BACKGROUND: Recent studies have shown that hyperspectral imaging (HSI) combined with neural networks can detect colorectal cancer. Usually, different pre-processing techniques (e.g., wavelength selection and scaling, smoothing, denoising) are analyzed in detail to achieve a well-trained network. The impact of post-processing was studied less. METHODS: We tested the following methods: (1) Two pre-processing techniques (Standardization and Normalization), with (2) Two 3D-CNN models: Inception-based and RemoteSensing (RS)-based, with (3) Two post-processing algorithms based on median filter: one applies a median filter to a raw predictions map, the other applies the filter to the predictions map after adopting a discrimination threshold. These approaches were evaluated on a dataset that contains ex vivo hyperspectral (HS) colorectal cancer records of 56 patients. RESULTS: (1) Inception-based models perform better than RS-based, with the best results being 92\% sensitivity and 94\% specificity; (2) Inception-based models perform better with Normalization, RS-based with Standardization; (3) Our outcomes show that the post-processing step improves sensitivity and specificity by 6.6\% in total. It was also found that both post-processing algorithms have the same effect, and this behavior was explained. CONCLUSION: HSI combined with tissue classification algorithms is a promising diagnostic approach whose performance can be additionally improved by the application of the right combination of pre- and post-processing.
%0 Journal Article
%1 Tkachenko2023-up
%A Tkachenko, Mariia
%A Chalopin, Claire
%A Jansen-Winkeln, Boris
%A Neumuth, Thomas
%A Gockel, Ines
%A Maktabi, Marianne
%D 2023
%J Cancers (Basel)
%K topic_lifescience cancer cancer; classification; colorectal convolutional filter; hyperspectral imaging; learning; machine median networks; post-processing; pre-processing
%N 7
%T Impact of pre- and post-processing steps for supervised classification of colorectal cancer in hyperspectral images
%V 15
%X BACKGROUND: Recent studies have shown that hyperspectral imaging (HSI) combined with neural networks can detect colorectal cancer. Usually, different pre-processing techniques (e.g., wavelength selection and scaling, smoothing, denoising) are analyzed in detail to achieve a well-trained network. The impact of post-processing was studied less. METHODS: We tested the following methods: (1) Two pre-processing techniques (Standardization and Normalization), with (2) Two 3D-CNN models: Inception-based and RemoteSensing (RS)-based, with (3) Two post-processing algorithms based on median filter: one applies a median filter to a raw predictions map, the other applies the filter to the predictions map after adopting a discrimination threshold. These approaches were evaluated on a dataset that contains ex vivo hyperspectral (HS) colorectal cancer records of 56 patients. RESULTS: (1) Inception-based models perform better than RS-based, with the best results being 92\% sensitivity and 94\% specificity; (2) Inception-based models perform better with Normalization, RS-based with Standardization; (3) Our outcomes show that the post-processing step improves sensitivity and specificity by 6.6\% in total. It was also found that both post-processing algorithms have the same effect, and this behavior was explained. CONCLUSION: HSI combined with tissue classification algorithms is a promising diagnostic approach whose performance can be additionally improved by the application of the right combination of pre- and post-processing.
@article{Tkachenko2023-up,
abstract = {BACKGROUND: Recent studies have shown that hyperspectral imaging (HSI) combined with neural networks can detect colorectal cancer. Usually, different pre-processing techniques (e.g., wavelength selection and scaling, smoothing, denoising) are analyzed in detail to achieve a well-trained network. The impact of post-processing was studied less. METHODS: We tested the following methods: (1) Two pre-processing techniques (Standardization and Normalization), with (2) Two 3D-CNN models: Inception-based and RemoteSensing (RS)-based, with (3) Two post-processing algorithms based on median filter: one applies a median filter to a raw predictions map, the other applies the filter to the predictions map after adopting a discrimination threshold. These approaches were evaluated on a dataset that contains ex vivo hyperspectral (HS) colorectal cancer records of 56 patients. RESULTS: (1) Inception-based models perform better than RS-based, with the best results being 92\% sensitivity and 94\% specificity; (2) Inception-based models perform better with Normalization, RS-based with Standardization; (3) Our outcomes show that the post-processing step improves sensitivity and specificity by 6.6\% in total. It was also found that both post-processing algorithms have the same effect, and this behavior was explained. CONCLUSION: HSI combined with tissue classification algorithms is a promising diagnostic approach whose performance can be additionally improved by the application of the right combination of pre- and post-processing.},
added-at = {2024-09-10T10:41:24.000+0200},
author = {Tkachenko, Mariia and Chalopin, Claire and Jansen-Winkeln, Boris and Neumuth, Thomas and Gockel, Ines and Maktabi, Marianne},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2b36ee879f7c50300b99c509c7a5f2f22/scadsfct},
interhash = {0e5eae9983317cf80cef0b48c896b666},
intrahash = {b36ee879f7c50300b99c509c7a5f2f22},
journal = {Cancers (Basel)},
keywords = {topic_lifescience cancer cancer; classification; colorectal convolutional filter; hyperspectral imaging; learning; machine median networks; post-processing; pre-processing},
language = {en},
month = apr,
number = 7,
timestamp = {2024-11-22T15:48:30.000+0100},
title = {Impact of pre- and post-processing steps for supervised classification of colorectal cancer in hyperspectral images},
volume = 15,
year = 2023
}
