Seed point selection for seed-based region growing in segmenting microcalcifications

Malek, Aminah Abdul; Rahman, Wan Eny Zarina Wan Abdul; Yasiran, Siti Salmah; Jumaat, Abdul Kadir; Jalil, Ummu Mardhiah Abdul

doi:10.1109/icssbe.2012.6396580

Cited by 17 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We developed a novel method to automatically segment cerebral arteries with a region growing algorithm for two combined seed masks from T1w MP2RAGE sequence images at 7 T. The two seed masks were defined by Frangi filtering of the T1w image and by a simple calculation of multi-contrast images in the MP2RAGE sequence. The seed mask of the region growing algorithm, which has been widely used as a segmentation method for medical images (Malek et al, 2012), is important to define core voxels of arteries for the robust region growth of cerebral arteries. Most of the seed voxels were defined by Frangi filtering, which has been employed to segment blood vessels in the retina (Oliveira et al, 2016) and the brain (Fiederer et al, 2016;Hsu et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Cerebral artery segmentation based on magnetization-prepared two rapid acquisition gradient echo multi-contrast images in 7 Tesla magnetic resonance imaging

Choi

Kawaguchi

Kida

2019

Preprint

View full text Add to dashboard Cite

Cerebral artery segmentation plays an important role in the direct visualization of the human brain to obtain vascular system information. At ultra-high field magnetic resonance imaging, hyperintensity of the cerebral arteries in T1 weighted (T1w) images could be segmented from brain tissues such as gray and white matter. In this study, we propose an automated method to segment the cerebral arteries using multi-contrast images including T1w images of a magnetization-prepared two rapid acquisition gradient echoes (MP2RAGE) sequence at 7 T. The proposed method employed a seed-based regiongrowing strategy with the following procedures. (1) Two seed regions were defined by Frangi filtering applied to T1w images and by a simple calculation from multi-contrast images, (2) the two seed regions were combined, (3) the combined seed regions were expanded using a region growing algorithm to acquire the cerebral arteries. Time-of-flight (TOF) images were obtained as a reference to evaluate the proposed method. We successfully performed vessel segmentations from T1w MP2RAGE images, which mostly overlapped with the segmentations from the TOF images. As large arteries can affect the normalization of anatomical images to the standard coordinate space in functional and structural studies, we also investigated the effect of the cerebral arteries on spatial transformation using vessel segmentation by the proposed method. As a result, the T1w image removing the cerebral arteries showed better agreement with the standard atlas compared with the T1w image containing the arteries. Thus, because the proposed method using MP2RAGE images can obtain brain tissue anatomical information as well as cerebral artery information without need for additional acquisitions such as of the TOF sequence, it is useful and time saving for medical diagnosis and functional and structural studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Cerebral artery segmentation based on magnetization-prepared two rapid acquisition gradient echo multi-contrast images in 7 Tesla magnetic resonance imaging

Choi

Kawaguchi

Kida

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Malek et al [80] proposed a method for growing the seed regions for segmenting mammogram microcalcification images. The proposed method was developed using an automated initial seed point selection algorithm.…”

Section: Mammograms Breast Cancer Segmentation-based Region Methods (Rm) Dehghani and Dezfoolimentioning

confidence: 99%

Breast Cancer Segmentation Methods: Current Status and Future Potentials

Michael

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

Early breast cancer detection is one of the most important issues that need to be addressed worldwide as it can help increase the survival rate of patients. Mammograms have been used to detect breast cancer in the early stages; if detected in the early stages, it can drastically reduce treatment costs. The detection of tumours in the breast depends on segmentation techniques. Segmentation plays a significant role in image analysis and includes detection, feature extraction, classification, and treatment. Segmentation helps physicians quantify the volume of tissue in the breast for treatment planning. In this work, we have grouped segmentation methods into three groups: classical segmentation that includes region-, threshold-, and edge-based segmentation; machine learning segmentation; and supervised and unsupervised and deep learning segmentation. The findings of our study revealed that region-based segmentation is frequently used for classical methods, and the most frequently used techniques are region growing. Further, a median filter is a robust tool for removing noise. Moreover, the MIAS database is frequently used in classical segmentation methods. Meanwhile, in machine learning segmentation, unsupervised machine learning methods are more frequently used, and U-Net is frequently used for mammogram image segmentation because it does not require many annotated images compared with other deep learning models. Furthermore, reviewed papers revealed that it is possible to train a deep learning model without performing any preprocessing or postprocessing and also showed that the U-Net model is frequently used for mammogram segmentation. The U-Net model is frequently used because it does not require many annotated images and also because of the presence of high-performance GPU computing, which makes it easy to train networks with more layers. Additionally, we identified mammograms and utilised widely used databases, wherein 3 and 28 are public and private databases, respectively.

show abstract

“…Noise removal from medical pictures is tough, according to an MRI approach. Because our predicted outcomes are grayscale, and the intensity among the pixels is barely affected, they are difficult to analyze [14]. To minimize the noise in medical imaging, many strategies have been used.…”

Section: Issues With Image Noisementioning

confidence: 99%

New hybrid Filtering Methods to remove noise from Digital Images

Rasheed¹,

Essa²,

Jumaa³

2022

J. Adv. Sci. Nanotechnol.

View full text Add to dashboard Cite

Using hybrid digital filtering techniques to reduce the amount of time a patient is exposed to radiation. If the patient is exposed to radiation for an extended length of time, his life will be jeopardized. Noise reduction in the photos is necessary when asked to lower the high radiation dosage and time it takes, which hides some of the right information from the physician and makes it difficult for him to appropriately analyze it. As a consequence, pre-processing has become the most significant item in digital image processors, and in this research, we offer a novel hybrid technology approach to decrease noise caused when photos are captured with medical equipment or when they are transferred. While respecting the image's edges, the resulting noise of the salt and pepper type. The statistical quantity measurements, Peak Signal-to-Noise Ratio (PSNR), and Root Mean Square Error (RMSE) are used to assess the enhanced picture quality. To illustrate this method, take 0.08 salts and pepper noise and compute it as MSE it becomes 2.58 and PSNR 202.67, which indicates that this method is better than others at removing higher noise as well.

show abstract

Seed point selection for seed-based region growing in segmenting microcalcifications

Cited by 17 publications

References 11 publications

Cerebral artery segmentation based on magnetization-prepared two rapid acquisition gradient echo multi-contrast images in 7 Tesla magnetic resonance imaging

Cerebral artery segmentation based on magnetization-prepared two rapid acquisition gradient echo multi-contrast images in 7 Tesla magnetic resonance imaging

Breast Cancer Segmentation Methods: Current Status and Future Potentials

New hybrid Filtering Methods to remove noise from Digital Images

Contact Info

Product

Resources

About