Real Clinical Images Research Articles

A lightweight detection algorithm for tooth cracks in optical images

ObjectivesCracked tooth syndrome (CTS) is one of the major causes of tooth loss, presents the problem of early microcrack symptoms that are difficult to distinguish. This paper aims to investigate the practicality and feasibility of an improved object detection algorithm for automatically detecting cracks in dental optical images. MethodsA total of 286 teeth were obtained from Sun Yat-sen University and Guangdong University of Technology, and simulated cracks were generated using thermal expansion and contraction. Over 3000 images of cracked teeth were collected, including 360 real clinical images. To make the model more lightweight and better suited for deployment on embedded devices, this paper improves the YOLOv8 model for detecting tooth cracks through model pruning and backbone replacement. Additionally, the impact of image enhancement modules and coordinate attention modules on optimizing our model was analyzed. ResultsThrough experimental validation, we conclude that that model pruning reduction maintains performance better than replacing a lightweight backbone network on a tooth crack detection task. This approach achieved a reduction in parameters and GFLOPs by 16.8 % and 24.3 %, respectively, with minimal impact on performance. These results affirm the effectiveness of the proposed method in identifying and labeling tooth fractures. In addition, this paper demonstrated that the impact of image enhancement modules and coordinate attention mechanisms on YOLOv8's performance in the task of tooth crack detection was minimal. ConclusionsAn improved object detection algorithm has been proposed to reduce model parameters. This lightweight model is easier to deploy and holds potential for assisting dentists in identifying cracks on tooth surfaces.

Assessing the Efficacy of Synthetic Optic Disc Images for Detecting Glaucomatous Optic Neuropathy Using Deep Learning.

Deep learning architectures can automatically learn complex features and patterns associated with glaucomatous optic neuropathy (GON). However, developing robust algorithms requires a large number of data sets. We sought to train an adversarial model for generating high-quality optic disc images from a large, diverse data set and then assessed the performance of models on generated synthetic images for detecting GON. A total of 17,060 (6874 glaucomatous and 10,186 healthy) fundus images were used to train deep convolutional generative adversarial networks (DCGANs) for synthesizing disc images for both classes. We then trained two models to detect GON, one solely on these synthetic images and another on a mixed data set (synthetic and real clinical images). Both the models were externally validated on a data set not used for training. The multiple classification metrics were evaluated with 95% confidence intervals. Models' decision-making processes were assessed using gradient-weighted class activation mapping (Grad-CAM) techniques. Following receiver operating characteristic curve analysis, an optimal cup-to-disc ratio threshold for detecting GON from the training data was found to be 0.619. DCGANs generated high-quality synthetic disc images for healthy and glaucomatous eyes. When trained on a mixed data set, the model's area under the receiver operating characteristic curve attained 99.85% on internal validation and 86.45% on external validation. Grad-CAM saliency maps were primarily centered on the optic nerve head, indicating a more precise and clinically relevant attention area of the fundus image. Although our model performed well on synthetic data, training on a mixed data set demonstrated better performance and generalization. Integrating synthetic and real clinical images can optimize the performance of a deep learning model in glaucoma detection. Optimizing deep learning models for glaucoma detection through integrating DCGAN-generated synthetic and real-world clinical data can be improved and generalized in clinical practice.

Generation of fluoroscopy-alike radiographs as alternative datasets for deep learning in interventional radiology.

In fluoroscopy-guided interventions (FGIs), obtaining large quantities of labelled data for deep learning (DL) can be difficult. Synthetic labelled data can serve as an alternative, generated via pseudo 2D projections of CT volumetric data. However, contrasted vessels have low visibility in simple 2D projections of contrasted CT data. To overcome this, we propose an alternative method to generate fluoroscopy-like radiographs from contrasted head CT Angiography (CTA) volumetric data. The technique involves segmentation of brain tissue, bone, and contrasted vessels from CTA volumetric data, followed by an algorithm to adjust HU values, and finally, a standard ray-based projection is applied to generate the 2D image. The resulting synthetic images were compared to clinical fluoroscopy images for perceptual similarity and subject contrast measurements. Good perceptual similarity was demonstrated on vessel-enhanced synthetic images as compared to the clinical fluoroscopic images. Statistical tests of equivalence show that enhanced synthetic and clinical images have statistically equivalent mean subject contrast within 25% bounds. Furthermore, validation experiments confirmed that the proposed method for generating synthetic images improved the performance of DL models in certain regression tasks, such as localizing anatomical landmarks in clinical fluoroscopy images. Through enhanced pseudo 2D projection of CTA volume data, synthetic images with similar features to real clinical fluoroscopic images can be generated. The use of synthetic images as an alternative source for DL datasets represents a potential solution to the application of DL in FGIs procedures.

A sparse dictionary representation approach for anti-scattering grid artifact removal in X-ray images

The aim of this work is to introduce a new joint estimation approach for anatomical content and artifacts in digital radiography. Herein, we apply this approach to the anti-scattering grid suppression problem. These grids are generally used in low-dose radiography to improve the image contrast by absorbing the scattered radiation. However, they introduce an irregular stripe pattern in the clinical images which can hinder the diagnosis made by the radiologist.The problem is tackled in a sparse dictionary representation framework with an observation and prior models accounting for the physical model of image contents. Thus, the anatomical content is supposed to be sparsely represented by a Fourier or K-SVD dictionary. Furthermore, the artifact is modeled by a frequency dictionary. In addition, the noise is modeled by a locally stationary Gaussian distribution with zero mean and unknown variance. The joint estimation of all the projections is then performed using two methods: Beam-forming (IAA) and Bayesian (SUBLIM). Moreover, patch-wise processing is applied to avoid models’ errors due to spatial variations of the clinical contents and the artifact.IAA and SUBLIM performance is demonstrated for the anti-scattering grid extraction problem using experimental and real clinical images. The proposed methods remove gridline artifacts while maintaining the image details and avoiding ringing artifacts. In addition, they produce better results compared to the conventional filtering approaches, especially when the metallic materials are present in or on the patients. SUBLIM outperforms IAA in those regions thanks to a better clinical content model and physical noise prior.

Non-local adaptive hysteresis despeckling approach for medical ultrasound images

Speckle noise is a major problem in medical ultrasound imaging that reduces the image quality and leads to a negative impact on further diagnosis. In this paper, aiming to alleviate the effect of speckle, a new ultrasound image noise reduction approach called Non-local Adaptive Hysteresis Despeckling is proposed, which effectively exploits data redundancy not only for suppression of speckle noise but also for preserving meaningful structural details in ultrasound images. Since Hysteresis smoothing-based filters are initially introduced to eliminate additive white Gaussian noise, we attempt to adapt this category of filters to the signal-dependent and multiplicative nature of speckle noise in ultrasound images. Furthermore, the local functionality of Hysteresis smoothing-based filters, which is a limitation of their effectiveness, is addressed by proposing more efficient non-local weighting and averaging schemes to be more compatible with the speckle noise model. The qualitative and quantitative evaluations of the simulated and real clinical ultrasound images show that the proposed method can outperform other state-of-the-art methods.

Automated detection of hippocampal sclerosis using real-world clinical MRI images.

Hippocampal sclerosis (HS) is the most common pathological type of temporal lobe epilepsy (TLE) and one of the important surgical markers. Currently, HS is mainly diagnosed manually by radiologists based on visual inspection of MRI, which greatly relies on MRI quality and physician experience. In clinical practice, non-thin MRI scans are often used due to the time and efficiency needed for the acquisition. However, these scans can be difficult for junior physicians to interpret accurately. Thus, the rapid and accurate diagnosis of HS using real-world MRI images in clinical settings is a challenging task. Our aim was to explore the feasibility of using computer vision methods to diagnose HS on real-world clinical MRI images and to provide a reference for future clinical applications of artificial intelligence methods to aid in detecting HS. We proposed a deep learning algorithm called "HS-Net" to discriminate HS using real-world clinical MRI images. First, we delineated and segmented a region of interest (ROI) around the hippocampus. Then, we utilized the fractional differential (FD) method to enhance the textures of the ROIs. Finally, we used a small-sample image classification method based on transfer learning to fine-tune the feature extraction part of a pretrained model and added two fully connected layers and an output layer. In the study, 96 TLE patients with HS confirmed by postoperative pathology and 89 healthy controls were retrospectively enrolled. All subjects were cross-validated, and models were evaluated for performance, robustness, and clinical utility. The HS-Net model achieved an area under the curve (AUC) of 0.894, an accuracy of 82.88%, an F1-score of 84.08% in the test cohort based on real, routine, clinical T2-weighted fluid attenuated inversion recovery (FLAIR) sequence MRI images. Additionally, the AUC, accuracy and F1 scores of our model all increased by around 3 percentage points when the inputs were augmented with the ROIs of the textures enhanced using the FD method. Our computational model has the potential to be used for the diagnosis of HS in real clinical MRI images, which could assist physicians, particularly junior physicians, in improving the accuracy of discrimination.

PCcS-RAU-Net: Automated parcellated Corpus callosum segmentation from brain MRI images using modified residual attention U-Net

BackgroundThe Corpus callosum (Cc) in the cerebral cortex is a bundle of neural fibers that facilitates inter-hemispheric communication. The Cc area and area of its sub-regions (also known as parcels) have been examined as a biomarker for cortical pathology and differential diagnosis in neurodegenerative diseases such as Autism, Alzheimer’s disease (AD), and more. Manual segmentation and parcellation of Cc are laborious and time-consuming. The present work proposes a novel work of automated parcellated Cc (PCc) segmentation that will serve as a potential biomarker to study and diagnose neurological disorders in brain MRI images. MethodIn this perspective, the present work aims to develop an automated PCc segmentation from mid-sagittal T1- weighted (w) 2D brain MRI images using a deep learning-based fully convolutional network, a modified residual attention U-Net, referred to as PCcS-RAU-Net. The model has been modified to use a multi-class segmentation configuration with five target classes (parcels): rostrum, genu, mid-body, isthmus and splenium. ResultsThe experimental research uses two benchmark MRI datasets, ABIDE and OASIS. The proposed PCcS-RAU-Net outperformed existing methods on the ABIDE dataset with a DSC of 97.10% and MIoU of 94.43%. Furthermore, the model's performance is validated on the OASIS and Real clinical image (RCI) data and hence verifies the model’s generalization capability. ConclusionThe proposed PCcS-RAU-Net model extracts essential characteristics such as the total area of the Cc (TCcA) to categorize MRI slices into healthy controls (HC) and disease groups. Also, sub-regional areas, Cc1A to Cc5A, help study atrophy progression for early diagnosis.

RFormer: Transformer-Based Generative Adversarial Network for Real Fundus Image Restoration on a New Clinical Benchmark.

Ophthalmologists have used fundus images to screen and diagnose eye diseases. However, different equipments and ophthalmologists pose large variations to the quality of fundus images. Low-quality (LQ) degraded fundus images easily lead to uncertainty in clinical screening and generally increase the risk of misdiagnosis. Thus, real fundus image restoration is worth studying. Unfortunately, real clinical benchmark has not been explored for this task so far. In this paper, we investigate the real clinical fundus image restoration problem. Firstly, We establish a clinical dataset, Real Fundus (RF), including 120 low- and high-quality (HQ) image pairs. Then we propose a novel Transformer-based Generative Adversarial Network (RFormer) to restore the real degradation of clinical fundus images. The key component in our network is the Window-based Self-Attention Block (WSAB) which captures non-local self-similarity and long-range dependencies. To produce more visually pleasant results, a Transformer-based discriminator is introduced. Extensive experiments on our clinical benchmark show that the proposed RFormer significantly outperforms the state-of-the-art (SOTA) methods. In addition, experiments of downstream tasks such as vessel segmentation and optic disc/cup detection demonstrate that our proposed RFormer benefits clinical fundus image analysis and applications.

19. Breastgan: Artificial Intelligence-enabled Breast Augmentation Simulation

Purpose: Managing patient expectations is important to ensuring patient satisfaction in aesthetic medicine. To this end, computer technology developed to photograph, digitize, and manipulate three-dimensional (3D) objects has been applied to the female breast. However, the systems remain complex, physically cumbersome, and extremely expensive. The authors of the current study wish to introduce the plastic surgery community to BreastGAN (Breast Generative Adversarial Network), a portable, artificial intelligence-equipped tool trained on real clinical images to simulate breast augmentation outcomes. Methods: Charts of all patients who underwent bilateral breast augmentation performed by the senior author were retrieved and analyzed. Frontal before and after images were collected from each patient’s chart, cropped in a standardized fashion, and used to train a neural network designed to manipulate before images to simulate a surgical result. AI-generated frontal after images were then compared to the real surgical results. Results: Standardizing the evaluation of surgical results is a timeless challenge which persists in the context of AI-synthesized after images. In this study, AI-generated images were comparable to real surgical results. Conclusion: This study features a portable, cost-effective neural network trained on real clinical images and designed to simulate surgical results following bilateral breast augmentation. Tools trained on a larger dataset of standardized surgical image pairs will be the subject of future studies.

Joint synthesis and registration network for deformable MR-CBCT image registration for neurosurgical guidance

Objective. The accuracy of navigation in minimally invasive neurosurgery is often challenged by deep brain deformations (up to 10 mm due to egress of cerebrospinal fluid during neuroendoscopic approach). We propose a deep learning-based deformable registration method to address such deformations between preoperative MR and intraoperative CBCT. Approach. The registration method uses a joint image synthesis and registration network (denoted JSR) to simultaneously synthesize MR and CBCT images to the CT domain and perform CT domain registration using a multi-resolution pyramid. JSR was first trained using a simulated dataset (simulated CBCT and simulated deformations) and then refined on real clinical images via transfer learning. The performance of the multi-resolution JSR was compared to a single-resolution architecture as well as a series of alternative registration methods (symmetric normalization (SyN), VoxelMorph, and image synthesis-based registration methods). Main results. JSR achieved median Dice coefficient (DSC) of 0.69 in deep brain structures and median target registration error (TRE) of 1.94 mm in the simulation dataset, with improvement from single-resolution architecture (median DSC = 0.68 and median TRE = 2.14 mm). Additionally, JSR achieved superior registration compared to alternative methods—e.g. SyN (median DSC = 0.54, median TRE = 2.77 mm), VoxelMorph (median DSC = 0.52, median TRE = 2.66 mm) and provided registration runtime of less than 3 s. Similarly in the clinical dataset, JSR achieved median DSC = 0.72 and median TRE = 2.05 mm. Significance. The multi-resolution JSR network resolved deep brain deformations between MR and CBCT images with performance superior to other state-of-the-art methods. The accuracy and runtime support translation of the method to further clinical studies in high-precision neurosurgery.

Development of anthropomorphic mathematical phantoms for simulations of clinical cases in diagnostic nuclear medicine

ABSTRACT We seek to propose a new generation of mathematically stylised phantoms with high levels of anatomical detail for the purposes of SPECT and PET simulations. Two basic phantoms were created: a mathematical model of the torso (MMT) and a mathematical model of the whole body (MMB). The phantoms can be manipulated by varying the position, size and shape of bones and organs to simulate patients with anatomical variants. Verification of the developed phantoms was performed by comparing simulated planar images for MMT and MMB with clinical data. Both phantoms did produce realistic planar images, which closely mimic real clinical planar images. Images obtained in computer simulation of myocardial perfusion SPECT with virtual patient (MMT) demonstrate the same errors and interpretation problems that exist in clinical routine. These phantoms can be used for simulations of clinical cases to help medical experts to understand the causes of artefacts and bias in PET and SPECT images.

Impact of pixel value truncation on image quality of low dose chest CT.

In some noisy low dose CT lung cancer screening images, we noticed that the CT density values of air were increased and the visibility of emphysema was distinctly decreased. By examining histograms of these images, we found that the CT density values were truncated at -1024 HU. The purpose of this study was to investigate the effect of pixel value truncation on the visibility of emphysema using mathematical models. Assuming CT noise follows a normal distribution, we derived the relationship between the mean CT density value and the standard deviation (SD) when the pixel values below -1024 HU are truncated and replaced by -1024 HU. To validate our mathematical model, 20 untruncated phantom CT images were truncated by simulation, and the mean CT density values and SD of air in the images were measured and compared with the theoretical values. In addition, the mean CT density values and SD of air were measured in 100 cases of real clinical images obtained by GE, Siemens, and Philips scanners, respectively, and the agreement with the theoretical values was examined. Next, the contrast-to-noise ratio (CNR) between air (-1000 HU) and lung parenchyma (-850 HU) was derived from the mathematical model in the presence and absence of truncation as a measure of the visibility of emphysema. In addition, the radiation dose ratios required to obtain the same CNR in the case with and without truncation were also calculated. The mathematical model revealed that when the pixel values are truncated, the mean CT density values are proportional to the noise magnitude when the magnitude exceeds a certain level. The mean CT density values and SD measured in the images with pixel values truncated by simulation and in the real clinical images acquired by GE and Philips scanners agreed well with the theoretical values from our mathematical model. In the Siemens images, the measured and theoretical values agreed well when a portion of the truncated values were replaced by random values instead of simply replacing by -1024 HU. The CNR of air and lung parenchyma was lowered by truncating CT density values compared to that of no truncation. Furthermore, it was found that higher radiation dose was required to obtain the same CNR with truncation as without. As an example, when the noise SD was 60 HU, the radiation dose required for the GE and Philips truncation method was about 1.2 times higher than that without truncation, and that for the Siemens truncation method was about 1.4 times higher. It was demonstrated mathematically that pixel value truncation causes a brightening of the mean CT density value and decreases the CNR of emphysema. Our results indicate that it is advisable to turn off truncation at -1024 HU, especially when scanning at low and ultra-low radiation doses in the thorax.

BreastGAN: Artificial Intelligence-Enabled Breast Augmentation Simulation.

BackgroundManaging patient expectations is important to ensuring patient satisfaction in aesthetic medicine. To this end, computer technology developed to photograph, digitize, and manipulate three-dimensional (3D) objects has been applied to the female breast. However, the systems remain complex, physically cumbersome, and extremely expensive.ObjectivesThe authors of the current study wish to introduce the plastic surgery community to BreastGAN, a portable, artificial intelligence (AI)-equipped tool trained on real clinical images to simulate breast augmentation outcomes.MethodsCharts of all patients who underwent bilateral breast augmentation performed by the senior author were retrieved and analyzed. Frontal before and after images were collected from each patient’s chart, cropped in a standardized fashion, and used to train a neural network designed to manipulate before images to simulate a surgical result. AI-generated frontal after images were then compared with the real surgical results.ResultsStandardizing the evaluation of surgical results is a timeless challenge which persists in the context of AI-synthesized after images. In this study, AI-generated images were comparable to real surgical results.ConclusionsThis study features a portable, cost-effective neural network trained on real clinical images and designed to simulate surgical results following bilateral breast augmentation. Tools trained on a larger dataset of standardized surgical image pairs will be the subject of future studies.

A metal artifact reduction scheme in CT by a Poisson fusion sinogram based postprocessing method.

To reduce secondary artifactes generated by the current interpolation-based metal artifact reduction (MAR) methods, this study proposes and tests a new Poisson fusion sinogram based metal artifact reduction (FS-MAR) method. The proposed FS-MAR method consists of (1) generating the prior image, (2) forward projecting this prior image and applying the Poisson blending technique to seamlessly replace the metal-affected sinogram of the original projection in the metal projection region (MPR) by the prior image projection to get the corrected metal-free sinogram, and (3) performing the filtered back projection (FBP) on the corrected sinogram and filling the metal image back to the metal-free corrected image to get the final artifact reduced image. Simulated images are calculated by taking clinical metal-free CT images as phantoms and inserting metals during the simulated projection process to get the corresponding metal-affected images by the FBP. After the simulated images are processed by the proposed MAR method, two metrics structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) are used to evaluate image quality. Finally, visual evaluation is also performed using several real clinical metal-affected images obtained from the Revision Radiology group. In two testing samples, using FS-MAR method yields the highest SSIM and PSNR of 0.8912 and 30.6693, respectively. Visual evaluation results on both simulated and clinical images also show that using FS-MAR method generates less image artifacts than using the interpolation-based algorithm. This study demonstrated that with the same prior image, applying the proposed Poisson FS-MAR method can achieve the higher image quality than using the interpolation-based algorithm.

Wavelet Methods and Pattern Recognition for Clinical Image Fusion

This research focuses of the efficacious wavelet-based methodology for clinical image fusion that is established by considering the human visual system, including the physical effects of the wavelet coefficients. Once the clinical images that have to be fused have been decomposed via the transforms of wavelet, different systems of fusion for integrating these coefficients are projected. The coefficients in the lower frequencies are chosen with the visibility-centered system, and those coefficients with the highest frequency bands are chosen using the variance-oriented approach. To effective mitigate the issue of noise and guarantee homogeneity of an image, which is being fused, coefficients are typically done based on the application of the window-centered verification process. The images are lastly structured using the inverse wavelet transforms with the composite coefficient. To effectively assess and effectively prove the effective applicability of the proposed methodology, experimentation series and comparison of the fusion approaches are done. The results of the experimentation on the real and simulated clinical images show that the projected approach is effective and is capable of yielding the proposed results of the fusion process.

Artificial Bee Colony Optimization Based Despeckling Framework for Ultrasound Images

This paper proposed an artificial bee colony optimization (ABC) algorithm based despeckling framework to overcome the effect of speckle noise present in real ultrasound images. A low pass filter and fast non-local mean filter along with Artificial Bee Colony (ABC) optimization algorithm are used for the quality enhancement of ultrasound images. The output results obtained for the real ultrasound images filtered with the proposed approach and the other most studied approaches discussed in the literature. The outperformance of the proposed method is verified by calculation of peak signal to noise ratio (PSNR), mean square error (MSE), mean absolute error (MAE), and structure similarity index (SSIM) quality measures. The proposed filtering approach is tested on eight real clinical ultrasound images of adrenal gland, appendicitis, bladder, pancreas, parathyroid gland, scrotal gland, thoracic wall, and uterus. The experimental results yield that the quantitative and qualitative results of the proposed framework are better than benchmark despeckling methods compared to real ultrasound images. Further, the proposed framework also preserves the fine details in real ultrasound images.

Noise-Robust MRI Upsampling Using Adaptive Local Steering Kernel

Upsampling and denoising of magnetic resonance images are conventionally performed separately, which would introduce unwanted artifacts such as blurring. To address this problem, we propose an innovative adaptive interpolation framework to achieve simultaneous image upsampling, denoising, and detail enhancement. First, local steering kernel (LSK) function is leveraged to adapt the interpolation weights according to geometric structures in the magnetic resonance (MR) images. An adaptive sharpening of the LSK weight matrix and a Rician bias correction are then adopted to remove Rician noise and enhance fine details. In this regard, the adaptive LSK extends the zero-order point estimation framework to higher orders of regression, and therefore facilitates edge preservation and detail reconstruction. The post-processing Rician correction avoids the bias caused by the asymmetry of Rician noise distributions. Experimental results using both real and synthetic clinical MR cranial images (with and without noise) demonstrated that our algorithm produced better reconstruction results than several traditional interpolation-based upsampling methods, including nearest neighbor (NN), non-local means (NLM), self-learning super resolution (SLSR), Gaussian process regression (GPR), and even comparable to four deep-learning-based methods but with less data requirements and computational complexity. The proposed technique resulted in PSNR and SSIM values were ~3%-16% higher than any of the other traditional algorithms tested, and our method recovered more clear textures from noisy images compared with deep-learning-based methods. As such, the presented technique is a viable new approach to MR upsampling, particularly for noisy images.

Multiscale brain MRI super-resolution using deep 3D convolutional networks

The purpose of super-resolution approaches is to overcome the hardware limitations and the clinical requirements of imaging procedures by reconstructing high-resolution images from low-resolution acquisitions using post-processing methods. Super-resolution techniques could have strong impacts on structural magnetic resonance imaging when focusing on cortical surface or fine-scale structure analysis for instance. In this paper, we study deep three-dimensional convolutional neural networks for the super-resolution of brain magnetic resonance imaging data. First, our work delves into the relevance of several factors in the performance of the purely convolutional neural network-based techniques for the monomodal super-resolution: optimization methods, weight initialization, network depth, residual learning, filter size in convolution layers, number of the filters, training patch size and number of training subjects. Second, our study also highlights that one single network can efficiently handle multiple arbitrary scaling factors based on a multiscale training approach. Third, we further extend our super-resolution networks to the multimodal super-resolution using intermodality priors. Fourth, we investigate the impact of transfer learning skills onto super-resolution performance in terms of generalization among different datasets. Lastly, the learnt models are used to enhance real clinical low-resolution images. Results tend to demonstrate the potential of deep neural networks with respect to practical medical image applications.

Social-Group-Optimization based tumor evaluation tool for clinical brain MRI of Flair/diffusion-weighted modality

Brain tumor is one of the harsh diseases among human community and is usually diagnosed with medical imaging procedures. Computed-Tomography (CT) and Magnetic-Resonance-Image (MRI) are the regularly used non-invasive methods to acquire brain abnormalities for medical study. Due to its importance, a significant quantity of image assessment and decision-making procedures exist in literature. This article proposes a two-stage image assessment tool to examine brain MR images acquired using the Flair and DW modalities. The combination of the Social-Group-Optimization (SGO) and Shannon’s-Entropy (SE) supported multi-thresholding is implemented to pre-processing the input images. The image post-processing includes several procedures, such as Active Contour (AC), Watershed and region-growing segmentation, to extract the tumor section. Finally, a classifier system is implemented using ANFIS to categorize the tumor under analysis into benign and malignant. Experimental investigation was executed using benchmark datasets, like ISLES and BRATS, and also clinical MR images obtained with Flair/DW modality. The outcome of this study confirms that AC offers enhanced results compared with other segmentation procedures considered in this article. The ANFIS classifier obtained an accuracy of 94.51% on the used ISLES and real clinical images.

IMCAD: Computer Aided System for Breast Masses Detection based on Immune Recognition

Computer Aided Detection (CAD) systems are very important tools which help radiologists as a second reader in detecting early breast cancer in an efficient way, specially on screening mammograms. One of the challenging problems is the detection of masses, which are powerful signs of cancer, because of their poor apperance on mammograms. This paper investigates an automatic CAD for detection of breast masses in screening mammograms based on fuzzy segmentation and a bio-inspired method for pattern recognition: Artificial Immune Recognition System. The proposed approach is applied to real clinical images from the full field digital mammographic database: Inbreast. In order to validate our proposition, we propose the Receiver Operating Characteristic Curve as an analyzer of our IMCAD classifier system, which achieves a good area under curve, with a sensitivity of 100% and a specificity of 95%. The recognition system based on artificial immunity has shown its efficiency on recognizing masses from a very restricted set of training regions.