A Novel Deep Learning Approach in Haematology for Classification of Leucocytes

被引：4

作者：

Bevilacqua, Vitoantonio ^{[1
]}

Brunetti, Antonio ^{[1
]}

Trotta, Gianpaolo Francesco ^{[2
]}

De Marco, Domenico ^{[1
]}

Quercia, Marco Giuseppe ^{[1
]}

Buongiorno, Domenico ^{[1
]}

D'Introno, Alessia ^{[3
,4
]}

Girardi, Francesco ^{[5
]}

Guarini, Attilio ^{[6
]}

机构：

[1] Polytech Univ Bari, Dept Elect & Informat Engn, Via Orabona 4, I-70126 Bari, Italy

[2] Polytech Univ Bari, Dept Mech Math & Management DMMM, Via Orabona 4, I-70126 Bari, Italy

[3] Univ Bari Aldo Moro, Geriatr Med Memory Unit, Bari, Italy

[4] Univ Bari Aldo Moro, Rare Dis Ctr, Bari, Italy

[5] UVARP ASL Bari, Bari, Italy

[6] Ist Tumori Giovanni Paolo II IRCCS, Bari, Italy

来源：

QUANTIFYING AND PROCESSING BIOMEDICAL AND BEHAVIORAL SIGNALS | 2019年 / 103卷

关键词：

Computer aided diagnosis; Classification; Artificial neural network; Deep learning; Convolutional neural network; Transfer learning;

D O I：

10.1007/978-3-319-95095-2_25

中图分类号：

B84 [心理学]; C [社会科学总论]; Q98 [人类学];

学科分类号：

03 ; 0303 ; 030303 ; 04 ; 0402 ;

摘要：

This paper presents a comparison between two different Computer Aided Diagnosis systems for classification of five types of leucocytes located in the tail of a Peripheral Blood Smears: Lymphocytes, Monocytes, Neutrophils, Basophils and Eosinophils. In particular, we have evaluated and compared the performance of a previous feature-based Back Propagation Neural Network classifier with the performance of two novel classifiers both based on Deep Learning using Convolutional Neural Networks introduced in this study. All the classifiers are built considering the same dataset of images acquired in a previous study. The experimental results, reported in terms of accuracy, sensitivity, specificity and precision, show that the different strategies could be compared and discussed from both clinical and technical point of view.

引用

页码：265 / 274

页数：10

共 13 条

[1]

Alagappan M., 2012, INT C MATH MOD APPL, P846

[2]

Bevilacqua A, 2015, ESTRATTI DA CONGRESSO NAZIONALE SIFIOG, 2015, P1

[3]

Bevilacqua V, 2006, IEEE IJCNN, P1958

[4]

Bevilacqua V., 2017, LECT NOTES ARTIFICIA, V9773

[5]

Bevilacqua V., 2015, ADV ARTIFICIAL LIFE, P53

[6]

Bevilacqua V, 2008, LECT NOTES COMPUT SC, V5227, P1229, DOI 10.1007/978-3-540-85984-0_147

[7]

Bevilacqua V, 2016, IEEE INT SYM MED MEA, P346

[8]

Erhan D, 2010, J MACH LEARN RES, V11, P625

[9]

Fakoor R., 2015, P INT C MACH LEARN, P1310

[10] Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels [J].

Han, Bo ;

Yao, Quanming ;

Yu, Xingrui ;

Niu, Gang ;

Xu, Miao ;

Hu, Weihua ;

Tsang, Ivor W. ;

Sugiyama, Masashi .

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31

← 1 2 →