Kullback Leibler divergence for image quantitative evaluation

Pheng, Hang See; Shamsuddin, Siti Mariyam; Leng, Wong Yee; Alwee, Razana

doi:10.1063/1.4954516

Cited by 4 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jenson–Shannon (JS) divergence [ 16 – 19 ] was used to quantify the difference in grayscale distribution between two regions, for both intracase and intercase sampling. JS divergence offers an information-theoretic set-similarity measure that works naturally for pair-wise comparisons.…”

Section: Methodsmentioning

confidence: 99%

“…All these computer-generated features were used to train models. The independence between image region grayscale distributions were quantified by Jensen–Shannon (JS) divergence, a bounded symmetrization of the unbounded Kullback–Leibler (KL) divergence [ 16 – 19 ]. JS divergence was measured for B-mode ultrasound images acquired from images of three pathologies: normal cases, and then two groups of liver disease, namely steatosis (fatty liver) and fibrosis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics

Sultan

Cary

Al‐Hasani

et al. 2022

View full text Add to dashboard Cite

Machine learning for medical imaging not only requires sufficient amounts of data for training and testing but also that the data be independent. It is common to see highly interdependent data whenever there are inherent correlations between observations. This is especially to be expected for sequential imaging data taken from time series. In this study, we evaluate the use of statistical measures to test the independence of sequential ultrasound image data taken from the same case. A total of 1180 B-mode liver ultrasound images with 5903 regions of interests were analyzed. The ultrasound images were taken from two liver disease groups, fibrosis and steatosis, as well as normal cases. Computer-extracted texture features were then used to train a machine learning (ML) model for computer-aided diagnosis. The experiment resulted in high two-category diagnosis using logistic regression, with AUC of 0.928 and high performance of multicategory classification, using random forest ML, with AUC of 0.917. To evaluate the image region independence for machine learning, Jenson–Shannon (JS) divergence was used. JS distributions showed that images of normal liver were independent from each other, while the images from the two disease pathologies were not independent. To guarantee the generalizability of machine learning models, and to prevent data leakage, multiple frames of image data acquired of the same object should be tested for independence before machine learning. Such tests can be applied to real-world medical image problems to determine if images from the same subject can be used for training.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Can Sequential Images from the Same Object Be Used for Training Machine Learning Models? A Case Study for Detecting Liver Disease by Ultrasound Radiomics

Sultan

Cary

Al‐Hasani

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Statistical divergence was applied mainly as classifiers on multimedia content [3], especially as kernels in SVMs [2]. As a similarity measurement, it can also be used in qualitative and quantitative analysis in image evaluation [4], [5]. [1] adopted divergence to detect events in multimedia streams.…”

Section: A Data Anomaly Detectionmentioning

confidence: 99%

“…Statistical divergence is widely applied in multimedia processing. Prevalent applications include multimedia event detection [1], content classification [2], [3] and qualification [4], [5]. It has been attracting more attention since the dawn of big data era, basically due to regularity and interpretable features displayed in the data.…”

Section: Introductionmentioning

confidence: 99%

Statistical Detection Of Collective Data Fraud

Wang

Sun

et al. 2020

2020 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Statistical divergence is widely applied in multimedia processing, basically due to regularity and explainable features displayed in data. However, in a broader range of data realm, these advantages may not out-stand, and therefore a more general approach is required. In data detection, statistical divergence can be used as an similarity measurement based on collective features. In this paper, we present a collective detection technique based on statistical divergence. The technique extracts distribution similarities among data collections, and then uses the statistical divergence to detect collective anomalies. Our technique continuously evaluates metrics as evolving features and calculates adaptive threshold to meet the best mathematical expectation. To illustrate details of the technique and explore its efficiency, we case-studied a real world problem of click farming detection against malicious online sellers. The evaluation shows that these techniques provided efficient classifiers. They were also sufficiently sensitive to a much smaller magnitude of data alteration, compared with real world malicious behaviours. Thus, it is applicable in the real world.

show abstract