Control and Diagnosis of Brain Tumors Using Deep Neural Networks

Alireza Izadi; Farshid Hajati; Roohollah Barzamini; Negar Janpors; Babak Farjad; Sahar Barzamini

doi:10.1007/978-3-031-28694-0_53

Control and Diagnosis of Brain Tumors Using Deep Neural Networks

Alireza Izadi
, Farshid Hajati
, Roohollah Barzamini
, Negar Janpors
, Babak Farjad
, Sahar Barzamini

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

Early recognition of various brain tumours can be useful for physicians to control and prevent the progression of the disease and can be very effective and useful in rescuing and healing patients. Computer-aided detection (CAD) plays an essential role in diagnosis and detection of numerous diseases. In this study, an artificial intelligence model, ResNet 50, is developed to diagnose three types of brain tumors (meningioma, gliomas, and pituitary tumors). The model is trained and tested based on a data set which contains 3064 MRI images. The model achieved an accuracy of 95.32% with a 95.11% precision, 95.15% recall, and 95.13% F1-score.

Original language	English
Title of host publication	Proceedings of the 37th International Conference on Advanced Information Networking and Applications (AINA-2023), Volume 3
Editors	Leonard Barolli
Place of Publication	Switzerland
Publisher	Springer Cham
Pages	562-572
Volume	3
ISBN (Print)	9783031286933, 9783031286940
DOIs	https://doi.org/10.1007/978-3-031-28694-0_53
Publication status	Published - 15 Mar 2023
Event	AINA 2023: The 37th International Conference on Advanced Information Networking and Applications - Federal University of Juiz de Fora, Brazil, Brazil Duration: 29 Mar 2023 → 31 Mar 2023

Publication series

Name	Lecture Notes in Networks and Systems
Number	655

Conference

Conference	AINA 2023: The 37th International Conference on Advanced Information Networking and Applications
City	Brazil
Period	29/03/23 → 31/03/23

Access to Document

10.1007/978-3-031-28694-0_53

https://hdl.handle.net/1959.11/70640

Handle.net

Persistent link

Cite this

Izadi, A., Hajati, F., Barzamini, R., Janpors, N., Farjad, B., & Barzamini, S. (2023). Control and Diagnosis of Brain Tumors Using Deep Neural Networks. In L. Barolli (Ed.), Proceedings of the 37th International Conference on Advanced Information Networking and Applications (AINA-2023), Volume 3 (Vol. 3, pp. 562-572). (Lecture Notes in Networks and Systems; No. 655). Springer Cham. https://doi.org/10.1007/978-3-031-28694-0_53

Izadi, Alireza ; Hajati, Farshid ; Barzamini, Roohollah et al. / Control and Diagnosis of Brain Tumors Using Deep Neural Networks. Proceedings of the 37th International Conference on Advanced Information Networking and Applications (AINA-2023), Volume 3. editor / Leonard Barolli. Vol. 3 Switzerland : Springer Cham, 2023. pp. 562-572 (Lecture Notes in Networks and Systems; 655).

@inproceedings{4cda4986bd11429182b2a795ec0351e0,

title = "Control and Diagnosis of Brain Tumors Using Deep Neural Networks",

abstract = "Early recognition of various brain tumours can be useful for physicians to control and prevent the progression of the disease and can be very effective and useful in rescuing and healing patients. Computer-aided detection (CAD) plays an essential role in diagnosis and detection of numerous diseases. In this study, an artificial intelligence model, ResNet 50, is developed to diagnose three types of brain tumors (meningioma, gliomas, and pituitary tumors). The model is trained and tested based on a data set which contains 3064 MRI images. The model achieved an accuracy of 95.32\% with a 95.11\% precision, 95.15\% recall, and 95.13\% F1-score.",

author = "Alireza Izadi and Farshid Hajati and Roohollah Barzamini and Negar Janpors and Babak Farjad and Sahar Barzamini",

year = "2023",

month = mar,

day = "15",

doi = "10.1007/978-3-031-28694-0\_53",

language = "English",

isbn = "9783031286933",

volume = "3",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Cham",

number = "655",

pages = "562--572",

editor = "Leonard Barolli",

booktitle = "Proceedings of the 37th International Conference on Advanced Information Networking and Applications (AINA-2023), Volume 3",

note = "AINA 2023: The 37th International Conference on Advanced Information Networking and Applications ; Conference date: 29-03-2023 Through 31-03-2023",

}

Izadi, A, Hajati, F, Barzamini, R, Janpors, N, Farjad, B & Barzamini, S 2023, Control and Diagnosis of Brain Tumors Using Deep Neural Networks. in L Barolli (ed.), Proceedings of the 37th International Conference on Advanced Information Networking and Applications (AINA-2023), Volume 3. vol. 3, Lecture Notes in Networks and Systems, no. 655, Springer Cham, Switzerland, pp. 562-572, AINA 2023: The 37th International Conference on Advanced Information Networking and Applications, Brazil, 29/03/23. https://doi.org/10.1007/978-3-031-28694-0_53

Control and Diagnosis of Brain Tumors Using Deep Neural Networks. / Izadi, Alireza; Hajati, Farshid; Barzamini, Roohollah et al.
Proceedings of the 37th International Conference on Advanced Information Networking and Applications (AINA-2023), Volume 3. ed. / Leonard Barolli. Vol. 3 Switzerland: Springer Cham, 2023. p. 562-572 (Lecture Notes in Networks and Systems; No. 655).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Control and Diagnosis of Brain Tumors Using Deep Neural Networks

AU - Izadi, Alireza

AU - Hajati, Farshid

AU - Barzamini, Roohollah

AU - Janpors, Negar

AU - Farjad, Babak

AU - Barzamini, Sahar

PY - 2023/3/15

Y1 - 2023/3/15

N2 - Early recognition of various brain tumours can be useful for physicians to control and prevent the progression of the disease and can be very effective and useful in rescuing and healing patients. Computer-aided detection (CAD) plays an essential role in diagnosis and detection of numerous diseases. In this study, an artificial intelligence model, ResNet 50, is developed to diagnose three types of brain tumors (meningioma, gliomas, and pituitary tumors). The model is trained and tested based on a data set which contains 3064 MRI images. The model achieved an accuracy of 95.32% with a 95.11% precision, 95.15% recall, and 95.13% F1-score.

AB - Early recognition of various brain tumours can be useful for physicians to control and prevent the progression of the disease and can be very effective and useful in rescuing and healing patients. Computer-aided detection (CAD) plays an essential role in diagnosis and detection of numerous diseases. In this study, an artificial intelligence model, ResNet 50, is developed to diagnose three types of brain tumors (meningioma, gliomas, and pituitary tumors). The model is trained and tested based on a data set which contains 3064 MRI images. The model achieved an accuracy of 95.32% with a 95.11% precision, 95.15% recall, and 95.13% F1-score.

U2 - 10.1007/978-3-031-28694-0_53

DO - 10.1007/978-3-031-28694-0_53

M3 - Conference contribution

SN - 9783031286933

SN - 9783031286940

VL - 3

T3 - Lecture Notes in Networks and Systems

SP - 562

EP - 572

BT - Proceedings of the 37th International Conference on Advanced Information Networking and Applications (AINA-2023), Volume 3

A2 - Barolli, Leonard

PB - Springer Cham

CY - Switzerland

T2 - AINA 2023: The 37th International Conference on Advanced Information Networking and Applications

Y2 - 29 March 2023 through 31 March 2023

ER -

Izadi A, Hajati F, Barzamini R, Janpors N, Farjad B, Barzamini S. Control and Diagnosis of Brain Tumors Using Deep Neural Networks. In Barolli L, editor, Proceedings of the 37th International Conference on Advanced Information Networking and Applications (AINA-2023), Volume 3. Vol. 3. Switzerland: Springer Cham. 2023. p. 562-572. (Lecture Notes in Networks and Systems; 655). doi: 10.1007/978-3-031-28694-0_53

Control and Diagnosis of Brain Tumors Using Deep Neural Networks

Abstract

Publication series

Conference

Access to Document

Handle.net

Fingerprint

Cite this