Developing an automatic warning system for anomalous chicken dispersion and movement using deep learning and machine learning.

Chicken is a major source of dietary protein worldwide. The dispersion and movement of chickens constitute vital indicators of their health and status. This is especially evident in Taiwanese native chickens (TNCs), a local variety which is high in physical activity when healthy. Conventionally, the dispersion and movement of chicken flocks are observed in patrols. However, manual patrolling is laborious and time-consuming. Moreover, frequent patrols increase the risk of carrying pathogens into chicken farms. To address these issues, this study proposes an approach to develop an automatic warning system for anomalous dispersion and movement of chicken flocks in commercial chicken farms. Embendded systems were developed to acquire videos of chickens from overhead view in a chicken house, in which approximately 20,000 TNCs were raised for a period of 10 wk. Each video was 5-min in length. The videos were transmitted to a remote cloud server and were converted into images. A You Only Look Once-version 7 tiny (YOLOv7-tiny) object detection model was trained to detect chickens in the images. The dispersion of the chicken flocks in a 5-min long video was calculated using nearest neighbor index (NNI). The movement of the chicken flocks in a 5-min long video was quantified using simple online and real-time tracking algorithm (SORT). The normal ranges (i.e., 95% confidence intervals) of chicken dispersion and movement were established using an autoregressive integrated moving average (ARIMA) model and a seasonal autoregressive integrated moving average with exogenous factors (SARIMAX) model, respectively. The system allows farmers to check up on the chicken farm only when the dispersion or movement values were not in the normal ranges. Thus, labor time can be saved and the risk of carrying pathogens into chicken farms can be reduced. The trained YOLOv7-tiny model achieved an average precision of 98.2% in chicken detection. SORT achieved a multiple object tracking accuracy of 95.3%. The ARIMA and SARIMAX achieved a mean absolute percentage error 3.71% and 13.39%, respectively, in forecasting dispersion and movement. The proposed approach can serve as a solution for automatic monitoring of anomalous chicken dispersion and movement in chicken farming, alerting farmers of potential health risks and environmental hazards in chicken farms.

Nectar Guide Patterns on Developmentally Homologous Regions of the Subtribe Ligeriinae (Gesneriaceae).

Homology is a crucial concept that should be considered while conducting a comparative analysis between organisms. In particular, in the subtribe Ligeriinae, the nectar guide pattern is associated with high diversity in petal shapes and sizes. This largely limits researchers to exclusively examining the interspecific variation in nectar guide patterns on the developmentally homologous region. Thus, to solve this problem, we proposed an approach for defining a homologous region of interest (ROI) that aligns the petal image between specimens based on petal contours and vasculatures. We identified petal contours and vasculatures from the fresh petal image and its histological image through image processing. The homologous ROI was subsequently obtained by applying geometric transformation to the contour and vasculature. The qualification and quantification of nectar guide patterns were subsequently performed based on the homologous ROI. Four patterning modes, namely vascular, random, distal, and proximal, were defined for the qualitative analysis of nectar guide patterns. In the quantitative analysis, principal component (PC) analysis was applied to homologous ROIs, and the PC score of each specimen served as the trait values of nectar guide patterns. The results of the two analyses coincided, and both showed significant associations between nectar guide patterns and pollination types. The proximal mode (corresponding to PC1) and distal mode (corresponding to PC2) together showed the strongest association with pollination types. Species exhibiting the hummingbird and bee pollination types tended to recruit the distal and proximal modes, respectively. Our study conducted a comparative analysis of nectar guide patterns on the developmentally homologous region and provided a comprehensive view of the variation in the nectar guide patterns of Ligeriinae.

Automatic Identification of First-Order Veins and Corolla Contours in Three-Dimensional Floral Images.

Defining and quantifying corolla traits are essential for studying corolla shape variation. Three-dimensional (3D) images of corollas contain comprehensive information regarding corolla structures and are optimal for studying corolla shapes. Conventionally, corolla traits are identified and quantified manually from 3D images. Manual identification is time consuming and labor intensive. In this study, approaches are proposed to automatically identify first-order veins and corolla contours in 3D corolla images. The first-order veins of the corollas were identified using Hessian of Gaussian and Dijkstra's algorithm. The contours of the corollas were identified using vector harmony and node distance thresholding. A total of 130 3D images of 28 species in the subtribe Ligeriinae were collected and used to test the proposed approaches. The successful detection rate reached 86.54%. Two derived traits, contour-vein ratio and corolla angle, were defined and quantified using the first-order veins and corolla contour results to investigate the relationship between corolla shapes and pollination types of the subtribe Ligeriinae. Analyses revealed that the mean corolla contour, mean absolute corolla angle, and mean contour-vein ratio of the ornithophilic species were significantly smaller compared with the other species. The mean corolla contour, mean corolla angle, and mean contour-vein ratio of the melittophilic species were significantly larger compared with those of the ornithophilic species. The proposed method was also applied to certain Gesneriaceae species in the subtribes Gloxiniinae, Streptocarpinae, and Didymocarpinae. The results revealed that the method could be applied to most fresh sympetalous flowers for identifying first-order veins and corolla contours.

3D revelation of phenotypic variation, evolutionary allometry, and ancestral states of corolla shape: a case study of clade Corytholoma (subtribe Ligeriinae, family Gesneriaceae).

BACKGROUND: Quantification of corolla shape variations helps biologists to investigate plant diversity and evolution. 3D images capture the genuine structure and provide comprehensive spatial information. RESULTS: This study applied X-ray micro-computed tomography (µCT) to acquire 3D structures of the corollas of clade Corytholoma and extracted a set of 415 3D landmarks from each specimen. By applying the geometric morphometrics (GM) to the landmarks, the first 4 principal components (PCs) in the 3D shape and 3D form analyses, respectively, accounted for 87.86% and 96.34% of the total variance. The centroid sizes of the corollas only accounted for 5.46% of the corolla shape variation, suggesting that the evolutionary allometry was weak. The 4 morphological traits corresponding to the 4 shape PCs were defined as tube curvature, lobe area, tube dilation, and lobe recurvation. Tube curvature and tube dilation were strongly associated with the pollination type and contained phylogenetic signals in clade Corytholoma. The landmarks were further used to reconstruct corolla shapes at the ancestral states. CONCLUSIONS: With the integration of µCT imaging into GM, the proposed approach boosted the precision in quantifying corolla traits and improved the understanding of the morphological traits corresponding to the pollination type, impact of size on shape variation, and evolution of corolla shape in clade Corytholoma.

Association between Petal Form Variation and CYC2-like Genotype in a Hybrid Line of Sinningia speciosa.

This study used three-dimensional (3D) micro-computed tomography (µCT) imaging to examine petal form variation in a hybrid cross of Sinningia speciosa between a cultivar with actinomorphic flowers and a variety with zygomorphic flowers. The major objectives were to determine the genotype-phenotype associations between the petal form variation and CYCLOIDEA2-like alleles in S. speciosa (SsCYC) and to morphologically investigate the differences in petal types between actinomorphic and zygomorphic flowers. In this study, µCT was used to accurately acquire 3D floral images. Landmark-based geometric morphometrics (GM) was applied to evaluate the major form variations of the petals. Nine morphological traits of the petals were defined according to the form variations quantified through the GM analysis. The results indicated that the outward curvature of dorsal petals, the midrib asymmetry of lateral petals, and the dilation of ventral region of the tube were closely associated with the SsCYC genotype. Multiple analyses of form similarity between the petals suggested that the dorsal and ventral petals of actinomorphic plants resembled the ventral petals of zygomorphic plants. This observation indicated that the transition from zygomorphic to actinomorphic flowers in S. speciosa might be caused by the ventralization of the dorsal petals. We demonstrated that the 3D-GM approach can be used to determine genotype-phenotype associations and to provide morphological evidence for the transition of petal types between actinomorphic and zygomorphic flowers in S. speciosa.

Quantifying floral shape variation in 3D using microcomputed tomography: a case study of a hybrid line between actinomorphic and zygomorphic flowers.

The quantification of floral shape variations is difficult because flower structures are both diverse and complex. Traditionally, floral shape variations are quantified using the qualitative and linear measurements of two-dimensional (2D) images. The 2D images cannot adequately describe flower structures, and thus lead to unsatisfactory discrimination of the flower shape. This study aimed to acquire three-dimensional (3D) images by using microcomputed tomography (µCT) and to examine the floral shape variations by using geometric morphometrics (GM). To demonstrate the advantages of the 3D-µCT-GM approach, we applied the approach to a second-generation population of florist's gloxinia (Sinningia speciosa) crossed from parents of zygomorphic and actinomorphic flowers. The flowers in the population considerably vary in size and shape, thereby served as good materials to test the applicability of the proposed phenotyping approach. Procedures were developed to acquire 3D volumetric flower images using a µCT scanner, to segment the flower regions from the background, and to select homologous characteristic points (i.e., landmarks) from the flower images for the subsequent GM analysis. The procedures identified 95 landmarks for each flower and thus improved the capability of describing and illustrating the flower shapes, compared with typically lower number of landmarks in 2D analyses. The GM analysis demonstrated that flower opening and dorsoventral symmetry were the principal shape variations of the flowers. The degrees of flower opening and corolla asymmetry were then subsequently quantified directly from the 3D flower images. The 3D-µCT-GM approach revealed shape variations that could not be identified using typical 2D approaches and accurately quantified the flower traits that presented a challenge in 2D images. The approach opens new avenues to investigate floral shape variations.

Computer-aided assessment of tumor grade for breast cancer in ultrasound images.

This study involved developing a computer-aided diagnosis (CAD) system for discriminating the grades of breast cancer tumors in ultrasound (US) images. Histological tumor grades of breast cancer lesions are standard prognostic indicators. Tumor grade information enables physicians to determine appropriate treatments for their patients. US imaging is a noninvasive approach to breast cancer examination. In this study, 148 3-dimensional US images of malignant breast tumors were obtained. Textural, morphological, ellipsoid fitting, and posterior acoustic features were quantified to characterize the tumor masses. A support vector machine was developed to classify breast tumor grades as either low or high. The proposed CAD system achieved an accuracy of 85.14% (126/148), a sensitivity of 79.31% (23/29), a specificity of 86.55% (103/119), and an A Z of 0.7940.