Noninvasive detection of bladder cancer using mid-infrared spectra classification

作者：

Highlights：

• New system is used to acquire mid-infrared spectra from urine samples.

• New PLSDA-based classifiers are designed for automatic bladder cancer detection.

• The best classifier allows for automatic detection of bladder cancer with an accuracy of 82.35%.

• A minimally invasive medical device with a high potential for screening and follow-up is envisioned.

摘要

•New system is used to acquire mid-infrared spectra from urine samples.•New PLSDA-based classifiers are designed for automatic bladder cancer detection.•The best classifier allows for automatic detection of bladder cancer with an accuracy of 82.35%.•A minimally invasive medical device with a high potential for screening and follow-up is envisioned.

论文关键词：Bladder cancer,Variable selection,Infrared spectroscopy,Automatic detection,Chalcogenide glass fibers,PLSDA,SVM

论文评审过程：Received 6 January 2017, Revised 6 July 2017, Accepted 29 July 2017, Available online 31 July 2017, Version of Record 24 August 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.07.052