Optimal segmentation of cell images

Wu, Huihui; Gil, Joan; Barba, J.

doi:10.1049/ip-vis:19981690

Cited by 56 publications

(34 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed PCA-based algorithm was compared with five common threshold selection techniques that have been used widely by many researchers for similar cell segmentation purposes (5,32,33), since they hold the advantage of being fast and simple to implement, as discussed by others (6). These thresholding techniques were: method A, iterative selection (24); method B, entropic thresholding (22); method C, Otsu's method (23); and method D, fuzzy sets (21).…”

Section: Comparison Of the Pca-based Methods With Other Thresholding Tmentioning

confidence: 99%

An image analysis‐based approach for automated counting of cancer cell nuclei in tissue sections

et al. 2003

View full text Add to dashboard Cite

BackgroundSemiquantitative evaluation and manual cell counting are the commonly used procedures to assess positive staining of molecular markers in tissue sections. Manual counting is also a laborious task in which consistent objectivity is difficult to achieve. Recently, image analysis has been explored, but the studies reported were limited to histological images acquired at high magnification and containing uniformly stained cells.MethodsThe analyzed material consisted of histological sections from different squamous cell cancers that had stained for proliferation using Ki‐67 and cyclin A detection. The first step of the method was based on detecting the overall number of cells irrespective to their stain, using second‐order edge detection methodology. Then proliferating cells were located using principal component analysis (PCA) of the color image, combined with histogram thresholding.ResultsThe algorithms' performances were validated on tissue section images encountered in routine clinical practice by comparison with objective measures of performance and manual cell identification. The algorithms correlated closely with manual counting of all cells (r2 = 0.96–0.97) and stained cells (4–7% cell count error).ConclusionsCell counting in complex large‐scale histological images could be applied in routine practice using edge and color information. The proposed technique provides several benefits, such as speed of analysis, consistency, and automation. Moreover, it is faster than human observation and could replace the laborious task of manual cell counting. Cytometry Part A 55A:30–42, 2003. © 2003 Wiley‐Liss, Inc.

show abstract

Section: Comparison Of the Pca-based Methods With Other Thresholding Tmentioning

confidence: 99%

An image analysis‐based approach for automated counting of cancer cell nuclei in tissue sections

et al. 2003

View full text Add to dashboard Cite

show abstract

“…Metode berbasis cluster yaitu Possibilistic Fuzzy CMeans diusulkan untuk melakukan segmentasi pada citra smear serviks [2]. Kemudian, beberapa peneliti mengusulkan teknik thresholding untuk proses segmentasi sel nukleus dan sitoplasma dari citra smear serviks [3]. Ada juga yang menggunakan metode watershed [4].…”

Section: Pendahuluanunclassified

Segmentasi Citra Sel Tunggal Smear Serviks Menggunakan Radiating Component Normalized Generalized GVFS

Husain¹,

Fatichah²

2017

Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI)

View full text Add to dashboard Cite

Abstract-Component Normalized Generalized GradientVector Flow Snake (CNGGVFS) method is the development of Gradient Vector Flow Snake (GVFS) method as an external force algorithm for active contour (snake) that can be used to get the contour of nucleus and cytoplasm of cervical smear image. However, CNGGVFS using a conventional calculation of edge map such as Sobel can not detect the nucleus area correctly in single cell cervical smear image segmentation. In this study, an external force algorithm in snake that uses Radiating Edge Intisari-Metode Component Normalized Generalized GradientVector Flow Snake (CNGGVFS) merupakan pengembangan dari metode Gradient Vector Flow Snake (GVFS) sebagai algoritme pengganti energi eksternal active countour (snake). Namun, CNGGVFS menggunakan perhitungan edge map konvensional seperti Sobel yang belum mampu mendeteksi daerah nukleus dengan benar pada segmentasi kontur citra sel tunggal smear serviks. Makalah ini mengusulkan algoritme pengganti energi eksternal pada snake yang memanfaatkan perhitungan Radiating Edge Map (REM) untuk pencarian edge map pada CNGGVFS yang dinamakan Radiating Component Normalized Generalized Gradient Vector Flow Snake (RCNGGVFS). Metode RCNGGVFS digunakan untuk mendapatkan kontur nukleus dan sitoplasma pada citra sel tunggal smear serviks. Terdapat tiga tahapan utama untuk melakukan segmentasi kontur citra sel tunggal smear serviks pada makalah ini, yaitu: pra proses, segmentasi awal, dan segmentasi kontur. Uji coba dilakukan dengan menggunakan data set Herlev. Pengujian dilakukan dengan membandingkan hasil segmentasi metode yang diusulkan dengan metode pada penelitian sebelumnya dalam melakukan segmentasi citra sel tunggal smear serviks. Hasil pengujian menunjukkan bahwa metode yang diusulkan mampu mendeteksi area nukleus lebih optimal dibanding metode Radiating GVFS & Fuzzy C-Means (FCM) dan Radiating GVFS & K-means. Nilai rata-rata akurasi dan Zijdenbos similarity index (ZSI) untuk segmentasi nukleus adalah 95,34% dan 88,06%. Kemudian, nilai rata-rata akurasi dan ZSI untuk segmentasi sitoplasma adalah 83,48% dan 87,16%. Dari hasil evaluasi tersebut, disimpulkan metode yang diusulkan dapat digunakan sebagai proses segmentasi citra smear serviks pada identifikasi kanker serviks secara otomatis. Kata Kunci-Radiating Component Normalized GeneralizedGradient Vector Flow Snake, sel tunggal smear serviks, ekstraksi kontur. I. PENDAHULUANPemeriksaan pap smear merupakan prosedur penapisan manual yang digunakan untuk mendeteksi kanker serviks yang dikembangkan oleh Dr. Georges Papanicolaou pada Tahun 1940. Hasil pemeriksaan akan menunjukkan sel-sel serviks masih normal atau sudah terdapat gejala awal kanker serviks. Analisis hasil pemeriksaan pap smear secara manual memiliki kelemahan yaitu membutuhkan banyak tenaga ahli di bidang patologi, memakan banyak waktu, dan rawan terhadap kesalahan. Sebuah sistem penyaringan otomatis dan sistem diagnosa yang akurat untuk hasil pemeriksaan pap smear akan sangat bermanfaat untuk mengatasi kelemahankelemahan tersebut....

show abstract

“…There are several methods which segments cervical cells. Earlier attempts to detect and segment cells in cervical microscopic images were based on image-thresholding techniques [5]. Pixel classification was also tried for the segmentation of cervical images [6].…”

Section: Problem Definition and Related Workmentioning

confidence: 99%

A fast and reliable approach to cell nuclei segmentation in PAP stained cervical smears

Byju

Sujathan

Malm

et al. 2013

CSIT

View full text Add to dashboard Cite

Fast and reliable segmentation of cervical cell nuclei is one of the crucial steps of an automated screening system that aims early detection of cervical cancer. In this paper, we propose an edge based approach using customized Laplacian of Gaussian (LoG) filter to segment free lying cell nuclei in bright-field microscope images of Pap smear. The LoG is generally employed as a second order edge detector in image processing. The images may have the challenges of inconsistent staining, overlapping and folded cells. Experimenting proposed method over all types of cervical images including sufficient number of high grade lesions of cervical cancer shows that our method performs well for stain varied images containing focused nuclei.

show abstract

Optimal segmentation of cell images

Cited by 56 publications

References 6 publications

An image analysis‐based approach for automated counting of cancer cell nuclei in tissue sections

An image analysis‐based approach for automated counting of cancer cell nuclei in tissue sections

Segmentasi Citra Sel Tunggal Smear Serviks Menggunakan Radiating Component Normalized Generalized GVFS

A fast and reliable approach to cell nuclei segmentation in PAP stained cervical smears

Contact Info

Product

Resources

About