Chamani Shiranthika
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Chamani Shiranthika has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Parvaneh Saeedi
Simon Fraser University
5 shared publications - Ivan V. Bajic
School of Engineering Science Simon Fraser University Burnaby BC Canada
3 shared publications - Chan-Yun Yang
Department of Electrical Engineering, National Taipei University, New Taipei City, Taiwan
2 shared publications Chung-Yih Wang
Department of Radiation Oncology, Cheng Hsin General Hospital, Taipei City, Taiwan
2 shared publications- Hadi Hadizadeh
School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada
2 shared publications Nilantha Premakumara
University of Moratuwa,Faculty of Information Technology,Moratuwa,Sri Lanka
2 shared publications
Latest Publications
- 8 July 2026
- Published by Springer Nature
- p. 153-163
When to Adapt? Adapting the Model or Data in Federated Medical Imaging
- 8 July 2026
- Published by Springer Nature
- p. 153-163
When to Adapt? Adapting the Model or Data in Federated Medical Imaging
- Open Access
- 15 January 2026
- Published by MDPI AG in Bioengineering
- Vol. 13 (1) , 104
MedSegNet10: A Publicly Accessible Network Repository for Split Federated Medical Image Segmentation
Machine Learning (ML) and Deep Learning (DL) have shown significant promise in healthcare, particularly in medical image segmentation, which is crucial for accurate disease diagnosis and treatment planning. Despite their potential, challenges such as data privacy concerns, limited annotated data, and inadequate training data persist. Decentralized learning approaches such as federated learning (FL), split learning (SL), and split federated learning (SplitFed/SFL) address these issues effectively. This paper introduces “MedSegNet10,” a publicly accessible repository designed for medical image segmentation using split-federated learning. MedSegNet10 provides a collection of pre-trained neural network architectures optimized for various medical image types, including microscopic images of human blastocysts, dermatoscopic images of skin lesions, and endoscopic images of lesions, polyps, and ulcers. MedSegNet10 implements SplitFed versions of ten established segmentation architectures, enabling collaborative training without centralizing raw data and labels, reducing the computational load required at client sites. This repository supports researchers, practitioners, trainees, and data scientists, aiming to advance medical image segmentation while maintaining patient data privacy.
- 15 January 2026
- Published by MDPI AG in Bioengineering
- Vol. 13 (1) , 104
Open AccessMedSegNet10: A Publicly Accessible Network Repository for Split Federated Medical Image Segmentation
Machine Learning (ML) and Deep Learning (DL) have shown significant promise in healthcare, particularly in medical image segmentation, which is crucial for accurate disease diagnosis and treatment planning. Despite their potential, challenges such as data privacy concerns, limited annotated data, and inadequate training data persist. Decentralized learning approaches such as federated learning (FL), split learning (SL), and split federated learning (SplitFed/SFL) address these issues effectively. This paper introduces “MedSegNet10,” a publicly accessible repository designed for medical image segmentation using split-federated learning. MedSegNet10 provides a collection of pre-trained neural network architectures optimized for various medical image types, including microscopic images of human blastocysts, dermatoscopic images of skin lesions, and endoscopic images of lesions, polyps, and ulcers. MedSegNet10 implements SplitFed versions of ten established segmentation architectures, enabling collaborative training without centralizing raw data and labels, reducing the computational load required at client sites. This repository supports researchers, practitioners, trainees, and data scientists, aiming to advance medical image segmentation while maintaining patient data privacy.
- Open Access
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 182496-182515
Adaptive Asynchronous Split Federated Learning for Medical Image Segmentation
Split federated (SplitFed) learning offers promise for collaborative machine learning across decentralized and resource-constrained clients (edge devices, nodes, or organizations) in various applications, including healthcare. However, real-world challenges arise in heterogeneous environments where clients experience communication-related data losses, differ in computational capabilities, and have varying local dataset sizes. In this paper, we introduce adaptive asynchronous split federated learning (AASFL), an innovative training scheme to address such challenges. AASFL blends asynchronous SplitFed learning with client-level adaptability, acknowledging varying client capabilities. In AASFL, each client independently adapts its learning rate and the number of local training epochs based on its local training speed, dataset size, and packet loss probability. To demonstrate the effectiveness of AASFL, we implement and evaluate it on a SplitFed network architecture for medical image segmentation. Moreover, we demonstrate the validity of AASFL by emphasizing the necessity of training each client in the collaborative network and revealing drawbacks of client selection. The results on two public datasets indicate that it greatly enhances global model performance, leading to more accurate segmentation results. We also statistically show that AASFL outperforms the standard SplitFed. Furthermore, we provide a theoretical convergence analysis of AASFL. To the best of our knowledge, this is the first analysis of SplitFed in an adaptive, asynchronous setting. The proposed AASFL training scheme offers a promising avenue for improving medical image segmentation tasks in practical decentralized learning environments.
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 182496-182515
Open AccessAdaptive Asynchronous Split Federated Learning for Medical Image Segmentation
Split federated (SplitFed) learning offers promise for collaborative machine learning across decentralized and resource-constrained clients (edge devices, nodes, or organizations) in various applications, including healthcare. However, real-world challenges arise in heterogeneous environments where clients experience communication-related data losses, differ in computational capabilities, and have varying local dataset sizes. In this paper, we introduce adaptive asynchronous split federated learning (AASFL), an innovative training scheme to address such challenges. AASFL blends asynchronous SplitFed learning with client-level adaptability, acknowledging varying client capabilities. In AASFL, each client independently adapts its learning rate and the number of local training epochs based on its local training speed, dataset size, and packet loss probability. To demonstrate the effectiveness of AASFL, we implement and evaluate it on a SplitFed network architecture for medical image segmentation. Moreover, we demonstrate the validity of AASFL by emphasizing the necessity of training each client in the collaborative network and revealing drawbacks of client selection. The results on two public datasets indicate that it greatly enhances global model performance, leading to more accurate segmentation results. We also statistically show that AASFL outperforms the standard SplitFed. Furthermore, we provide a theoretical convergence analysis of AASFL. To the best of our knowledge, this is the first analysis of SplitFed in an adaptive, asynchronous setting. The proposed AASFL training scheme offers a promising avenue for improving medical image segmentation tasks in practical decentralized learning environments.
- 25 July 2024
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 118
Development of gravitationally aligned pendant IMU frailty identifier
- 25 July 2024
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 118
Development of gravitationally aligned pendant IMU frailty identifier
- 1 December 2023
- Published by Springer Nature
- p. 367-377
SplitFed Resilience to Packet Loss: Where to Split, that is the Question
- 1 December 2023
- Published by Springer Nature
- p. 367-377
SplitFed Resilience to Packet Loss: Where to Split, that is the Question
- Open Access
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 54188-54209
Decentralized Learning in Healthcare: A Review of Emerging Techniques
Recent developments in deep learning have contributed to numerous success stories in healthcare. The performance of a deep learning model generally improves with the size of the training data. However, there are privacy, ownership, and regulatory issues that prevent combining medical data into traditional centralized storage. With common, universal deep learning models and centralized aggregator servers, Federated Learning (FL) overcomes the aforementioned difficulties. Additionally, patient data remains at the local party, upholding the security and anonymity of the data. Split Learning (SL) enables machine learning without directly accessing data on clients or end devices. It further enhances privacy in a decentralized setting and mitigates clients’ storage issues. In this survey, we first provide a contemporary survey of the decentralized learning approaches of FL, SL, and the hybrid approaches of FL and SL. Second, we discuss their state-of-the-art applications in healthcare, particularly in medical image analysis. Third, we review decentralized learning approaches under challenging conditions such as statistical and system heterogeneity, privacy preservation, communication efficiency, fairness, etc. Then, we address existing approaches to tackle these challenges. Finally, we discuss the challenges specific to healthcare and show the promising potential of decentralized learning approaches in the future of healthcare.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 54188-54209
Open AccessDecentralized Learning in Healthcare: A Review of Emerging Techniques
Recent developments in deep learning have contributed to numerous success stories in healthcare. The performance of a deep learning model generally improves with the size of the training data. However, there are privacy, ownership, and regulatory issues that prevent combining medical data into traditional centralized storage. With common, universal deep learning models and centralized aggregator servers, Federated Learning (FL) overcomes the aforementioned difficulties. Additionally, patient data remains at the local party, upholding the security and anonymity of the data. Split Learning (SL) enables machine learning without directly accessing data on clients or end devices. It further enhances privacy in a decentralized setting and mitigates clients’ storage issues. In this survey, we first provide a contemporary survey of the decentralized learning approaches of FL, SL, and the hybrid approaches of FL and SL. Second, we discuss their state-of-the-art applications in healthcare, particularly in medical image analysis. Third, we review decentralized learning approaches under challenging conditions such as statistical and system heterogeneity, privacy preservation, communication efficiency, fairness, etc. Then, we address existing approaches to tackle these challenges. Finally, we discuss the challenges specific to healthcare and show the promising potential of decentralized learning approaches in the future of healthcare.
- 25 November 2022
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 229, 107280
Reinforcement learning strategies in cancer chemotherapy treatments: A review
- 25 November 2022
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 229, 107280
Reinforcement learning strategies in cancer chemotherapy treatments: A review
- 17 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (9) , 4763-4772
Supervised Optimal Chemotherapy Regimen Based on Offline Reinforcement Learning
In recent years, reinforcement learning (RL) has achieved a remarkable achievement and it has attracted researchers’ attention in modeling real-life scenarios by expanding its research beyond conventional complex games. Prediction of optimal treatment regimens from observational real clinical data is being popularized, and more advanced versions of RL algorithms are being implemented in the literature. However, RL-generated medications still need careful supervision of expertise parties or doctors in healthcare. Hence, in this paper, a Supervised Optimal Chemotherapy Regimen (SOCR) approach to investigate optimal chemotherapy-dosing schedule for cancer patients was presented by using Offline Reinforcement Learning. The optimal policy suggested by the RL approach was supervised by incorporating previous treatment decisions of oncologists, which could add clinical expertise knowledge on algorithmic results. Presented SOCR approach followed a model-based architecture using conservative Q-Learning (CQL) algorithm. The developed model was tested using a manually constructed database of forty Stage-IV colon cancer patients, receiving line-1 chemotherapy treatments, who were clinically classified as ‘Bevacizumab based patient’ and ‘Cetuximab based patient’. Experimental results revealed that the supervision from the oncologists has considered the effect to stabilize chemotherapy regimen and it was suggested that the proposed framework could be successfully used as a supportive model for oncologists in deciding their treatment decisions.
- 17 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (9) , 4763-4772
Supervised Optimal Chemotherapy Regimen Based on Offline Reinforcement Learning
In recent years, reinforcement learning (RL) has achieved a remarkable achievement and it has attracted researchers’ attention in modeling real-life scenarios by expanding its research beyond conventional complex games. Prediction of optimal treatment regimens from observational real clinical data is being popularized, and more advanced versions of RL algorithms are being implemented in the literature. However, RL-generated medications still need careful supervision of expertise parties or doctors in healthcare. Hence, in this paper, a Supervised Optimal Chemotherapy Regimen (SOCR) approach to investigate optimal chemotherapy-dosing schedule for cancer patients was presented by using Offline Reinforcement Learning. The optimal policy suggested by the RL approach was supervised by incorporating previous treatment decisions of oncologists, which could add clinical expertise knowledge on algorithmic results. Presented SOCR approach followed a model-based architecture using conservative Q-Learning (CQL) algorithm. The developed model was tested using a manually constructed database of forty Stage-IV colon cancer patients, receiving line-1 chemotherapy treatments, who were clinically classified as ‘Bevacizumab based patient’ and ‘Cetuximab based patient’. Experimental results revealed that the supervision from the oncologists has considered the effect to stabilize chemotherapy regimen and it was suggested that the proposed framework could be successfully used as a supportive model for oncologists in deciding their treatment decisions.
- 24 July 2019
- Published by Springer Nature
- p. 583-592
Realtime Computer Vision-Based Accurate Vehicle Counting and Speed Estimation for Highways
- 24 July 2019
- Published by Springer Nature
- p. 583-592
Realtime Computer Vision-Based Accurate Vehicle Counting and Speed Estimation for Highways
- 1 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Application of Summarization and Sentiment Analysis in the Tourism domain
Text summarization helps in reducing the size of a text while preserving its information content. Text Summarization can be derived as shortening the source text in to a version that it’s information content and overall meaning is preserved. It is very difficult for human beings to manually summarize large documents of text. These Text summarization methods can be classified into two broader methods such as extractive summarization and abstractive summarization. The prior method consists of selecting important sentences; paragraphs etc. from the source document and make a brief version of it by combining them. The latter method consists of understanding the overall meaning embedded in the original text and re-generates the content briefly. Sentiment analysis on the other hand is the process of computationally identifying and categorizing opinions expressed in text to clarify someone’s’ attitude towards a topic is positive or else negative or even neutral. In this paper, a Survey of Summarization and sentiment analysis and their application in the tourism domain has been presented.
- 1 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Application of Summarization and Sentiment Analysis in the Tourism domain
Text summarization helps in reducing the size of a text while preserving its information content. Text Summarization can be derived as shortening the source text in to a version that it’s information content and overall meaning is preserved. It is very difficult for human beings to manually summarize large documents of text. These Text summarization methods can be classified into two broader methods such as extractive summarization and abstractive summarization. The prior method consists of selecting important sentences; paragraphs etc. from the source document and make a brief version of it by combining them. The latter method consists of understanding the overall meaning embedded in the original text and re-generates the content briefly. Sentiment analysis on the other hand is the process of computationally identifying and categorizing opinions expressed in text to clarify someone’s’ attitude towards a topic is positive or else negative or even neutral. In this paper, a Survey of Summarization and sentiment analysis and their application in the tourism domain has been presented.