Search

Question: Is periodised circuit training delivered via a telerehabilitation model of care as effective as the same training applied face-to-face for improving pain intensity, physical function, muscle strength, pain catastrophising, body composition, intermuscular adipose tissue and muscle architecture in people with knee osteoarthritis (OA)?, Design: Randomised controlled, non-inferiority trial with concealed allocation, blinded assessors and intention-to-treat analysis., Participants: One hundred adults aged ≥ 40 years with knee OA and pain for ≥ 3 months, with current pain ≥ 40 mm on a 100-mm visual analogue scale (VAS)., Intervention: The experimental group received 14 weeks of circuit training delivered via telerehabilitation using video recordings, followed by periodic phone calls in order to motivate and instruct participants. The control group received the same circuit training program in a face-to-face format., Outcome Measures: The primary outcomes were pain VAS and the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) physical function subscale, measured at 14 weeks. Secondary outcomes included objective physical function, strength, pain catastrophising and morphological measures (muscle architecture and thigh and body composition). Outcomes were measured at 14 and 26 weeks., Results: Periodised circuit training delivered via telerehabilitation had equivalent effects to face-to-face delivery for pain intensity, physical function, muscle strength, pain catastrophising, thigh composition, intermuscular adipose tissue and muscle architecture. Whole body composition did not change appreciably in either group. Adherence to the training was excellent and participants in each group reported good perceptions of their randomised intervention., Conclusion: A periodised circuit training protocol can be delivered to people with knee OA in their own homes, using available technology while maintaining high levels of acceptability. More importantly, telerehabilitation appears to cause non-inferior physical and functional outcomes to face-to-face rehabilitation programs., Trial Registration: RBR-662hn2., (Copyright © 2023 Australian Physiotherapy Association. Published by Elsevier B.V. All rights reserved.)

Background and Objective: Alzheimer's disease (AD) is a neurodegenerative, progressive, and irreversible disease that accounts for up to 80% of all dementia cases. AD predominantly affects older adults, and its clinical diagnosis is a challenging evaluation process, with imprecision rates between 12 and 23%. Structural magnetic resonance (MR) imaging has been widely used in studies related to AD because this technique provides images with excellent anatomical details and information about structural changes induced by the disease in the brain. Current studies are focused on detecting AD in its initial stage, i.e., mild cognitive impairment (MCI), since treatments for preventing or delaying the onset of symptoms is more effective when administered at the early stages of the disease. This study proposes a new technique to perform MR image classification in AD diagnosis using discriminative hippocampal point landmarks among the cognitively normal (CN), MCI, and AD populations., Methods: Our approach, based on a two-level classification, first detects and selects discriminative landmark points from two diagnosis populations based on their matching distance compared to a probabilistic atlas of 3-D labeled landmark points. The points are classified using attributes computed in a spherical support region around each point using information from brain probability image tissues of gray matter, white matter, and cerebrospinal fluid as sources of information. Next, at the second level, the images are classified based on a quantitative evaluation obtained from the first-level classifier outputs., Results: For the CN×MCI experiment, we achieved an AUC of 0.83, an accuracy of 75.58%, with 72.9% of sensitivity and 77.81% of specificity. For the MCI×AD experiment, we achieved an AUC value of 0.73, an accuracy of 69.8%, a sensitivity of 74.09% and specificity of 64.57%. Finally, for the CN×AD, we achieved an AUC of 0.95, an accuracy of 89.24%, with 85.58% of sensitivity and 92.71% of specificity., Conclusions: The obtained classification results are similar to (or even higher than) other studies that classify AD compared to CN individuals and comparable to those classified patients with MCI., (Copyright © 2021 Elsevier B.V. All rights reserved.)

The analysis of leukocyte recruitment in intravital video microscopy (IVM) is essential to the understanding of inflammatory processes. However, because IVM images often present a large variety of visual characteristics, it is hard for an expert human or even conventional machine learning techniques to detect and count the massive amount of cells and extract statistical measures precisely. Convolutional neural networks are a promising approach to overcome this problem, but due to the difficulty of labeling cells, large data sets with ground truth are rare. The present work explores an adaptation of the RetinaNet model with a suite of augmentation techniques and transfer learning for detecting leukocytes in IVM data. The augmentation techniques include simulating the Airy pattern and motion artifacts present in microscopy imaging, followed by traditional photometric, geometric and smooth elastic transformations to reproduce color and shape changes in cells. In addition, we analyzed the use of different network backbones, feature pyramid levels, and image input scales. We have found that even with limited data, our strategy not only enables training without overfitting but also boosts generalization performance. Among several experiments, the model reached a value of 94.84 for the average precision (AP) metric as our best outcome when using data from different image modalities. We also compared our results with conventional image processing techniques and open-source tools. The results showed an outstanding precision of the method compared with other approaches, presenting low error rates for cell counting and centroid distances. Code is available at: https://github.com/brunoggregorio/retinanet-cell-detection., (Copyright © 2020 Elsevier Ltd. All rights reserved.)

Background: Brain Magnetic Resonance (MR) image segmentation methods based on deformable models depend on the initial positioning to maximize the chances of successful segmentation. To minimize this limitation, salient-point based registration is used to perform the initial positioning of brain structure meshes close to their image target representation. The analysis of brain structures (such as the hippocampus) can help in the diagnosis and follow-up of neurodegenerative diseases like Alzheimer's., Methods: We present a technique for detection and description of 3-D salient points, which combines filter response maps estimated for different scales and orientations of the dual-tree complex wavelet transform (DT-CWT). We apply our technique to detect salient points in volumetric brain MR images and use the detected points in a positioning methodology. To illustrate the applicability, we applied our method for the positioning of hippocampi meshes in 3-D brain MR images and assessed the results by overlapping the positioned meshes with manual annotations made by medical specialists., Results: Our method yielded mean values of normalized Dice Similarity Coefficient (nDSC) of 0.74/0.68 and Hausdorff Average Distance (HAD) of 0.73/0.75 for the left and right hippocampus, respectively., Comparison With Other Methods: The mean nDSC and HAD results of our detector were significantly better than the ones achieved by an Affine and a Phase Congruency (PC) guided positioning., Conclusions: The detection via DT-CWT decomposition is computationally less demanding than the detection via PC and represents a robust alternative for the positioning of mesh models., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Objective: To analyze the influence of a 14-week periodized circuit training (CT) protocol on thigh intermuscular fat and muscle quality (force per unit area of lean tissue) in patients with knee osteoarthritis (KOA)., Design: Randomized controlled trial METHODS: Sixty-one selected participants with KOA grades 2 and 3, 40-65 years old, and BMI < 30 kg/m 2 were randomized into three groups: CT, conventional strength training (ST), and educational protocol (EP). The CT and ST protocols consisted of 14-week training protocols conducted 3 times a week. The CT group performed exercises stratified as light, moderate, and intense, arranged progressively in a circuit model. The ST group performed conventional strength exercises, and the EP group participated in lectures twice a month about healthy lifestyles. Baseline and follow-up (week 0 and week 14) evaluations were conducted for thigh intermuscular fat (computed tomography), knee extension maximal isometric voluntary contraction (MIVC), and muscle quality (knee extension MIVC/muscle mass cross-sectional area)., Results: Only the CT group presented significant reductions in thigh intermuscular fat (p = 0.003) and significantly lower values in week 14 compared with the EP (p = 0.032). Both trained groups presented significant increases in muscle mass area (p=0.002 for CT and p=0.008 for ST) and increments in knee extension MIVC (p=0,033 for CT nd p=0.019 for ST) in week 14 compared with the EP and increases in muscle quality (p = 0.004 and 0.042)., Conclusion: It can be concluded that a 14-week periodized CT protocol attenuates thigh intermuscular fat and improves muscle quality in patients with KOA., Trial Registration: ClinicalTrials.gov, NCT02761590; https://clinicaltrials.gov/ct2/show/NCT02761590Key Points•Fourteen weeks of periodized circuit training attenuates thigh intermuscular fat in patients with knee osteoarthritis.•Circuit training is as effective as strength training for improving muscle mass, strength, and quality.

Rhodocybe fumanellii is described from Italy as a new species based both on morphological and molecular nrITS/nrLSU data. It belongs in sect. Rufobrunnea and is characterised by massive tricholomatoid basidiomata with reddish-brown tinges, adnate and crowded lamellae, an enlarged stipe base with long rhizomorphs, long sinuose slender cheilocystidia, ellipsoid basidiospores and the presence of caulocystidia. Drawings of the main micromorphological features as well as a colour photograph of fresh basidiomata in situ are provided and its morphological relationships with allied species are discussed.

Multiple sclerosis (MS) is a demyelinating autoimmune disease that attacks the central nervous system (CNS) and affects more than 2 million people worldwide. The segmentation of MS lesions in magnetic resonance imaging (MRI) is a very important task to assess how a patient is responding to treatment and how the disease is progressing. Computational approaches have been proposed over the years to segment MS lesions and reduce the amount of time spent on manual delineation and inter- and intra-rater variability and bias. However, fully-automatic segmentation of MS lesions still remains an open problem. In this work, we propose an iterative approach using Student's t mixture models and probabilistic anatomical atlases to automatically segment MS lesions in Fluid Attenuated Inversion Recovery (FLAIR) images. Our technique resembles a refinement approach by iteratively segmenting brain tissues into smaller classes until MS lesions are grouped as the most hyperintense one. To validate our technique we used 21 clinical images from the 2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge dataset. Evaluation using Dice Similarity Coefficient (DSC), True Positive Ratio (TPR), False Positive Ratio (FPR), Volume Difference (VD) and Pearson's r coefficient shows that our technique has a good spatial and volumetric agreement with raters' manual delineations. Also, a comparison between our proposal and the state-of-the-art shows that our technique is comparable and, in some cases, better than some approaches, thus being a viable alternative for automatic MS lesion segmentation in MRI., (Copyright © 2016 Elsevier Ltd. All rights reserved.)

Intravital microscopy is an important experimental tool for the study of cellular and molecular mechanisms of the leukocyte-endothelial interactions in the microcirculation of various tissues and in different inflammatory conditions of in vivo specimens. However, due to the limited control over the conditions of the image acquisition, motion blur and artifacts, resulting mainly from the heartbeat and respiratory movements of the in vivo specimen, will very often be present. This problem can significantly undermine the results of either visual or computerized analysis of the acquired video images. Since only a fraction of the total number of images are usually corrupted by severe motion blur, it is necessary to have a procedure to automatically identify such images in the video for either further restoration or removal. This paper proposes a new technique for the detection of motion blur in intravital video microscopy based on directional statistics of local energy maps computed using a bank of 2D log-Gabor filters. Quantitative assessment using both artificially corrupted images and real microscopy data were conducted to test the effectiveness of the proposed method. Results showed an area under the receiver operating characteristic curve (AUC) of 0.95 (AUC = 0.95; 95 % CI 0.93-0.97) when tested on 329 video images visually ranked by four observers.

Purpose: To compare the acute toxicities in radical treatment of prostate cancer between conventional schedule (C-ARM) with 78 Gy/39 fractions and hypofractionation conformal treatment (H-ARM) with 69 Gy/23 fractions., Methods and Material: This prospective double arm study consisted of 217 patients with prostate cancer, 112 in H-ARM and 105 in C-ARM arm. C-ARM received conventional six- field conformal radiotherapy with 78 Gy in 39 fractions while H-ARM received hypofractionation with 69 Gy in 23 fractions. Weekly assessment of acute reactions was done during treatment and with one, and 3 months using RTOG scale. Univariated analysis was performed to evaluate differences between the incidences of acute reaction in the treatment arms. Variables with p value less than 0.1 were included in the multivariated logistic regression., Results: There was no difference between H-ARM versus C-ARM for severity and incidence in genitourinary (GU) and gastrointestinal (GI) acute toxicity. During the treatment comparing H-ARM with C-ARM no differences was observed for GI toxicity (grade 0-3; H-ARM=45.5%, 34%, 18.7% and 1.8% versus C-ARM=47.6%, 35.2%, 17.2% and 0). For acute GU toxicity no difference was detected between H-ARM (grade 0-3; 22.3%, 54.5%, 18.7% and 4.5%) and C-ARM (grade 0-3; 25.8%, 53.3%, 17.1% and 3.8%).At the 3- months follow-up, persistent Grade> =2 acute GU and GI toxicity were 2.5% and 1.8% in H-ARM versus 5.7% and 3% in C-ARM (p>0.05). In univariated and multivariated analyses, there was not any dosimetric predictor for GI and GU toxicity., Conclusions: Our data demonstrate that hypofractionated radiotherapy achieving high biological effective dose using conformal radiotherapy is feasible for prostate cancer, being well tolerated with minimal severe acute toxicity.

Although anisotropic diffusion filters have been used extensively and with great success in medical image denoising, one limitation of this iterative approach, when used on fully automatic medical image processing schemes, is that the quality of the resulting denoised image is highly dependent on the number of iterations of the algorithm. Using many iterations may excessively blur the edges of the anatomical structures, while a few may not be enough to remove the undesirable noise. In this work, a mathematical model is proposed to automatically determine the number of iterations of the robust anisotropic diffusion filter applied to the problem of denoising three common human brain magnetic resonance (MR) images (T1-weighted, T2-weighted and proton density). The model is determined off-line by means of the maximization of the mean structural similarity index, which is used in this work as metric for quantitative assessment of the resulting processed images obtained after each iteration of the algorithm. After determining the model parameters, the optimal number of iterations of the algorithm is easily determined without requiring any extra computation time. The proposed method was tested on 3D synthetic and clinical human brain MR images and the results of qualitative and quantitative evaluation have shown its effectiveness.

Cellular therapy is a potential approach to improve the regenerative capacity of damaged or diseased skeletal muscle. However, its clinical use has often been limited by impaired donor cell survival, proliferation and differentiation following transplantation. Additionally, functional improvements after transplantation are all-too-often negligible. Because the host microenvironment plays an important role in the fate of transplanted cells, methods to modulate the microenvironment and guide donor cell behavior are warranted. The purpose of this study was to investigate whether the use of neuromuscular electrical stimulation (NMES) for 1 or 4 weeks following muscle-derived stem cell (MDSC) transplantation into dystrophic skeletal muscle can modulate the fate of donor cells and enhance their contribution to muscle regeneration and functional improvements. Animals submitted to 4 weeks of NMES after transplantation demonstrated a 2-fold increase in the number of dystrophin+ myofibers as compared to control transplanted muscles. These findings were concomitant with an increased vascularity in the MDSC+NMES group when compared to non-stimulated counterparts. Additionally, animals subjected to NMES (with or without MDSC transplantation) presented an increased maximal specific tetanic force when compared to controls. Although cell transplantation and/or the use of NMES resulted in no changes in fatigue resistance, the combination of both MDSC transplantation and NMES resulted in a faster recovery from fatigue, when compared to non-injected and non-stimulated counterparts. We conclude that NMES is a viable method to improve MDSC engraftment, enhance dystrophic muscle strength, and, in combination with MDSC transplantation, improve recovery from fatigue. These findings suggest that NMES may be a clinically-relevant adjunct approach for cell transplantation into skeletal muscle.

Purpose: Image texture has recently attracted much attention in providing quantitative features that are unique to various different tissue types, in particular, in MR images of the brain. Such image features may be useful for tumor response quantification. As a first step, one needs to establish if these features are sensitive to different tissues of clinical relevance. Here, a novel method of texture analysis based on the Hartley transform has been investigated and applied to MR images of glioblastoma multiforme (GBM)., Methods: Contrast-enhanced T1-weighted gradient-echo and T2-FLAIR spin-echo MR images of 27 GBM patients acquired prior to radiation therapy were available for analysis. Before computing texture features on these images, a novel image transformation was employed in the form of a power map computed from the localized Hartley transform of the image. Haralick statistical texture features were then computed based on the power map. This method was compared to the standard approach of obtaining texture features directly from the image. Twelve different features were computed on different resolution levels. On a regional resolution level, image texture features were identified that are able to correctly classify entire regions within T1-weighted and T2-FLAIR brain MR images of GBM patients into abnormal (containing contrast-enhancing GBM tumor) and brain tissue. Various metrics [area under the ROC curve (AUC), maximum accuracy, and Canberra distance] have been computed to quantify the usefulness of these features. On a local resolution level, it was investigated which of these features are able to provide a voxel-by-voxel enhancement that could be used for assisting the segmentation of the gross tumor volume on T1 images. The "gold standard" for this analysis was a gross tumor volume corresponding to the contrast-enhancing lesion visualized on T1-weighted images as segmented by a radiation oncologist., Results: The Sum-mean and Variance features demonstrated the best performance overall. For the T1-weighted images, the identification performance of Sum-mean and Variance features computed from the power map was higher (AUC = 0.9959 and AUC = 0.9918, respectively) and with higher Canberra distances as compared to features computed directly from the images (AUC = 0.8930 and AUC = 0.9163, respectively). These results in T2-FLAIR images were even superior. The features computed from the power map showed an unequivocal identification (AUC = 1) with higher Canberra distances, whereas the performance of the features from the original images was slightly lower (AUC = 0.9739 and AUC = 0.9904, respectively). The same features computed on the power map of the T1-weighted images also provided superior enhancement in individual tumor voxels as compared to the features computed on the original images., Conclusions: The Sum-mean and Variance features are both useful for identifying and segmenting GBM tumors on localized Hartley transformed MR images.

Muscle-derived stem-cell (MDSC) transplantation presents a promising method for the treatment of muscle injuries. This study investigated the ability of exercise to enhance MDSC transplantation into the injured muscle. Mice were divided into four groups: contusion + phosphate-buffered saline (C + PBS; n = 14 muscles), C + MDSC transplantation (n = 12 muscles), C + PBS + treadmill running (C + PBS + TM; n = 17 muscles), and C + MDSC + TM (n = 13 muscles). One day after injury, the TM groups began running for 1 or 5 weeks. Two days after injury, muscles of C + MDSC and C + MDSC + TM groups were injected with MDSCs. One or 5 weeks later, the number and differentiation of transplanted MDSCs, myofiber regeneration, collagen I formation, and vascularity were assessed histologically. In vitro, MDSCs were subjected to mechanical stimulation, and growth kinetics were quantified. In vitro, mechanical stimulation decreased the MDSC population doubling time (18.6 +/- 1.6 h) and cell division time (10.9 +/- 0.7 h), compared with the controls (population doubling time: 23.0 +/- 3.4 h; cell division time: 13.3 +/- 1.1 h) (p = 0.01 and 0.03, respectively). In vivo, 5 weeks of TM increased the myogenic contribution of transplanted MDSCs, compared with the controls (p = 0.02). C + MDSC, C + PBS + TM, and C + MDSC + TM demonstrated decreased fibrosis at 5 weeks, compared with the C + PBS controls (p = 0.00, p = 0.03, and p = 0.02, respectively). Results suggest that the mechanical stimulation favors MDSC proliferation, both in vitro and in vivo, and that exercise enhances MDSC transplantation after injury.

Objectives: To evaluate the effect of functional overloading on the transplantation of muscle derived stem cells (MDSCs) into dystrophic muscle and the ability of transplanted cells to increase dystrophic muscle's ability to resist overloading-induced weakness., Design: Cross-sectional., Setting: Laboratory., Animals: Male mice (N=10) with a dystrophin gene mutation., Interventions: MDSCs were intramuscularly transplanted into the extensor digitorum longus muscle (EDL). Functional overloading of the EDL was performed by surgical ablation of the EDL's synergist., Main Outcome Measures: The total number of dystrophin-positive fibers/cross-section (as a measure of stem cell engraftment), the average number of CD31+ cells (as a measure of capillarity), and in vitro EDL contractile strength. Independent t tests were used to investigate the effect of overloading on engraftment, capillarity, and strength. Paired t tests were used to investigate the effect of MDSC engraftment on strength and capillarity., Results: MDSC transplantation protects dystrophic muscles against overloading-induced weakness (specific twitch force: control 4.5N/cm2+/-2.3; MDSC treated 7.9N/cm2+/-1.4) (P=.02). This improved force production following overloading is concomitant with an increased regeneration by transplanted MDSCs (MDSC: 26.6+/-20.2 dystrophin-positive fibers/cross-section; overloading + MDSC: 170.6+/-130.9 dystrophin-positive fibers/cross-section [P=.03]). Overloading-induced increases in skeletal muscle capillarity is significantly correlated with increased MDSC engraftment (R2=.80, P=.01)., Conclusions: These findings suggest that the functional contribution of transplanted MDSCs may rely on activity-dependent mechanisms, possibly mediated by skeletal muscle vascularity. Rehabilitation modalities may play an important role in the development of stem cell transplantation strategies for the treatment of muscular dystrophy.

Unlabelled: The effects of different mobilization protocols for muscle regeneration after myotoxin injury was compared in the rat tibialis anterior (TA) muscle. Adult Wistar rats were divided into control (C); mobilized (M); injury (I); injury + late mobilization (LM) and injury + early mobilization (EM) groups. Muscle injury was induced by intramuscular lidocaine injection. The exercised animals were mobilized for 5 and 8 days during 15 and 45 minutes/session. The swimming started 1 hour or 3 days after injury. All animals were killed 8 days after the injury, together with the control group, when the TA muscles were weighted and excised. Cross sections were obtained by cryostat and submitted to Toluidine Blue stain. Qualitative morphological characterization of muscle regeneration and quantitative analysis of muscle fiber and non-muscle fiber area density were performed. The I and late mobilization groups showed decreased muscle mass when compared to all other groups. All injured animals showed signs of muscle fiber damage, although signs of early regenerated muscle fibers were more evident in injury + mobilization groups. Only the EM groups submitted to 45 minutes of exercise had increased muscle fiber and decreased non-muscle fiber area density values when compared to I group (p<0.05)., Conclusion: the regeneration process is related to the onset of exercise, since animals submitted to early mobilization showed improved regeneration when comparted to LM groups. Besides, the length of session is also important for accelerating the regeneration process, as it was observed that 45 minutes was better than 15 minutes duration.

This paper presents a technique for denoising digital radiographic images based upon the wavelet-domain Hidden Markov tree (HMT) model. The method uses the Anscombe's transformation to adjust the original image, corrupted by Poisson noise, to a Gaussian noise model. The image is then decomposed in different subbands of frequency and orientation responses using the dual-tree complex wavelet transform, and the HMT is used to model the marginal distribution of the wavelet coefficients. Two different correction functions were used to shrink the wavelet coefficients. Finally, the modified wavelet coefficients are transformed back into the original domain to get the denoised image. Fifteen radiographic images of extremities along with images of a hand, a line-pair, and contrast-detail phantoms were analyzed. Quantitative and qualitative assessment showed that the proposed algorithm outperforms the traditional Gaussian filter in terms of noise reduction, quality of details, and bone sharpness. In some images, the proposed algorithm introduced some undesirable artifacts near the edges.

The paper presents a technique for the segmentation of the fibro-glandular disc in mammograms based upon a statistical model of breast density. The density function of the model was represented by a mixture of up to four weighted Gaussians, each one corresponding to a specific density class in the breast. The parameters of the model and the number of tissue classes in the breast were determined using the expectation-maximisation algorithm and the minimum description length method. Grey-level statistics of the pectoral muscle were used to determine the tissue categories that are likely to represent the fibro-glandular disc. The method was applied to 84 medio-lateral oblique mammograms from the Mini-MIAS database. The results of the segmented fibro-glandular disc were assessed by a radiologist using the original and the segmented images, with reference to a ranking table categorising the results of segmentation as: 1: excellent; 2: good; 3: average; 4: poor; and 5: complete failure. Of the 84 cases analysed, 64.3% were rated as excellent, 16.7% were rated as good, 10.7% were rated as average, and 4.7% were rated as poor; only 3.6% of the cases were rated as a complete failure with regard to segmentation of the fibro-glandular disc.

A method for the identification of the breast boundary in mammograms is presented. The method can be used in the preprocessing stage of a system for computer-aided diagnosis (CAD) of breast cancer and also in the reduction of image file size in picture archiving and communication system applications. The method started with modification of the contrast of the original image. A binarisation procedure was then applied to the image, and the chain-code algorithm was used to find an approximate breast contour. Finally, the identification of the true breast boundary was performed by using the approximate contour as the input to an active contour model algorithm specially tailored for this purpose. After demarcation of the breast boundary, all artifacts outside the breast region were eliminated. The method was applied to 84 medio-lateral oblique mammograms from the Mini-MIAS database. Evaluation of the detected breast boundary was performed based upon the percentage of false-positive and false-negative pixels determined by a quantitative comparison between the contours identified by a radiologist and those identified by the proposed method. The average false positive and false negative rates were 0.41% and 0.58%, respectively. The two radiologists who evaluated the results considered the segmentation results to be acceptable for CAD purposes.

The pectoral muscle represents a predominant density region in most medio-lateral oblique (MLO) views of mammograms; its inclusion can affect the results of intensity-based image processing methods or bias procedures in the detection of breast cancer. Local analysis of the pectoral muscle may be used to identify the presence of abnormal axillary lymph nodes, which may be the only manifestation of occult breast carcinoma. We propose a new method for the identification of the pectoral muscle in MLO mammograms based upon a multiresolution technique using Gabor wavelets. This new method overcomes the limitation of the straight-line representation considered in our initial investigation using the Hough transform. The method starts by convolving a group of Gabor filters, specially designed for enhancing the pectoral muscle edge, with the region of interest containing the pectoral muscle. After computing the magnitude and phase images using a vector-summation procedure, the magnitude value of each pixel is propagated in the direction of the phase. The resulting image is then used to detect the relevant edges. Finally, a post-processing stage is used to find the true pectoral muscle edge. The method was applied to 84 MLO mammograms from the Mini-MIAS (Mammographic Image Analysis Society, London, U.K.) database. Evaluation of the pectoral muscle edge detected in the mammograms was performed based upon the percentage of false-positive (FP) and false-negative (FN) pixels determined by comparison between the numbers of pixels enclosed in the regions delimited by the edges identified by a radiologist and by the proposed method. The average FP and FN rates were, respectively, 0.58% and 5.77%. Furthermore, the results of the Gabor-filter-based method indicated low Hausdorff distances with respect to the hand-drawn pectoral muscle edges, with the mean and standard deviation being 3.84 +/- 1.73 mm over 84 images.

This paper presents a procedure for the analysis of left-right (bilateral) asymmetry in mammograms. The procedure is based upon the detection of linear directional components by using a multiresolution representation based upon Gabor wavelets. A particular wavelet scheme with two-dimensional Gabor filters as elementary functions with varying tuning frequency and orientation, specifically designed in order to reduce the redundancy in the wavelet-based representation, is applied to the given image. The filter responses for different scales and orientation are analyzed by using the Karhunen-Loève (KL) transform and Otsu's method of thresholding. The KL transform is applied to select the principal components of the filter responses, preserving only the most relevant directional elements appearing at all scales. The selected principal components, thresholded by using Otsu's method, are used to obtain the magnitude and phase of the directional components of the image. Rose diagrams computed from the phase images and statistical measures computed thereof are used for quantitative and qualitative analysis of the oriented patterns. A total of 80 images from 20 normal cases, 14 asymmetric cases, and six architectural distortion cases from the Mini-MIAS (Mammographic Image Analysis Society, London, U.K.) database were used to evaluate the scheme using the leave-one-out methodology. Average classification accuracy rates of up to 74.4% were achieved.