Deep learning algorithm development for early detection of Botrytis cinerea infected strawberry fruit using hyperspectral fluorescence imaging

Authors: CHUN, SEUNG-WOO - Kangwon National University; SONG, DOO-JIN - Kangwon National University; LEE, KWANG-HO - Kangwon National University; KIM, MIIN-JEE - Kangwon National University; Kim, Moon; KYOUNG-SU, KIM - Kangwon National University; MO, CHANGYEUN - Kangwon National University

Submitted to: Postharvest Biology and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/25/2024
Publication Date: 5/10/2024
Citation: Chun, S., Song, D., Lee, K., Kim, M., Kim, M.S., Kyoung-Su, K., Mo, C. 2024. Deep learning algorithm development for early detection of Botrytis cinerea infected strawberry fruit using hyperspectral fluorescence imaging. Postharvest Biology and Technology. 214: Article e112918. https://doi.org/10.1016/j.postharvbio.2024.112918.
DOI: https://doi.org/10.1016/j.postharvbio.2024.112918

Interpretive Summary: Fungal infection of fruits during postharvest storage or transportation can spread rapidly, resulting in significant economic loss. There is a need to develop early diagnostic techniques to prevent the spread of the fungal infection and loss of fruits during the processing, storage, and distribution stages. A hyperspectral fluorescence imaging study was conducted to develop a method to rapidly determine four stages of fungal infection on strawberries. Fluorescence spectra of fruit samples, both infected and non-infected, were extracted from the hyperspectral image data to develop a one-dimensional convolutional neural network model in conjunction with the applications of data augmentation techniques and six spectral preprocessing techniques. The results of this study showed that it is possible to determine the fungal infection stages on strawberries with over 94% accuracy. The nondestructive evaluation technology can potentially be used by fruit producers and processors in the fresh produce industry for screening of fungal infection on strawberries at growth, postharvest sorting and packaging, and distribution stages.

Technical Abstract: Botrytis cinerea is a strawberry disease that causes economic loss worldwide. If a disease outbreak occurs during storage or transportation, it can spread rapidly to neighboring objects; thus, there is a need to develop early diagnostic techniques to prevent it. In this study, we developed a method to rapidly and nondestructively determine the infection stage in strawberry fruit using hyperspectral fluorescence imaging. ‘Keumsil’ cultivar strawberries were used, and hyperspectral fluorescence images were acquired over 144 h in control and inoculation groups. Strawberries were categorized into four infection stages based on visible mold spores: healthy, asymptomatic, infected, and after-infected. Hyperspectral fluorescence spectra were extracted to develop a one-dimensional convolutional neural network (1D-CNN) model based on partial least squares-discriminant analysis (PLS-DA), VGG-19, and ResNet-50; data augmentation techniques and six spectral preprocessing techniques were applied to the datasets. The application of data augmentation techniques improved the performances of the PLS-DA and 1D-CNN models in determining the infection stage. The performance of the ResNet-50-based 1D-CNN model with mean normalization data and data augmentation technique was the best, with 94.77 % precision, 94.72 % recall, 94.72 % F1-score, and 94.57 % accuracy. The results of this study showed that it is possible to determine the infection stage of Botrytis cinerea on strawberry fruit using hyperspectral fluorescence imaging and 1D-CNN techniques. This technology is expected to be applied for the early detection of Botrytis cinerea in strawberry growth, postharvest sorting and packing, and distribution stages.