DF-SegDiff: A Diffusion Segmentation Model using a New Distributed Parallel Computing Algorithm

Hancang Mi, Hong Seng Gan*, Xiaoyi Wang, Akinobu Shimizu, Muhammad Hanif Ramlee, Mehmet Zubeyir Unlu

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Brain tumours are among the most life-threatening diseases, and automatic segmentation of brain tumours from medical images is crucial for clinicians to identify and quantify tumour regions with high precision. While traditional segmentation models have laid the groundwork, diffusion models have since been developed to better manage complex medical data. However, diffusion models often face challenges related to insufficient parallel computing power and inefficient GPU utilization. To address these issues, we propose the DF-SegDiff model, which includes diffusion segmentation, parallel data processing, a distributed training model, a dynamic balancing parameter and model fusion. This approach significantly reduces training time while achieving an average Dice score of 0.87, with several samples reaching Dice values close to 0.94. By combining BRATS2020 with the Medical Segmentation Decathlon dataset, we also integrated a comprehensive dataset containing 800 training samples and 53 test samples. Evaluation of the model using Dice, IoU, and other relevant metrics demonstrates that our method outperforms current state-of-the-art techniques.

Original languageEnglish
Title of host publication2024 IEEE International Conference on Cognitive Computing and Complex Data, ICCD 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages13-17
Number of pages5
ISBN (Electronic)9798350352894
DOIs
Publication statusPublished - 2024
Event2024 IEEE International Conference on Cognitive Computing and Complex Data, ICCD 2024 - Qinzhou, China
Duration: 28 Sept 202430 Sept 2024

Publication series

Name2024 IEEE International Conference on Cognitive Computing and Complex Data, ICCD 2024

Conference

Conference2024 IEEE International Conference on Cognitive Computing and Complex Data, ICCD 2024
Country/TerritoryChina
CityQinzhou
Period28/09/2430/09/24

Keywords

  • Brain Tumour
  • Diffusion
  • Distributed Algorithms
  • Segmentation

Fingerprint

Dive into the research topics of 'DF-SegDiff: A Diffusion Segmentation Model using a New Distributed Parallel Computing Algorithm'. Together they form a unique fingerprint.

Cite this