Pathological image compression for big data image analysis: Application to hotspot detection in breast cancer

作者：

Highlights：

• We developed a novel ROI selection method where information most relevant to a task is stored and transmitted preferentially.

• The method minimizes the amount of data transfer between the storage (client) and computing nodes (server).

• Significantly reduces the computational demands of the decompression engine.

摘要

•We developed a novel ROI selection method where information most relevant to a task is stored and transmitted preferentially.•The method minimizes the amount of data transfer between the storage (client) and computing nodes (server).•Significantly reduces the computational demands of the decompression engine.

论文关键词：Compression,Pathology images,JPIP,Ki-67,Hotspot detection,Alpha shapes

论文评审过程：Received 15 May 2017, Revised 20 August 2018, Accepted 12 September 2018, Available online 25 September 2018, Version of Record 20 March 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2018.09.002