Dataset Information

Hyperspectral Imaging Combined With Deep Transfer Learning for Rice Disease Detection

ABSTRACT: Various rice diseases threaten the growth of rice. It is of great importance to achieve the rapid and accurate detection of rice diseases for precise disease prevention and control. Hyperspectral imaging (HSI) was performed to detect rice leaf diseases in four different varieties of rice. Considering that it costs much time and energy to develop a classifier for each variety of rice, deep transfer learning was firstly introduced to rice disease detection across different rice varieties. Three deep transfer learning methods were adapted for 12 transfer tasks, namely, fine-tuning, deep CORrelation ALignment (CORAL), and deep domain confusion (DDC). A self-designed convolutional neural network (CNN) was set as the basic network of the deep transfer learning methods. Fine-tuning achieved the best transferable performance with an accuracy of over 88% for the test set of the target domain in the majority of transfer tasks. Deep CORAL obtained an accuracy of over 80% in four of all the transfer tasks, which was superior to that of DDC. A multi-task transfer strategy has been explored with good results, indicating the potential of both pair-wise, and multi-task transfers. A saliency map was used for the visualization of the key wavelength range captured by CNN with and without transfer learning. The results indicated that the wavelength range with and without transfer learning was overlapped to some extent. Overall, the results suggested that deep transfer learning methods could perform rice disease detection across different rice varieties. Hyperspectral imaging, in combination with the deep transfer learning method, is a promising possibility for the efficient and cost-saving field detection of rice diseases among different rice varieties.

SUBMITTER: Feng L

PROVIDER: S-EPMC8511421 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The currently available methods for evaluating most biochemical traits of plant phenotyping are destructive and have extremely low throughput. However, hyperspectral techniques can non-destructively obtain the spectral reflectance characteristics of plants, which can provide abundant biophysical and biochemical information. Therefore, plant spectra combined with machine learning algorithms can be used to predict plant phenotyping traits. However, the raw spectral reflectance characteristics contain noise and redundant information, thus can easily affect the robustness of the models developed via multivariate analysis methods. In this study, two end-to-end deep learning models were developed based on 2D convolutional neural networks (2DCNN) and fully connected neural networks (FCNN; Deep2D and DeepFC, respectively) to rapidly and non-destructively predict the phenotyping traits of lettuces from spectral reflectance. Three linear and two nonlinear multivariate analysis methods were used to develop models to weigh the performance of the deep learning models. The models based on multivariate analysis methods require a series of manual feature extractions, such as pretreatment and wavelength selection, while the proposed models can automatically extract the features in relation to phenotyping traits. A visible near-infrared hyperspectral camera was used to image lettuce plants growing in the field, and the spectra extracted from the images were used to train the network. The proposed models achieved good performance with a determination coefficient of prediction ( Rp2 ) of 0.9030 and 0.8490 using Deep2D for soluble solids content and DeepFC for pH, respectively. The performance of the deep learning models was compared with five multivariate analysis method. The quantitative analysis showed that the deep learning models had higher Rp2 than all the multivariate analysis methods, indicating better performance. Also, wavelength selection and different pretreatment methods had different effects on different multivariate analysis methods, and the selection of appropriate multivariate analysis methods and pretreatment methods increased more time and computational cost. Unlike multivariate analysis methods, the proposed deep learning models did not require any pretreatment or dimensionality reduction and thus are more suitable for application in high-throughput plant phenotyping platforms. These results indicate that the deep learning models can better predict phenotyping traits of plants using spectral reflectance.

Project description:Surgical resection of head and neck (H and N) squamous cell carcinoma (SCC) may yield inadequate surgical cancer margins in 10 to 20% of cases. This study investigates the performance of label-free, reflectance-based hyperspectral imaging (HSI) and autofluorescence imaging for SCC detection at the cancer margin in excised tissue specimens from 102 patients and uses fluorescent dyes for comparison. Fresh surgical specimens (n = 293) were collected during H and N SCC resections (n = 102). The tissue specimens were imaged with reflectance-based HSI and autofluorescence imaging and afterwards with two fluorescent dyes for comparison. A histopathological ground truth was made. Deep learning tools were developed to detect SCC with new patient samples (inter-patient) and machine learning for intra-patient tissue samples. Area under the curve (AUC) of the receiver-operator characteristic was used as the main evaluation metric. Additionally, the performance was estimated in mm increments circumferentially from the tumor-normal margin. In intra-patient experiments, HSI classified conventional SCC with an AUC of 0.82 up to 3 mm from the cancer margin, which was more accurate than proflavin dye and autofluorescence (both p < 0.05). Intra-patient autofluorescence imaging detected human papilloma virus positive (HPV+) SCC with an AUC of 0.99 at 3 mm and greater accuracy than proflavin dye (p < 0.05). The inter-patient results showed that reflectance-based HSI and autofluorescence imaging outperformed proflavin dye and standard red, green, and blue (RGB) images (p < 0.05). In new patients, HSI detected conventional SCC in the larynx, oropharynx, and nasal cavity with 0.85-0.95 AUC score, and autofluorescence imaging detected HPV+ SCC in tonsillar tissue with 0.91 AUC score. This study demonstrates that label-free, reflectance-based HSI and autofluorescence imaging methods can accurately detect the cancer margin in ex-vivo specimens within minutes. This non-ionizing optical imaging modality could aid surgeons and reduce inadequate surgical margins during SCC resections.

Dataset Information

Hyperspectral Imaging Combined With Deep Transfer Learning for Rice Disease Detection

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets