Semantic Cardiac Segmentation in Chest CT Images Using K-Means Clustering and the Mathematical Morphology Method

Lee, Sung‐Jin; Lee, Ah Young; Gil, Hyo‐Wook; Hong, Min

doi:10.3390/s21082675

Cited by 8 publications

(4 citation statements)

References 22 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then other body material-such as lungs, muscle, and fat-are filtered by the convex envelope of the lung mask. Finally, the spinal material is filtered by the convex hull of the spinal mask [24]. Figure 7 shows the results of the segmentation process, and in this paper, unnecessary regions in the heart CT image were removed by applying this algorithm.…”

Section: Overall Workflow Of the Proposed Methodsmentioning

confidence: 99%

Deep-Learning-Based Coronary Artery Calcium Detection from CT Image

Lee

Jou

Gil

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

One of the most common methods for diagnosing coronary artery disease is the use of the coronary artery calcium score CT. However, the current diagnostic method using the coronary artery calcium score CT requires a considerable time, because the radiologist must manually check the CT images one-by-one, and check the exact range. In this paper, three CNN models are applied for 1200 normal cardiovascular CT images, and 1200 CT images in which calcium is present in the cardiovascular system. We conduct the experimental test by classifying the CT image data into the original coronary artery calcium score CT images containing the entire rib cage, the cardiac segmented images that cut out only the heart region, and cardiac cropped images that are created by using the cardiac images that are segmented into nine sub-parts and enlarged. As a result of the experimental test to determine the presence of calcium in a given CT image using Inception Resnet v2, VGG, and Resnet 50 models, the highest accuracy of 98.52% was obtained when cardiac cropped image data was applied using the Resnet 50 model. Therefore, in this paper, it is expected that through further research, both the simple presence of calcium and the automation of the calcium analysis score for each coronary artery calcium score CT will become possible.

show abstract

Section: Overall Workflow Of the Proposed Methodsmentioning

confidence: 99%

Deep-Learning-Based Coronary Artery Calcium Detection from CT Image

Lee

Jou

Gil

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…It uses set theory to modify an image's geometric structure. It is widely used for noise reduction, feature extraction, edge detection, image segmentation, form identification, image comparison, and texture analysis [23]. The mathematical morphology algorithm is a representation of the interaction between a set of objects and their structural components.…”

Section: Mathematical Morphologymentioning

confidence: 99%

Edge-Morphology Detection Approach for Median Nerve Segmentation on Ultrasound Images

Thinley

Tangkawanit

Kanprachar

2022

ECTI-CIT Transactions

View full text Add to dashboard Cite

Carpal Tunnel Syndrome (CST) is a form of peripheral neuropathy that affects a significant number of people. It is triggered by the compression of the median nerve in the wrist. CTS has recently been diagnosed using ultrasonography. This article presents a method that employs an edge-morphology detection approach to extract the structural feature of the median nerve from ultrasound images to permit automated segmentation of the median nerve. Pre-processing is applied to reduce the associated noise to boost the sensitivity and increase the accuracy of the model in segmenting the median nerve in ultrasound images. When tried on the test images, the suggested model performed well, with average precision, recall, F-score, and Jaccard similarity values of 0.87, 0.93, 0.76, and 0.93, respectively. Furthermore, a strong correlation of Cross-Sectional Area (CSA) between the ground truth and the segmented image of 0.962 is observed, allowing this model to serve as a useful initial screening tool to expedite the detection, diagnosis, and assessment of CTS in clinical practice.

show abstract

“…This neural network learning technique came to be called deep learning [3,4]. Currently, deep learning technology is applied to various fields of medical imaging, and it is used in various forms, such as classifying medical images according to specific diseases, locating lesions, and segmenting organs [5][6][7][8]. In this paper, by learning chest CT on a deep learning model, calcified data and normal data were distinguished.…”

Section: Introductionmentioning

confidence: 99%

Cardiac CT Image Segmentation for Deep Learning–Based Coronary Calcium Detection Using K-Means Clustering and Grabcut Algorithm

Lee¹,

Lee²,

Hong³

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Specific medical data has limitations in that there are not many numbers and it is not standardized. to solve these limitations, it is necessary to study how to efficiently process these limited amounts of data. In this paper, deep learning methods for automatically determining cardiovascular diseases are described, and an effective preprocessing method for CT images that can be applied to improve the performance of deep learning was conducted. The cardiac CT images include several parts of the body such as the heart, lungs, spine, and ribs. The preprocessing step proposed in this paper divided CT image data into regions of interest and other regions using K-means clustering and the Grabcut algorithm. We compared the deep learning performance results of original data, data using only K-means clustering, and data using both K-means clustering and the Grabcut algorithm. All data used in this paper were collected at Soonchunhyang University Cheonan Hospital in Korea and the experimental test proceeded with IRB approval. The training was conducted using Resnet 50, VGG, and Inception resnet V2 models, and Resnet 50 had the best accuracy in validation and testing. Through the preprocessing process proposed in this paper, the accuracy of deep learning models was significantly improved by at least 10% and up to 40%.

show abstract

Semantic Cardiac Segmentation in Chest CT Images Using K-Means Clustering and the Mathematical Morphology Method

Cited by 8 publications

References 22 publications

Deep-Learning-Based Coronary Artery Calcium Detection from CT Image

Deep-Learning-Based Coronary Artery Calcium Detection from CT Image

Edge-Morphology Detection Approach for Median Nerve Segmentation on Ultrasound Images

Cardiac CT Image Segmentation for Deep Learning–Based Coronary Calcium Detection Using K-Means Clustering and Grabcut Algorithm

Contact Info

Product

Resources

About