3D segmentation of thyroid ultrasound images using active contours

Poudel, Prabal; Hansen, Christian; Sprung, Julian; Friebe, Michael

doi:10.1515/cdbme-2016-0103

Cited by 15 publications

(12 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Regarding treatment of thyroid diseases, it is important that the shape and size of the thyroid are tracked over time, which can be conducted with ultrasound scanning. Hence, several 2D segmentation algorithms for thyroid ultrasound images have been developed, and 3D segmentation is now possible [37,38]. Three-dimensional visualizations of the thyroid are also crucial for surgical intervention [39].…”

Section: Discussionmentioning

confidence: 99%

Imaging the Human Thyroid Using Three-Dimensional Diffuse Optical Tomography: A Preliminary Study

et al. 2021

View full text Add to dashboard Cite

Thyroid cancer is usually diagnosed by ultrasound imaging and fine-needle aspiration biopsy. However, diagnosis of follicular thyroid carcinomas (FTC) is difficult because FTC lacks nuclear atypia and a consensus on histological interpretation. Diffuse optical tomography (DOT) offers the potential to diagnose FTC because it can measure tumor hypoxia, while image reconstruction of the thyroid is still challenging mainly due to the complex anatomical features of the neck. In this study, we attempted to solve this issue by creating a finite element model of the human neck excluding the trachea (a void region). By reconstruction of the absorption coefficients at three wavelengths, 3D tissue oxygen saturation maps of the human thyroid are obtained for the first time by DOT.

show abstract

Section: Discussionmentioning

confidence: 99%

Imaging the Human Thyroid Using Three-Dimensional Diffuse Optical Tomography: A Preliminary Study

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Using this information, the Euclidean distance between the image centres of the current and the next image is computed and the angle between the centres is computed. After computing the distance and angle between the two image centres, a probable centre of mass of the thyroid in the next image is computed by traversing the same distance and angle from the centre of mass of the current segmented thyroid [ 26 ]. Centre of mass computed this way will serve to be the centre of rectangle in the next image frame around which the new mask will be initialized automatically.…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Commonly Used Algorithms for Thyroid Ultrasound Images Segmentation and Improvement Using Machine Learning Approaches

Poudel

Illanes

Sheet

et al. 2018

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

The thyroid is one of the largest endocrine glands in the human body, which is involved in several body mechanisms like controlling protein synthesis and the body's sensitivity to other hormones and use of energy sources. Hence, it is of prime importance to track the shape and size of thyroid over time in order to evaluate its state. Thyroid segmentation and volume computation are important tools that can be used for thyroid state tracking assessment. Most of the proposed approaches are not automatic and require long time to correctly segment the thyroid. In this work, we compare three different nonautomatic segmentation algorithms (i.e., active contours without edges, graph cut, and pixel-based classifier) in freehand three-dimensional ultrasound imaging in terms of accuracy, robustness, ease of use, level of human interaction required, and computation time. We figured out that these methods lack automation and machine intelligence and are not highly accurate. Hence, we implemented two machine learning approaches (i.e., random forest and convolutional neural network) to improve the accuracy of segmentation as well as provide automation. This comparative study intends to discuss and analyse the advantages and disadvantages of different algorithms. In the last step, the volume of the thyroid is computed using the segmentation results, and the performance analysis of all the algorithms is carried out by comparing the segmentation results with the ground truth.

show abstract

“…Namun, gambar ultrasound ini cenderung dipenuhi dengan speckle noise dan artifak lainnya. Penelitian dengan citra ultrasound B-Mode membutuhkan pemrosesan awal untuk meningkatkan kualitas citra (image enhancement), misalnya dengan filter Gaussian [12], [13] untuk mendapatkan citra yang lebih halus (blur), filter Median [12], [14], [15] untuk mengurangi noise berupa bintik kecil pada citra (salt and pepper), dan histogram equalization [15] untuk meningkatkan kontras dari citra. Kualitas gambar yang lebih baik di bagian Region of Interest (RoI) dapat membantu dalam proses penentuan area arteri karotis.…”

Section: Pendahuluanunclassified

“…Hasil IE dengan filter Gaussian memperlihatkan citra yang lebih halus (blur) seperti [12], [13]. Hasil IE dengan histogram equalization menunjukkan peningkatan kontras dan peningkatan nilai di area batas arteri karotis sehingga batas tersebut semakin terlihat jelas seperti [15]. Hasil IE filter Median memperlihatkan hasil pengurangan noise yang berupa salt dan pepper seperti [12], [14], [15].…”

Section: Hasil Dan Pembahasanunclassified

“…Hasil IE dengan histogram equalization menunjukkan peningkatan kontras dan peningkatan nilai di area batas arteri karotis sehingga batas tersebut semakin terlihat jelas seperti [15]. Hasil IE filter Median memperlihatkan hasil pengurangan noise yang berupa salt dan pepper seperti [12], [14], [15]. Dataset citra yang digunakan dalam pelatihan diberikan label yang menandakan area Region of Interest (RoI) arteri karotis.…”

Section: Hasil Dan Pembahasanunclassified

See 1 more Smart Citation

Deteksi Arteri Karotis pada Citra Ultrasound B-Mode Berbasis Convolution Neural Network Single Shot Multibox Detector

Sunarya

Karlita

Priambodo

et al. 2019

Jurnal Teknologi dan Sistem Komputer

View full text Add to dashboard Cite

Detection of vascular areas (blood vessels) using B-Mode ultrasound images is needed for automatic applications such as registration and navigation in medical operations. This study developed the detection of the carotid artery area using Convolution Neural Network Single Shot Network Multibox Detector (SSD) to determine the bounding box ROI of the carotid artery area in B-mode ultrasound images. The data used are B-Mode ultrasound images on the neck that contain the carotid artery area (primary data). SSD method result is 95% of accuracy which is higher than the Hough transformation method, Ellipse method, and Faster RCNN in detecting carotid artery area in the B-Mode ultrasound image. The use of image enhancement with Gaussian filter, histogram equalization, and Median filters in this method can increase detection accuracy. The best process time of the proposed method is 2.09 seconds so that it can be applied in a real-time system. Keywords -object detection; carotid artery; ultrasound B-Mode; convolutional neural network; single shot multibox detector Abstrak -Deteksi area vaskular (pembuluh darah) menggunakan citra ultrasound B-Mode diperlukan untuk aplikasi otomatis seperti registrasi dan navigasi dalam operasi medis. Penelitian ini melakukan kajian deteksi area arteri karotis menggunakan Convolution Neural Network Single Shot Multibox Detector (SSD) untuk menentukan RoI area arteri karotis dengan fitur bounding box pada citra ultrasound B-Mode. Data yang digunakan dalam penelitian adalah citra ultrasound B-Mode pada bagian leher yang mengandung area arteri karotis (data primer). Hasil metode SSD memiliki akurasi 95% dan akurasi yang lebih tinggi dari metode transformasi Hough, metode Ellipse dan Faster RCNN dalam mendeteksi area arteri karotis pada citra ultrasound B-Mode. Penerapan image enhancement dengan filter Gaussian, histogram equalization dan filter Median memberikan pengaruh dalam peningkatan akurasi deteksi. Waktu proses terbaik dari metode yang diusulkan adalah 2,09 detik sehingga dapat diterapkan dalam sistem yang bersifat real-time.Kata kunci -deteksi objek; arteri karotis; ultrasound B-Mode; convolutional neural network; single shot multibox detektor

show abstract

3D segmentation of thyroid ultrasound images using active contours

Cited by 15 publications

References 6 publications

Imaging the Human Thyroid Using Three-Dimensional Diffuse Optical Tomography: A Preliminary Study

Imaging the Human Thyroid Using Three-Dimensional Diffuse Optical Tomography: A Preliminary Study

Evaluation of Commonly Used Algorithms for Thyroid Ultrasound Images Segmentation and Improvement Using Machine Learning Approaches

Deteksi Arteri Karotis pada Citra Ultrasound B-Mode Berbasis Convolution Neural Network Single Shot Multibox Detector

Contact Info

Product

Resources

About