Privacy focused classification of prostate cancer using federated learning

Syeda Umme Salma; Md Sadman Sakib; Nahiyan Yasaar; Mohammed Moinul Morshed Alvee; Md Tanzim Reza; Mohammad Zavid Parvez

doi:10.1007/978-981-99-8324-7_24

Privacy focused classification of prostate cancer using federated learning

Syeda Umme Salma, Md Sadman Sakib, Nahiyan Yasaar, Mohammed Moinul Morshed Alvee, Md Tanzim Reza, Mohammad Zavid Parvez

BRAC University

Research output: Book chapter/Published conference paper › Conference paper › peer-review

Abstract

Prostate cancer detection is an extremely challenging problem due to the socially sensitive nature of the data. As such, it negatively impacts early detection, including new procedures becoming difficult to develop owing to a lack of enough datasets. The proposed approach, which is based on Federated Learning, is a decentralized strategy that uses weight averaging and can quickly find anomalies while retaining data confidentiality. Additionally, the results of the customized basic CNN model with three Conv2D layers and two state-of-the-art models, VGG19 and Xception, were compared to those obtained in centralized and decentralized configurations. To recapitulate, this research’s findings indicate that the decentralized technique yields results that are very consistent with those yielded by state-of-the-art centralized methods.

Original language	English
Title of host publication	Proceedings of International Conference on Information Technology and Applications - ICITA 2023
Editors	Abrar Ullah, Sajid Anwar, Davide Calandra, Raffaele Di Fuccio
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	265-281
Number of pages	17
ISBN (Electronic)	9789819983247
ISBN (Print)	9789819983230
DOIs	https://doi.org/10.1007/978-981-99-8324-7_24
Publication status	Published - 2024
Event	17th International Conference on Information Technology and Applications ICITA: ICITA 2023 - University of Turin, Turin, Italy Duration: 20 Oct 2023 → 22 Oct 2023 https://www.worldconferencealerts.com/conferencedetail/WCA508449/17th-international-conference-on-information-technology-and-applications-icita https://2023.icita.world/#/ (Event website) https://www.icita.world/files/ICITA_2023.pdf (Program)

Publication series

Name	Lecture Notes in Networks and Systems
Volume	839
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	17th International Conference on Information Technology and Applications ICITA
Country/Territory	Italy
City	Turin
Period	20/10/23 → 22/10/23
Other	The 17th International Conference on Information Technology and Applications (ICITA 2023) will be held in Turin, Italy on 20 - 22 October 2023. The conference is an annual event and recognized as one of the major series of conferences in Information Technology (IT in short). ICITA continues to retain its tradition of being a high quality conference. The event will open an opportunity for academics and industry professionals worldwide to exchange their knowledge of the state-of-the-art research and development in information technology and applications. It will help participants establish new links and extend professional networks. This conference addresses the importance that IT professionals stretch across narrowly defined subject areas and constantly acquire a global technical and social perspective. ICITA 2023 offers such an opportunity to facilitate cross-disciplinary and social gatherings.
Internet address	https://www.worldconferencealerts.com/conferencedetail/WCA508449/17th-international-conference-on-information-technology-and-applications-icita https://2023.icita.world/#/ (Event website) https://www.icita.world/files/ICITA_2023.pdf (Program)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-981-99-8324-7_24

Cite this

Salma, S. U., Sakib, M. S., Yasaar, N., Alvee, M. M. M., Reza, M. T., & Parvez, M. Z. (2024). Privacy focused classification of prostate cancer using federated learning. In A. Ullah, S. Anwar, D. Calandra, & R. Di Fuccio (Eds.), Proceedings of International Conference on Information Technology and Applications - ICITA 2023 (pp. 265-281). (Lecture Notes in Networks and Systems; Vol. 839). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-8324-7_24

Salma, Syeda Umme ; Sakib, Md Sadman ; Yasaar, Nahiyan et al. / Privacy focused classification of prostate cancer using federated learning. Proceedings of International Conference on Information Technology and Applications - ICITA 2023. editor / Abrar Ullah ; Sajid Anwar ; Davide Calandra ; Raffaele Di Fuccio. Springer Science and Business Media Deutschland GmbH, 2024. pp. 265-281 (Lecture Notes in Networks and Systems).

@inproceedings{08c908eee70b479aa5a05d1484982d0b,

title = "Privacy focused classification of prostate cancer using federated learning",

abstract = "Prostate cancer detection is an extremely challenging problem due to the socially sensitive nature of the data. As such, it negatively impacts early detection, including new procedures becoming difficult to develop owing to a lack of enough datasets. The proposed approach, which is based on Federated Learning, is a decentralized strategy that uses weight averaging and can quickly find anomalies while retaining data confidentiality. Additionally, the results of the customized basic CNN model with three Conv2D layers and two state-of-the-art models, VGG19 and Xception, were compared to those obtained in centralized and decentralized configurations. To recapitulate, this research{\textquoteright}s findings indicate that the decentralized technique yields results that are very consistent with those yielded by state-of-the-art centralized methods.",

keywords = "Distributed learning, Federated learning, Medical imaging, Privacy, Prostate cancer, Secure deep learning",

author = "Salma, {Syeda Umme} and Sakib, {Md Sadman} and Nahiyan Yasaar and Alvee, {Mohammed Moinul Morshed} and Reza, {Md Tanzim} and Parvez, {Mohammad Zavid}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 17th International Conference on Information Technology and Applications ICITA : ICITA 2023 ; Conference date: 20-10-2023 Through 22-10-2023",

year = "2024",

doi = "10.1007/978-981-99-8324-7_24",

language = "English",

isbn = "9789819983230",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "265--281",

editor = "Abrar Ullah and Sajid Anwar and Davide Calandra and {Di Fuccio}, Raffaele",

booktitle = "Proceedings of International Conference on Information Technology and Applications - ICITA 2023",

address = "Germany",

url = "https://www.worldconferencealerts.com/conferencedetail/WCA508449/17th-international-conference-on-information-technology-and-applications-icita, https://2023.icita.world/#/, https://www.icita.world/files/ICITA_2023.pdf",

}

Salma, SU, Sakib, MS, Yasaar, N, Alvee, MMM, Reza, MT & Parvez, MZ 2024, Privacy focused classification of prostate cancer using federated learning. in A Ullah, S Anwar, D Calandra & R Di Fuccio (eds), Proceedings of International Conference on Information Technology and Applications - ICITA 2023. Lecture Notes in Networks and Systems, vol. 839, Springer Science and Business Media Deutschland GmbH, pp. 265-281, 17th International Conference on Information Technology and Applications ICITA, Turin, Italy, 20/10/23. https://doi.org/10.1007/978-981-99-8324-7_24

Privacy focused classification of prostate cancer using federated learning. / Salma, Syeda Umme; Sakib, Md Sadman; Yasaar, Nahiyan et al.
Proceedings of International Conference on Information Technology and Applications - ICITA 2023. ed. / Abrar Ullah; Sajid Anwar; Davide Calandra; Raffaele Di Fuccio. Springer Science and Business Media Deutschland GmbH, 2024. p. 265-281 (Lecture Notes in Networks and Systems; Vol. 839).

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Privacy focused classification of prostate cancer using federated learning

AU - Salma, Syeda Umme

AU - Sakib, Md Sadman

AU - Yasaar, Nahiyan

AU - Alvee, Mohammed Moinul Morshed

AU - Reza, Md Tanzim

AU - Parvez, Mohammad Zavid

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - Prostate cancer detection is an extremely challenging problem due to the socially sensitive nature of the data. As such, it negatively impacts early detection, including new procedures becoming difficult to develop owing to a lack of enough datasets. The proposed approach, which is based on Federated Learning, is a decentralized strategy that uses weight averaging and can quickly find anomalies while retaining data confidentiality. Additionally, the results of the customized basic CNN model with three Conv2D layers and two state-of-the-art models, VGG19 and Xception, were compared to those obtained in centralized and decentralized configurations. To recapitulate, this research’s findings indicate that the decentralized technique yields results that are very consistent with those yielded by state-of-the-art centralized methods.

AB - Prostate cancer detection is an extremely challenging problem due to the socially sensitive nature of the data. As such, it negatively impacts early detection, including new procedures becoming difficult to develop owing to a lack of enough datasets. The proposed approach, which is based on Federated Learning, is a decentralized strategy that uses weight averaging and can quickly find anomalies while retaining data confidentiality. Additionally, the results of the customized basic CNN model with three Conv2D layers and two state-of-the-art models, VGG19 and Xception, were compared to those obtained in centralized and decentralized configurations. To recapitulate, this research’s findings indicate that the decentralized technique yields results that are very consistent with those yielded by state-of-the-art centralized methods.

KW - Distributed learning

KW - Federated learning

KW - Medical imaging

KW - Privacy

KW - Prostate cancer

KW - Secure deep learning

UR - http://www.scopus.com/inward/record.url?scp=85189502807&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85189502807&partnerID=8YFLogxK

U2 - 10.1007/978-981-99-8324-7_24

DO - 10.1007/978-981-99-8324-7_24

M3 - Conference paper

AN - SCOPUS:85189502807

SN - 9789819983230

T3 - Lecture Notes in Networks and Systems

SP - 265

EP - 281

BT - Proceedings of International Conference on Information Technology and Applications - ICITA 2023

A2 - Ullah, Abrar

A2 - Anwar, Sajid

A2 - Calandra, Davide

A2 - Di Fuccio, Raffaele

PB - Springer Science and Business Media Deutschland GmbH

T2 - 17th International Conference on Information Technology and Applications ICITA

Y2 - 20 October 2023 through 22 October 2023

ER -

Salma SU, Sakib MS, Yasaar N, Alvee MMM, Reza MT, Parvez MZ. Privacy focused classification of prostate cancer using federated learning. In Ullah A, Anwar S, Calandra D, Di Fuccio R, editors, Proceedings of International Conference on Information Technology and Applications - ICITA 2023. Springer Science and Business Media Deutschland GmbH. 2024. p. 265-281. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-99-8324-7_24

Privacy focused classification of prostate cancer using federated learning

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this