Search

Lettuce is an annual plant of the family Asteraceae. It is most often grown as a leaf vegetable, but sometimes for its stem and seeds, and its growth status and quality are evaluated based on its morphological phenotypic traits. However, traditional measurement methods are often labor-intensive and time-consuming due to manual measurements and may result in less accuracy. In this study, we proposed a new method utilizing RGB images and Mask R-Convolutional Neural Network (CNN) for estimating lettuce critical phenotypic traits. Leveraging publicly available datasets, we employed an improved Mask R-CNN model to perform a phenotypic analysis of lettuce images. This allowed us to estimate five phenotypic traits simultaneously, which include fresh weight, dry weight, plant height, canopy diameter, and leaf area. The enhanced Mask R-CNN model involved two key aspects: (1) replacing the backbone network from ResNet to RepVGG to enhance computational efficiency and performance; (2) adding phenotypic branches and constructing a multi-task regression model to achieve end-to-end estimation of lettuce phenotypic traits. Experimental results demonstrated that the present method achieved high accuracy and stable results in lettuce image segmentation, detection, and phenotypic estimation tasks, with APs for detection and segmentation being 0.8684 and 0.8803, respectively. Additionally, the R2 values for the five phenotypic traits are 0.96, 0.9596, 0.9329, 0.9136, and 0.9592, with corresponding mean absolute percentage errors (MAPEs) of 0.1072, 0.1522, 0.0757, 0.0548, and 0.0899, respectively. This study presents a novel technical advancement based on digital knowledge for phenotypic analysis and evaluation of lettuce quality, which could lay the foundation for artificial intelligence expiation in fresh vegetable production.

Introduction: It is worth to explore a more effective treatment method to minimize the damage for patients during the treatment process. Aim: To explore the method, feasibility and efficacy of B-ultrasound or computed tomography (CT)-guided 3D printing individualized non-coplanar template brachytherapy in the treatment of locally uncontrolled recurrent head and neck squamous cell carcinoma. Material and methods: Ten patients with locally uncontrolled recurrent head and neck squamous cell carcinoma who were treated in our department from August 2021 to February 2023 were collected and treated by 3D printing individualized non-coplanar template brachytherapy under the guidance of B-ultrasound or CT, using the 192Ir high-dose rate afterloading treatment machine of NUCLETRON Technologies GmbH. The radiation source was 192Ir, with a diameter of 0.5 mm, a length of 3.5 mm, a total dose of 10-24 Gy, 5-8 Gy/time, once a week. Results: According to the efficacy evaluation criteria, CT scan was performed after 1-6 months, followed up for 24 months, including CR 40% (4/10), PR 50% (5/10), NC 10% (5/10), PD 0 (0). The total effective rate of CR + PR was 90% (9/10), the 6-month local control rate was 90%, the 12-month local control rate was 80%, the 18-month local control rate was 70%, and the 24-month local control rate was 70%. The overall survival rate at 24 months was 100%. Conclusions: Safe and effective interpolation is used to guide the 3D printing of a single non-coplanar template with B-ultrasound or CT in the radiotherapy of local and uncontrolled recurrent head and neck squamous cell carcinoma. According to the guidance of B-ultrasound or CT, the 3D printing individualized non-coplanar template has an obvious healing effect especially in the brachytherapy, and can also protect the functional organs well, with less side effects and fewer complications. Therefore, this method is the most effective for the treatment of locally uncontrolled recurrent head and neck squamous cell carcinoma. [ABSTRACT FROM AUTHOR]