دورية أكاديمية
Deep learning for cell image segmentation and ranking.
| العنوان: | Deep learning for cell image segmentation and ranking. |
|---|---|
| المؤلفون: | Araújo FHD; Federal University of Piauí, Brazil; Federal University of Ceará, Brazil. Electronic address: flavio86@ufpi.edu.br., Silva RRV; Federal University of Piauí, Brazil; Federal University of Ceará, Brazil. Electronic address: romuere@ufpi.edu.br., Ushizima DM; University of California, Berkeley, USA; Lawrence Berkeley National Laboratory, USA. Electronic address: dushizima@lbl.gov., Rezende MT; Federal University of Ouro Preto, Brazil. Electronic address: trevisanrezende@gmail.com., Carneiro CM; Federal University of Ouro Preto, Brazil. Electronic address: carneirocm@gmail.com., Campos Bianchi AG; Federal University of Ouro Preto, Brazil. Electronic address: andrea@ufop.edu.br., Medeiros FNS; Federal University of Ceará, Brazil. Electronic address: fsombra@ufc.br. |
| المصدر: | Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society [Comput Med Imaging Graph] 2019 Mar; Vol. 72, pp. 13-21. Date of Electronic Publication: 2019 Jan 30. |
| نوع المنشور: | Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S. |
| اللغة: | English |
| بيانات الدورية: | Publisher: Elsevier Science Country of Publication: United States NLM ID: 8806104 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-0771 (Electronic) Linking ISSN: 08956111 NLM ISO Abbreviation: Comput Med Imaging Graph Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: Tarrytown Ny : Elsevier Science Original Publication: New York : Pergamon Press, c1988- |
| مواضيع طبية MeSH: | Deep Learning*, Image Processing, Computer-Assisted/*methods, Algorithms ; Female ; Humans ; Neural Networks, Computer ; Papanicolaou Test ; Uterine Cervical Neoplasms/pathology |
| مستخلص: | Ninety years after its invention, the Pap test continues to be the most used method for the early identification of cervical precancerous lesions. In this test, the cytopathologists look for microscopic abnormalities in and around the cells, which is a time-consuming and prone to human error task. This paper introduces computational tools for cytological analysis that incorporate cell segmentation deep learning techniques. These techniques are capable of processing both free-lying and clumps of abnormal cells with a high overlapping rate from digitized images of conventional Pap smears. Our methodology employs a preprocessing step that discards images with a low probability of containing abnormal cells without prior segmentation and, therefore, performs faster when compared with the existing methods. Also, it ranks outputs based on the likelihood of the images to contain abnormal cells. We evaluate our methodology on an image database of conventional Pap smears from real scenarios, with 108 fields-of-view containing at least one abnormal cell and 86 containing only normal cells, corresponding to millions of cells. Our results show that the proposed approach achieves accurate results (MAP = 0.936), runs faster than existing methods, and it is robust to the presence of white blood cells, and other contaminants. (Copyright © 2019 Elsevier Ltd. All rights reserved.) |
| فهرسة مساهمة: | Keywords: Cervical cells; Convolutional neural network; Quantitative microscopy; Segmentation |
| تواريخ الأحداث: | Date Created: 20190215 Date Completed: 20200702 Latest Revision: 20200702 |
| رمز التحديث: | 20221213 |
| DOI: | 10.1016/j.compmedimag.2019.01.003 |
| PMID: | 30763802 |
| قاعدة البيانات: | MEDLINE |
Full Text via ClinicalKey 
Full Text Finder كن أول من يترك تعليقا!