Fast Maximum Intensity Projections of Large Medical Data Sets by Exploiting Hierarchical Memory Architectures

2006 ◽  
Vol 10 (2) ◽  
pp. 385-394 ◽  
Author(s):  
G. Kiefer ◽  
H. Lehmann ◽  
J. Weese
Keyword(s):  
Medical Data ◽  
Maximum Intensity ◽  
Data Sets ◽  
Hierarchical Memory ◽  
Maximum Intensity Projections ◽  
Memory Architectures

scholarly journals Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1573
Author(s):  
Loris Nanni ◽  
Giovanni Minchio ◽  
Sheryl Brahnam ◽  
Gianluca Maguolo ◽  
Alessandra Lumini
Keyword(s):  
Vector Space ◽  
Image Classification ◽  
Ad Hoc ◽  
Feature Space ◽  
Medical Data ◽  
Training Data ◽  
Data Sets ◽  
Large Set ◽  
Clustering Methods ◽  
Siamese Networks

Traditionally, classifiers are trained to predict patterns within a feature space. The image classification system presented here trains classifiers to predict patterns within a vector space by combining the dissimilarity spaces generated by a large set of Siamese Neural Networks (SNNs). A set of centroids from the patterns in the training data sets is calculated with supervised k-means clustering. The centroids are used to generate the dissimilarity space via the Siamese networks. The vector space descriptors are extracted by projecting patterns onto the similarity spaces, and SVMs classify an image by its dissimilarity vector. The versatility of the proposed approach in image classification is demonstrated by evaluating the system on different types of images across two domains: two medical data sets and two animal audio data sets with vocalizations represented as images (spectrograms). Results show that the proposed system’s performance competes competitively against the best-performing methods in the literature, obtaining state-of-the-art performance on one of the medical data sets, and does so without ad-hoc optimization of the clustering methods on the tested data sets.

Sparse Matrix Approach in Neural Networks for Effective Medical Data Sets Classifications

2020 ◽  
Vol 6 (2) ◽  
pp. 90-97
Author(s):  
Sagir Masanawa ◽  
Hamza Abubakar
Keyword(s):  
Intelligent System ◽  
Sparse Matrix ◽  
Data Classification ◽  
Medical Data ◽  
Data Sets ◽  
Matrix Approach ◽  
Neural Network Learning ◽  
Network Learning ◽  
Hybrid Intelligent System ◽  
Medical Data Classification

In this paper, a hybrid intelligent system that consists of the sparse matrix approach incorporated in neural network learning model as a decision support tool for medical data classification is presented. The main objective of this research is to develop an effective intelligent system that can be used by medical practitioners to accelerate diagnosis and treatment processes. The sparse matrix approach incorporated in neural network learning algorithm for scalability, minimize higher memory storage capacity usage, enhancing implementation time and speed up the analysis of the medical data classification problem. The hybrid intelligent system aims to exploit the advantages of the constituent models and, at the same time, alleviate their limitations. The proposed intelligent classification system maximizes the intelligently classification of medical data and minimizes the number of trends inaccurately identified. To evaluate the effectiveness of the hybrid intelligent system, three benchmark medical data sets, viz., Hepatitis, SPECT Heart and Cleveland Heart from the UCI Repository of Machine Learning, are used for evaluation. A number of useful performance metrics in medical applications which include accuracy, sensitivity, specificity. The results were analyzed and compared with those from other methods published in the literature. The experimental outcomes positively demonstrate that the hybrid intelligent system was effective in undertaking medical data classification tasks.

scholarly journals Generating lung tumor internal target volumes from 4D-PET maximum intensity projections

2011 ◽  
Vol 38 (10) ◽  
pp. 5732-5737 ◽  
Author(s):  
J. M. Lamb ◽  
C. Robinson ◽  
J. Bradley ◽  
R. Laforest ◽  
F. Dehdashti ◽  
...  
Keyword(s):  
Lung Tumor ◽  
Maximum Intensity ◽  
Internal Target ◽  
Target Volumes ◽  
Maximum Intensity Projections

scholarly journals Future of Medical Research in Rare Diseases and Cancers: Shift from Pharma to Biotech and the Golden Age of Medical Advancement

2017 ◽  
Vol 6 (2) ◽  
pp. 12
Author(s):  
Abhith Pallegar
Keyword(s):  
Big Data ◽  
Medical Research ◽  
Rare Diseases ◽  
Network Effects ◽  
Medical Knowledge ◽  
Economic Cost ◽  
Medical Data ◽  
Data Sets ◽  
Leading Role ◽  
Diverse Data

The objective of the paper is to elucidate how interconnected biological systems can be better mapped and understood using the rapidly growing area of Big Data. We can harness network efficiencies by analyzing diverse medical data and probe how we can effectively lower the economic cost of finding cures for rare diseases. Most rare diseases are due to genetic abnormalities, many forms of cancers develop due to genetic mutations. Finding cures for rare diseases requires us to understand the biology and biological processes of the human body. In this paper, we explore what the historical shift of focus from pharmacology to biotechnology means for accelerating biomedical solutions. With biotechnology playing a leading role in the field of medical research, we explore how network efficiencies can be harnessed by strengthening the existing knowledge base. Studying rare or orphan diseases provides rich observable statistical data that can be leveraged for finding solutions. Network effects can be squeezed from working with diverse data sets that enables us to generate the highest quality medical knowledge with the fewest resources. This paper examines gene manipulation technologies like Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) that can prevent diseases of genetic variety. We further explore the role of the emerging field of Big Data in analyzing large quantities of medical data with the rapid growth of computing power and some of the network efficiencies gained from this endeavor. 

GRASP for Instance Selection in Medical Data Sets

2010 ◽  
pp. 53-60 ◽  
Author(s):  
Alfonso Fernández ◽  
Abraham Duarte ◽  
Rosa Hernández ◽  
Ángel Sánchez
Keyword(s):  
Medical Data ◽  
Instance Selection ◽  
Data Sets

SU-E-T-285: Generating Lung Tumor Internal Target Volumes from 4D-PET Maximum Intensity Projections

2011 ◽  
Vol 38 (6Part14) ◽  
pp. 3553-3553
Author(s):  
J Lamb ◽  
C Robinson ◽  
J Bradley ◽  
F Dehdashti ◽  
R Laforest ◽  
...  
Keyword(s):  
Lung Tumor ◽  
Maximum Intensity ◽  
Internal Target ◽  
Target Volumes ◽  
Maximum Intensity Projections

scholarly journals Novel Approaches to Smoothing and Comparing SELDI TOF Spectra

2005 ◽  
Vol 1 ◽  
pp. 117693510500100 ◽  
Author(s):  
Sreelatha Meleth ◽  
Isam-Eldin Eltoum ◽  
Liu Zhu ◽  
Denise Oelschlager ◽  
Chandrika Piyathilake ◽  
...  
Keyword(s):  
Spectral Analysis ◽  
Fourier Transforms ◽  
Area Under The Curve ◽  
Maximum Intensity ◽  
Data Sets ◽  
Intensity Level ◽  
Prominent Feature ◽  
Data Set ◽  
The Third ◽  
Novel Approaches

Background Most published literature using SELDI-TOF has used traditional techniques in Spectral Analysis such as Fourier transforms and wavelets for denoising. Most of these publications also compare spectra using their most prominent feature, ie, peaks or local maximums. Methods The maximum intensity value within each window of differentiable m/z values was used to represent the intensity level in that window. We also calculated the ‘Area under the Curve’ (AUC) spanned by each window. Results Keeping everything else constant, such as pre-processing of the data and the classifier used, the AUC performed much better as a metric of comparison than the peaks in two out of three data sets. In the third data set both metrics performed equivalently. Conclusions This study shows that the feature used to compare spectra can have an impact on the results of a study attempting to identify biomarkers using SELDI TOF data.

Sign in / Sign up

Export Citation Format

Share Document