Journal article
Explainable liver tumor delineation in surgical specimens using hyperspectral imaging and deep learning
Biomedical optics express, Vol.12(7), pp.4510-4529
07/01/2021
DOI: 10.1364/BOE.432654
Abstract
Surgical removal is the primary treatment for liver cancer, but frequent recurrence caused by residual malignant tissue remains an important challenge, as recurrence leads to high mortality. It is unreliable to distinguish tumors from normal tissues merely under visual inspection. Hyperspectral imaging (HSI) has been proved to be a promising technology for intra-operative use by capturing the spatial and spectral information of tissue in a fast, non-contact and label-free manner. In this work, we investigated the feasibility of HSI for liver tumor delineation on surgical specimens using a multi-task U-Net framework. Measurements are performed on 19 patients and a dataset of 36 specimens was collected with corresponding pathological results serving as the ground truth. The developed framework can achieve an overall sensitivity of 94.48% and a specificity of 87.22%, outperforming the baseline SVM method by a large margin. In particular, we propose to add explanations on the well-trained model from the spatial and spectral dimensions to show the contribution of pixels and spectral channels explicitly. On that basis, a novel saliency-weighted channel selection method is further proposed to select a small subset of 5 spectral channels which provide essentially as much information as using all 224 channels. According to the dominant channels, the absorption difference of hemoglobin and bile content in the normal and malignant tissues seems to be promising markers that could be further exploited.
Details
- Title: Subtitle
- Explainable liver tumor delineation in surgical specimens using hyperspectral imaging and deep learning
- Creators
- Yating Zhang - Tsinghua UniversitySi Yu - Peking Union Medical College HospitalXueyu Zhu - University of IowaXuefei Ning - Tsinghua UniversityWei Liu - Chinese Academy of Medical Sciences & Peking Union Medical CollegeChuting Wang - Peking Union Medical College HospitalXiaohu Liu - Tsinghua UniversityDing Zhao - Tsinghua UniversityYongchang Zheng - Peking Union Medical College HospitalJie Bao - Tsinghua University
- Resource Type
- Journal article
- Publication Details
- Biomedical optics express, Vol.12(7), pp.4510-4529
- Publisher
- OPTICAL SOC AMER
- DOI
- 10.1364/BOE.432654
- ISSN
- 2156-7085
- eISSN
- 2156-7085
- Number of pages
- 20
- Grant note
- 504054 / Simons Foundation CFHPC 2020021 / WBE Liver Fibrosis Foundation BNR2019ZS01005 / Beijing National Research Center For Information Science And Technology 2020I2MCTB019 / CAMS Innovation Fund for Medical Sciences (CIFMS)
- Language
- English
- Date published
- 07/01/2021
- Academic Unit
- Mathematics
- Record Identifier
- 9984241153502771
Metrics
8 Record Views