Symmetry and asymmetry analysis and its implications to computer-aided diagnosis: A review of the literature

Influence of dental midline deviation with respect to facial flow line on smile esthetics-A cross-sectional study

BACKGROUND/OBJECTIVE

A contemporary concept states that dental midline deviation towards the direction of facial flow line (FFL) can mask the compromised smile esthetics. This study aimed to identify a range of midline deviations that can be perceived towards or away from the FFL influencing smile esthetics.

MATERIALS AND METHODS

A cross-sectional study was conducted using a frontal smile photograph of an adult female. The photograph was altered on Adobe Photoshop software into six different photographs by deviating the dental midlines towards and away from the FFL. A constant deviation of chin towards the left side was incorporated in all the photographs. Forty-three laypersons (LP) and dental professionals (DPs) evaluated those photographs. Independent t-test was used to compare the perception of dental midline deviation between LP and DPs. Simple linear regression was run to identify the factors associated with the scoring.

RESULTS

A statistically significant difference was observed for picture two with 4 mm towards FFL in the perception of midline deviation between LP and DPs. LP could not perceive the midline deviations up to 4 mm while DPs were able to perceive deviations above 2 mm. The greater the age the better the scores were and female raters had a greater inclination towards poor scores.

CONCLUSIONS

From 2 to 4 mm of midline deviation towards the FFL can be tolerated by LP and DPs.

CLINICAL SIGNIFICANCE

These findings underscore the importance of considering facial symmetry in orthodontic and cosmetic dental treatments to optimize smile esthetics.

Deep learning model for breast cancer diagnosis based on bilateral asymmetrical detection (BilAD) in digital breast tomosynthesis images

The purpose of this study was to develop a deep learning model to diagnose breast cancer by embedding a diagnostic algorithm that examines the asymmetry of bilateral breast tissue. This retrospective study was approved by the institutional review board. A total of 115 patients who underwent breast surgery and had pathologically confirmed breast cancer were enrolled in this study. Two image pairs [230 pairs of bilateral breast digital breast tomosynthesis (DBT) images with 115 malignant tumors and contralateral tissue (M/N), and 115 bilateral normal areas (N/N)] were generated from each patient enrolled in this study. The proposed deep learning model is called bilateral asymmetrical detection (BilAD), which is a modified convolutional neural network (CNN) model of Xception with two-dimensional tensors for bilateral breast images. BilAD was trained to classify the differences between pairs of M/N and N/N datasets. The results of the BilAD model were compared to those of the unilateral control CNN model (uCNN). The results of BilAD and the uCNN were as follows: accuracy, 0.84 and 0.75; sensitivity, 0.73 and 0.58; and specificity, 0.93 and 0.92, respectively. The mean area under the receiver operating characteristic curve of BilAD was significantly higher than that of the uCNN (p = 0.02): 0.90 and 0.84, respectively. The proposed deep learning model trained by embedding a diagnostic algorithm to examine the asymmetry of bilateral breast tissue improves the diagnostic accuracy for breast cancer.

Detecting and Extracting Brain Hemorrhages from CT Images Using Generative Convolutional Imaging Scheme

Purpose

The need for computerized medical assistance for accurate detection of brain hemorrhage from Computer Tomography (CT) images is more mandatory than conventional clinical tests. Recent technologies and advanced computerized algorithms follow Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques to improve medical diagnosis platforms. This technology is making the diagnosis practice of brain issues easier for medical practitioners to analyze and identify diseases with an assured degree of precision and performance.

Methods

As the existing CT image analysis models use standard procedures to detect hemorrhages, the need for DL-based data analysis is essential to provide more accurate results. Generally, the existing techniques are limited with image training efficiency, image filtering procedures, and runtime system tuning modules. On the scope, this work develops a DL-based automated analysis of CT scan slices to find various levels of brain hemorrhages. Notably, this proposed system integrates Convolutional Neural Network (CNN) and Generative Adversarial Network (GAN) architectures as Integrated Generative Adversarial-Convolutional Imaging Model (IGACM) for extracting the CT image features for detecting brain hemorrhages.

Results

This system produces good results and takes lesser training time than existing techniques. This proposed system effectively works over CT images and classifies the abnormalities with more accuracy than current techniques. The experiments and results deliver the optimal detection of hemorrhages with better accuracy. It shows that the proposed system works with 5% to 10% of the better performance compared to other diagnostic techniques.

Conclusion

The complex nature of CT images leads to noncorrelated feature complexities in diagnosis models. Considering the issue, the proposed system used GAN-based effective sampling techniques for enriching complex image samples into CNN training phases. This concludes the effective contribution of the proposed IGACM technique for detecting brain hemorrhages than the existing diagnosis models.

Neuroimaging gradient alterations and epileptogenic prediction in focal cortical dysplasia Ⅲa

INTRODUCTION

Focal cortical dysplasia Type Ⅲa (FCD Ⅲa) is a highly prevalent temporal lobe epilepsy but the seizure outcomes are not satisfactory after epilepsy surgery. Hence, quantitative neuroimaging, epileptogenic alterations, as well as their values in guiding surgery are worth exploring.

METHODS

We examined 69 patients with pathologically verified FCD Ⅲa using multimodal neuroimaging and stereoelectroencephalography (SEEG). Among them, 18 received postoperative imaging which showed the extent of surgical resection and 9 underwent SEEG implantation. We also explored neuroimaging gradient alterations along with the distance to the temporal pole. Subsequently, the machine learning regression model was employed to predict whole-brain epileptogenicity. Lastly, the correlation between neuroimaging or epileptogenicity and surgical cavities was assessed.

RESULTS

FCD Ⅲa displayed neuroimaging gradient alterations on the temporal neocortex, morphology-signal intensity decoupling, low similarity of intra-morphological features and high similarity of intra-signal intensity features. The support vector regression model was successfully applied at the whole-brain level to calculate the continuous epileptogenic value at each vertex (mean-squared error = 13.8 ± 9.8).

CONCLUSION

Our study investigated the neuroimaging gradient alterations and epileptogenicity of FCD Ⅲa, along with their potential values in guiding suitable resection range and in predicting postoperative seizure outcomes. The conclusions from this study may facilitate an accurate presurgical examination of FCD Ⅲa. However, further investigation including a larger cohort is necessary to confirm the results.

In vivo stiffness of multiple sclerosis lesions is similar to that of normal-appearing white matter

In 1868, French neurologist Jean-Martin Charcot coined the term multiple sclerosis (MS) after his observation that numerous white matter (WM) glial scars felt like sclerotic tissue. Nowadays, magnetic resonance elastography (MRE) can generate images with contrast of stiffness (CS) in soft in vivo tissues and may therefore be sensitive to MS lesions, provided that sclerosis is indeed a mechanical signature of this disease. We analyzed CS in a total of 147 lesions in patients with relapsing-remitting MS, compared with control regions in contralateral brain regions, and phantom data as well as performed numerical simulations to determine the delineation limits of multifrequency MRE (20 - 40 Hz) in MS. MRE analysis of simulated waves revealed a delineation limit of approximately 10% CS for detecting 9-mm lesions (mean size in our patient population). Due to inversion bias, this limit is reached when true CS is -11% for soft and 35% for stiff lesions. In vivo MRE identified 35 stiffer lesions and 17 softer lesions compared with surrounding WM (mean stiffness: 934±82 Pa). However, a similar pattern was found in the contralateral brain, suggesting that the range of stiffness changes in WM lesions due to MS is within the normal range of WM variability and normal heterogeneity-related CS. Consequently, Charcot's original intuition that MS is a focal sclerotic disease can neither be dismissed nor confirmed by in vivo MRE. However, the observation that MS lesions do not markedly differ in stiffness from surrounding brain tissue suggests that marked tissue sclerosis is not a mechanical signature of MS. STATEMENT OF SIGNIFICANCE: Multiple sclerosis (MS) was named by J.M. Charcot after the sclerotic changes in brain tissue he found in post-mortem autopsies. Since then, nothing has been revealed about the actual stiffening of MS lesions in vivo. Studying the viscoelastic properties of plaques in their natural environment is a major challenge that can only be overcome by MR elastography (MRE). Therefore, we used multifrequency MRE to answer the question whether MS lesions in patients with a relapsing-remitting disease course are mechanically different than surrounding tissue. Our findings suggest that the range of stiffness changes in white matter lesions due to MS is within the normal range of white matter variability and in vivo tissue sclerosis might not be a mechanical signature of MS.

MDAN: Mirror Difference Aware Network for Brain Stroke Lesion Segmentation

Brain stroke lesion segmentation is of great importance for stroke rehabilitation neuroimaging analysis. Due to the large variance of stroke lesion shapes and similarities of tissue intensity distribution, it remains a challenging task. To help detect abnormalities, the anatomical symmetries of brain magnetic resonance (MR) images have been widely used as visual cues for clinical practices. However, most methods do not fully utilize structural symmetry information in brain images segmentation. This paper presents a novel mirror difference aware network (MDAN) for stroke lesion segmentation in an encoder-decoder architecture, aiming at holistically exploiting the symmetries of image features. Specifically, a differential feature augmentation (DFA) module is developed in the encoding path to highlight the semantically pathological asymmetries of the features in abnormalities. In the DFA module, a Siamese contrastive supervised loss is designed to enhance discriminative features, and a mirror position-based difference augmentation (MDA) module is used to further magnify the discrepancy information. Moreover, mirror feature fusion (MFF) modules are applied to fuse and transfer the information both of the original input and the horizontally flipped features to the decoding path. Extensive experiments on the Anatomical Tracings of Lesions After Stroke (ATLAS) dataset show the proposed MDAN outperforms the state-of-the-art methods.

Automatic Symmetry Detection From Brain MRI Based on a 2-Channel Convolutional Neural Network

Symmetry detection is a method to extract the ideal mid-sagittal plane (MSP) from brain magnetic resonance (MR) images, which can significantly improve the diagnostic accuracy of brain diseases. In this article, we propose an automatic symmetry detection method for brain MR images in 2-D slices based on a 2-channel convolutional neural network (CNN). Different from the existing detection methods that mainly rely on the local image features (gradient, edge, etc.) to determine the MSP, we use a CNN-based model to implement the brain symmetry detection, which does not require any local feature detections and feature matchings. By training to learn a wide variety of benchmarks in the brain images, we can further use a 2-channel CNN to evaluate the similarity between the pairs of brain patches, which are randomly extracted from the whole brain slice based on a Poisson sampling. Finally, a scoring and ranking scheme is used to identify the optimal symmetry axis for each input brain MR slice. Our method was evaluated in 2166 artificial synthesized brain images and 3064 collected in vivo MR images, which included both healthy and pathological cases. The experimental results display that our method achieves excellent performance for symmetry detection. Comparisons with the state-of-the-art methods also demonstrate the effectiveness and advantages for our approach in achieving higher accuracy than the previous competitors.

Exploring partial intrinsic and extrinsic symmetry in 3D medical imaging

We present a novel methodology to detect imperfect bilateral symmetry in CT of human anatomy. In this paper, the structurally symmetric nature of the pelvic bone is explored and is used to provide interventional image augmentation for treatment of unilateral fractures in patients with traumatic injuries. The mathematical basis of our solution is based on the incorporation of attributes and characteristics that satisfy the properties of intrinsic and extrinsic symmetry and are robust to outliers. In the first step, feature points that satisfy intrinsic symmetry are automatically detected in the Möbius space defined on the CT data. These features are then pruned via a two-stage RANSAC to attain correspondences that satisfy also the extrinsic symmetry. Then, a disparity function based on Tukey's biweight robust estimator is introduced and minimized to identify a symmetry plane parametrization that yields maximum contralateral similarity. Finally, a novel regularization term is introduced to enhance similarity between bone density histograms across the partial symmetry plane, relying on the important biological observation that, even if injured, the dislocated bone segments remain within the body. Our extensive evaluations on various cases of common fracture types demonstrate the validity of the novel concepts and the accuracy of the proposed method.

Content-Based Estimation of Brain MRI Tilt in Three Orthogonal Directions

In a general scenario, the brain images acquired from magnetic resonance imaging (MRI) may experience tilt, distorting brain MR images. The tilt experienced by the brain MR images may result in misalignment during image registration for medical applications. Manually correcting (or estimating) the tilt on a large scale is time-consuming, expensive, and needs brain anatomy expertise. Thus, there is a need for an automatic way of performing tilt correction in three orthogonal directions (X, Y, Z). The proposed work aims to correct the tilt automatically by measuring the pitch angle, yaw angle, and roll angle in X-axis, Z-axis, and Y-axis, respectively. For correction of the tilt around the Z-axis (pointing to the superior direction), image processing techniques, principal component analysis, and similarity measures are used. Also, for correction of the tilt around the X-axis (pointing to the right direction), morphological operations, and tilt correction around the Y-axis (pointing to the anterior direction), orthogonal regression is used. The proposed approach was applied to adjust the tilt observed in the T1- and T2-weighted MR images. The simulation study with the proposed algorithm yielded an error of 0.40 ± 0.09°, and it outperformed the other existing studies. The tilt angle (in degrees) obtained is ranged from 6.2 ± 3.94, 2.35 ± 2.61, and 5 ± 4.36 in X-, Z-, and Y-directions, respectively, by using the proposed algorithm. The proposed work corrects the tilt more accurately and robustly when compared with existing studies.

Iterative machine learning based rotational alignment of brain 3D CT data

The optimal rotational alignment of brain Computed Tomography (CT) images to a required standard position has a crucial importance for both automatic and manual diagnostic analysis. In this contribution, we present a novel two-step iterative approach for the automatic 3D rotational alignment of brain CT data. The angles of axial and coronal rotations are determined by an unsupervised by localisation of the Midsagittal Plane (MSP) method. This includes detection and pairing of medially symmetrical feature points. The sagittal rotation angle is subsequently estimated by regression convolutional neural network (CNN). The proposed methodology has been evaluated on a dataset of CT data manually aligned by radiologists. It has been shown that the algorithm achieved the low error of estimated rotations (≈1 degree) and in a significantly shorter time than the experts (≈2 minutes per case).

A Relative Noncontrast CT Map to Detect Early Ischemic Changes in Acute Stroke

BACKGROUND AND PURPOSE

Early ischemic changes on noncontrast computed tomography (NCCT) are often subtle. We developed a novel postprocessing technique that aids in detecting such changes.

METHODS

NCCT maps were generated that display the relative density difference between corresponding voxels in contralateral hemispheres (ratio maps of the NCCT [rNCCT]). Voxels with a relative density difference below .95 were designated as infarct. We pilot tested the rNCCT for infarct segmentation on 6 consecutive subjects enrolled in the CT Perfusion to predict Response in Ischemic Stroke Project (CRISP) study and applied the inclusion criteria of an adequate quality NCCT and successful endovascular reperfusion. rNCCT infarct segmentation was compared to baseline NCCT, baseline CTP, and day-5 follow-up fluid-attenuated inversion recovery (FLAIR).

RESULTS

Five of the six selected cases met the inclusion criteria. Their median time from symptom onset to CT was 4.95 hours (standard deviation [SD], ±3.5; range, 1.05-10.45), and median NIHSS was 13. Early ischemic changes were identified on the rNCCT in all five cases and on the standard NCCT in three of the five cases. Lesions outlined by the rNCCT maps trended toward a better estimation of the day-5 FLAIR volume (median difference = 6.2 mL) than the ischemic core volumes assessed on baseline CTP (median difference = 51.7 mL) in the four cases with a day-5 FLAIR (P = .1).

CONCLUSION

In this proof-of-concept study, the rNCCT appears promising for detecting and quantifying early ischemic changes. These findings should be confirmed in a larger cohort.

An Efficient Automatic Midsagittal Plane Extraction in Brain MRI

In this paper, a fully automatic and computationally efficient midsagittal plane (MSP) extraction technique in brain magnetic resonance images (MRIs) has been proposed. Automatic detection of MSP in neuroimages can significantly aid in registration of medical images, asymmetric analysis, and alignment or tilt correction (recenter and reorientation) in brain MRIs. The parameters of MSP are estimated in two steps. In the first step, symmetric features and principal component analysis (PCA)-based technique is used to vertically align the bilateral symmetric axis of the brain. In the second step, PCA is used to achieve a set of parallel lines (principal axes) from the selected two-dimensional (2-D) elliptical slices of brain MRIs, followed by a plane fitting using orthogonal regression. The developed algorithm has been tested on 157 real T1-weighted brain MRI datasets including 14 cases from the patients with brain tumors. The presented algorithm is compared with a state-of-the-art approach based on bilateral symmetry maximization. Experimental results revealed that the proposed algorithm is fast (<1.04 s per MRI volume) and exhibits superior performance in terms of accuracy and precision (a mean z-distance of 0.336 voxels and a mean angle difference of 0.06).

Classifying symmetrical differences and temporal change for the detection of malignant masses in mammography using deep neural networks

We investigate the addition of symmetry and temporal context information to a deep convolutional neural network (CNN) with the purpose of detecting malignant soft tissue lesions in mammography. We employ a simple linear mapping that takes the location of a mass candidate and maps it to either the contralateral or prior mammogram, and regions of interest (ROIs) are extracted around each location. Two different architectures are subsequently explored: (1) a fusion model employing two datastreams where both ROIs are fed to the network during training and testing and (2) a stagewise approach where a single ROI CNN is trained on the primary image and subsequently used as a feature extractor for both primary and contralateral or prior ROIs. A "shallow" gradient boosted tree classifier is then trained on the concatenation of these features and used to classify the joint representation. The baseline yielded an AUC of 0.87 with confidence interval [0.853, 0.893]. For the analysis of symmetrical differences, the first architecture where both primary and contralateral patches are presented during training obtained an AUC of 0.895 with confidence interval [0.877, 0.913], and the second architecture where a new classifier is retrained on the concatenation an AUC of 0.88 with confidence interval [0.859, 0.9]. We found a significant difference between the first architecture and the baseline at high specificity with [Formula: see text]. When using the same architectures to analyze temporal change, we yielded an AUC of 0.884 with confidence interval [0.865, 0.902] for the first architecture and an AUC of 0.879 with confidence interval [0.858, 0.898] in the second setting. Although improvements for temporal analysis were consistent, they were not found to be significant. The results show our proposed method is promising and we suspect performance can greatly be improved when more temporal data become available.

Evaluation of the effect of doubling atlases using midsagittal plane on multi-atlas based segmentation of brain structures

Normal human brain exhibits approximately bi-fold symmetry with respect to its midsagittal plane (MSP). The objective of this work is to investigate the effect of doubling atlases (i.e., reference images) used in multi-atlas fusion methods by exploiting the inherent bilateral symmetry of human brain. To this end, we perform automated segmentation of 15 subcortical structures using Local Weighted Voting (LWV) fusion method with varying number of atlases. We consider three specific scenarios for atlases while performing fusion: (i) fusion with original OASIS atlases, (ii) with atlases obtained by flipping the original atlases based on their MSP, and (iii) with both original and flipped atlases. Evaluations are performed on the publicly available OASIS dataset of 20 normal human brain MR images. One of the key findings of this study is that when the number of atlases available for fusion is less than 10, fusion by combining both the original and flipped atlases provided more accurate segmentations than using only the original atlases, or only the flipped atlases.

A hybrid approach of using symmetry technique for brain tumor segmentation

Tumor and related abnormalities are a major cause of disability and death worldwide. Magnetic resonance imaging (MRI) is a superior modality due to its noninvasiveness and high quality images of both the soft tissues and bones. In this paper we present two hybrid segmentation techniques and their results are compared with well-recognized techniques in this area. The first technique is based on symmetry and we call it a hybrid algorithm using symmetry and active contour (HASA). In HASA, we take refection image, calculate the difference image, and then apply the active contour on the difference image to segment the tumor. To avoid unimportant segmented regions, we improve the results by proposing an enhancement in the form of the second technique, EHASA. In EHASA, we also take reflection of the original image, calculate the difference image, and then change this image into a binary image. This binary image is mapped onto the original image followed by the application of active contouring to segment the tumor region.

Midsagittal plane extraction from brain images based on 3D SIFT

Midsagittal plane (MSP) extraction from 3D brain images is considered as a promising technique for human brain symmetry analysis. In this paper, we present a fast and robust MSP extraction method based on 3D scale-invariant feature transform (SIFT). Unlike the existing brain MSP extraction methods, which mainly rely on the gray similarity, 3D edge registration or parameterized surface matching to determine the fissure plane, our proposed method is based on distinctive 3D SIFT features, in which the fissure plane is determined by parallel 3D SIFT matching and iterative least-median of squares plane regression. By considering the relative scales, orientations and flipped descriptors between two 3D SIFT features, we propose a novel metric to measure the symmetry magnitude for 3D SIFT features. By clustering and indexing the extracted SIFT features using a k-dimensional tree (KD-tree) implemented on graphics processing units, we can match multiple pairs of 3D SIFT features in parallel and solve the optimal MSP on-the-fly. The proposed method is evaluated by synthetic and in vivo datasets, of normal and pathological cases, and validated by comparisons with the state-of-the-art methods. Experimental results demonstrated that our method has achieved a real-time performance with better accuracy yielding an average yaw angle error below 0.91° and an average roll angle error no more than 0.89°.