Robust Hausdorff Distance Research Articles

CerebNet: A fast and reliable deep-learning pipeline for detailed cerebellum sub-segmentation

Quantifying the volume of the cerebellum and its lobes is of profound interest in various neurodegenerative and acquired diseases. Especially for the most common spinocerebellar ataxias (SCA), for which the first antisense oligonculeotide-base gene silencing trial has recently started, there is an urgent need for quantitative, sensitive imaging markers at pre-symptomatic stages for stratification and treatment assessment. This work introduces CerebNet, a fully automated, extensively validated, deep learning method for the lobular segmentation of the cerebellum, including the separation of gray and white matter. For training, validation, and testing, T1-weighted images from 30 participants were manually annotated into cerebellar lobules and vermal sub-segments, as well as cerebellar white matter. CerebNet combines FastSurferCNN, a UNet-based 2.5D segmentation network, with extensive data augmentation, e.g. realistic non-linear deformations to increase the anatomical variety, eliminating additional preprocessing steps, such as spatial normalization or bias field correction. CerebNet demonstrates a high accuracy (on average 0.87 Dice and 1.742mm Robust Hausdorff Distance across all structures) outperforming state-of-the-art approaches. Furthermore, it shows high test-retest reliability (average ICC >0.97 on OASIS and Kirby) as well as high sensitivity to disease effects, including the pre-ataxic stage of spinocerebellar ataxia type 3 (SCA3). CerebNet is compatible with FreeSurfer and FastSurfer and can analyze a 3D volume within seconds on a consumer GPU in an end-to-end fashion, thus providing an efficient and validated solution for assessing cerebellum sub-structure volumes. We make CerebNet available as source-code (https://github.com/Deep-MI/FastSurfer).

Efficient Claustrum Segmentation in T2-weighted Neonatal Brain MRI Using Transfer Learning from Adult Scans

PurposeIntrauterine claustrum and subplate neuron development have been suggested to overlap. As premature birth typically impairs subplate neuron development, neonatal claustrum might indicate a specific prematurity impact; however, claustrum identification usually relies on expert knowledge due to its intricate structure. We established automated claustrum segmentation in newborns.MethodsWe applied a deep learning-based algorithm for segmenting the claustrum in 558 T2-weighted neonatal brain MRI of the developing Human Connectome Project (dHCP) with transfer learning from claustrum segmentation in T1-weighted scans of adults. The model was trained and evaluated on 30 manual bilateral claustrum annotations in neonates.ResultsWith only 20 annotated scans, the model yielded median volumetric similarity, robust Hausdorff distance and Dice score of 95.9%, 1.12 mm and 80.0%, respectively, representing an excellent agreement between the automatic and manual segmentations. In comparison with interrater reliability, the model achieved significantly superior volumetric similarity (p = 0.047) and Dice score (p < 0.005) indicating stable high-quality performance. Furthermore, the effectiveness of the transfer learning technique was demonstrated in comparison with nontransfer learning. The model can achieve satisfactory segmentation with only 12 annotated scans. Finally, the model’s applicability was verified on 528 scans and revealed reliable segmentations in 97.4%.ConclusionThe developed fast and accurate automated segmentation has great potential in large-scale study cohorts and to facilitate MRI-based connectome research of the neonatal claustrum. The easy to use models and codes are made publicly available.

Integrating multiple MRI sequences for pelvic organs segmentation via the attention mechanism.

To create a network which fully utilizes multi-sequence MRI and compares favorably with manual human contouring. We retrospectively collected 89 MRI studies of the pelvic cavity from patients with prostate cancer and cervical cancer. The dataset contained 89 samples from 87 patients with a total of 84 valid samples. MRI was performed with T1-weighted (T1), T2-weighted (T2), and Enhanced Dixon T1-weighted (T1DIXONC) sequences. There were two cohorts. The training cohort contained 55 samples and the testing cohort contained 29 samples. The MRI images in the training cohort contained contouring data from radiotherapist α. The MRI images in the testing cohort contained contouring data from radiotherapist α and contouring data from another radiotherapist: radiotherapist β. The training cohort was used to optimize the convolution neural networks, which included the attention mechanism through the proposed activation module and the blended module into multiple MRI sequences, to perform autodelineation. The testing cohort was used to assess the networks' autodelineation performance. The contoured organs at risk (OAR) were the anal canal, bladder, rectum, femoral head (L), and femoral head (R). We compared our proposed network with UNet and FuseUNet using our dataset. When T1 was the main sequence, we input three sequences to segment five organs and evaluated the results using four metrics: the DSC (Dice similarity coefficient), the JSC (Jaccard similarity coefficient), the ASD (average mean distance), and the 95% HD (robust Hausdorff distance). The proposed network achieved improved results compared with the baselines among all metrics. The DSC were 0.834±0.029, 0.818±0.037, and 0.808±0.050 for our proposed network, FuseUNet, and UNet, respectively. The 95% HD were 7.256±2.748mm, 8.404±3.297mm, and 8.951±4.798mm for our proposed network, FuseUNet, and UNet, respectively. Our proposed network also had superior performance on the JSC and ASD coefficients. Our proposed activation module and blended module significantly improved the performance of FuseUNet for multi-sequence MRI segmentation. Our proposed network integrated multiple MRI sequences efficiently and autosegmented OAR rapidly and accurately. We also discovered that three-sequence fusion (T1-T1DIXONC-T2) was superior to two-sequence fusion (T1-T2 and T1-T1DIXONC, respectively). We infer that the more MRI sequences fused, the better the automatic segmentation results.

Automated claustrum segmentation in human brain MRI using deep learning

In the last two decades, neuroscience has produced intriguing evidence for a central role of the claustrum in mammalian forebrain structure and function. However, relatively few in vivo studies of the claustrum exist in humans. A reason for this may be the delicate and sheet‐like structure of the claustrum lying between the insular cortex and the putamen, which makes it not amenable to conventional segmentation methods. Recently, Deep Learning (DL) based approaches have been successfully introduced for automated segmentation of complex, subcortical brain structures. In the following, we present a multi‐view DL‐based approach to segment the claustrum in T1‐weighted MRI scans. We trained and evaluated the proposed method in 181 individuals, using bilateral manual claustrum annotations by an expert neuroradiologist as reference standard. Cross‐validation experiments yielded median volumetric similarity, robust Hausdorff distance, and Dice score of 93.3%, 1.41 mm, and 71.8%, respectively, representing equal or superior segmentation performance compared to human intra‐rater reliability. The leave‐one‐scanner‐out evaluation showed good transferability of the algorithm to images from unseen scanners at slightly inferior performance. Furthermore, we found that DL‐based claustrum segmentation benefits from multi‐view information and requires a sample size of around 75 MRI scans in the training set. We conclude that the developed algorithm allows for robust automated claustrum segmentation and thus yields considerable potential for facilitating MRI‐based research of the human claustrum. The software and models of our method are made publicly available.

Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images

White matter hyperintensities (WMH) are commonly found in the brains of healthy elderly individuals and have been associated with various neurological and geriatric disorders. In this paper, we present a study using deep fully convolutional network and ensemble models to automatically detect such WMH using fluid attenuation inversion recovery (FLAIR) and T1 magnetic resonance (MR) scans. The algorithm was evaluated and ranked 1st in the WMH Segmentation Challenge at MICCAI 2017. In the evaluation stage, the implementation of the algorithm was submitted to the challenge organizers, who then independently tested it on a hidden set of 110 cases from 5 scanners. Averaged dice score, precision and robust Hausdorff distance obtained on held-out test datasets were 80%, 84% and 6.30 mm respectively. These were the highest achieved in the challenge, suggesting the proposed method is the state-of-the-art. Detailed descriptions and quantitative analysis on key components of the system were provided. Furthermore, a study of cross-scanner evaluation is presented to discuss how the combination of modalities affect the generalization capability of the system. The adaptability of the system to different scanners and protocols is also investigated. A quantitative study is further presented to show the effect of ensemble size and the effectiveness of the ensemble model. Additionally, software and models of our method are made publicly available. The effectiveness and generalization capability of the proposed system show its potential for real-world clinical practice.

Fast and robust Hausdorff distance computation from triangle mesh to quad mesh in near-zero cases

We present an algorithm that computes the one-sided Hausdorff distance from a triangle mesh to a quad mesh. Our algorithm is much more robust than previous ones in the sense that memory requirement is vastly reduced, by avoiding storing combinatorial pairs of each two input model's parts. Meanwhile, point projection via uniform grid greatly accelerates the algorithm. Experimental results show that even for cases where the Hausdorff distance is near zero, its precise computation is done in an interactive speed, while memory consumption is easily manageable.

Image retrieval by information fusion based on scalable vocabulary tree and robust Hausdorff distance

In recent years, Scalable Vocabulary Tree (SVT) has been shown to be effective in image retrieval. However, for general images where the foreground is the object to be recognized while the background is cluttered, the performance of the current SVT framework is restricted. In this paper, a new image retrieval framework that incorporates a robust distance metric and information fusion is proposed, which improves the retrieval performance relative to the baseline SVT approach. First, the visual words that represent the background are diminished by using a robust Hausdorff distance between different images. Second, image matching results based on three image signature representations are fused, which enhances the retrieval precision. We conducted intensive experiments on small-scale to large-scale image datasets: Corel-9, Corel-48, and PKU-198, where the proposed Hausdorff metric and information fusion outperforms the state-of-the-art methods by about 13, 15, and 15%, respectively.

Towards measuring neuroimage misalignment

To enhance neuro-navigation, high quality pre-operative images must be registered onto intra-operative configuration of the brain. Therefore evaluation of the degree to which structures may remain misaligned after registration is critically important. We consider two Hausdorff Distance (HD)-based evaluation approaches: the edge-based HD (EBHD) metric and the Robust HD (RHD) metric as well as various commonly used intensity-based similarity metrics such as Mutual Information (MI), Normalised Mutual Information (NMI), Entropy Correlation Coefficient (ECC), Kullback–Leibler Distance (KLD) and Correlation Ratio (CR). We conducted the evaluation by applying known deformations to simple sample images and real cases of brain shift. We conclude that the intensity-based similarity metrics such as MI, NMI, ECC, KLD and CR do not correlate well with actual alignment errors, and hence are not useful for assessing misalignment. On the contrary, the EBHD and the RHD metrics correlated well with actual alignment errors; however, they have been found to underestimate the actual misalignment. We also note that it is beneficial to present HD results as a percentile-HD curve rather than a single number such as the 95-percentile HD. Percentile-HD curves present the full range of alignment errors and also facilitate the comparison of results obtained using different approaches. Furthermore, the qualities that should be possessed by an ideal evaluation metric were highlighted. Future studies could focus on developing such an evaluation metric.

Accurate M-hausdorff distance similarity combining distance orientation for matching multi-modal sensor images

Although Hausdorff distance (HD) has been widely used in an object identification between same modality images, the object identification between different modality images are challenging because of the poor edge correspondence coming from heterogeneous image characteristics. This paper proposes a robust Hausdorff distance similarity (accurate M-HD: AMHD) between multi-modal sensor data. To improve robustness against the outliers when comparing the pairs of multi-modal images, the AMHD utilizes the orientation information of each point in addition to the distance transform (DT) map as a similarity criterion. In the AMHD scheme, the DT map is generated by applying dead-reckoning signed DT, and the distance orientation (DO) map is constructed by employing the Kirsch compass kernel to the DT map, respectively. Using the additional information on the DO, the proposed similarity can precisely examine the outliers including non-correspondent edges and noises, and discard false correspondent distances efficiently. The computer simulations show that the proposed AMHD yields superior performance at aligning multi-modal sensor data (visible-thermal IR face images) over those achieved by the conventional robust schemes in terms of the position error between the ground truth and the computed position.

Object matching algorithm based on robust hausdorff distance

Based on the conventional Hausdorff distance of edge position, we introduced the information of edge gradient to distance measuring, and constructed a new distance function that used the information of edge position and gradient. Then we presented a robust three-dimension Hausdorff distance and the object matching algorithm using the proposed Hausdorff distance. In the proposed algorithm, we used a two-step matching scheme that combined two steps of coarse and refined matching to solve the problem of computation complexity increasing caused by using 3D distance measure. Experimental result shows that the matching robustness of the proposed algorithm has been improved greatly compared to conventional algorithms that only use the information of edge position.

Face recognition based on 3D ridge images obtained from range data

In this paper, we present an approach for 3D face recognition from frontal range data based on the ridge lines on the surface of the face. We use the principal curvature, k max , to represent the face image as a 3D binary image called ridge image. The ridge image shows the locations of the ridge points around the important facial regions on the face (i.e., the eyes, the nose, and the mouth). We utilized the robust Hausdorff distance and the iterative closest points (ICP) for matching the ridge image of a given probe image to the ridge images of the facial images in the gallery. To evaluate the performance of our approach for 3D face recognition, we performed experiments on GavabDB face database (a small size database) and Face Recognition Grand Challenge V2.0 (a large size database). The results of the experiments show that the ridge lines have great capability for 3D face recognition. In addition, we found that as long as the size of the database is small, the performance of the ICP-based matching and the robust Hausdorff matching are comparable. But, when the size of the database increases, ICP-based matching outperforms the robust Hausdorff matching technique.

Robust Hausdorff distance measure for face recognition

Face is considered to be one of the biometrics in automatic person identification. The non-intrusive nature of face recognition makes it an attractive choice. For face recognition system to be practical, it should be robust to variations in illumination, pose and expression as humans recognize faces irrespective of all these variations. In this paper, an attempt to address these issues is made using a new Hausdorff distance-based measure. The proposed measure represent the gray values of pixels in face images as vectors giving the neighborhood intensity distribution of the pixels. The transformation is expected to be less sensitive to illumination variations besides preserving the appearance of face embedded in the original gray image. While the existing Hausdorff distance-based measures are defined between the binary edge images of faces which contains primarily structural information, the proposed measure gives the dissimilarity between the appearance of faces. An efficient method to compute the proposed measure is presented. The performance of the method on bench mark face databases shows that it is robust to considerable variations in pose, expression and illumination. Comparison with some of the existing Hausdorff distance-based methods shows that the proposed method performs better in many cases.

Multiple Face Segmentation and Tracking Based on Robust Hausdorff Distance Matching

Multiple Face Segmentation and Tracking Based on Robust Hausdorff Distance Matching

Multiple Face Segmentation and Tracking Based on Robust Hausdorff Distance Matching

This paper describes a system for tracking multiple faces in an input video sequence using facial convex hull based facial segmentation and robust hausdorff distance. The algorithm adapts skin color reference map in YCbCr color space and hair color reference map in RGB color space for classifying face region. Then, we obtain an initial face model with preprocessing and convex hull. For tracking, this algorithm computes displacement of the point set between frames using a robust hausdorff distance and the best possible displacement is selected. Finally, the initial face model is updated using the displacement. We provide an example to illustrate the proposed tracking algorithm, which efficiently tracks rotating and zooming faces as well as existing multiple faces in video sequences obtained from CCD camera.

ROBUST OBJECT MATCHING USING A MODIFIED VERSION OF THE HAUSDORFF MEASURE

The Hausdorff distance (HD) between planar sets of points is known to be an effective measure for determining the degree of resemblance between binary images. In this paper, we analyze the conventional HD measure and propose a new Robust HD (RHD) measure. The proposed RHD measure takes into account not only the location information of the edge points, but also other factors such as the total number of the edge points whose nearest neighbors are within a specified directed distance, spurious edge segments defined by a small number of points, outliers, and occlusions. Experimental results for both synthetic and real images show that the proposed RHD measure is more efficient than the conventional HD measure.

Computer vision technology in log volume inspection

Log volume inspection is very important in forestry research and paper making engineering. This paper proposed a novel approach based on computer vision technology to cope with log volume inspection. The needed hardware system was analyzed and the details of the inspection algorithms were given. A fuzzy entropy based on image enhancement algorithm was presented for enhancing the image of the cross-section of log. In many practical applications the cross-section is often partially invisible, and this is the major obstacle for correct inspection. To solve this problem, a robust Hausdorff distance method was proposed to recover the whole cross-section. Experiment results showed that this method was efficient.

Robust Hausdorff distance matching algorithms using pyramidal structures

This paper proposes two Hausdorff distance (HD) matching algorithms, in which robust HD measures are implemented in pyramidal structures. By computer simulations, the matching performance of the conventional HD measures and the proposed robust HD matching algorithms using pyramidal structures is compared, with real images which are degraded by noise and occlusions.

Object matching algorithms using robust Hausdorff distance measures

A Hausdorff distance (HD) is one of commonly used measures for object matching. This work analyzes the conventional HD measures and proposes two robust HD measures based on m-estimation and least trimmed square (LTS) which are more efficient than the conventional HD measures. By computer simulation, the matching performance of the conventional and proposed HD measures is compared with synthetic and real images.