Computer Assistance Research Articles

A quasi-qualitative analysis of flipped classroom implementation in an engineering course: from theory to practice

Students have different learning approaches and acquire knowledge in different ways owing to their varied perceptions and grasping abilities. Treating students equally, following the traditional teacher-cantered approach, may not be effective and calls for innovations in knowledge dissemination. This article takes a student-centric approach to implement a ‘flipped classroom’ model in an engineering course for constructivism (i.e. experience-based learning), and students’ personalized learning. The performance of the flipped classroom approach is compared with the traditional lecturing approach using four lenses: students’ grades, students’ reflection using three surveys at different stages during the semester, teacher’s observation, and peer observation. In most of the existing approaches, analysis of the qualitative survey data is performed manually without computer assistance, and therefore these are criticized for being primeval and instinctive. In this research, a novel approach, based on fuzzy logic, is devised to evaluate the qualitative survey responses from the students. It is shown in this research, that the linguistic survey responses can be summarized in an index more meaningfully using a fuzzy logic-based approach. The results further showed that the flipped classroom model helped students to improve their grades and enhance engagements with their teacher and their peers. Increased interaction, during interactive class activities, was instrumental in evolving students’ problem-solving and critical analysis skills towards better learning experiences. Furthermore, students’ survey results, analyzed using the novel fuzzy indexing and a non-parametric statistical test showed that the intervention in the form of flipped classes was effective and found to be statistically significant. The findings of this study may help other academics, endeavoring for experience-based, and students’ personalized learning.

On difference sets with small $$\lambda $$

In a 1989 paper, Arasu (Arch Math 53:622–624, 1989) used an observation about multipliers to show that no (352, 27, 2) difference set exists in any abelian group. The proof is quite short and required no computer assistance. We show that it may be applied to a wide range of parameters \((v,k,\lambda )\), particularly for small values of \(\lambda \). With it, a computer search was able to show that the Prime Power Conjecture is true up to order \(2 \cdot 10^{10}\), extend Hughes and Dickey’s computations for \(\lambda =2\) and \(k \le 5000\) up to \(10^{10}\), and show nonexistence for many other parameters.

Computer-assisted femoral head reduction osteotomies: an approach for anatomic reconstruction of severely deformed Legg-Calv\xe9-Perthes hips. A pilot study of six patients

BackgroundLegg–Calvé–Perthes (LCP) is a common orthopedic childhood disease that causes a deformity of the femoral head and to an adaptive deformity of the acetabulum. The altered joint biomechanics can result in early joint degeneration that requires total hip arthroplasty. In 2002, Ganz et al. introduced the femoral head reduction osteotomy (FHRO) as a direct joint-preserving treatment. The procedure remains one of the most challenging in hip surgery. Computer-based 3D preoperative planning and patient-specific navigation instruments have been successfully used to reduce technical complexity in other anatomies. The purpose of this study was to report the first results in the treatment of 6 patients to investigate whether our approach is feasible and safe.MethodsIn this retrospective pilot study, 6 LCP patients were treated with FHRO in multiple centers between May 2017 and June 2019. Based on patient-specific 3D-models of the hips, the surgeries were simulated in a step-wise fashion. Patient-specific instruments tailored for FHRO were designed, 3D-printed and used in the surgeries for navigating the osteotomies. The results were assessed radiographically [diameter index, sphericity index, Stulberg classification, extrusion index, LCE-, Tönnis-, CCD-angle and Shenton line] and the time and costs were recorded. Radiologic values were tested for normal distribution using the Shapiro–Wilk test and for significance using Wilcoxon signed-rank test.ResultsThe sphericity index improved postoperatively by 20% (p = 0.028). The postoperative diameter of the femoral head differed by only 1.8% (p = 0.043) from the contralateral side and Stulberg grading improved from poor coxarthrosis outcome to good outcome (p = 0.026). All patients underwent acetabular reorientation by periacetabular osteotomy. The average time (in minutes) for preliminary analysis, computer simulation and patient-specific instrument design was 63 (±48), 156 (±64) and 105 (±68.5), respectively.ConclusionThe clinical feasibility of our approach to FHRO has been demonstrated. The results showed significant improvement compared to the preoperative situation. All operations were performed by experienced surgeons; nevertheless, three complications occurred, showing that FHRO remains one of the most complex hip surgeries even with computer assistance. However, none of the complications were directly related to the simulation or the navigation technique.

Dam Behavior Classification System Using K-Nearest Neighbor Based on Temporal Data At the Djuanda Dam

Dam had a vital role in the social and economic communities, including water providers for irrigation, industry, power plant, recreation, and flood control. Besides having various benefits, Dam also holds the potential of disaster. Preventive action in disaster management was necessary. Dam behavior pattern classification with computational assistance was needed to determine the results of determining accurate, fast, and efficient behavior patterns. In this research, the system made by using a K-NN Classifier based on temporal data that formed to predict the behavior patterns of dams in the Djuanda Dam. The system test results produce the best accuracy of 88% for safe labels, 82% for standby labels and 92% for alert labels with the best k value is 8.

Computational Assistant for the Assessment University Competencies in B-Learning Environments

Competency assessment is a complex problem that has been approached from multiple perspectives but remains a work in progress. This paper presents a new competency assessment model accompanied by a computational assistant that guides its implementation. The model covers seven phases of an evaluation process, beginning with the definition of the competency and ending with the feedback of evidence provided from the teacher to the students. In each phase, the assistant provides suggestions to the teacher, which are obtained through text analysis algorithms and improve as information is added. The model was validated through pre and post-test study requiring the participation of a group of university teachers. The results indicate that with the use of the model, the time invested by the teacher in evaluation tasks is reduced, the clarity and completeness of the process improves, and an integrated evaluation of generic and specific competences is achieved.

A note on a prototype system for simple computer-assisted matching of individually identified southern right whales, Eubalaena australis

A system using computer assistance in the matching of the callosity patterns of individual southern right whales is described. Whenprovided with a digitised representation of an individual whale’s callosity pattern, the prototype system produces a hierarchical output ofthe most similar patterns in the database with relatively high accuracy. A trial database of binary images of the callosity patterns of 165individually identified southern right whales was created. A further two replicates each of nine different individual whales within the trialdatabase, were then created by two different operators, producing a test set of 18 images. A software program, utilising a pattern recognitionalgorithm and incorporating a mouse driven user interface, was developed so that when provided with a binary bitmap of an individualwhale from the test set, the program compares it against a trial database of previously saved bitmaps and produces a hierarchical outputof the most similar whales, or nearest ‘matches’. For 15 of the 18 test images (83%), the system returned the correct whale as the top matchout of the 165 in the trial database. For the remaining three test images the correct whale was the second, sixth and sixteenth ranked whalein the trial database containing 165 whales. The program was successful in reducing the number of individuals required for manualcomparison to a small percentage of the total catalogue, with a high degree of accuracy, and with a significant associated time saving. Itis envisaged that the final matching will continue to be done visually by an experienced operator using the original photographs. Furtherrefinement of the system with the aim of streamlining and simplifying the input process and incorporating partial pattern recognition isintended.

Biomolecular Quantum Computation

In terms of leveraging the total power of quantum computing, the prevalent current (2020) model of designing quantum computation devices to follow the von Neuman model of abstraction is highly unlikely to be making full use of the full range of computational assistance possible at the atomic and molecular level. This is particularly the case for molecular modeling, in using computational models that more directly leverage the quantum effects of one set of molecules to estimate the behavior of some other set of molecules would remove the bottleneck of insisting that modeling first be converted to the virtual binary or digital format of quantum von Neuman machines. It is argued that even though this possibility of “fighting molecular quantum dynamics with molecular quantum dynamics” was recognized by early quantum computing founders such as Yuri Manin and Richard Feynman, the idea was quickly overlooked in favor of the more computer-compatible model that later developed into qubits and qubit processing.

A 40 years journey with fish spermatozoa as companions as I personally experienced it.

When, in the 1980s, I became interested in the spermatology of fish under the light microscope, active spermatozoa were only visible thanks to their head presenting a sort of "tremor." This situation was quite frustrating given the lack of possible information regarding the motor part called flagellum. We decided to apply simple technologies, including photography. Due to the high speed of the moving fish flagellum, the microscope illumination used a pulsed light strobe combined with a dark field microscope to record the flagellum image despite its small diameter (< 0.5 μm). Then came high-speed cinematographic microscopy up to 200 fps, as well as video cameras. At the end of the 1990s, an automatic moving object video tracking system began to be commercialized (CASA) with main advantages such as (a) a large number of cells tracked, which greatly improves statistics, (b) computer assistance allowing an automatic analysis that provides many motility parameters. Nevertheless, CASA systems are still unable to provide information about fish sperm flagella that move fast. During the 1990s, analog video camera technologies allowed acquisition of flagellum images with high resolution for detailed analysis. Since the 2000s, the use of high-speed video cameras allows the acquisition of images at a much higher resolution and frequency, up to 10,000 frames per second. Since it became possible to visualize the flagella in motion, a noble function was added to that of a propeller: that of a rudder with what a spermatozoon responds to specific signals delivered by the egg for its guidance. In the future, one can wish that an automatic flagella movement analyzer will become functional. This brief anthology puts forward the large amount of progress accomplished during past 40-year period about spermatozoa movement analysis, especially in fish.

Utility of a Computer-assisted Rod Bending System to Avoid Pull-out and Loosening of Percutaneous Pedicle Screws.

This was a retrospective observational study of a cohort of consecutive patients. To compare the influence of (1) manual and (2) computer-assisted (CA) rod bending techniques on pedicle screw pull-out resulting in loosening during rod reduction and final tightening. Our recent study showed screw pull-out during rod reduction might be a risk factor for loosening of percutaneous pedicle screws (PPSs) postoperatively, resulting in worse postoperative back pain. We retrospectively analyzed data from 53 consecutive patients who underwent minimally invasive lumbar or thoracic spinal stabilization using intraoperative computed tomography image (CT)-guided navigation with conventional manual rod bending or CA rod bending and were followed up for 1 year. Screw pull-out length was measured on axial CT images obtained immediately after screw insertion and postoperatively. Loosening of screws and clinical outcome were evaluated radiographically, clinically, and by CT 1 year after surgery. The frequencies of screw pull-out and screw loosening between the 2 rod bending techniques were compared. Lumbar pain-related factors for both groups of patients were determined preoperatively and 1 year after surgery. Overall, 360 pedicle screws were placed in the manual group and 124 pedicle screws were placed in the CA group. There was no significant difference in the mean age, sex, bone mineral density, mean stabilized length, or smoking habits of patients between the groups. The diameters, lengths, and trajectory angle (axial and sagittal) of the screws placed were not significantly different between the groups. Screw pull-out rate/length and loosening in the CA group was significantly lower than that in the manual group. Postoperative low back pain improved significantly in the CA group compared with that in the manual group. CA bending is useful to avoid PPS pull-out during rod reduction and screw loosening postoperatively. CA bending is useful to avoid PPS pull-out during rod reduction and screw loosening postoperatively. This result might have been a factor leading to reduced postoperative back pain in the CA group, however, that future studies are need to investigate this association.

Analysis of the Teaching Contents and Methods of Art Education in Higher Vocational Colleges Based on Computer-aided

At present, China’s economy is in a period of rapid development, and the traditional mode of education is no longer in line with the needs of the current society. In order to promote quality education, art teachers in higher vocational colleges should make appropriate reforms in teaching based on computer assistance. As an important part of higher education, art education in higher vocational colleges has not yet formed a complete and unique theoretical knowledge system, and is facing many practical problems. Starting from the characteristics of higher vocational colleges and their students, this paper makes a preliminary exploration on the selection and setting of teaching contents, the use and exploration of teaching methods. The teaching content of art education in higher vocational colleges should not only adapt to computer-aided, but also fully consider the characteristics of students, improve teaching methods and enhance students’ comprehensive quality.

WÜNDERLICH SYNDROME: A CASE OF HYPOVOLEMIC HEMORRHAGIC SHOCK

SESSION TITLE: Medical Student/Resident Critical Care Posters SESSION TYPE: Med Student/Res Case Rep Postr PRESENTED ON: October 18-21, 2020 INTRODUCTION: Wünderlich syndrome (WS) is a rare presentation of hypovolemic hemorrhagic shock. It is a fatal disease described as a syndrome of spontaneous non-traumatic subcapsular and retroperitoneal hemorrhage. The etiology of WS is varied, with renal causes including malignancy being the most common, followed by renal vasculature abnormalities, vasculitis, cystic rupture, pyelonephritis, and idiopathic. The appropriate treatment depends on the accuracy of diagnosis and precise determination of its cause. To our knowledge, this is the first case report of WS due to acute pyelonephritis in a patient with congenital solitary kidney and Jehovah's Witness religious beliefs which impacted his care. CASE PRESENTATION: A 77 year old male with a two day history of flank pain accentuated on the right side, fevers, and confusion presented as critically ill and requiring vasopressor support. His medical history comprises prostate cancer in remission and atrial fibrillation on aspirin. He was diagnosed clinically with pyelonephritis, and culture positive urinary tract infection and sepsis with Escherichia coli. The initial hemoglobin was of 10.3 g/dL. Computed tomography (CT) of the abdomen showed nonspecific stranding and a solitary right kidney. He clinically deteriorated prompting repeat CT imaging that showed a large right perirenal hematoma with retroperitoneal blood. He underwent emergent coil angioembolization of a hemorrhagic branch of the inferior pole renal artery. His hemoglobin of 4 g/dL recovered with erythropoietin and intravenous iron. He briefly required hemodialysis for his acute kidney injury. The patient survived and the function of his congenital solitary kidney was preserved. DISCUSSION: The classic signs of WS include Lenk’s triad of flank pain, abdominal mass, and hypovolemic shock. However, in only 20% of cases, all three symptoms present. Acute onset of flank pain is the most common symptom. Although pyelonephritis is a rare cause of WS, in our case we believe that bleeding diathesis and etiology of WS was driven by cytokine induced endothelial damage from pyelonephritis along with aspirin induced platelet dysfunction. CT is preferred for the initial imaging workup. Angioembolization is a minimally invasive treatment modality for acute hemorrhage. Exploratory laparotomy or nephrectomy is typically recommended if malignancy is suspected. CONCLUSIONS: WS requires prompt recognition to prevent death from exsanguination. Shock is relatively common with WS, however, surgical exploration is not absolutely necessary with the advent of angioembolization. The unconventional treatment method with erythropoietin instead of blood may be considered in patients with Jehovah’s Witness religious beliefs. Reference #1: Katabathina VS, Katre R, Prasad SR, Surabhi VR, Shanbhogue AK, Sunnapwar A. Wunderlich syndrome: cross-sectional imaging review. J Comput Assist Tomogr. 2011;35(4):425-33. Reference #2: Chen YC, Lin YC. Wunderlich syndrome. QJM. 2013;106(2):187-8. Reference #3: Chamarthi G, Koratala A. Wunderlich syndrome. Clin Case Rep. 2018;6(9):1901-1902. DISCLOSURES: No relevant relationships by Francois Kaleta, source=Web Response No relevant relationships by Mitra Sahebazamani, source=Web Response No relevant relationships by Pratyaksha Sankhyan, source=Web Response

ACUTE DYSPNEA ASSOCIATED WITH CRAZY PAVING APPEARANCE

SESSION TITLE: Global Case Report Posters SESSION TYPE: Global Case Reports PRESENTED ON: October 18-21, 2020 INTRODUCTION: A ‘crazy-paving’ appearance of the lungs on computed tomography scanning of the chest was first described nearly 20 years ago in patients with pulmonary alveolar proteinosis, and was thought to be characteristic of this condition. However, this pattern has subsequently been reported in a variety of pulmonary diseases and is now considered to be nonspecific. We report a case 43 yrs old middle aged lady admitted with Acute onset of breathlessness with crazy paving appearance on chest Computed tomography of chest, secondary to heart failure. CASE PRESENTATION: Middle age lady with no other comorbidities admitted with complaints of sudden onset of breathlessness since today evening. At the time of presentation to emergency room she was dyspneic, Tachypneic, Tachycardia. Her vitals were HR 102/mt, RR 36/mt,spo2 86% on Room air, Bp 180/100mmhg. She was started on high flow oxygen and nebulized medications.Cardiac examination revealed a normal S1 and diminished S2, with no murmurs or extra sounds. Auscultation of the chest revealed inspiratory crackles bilaterally. His abdominal examination was unremarkable without organomegaly. Laboratory findings revealed a normal complete blood count and differential blood count. Serum electrolytes, liver and renal function tests were all normal.A chest radiograph (figure1) demonstrated diffuse airspace opacities on both sides of lung. A CT scan of the chest (figure2) was obtained showed diffuse, multifocal, patchy, ground-glass opacities with superimposed reticulations resulting in a crazy-paving appearance.Routine 2 D echo was done, revealed Rheumatic Heart disease with Severe mitral stenosis, Tricuspid stenosis and Moderate Tricuspid regurgitation,and diagnosed as acute decompensated heart failure. NT-pro BNP was 3450pg/ml. She was started on diuretics along with other medications. Repeated x ray (figure 3)showed complete clearance of airspace opacities. DISCUSSION: A ‘crazy-paving’ appearance of the lungs on a high-resolution computed tomography (CT) scan of the chest, defined as scattered or diffuse ground-glass attenuation superimposed on a network of interlobular septal thickening and intralobular lines. Initially, this radiographic pattern was thought to be specific for alveolar proteinosis, (1) but has subsequently been reported in a variety of interstitial and airspace pulmonary disorders (2,3) Although common, congestive heart failure and cardiogenic pulmonary edema have been reported previously as a cause for crazy-paving appearance in only in few cases. (3) CONCLUSIONS: Crazy-paving pattern on CT scan, once considered to be specific for pulmonary alveolar proteinosis, is now known to be nonspecific and may be seen in association with a wide spectrum of pulmonary diseases. Reference #1: Godwin JD, Muller NL, Takasugi JE. Pulmonary alveolar proteinosis: CT findings. Radiology. 1988;169:609–13. Reference #2: Johkoh T, Itoh H, Muller NL, et al. Crazy-paving appearance at thin-section CT: Spectrum of disease and pathologic findings. Radiology. 1999;211:155–60. Reference #3: Murayama S, Murakami J, Yabuuchi H, Soeda H, Masuda K. “Crazy paving appearance” on high resolution CT in various diseases. J Comput Assist Tomogr. 1999;23:749–52. DISCLOSURES: No relevant relationships by Nagarajan Appusamy, source=Web Response

Brain Tumor Extraction from MRI Images Using MATLAB

Computerized or Automatic detection of tumors in medical images is motivated by the necessity of high accuracy when dealing with a human life. The computer assistance is also demanded in medical institutions because it could improve the results of disease identification and negative cases should be very low. So, the Processing of Magnetic Resonance Imaging (MRI) images is one of the techniques to diagnose the brain tumor. This paper describes the strategy to detect and extract brain tumor from patient’s MRI scanned images. In this the Steps includes are pre-processing, segmentation, morphological operation, watershed segmentation and calculation of the tumor area and determination of the tumor location and this Application is Developed using Matrix Laboratory (MATLAB)

Computer assistance in hip preservation surgery-current status and introduction of our system.

Preservation surgery of the hip with open or arthroscopic approach has always been challenging as complex 3-D anatomy and limited surgical access make intraoperative evaluation difficult. Recent advances in computer technology offer a wide range of innovative solutions with a goal to improve accuracy and safety of corrective procedures on human joints. The author critically reviews currently available literature in the field of computer assistance in hip preservation surgery. Basic features of unique planning software and navigation surgical system used in treatment of femoroacetabular impingement and hip dysplasia are introduced. Currently available software provides preoperative identification of hip deformity on CT-based 3-D model and planning of the surgical correction using kinematic protocols. Real-time intraoperative 3-D orientation is possible, and execution of surgical correction can be performed either with navigation of surgical tools or with printed templates. Computer assistance in hip preservation surgery is in the developing phase. First clinical experiences of its use in treatment of femoroacetabular impingement, hip dysplasia, hip tumors, and avascular necrosis of the femoral head are promising. Computer assistance has been applied for treatment of several hip disorders. Technical advances are suggested and quality basic studies and clinical trials are encouraged for the novel technology to become more user friendly and widely accepted.

Attraction in Nonmonotone Planar Systems and Real-Life Models

Let $$h:V\subset {\mathbb {R}}^{2}\longrightarrow {\mathbb {R}}^{2}$$ be an embedding. The aim of this paper is to analyze the dynamical behavior of h depending on the number of fixed points and 2-cycles, their local behaviors and the features of V. Our approach allows us to extend some celebrated results of the theory of monotone flows, namely the order interval trichotomy, for non-monotone maps. Moreover, we discuss several applications in classical models. In the particular case of the Ricker system, we recover some recent results deduced from computer assistance.

3D analysis and computer assisted reconstruction for scaphoid non-union

The odd shape of the scaphoid is a challenge to our spatial sense. Computer assistance is of an unmatched value when reconstructing a non-united scaphoid: From CT data a true 3-D-model can be generated, fully interactive; thus it can be moved, manipulated and of course also printed for hands-on experience. Comparing the virtual 3-D-models of the nonunion with the healthy contralateral scaphoid, the exact amount of the deformity is calculated which allows for the planning of an anatomically precise reconstruction of the scaphoid shape. Finally, computer generated patient specific instruments will facilitate the implementation of this planning intraoperatively. This proceeding enables us to reconstruct the non-united scaphoid markedly more accurately and with this reliably normalize wrist kinematics. Meanwhile we have applied this technique successfully in more than 50 cases of scaphoid-nonunions presenting with significant deformity.

“A tiny cog in a large machine”

Abstract Translators have worked with the assistance of computers for many years, usually translating whole texts, divided into segments but in sequential order. In order to maximise efficiency and inspired by similar moves in the tech industry and predictions for Industry 4.0, large translation companies have begun to break tasks down into smaller chunks and to rigidly define and monitor translation processes. This is particularly true of platform-mediated work, highly collaborative workflows, and multimedia work that requires near-live turnaround times. This article considers such workflows in the context of measures of job satisfaction and discussion of sustainable work systems, proposing that companies prioritise long-term returns and attempt to balance the needs of all stakeholders in a translation process. Translators and translator trainers also have a role to play in achieving this balance.

Jaw and Teeth Segmentation on the Panoramic X-Ray Images for Dental Human Identification.

Due to the damage to biometric properties in the event of natural disasters, like fire or earthquakes, it is very difficult to identify human remains. As teeth are more durable than other biometric properties, identifying information obtained from them is much more reliable. Therefore, in cases where alternative biometric properties cannot be obtained or used, information taken from teeth may be used to identify a person's remains. In recent years, many studies have shown how the identification process, previously performed manually by a forensic dental specialist, can be made faster and more reliable with the assistance of computers and technology. In these studies, the x-ray image is subdivided into meaningful parts, including jaws and teeth, and dental properties are extracted and matched. In order to extract the features accurately and ensure better matching, it is important to segment images properly. In this study, (i) lower and upper jaw and (ii) tooth separation was performed to segment panoramic dental x-ray images to assist in identifying human remains. To separate the jaws, a novel meta-heuristic optimization-based model is proposed. To separate teeth, a user-assisted, semi-automatic approach is presented. The proposed methods have been performed with a computer program. The results of the implementation of these methods of jaw and tooth separation in panoramic tooth images are encouraging.

Computer Assisted Wargame for Military Capability-Based Planning.

Capability-based planning as an approach to defense planning is an almost infinitely complex engineered system with countless nodes and layers of interdependency, influenced by state and non-state diplomatic activities, information, military and economic actions creating secondary and third order effects. The main output of capability-based planning is the set of capability requirements needed to achieve the expected end-state. One revitalized qualitative technique that allows us to gain insights into unstructured and fuzzy problems in the military is wargaming—in its simplest form this involves manual wargaming. At the same time, there has been a push to bring computer assistance to such wargaming, especially to support umpire adjudication and move more generally towards full automation of human elements in wargames. However, computer assistance in wargaming should not be pushed, regardless of cost, towards quantitative techniques. The objective complexity of a problem often does not allow us to replicate the operational environment with the required fidelity to get credible experimental results. This paper discusses a discovery experiment aiming to verify the concept of applying a qualitative expert system within computer assisted wargaming for developing capability requirements in order to reduce umpire bias and risk associated with their decisions. The innovation here lies in applying system dynamics modelling and simulation paradigms when designing the theoretical model of capability development, which forms the core of the expert system. This new approach enables qualitative comparisons between different sets of proposed capability requirements. Moreover, the expert system allows us to reveal the effects of budget cuts on proposed capability requirement solutions, which the umpire was previously unable to articulate when comparing individual solutions by relying solely on his own knowledge. Players in the wargame validated the proposed concept and suggested how the study might be developed going forward: namely, by enabling users to define their own capabilities and not being limited by a predefined set of capabilities.

RETRACTED ARTICLE: Computer aided diagnosis of brain tumor using novel classification techniques

Brain cancer treatment mainly depends on the accurate detection of the tumor type, location, size and borders. Magnetic resonance images (MRI) can be used to analyze the properties of the desired region such as tissues and tumors with automated and semi-automated approaches. So, the extraction of MRI brain tumor image is a challenging task in medical image processing. The major problems associated with MRI analysis by a physician are time consuming and the accuracy depends on the expertise of the physician.This limitation can be overcome by the computer aided diagnosis (CAD) technology. In this paper, a CAD system is designed to detect brain tumors with computer assistance using T1 and T2 weighted MR images. The designed system classifies the tumor into benign or malignant from MR Image using a novel automated method which increases the performance and reduces the complexity involved in the tumor diagnosis. The CAD system has four stages such as image acquisition, segmentation, feature extraction and classification. Segmentation is done with the help of K-means clustering, which enhances the medical image and the clustering quality to avoid local optima and to find global optima. The feature extraction is performed by gray level co-occurrence matrix (GLCM). The tumor classification is done using support vector machine (SVM) and bag of visual words (BOVW) classifiers. The test result of the SVM classifier gives accuracy 95.0%, sensitivity 91.79% and specificity 94.75%. Whereas, the BOVW classifier yields results of accuracy 96.0%, sensitivity 90.0% and specificity 100%. This result shows that, the designed system classifies the tumor into benign or malignant with a good level of accuracy.