Current Medical Imaging Reviews (v.12, #1)

Preface by E. Edmund Kim (1-1).

Meet Our Editorial Board Member by Franca Podo (2-3).

Segmentation of Brain Regions by Integrating Meta Heuristic Multilevel Threshold with Markov Random Field by Palani T. Krishnan, Parvathavarthini Balasubramanian, Chitra Krishnan (4-12).
Image segmentation is a method of delineating prominent structures in an input image for post processing such as texture based analysis, feature extraction, selection, and classification. Various medical applications rely on efficient image segmentation algorithms for disease diagnosis and management. In this work, autonomous segmentation of brain regions of Magnetic Resonance Images (MRI) is attempted for neuroimaging applications. It is carried out by combining heuristic based image segmentation with stochastic modeling. Initially, Particle Swarm Optimization (PSO) algorithm is used to identify ideal intensity thresholds. Labeling priors from PSO are derived for the Markov random field. Markov Random Field (MRF), a probabilistic approach is used to improve the partitioning of the initial segmented image obtained by the multilevel threshold technique. The efficacy of the segmentation procedure is improved by refining the obtained apriori information by Maximum a posteriori (MAP) estimation of the MRFMAP model. By this approach, the spatial information is incorporated into the segmentation process using MRF. A new metaheuristic MRF image segmentation technique is proposed here to take advantage of both the methods. Performance assessment of the proposed method is carried out using a numerical metric that evaluates the silhouette index of the estimated clusters. Experiments conducted on different MRI datasets show the proposed methodology produces an average improvement in cluster classification of 4.42% in terms of silhouette index for clinical datasets.

A Survey of PET Image Segmentation: Applications in Oncology, Cardiology and Neurology by Abir Baazaoui, Walid Barhoumi, Ezzeddine Zagrouba, Rostom Mabrouk (13-27).
Positron Emission Tomography, which is a functional imaging technique, measures in three-dimension the bio-distribution of a radiotracer in a specific organ or tissue. Thanks to tracer characteristics, the PET imaging was successfully experimented into several applications in oncology, cardiology and neurology for clinical and research trials. The segmentation of PET image is a mandatory step in all PET applications since it allows to relay imaged tracer uptake within a region of interest to its underlying biology. However, manual segmentation was limited by its time consuming, labor intensive and its high intra- and inter-operator variability. Therefore, several automated PET image segmentation methods were developed. In this paper, we presented the most relevant methods in the literature including thresholding-based methods of static PET images, deformable models for cardiac PET studies and mono and multi-modal segmentation methods for brain PET images.

Content Based Medical Image Retrieval System Based on Generalized Gamma Distribution and Feature Matching Methodology by Telu V. Madhusudhanarao, Sanaboina P. Setty, Yarramalle Srinivas (28-35).
Medical imaging is an area of image processing which concerns about the study of diseases. Medical imaging technologies have been improved significantly as a result of recent technological developments. However, these developments could not reach the level of expectations due to the lack of efficient radiologists and Specialized Doctors at remote areas, which in turn became a problem of concern for identifying the diseases and imparting the treatment to the patients residing at remote areas. This paper addresses the issue by presenting an approach for delivering effective treatment to the people living at rural regions using Content Based Medical Image Retrieval (CBMIR) system. The results derived are tested using metrics like Precision and Recall. The relevant images retrieved based on the developed model are evaluated for efficiency using Quality metrics and are compared with that of the existing models based on the Gaussian Mixture Model and Skew Gaussian Mixture model.

Developing an Automatic Vision based Abdominal Muscle Extraction and Analysis Method from Ultrasonography by Kwang B. Kim, Hyun J. Park, Doo H. Song, Byung-Kwan Choi (36-42).
Analyzing abdominal muscles and measuring useful associated morphological features is important in many clinical researches. While ultrasonography is a non-invasive reliable tool for such tasks, it may cause the experimenter dependent subjective diagnosis thus a computer vision based automatic muscle detector/analyzer is much needed in this area. In this paper, we propose such an automatic vision based method using a series of image processing algorithms. The novelty of our method is to extract internal oblique muscle from abdominal ultrasonographic image which was excluded in previous study due to their irregular features. Previously, we used Mask searching method to restore vague part of abdominal image but the third layer of muscle (transverse abdominis) was not clearly extracted because of the image distortion in the process. In order to analyze muscle morphometric features like the thickness, the second layer (internal oblique muscle) should also be extracted correctly thus we develop a new muscle extraction process that includes extracting the second layer by using unsharp masking. Extraction of transverse abdominis is also improved by developing a new data structure Both-Map in candidate search process. In that process, we save the morphological features of initially extracted muscle area and later such information is used to restore the fascia area with various image processing techniques to extract target muscle accurately. The effectiveness of the proposed method is verified by the practical diagnostic field of rehabilitation in the extraction accuracy and the magnitude of the muscle thickness measurement error that lies within 0.02cm in more than 60% of cases used in the experiment.

A Novel Pigeon Inspired Optimization in Ovarian Cyst Detection by Saranya Rajendran, Uma M. Sankareswaran (43-49).
Follicular cyst is characterized by the fluid filled sac presence in the female ovary. Ultrasound imaging system is the one commonly used for this cyst diagnosis. In this system, transvaginal ultrasound is used to take a look into women's reproductive system, the uterus and ovaries. Presently, while scanning, the radiologists manually trace the details of the follicular cysts, its number and size which is painful for the patients. In this paper, a novel optimization technique called Pigeon Inspired Optimization (PIO) algorithm is proposed to obtain the optimal threshold value for automatic detection of follicular cyst from the ovarian image and extract it features. The proposed method effectively obtains the threshold value by maximizing the between class variance of the modified Otsu method. The automatic follicular cyst detection system proposed in this paper reduces the error in manual detection and time taken for diagnosis. The proposed PIO algorithm has been compared with Invasive Weed Optimization (IWO). The experimental results show that the proposed method finds the better solution and converges faster than the IWO.

Posterior reversible encephalopathy syndrome (PRES) refers to a clinical and radiologic entity with diverse clinical causes. Patients present with a variety of symptoms ranging from headache, altered mental status, seizures and vision abnormalities to loss of consciousness. In cases with severe clinical manifestations, such as coma and/or status epilepticus, admission to the intensive care unit may be required. PRES is usually characterized by altered signal intensity in subcortical white matter of posterior cerebral hemispheres in magnetic resonance imaging (MRI) studies and resolve in weeks with appropriate treatment. Diagnosis depends on combination of suggestive clinical findings and radiological features. With increasing experience on PRES, atypical imaging features are described in case series. In this pictorial review, wide imaging feature spectrum of PRES is illustrated including unusual locations and atypical manifestations. Since MRI contributes to an essential part of the diagnosis, atypical imaging features of this syndrome should be well known by physicians and radiologists in order to recognize and treat it immediately. In suitable cases with atypical radiological features in the absence of classical findings, diagnosis of PRES should be kept in mind to avoid delay in diagnosis and hence, permanent neurological sequela.

Effect of Magnetic Resonance Applications on Dental Amalgam Phase Changes by Meryem T. Alkurt, Elif Sadik, Ilkay Peker, Mehmet Cakmak (59-66).
Aim: The aim of this study was to examine the potential for low- versus high-field strength magnetic resonance applications to effect phase changes in high-copper dental amalgam as detected by X-ray diffraction (XRD) analysis. Materials and Methods: Disk-shaped samples (5 x 1 mm2) of amalgam filling were prepared (n = 90) and were thermocycled for 1000 cycles. The samples were then divided into three groups that were exposed to a 0.2 tesla or a 1.5 tesla magnetic field, or received no magnetic field exposure as a control. The samples were subsequently examined by XRD for phase determination 1, 7, and 30 days later. Results: The relationships between the gama, gama1, and eta phases, as well as the mercury peak intensities, were statistically analyzed using analysis of variance and the Kruskal Wallis test. No statistically significant differences were observed (p > 0.05). There were also no significant time-dependent differences observed between the gama, gama1, and eta phases, or in the mercury peak intensities, of the groups, according to the Friedman test (p > 0.05). Conclusion: The results of this study indicate that exposure to a magnetic field via magnetic resonance imaging does not affect the structure of dental amalgam.

Synthesis of Fluorine-18-Labelled Choline (18F-Fluorocholine): Towards an Early and Accurate Management of Prostate Cancer in Malaysia by Hishar Hassan, Suharzelim A. Baker, Khairul N. C. A. Halim, Jaleezah Idris, Fathinul F. A. Saad, Abdul J. Nordin (67-74).
Prostate cancer is ranked fourth among the most prevalent cancers in men in Malaysia. It is anticipated that the number of prostate cancer sufferers' will increase in future. With the emergence of reputable imaging tracers such as fluorine-18-labelled choline (18F-fluorocholine) and gallium-68 labelled prostate specific membrane antigen (68Ga-PSMA) for the diagnosis of prostate cancer in positron emission tomography / computed tomography (PET/CT) modality, the challenges in the staging and detection accuracy would promise a better management strategy for patients. This article presents the synthesis of 18F-fluorocholine and a convenient method for quality control analysis of 18F-fluorocholine. In addition, the aim of this research work is to assist local Good Manufacturing Practice (GMP) radiopharmaceutical laboratories that routinely produce 18F-fluorodeoxyglucose (18F-FDG), to start producing 18F-fluorocholine as a tracer for prostate cancer imaging.