Local Indicators of Spatial Autocorrelation (LISA): Application to Blind Noise-Based Perceptual Quality Metric Index for Magnetic Resonance Images

Osadebey, Michael; Pedersen, Marius; Arnold, Douglas L.; Wendel-Mitoraj, Katrina

doi:10.3390/jimaging5010020

Cited by 8 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If the classifier predicts NL that the image do not contain a lung region, a function CBK generates an image TBK having only zero pixels as the segmented slice SGM. For prediction LR which indicate the presence of lung region, the quality of the test image is evaluated QEV using our previous contribution [31]. We set quality score of 0.9 as threshold τ 1 to determine whether to enhance Y or not to enhance N the contrast quality of the test image before it is moved further for processing.…”

Section: Pre-processingmentioning

confidence: 99%

Three-stage segmentation of lung region from CT images using deep neural networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background Lung region segmentation is an important stage of automated image-based approaches for the diagnosis of respiratory diseases. Manual methods executed by experts are considered the gold standard, but it is time consuming and the accuracy is dependent on radiologists’ experience. Automated methods are relatively fast and reproducible with potential to facilitate physician interpretation of images. However, these benefits are possible only after overcoming several challenges. The traditional methods that are formulated as a three-stage segmentation demonstrate promising results on normal CT data but perform poorly in the presence of pathological features and variations in image quality attributes. The implementation of deep learning methods that can demonstrate superior performance over traditional methods is dependent on the quantity, quality, cost and the time it takes to generate training data. Thus, efficient and clinically relevant automated segmentation method is desired for the diagnosis of respiratory diseases. Methods We implement each of the three stages of traditional methods using deep learning methods trained on five different configurations of training data with ground truths obtained from the 3D Image Reconstruction for Comparison of Algorithm Database (3DIRCAD) and the Interstitial Lung Diseases (ILD) database. The data was augmented with the Lung Image Database Consortium (LIDC-IDRI) image collection and a realistic phantom. A convolutional neural network (CNN) at the preprocessing stage classifies the input into lung and none lung regions. The processing stage was implemented using a CNN-based U-net while the postprocessing stage utilize another U-net and CNN for contour refinement and filtering out false positives, respectively. Results The performance of the proposed method was evaluated on 1230 and 1100 CT slices from the 3DIRCAD and ILD databases. We investigate the performance of the proposed method on five configurations of training data and three configurations of the segmentation system; three-stage segmentation and three-stage segmentation without a CNN classifier and contrast enhancement, respectively. The Dice-score recorded by the proposed method range from 0.76 to 0.95. Conclusion The clinical relevance and segmentation accuracy of deep learning models can improve though deep learning-based three-stage segmentation, image quality evaluation and enhancement as well as augmenting the training data with large volume of cheap and quality training data. We propose a new and novel deep learning-based method of contour refinement.

show abstract

Section: Pre-processingmentioning

confidence: 99%

Three-stage segmentation of lung region from CT images using deep neural networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Apabila suatu daerah memiliki autokorelasi spasial maka dapat dikatakatan daerah tersebut membentuk sebuah hubungan. Selanjutnya nilai LISA dapat dikelompokkan kedalam empat hubungan yakni (Osadebey et al 2019) :…”

Section: Metode Penelitianunclassified

Penerapan Model Spasial Durbin Dengan Uji Lanjutan Local Indicator of Spatial Autocorrelation Untuk Melihat Penyebaran Stunting Di Kabupaten Bone Bolango

HASIRU¹,

DJAKARIA²,

HASAN³

2022

Jambura J. Probab. Stat.

View full text Add to dashboard Cite

One of the spatial regression analysis used is the spatial durbin model (SDM). This model can be applied to obtain the relationship between X and Y variables and their spatial effects. This research was continued by testing the local spatial autocorrelation, namely the local indicator of spatial autocorrelation (LISA) which aims to provide information on the pattern of spatial relationships of each observation area in Bone Bolango regency. Stunting cases in Gorontalo province, especially in Bone Bolango regency, are in a status that needs to be addressed immediately due to the prevalence rate in Bone Bolango regency in 2019 above 20% based on the WHO standard. The results showed that the factors that significantly affected stunting in 2019 in Bone Bolango regency were exclusive breastfeeding, the proper sanitation and poverty. Meanwhile, based on the spatial effect, the factors that significantly affected stunting in 2019 in Bone Bolango regency were the percentage of exclusive breastfeeding, the percentage of LBW, the number of children with CBI and poverty. Based on result from the LISA, the observation areas of stunting cases showed that the percentage of exclusive breastfeeding, the number of children with CBI and povertu had a spatial autocorrelation or forming a grouping on the distribution of the stunting cases, the number of children with IDL and poverty, there are sub-districts that have spatial autocorrelation.

show abstract

“…The results show that our CC-DNN model has the ability to learn the complex relationships between three Equations (1), (2), and (4) and reproduce synthetic STIR images from T1-w, T2-w, and GRE images. Additional experiments with various levels of Rician noise 40 added were performed to reflect real MR scanning conditions. More information about Rician noise is provided in Supporting Information Equation S1, which is available online.…”

Section: Simulation Studiesmentioning

confidence: 99%

Deep‐learned short tau inversion recovery imaging using multi‐contrast MR images

Kim

Jang

et al. 2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To generate short tau, or short inversion time (TI), inversion recovery (STIR) images from three multi‐contrast MR images, without additional scanning, using a deep neural network. Methods For simulation studies, we used multi‐contrast simulation images. For in‐vivo studies, we acquired knee MR images including 288 slices of T1‐weighted (T1‐w), T2‐weighted (T2‐w), gradient‐recalled echo (GRE), and STIR images taken from 12 healthy volunteers. Our MR image synthesis method generates a new contrast MR image from multi‐contrast MR images. We used a deep neural network to identify the complex relationships between MR images that show various contrasts for the same tissues. Our contrast‐conversion deep neural network (CC‐DNN) is an end‐to‐end architecture that trains the model to create one image from three (T1‐w, T2‐w, and GRE images). We propose a new loss function to take into account intensity differences, misregistration, and local intensity variations. The CC‐DNN‐generated STIR images were evaluated with four quantitative evaluation metrics, including mean squared error, peak signal‐to‐noise ratio (PSNR), structural similarity (SSIM), and multi‐scale SSIM (MS‐SSIM). Furthermore, a subjective evaluation was performed by musculoskeletal radiologists. Results Our method showed improved results in all quantitative evaluations compared with other methods and received the highest scores in subjective evaluations by musculoskeletal radiologists. Conclusion This study suggests the feasibility of our method for generating STIR sequence images without additional scanning that offered a potential alternative to the STIR pulse sequence when additional scanning is limited or STIR artifacts are severe.

show abstract

Local Indicators of Spatial Autocorrelation (LISA): Application to Blind Noise-Based Perceptual Quality Metric Index for Magnetic Resonance Images

Cited by 8 publications

References 40 publications

Three-stage segmentation of lung region from CT images using deep neural networks

Three-stage segmentation of lung region from CT images using deep neural networks

Penerapan Model Spasial Durbin Dengan Uji Lanjutan Local Indicator of Spatial Autocorrelation Untuk Melihat Penyebaran Stunting Di Kabupaten Bone Bolango

Deep‐learned short tau inversion recovery imaging using multi‐contrast MR images

Contact Info

Product

Resources

About