In today's competitive production era, the ability to identify and track important objects in a near real-time manner is greatly desired among manufacturers who are moving towards the streamline production. Manually keeping track of every object in a complex manufacturing plant is infeasible; therefore, an automatic system of that functionality is greatly in need. This study was motivated to develop a Mask Region-based Convolutional Neural Network (Mask RCNN) model to semantically segment objects and important zones in manufacturing plants. The Mask RCNN was trained through transfer learning that used a neural network (NN) pre-trained with the MS-COCO dataset as the starting point and further fine-tuned that NN using a limited number of annotated images. Then the Mask RCNN model was modified to have consistent detection results from videos, which was realized through the use of a two-staged detection threshold and the analysis of the temporal coherence information of detected objects. The function of object tracking was added to the system for identifying the misplacement of objects. The effectiveness and efficiency of the proposed system were demonstrated by analyzing a sample of video footages.
more »
« less
Mask refinement network for tooth segmentation on panoramic radiographs
Instance-level tooth segmentation extracts abundant localization and shape information from panoramic radiographs (PRs). The aim of this study was to evaluate the performance of a mask refinement network that extracts precise tooth edges.
A public dataset which consists of 543 PRs and 16211 labelled teeth was utilized. The structure of a typical Mask Region-based Convolutional Neural Network (Mask RCNN) was used as the baseline. A novel loss function was designed focus on producing accurate mask edges. In addition to our proposed method, 3 existing tooth segmentation methods were also implemented on the dataset for comparative analysis. The average precisions (APs), mean intersection over union (mIoU), and mean Hausdorff distance (mHAU) were exploited to evaluate the performance of the network.
A novel mask refinement region-based convolutional neural network was designed based on Mask RCNN architecture to extract refined masks for individual tooth on PRs. A total of 3311 teeth were correctly detected from 3382 tested teeth in 111 PRs. The AP, precision, and recall were 0.686, 0.979, and 0.952, respectively. Moreover, the mIoU and mHAU achieved 0.941 and 9.7, respectively, which are significantly better than the other existing segmentation methods.
This study proposed an efficient deep learning algorithm for accurately extracting the mask of any individual tooth from PRs. Precise tooth masks can provide valuable reference for clinical diagnosis and treatment. This algorithm is a fundamental basis for further automated processing applications.
- PAR ID:
- 10490081
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Dentomaxillofacial Radiology
- Volume:
- 53
- Issue:
- 2
- ISSN:
- 0250-832X
- Format(s):
- Medium: X Size: p. 127-136
- Size(s):
- p. 127-136
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Contemporary approaches to instance segmentation in cell science use 2D or 3D convolutional networks depending on the experiment and data structures. However, limitations in microscopy systems or efforts to prevent phototoxicity commonly require recording sub-optimally sampled data that greatly reduces the utility of such 3D data, especially in crowded sample space with significant axial overlap between objects. In such regimes, 2D segmentations are both more reliable for cell morphology and easier to annotate. In this work, we propose the projection enhancement network (PEN), a novel convolutional module which processes the sub-sampled 3D data and produces a 2D RGB semantic compression, and is trained in conjunction with an instance segmentation network of choice to produce 2D segmentations. Our approach combines augmentation to increase cell density using a low-density cell image dataset to train PEN, and curated datasets to evaluate PEN. We show that with PEN, the learned semantic representation in CellPose encodes depth and greatly improves segmentation performance in comparison to maximum intensity projection images as input, but does not similarly aid segmentation in region-based networks like Mask-RCNN. Finally, we dissect the segmentation strength against cell density of PEN with CellPose on disseminated cells from side-by-side spheroids. We present PEN as a data-driven solution to form compressed representations of 3D data that improve 2D segmentations from instance segmentation networks.
-
more » « less
Abstract Background Plant architecture can influence crop yield and quality. Manual extraction of architectural traits is, however, time-consuming, tedious, and error prone. The trait estimation from 3D data addresses occlusion issues with the availability of depth information while deep learning approaches enable learning features without manual design. The goal of this study was to develop a data processing workflow by leveraging 3D deep learning models and a novel 3D data annotation tool to segment cotton plant parts and derive important architectural traits.
Results The Point Voxel Convolutional Neural Network (PVCNN) combining both point- and voxel-based representations of 3D data shows less time consumption and better segmentation performance than point-based networks. Results indicate that the best mIoU (89.12%) and accuracy (96.19%) with average inference time of 0.88 s were achieved through PVCNN, compared to Pointnet and Pointnet++. On the seven derived architectural traits from segmented parts, an R2value of more than 0.8 and mean absolute percentage error of less than 10% were attained.
Conclusion This plant part segmentation method based on 3D deep learning enables effective and efficient architectural trait measurement from point clouds, which could be useful to advance plant breeding programs and characterization of in-season developmental traits. The plant part segmentation code is available at
https://github.com/UGA-BSAIL/plant_3d_deep_learning . -
more » « less
Abstract Objectives Linear enamel hypoplasia (LEH) is a common skeletal marker of physiological stress (e.g., malnutrition or illness) that is studied within and across populations, without reference to familial risk. We examine LEH prevalence in a population with known genealogical relationships to determine the potential influence of genetic heritability and shared environment.
Methods LEH data of 239 individuals from a single population were recorded from the Ohio State University Menegaz‐Bock collection dental casts. All individuals were of known age, sex, and genealogy. Narrow‐sense heritability estimates were obtained for LEH presence and count data from all unworn, fully erupted teeth (excluding third molars) using SOLAR (v.8.1.1). Age, sex, and age–sex interaction were included as covariates. Models were re‐run with a household effect variable.
Results LEH persists across generations in this study population with moderate, significant heritability estimates for presence in four teeth, and count in four teeth (three teeth were significant for both). When a household effect variable was added, no residual heritability remained for LEH count on any tooth. There was no significant household effect for three of the four teeth that had significant heritability estimates for LEH presence. Age was a significant covariate. Further analyses with birth year data revealed a secular trend toward less LEH.
Conclusions This study provides evidence for familial risk of LEH (genetic and environmental) that has consequences for the broad use of this skeletal marker of stress. These results have repercussions for archaeological assemblages, or population health studies, where genetic relatives and household groups might be heavily represented.
-
more » « less
Premise The functional significance of leaf margins has long been debated. In this study, we explore influences of climate, leaf lobing, woodiness, and shared evolutionary history on two leaf margin traits within the genus
Pelargonium .Methods Leaves from 454 populations of
Pelargonium (161 species) were collected in the Greater Cape Floristic Region and scored for tooth presence/absence and degree of lobing. Tooth density (number of teeth per interior perimeter distance) was calculated for a subset of these. We compared five hypotheses to explain tooth presence and density using mixed effect models.Results Tooth presence/absence was best predicted by the interaction of leaf lobing and mean annual temperature (
MAT ), but often in patterns opposite those previously reported: species were more likely to be toothed with warmer temperatures, particularly for unlobed and highly lobed leaves. In contrast, tooth density was best predicted by the interaction ofMAT and the season of most rain; density declines with temperature as consistent with expectations, but only in winter‐rain dominated areas. Woody and nonwoody species withinPelargonium have similar associations between tooth presence/absence andMAT , contrary to the expectation that patterns within nonwoody species would be insignificant.Conclusions We conclude
Pelargonium leaf margins show predictable responses to climate, but these responses are complex and can contradict those found for global patterns across plant communities.
