Abstract
The development of digital stethoscopes and automatic respiratory sound algorithms is crucial for accelerating diagnosis, reducing physician workload, and lowering mortality rates from respiratory diseases. However, transmitting data from digital stethoscopes to cloud or other storage devices requires substantial storage and transmission capacities, especially for wearable devices used for long-term monitoring. Besides, current automatic algorithms often predict labels for segmented sound events, lacking precision in detecting the onsets and offsets of respiratory sound events. To address these challenges, we organized a Grand Challenge inviting the community to develop data compression and event detection algorithms to reduce the storage and transmission burden and event segmentation workload. A new testing set was prepared to evaluate the performance of the submissions. The top teams presented their work at the 20th IEEE Biomedical Circuits and Systems Conference (BioCAS) 2024.
Funding Information
  • National Key Research and Development Program of China (2019YFB2204500)
  • Medical-Engineering Joint Funds of Shanghai Jiao Tong University (YG2024ZD20, YG2021QN109, YG2022QN095)
  • Shanghai Public Health Excellent Talent Project (GWVI-11.2-YQ58)
  • Science and Technology Committee of Shanghai, China (22015821400)
  • Sanya Science and Technology Special Fund (2022KJCX41)
  • Hainan Provincial Health and Health Commission research program (22A200147)
  • Hainan Province Science and Technology Special Fund (ZDYF2024SHFZ059)
  • JINYE ZHONGZI Project from SCMC-HN (JYZZ-HQ-202106)
  • Science and Technology Committee of Shanghai, China (20DZ2253900)

This publication has 30 references indexed in Scilit: