Journal of Spectral Imaging JSI—Journal of Spectral Imaging is an online, Open Access, peer-review journal publishing high-quality papers in the rapidly growing field of spectral, hyperspectral and chemical imaging. https://www.impopen.com/jsi-toc/10 IM Publications Open en © IM Publications Open LLP Journal of Spectral Imaging 2040-4565 © IM Publications Open LLP info@impopen.com Prospective study for commercial and low-cost hyperspectral imaging systems to evaluate thermal tissue effect on bovine liver samples https://doi.org/10.1255/jsi.2021.a5 Thermal ablation modalities, for example radiofrequency ablation (RFA) and microwave ablation, are intended to prompt controlled tumour removal by raising tissue temperature. However, monitoring the size of the resulting tissue damage during the thermal removal procedures is a challenging task. The objective of this study was to evaluate the observation of RFA on an ex vivo liver sample with both a commercial and a low-cost system to distinguish between the normal and the ablated regions as well as the thermally affected regions. RFA trials were conducted on five different ex vivo normal bovine samples and monitored initially by a custom hyperspectral (HS) camera to measure the diffuse reflectance (Rd) utilising a polychromatic light source (tungsten halogen lamp) within the spectral range 348–950 nm. Next, the light source was replaced with monochromatic LEDs (415, 565 and 660 nm) and a commercial charge-coupled device (CCD) camera was used instead of the HS camera. The system algorithm comprises image enhancement (normalisation and moving average filter) and image segmentation with K-means clustering, combining spectral and spatial information to assess the variable responses to polychromatic light and monochromatic LEDs to highlight the differences in the Rd properties of thermally affected/normal tissue regions. The measured spectral signatures of the various regions, besides the calculation of the standard deviations (?) between the generated six groups, guided us to select three optimal wavelengths (420, 540 and 660 nm) to discriminate between these various regions. Next, we selected six spectral images to apply the image processing to (at 450, 500, 550, 600, 650 and 700 nm). We noticed that the optimum image is the superimposed spectral images at 550, 600, 650 and 700 nm, which are capable of discriminating between the various regions. Later, we measured Rd with the CCD camera and commercially available monochromatic LED light sources at 415, 565 and 660 nm. Compared to the HS camera results, this system was more capable of identifying the ablated and the thermally affected regions of surface RFA than the side-penetration RFA of the investigated ex vivo liver samples. However, we succeeded in developing a low-cost system that provides satisfactory information to highlight the ablated and thermally affected region to improve the outcome of surgical tumour ablation with much shorter time for image capture and processing compared to the HS system. Prospective study for commercial and low-cost hyperspectral imaging systems to evaluate thermal tissue effect on bovine liver samples

J. Spectral Imaging 10, a5 (2021). doi:10.1255/jsi.2021.a5

Thermal ablation modalities, for example radiofrequency ablation (RFA) and microwave ablation, are intended to prompt controlled tumour removal by raising tissue temperature. However, monitoring the size of the resulting tissue damage during the thermal removal procedures is a challenging task. The objective of this study was to evaluate the observation of RFA on an ex vivo liver sample with both a commercial and a low-cost system to distinguish between the normal and the ablated regions as well as the thermally affected regions. RFA trials were conducted on five different ex vivo normal bovine samples and monitored initially by a custom hyperspectral (HS) camera to measure the diffuse reflectance (Rd) utilising a polychromatic light source (tungsten halogen lamp) within the spectral range 348–950 nm. Next, the light source was replaced with monochromatic LEDs (415, 565 and 660 nm) and a commercial charge-coupled device (CCD) camera was used instead of the HS camera. The system algorithm comprises image enhancement (normalisation and moving average filter) and image segmentation with K-means clustering, combining spectral and spatial information to assess the variable responses to polychromatic light and monochromatic LEDs to highlight the differences in the Rd properties of thermally affected/normal tissue regions. The measured spectral signatures of the various regions, besides the calculation of the standard deviations (?) between the generated six groups, guided us to select three optimal wavelengths (420, 540 and 660 nm) to discriminate between these various regions. Next, we selected six spectral images to apply the image processing to (at 450, 500, 550, 600, 650 and 700 nm). We noticed that the optimum image is the superimposed spectral images at 550, 600, 650 and 700 nm, which are capable of discriminating between the various regions. Later, we measured Rd with the CCD camera and commercially available monochromatic LED light sources at 415, 565 and 660 nm. Compared to the HS camera results, this system was more capable of identifying the ablated and the thermally affected regions of surface RFA than the side-penetration RFA of the investigated ex vivo liver samples. However, we succeeded in developing a low-cost system that provides satisfactory information to highlight the ablated and thermally affected region to improve the outcome of surgical tumour ablation with much shorter time for image capture and processing compared to the HS system.

]]>
Prospective study for commercial and low-cost hyperspectral imaging systems to evaluate thermal tissue effect on bovine liver samples Mohamed Hisham Aref Abou-Bakr M. Youssef Ibrahim H. Aboughaleb Amr A.R. Sharawi Abdallah Abdelkader Hussein Paola Saccomandi Yasser H. El-Sharkawy doi:10.1255/jsi.2021.a5 J. Spectral Imaging 10, a5 (2021) 2021-10-04 Journal of Spectral Imaging 2021-10-04 10 1 27 10.1255/jsi.2021.a5 https://doi.org/10.1255/jsi.2021.a5
Hyperspectral reflectance for non-invasive early detection of black shank disease in flue-cured tobacco https://doi.org/10.1255/jsi.2021.a4 Flue-cured tobacco (Nicotiana tabacum L.) is a high value-per-acre crop that is intensively managed to optimise the yield of high-quality cured leaf. A 15-day study assessed the potential of hyperspectral reflectance data for detecting Phytophthora nicotianae (black shank) incidence in flue-cured tobacco. Hyperspectral reflectance data were taken from a commercial flue-cured tobacco field with a progressing black shank infestation. The effort encompassed two key objectives. First, develop hyperspectral indices and/or machine learning classification models capable of detecting Phytophthora nicotianae (black shank) incidence in flue-cured tobacco. Second, evaluate the model’s ability to separate pre-symptomatic plants from healthy plants. Two hyperspectral indices were developed to detect black shank incidence based on differences in the spectral profiles of asymptomatic flue-cured tobacco plants compared to those with black shank symptoms. While one of the indices is a broad-band index and the other uses narrow wavelength values, the statistical difference between the two indices was not significant and both provided an accurate classification of symptomatic plants. Further analysis of the indices showed significant differences between the index values of healthy and symptomatic plants (? = 0.05). In addition, the indices were able to detect black shank symptoms pre-symptomatically (? = 0.09). Subspace linear discriminant analysis, a machine learning classification, was also used for prediction of black shank incidence with up to 85.7 % classification accuracy. The implications of using either spectral indices or machine learning for classification for future black shank research are discussed. Hyperspectral reflectance for non-invasive early detection of black shank disease in flue-cured tobacco

J. Spectral Imaging 10, a4 (2021). doi:10.1255/jsi.2021.a4

Flue-cured tobacco (Nicotiana tabacum L.) is a high value-per-acre crop that is intensively managed to optimise the yield of high-quality cured leaf. A 15-day study assessed the potential of hyperspectral reflectance data for detecting Phytophthora nicotianae (black shank) incidence in flue-cured tobacco. Hyperspectral reflectance data were taken from a commercial flue-cured tobacco field with a progressing black shank infestation. The effort encompassed two key objectives. First, develop hyperspectral indices and/or machine learning classification models capable of detecting Phytophthora nicotianae (black shank) incidence in flue-cured tobacco. Second, evaluate the model’s ability to separate pre-symptomatic plants from healthy plants. Two hyperspectral indices were developed to detect black shank incidence based on differences in the spectral profiles of asymptomatic flue-cured tobacco plants compared to those with black shank symptoms. While one of the indices is a broad-band index and the other uses narrow wavelength values, the statistical difference between the two indices was not significant and both provided an accurate classification of symptomatic plants. Further analysis of the indices showed significant differences between the index values of healthy and symptomatic plants (? = 0.05). In addition, the indices were able to detect black shank symptoms pre-symptomatically (? = 0.09). Subspace linear discriminant analysis, a machine learning classification, was also used for prediction of black shank incidence with up to 85.7 % classification accuracy. The implications of using either spectral indices or machine learning for classification for future black shank research are discussed.

]]>
Hyperspectral reflectance for non-invasive early detection of black shank disease in flue-cured tobacco Austin Hayes T. David Reed doi:10.1255/jsi.2021.a4 J. Spectral Imaging 10, a4 (2021) 2021-09-28 Journal of Spectral Imaging 2021-09-28 10 1 10 10.1255/jsi.2021.a4 https://doi.org/10.1255/jsi.2021.a4
Estimation of strawberry firmness using hyperspectral imaging: a comparison of regression models https://doi.org/10.1255/jsi.2021.a3 Firmness is one of the most important quality measures of strawberries, and is related to other aspects of the fruit, such as flavour, ripeness and internal characteristics. The most popular method for measuring firmness is puncturing with a penetrometer, which is destructive and time-consuming. In the present study, we make an attempt to predict the firmness of strawberries in a fast, non-destructive and non-contact way using hyperspectral imaging (HSI) and data analysis with various regression techniques. The primary goal of this research is to investigate and compare the firmness prediction capability of seven prominent regression techniques. We have performed HSI data acquisition of 150 strawberries and optimised seven regression models using the spectral information to predict strawberry firmness. These models are linear, ridge, lasso, k-neighbours, random forest, support vector and partial least square regression. The results show that HSI data with regression models has the potential to predict firmness in a rapid, non-destructive manner. Out of these seven regression models, the k-neighbours regression model outperformed all other methods with a standard error of prediction of 0.14, which is better than that of the state-of-the-art results. Estimation of strawberry firmness using hyperspectral imaging: a comparison of regression models

J. Spectral Imaging 10, a3 (2021). doi:10.1255/jsi.2021.a3

Firmness is one of the most important quality measures of strawberries, and is related to other aspects of the fruit, such as flavour, ripeness and internal characteristics. The most popular method for measuring firmness is puncturing with a penetrometer, which is destructive and time-consuming. In the present study, we make an attempt to predict the firmness of strawberries in a fast, non-destructive and non-contact way using hyperspectral imaging (HSI) and data analysis with various regression techniques. The primary goal of this research is to investigate and compare the firmness prediction capability of seven prominent regression techniques. We have performed HSI data acquisition of 150 strawberries and optimised seven regression models using the spectral information to predict strawberry firmness. These models are linear, ridge, lasso, k-neighbours, random forest, support vector and partial least square regression. The results show that HSI data with regression models has the potential to predict firmness in a rapid, non-destructive manner. Out of these seven regression models, the k-neighbours regression model outperformed all other methods with a standard error of prediction of 0.14, which is better than that of the state-of-the-art results.

]]>
Estimation of strawberry firmness using hyperspectral imaging: a comparison of regression models Binu Melit Devassy Sony George doi:10.1255/jsi.2021.a3 J. Spectral Imaging 10, a3 (2021) 2021-06-30 Journal of Spectral Imaging 2021-06-30 10 1 14 10.1255/jsi.2021.a3 https://doi.org/10.1255/jsi.2021.a3
1D conditional generative adversarial network for spectrum-to-spectrum translation of simulated chemical reflectance signatures https://doi.org/10.1255/jsi.2021.a2 The classification of trace chemical residues through active spectroscopic sensing is challenging due to the lack of physics-based models that can accurately predict spectra. To overcome this challenge, we leveraged the field of domain adaptation to translate data from the simulated to the measured domain for training a classifier. We developed the first 1D conditional generative adversarial network (GAN) to perform spectrum-to-spectrum translation of reflectance signatures. We applied the 1D conditional GAN to a library of simulated spectra and quantified the improvement in classification accuracy on real data using the translated spectra for training the classifier. Using the GAN-translated library, the average classification accuracy increased from 0.622 to 0.723 on real chemical reflectance data, including data from chemicals not included in the GAN training set. 1D conditional generative adversarial network for spectrum-to-spectrum translation of simulated chemical reflectance signatures

J. Spectral Imaging 10, a2 (2021). doi:10.1255/jsi.2021.a2

The classification of trace chemical residues through active spectroscopic sensing is challenging due to the lack of physics-based models that can accurately predict spectra. To overcome this challenge, we leveraged the field of domain adaptation to translate data from the simulated to the measured domain for training a classifier. We developed the first 1D conditional generative adversarial network (GAN) to perform spectrum-to-spectrum translation of reflectance signatures. We applied the 1D conditional GAN to a library of simulated spectra and quantified the improvement in classification accuracy on real data using the translated spectra for training the classifier. Using the GAN-translated library, the average classification accuracy increased from 0.622 to 0.723 on real chemical reflectance data, including data from chemicals not included in the GAN training set.

]]>
1D conditional generative adversarial network for spectrum-to-spectrum translation of simulated chemical reflectance signatures Cara P. Murphy John Kerekes doi:10.1255/jsi.2021.a2 J. Spectral Imaging 10, a2 (2021) 2021-06-11 Journal of Spectral Imaging 2021-06-11 10 1 11 10.1255/jsi.2021.a2 https://doi.org/10.1255/jsi.2021.a2
IDCube Lite: Free Interactive Discovery Cube software for multi and hyperspectral applications https://doi.org/10.1255/jsi.2021.a1 Multi- and hyperspectral imaging modalities encompass a growing number of spectral techniques that find many applications in geospatial, biomedical, machine vision and other fields. The rapidly increasing number of applications requires convenient easy-to-navigate software that can be used by new and experienced users to analyse data, and develop, apply and deploy novel algorithms. Herein, we present our platform, IDCube Lite, an Interactive Discovery Cube that performs essential operations in hyperspectral data analysis to realise the full potential of spectral imaging. The strength of the software lies in its interactive features that enable the users to optimise parameters and obtain visual input for the user in a way not previously accessible with other software packages. The entire software can be operated without any prior programming skills allowing interactive sessions of raw and processed data. IDCube Lite, a free version of the software described in the paper, has many benefits compared to existing packages and offers structural flexibility to discover new, hidden features that allow users to integrate novel computational methods. IDCube Lite: Free Interactive Discovery Cube software for multi and hyperspectral applications

J. Spectral Imaging 10, a1 (2021). doi:10.1255/jsi.2021.a1

Multi- and hyperspectral imaging modalities encompass a growing number of spectral techniques that find many applications in geospatial, biomedical, machine vision and other fields. The rapidly increasing number of applications requires convenient easy-to-navigate software that can be used by new and experienced users to analyse data, and develop, apply and deploy novel algorithms. Herein, we present our platform, IDCube Lite, an Interactive Discovery Cube that performs essential operations in hyperspectral data analysis to realise the full potential of spectral imaging. The strength of the software lies in its interactive features that enable the users to optimise parameters and obtain visual input for the user in a way not previously accessible with other software packages. The entire software can be operated without any prior programming skills allowing interactive sessions of raw and processed data. IDCube Lite, a free version of the software described in the paper, has many benefits compared to existing packages and offers structural flexibility to discover new, hidden features that allow users to integrate novel computational methods.

]]>
IDCube Lite: Free Interactive Discovery Cube software for multi and hyperspectral applications Deependra Mishra Helena Hurbon John Wang Steven T. Wang Tommy Du Qian Wu David Kim Shiva Basir Qian Cao Hairong Zhang Kathleen Xu Andy Yu Yifan Zhang Yunshen Huang Roman Garnett Maria Gerasimchuk-Djordjevic Mikhail Y. Berezin doi:10.1255/jsi.2021.a1 J. Spectral Imaging 10, a1 (2021) 2021-05-05 Journal of Spectral Imaging 2021-05-05 10 1 12 10.1255/jsi.2021.a1 https://doi.org/10.1255/jsi.2021.a1