiation on the heart could be imaged non-invasively through echocardiography, Computed Tomography (CT), nuclear tomographic imaging, and Magnetic Resonance Imaging (MRI), each with relative strengths in assessing different parameters of radiation- induced injury. The latest in the line of various options of imaging is hybrid technology of imaging that allows functional imaging with highest resolution. The present review article is aimed to discuss all these imaging modalities with respect to their advantages and disadvantages. Also, their potential role for studying radiation-induced cardiac toxicity is discussed.

Background: Clitoris is an organ, whose only known function is sexual pleasure. Clinically, clitoris is only partially visible. Therefore medical imaging is important for studying it. Objective: Knowledge of radiologic anatomy and variations of the clitoris is useful for studying female sexual function, understanding it's pathological conditions and planning clitoral surgical interventions. Discussion: Anatomy of clitoris is complex with an external part, including the glans and a body and an internally lying part, the crura, in contact with vestibular bulbs. Ultrasound offers high spatial resolution and possibility of dynamic assessment allowing optimal exploration of the superficial parts of the organ. MRI is the imaging modality of choice for investigating anatomy of the whole organ, including its' deep-lying parts. It has excellent soft tissue contrast and the possibility of imaging in all planes. Conclusion: In this article, are presented imaging methods assessing normal clitoral anatomy and physiology, as well as the main pathological conditions of the organ as assessed by imaging.

Background: Lung cancer is the main cause of cancer death in both men and women. With the development of Computed Tomography (CT) scans technology, the detection rate of early stage lung cancer has significantly raised. The pulmonary CAD system has been a phenomenal and revolutionary step, in the early and premature detection of lung abnormalities. Discussion: In recent years Computer-Aided Detection (CADe) and Computer-Aided Diagnosis (CADx) system on CT has come to be “the second eyes” of radiologists. It can identify lung nodules on chest CT by itself, and can automatically measure nodule size, density and other information to provide a likelihood of malignancy or benignity. Conclusion: In this article we mainly reviewed the basic method and function of CAD, and its clinical application and research progres.

Background: We propose a novel global region based method for segmentation of biomedical images with a fast level set model using Kernel Fuzzy Particles Swarm Optimization (KFPSO) clustering. In the field of medical study, segmentation of biomedical images is one of the most important approaches for the diagnosis of a patient. Segmentation of these images is still a tedious task and cumbersome due to weak contrast and poor resolution of images etc. The automatic segmentation of such images is very difficult. The main reason is a large amount of inhomogeneity present in the background and foreground of real world image. The conventional methods like C-V model and Distance Regularized Level Set (DRLS) method lead to getting improper segmentation with unconvinced results. Methods: We proposed an efficient segmentation method for MRI biomedical images with level set approach using KFPSO clustering. In the pre-processing step, Kernel Fuzzy C- Means (KFCM) clustering is combined with PSO Initialization algorithm called KFPSO clustering for improving the clustering efficiency. In KFCM clustering algorithm, the initial cluster center is chosen randomly, and with the help of PSO, the optimal cluster centers are chosen. Results: The Membership Function (MF) of this algorithm is less sensitive to noise and consideration of the spatial information. In the post processing step, the resulting Kernel fuzzy PSO clustering is modified to the level set model for faster and accurate segmentation. Conclusion: The Proposed segmentation results are effective, superior and accurate compared to conventional methods. This new approach is very helpful for accurate detection of the white matter and gray matter, cancerous cells in brain and bone images.

Background: In spite of the fact that advanced neuroimaging applications are used for the evaluation of Tuberous Sclerosis (TS) patients, a few studies analyzed relationship between the measurements of DTI (diffusion tensor imaging) and neurological findings. Objectives: Evaluate DTI properties of cortical tubers and white matter lesions in TS, and analyze whether there was a correlation between DTI findings and neurological findings. Materials and Methods: MRI and DTI were performed on 31 subjects with TS. DTI findings of subjects with TS were compared with those of the control group. Then, the correlation between DTI values and neurological findings was analyzed. Results: ADC values of cortical tubers and white matter lesions in subjects with epilepsy were higher than in those without epilepsy. Additionally, the MRI lesion scores showed that our subjects with epilepsy had more lesions than without epilepsy. Conclusions: DTI findings of cortical tubers and white matter lesions in TS subjects could be related to microstructural changes such as neuronal loss and the impairment of myelin integrity. We hypothesized that severity neurological symptoms may be correlated with MRI lesion load and DTI parameters.

Background: In this paper, the Stationary Wavelet Transform (SWT) together with Hidden Markov Model (HMM) were utilized for accurate prediction of epileptic seizure patterns. Tests using popular intracranial Electroencephalograph (iEEG) recordings involving 18 seizure patients of different sex, age and seizure's type indicated that the algorithm performs reasonably well by three major iEEG rhythms. Methods: Three different seizure states were considered in the investigation - (i) ictal, (ii) and preictal and, (iii) interictal. A sliding window approach with data averaging was implemented in order to avoid overlapping and ensuring balanced datasets. Meanwhile the 4th order Daubechies wavelet was utilized in signal decomposition, while machine learning was established by means of 5-state HMM classifier. During training the Wilks' lambda algorithm was invoked in order to reduce correlationship between variables by selecting those with high discriminant power. Results: The algorithm took forty-seven steps to converge, producing a subset containing 44 variables from 2560 available. Results from this study reveal that the classification after Wilks' lambda analysis was more precise compared to direct classification. Prediction analysis performed on all principle components yielded a correct classification rate of 95.1%, 95.2% sensitivity, and 97.6 % specificity. Results demonstrate that the proposed method were more accurate compared to the existing methods. Conclusion: It is shown in this paper that HMM with Wilks' lambda analysis were capable of escalating the correct classification decisions compared to direct approach. The difficulty in separating preictal from ictal rhythms is evident from the canonical plot and proven by classification analysis.

Objective: To study the difference of the Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) parameters among the primary tumor, metastatic node and peripheral normal tissue of head and neck cancer. Materials and Methods: Consecutive newly-diagnosed head and neck cancer patients with nodal metastasis between December 2010 and July 2013 were recruited, and 25 patients (8 females; 24~63, mean 43±11 years old) were enrolled. DCE-MRI was performed in the primary tumor region including the regional lymph nodes on a 3.0-T MRI system. Three quantitative parameters: Ktrans (volume transfer constant), ve (volume fraction of extravascular extracellular space) and kep (the rate constant of contrast transfer) were calculated for the largest node. A repeated-measure ANOVA with a Greenhouse-Geisser correction and post hoc tests using the Bonferroni correction were used to evaluate the differences in Ktrans, ve and kep among primary tumors, metastatic nodes and normal tissue. Results: The values of both Ktrans and ve of normal tissue differed significantly from those of nodes (both P < 0.001) and primary tumors (both P < 0.001) respectively, while no significant differences of Ktrans and ve were observed between nodes and primary tumors (P = 0.075 and 0.365 respectively). The kep values of primary tumors were significantly different from those of nodes (P = 0.001) and normal tissue (P = 0.002), while no significant differences between nodes and normal tissue (P > 0.999). Conclusion: The DCE-MRI parameters were different in the tumors, metastatic nodes and normal tissue in head and neck cancer. These findings may be useful in the characterization of head and neck cancer.

Backgroud: Lung cancer is the most common cancer in terms of both incidence and mortality. Where medical science is playing its role to overcome this deadly disease, new advancements's and research areis also going on in computer science especially in the domain of image processing to support doctors and radiologists to tackle it. Developments are going on in image processing and CAD evaluation for applications that include cancer screening, diagnosis, and image- guided intervention, and treatment. Methods: The most efficient way to stop the cancer is to detect and diagnose it at an early stage. Most of the existing CAD systems monitor the growth of lung nodules over a period of time, which is not possible at the early stage of lung cancer. In case of lung cancer treatment in Pakistan, even if the cancer is at later stages, there are no such archives in which the history of patient is maintained. So in that case, it becomes extremely important to develop such system which detects lung cancer at its early stage without depending on the requirement of patient history. Secondly, majority of the CAD systems require training prior to use and after the training, they still cannot produce satisfactory results. And the last point is most of the scanners comes with built-in software and most of the scanners do notesn't support third party software's. Results: In this study, a CAD system is proposed for the detection of malignant nodules through traditional image processing techniques fused with the techniques used by radiologists. The system goes through three main phases; pre-processing, segmentation and 3D reconstruction. In the first phase, pre-processing techniques weare used to remove unwanted information and enhance the image for further processing. During the second phase, the nodule wais detected and localized and in the last phase, 3D reconstruction of the nodule is performed for better visualization that supports the radiologist and the surgeon/doctor. At By the end of the study, we have discussed the performance of our CAD system on LIDC dataset. Discussion: This dataset consists of 1018 cases from which we randomly selected 340 cases and compared the results of our methodology using four different scenarios against studies which have used Artificial Neural Networks (ANN) and Support Vector Machine (SVM). Conclusion: The methodology used in this study, clearly outperforms in two out of the four scenarios when compared to ANN and SVM.

Background: No previous studies have reported the direct comparison between Ultrasonography (US) and Computed Tomography (CT) features of Calcified Thyroid Nodules (CTNs). Objective: This study aimed to compare the patterns and types of CTNs examined by preoperative neck US and CT. Methods: From January to June 2011, 224 patients who underwent neck US and CT before thyroid surgery were included. Out of the 224 patients, 165 had a CTN showing a clear match on US and CT. The CTN patterns were classified as follows: peripheral, central, and combined. The CTN types were classified as follows: micro-, nodular, eggshell, curvilinear, pure, and mixed. Results: Out of the 165 CTNs in 165 patients, 143 were papillary thyroid carcinomas, 2 follicular thyroid carcinomas, 7 follicular adenomas, and 13 nodular hyperplasias. The most common CTN pattern on US and CT was combined and central, respectively, and a statistical difference was observed in the CTN patterns between US and CT (p < 0.0001). In the type of CTNs, the most common type on US was microcalcification (64.2%, 106/165), whereas the prevalence rate of punctate calcification on CT was only 9.1% (15/165). A statistical difference was observed in the type of CTNs between US and CT (p < 0.0001). Conclusion: US is superior to CT in the evaluation of microcalcifications, whereas macrocalcifications showed the different features between US and CT. Recognizing the different features of CTNs on US and CT may be helpful in the evaluation of thyroid nodules.

Background: Thyroid cancer is a commonly occurred cancer in all men and women around the world. This cancer can be cured if it is timely detected by proper treatment. This paper proposes a computer aided detection and screening of thyroid cancer using Adaptive Neuro Fuzzy Inference (ANFIS) classifier. Methods: The proposed methodology has the following stages such as preprocessing, feature extraction and classification. Gaussian filter is used in the preprocessing stage to smooth the edge regions in thyroid image and further features are extracted from the preprocessed thyroid image. These extracted features are trained and classified using ANFIS classifier to classify the thyroid image into either benign or malignant. Results: The morphological operations are further applied on the classified thyroid image to segment the cancer region. The performance of the proposed thyroid cancer detection system is analyzed in terms of sensitivity, specificity and accuracy.

Background: This research presents a novel automatic approach to initialization of contour curve problem for the level set segmentation method inside liver discontinuity regions in CT 2D images. This approach allows different types of level set methods to achieve accurate results in segmenting liver regions. Methods: The proposed approach includes three steps. First, a pixel-level texture feature extraction of an abdominal CT scan using Gray Level Co-occurrence Matrices (GLCM) is performed. Second, Principal Component Analysis (PCA) classifier is used to classify the pixel texture features in abdominal CT scans to get the discontinuity regions (multiple lobes) of the liver. Finally, an initial contour curve inside discontinuous regions (lobes) of liver is generated and level set segmentation is performed. Results & Conclusion: Experimental results on abdominal CT scans demonstrate the significant performance of our approach.

Background: Cervical cancer is the second most common cancer in women around the world. It can be cured if the severity level of the cancer is in the category of mild and moderate. The surgery is required for severe case and earlier death can be prevented if timely treatment is stipulated. Methods: In this paper, a computer aided fully automatic methodology for cervical cancer detection using cervigram is proposed. The methodology has used image fusion technique to enhance the contrast level of the cervical image. Then, features are extracted and classified by Support Vector Machine (SVM) classifier to diagnose the cervical image into either normal or malignant. Results: The performance of the proposed cervical cancer diagnosing system is analyzed in terms of sensitivity, specificity and accuracy.

Background: Highly advanced and sophisticated imaging modality, Cardiac Magnetic Resonance (CMR) images are referred to examine the cardiac morphology and its function. Methods: In this work, the main aim is to develop a hybrid segmentation method for automatic segmentation of both left, right ventricles from short axis CMR images. In the proposed hybrid segmentation method, Fast Adaptive K-Means (FAKM) clustering method is used to locate the ventricles which are further segmented by Distance Regularized Level Set Evolution (DRLSE) method. Results: The validation parameters show that the segmentation by proposed hybrid method is better than hybrid methods like Gaussian mixture model with dynamic programming and semi-automatic method. Discussions: Further, FAKM hybrid method is evaluated based on End Systolic Volume (ESV), End Diastolic Volume (EDV) and Ejection Fraction (EF). Conclusion: The analytical result shows that the hybrid method of FAKM with DRLSE gives faster and better results.

Objective: Numerical simulations and experiments were performed to compare eight pure mathematical models for fitting the contrast agent concentration curves (C(t)) obtained from dynamic contrast enhanced (DCE) MRI data. Methods: For simulations, randomly generated pharmacokinetic parameters (Ktrans and ve) were used to calculate the C(t) using the standard Tofts model of DCE-MRI. For experiments, DCE-MRI data of the Copenhagen rats with implanted prostate tumors on the hind limb were acquired with a temporal resolution of ~5 sec at 4.7 Tesla small animal scanner. A total of eight pure mathematical models, including empirical mathematical models with three (EMM3), four (EMM4), and five parameters (EMM), a modified logistic model (MLM), a modified sigmoidal function (MSF), the Weibull model, an extended phenomenological universalities (EU1) and a 5th order of polynomial (POLY5) were compared to fitting the C(t). The normalized root mean square errors (NRMSEs) were calculated to measure the goodness of fits. Results: The results showed that the EMM provided the best fitting to C(t) among eight models. For most of the experiment cases, the four-parameter models had significantly smaller errors (p < 0.05) than the three-parameter models. Conclusion: The pure mathematical models were not equal even if they had the same number of parameters. The EMM model could be used to accurately fit a variety of C(t).

Background: Medical ultrasonic images are usually degraded by a special kind of noise called ‘speckle’. The speckle noises usually have an effect more on edges and fine details of an ultrasound images which lead to reduction in their contrast resolution consequently create difficulties in the diagnosis of illnesses. Methods: In this paper, to reduce the speckle noise of medical ultrasound image, we have proposes a denoising approach by using ‘discrete shearlet transform’ based on pseudo-polar fast Fourier transform. The mathematical structure of present method is briefly discussed. To illustrate the efficiency of proposed approach, the experimental results of synthesis of some real Ultrasound images are considered. Results: Experimental results illustrate that proposed approach can obtain better performance in terms of Peak Signal To Noise Ratio (PSNR) for ultrasound image denoising. Our numerical tests include a series of computer-simulated and in MATLAB experiments.

Background: Schwannomas develop from schwann cells of peripheral nerve sheaths. Schwannomas are slow-growing lesions. The majority of schwannomas are benign. They are often seen in the head and neck region but they can be encountered in any tissue containing peripheral nerves. Pelvic localication of schwannomas is rare. Results: In this case report we present a case of pelvic schwannoma. A 22-year-old female patient was admitted to our hospital with pelvic pain. A hypoechoic mass measuring 10 cm in diameter was found on the ultrasonographic examination. On MRI, imaging findings were compatible with schwannoma. Conclusion: Patient underwent surgery and subsquent pathological examination confirmed the diagnosis of schwannoma. Uterine and ovarian masses are the major cause of pelvic pain, but adnexal schwannomas should be kept in mind as a rare cause of pelvic pain.