Three-level Local Thresholding Berbasis Metode Otsu untuk Segmentasi Leukosit pada Citra Leukemia Limfoblastik Akut

Abstract. Segmentation of Acute Lymphoblastic Leukemia (ALL) images can be used to identify the presence of ALL disease. In this paper, three-level local thresholdings based on Otsu method is presented for leucocytes segmentation in ALL image. Firstly, a method based on Gram-Schmidt orthogonalization theory is applied to partition the input image into several sub-images. The proposed method extends Otsuâ€™s bi-level thresholding to three-level thresholding methodÂ to find two local threshold values that maximize between-class variance. Using the two local threshold values and three-level local thresholding technique then segmenting each of sub-images into three regions, e.g. nucleus, cytoplasm, and background. To evaluate the performance of the proposed method, 32 peripheral blood smear images are used. The performance of the proposed method is compared with manually segmented ground truth using Zijdenbos similarity index (ZSI), precision, and recall. An experimental evaluation demonstrates superior performance over three-level global thresholding for ALL image segmentation.Keywords: three-level local thresholding, acute lymphoblastic leukemia, three-level Otsu thresholding, gram-schmidt orthogonalizationÂ Abstrak. Segmentasi citra Limfoblastik Leukemia Akut (LLA) dapat digunakan untuk mengidentifikasi kehadiran penyakit LLA. Pada penelitian ini diusulkan metode three-level local thresholding berbasis metode Otsu untuk segmentasi leukosit pada citra LLA. Pertama-tama, metode berbasis teori ortogonalisasi Gram-Schmidt diaplikasikan untuk membagi citra LLA menjadi sub-sub citra. Metode yang diusulkan memperluas metode bi-level thresholding Otsu ke dalam kasus three-level thresholding untuk pencarian dua nilai ambang lokal tiap sub-citra yang memaksimumkan varian antar kelas. Dengan nilai ambang jamak lokal tersebut, teknik three-level local thresholding selanjutnyaÂ mensegmentasi tiap sub-citra ke dalam tiga region, yaitu nukelus, sitoplasma, dan latar belakang. Untuk mengevaluasi performa metode usulan, 32 citra uji digunakan. Performa metode yang diusulkan dibandingkan dengan citra segmentasi manual menggunakan Zijdenbos similarity index (ZSI), presisi, dan recall. Hasil uji coba menunjukkan performa three-level local thresholding lebih unggul daripada metode three-level global thresholding untuk segmentasi citra LLA. Kata Kunci: three-level local thresholding, leukemia limfoblastik akut, three-level Otsu thresholding, ortogonalisasi gram-schmidt

Download Full-text

FUZZY C-MEANS ALGORITHM WITH LOCAL THRESHOLDING FOR GRAY-SCALE IMAGES

International Journal of Artificial Intelligence Tools ◽

10.1142/s021821300800414x ◽

2008 ◽

Vol 17 (04) ◽

pp. 765-775 ◽

Cited By ~ 3

Author(s):

HSIAO PIAU NG ◽

SIM HENG ONG ◽

KELVIN WENG CHIONG FOONG ◽

POH SUN GOH ◽

WIESLAW L. NOWINSKI

Keyword(s):

Feature Space ◽

Boundary Region ◽

Superior Performance ◽

Local Minima ◽

Threshold Values ◽

Fuzzy C Means ◽

Otsu Thresholding ◽

Local Thresholding ◽

Fcm Clustering ◽

Comparison Of The Results

An improved fuzzy C-means (FCM) clustering method is proposed. It incorporates Otsu thresholding with conventional FCM to reduce FCM's susceptibility to local minima, as well as its tendency to derive a threshold that is biased towards the component with larger probability, and derive threshold values with greater accuracy. Thresholding is performed at the cluster boundary region in feature space. A comparison of the results produced by improved and conventional algorithms confirms the superior performance of the former.

Download Full-text

DOCUMENT IMAGE BINARISATION USING A SUPERVISED NEURAL NETWORK

International Journal of Neural Systems ◽

10.1142/s0129065708001671 ◽

2008 ◽

Vol 18 (05) ◽

pp. 405-418 ◽

Cited By ~ 21

Author(s):

ADNAN KHASHMAN ◽

BORAN SEKEROGLU

Keyword(s):

Neural Network ◽

Digital Libraries ◽

Cost Effective ◽

Threshold Value ◽

Document Image ◽

Local Threshold ◽

Global Threshold ◽

Local Thresholding ◽

Global Thresholding ◽

Degraded Documents

Advances in digital technologies have allowed us to generate more images than ever. Images of scanned documents are examples of these images that form a vital part in digital libraries and archives. Scanned degraded documents contain background noise and varying contrast and illumination, therefore, document image binarisation must be performed in order to separate foreground from background layers. Image binarisation is performed using either local adaptive thresholding or global thresholding; with local thresholding being generally considered as more successful. This paper presents a novel method to global thresholding, where a neural network is trained using local threshold values of an image in order to determine an optimum global threshold value which is used to binarise the whole image. The proposed method is compared with five local thresholding methods, and the experimental results indicate that our method is computationally cost-effective and capable of binarising scanned degraded documents with superior results.

Download Full-text

Challenges and Clinical Strategies of CAR T-Cell Therapy for Acute Lymphoblastic Leukemia: Overview and Developments

Frontiers in Immunology ◽

10.3389/fimmu.2020.569117 ◽

2021 ◽

Vol 11 ◽

Author(s):

Xinjie Xu ◽

Shengkang Huang ◽

Xinyi Xiao ◽

Qihang Sun ◽

Xiaoqian Liang ◽

...

Keyword(s):

Acute Lymphoblastic Leukemia ◽

T Cell ◽

Cell Therapy ◽

Lymphoblastic Leukemia ◽

Superior Performance ◽

T Cell Therapy ◽

Car T Cell ◽

Car T Cell Therapy ◽

Car T ◽

Clinical Strategies

Chimeric antigen receptor (CAR) T-cell therapy exhibits desirable and robust efficacy in patients with acute lymphoblastic leukemia (ALL). Stimulated by the revolutionized progress in the use of FDA-approved CD19 CAR T cells, novel agents with CAR designs and targets are being produced in pursuit of superior performance. However, on the path from bench to bedside, new challenges emerge. Accessibility is considered the initial barrier to the transformation of this patient-specific product into a commercially available product. To ensure infusion safety, profound comprehension of adverse events and proactive intervention are required. Additionally, resistance and relapse are the most critical and intractable issues in CAR T-cell therapy for ALL, thus precluding its further development. Understanding the limitations through up-to-date insights and characterizing multiple strategies will be critical to leverage CAR T-cell therapy flexibly for use in clinical situations. Herein, we provide an overview of the application of CAR T-cell therapy in ALL, emphasizing the main challenges and potential clinical strategies in an effort to promote a standardized set of treatment paradigms for ALL.

Download Full-text