CLASSIFICATION OF PULMONARY EMBOLISM ON COMPUTED TOMOGRAPHY ANGIOGRAPHY USING ARTIFICIAL INTELLIGENCE

被引：0

作者：

Silva, Luan ^{[1
,3
]}

Carolina, Maria ^{[1
]}

Ribeiro, Guilherme ^{[1
]}

Ortiz, Thiago ^{[1
,2
]}

Victor, Paulo ^{[1
,2
]}

Mendes, Giovanna ^{[1
]}

de Paiva, Joselisa ^{[1
]}

Calixto, Wesley ^{[2
]}

Rittner, Leticia ^{[1
,4
]}

Loureiro, Rafael ^{[1
]}

Reis, Marcio ^{[1
]}

Soares, Anderson ^{[3
]}

机构：

[1] Hosp Israelita Albert Einstein, Sao Paulo, Brazil

[2] Univ Fed Goias, Elect Mech & Comp Engn Sch, Goiania, Go, Brazil

[3] Univ Fed Goias, Inst Informat INF, Goiania, Go, Brazil

[4] Univ Estadual Campinas, Dept Comp Engn & Ind Automat, Sao Paulo, Brazil

来源：

IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI 2024 | 2024年

关键词：

Pulmonary Embolism; Deep Learning; CT pulmonary angiography; Convolutional Neural Network;

D O I：

10.1109/ISBI56570.2024.10635197

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Pulmonary embolism is a serious condition in which a blood clot (thrombus) forms in a deep vein, usually in the legs (deep vein thrombosis), and then travels to the lungs and blocks the pulmonary artery. The diagnosis of pulmonary embolism is a complex process as there is a variety of clinical presentations and the symptoms overlap with other medical conditions. This study aims to fill a gap by proposing a classification model for pulmonary embolism, trained on limited annotated public data and validated on a comprehensive in-house dataset. The results showed that the classification model is promising in detecting negative cases of pulmonary embolism and has satisfactory precision (95%) and recall (96%). Its efficiency in avoiding false-positive diagnoses indicates its reliability in identifying patients without pulmonary embolism, which plays an important role in clinical practice.

引用

页数：5

共 19 条

[1] How artificial intelligence improves radiological interpretation in suspected pulmonary embolism [J].

Ben Cheikh, Alexandre ;

Gorincour, Guillaume ;

Nivet, Hubert ;

May, Julien ;

Seux, Mylene ;

Calame, Paul ;

Thomson, Vivien ;

Delabrousse, Eric ;

Crombe, Amandine .

EUROPEAN RADIOLOGY, 2022, 32 (09) :5831-5842

[2] WEAKLY SUPERVISED MULTIMODAL 30-DAY ALL-CAUSE MORTALITY PREDICTION FOR PULMONARY EMBOLISM PATIENTS [J].

Cahan, Noa ;

Marom, Edith M. ;

Soffer, Shelly ;

Barash, Yiftach ;

Konen, Eli ;

Klang, Eyal ;

Greenspan, Hayit .

2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022), 2022,

[3] Computer Aided Detection of Pulmonary Embolism Using Multi-Slice Multi-Axial Segmentation [J].

Cano-Espinosa, Carlos ;

Cazorla, Miguel ;

Gonzalez, German .

APPLIED SCIENCES-BASEL, 2020, 10 (08)

[4]

Chung JY, 2014, Arxiv, DOI [arXiv:1412.3555, DOI 10.48550/ARXIV.1412.3555]

[5] The RSNA Pulmonary Embolism CT Dataset [J].

Cob, Errol ;

Kitamura, Felipe C. ;

Hobbs, Stephen B. ;

Wu, Carol C. ;

Lungren, Matthew P. ;

Prevedello, Luciano M. ;

Kalpathy-Cramer, Jayashree ;

Ball, Robyn L. ;

Shih, George ;

Stein, Anouk ;

Halabi, Safwan S. ;

Akinmakas, Emre ;

Law, Meng ;

Kumar, Parveen ;

Manzalawi, Karam A. ;

Rubio, Dennis Charles Nelson ;

Sechrist, Jacob W. ;

Germaine, Pauline ;

Lopez, Eva Castro ;

Amerio, Tomas ;

Gupta, Puslpender ;

Jain, Manoj ;

Kay, Fernando U. ;

Lin, Cheng Ting ;

Sen, Saugata ;

Revels, Jonathan Wesley ;

Brussaarel, Carok C. ;

Mongan, John .

RADIOLOGY-ARTIFICIAL INTELLIGENCE, 2021, 3 (02) :1-7

[6] Measuring and managing radiologist workload: Measuring radiologist reporting times using data from a Radiology Information System [J].

Cowan, Ian A. ;

MacDonald, Sharyn L. S. ;

Floyd, Richard A. .

JOURNAL OF MEDICAL IMAGING AND RADIATION ONCOLOGY, 2013, 57 (05) :558-566

[7]

Graves A, 2013, INT CONF ACOUST SPEE, P6645, DOI 10.1109/ICASSP.2013.6638947

[8]

Graves A, 2012, STUD COMPUT INTELL, V385, P37

[9]

Hochreiter Sepp, 1997, Neural Computation, V9, P11

[10]

Huang SC, 2020, NPJ DIGIT MED, V3, DOI 10.1038/s41746-020-00310-6

← 1 2 →