Artificial intelligence optimized image segmentation techniques for renal cyst detection.

The vast number of image modalities available nowadays has given rise and access to a number of medical images. These images perhaps suffer issues such as low contrast, noise, ill-defined boundaries and poor visualisation. Therefore, a need for effective segmentation arises. Medical image segmentation plays a significant role in identifying a disorder, treatment planning, routine follow ups and computer-guided surgery respectively. The paper presents automatic medical image segmentation to overcome the imaging concerns and demarcate each notch & boundary in an image. The proposed algorithm identifies the existing kidney cyst precisely as they may be related to extreme disorders that may affect kidney function. The algorithm has been further tested on automatic segmentation using Genetic Algorithm, Ant Colony Optimisation and Fuzzy C Means Clustering. In terms of visualisation of valuable pathology, GA stands out and further helps in better assessment of the extent of the disease providing with better representation of the kidney cysts thereby giving a better diagnostic assurance and understanding of the nature of any disorder helping the medical practitioners as well as the patients. Experimental results on segmentation of kidney CT images conclusively demonstrate that the Genetic Algorithm is much more effective and robust.

Advance computer analysis of magnetic resonance imaging (MRI) for early brain tumor detection.

PURPOSE: The brain tumor grows inside the skull and interposes with regular brain functioning. The tumor growth may possibly result in cancer at a later stage. The early detection of brain tumor is crucial for successful treatment of fatal disease. The tumor presence is normally detected by Computed Tomography (CT) or Magnetic Resonance Imaging (MRI) images. The MRI/CT images are highly complex and involve huge data. This requires highly tedious and time-consuming process for detection of small tumors for the neurologists. Thus, there is a need to develop an effective and less time-consuming imaging technique for early detection of brain tumors. MATERIALS AND METHODS: This paper mainly focuses on early detecting and localizing the brain tumor region using segmentation of patient's MRI images. The Matlab software experiments are performed on a set of fifteen tumorous MRI images. In the proposed work, four image segmentation modalities namely watershed transform, k-means clustering, thresholding and Fuzzy C Means Clustering techniques with median filtering have been implemented. RESULTS: The results are verified by quantitative comparison of results in terms of image quality evaluation parameters-Entropy, standard deviation and Naturalness Image Quality Evaluator. A remarkable rise in the entropy and standard deviation values has been noticed. CONCLUSIONS: The watershed transform segmentation with median filtering yields the best quality brain tumor images. The noteworthy improvement in visibility of the MRI images may highly increase the possibilities of early detection and successful treatment of brain tumor disease and thereby assists the clinicians to decide the precise therapies.

Improved skin lesions detection using color space and artificial intelligence techniques.

Background: Automatic skin lesion image identification is of utmost importance to develop a fully automatized computer-aided skin analysis system. This will be helping the medical practitioners to provide skin lesions disease treatment more efficiently and effectively.Material and method: In this article, two image processing techniques for accurate detection of skin lesions have been proposed. In first technique, the optimization of edge detection has been carried out by using a branch of artificial intelligence called nature inspired algorithm. Ant colony optimization (ACO) is used to increase effectiveness of edge detection in skin lesion. The second technique deals with the color space-based split-and-merge process in combination with global thresholding segmentation and edge smoothing operations.Result: The performance of both techniques has been measured by entropy performance evaluation parameter. The results show remarkable improvement in output images obtained by Canny edge detection technique optimized by ACO in comparison with ACO-Sobel, ACO-Prewitt and Edge Smoothing-Color Space techniques.Conclusion: ACO-Canny Edge detection technique shows far better effieciency for skin lesion detection as compared to ACO-Sobel, ACO-Prewitt and Edge Smoothing Color Space technique.

Primary amoebic meningoencephalitis in an infant.

Primary amoebic meningoencephalitis is rare but fatal disease encountered in immunocompetent individuals. Here, we present a case of a previously healthy 8-month-old female child, who presented with features of meningoencephalitis of 2 days' duration. Rapidly moving trophozoites of amoeba were observed in cerebrospinal fluid, which were confirmed to be Naegleria fowleri on polymerase chain reaction. Broad-spectrum antimicrobial therapy with ceftriaxone, vancomycin, amphotericin B and acyclovir was initiated. However, the patient deteriorated and left the hospital against medical advice. The isolation of N. fowleri in this case demands for increased awareness for prompt diagnosis and management in view of its high mortality.

Improved skin lesion edge detection method using Ant Colony Optimization.

BACKGROUND: Skin lesion edge detection is a significant step in developing an automatized diagnostic system. The efficient diagnostic system leads to correct identification and detection of skin lesion diseases. In this paper, ant colony optimization (ACO) technique is used to improve the edge contour of skin lesion images. MATERIAL AND METHOD: Firstly, a three-stage preprocessing methodology involving color space conversion, contrast enhancement, and filtering is applied to improve the skin lesion image quality. The edge map is obtained by applying three types of conventional edge detection methods namely Canny, Sobel, and Prewitt. Thereafter, ACO is applied on these images to produce an improved edge contour. RESULT: The improvement of the proposed methodology is quantitatively verified by analysis of the entropy of the final image obtained by conventional and proposed techniques. CONCLUSION: From the result analysis, we can conclude that introduction of ACO has increased the efficiency of the conventional edge detection method in skin lesion images.

Study of Haralick's and GLCM texture analysis on 3D medical images.

PURPOSE OF THE STUDY: Medical field has highly evolved with advancements in the technologies which prove to be beneficial for radiologists and patients for better diagnosis. The era of medical science provides best healthcare solutions with the help of medical images. Till now, 2D MRIs played a prominent role in early detection of disease but with latest technologies taking over the charge, 3D MRIs are highly effective and great in demand nowadays. With the aid of advanced techniques such as edge detection, segmentation and texture analysis on these images, the disease detection may become much easier. MATERIALS AND METHODS: Texture of any image is recognized by distribution of gray levels in the neighborhood. The Texture Analysis plays an important role in study of medical images. It identifies the prominent features of an image and highlights the same using different feature extraction technique. In this paper, 3D MRI of human brain is considered and texture analysis based on Haralick's and GLCM texture features is performed. Haralick's feature explains the image intensities of each pixel and their relationship with neighborhood pixels. The entire data set consists of 40 brain tumor patients, out of which a sample has been depicted. RESULTS: The analysis of different features such as Contrast, Correlation, Energy, Homogeneity and Entropy is carried out. CONCLUSION: Further, the study highlights about the highly useful features for early detection of brain tumor disease.

NGA- A Novel Hypothetical Drug Model: Combinatorial Approach to Multifactorial Alzheimer's Disease.

Alzheimer's disease (AD) is supposed to stanch from inappropriate waving in the brain sections related to memory and perception. The incidence of AD in distressed person associated with an upsurge in the accumulation of amyloid plaque-rich senile plaques and neurofibrillary tangles in the brain. We hypothesize that a combination therapy provides a new treatment for AD. We propose that an anti-AD drug, NGA, a combination of NSAIDS, Galanthamine and ACS-40 may be useful in preventing the formation of amyloid plaques from ß-amyloid. Being a widespread incurable disease, the treatment for Alzheimer's has been at the forefront of the medical research work. We propose a novel drug-like NGA will allow for the effective control and treatment of the progression of AD by preventing acetylcholinesterase activity and reducing plaque formation that forms the distinctive symptom for the identification of the onset of AD. A combinatory use of NSAID with a natural neurotransmitter will allow for an efficient control of amyloid beta toxicity and will open doors for the treatment of a myriad of other neurodegenerative diseases.

Effect of different placement techniques on marginal microleakage of deep class-II cavities restored with two composite resin formulations.

AIM: The study aims to evaluate and compare marginal microleakage in deep class II cavities restored with various techniques using different composites. MATERIALS AND METHODS: Sixty freshly extracted teeth were divided into six groups of 10 teeth each. Standardized class II cavities were made and were restored using composites of different consistencies with different placement techniques. Group 1 with Microhybrid composite, Group 2 with Packable composite, Group 3 Microhybrid composite with a flowable composite liner, Group 4 Packable composite with a flowable composite liner, Group 5 Microhybrid composite with precured composite insert in second increment and Group 6 Packable composite with precured insert in second increment. Specimens then were stored in distilled water, thermocycled and immersed in 50% silver nitrate solution. These specimens were sectioned and evaluated for microleakage at the occlusal and cervical walls separately using stereomicroscope. RESULTS: The results demonstrated that in the occlusal wall, packable composite, showed significantly more marginal microleakage than the other groups. In the cervical wall, teeth restored with a flowable composite liner showed less marginal microleakage when compared to all other groups. CONCLUSION: Based on the results of this study, the use of flowable composite as the first increment is recommended in deep class II cavities.

Melanotic neuroectodermal tumor of infancy: 2 decades of clinical experience with 18 patients.

PURPOSE: The purpose of this article is to report our experience in the management of 18 patients with melanotic neuroectodermal tumor of infancy involving the maxillary alveolus. PATIENTS AND METHODS: All patients presented with hard nontender swelling involving the upper alveolus with facial deformity. Analysis included hematocrit, coagulation profile, serum creatinine, and screening for vanillyl mandelic acid and catecholamines. Imaging studies included x-ray of the maxilla and chest, ultrasound of the abdomen, computed tomography scan (1990 to 1999), and magnetic resonance imaging (after 1999). All surgeries were performed using endotracheal anesthesia, and complete gross excision of the tumor was achieved with coverage of the defect with mucoperiosteal flaps. All specimens were subjected to histopathology and immunohistochemistry. RESULTS: The expansion of the alveolus produced by the tumor improved in 4 to 6 months. Subsequent dentition was affected by the removal of involved tooth buds during the operation. All the patients are in regular follow-up (maximum 206 months) and there has been no local recurrence or distant metastasis. Mean follow-up time was 130.8 months (95% confidence interval, 168.8-210.6). Overall survival at 17 years was 85.6%. Median survival could not be established due to statistically insignificant sample size, while mean survival time was 189.7 months (95% confidence interval, 103.7-157.8). CONCLUSIONS: In the absence of metastatic disease, melanotic neuroectodermal tumors of infancy can be successfully managed by local excision.