PurposeSeveral methods have been proposed for the segmentation of 18F-FDG uptake in PET. In this study, we assessed the performance of four categories of 18F-FDG PET image segmentation techniques in pharyngolaryngeal squamous cell carcinoma using clinical studies where the surgical specimen served as the benchmark.MethodsNine PET image segmentation techniques were compared including: five thresholding methods; the level set technique (active contour); the stochastic expectation-maximization approach; fuzzy clustering-based segmentation (FCM); and a variant of FCM, the spatial wavelet-based algorithm (FCM-SW) which incorporates spatial information during the segmentation process, thus allowing the handling of uptake in heterogeneous lesions. These algorithms were evaluated using clinical studies in which the segmentation results were compared to the 3-D biological tumour volume (BTV) defined by histology in PET images of seven patients with T3–T4 laryngeal squamous cell carcinoma who underwent a total laryngectomy. The macroscopic tumour specimens were collected “en bloc”, frozen and cut into 1.7- to 2-mm thick slices, then digitized for use as reference.ResultsThe clinical results suggested that four of the thresholding methods and expectation-maximization overestimated the average tumour volume, while a contrast-oriented thresholding method, the level set technique and the FCM-SW algorithm underestimated it, with the FCM-SW algorithm providing relatively the highest accuracy in terms of volume determination (−5.9 ± 11.9%) and overlap index. The mean overlap index varied between 0.27 and 0.54 for the different image segmentation techniques. The FCM-SW segmentation technique showed the best compromise in terms of 3-D overlap index and statistical analysis results with values of 0.54 (0.26–0.72) for the overlap index.ConclusionThe BTVs delineated using the FCM-SW segmentation technique were seemingly the most accurate and approximated closely the 3-D BTVs defined using the surgical specimens. Adaptive thresholding techniques need to be calibrated for each PET scanner and acquisition/processing protocol, and should not be used without optimization.

Comparative methods for PET image segmentation in pharyngolaryngeal squamous cell carcinoma using surgical specimen as reference

Optimized unsupervised deep learning assisted reconstructed coder in the on-nodule wearable sensor for human activity recognition

Enhancing Privacy and Data Security across Healthcare Applications Using Blockchain and Distributed Ledger Concepts

Computational efficient wearable sensor network health monitoring system for sports athletics using IoT

Killer heuristic optimized convolution neural network-based fall detection with wearable IoT sensor devices

A dynamic and interoperable communication framework for controlling the operations of wearable sensors in smart healthcare applications

In the recent past Echocardiography image segmentation is one of the significant process describes about the segment out inner and outer walls or other parts of the organ boundaries. However, this kind of segmentation process is one of the difficult for physicians because of inexperience or subject specialists with the previous cases. To enhance the cardiac image segmentation accuracy and to minimise the segmentation time a machine learning method such as neural networks has been proposed in the segmentation process. In this research, feed forward artificial neural network (FFANN) has been utilised and fuzzy multi-scale edge detection (FMED) process has been applied to detect the segmented edges to define the detected texture boundary with the help of FFANN weights. An experimental result shows an efficient learning capacity of FFANN and this work deals with the segmentation of ultrasound images using MATLAB implementation.

Echocardiography image segmentation using feed forward artificial neural network (FFANN) with fuzzy multi-scale edge detection (FMED)

Alzheimer’s Neurodegenerative Disease is understood neurological issue, which is influenced cerebrum cells are causes the intellectual decrease and memory misfortune, the sickness begins gentle and deteriorates. There is a serious necessity to identify Alzheimer’s disease at an earlier stage, therefore that the appropriate treatment can initiate early. The foremost causes for Alzheimer’s diseases are low blood flow and brain activity. So, the serious Alzheimer disease has been recognized by several existing methodologies but they are fails to recognize the disease in the earlier stage. Thus, in this work use Single Photon Emission Nuclear Tomographic Imaging(SPECT) for find the Alzheimer’s diseases. The collected SPECT image noise is removed by applying Lucy-Richardson method and affected region is segmented by using Prolong adaptive exclusive analytical Atlas (PAEA). After this segmentation process Regional Atrophy Analysis (RAA) is apply for find the values of Gray Matters (GM) and White Matters (WM) regions in SPECT image. Finally Artificial Neural Network is applying for classification process. The experimental results shows that the promising outcomes in term of accuracy, sensitivity, and specificity.

Analysis of regional atrophy and prolong adaptive exclusive atlas to detect the alzheimers neuro disorder using medical images

Alzheimer's disease (AD) is a kind of Dementia. It affects the brain functions, thinking ability and creates memory loss. Each stage of AD is worsening the symptoms and also affects the patient's daily activities. The current diagnosis AD detection process is not providing an accurate report for the early stages of AD. Therefore, accurate Alzheimer detection is an open challenge for the researchers. In this research, a deep learning model is introduced to improve Alzheimer's stage diagnosis. The Hybrid deep model is designed to detect abnormal changes in brain (Magnetic Resonance Imaging) MRI scans. It utilizes the multi-class log loss (MCLL) function as the objective function to reduce the error rate in detecting AD stages. The MCLL approach computes the variations in actual and detected AD stages of each biomarkers features of input MRI images to identify loss rate. It helps to reduce the loss rate in AD stages detection. Moreover, the Hybrid deep learning model for Alzheimer stages detection (HDLMASD)system analysis the images deeply to provide accurate biomarkers detection with the help of all essential biomarkers processing steps. The efficiency of the Alzheimer stages diagnosis system is evaluated with various evaluation metrics. Finally, a comparative analysis is made with multiple present diagnosis systems to verify the performance of the AD detection system. The performance analysis proves that the AD stages diagnosis approach accuracy rate is improved up to 0.47% and the prediction error rate reduced up to 0.49% than comparison approaches.

Hippocampus Region's Volume-Based Alzheimer's Stages Detection Using a Deep Learning Model

/pdf/retraction-note-analysis-of-regional-atrophy-and-prolong-2jgpifp1.pdf

R. Sampath

Papers

A dynamic and interoperable communication framework for controlling the operations of wearable sensors in smart healthcare applications

Echocardiography image segmentation using feed forward artificial neural network (FFANN) with fuzzy multi-scale edge detection (FMED)

Analysis of regional atrophy and prolong adaptive exclusive atlas to detect the alzheimers neuro disorder using medical images

Hippocampus Region's Volume-Based Alzheimer's Stages Detection Using a Deep Learning Model

Retraction Note: analysis of regional atrophy and prolong adaptive exclusive atlas to detect the alzheimers neuro disorder using medical images