Patient Magnetic Resonance Research Articles

Is JAK effective in treating recurrent SAPHO syndrome? TwHF might be a good choice.

Recently, JAKi has also been widely proved to be an effective alternative to conventional treatment for Synovitis acne pustulosis-hyperostosis-osteitis (SAPHO) cases, after failure of multiple drugs including those described above. But what to do when all these treatments fail? We report a case of remission from Tripterygium wilfordii Hook (TwHF) treatment. The patient was treated with nonsteroidal anti-inflammatory drugs, oral prednisone, minocycline, bisphosphonate injection, etanercept, and tofacitinib, but the symptoms did not change significantly. Treatment with TwHF (1.0 mg/kg/day, patient weight 60 kg) was started for 24 weeks. After 50 months of unsatisfactory treatment, this patient was finally treated with herbal TwHF, and after 6 months of treatment, the patient's magnetic resonance imaging and inflammatory indexes were significantly improved, indicating that the disease had been better controlled. In this study, TwHF was successful in treating a patient with refractory SAPHO syndrome who was refractory to multiple Western medications without significant adverse effects or toxicities, but further follow-up is needed to determine long-term efficacy. More case reports as well as clinical trials are still needed to confirm whether TwHF can effectively treat refractory SAPHO syndrome.

Magnetoencephalography Atlas Viewer for Dipole Localization and Viewing.

Magnetoencephalography (MEG) is a noninvasive neuroimaging technique widely recognized for epilepsy and tumor mapping. MEG clinical reporting requires a multidisciplinary team, including expert input regarding each dipole's anatomic localization. Here, we introduce a novel tool, the "Magnetoencephalography Atlas Viewer" (MAV), which streamlines this anatomical analysis. The MAV normalizes the patient's Magnetic Resonance Imaging (MRI) to the Montreal Neurological Institute (MNI) space, reverse-normalizes MNI atlases to the native MRI, identifies MEG dipole files, and matches dipoles' coordinates to their spatial location in atlas files. It offers a user-friendly and interactive graphical user interface (GUI) for displaying individual dipoles, groups, coordinates, anatomical labels, and a tri-planar MRI view of the patient with dipole overlays. It evaluated over 273 dipoles obtained in clinical epilepsy subjects. Consensus-based ground truth was established by three neuroradiologists, with a minimum agreement threshold of two. The concordance between the ground truth and MAV labeling ranged from 79% to 84%, depending on the normalization method. Higher concordance rates were observed in subjects with minimal or no structural abnormalities on the MRI, ranging from 80% to 90%. The MAV provides a straightforward MEG dipole anatomic localization method, allowing a nonspecialist to prepopulate a report, thereby facilitating and reducing the time of clinical reporting.

Intracranial Solitary Fibrous Tumor Mimicking Meningioma.

Solitary fibrous tumor (SFT) is a clinically rare tumor derived from mesenchymal spindle cells. Central nervous system SFT represents only 0.09% of tumors occurring on the meninges, while intracranial solitary fibrous tumors (ISFT) are even more rare. Due to the similar genetic characteristics it shares with hemangiopericytoma, in 2016, the World Health Organization (WHO) classified it as a single disease called solitary fibrous tumor (SFT)/hemangiopericytoma. We reported a case of a 60-year-old female with an intracranial solitary fibrous tumor (ISFT). The patient's magnetic resonance imaging showed a mass adhering extensively to the dura mater, with adjacent thickening of the meninges and evidence of a meningeal tail sign. These radiologic findings suggested a meningioma. The tumor was surgically removed and sent for pathologic examination, which confirmed that the tumor was consistent with a solitary fibrous tumor(WHO III). Due to its rarity and similarities with meningioma, ISFT is often misdiagnosed as other types of brain tumors. ISFT is poorly understood and poses a diagnostic challenge. Our case report presents several features suggestive of meningioma, but histopathological examination after surgery confirmed the diagnosis of SFT. Knowledge of these tumors is crucial for neurosurgeons to include them in preoperative differential diagnosis.

Automatic aid diagnosis report generation for lumbar disc MR image based on lightweight artificial neural networks

Recently, artificial neural network (ANN)-based aid diagnosis methods for magnetic resonance (MR) images have made significant progress. However, due to the huge computational consumption, designing an aid diagnosis method for spinal MR images with detailed information output is still a challenging task. In this study, we propose an aid diagnosis report generation method for lumbar MR images based on lightweight ANNs, which allows radiologists to obtain intuitive diagnostic reports of lumbar discs with less computational consumption. Specifically, our method consists of three components. First, the lumbar disc pixels in the central sagittal slices of a patient's MR images would be segmented with a proposed lightweight algorithm. Then, based on the target region of the segmented lumbar disc pixels, a proposed dimensionality reduction algorithm would be performed. Finally, the diagnostic report text of the lumbar disc would be generated by a proposed lightweight text generation network according to the dimensionality reduced results. Our method could provide more meaningful support diagnosis information of lumbar discs for radiologists with less computational consumption. The experimental results show that our method could output the accurate image report text for lumbar discs with 89% accuracy of abnormal disc detection and 0.687 of BLEU-1 score, which means that our method has meaningful potential to aid diagnosis for radiologists in scenarios where computing power is limited.

Regional Cerebral Cortical Atrophy is Related to Urinary Tract Symptoms in Parkinson's Disease.

Lower urinary tract symptoms (LUTS) are the most common nonmotor symptoms usually occurring mid-stage of Parkinson's disease (PD); however, its underlying mechanisms are unknown. We aimed to assess whether corticometry or volumetry can identify a pattern of cerebral cortical changes in PD patients with LUTS. We recruited 85 idiopathic PD patients and performed corticometry and volumetry on various cortical regions using each patient's magnetic resonance imaging. To identify a correlation between the cortical thickness/volume and nonmotor symptoms scale domain 7 scores, which represent the severity of LUTS, we performed general linear model and region of interest analyses. Significant regional thinning of the left precuneus, left temporal pole, left precentral, right precuneus, and right pars opercularis was correlated with nonmotor symptoms scale domain 7 scores. We also found that cortical volumes of left precuneus and left frontal pole were inversely correlated with the severity of urinary symptoms. This study showed that the thicknesses and volumes of several cortical regions were significantly correlated with the severity of LUTS in PD patients. The findings of regional atrophy and thinning of specific cortical regions in this study provide additional evidence that multiple cortical regions, especially the precuneus cortex, not only may be involved in urinary dysfunctions of PD patients but also may help to elucidate the exact underlying mechanisms for LUTS in PD patients.

Making Magnets More Attractive

Patient comfort is an important factor of a successful magnetic resonance (MR) examination, and improvements in the patient's MR scanning experience can contribute to improved image quality, diagnostic accuracy, and efficiency in the radiology department, and therefore reduced cost. Magnet designs that are more open and accessible, reduced auditory noise of MR examinations, light and flexible radiofrequency (RF) coils, and faster motion-insensitive imaging techniques can all significantly improve the patient experience in MR imaging. In this work, we review the design, development, and implementation of these physics and engineering approaches to improve patient comfort.

Partial rupture of the distal biceps brachii tendon: a magnetic resonance imaging analysis

This study is the largest cohort of partial distal biceps brachii tendon ruptures in the literature that was analyzed according to rupture morphology of the long and short tendon heads. Patients with partial distal biceps tendon ruptures were identified using an institutional enterprise data warehouse query at a single institution. A retrospective chart review was performed to record patient demographics, past medical history, and injury mechanism for each patient. Each patient's magnetic resonance images were reviewed to determine injury patterns, specifically the extent of long head (LH) and short head (SH) tendon involvement, and associated injuries. Rupture morphologies were correlated with mechanism of injury, diabetes status, and smoking history. Seventy-seven patients were included in the study. The average age was 52 years (±11.9, range: 23-90 years); 67% were male, with an average body mass index of 28.3 (±4.3). A smoking history was reported in 31.2% of patients and 5.2% were diabetic. The partial ruptures were caused by a traumatic mechanism in 57.1% of cases, 23.4% were atraumatic, and 19.5% had an unknown mechanism. The most common injury morphology was a partial LH rupture with an intact SH tendon (33.8%). Isolated complete ruptures of the LH represented the least common injury morphology. Injury morphology was significantly related to mechanism (P < .01). Traumatic ruptures had a higher percentage of SH involvement compared with the atraumatic group (77.3% vs. 37.7%, respectively). In contrast, atraumatic ruptures involved the LH tendon in 89% of cases, with only 37.7% of cases involving the SH tendon. Patients with a history of smoking were more likely to have an atraumatic mechanism (P = .01). A history of diabetes was unrelated to mechanism (P = .20). Partial ruptures of the distal biceps brachii tendon represent a spectrum of patterns with varying involvement of the LH and SH tendons. Injury morphology was significantly related to mechanism (P < .01). LH tendon involvement was seen in 88.9% of atraumatic cases, whereas SH tendon involvement was seen in 77.3% of traumatic cases. A more comprehensive understanding of partial rupture patterns is critical to further understand the risk factors that may preclude to worse clinical outcomes, and aid in deciding which patients would benefit from operative vs. nonoperative management.

The magnetic resonance imaging appearances of the interureteric crest of the urinary bladder.

This study was devised to evaluate the imaging appearances of the interureteric crest (IUC) of the bladder on magnetic resonance imaging (MRI). The primary objective was to determine how commonly the IUC was observed on pelvic MRI examinations. The secondary objectives were to determine the average size of the IUC, its MRI signal characteristics and whether there is variation between men and women. By defining the imaging findings we hope to prevent misinterpretation of normal anatomy on MRI and, therefore, prevent unnecessary further investigations and procedures. We retrospectively reviewed 114 adult patient's magnetic resonance imaging examinations of the pelvis. Two readers independently recorded information about the presence and characteristics of the IUC with a third reader used to arbitrate in cases of disagreement. The IUC was demonstrated on MRI in 75% of patients. It was best observed on T2w sequences as a continual ridge of low signal intensity between the ureters. The mean AP diameter of the IUC at its mid-point on the sagittal images was 2.4mm. The IUC is often seen on MRI on T2w images of a non-collapsed bladder. Its characteristic appearance can be used to help the reporting radiologist confidently differentiate identify this normal structure from an area of focal bladder wall thickening that might be misinterpreted as a bladder tumor.

Source localization of high-frequency activity in tripolar electroencephalography of patients with epilepsy

ObjectiveThe objective of the study was to localize sources of interictal high-frequency activity (HFA), from tripolar electroencephalography (tEEG), in patient-specific, realistic head models. MethodsConcurrent electroencephalogram (EEG) and tEEG were recorded from nine patients undergoing video-EEG, of which eight had seizures during the recordings and the other had epileptic activity. Patient-specific, realistic boundary element head models were generated from the patient's magnetic resonance images (MRIs). Forward and inverse modeling was performed to localize the HFA to cortical surfaces. ResultsIn the present study, performed on nine patients with epilepsy, HFA observed in the tEEG was localized to the surface of subject-specific, realistic, cortical models, and found to occur almost exclusively in the seizure onset zone (SOZ)/irritative zone (IZ). SignificanceHigh-frequency oscillations (HFOs) have been studied as precise biomarkers of the SOZ in epilepsy and have resulted in good therapeutic effect in surgical candidates. Knowing where the sources of these highly focal events are located in the brain can help with diagnosis. High-frequency oscillations are not commonly observed in noninvasive EEG recordings, and invasive electrocorticography (ECoG) is usually required to detect them. However, tEEG, i.e., EEG recorded on the scalp with tripolar concentric ring electrodes (TCREs), has been found to detect narrowband HFA from high gamma (approximately 80 Hz) to almost 400 Hz that correlates with SOZ diagnosis. Thus, source localization of HFA in tEEG may help clinicians identify brain regions of the epileptic zone. At the least, the tEEG HFA localization may help determine where to perform intracranial recordings used for precise diagnosis.

Deep learning-based auto-segmentation of targets and organs-at-risk for magnetic resonance imaging only planning of prostate radiotherapy.

Magnetic resonance (MR) only radiation therapy for prostate treatment provides superior contrast for defining targets and organs-at-risk (OARs). This study aims to develop a deep learning model to leverage this advantage to automate the contouring process. Six structures (bladder, rectum, urethra, penile bulb, rectal spacer, prostate and seminal vesicles) were contoured and reviewed by a radiation oncologist on axial T2-weighted MR image sets from 50 patients, which constituted expert delineations. The data was split into a 40/10 training and validation set to train a two-dimensional fully convolutional neural network, DeepLabV3+, using transfer learning. The T2-weighted image sets were pre-processed to 2D false color images to leverage pre-trained (from natural images) convolutional layers' weights. Independent testing was performed on an additional 50 patient's MR scans. Performance comparison was done against a U-Net deep learning method. Algorithms were evaluated using volumetric Dice similarity coefficient (VDSC) and surface Dice similarity coefficient (SDSC). When comparing VDSC, DeepLabV3+ significantly outperformed U-Net for all structures except urethra (P < 0.001). Average VDSC was 0.93 ± 0.04 (bladder), 0.83 ± 0.06 (prostate and seminal vesicles [CTV]), 0.74 ± 0.13 (penile bulb), 0.82 ± 0.05 (rectum), 0.69 ± 0.10 (urethra), and 0.81 ± 0.1 (rectal spacer). Average SDSC was 0.92 ± 0.1 (bladder), 0.85 ± 0.11 (prostate and seminal vesicles [CTV]), 0.80 ± 0.22 (penile bulb), 0.87 ± 0.07 (rectum), 0.85 ± 0.25 (urethra), and 0.83 ± 0.26 (rectal spacer). A deep learning-based model produced contours that show promise to streamline an MR-only planning workflow in treating prostate cancer.

The Mixed Sellar Barrier: A New Subtype of this Novel Concept

The use of the recent concept of sellar barrier revealed that a specific group of patients were difficult to categorize. For this reason, we propose to add a new subtype: the mixed sellar barrier. The aim of this work was to define the new mixed barrier subtype and analyze this in a series of operated patients. A retrospective study was carried out. From January to December 2018, 72 patients with pituitary adenomas underwent surgery by transsphenoidal approach. Patients with more than 1 surgery were excluded. Each patient's magnetic resonance imaging (MRI) was analyzed and classified using the following criteria: strong barrier (>1 mm), weak barrier (<1 mm), and mixed barrier (<1 mm in one region and >1 mm in another part). Mixed sellar barrier is the coexistence of 2 types of sellar barrier (strong and weak). The presence of a mixed sellar barrier on MRI was associated with the presence of a mixed sellar barrier intraoperatively (P<0.0001). By using the new MRI classification that includes the mixed sellar barrier, we found a stronger statistically significant association regarding the risk of cerebrospinal fluid leak (for the extreme categories; i.e., strong and weak) compared to the original work. The new mixed sellar barrier subtype was precisely defined and illustrated. The correlation between MRI and intraoperative findings for this new subtype has been demonstrated in this study. A prospective study with a larger series of patients is required for validation.

Research and epilepsy

Advances in electroencephalography help identify the epileptic zone. It is now possible to locate the source of abnormalities on the patient's magnetic resonance imaging. For this, high resolution electroencephalogram is required. The software for this type of reconstruction are still being developed. If it is only one tool, research is progressing through simulations.

Improvement in the measurement error of the specific binding ratio in dopamine transporter SPECT imaging due to exclusion of the cerebrospinal fluid fraction using the threshold of voxel RI count.

In Japan, the Southampton method for dopamine transporter (DAT) SPECT is widely used to quantitatively evaluate striatal radioactivity. The specific binding ratio (SBR) is the ratio of specific to non-specific binding observed after placing pentagonal striatal voxels of interest (VOIs) as references. Although the method can reduce the partial volume effect, the SBR may fluctuate due to the presence of low-count areas of cerebrospinal fluid (CSF), caused by brain atrophy, in the striatal VOIs. We examined the effect of the exclusion of low-count VOIs on SBR measurement. We retrospectively reviewed DAT imaging of 36 patients with parkinsonian syndromes performed after injection of 123I-FP-CIT. SPECT data were reconstructed using three conditions. We defined the CSF area in each SPECT image after segmenting the brain tissues. A merged image of gray and white matter images was constructed from each patient's magnetic resonance imaging (MRI) to create an idealized brain image that excluded the CSF fraction (MRI-mask method). We calculated the SBR and asymmetric index (AI) in the MRI-mask method for each reconstruction condition. We then calculated the mean and standard deviation (SD) of voxel RI counts in the reference VOI without the striatal VOIs in each image, and determined the SBR by excluding the low-count pixels (threshold method) using five thresholds: mean-0.0SD, mean-0.5SD, mean-1.0SD, mean-1.5SD, and mean-2.0SD. We also calculated the AIs from the SBRs measured using the threshold method. We examined the correlation among the SBRs of the threshold method, between the uncorrected SBRs and the SBRs of the MRI-mask method, and between the uncorrected AIs and the AIs of the MRI-mask method. The intraclass correlation coefficient indicated an extremely high correlation among the SBRs and among the AIs of the MRI-mask and threshold methods at thresholds between mean-2.0D and mean-1.0SD, regardless of the reconstruction correction. The differences among the SBRs and the AIs of the two methods were smallest at thresholds between man-2.0SD and mean-1.0SD. The SBR calculated using the threshold method was highly correlated with the MRI-SBR. These results suggest that the CSF correction of the threshold method is effective for the calculation of idealized SBR and AI values.

Spontaneous Recanalization of Traumatic Transverse Sinus Occlusion despite Persistence of Depression Fracture

A 7-year-old boy was admitted to the emergency department after a closed head injury. Physical examination revealed no neurological disturbances or scalp laceration. Computed tomography revealed depressed skull fracture on the right occipital bone with multiple fracture lines over the right transverse sinus. Magnetic resonance imaging revealed right transverse sinus thrombosis, and magnetic resonance venography identified total occlusion of the right transverse sinus due to bone compression. Despite the presence of venous sinus injury secondary to a depressed skull fracture, surgery was not indicated for this patient. Despite persistence of a right occipital depression fracture identified during a three-dimensional cranial computed tomography performed in the third month following the trauma, the patient's magnetic resonance venography showed spontaneous recanalization of the right transverse sinus. It was demonstrated that venous sinus occlusion secondary to a depressed fracture could heal spontaneously and independently of bone pathology. With such characteristics, this report represents an extremely rare case.

Assessment of urethral support using MRI-derived computational modeling of the female pelvis.

This study aimed to assess the role of individual anatomical structures and their combinations to urethral support function. A realistic pelvic model was developed from an asymptomatic female patient's magnetic resonance (MR) images for dynamic biomechanical analysis using the finite element method. Validation was performed by comparing simulation results with dynamic MR imaging observations. Weaknesses of anatomical support structures were simulated by reducing their material stiffness. Urethral mobility was quantified by examining urethral axis excursion from rest to the final state (intra-abdominal pressure = 100 cmH2O). Seven individual support structures and five of their combinations were studied. Among seven urethral support structures, we found that weakening the vaginal walls, puborectalis muscle, and pubococcygeus muscle generated the top three largest urethral excursion angles. A linear relationship was found between urethral axis excursions and intra-abdominal pressure. Weakening all three levator ani components together caused a larger weakening effect than the sum of each individually weakened component, indicating a nonlinearly additive pattern. The pelvic floor responded to different weakening conditions distinctly: weakening the vaginal wall developed urethral mobility through the collapsed vaginal canal, while weakening the levator ani showed a more uniform pelvic floor deformation. The computational modeling and dynamic biomechanical analysis provides a powerful tool to better understand the dynamics of the female pelvis under pressure events. The vaginal walls, puborectalis, and pubococcygeus are the most important individual structures in providing urethral support. The levator ani muscle group provides urethral support in a well-coordinated way with a nonlinearly additive pattern.

Posterior reversible encephalopathy syndrome in Henoch-Schonlein purpura induced by oral steroid therapy and hypertension

An 11-year-old boy with Henoch-Schonlein purpura complicated by hypertension-induced encephalopathy is reported. Steroid therapy (oral prednisolone 2 mg/kg per day) was started immediately after diagnosis because of gastrointestinal involvement. A few days later the patient developed hypertension followed by generalized tonic-clonic seizures. A peripheral lesion in the posterior gray and white matter was seen on magnetic resonance imaging. The nature and location of the lesions and the normalization of the patient's magnetic resonance imaging reported a few months later was consistent with a posterior predominant parieto-occipital encephalopathy described in the literature as posterior reversible encephalopathy syndrome. The occurrence of this very rare syndrome in childhood requires close monitoring and normalization of blood pressure in patients in order to prevent central nervous system manifestations.

Cortical hot spots and labyrinths: why cortical neuromodulation for episodic migraine with aura should be personalized

Stimulation protocols for medical devices should be rationally designed. For episodic migraine with aura we outline model-based design strategies toward preventive and acute therapies using stereotactic cortical neuromodulation. To this end, we regard a localized spreading depression (SD) wave segment as a central element in migraine pathophysiology. To describe nucleation and propagation features of the SD wave segment, we define the new concepts of cortical hot spots and labyrinths, respectively. In particular, we firstly focus exclusively on curvature-induced dynamical properties by studying a generic reaction-diffusion model of SD on the folded cortical surface. This surface is described with increasing level of details, including finally personalized simulations using patient's magnetic resonance imaging (MRI) scanner readings. At this stage, the only relevant factor that can modulate nucleation and propagation paths is the Gaussian curvature, which has the advantage of being rather readily accessible by MRI. We conclude with discussing further anatomical factors, such as areal, laminar, and cellular heterogeneity, that in addition to and in relation to Gaussian curvature determine the generalized concept of cortical hot spots and labyrinths as target structures for neuromodulation. Our numerical simulations suggest that these target structures are like fingerprints, they are individual features of each migraine sufferer. The goal in the future will be to provide individualized neural tissue simulations. These simulations should predict the clinical data and therefore can also serve as a test bed for exploring stereotactic cortical neuromodulation.

Cervical transforaminal epidural steroid injections: a proposal for optimizing the preprocedural evaluation with available imaging.

Cervical transforaminal epidural steroid injection (CTFESI) has been used to treat cervical radicular pain; however, rare but serious complications such as cerebellar or spinal cord infarction have been reported. The most probable causes of the serious complications include vertebral artery trauma, spasm, or accidental arterial injection of particulate steroid. Several recommendations have been made to improve the safety of CTFESI; however, evaluation and risk assessment of the patient's anatomy by the interventionist have not been sufficiently emphasized. Significant correlations between foraminal narrowing and proximity of the vertebral artery to the target of needle have been reported. This correlation is particularly problematic for interventionists because patients considered or referred for CTFESI are more likely to have foraminal narrowing at the level concerned. Without knowing the patient's anatomy, a common practice of rotating the C-arm obliquely to obtain a full view of the target foramen may carry significant risk of needle's encounter with the vertebral artery. Risk assessment through careful preprocedural review of the patient's magnetic resonance imaging by the interventionist is a worthwhile practice to optimize safety. Special attention should be paid to the vital structures such as the vertebral artery, neural foramen, and carotid artery. A preprocedural roadmap for the safest predicted needle trajectory can be created by simulation using the patient's available magnetic resonance imaging scans. These considerations may guide and help the interventionist to minimize the risk of inadvertent needle placement involving vital structures such as the vertebral artery or carotid artery.

Design and evaluation of an image‐guidance system for robot‐assisted radical prostatectomy

WHAT'S KNOWN ON THE SUBJECT? AND WHAT DOES THE STUDY ADD?: Systems for image guidance during laparoscopic surgery can be broadly defined as systems that enable the surgeon to refer to preoperatively gathered information during the procedure. For a laparoscopic system the preoperative information can be overlaid onto the laparoscopic video screen. Examples of surgical image-guidance systems and the results of early testing are not uncommon but the technical methodologies used vary widely as do the visualisation methods. This study reports our experience of using an image-guidance system on 13 patients. Furthermore, we use previously proposed methodology to form a development and evaluation framework specific to image-guided laparoscopic radical prostatectomy. Finally, we propose that if the system development process is properly designed, it should be possible to correlate system technical parameters with clinical outcomes. We present a possible plot for the key technical parameter of accuracy. Better understanding of this correlation should enable robust development and evaluation of surgical image-guidance systems to optimise patient outcomes. To implement and test the feasibility of an image-guidance system for robot-assisted radical prostatectomy (RARP). Laparoscopic surgical outcomes may be improved through image guidance. However, to demonstrate improved outcomes rigorous evaluation techniques are required. Therefore we also present our work in establishing robust evaluation techniques. Development work used three cadavers and an anatomy phantom. The system has been used on 13 patients. During surgery the surgeon can refer to the patient's magnetic resonance imaging (collected before the operation) overlaid on the endoscopic video image. The result of the overlay process was measured qualitatively by the surgeon with reference to the desired clinical outcomes. The use of the overlay system has not resulted in any measurable change in clinical outcomes. The surgeons found the system to be a useful tool for reference during surgery. A more rigorous evaluation method is proposed that will enable on-going development. Image guidance during RARP is feasible. We propose a series of measures that will improve further development and evaluation.

Identification of brain regions responsible for Alzheimer’s disease using a Self-adaptive Resource Allocation Network

In this paper, we present a novel approach for the identification of brain regions responsible for Alzheimer's disease using the Magnetic Resonance (MR) images. The approach incorporates the recently developed Self-adaptive Resource Allocation Network (SRAN) for Alzheimer's disease classification using voxel-based morphometric features of MR images. SRAN classifier uses a sequential learning algorithm, employing self-adaptive thresholds to select the appropriate training samples and discard redundant samples to prevent over-training. These selected training samples are then used to evolve the network architecture efficiently. Since, the number of features extracted from the MR images is large, a feature selection scheme (to reduce the number of features needed) using an Integer-Coded Genetic Algorithm (ICGA) in conjunction with the SRAN classifier (referred to here as the ICGA-SRAN classifier) have been developed. In this study, different healthy/Alzheimer's disease patient's MR images from the Open Access Series of Imaging Studies data set have been used for the performance evaluation of the proposed ICGA-SRAN classifier. We have also compared the results of the ICGA-SRAN classifier with the well-known Support Vector Machine (SVM) and Extreme Learning Machine (ELM) classifiers. The study results clearly show that the ICGA-SRAN classifier produces a better generalization performance with a smaller number of features, lower misclassification rate and a compact network. The ICGA-SRAN selected features clearly indicate that the variations in the gray matter volume in the parahippocampal gyrus and amygdala brain regions may be good indicators of the onset of Alzheimer's disease in normal persons.