Morphological characteristics of X-ray thorax images of COVID-19 patients using the Bradley thresholding segmentation

Supriyanti, Retno; Alqaaf, Muhammad; Ramadhani, Yogi; Widodo, Haris Budi

doi:10.11591/ijeecs.v24.i2.pp1074-1083

Cited by 7 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The findings also reveal improved performance in data load, input/output (I/O) operations, network data transfer, query execution time, and data read and write through the optimization of key Hive parameters. The application [9] of the Bradley thresholding method in segmenting thorax X-ray images successfully delineated the thoracic area and identified white patches. This segmentation technique proves effective in simplifying the analysis of X-ray images for individuals with COVID-19, yielding more accurate and precise image information.…”

Section: Methodsmentioning

confidence: 99%

DeepCOVID: a deep learning approach for accurate COVID-19 detection in point-of-care lung ultrasound

Narayanan,

Sukumri

2024

IJEECS

View full text Add to dashboard Cite

Sickness still continued to spread through several countries when it first appeared in China. The number of COVID-19 cases is rising daily worldwide, posing a severe threat to the government and the populace. As a result of the virus’s rapid spread, doctors are having trouble recognizing positive cases. It is obvious that computer-based diagnosis must be developed to get results at a reasonable cost. The classic convolutional neural network (CNN) is used for this, utilizing the CT dataset, and the upgraded CNN model is used with the lung ultrasound (LUS) dataset. The CT and LUS COVID imaging datasets are compared in the model. The accuracy of both deep learning models is higher. We customized ResNet50, a pre-trained deep learning architecture, for a web application paradigm. First, we suggest a method for normalizing data that addresses its variability because it is collected in hospitals using various CT scanners and ultrasound machines. Second, we identify COVID-19 patients using U-Net segmentation and classification. The CNN architecture is added for deep learning purposes, and Res-Net 50 offers incredible accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

DeepCOVID: a deep learning approach for accurate COVID-19 detection in point-of-care lung ultrasound

Narayanan,

Sukumri

2024

IJEECS

View full text Add to dashboard Cite

show abstract

“…Hasil citra X-Ray pada penderita COVID-19 didapati cairan di dalam paru-paru akan terlihat seperti bintik-bintik putih. Penumpukan cairan ini di dalam rongga dada dapat mengganggu kinerja paru-paru, menyebabkan penderitanya mengalami kesulitan bernapas, bahkan yang paling parah kondisi ini dapat menyebabkan kematian sehingga penanganan harus segera dilakukan untuk mencegah meningkatnya pasien karena pandemi ini [7]. Edge Detection (Deteksi Tepi) pada citra merupakan suatu proses yang menghasilkan tepi objek citra dengan tujuan untuk menandai bagian-bagian yang detail pada citra dan mempertegas teks pada citra serta memperbaiki detail citra yang kabur.…”

Section: Pendahuluanunclassified

Identifikasi Citra Paru-Paru pada Pasien COVID-19 dengan Teknik Edge Detection

Pertiwi

2022

jsisfotek

View full text Add to dashboard Cite

X-ray chest radiographs produce digital radiographic images of the chest area such as the lungs, heart and ribs. This image can visualize the lung condition of patients with COVID-19. The Edge Detection technique can see the edges of objects in the lungs of COVID-19 patients more clearly. The lungs of patients with COVID-19 are damaged due to the GGO (Ground Glass Opacity) COVID-19, namely there is white fog, the lungs look blurry at the edges or areas affected by the disease and also affect the area of the area. This technique can make it easier for health workers to see X-ray results on objects in the lungs of COVID-19 patients and assist doctors in handling COVID-19 patients. With advances in the computer field in the application of image processing techniques, this Edge Detection Technique uses Matlab software to obtain edge and area images of clean lungs in COVDI-19 patients. The data used in this study were 30 samples of lung images of COVID patients and 10 images of healthy patients' lungs as a comparison sourced from Embung Fatimah Hospital Batam, which were processed in the grayscale stage, then the image was preprocessed with Intensity Adjustment then segmented with Active Contour and then using Edge Detection Technique. The results of this study were as many as 22 lung images produced an accuracy value of 73%. The image of the test results with the Edge Detection Technique to identify the edges of the object's lungs of COVID-19 patients which are quite clear by producing white pixels that are so visible. The perimeter of the right lung of COVID-19 patients ranged from 110,897 - 261,254 mm and Area 267,719 - 940,668 mm2, Perimeter of the left lung ranged from 114,613 - 262,943 and Area 170.616 - 856,993 mm2, while healthy patients as comparison had the right lung Perimeter range of 187,598 -270,624 and Area 514,947 - 1025.44 mm2, Perimeter of the left lung 182,226 - 287,358 and Area 480,592 - 901,418 mm2 means that COVID-19 virus infection reduces lung area, the range of COVID-19 lungs is lower than healthy lungs.

show abstract

“…Aswathy et al [19] used nano images enhanced with Gabor filters and histogram equalization in the early detection of lung cancer based on the guaranteed convergence particle swarm optimization (GCPSO) algorithm. In our previous research [20]- [23], we segmented the image of the lung area, including the white spots in it, in COVID-19 patients using the Bradley and Sauvola method. Unfortunately, the performance of this segmentation method still needs to be improved.…”

Section: Introductionmentioning

confidence: 99%

Morphological features of lung white spots based on the Otsu and Phansalkar thresholding method

Supriyanti,

Luke Dzihniza,

Alqaaf

et al. 2024

IJEECS

View full text Add to dashboard Cite

<span>COVID-19 is a disease that causes respiratory system disorders, so various tests are needed. One of them uses a chest X-ray or thorax. A chest X-ray will depict the lungs as a whole so that patches like white shadows will be visible. In this study, the number of lung areas and white spots can be observed and detected using segmentation techniques in image processing. But before entering the segmentation stage, the image will go through the preprocessing stage using the tri-threshold fuzzy intensification operators (fuzzy IO) method. It then segmented the lungs using the Otsu method by changing the digital image from grey to black and white based on comparing the threshold value with the pixel colour value of the digital image. Then, further segmentation was carried out using the Phansalkar method to detect and simultaneously count the number of white spots. Referring to the experiments we have carried out, Otsu Phansalkar's segmentation performance promises to be developed further.</span>

show abstract

Morphological characteristics of X-ray thorax images of COVID-19 patients using the Bradley thresholding segmentation

Cited by 7 publications

References 28 publications

DeepCOVID: a deep learning approach for accurate COVID-19 detection in point-of-care lung ultrasound

DeepCOVID: a deep learning approach for accurate COVID-19 detection in point-of-care lung ultrasound

Identifikasi Citra Paru-Paru pada Pasien COVID-19 dengan Teknik Edge Detection

Morphological features of lung white spots based on the Otsu and Phansalkar thresholding method

Contact Info

Product

Resources

About