Deep Segmentation of Point Clouds of Wheat.

The 3D analysis of plants has become increasingly effective in modeling the relative structure of organs and other traits of interest. In this paper, we introduce a novel pattern-based deep neural network, Pattern-Net, for segmentation of point clouds of wheat. This study is the first to segment the point clouds of wheat into defined organs and to analyse their traits directly in 3D space. Point clouds have no regular grid and thus their segmentation is challenging. Pattern-Net creates a dynamic link among neighbors to seek stable patterns from a 3D point set across several levels of abstraction using the K-nearest neighbor algorithm. To this end, different layers are connected to each other to create complex patterns from the simple ones, strengthen dynamic link propagation, alleviate the vanishing-gradient problem, encourage link reuse and substantially reduce the number of parameters. The proposed deep network is capable of analysing and decomposing unstructured complex point clouds into semantically meaningful parts. Experiments on a wheat dataset verify the effectiveness of our approach for segmentation of wheat in 3D space.

FFD: Fast Feature Detector.

Scale-invariance, good localization and robustness to noise and distortions are the main properties that a local feature detector should possess. Most existing local feature detectors find excessive unstable feature points that increase the number of keypoints to be matched and the computational time of the matching step. In this paper, we show that robust and accurate keypoints exist in the specific scale-space domain. To this end, we first formulate the superimposition problem into a mathematical model and then derive a closed-form solution for multiscale analysis. The model is formulated via difference-of-Gaussian (DoG) kernels in the continuous scale-space domain, and it is proved that setting the scale-space pyramid's blurring ratio and smoothness to 2 and 0.627, respectively, facilitates the detection of reliable keypoints. For the applicability of the proposed model to discrete images, we discretize it using the undecimated wavelet transform and the cubic spline function. Theoretically, the complexity of our method is less than 5% of that of the popular baseline Scale Invariant Feature Transform (SIFT). Extensive experimental results show the superiority of the proposed feature detector over the existing representative hand-crafted and learning-based techniques in accuracy and computational time. The code and supplementary materials can be found at https://github.com/mogvision/FFD.

DeepPod: a convolutional neural network based quantification of fruit number in Arabidopsis.

BACKGROUND: High-throughput phenotyping based on non-destructive imaging has great potential in plant biology and breeding programs. However, efficient feature extraction and quantification from image data remains a bottleneck that needs to be addressed. Advances in sensor technology have led to the increasing use of imaging to monitor and measure a range of plants including the model Arabidopsis thaliana. These extensive datasets contain diverse trait information, but feature extraction is often still implemented using approaches requiring substantial manual input. RESULTS: The computational detection and segmentation of individual fruits from images is a challenging task, for which we have developed DeepPod, a patch-based 2-phase deep learning framework. The associated manual annotation task is simple and cost-effective without the need for detailed segmentation or bounding boxes. Convolutional neural networks (CNNs) are used for classifying different parts of the plant inflorescence, including the tip, base, and body of the siliques and the stem inflorescence. In a post-processing step, different parts of the same silique are joined together for silique detection and localization, whilst taking into account possible overlapping among the siliques. The proposed framework is further validated on a separate test dataset of 2,408 images. Comparisons of the CNN-based prediction with manual counting (R2 = 0.90) showed the desired capability of methods for estimating silique number. CONCLUSIONS: The DeepPod framework provides a rapid and accurate estimate of fruit number in a model system widely used by biologists to investigate many fundemental processes underlying growth and reproduction.

Anatomical axes of the proximal and distal halves of the femur in a normally aligned healthy population: implications for surgery.

BACKGROUND: The anatomical axis of the femur is crucial for determining the correct alignment in corrective osteotomies of the knee, total knee arthroplasty (TKA), and retrograde and antegrade femoral intramedullary nailing (IMN). The aim of this study was to propose the concept of different anatomical axes for the proximal and distal parts of the femur; compare these axes in normally aligned subjects and also to propose the clinical application of these axes. METHODS: In this cross-sectional study, the horizontal distances between the anatomical axis of the proximal and distal halves of the femur and the center of the intercondylar notch were measured in 100 normally aligned femurs using standard full length alignment view X-rays. RESULTS: The average age was 34.44 ± 11.14 years. The average distance from the proximal anatomical axis to the center of the intercondylar notch was 6.68 ± 5.23 mm. The proximal anatomical axis of femur passed lateral to the center of the intercondylar notch in 12 cases (12%), medial in 84 cases (84%) and exactly central in 4 cases (4%). The average distance from the distal anatomical axis to the center of the intercondylar notch was 3.63 ± 2.09 mm. The distal anatomical axis of the femur passed medially to the center of the intercondylar notch in 82 cases (82%) and exactly central in 18 cases (18%). There was a significant difference between the anatomical axis of the proximal and distal parts of the femur in reference to the center of intercondylar notch (P value < 0.05), supporting the hypothesis that anatomical axes of the proximal and distal halves of the femur are different in the coronal plane. CONCLUSIONS: While surgeons are aware that the anatomical axis of the distal part of the femur is different than the anatomical axis of the proximal part in patients with femoral deformities, we have shown that these axes are also different in the normally aligned healthy people due to the anatomy of the femur in coronal plane. Also the normal ranges provided here can be used as a reference for the alignment guide entry point in TKA and antegrade and retrograde intramedullary femoral nailing.