cDNA microarray adaptive segmentation

Wang, Zidong; Zineddin, Bachar; Liang, Jinling; Zeng, Nianyin; Li, Yurong; Du, Min; Cao, Jie; Liu, Xiaohui

doi:10.1016/j.neucom.2014.03.052

Cited by 12 publications

(7 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This helps in the detection of cancer in its early stage so that the domain experts can make a treatment plan to enhance the survival rate of cancer patients [4, 9, 10]. Hence, the problem requires careful construction of a model that takes an input pattern which represents objects and predicts the category of the object under consideration and hence, there is a need to develop an accurate prediction model on the given test data [7, 11, 12].…”

Section: Introductionmentioning

confidence: 99%

Deep learning approach for microarray cancer data classification

Basavegowda

Dagnew

2020

CAAI trans. intell. technol.

162

View full text Add to dashboard Cite

Analysis of microarray data is a highly challenging problem due to the inherent complexity in the nature of the data associated with higher dimensionality, smaller sample size, imbalanced number of classes, noisy data‐structure, and higher variance of feature values. This has led to lesser classification accuracy and over‐fitting problem. In this work, the authors aimed to develop a deep feedforward method to classify the given microarray cancer data into a set of classes for subsequent diagnosis purposes. They have used a 7‐layer deep neural network architecture having various parameters for each dataset. The small sample size and dimensionality problems are addressed by considering a well‐known dimensionality reduction technique namely principal component analysis. The feature values are scaled using the Min–Max approach and the proposed approach is validated on eight standard microarray cancer datasets. To measure the loss, a binary cross‐entropy is used and adaptive moment estimation is considered for optimisation. The performance of the proposed approach is evaluated using classification accuracy, precision, recall, f ‐measure, log‐loss, receiver operating characteristic curve, and confusion matrix. A comparative analysis with state‐of‐the‐art methods is carried out and the performance of the proposed approach exhibit better performance than many of the existing methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning approach for microarray cancer data classification

Basavegowda

Dagnew

2020

CAAI trans. intell. technol.

162

View full text Add to dashboard Cite

show abstract

“…It can efficiently find maximum likelihood estimates of parameters in statistical model by using an iterative method. As we can see from [20,[28][29][30]34,[36][37][38][39], the EM algorithm has been widely used in all kinds of signal processing problems and gained computationally efficient estimations. The main motivation of studying the modeling method for time series data in sEMG signal is mainly twofold.…”

Section: Introductionmentioning

confidence: 99%

Time series modeling of surface EMG based hand manipulation identification via expectation maximization algorithm

Lü

Liu

et al. 2015

Neurocomputing

View full text Add to dashboard Cite

a b s t r a c tIn this paper, we focus on the method of employing the expectation maximization (EM) algorithm to the modeling of surface electromyography (sEMG) signals based on hand manipulations via available time series of the measured data. The model for the sEMG is developed as a hidden Markov model (HMM) framework. In order to represent dynamical characteristics of sEMG when multichannel observation sequence are given, a stochastic dynamic process is included in it based on the maximum likelihood estimation (MLE) principle. By using the EM algorithm, the hidden model parameters and the feature of the signal can be identified easily. Ten people of different time series data sets of different hand grasps and in-hand manipulations captured from different subjects are collected. The two different classifiers were used to recognize these hand manipulation signal. Compared with time and time-frequency domains and their combination feature, the proposed algorithm of the inferred model gains better performance and demonstrates the effectiveness. The average identification accuracy rate is 93% and the maximum classification ratio is 100%.

show abstract

“…We can classify these methods into the following categories: Thresholding-based algorithms make use of statistical intensity modeling and find the optimal threshold to segment out the spot [ 27 , 28 ], but its performance relies on the appropriate choice of background samples. Edge and shape detection-based methods utilize gradients, snakes and active contours to capture the boundary and region information of spot [ 13 – 14 , 29 ].…”

Section: Related Workmentioning

confidence: 99%

“…Thresholding-based algorithms make use of statistical intensity modeling and find the optimal threshold to segment out the spot [ 27 , 28 ], but its performance relies on the appropriate choice of background samples.…”

Section: Related Workmentioning

confidence: 99%

A Combinational Clustering Based Method for cDNA Microarray Image Segmentation

Shao

et al. 2015

PLoS ONE

View full text Add to dashboard Cite

Microarray technology plays an important role in drawing useful biological conclusions by analyzing thousands of gene expressions simultaneously. Especially, image analysis is a key step in microarray analysis and its accuracy strongly depends on segmentation. The pioneering works of clustering based segmentation have shown that k-means clustering algorithm and moving k-means clustering algorithm are two commonly used methods in microarray image processing. However, they usually face unsatisfactory results because the real microarray image contains noise, artifacts and spots that vary in size, shape and contrast. To improve the segmentation accuracy, in this article we present a combination clustering based segmentation approach that may be more reliable and able to segment spots automatically. First, this new method starts with a very simple but effective contrast enhancement operation to improve the image quality. Then, an automatic gridding based on the maximum between-class variance is applied to separate the spots into independent areas. Next, among each spot region, the moving k-means clustering is first conducted to separate the spot from background and then the k-means clustering algorithms are combined for those spots failing to obtain the entire boundary. Finally, a refinement step is used to replace the false segmentation and the inseparable ones of missing spots. In addition, quantitative comparisons between the improved method and the other four segmentation algorithms--edge detection, thresholding, k-means clustering and moving k-means clustering--are carried out on cDNA microarray images from six different data sets. Experiments on six different data sets, 1) Stanford Microarray Database (SMD), 2) Gene Expression Omnibus (GEO), 3) Baylor College of Medicine (BCM), 4) Swiss Institute of Bioinformatics (SIB), 5) Joe DeRisi’s individual tiff files (DeRisi), and 6) University of California, San Francisco (UCSF), indicate that the improved approach is more robust and sensitive to weak spots. More importantly, it can obtain higher segmentation accuracy in the presence of noise, artifacts and weakly expressed spots compared with the other four methods.

show abstract

cDNA microarray adaptive segmentation

Cited by 12 publications

References 70 publications

Deep learning approach for microarray cancer data classification

Deep learning approach for microarray cancer data classification

Time series modeling of surface EMG based hand manipulation identification via expectation maximization algorithm

A Combinational Clustering Based Method for cDNA Microarray Image Segmentation

Contact Info

Product

Resources

About