Robust occluding contour detection using the Hausdorff distance

2002 ◽  
Author(s):  
Xilin Yi ◽  
O.I. Camps
Keyword(s):  
Hausdorff Distance ◽  
Contour Detection ◽  
Occluding Contour

Right-Hemisphere Specialization for Contour Grouping

2014 ◽  
Vol 61 (5) ◽  
pp. 331-339 ◽  
Author(s):  
Gregor Volberg
Keyword(s):  
Right Hemisphere ◽  
Contour Detection ◽  
Global Processing ◽  
Detection Accuracy ◽  
Frequency Spectra ◽  
Visual Hemifield ◽  
Spatial Frequencies ◽  
A Chain ◽  
The Right ◽  
Hemisphere Specialization

Previous studies often revealed a right-hemisphere specialization for processing the global level of compound visual stimuli. Here we explore whether a similar specialization exists for the detection of intersected contours defined by a chain of local elements. Subjects were presented with arrays of randomly oriented Gabor patches that could contain a global path of collinearly arranged elements in the left or in the right visual hemifield. As expected, the detection accuracy was higher for contours presented to the left visual field/right hemisphere. This difference was absent in two control conditions where the smoothness of the contour was decreased. The results demonstrate that the contour detection, often considered to be driven by lateral coactivation in primary visual cortex, relies on higher-level visual representations that differ between the hemispheres. Furthermore, because contour and non-contour stimuli had the same spatial frequency spectra, the results challenge the view that the right-hemisphere advantage in global processing depends on a specialization for processing low spatial frequencies.

Saliency Object Detection Based on Domain Transform and Contour Detection

2018 ◽  
Vol 30 (8) ◽  
pp. 1457
Author(s):  
Zongmin Li ◽  
Chenchen Zhou ◽  
Yanhe Gong ◽  
Yujie Liu ◽  
Hua Li
Keyword(s):  
Object Detection ◽  
Contour Detection ◽  
Saliency Object Detection

Efficient Hausdorff Distance Calculation Algorithm Based on Z-Order and Octree

2018 ◽  
Vol 30 (10) ◽  
pp. 1794
Author(s):  
Dejun Zhang ◽  
Fazhi He ◽  
Long Tian ◽  
Zhuyang Xie ◽  
Lu Zou
Keyword(s):  
Hausdorff Distance ◽  
Calculation Algorithm ◽  
Distance Calculation

Implications of Digital Image Processing in the Paraclinical Assessment of the Partially Edentated Patient

2018 ◽  
Vol 69 (2) ◽  
pp. 521-524
Author(s):  
Magda Ecaterina Antohe ◽  
Doriana Agop Forna ◽  
Cristina Gena Dascalu ◽  
Norina Consuela Forna
Keyword(s):  
Image Processing ◽  
Image Enhancement ◽  
Treatment Plan ◽  
Digital Processing ◽  
Contour Detection ◽  
Anatomical Structures ◽  
Imaging Processing ◽  
Point To Point ◽  
Radiological Image ◽  
Processing Techniques

The application of certain digital processing techniques offers the possibility of extra accuracy in the interpretation of paraclinical examinations of this type, with profound implications in the diagnosis as well as in the hierarchy of the treatment plan. The purpose of this study is to identify the type of imaging processing for the identification of pathological elements from orthopantomographies and articular tomographies. A number of 20 orthopantomographies and 15 temporo-mandibular joint tomography have undergone through various image enhancement techniques. Various methods of image enhancement (enhancement) have been used for those procedures whereby it becomes more useful in the following aspects: specific details are highlighted; noise is eliminated; the image becomes more visually attractive. The workings were done in Corel PhotoPaint 7.0, using the automatic procedures available.The choice of a particular type of image enhancement technique has been selected for each type of pathology found in orthopantomographies or articular tomography, providing the best accuracy for an optimal imaging interpretation that underpins a precision diagnosis.Of the most useful imaging processing in the optimization of the orthopantomographic image accuracy the point-to-point transformations are to be noted. The image processing proposed in this article focused primarily on improving the radiological image attributes to highlight specific anatomical structures, and secondly, the contour detection, where it was necessary for the diagnostic purposes as well.

scholarly journals Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
C. A. Neves ◽  
E. D. Tran ◽  
I. M. Kessler ◽  
N. H. Blevins
Keyword(s):  
Facial Nerve ◽  
Inner Ear ◽  
Temporal Bone ◽  
Hausdorff Distance ◽  
Sigmoid Sinus ◽  
Ct Scans ◽  
Automated Segmentation ◽  
Dice Coefficient ◽  
Lateral Skull Base ◽  
End To End

AbstractMiddle- and inner-ear surgery is a vital treatment option in hearing loss, infections, and tumors of the lateral skull base. Segmentation of otologic structures from computed tomography (CT) has many potential applications for improving surgical planning but can be an arduous and time-consuming task. We propose an end-to-end solution for the automated segmentation of temporal bone CT using convolutional neural networks (CNN). Using 150 manually segmented CT scans, a comparison of 3 CNN models (AH-Net, U-Net, ResNet) was conducted to compare Dice coefficient, Hausdorff distance, and speed of segmentation of the inner ear, ossicles, facial nerve and sigmoid sinus. Using AH-Net, the Dice coefficient was 0.91 for the inner ear; 0.85 for the ossicles; 0.75 for the facial nerve; and 0.86 for the sigmoid sinus. The average Hausdorff distance was 0.25, 0.21, 0.24 and 0.45 mm, respectively. Blinded experts assessed the accuracy of both techniques, and there was no statistical difference between the ratings for the two methods (p = 0.93). Objective and subjective assessment confirm good correlation between automated segmentation of otologic structures and manual segmentation performed by a specialist. This end-to-end automated segmentation pipeline can help to advance the systematic application of augmented reality, simulation, and automation in otologic procedures.

scholarly journals Retraining Convolutional Neural Networks for Specialized Cardiovascular Imaging Tasks: Lessons from Tetralogy of Fallot

2021 ◽  
Author(s):  
Animesh Tandon ◽  
Navina Mohan ◽  
Cory Jensen ◽  
Barbara E. U. Burkhardt ◽  
Vasu Gooty ◽  
...  
Keyword(s):  
Tetralogy Of Fallot ◽  
Hausdorff Distance ◽  
Volumetric Analysis ◽  
Dice Similarity Coefficient ◽  
Algorithm Performance ◽  
Comprehensive Method ◽  
Combined Use ◽  
Median Error ◽  
Structural Abnormalities ◽  
Testing Data

AbstractVentricular contouring of cardiac magnetic resonance imaging is the gold standard for volumetric analysis for repaired tetralogy of Fallot (rTOF), but can be time-consuming and subject to variability. A convolutional neural network (CNN) ventricular contouring algorithm was developed to generate contours for mostly structural normal hearts. We aimed to improve this algorithm for use in rTOF and propose a more comprehensive method of evaluating algorithm performance. We evaluated the performance of a ventricular contouring CNN, that was trained on mostly structurally normal hearts, on rTOF patients. We then created an updated CNN by adding rTOF training cases and evaluated the new algorithm’s performance generating contours for both the left and right ventricles (LV and RV) on new testing data. Algorithm performance was evaluated with spatial metrics (Dice Similarity Coefficient (DSC), Hausdorff distance, and average Hausdorff distance) and volumetric comparisons (e.g., differences in RV volumes). The original Mostly Structurally Normal (MSN) algorithm was better at contouring the LV than the RV in patients with rTOF. After retraining the algorithm, the new MSN + rTOF algorithm showed improvements for LV epicardial and RV endocardial contours on testing data to which it was naïve (N = 30; e.g., DSC 0.883 vs. 0.905 for LV epicardium at end diastole, p < 0.0001) and improvements in RV end-diastolic volumetrics (median %error 8.1 vs 11.4, p = 0.0022). Even with a small number of cases, CNN-based contouring for rTOF can be improved. This work should be extended to other forms of congenital heart disease with more extreme structural abnormalities. Aspects of this work have already been implemented in clinical practice, representing rapid clinical translation. The combined use of both spatial and volumetric comparisons yielded insights into algorithm errors.

Sign in / Sign up

Export Citation Format

Share Document