Authenticating medical images using watermarking techniques has become a very popular area of research, and some works in this area have been reported worldwide recently. Besides authentication, many data-hiding techniques have been proposed to conceal patient’s data into medical images aiming to reduce the cost needed to store data and the time needed to transmit data when required. In this paper, we present a new hybrid watermarking scheme for DICOM images. In our scheme, two well-known techniques are combined to gain the advantages of both and fulfill the requirements of authentication and data hiding. The scheme divides the images into two parts, the region of interest (ROI) and the region of non-interest (RONI). Patient’s data are embedded into ROI using a reversible technique based on difference expansion, while tamper detection and recovery data are embedded into RONI using a robust technique based on discrete wavelet transform. The experimental results show the ability of hiding patient’s data with a very good visual quality, while ROI, the most important area for diagnosis, is retrieved exactly at the receiver side. The scheme also shows some robustness against certain levels of salt and pepper and cropping noise.
Watermarking; Data hiding; Medical Image Authentication; Electronic patient record
In telemedicine while transferring medical images tampers may be introduced. Before making any diagnostic decisions, the integrity of region of interest (ROI) of the received medical image must be verified to avoid misdiagnosis. In this paper, we propose a novel fragile block based medical image watermarking technique to avoid embedding distortion inside ROI, verify integrity of ROI, detect accurately the tampered blocks inside ROI, and recover the original ROI with zero loss. In this proposed method, the medical image is segmented into three sets of pixels: ROI pixels, region of noninterest (RONI) pixels, and border pixels. Then, authentication data and information of ROI are embedded in border pixels. Recovery data of ROI is embedded into RONI. Results of experiments conducted on a number of medical images reveal that the proposed method produces high quality watermarked medical images, identifies the presence of tampers inside ROI with 100% accuracy, and recovers the original ROI without any loss.
Digital medical images are very easy to be modified for illegal purposes. For example, microcalcification in mammography is an important diagnostic clue, and it can be wiped off intentionally for insurance purposes or added intentionally into a normal mammography. In this paper, we proposed two methods to tamper detection and recovery for a medical image. A 1024 × 1024 x-ray mammogram was chosen to test the ability of tamper detection and recovery. At first, a medical image is divided into several blocks. For each block, an adaptive robust digital watermarking method combined with the modulo operation is used to hide both the authentication message and the recovery information. In the first method, each block is embedded with the authentication message and the recovery information of other blocks. Because the recovered block is too small and excessively compressed, the concept of region of interest (ROI) is introduced into the second method. If there are no tampered blocks, the original image can be obtained with only the stego image. When the ROI, such as microcalcification in mammography, is tampered with, an approximate image will be obtained from other blocks. From the experimental results, the proposed near-lossless method is proven to effectively detect a tampered medical image and recover the original ROI image. In this study, an adaptive robust digital watermarking method combined with the operation of modulo 256 was chosen to achieve information hiding and image authentication. With the proposal method, any random changes on the stego image will be detected in high probability.
Medical image; image processing; image authentication
Nowadays, medical imaging equipments produce digital form of medical images. In a modern health care environment, new systems such as PACS (picture archiving and communication systems), use the digital form of medical image too. The digital form of medical images has lots of advantages over its analog form such as ease in storage and transmission. Medical images in digital form must be stored in a secured environment to preserve patient privacy. It is also important to detect modifications on the image. These objectives are obtained by watermarking in medical image.
In this paper, we present a dual and oblivious (blind) watermarking scheme in the contourlet domain. Because of importance of ROI (region of interest) in interpretation by medical doctors rather than RONI (region of non-interest), we propose an adaptive dual watermarking scheme with different embedding strength in ROI and RONI. We embed watermark bits in singular value vectors of the embedded blocks within lowpass subband in contourlet domain.
The values of PSNR (peak signal-to-noise ratio) and SSIM (structural similarity measure) index of ROI for proposed DICOM (digital imaging and communications in medicine) images in this paper are respectively larger than 64 and 0.997. These values confirm that our algorithm has good transparency. Because of different embedding strength, BER (bit error rate) values of signature watermark are less than BER values of caption watermark. Our results show that watermarked images in contourlet domain have greater robustness against attacks than wavelet domain. In addition, the qualitative analysis of our method shows it has good invisibility.
The proposed contourlet-based watermarking algorithm in this paper uses an automatically selection for ROI and embeds the watermark in the singular values of contourlet subbands that makes the algorithm more efficient, and robust against noise attacks than other transform domains. The embedded watermark bits can be extracted without the original image, the proposed method has high PSNR and SSIM, and the watermarked image has high transparency and can still conform to the DICOM format.
This study was to investigate whether various region-of-interest (ROI) methods for measuring dopamine transporter (DAT) availabilities by single photon emission computed tomography (SPECT) are statistically different, whether results of medical research are thereby influenced, and causes of these differences. Eighty-four healthy adults with 99mTc-TRODAT-1 SPECT and magnetic resonance imaging (MRI) scans were included. Six major analysis approaches were compared: (1) ROI drawn on the coregistered MRI; (2) ROIs drawn on the SPECT images; (3) standard ROI templates; (4) threshold-ROIs; (5) atlas-based mappings with coregistered MRI; and (6) atlas-based mappings with SPECT images. Using the atlas-based approaches we assessed the influence of striatum ROIs by slice-wise and voxel-wise comparisons. In (5) and (6), three partial-volume correction (PVC) methods were also explored. The results showed that DAT availabilities obtained from different methods were closely related but quite different and leaded to significant differences in determining the declines of DAT availability per decade (range: 5.95–11.99%). Use of 3D whole-striatum or more transverse slices could avoid biases in measuring the striatal DAT declines per decade. Atlas-based methods with PVC may be the preferable methods for medical research.
With biliary duct ligation and CCl4 induced rat liver fibrosis models, recent studies showed that MR T1rho imaging is able to detect liver fibrosis, and the degree of fibrosis is correlated with the degree of elevation of the T1rho measurements, suggesting liver T1rho quantification may play an important role for liver fibrosis early detection and grading. It has also been reported it is feasible to obtain consistent liver T1rho measurement for human subjects at 3 Tesla (3 T), and preliminary clinical data suggest liver T1rho is increased in patients with cirrhosis. In these previous studies, T1rho imaging was used with the rotary-echo spin-lock pulse for T1rho preparation, and number of signal averaging (NSA) was 2. Due to the presence of inhomogeneous B0 field, artifacts may occur in the acquired T1rho-weighted images. The method described by Dixon et al. (Magn Reson Med 1996;36:90-4), which is a hard RF pulse with 135° flip angle and same RF phase as the spin-locking RF pulse is inserted right before and after the spin-locking RF pulse, has been proposed to reduce sensitivity to B0 field inhomogeneity in T1rho imaging. In this study, we compared the images scanned by rotary-echo spin-lock pulse method (sequence 1) and the pulse modified according to Dixon method (sequence 2). When the artifacts occurred in T1rho images, we repeated the same scan until satisfactory. We accepted images if artifact in liver was less than 10% of liver area by visual estimation. When NSA =2, the breath-holding duration for data acquisition of one slice scanning was 8 sec due to a delay time of 6,000 ms for magnetization restoration. If NSA =1, the duration was shortened to be 2 sec. In previous studies, manual region of interest (ROI) analysis of T1rho map was used. In this current study, histogram analysis was also applied to evaluate liver T1rho value on T1rho maps. MRI data acquisition was performed on a 3 T clinical scanner. There were 29 subjects with 61 examinations obtained. Liver T1rho values obtained by sequence 1 (NSA =2) and sequence 2 (NSA =2) showed similar values, i.e., 43.1±2.1 ms (range: 38.6-48.0 ms, n=40 scans) vs. 43.5±2.5 ms (range: 39.0-47.7 ms,
n=12 scans, P=0.74) respectively. For the six volunteers scanned with both sequences in one session, the intraclass correlation coefficient (ICC) was 0.939. Overall, the success rate of obtaining satisfactory images per acquisition was slightly over 50% for both sequence 1 and sequence 2. Satisfactory images can usually be obtained by asking the volunteer subjects to better hold their breath. However, sequence 2 did not increase the scan success rate. For the nine subjects scanned by sequence 2 with both NSA =2 and NSA =1 during one session, the ICC was 0.274, demonstrated poor agreement. T1rho measurement by ROI method and histogram had an ICC of 0.901 (P>0.05), demonstrated very good agreement. We conclude that by including 135° flip angle before and after the spin-locking RF pulse, the rate of artifacts occurring did not decrease. On the other hand, sequence 1 and sequence 2 measured similar T1rho value in healthy liver. While reducing the breath—holding duration significantly, NSA =1 did not offer satisfactory signal-to-noise ratio. Histogram measurement can be adopted for future studies.
Magnetic resonance imaging; liver; T1rho; quantification
This paper presents a lossless watermarking scheme in the sense that the original image can be exactly recovered from the watermarked one, with the purpose of verifying the integrity and authenticity of medical images. In addition, the scheme has the capability of not introducing any embedding-induced distortion in the region of interest (ROI) of a medical image. Difference expansion of adjacent pixel values is employed to embed several bits. A region of embedding, which is represented by a polygon, is chosen intentionally to prevent introducing embedding distortion in the ROI. Only the vertex information of a polygon is transmitted to the decoder for reconstructing the embedding region, which improves the embedding capacity considerably. The digital signature of the whole image is embedded for verifying the integrity of the image. An identifier presented in electronic patient record (EPR) is embedded for verifying the authenticity by simultaneously processing the watermarked image and the EPR. Combining with fingerprint system, patient’s fingerprint information is embedded into several image slices and then extracted for verifying the authenticity.
Watermarking; telemedicine; security; integrity; confidentiality; image authentication; PACS; ROI
Studying structural and functional connectivities of human cerebral cortex has drawn significant interest and effort recently. A fundamental and challenging problem arises when attempting to measure the structural and/or functional connectivities of specific cortical networks: how to identify and localize the best possible regions of interests (ROIs) on the cortex? In our view, the major challenges come from uncertainties in ROI boundary definition, the remarkable structural and functional variability across individuals and high nonlinearities within and around ROIs. In this paper, we present a novel ROI prediction framework that localizes ROIs in individual brains based on their learned fiber shape models from multimodal task-based functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI) data. In the training stage, shape models of white matter fibers are learnt from those emanating from the functional ROIs, which are activated brain regions detected from task-based fMRI data. In the prediction stage, functional ROIs are predicted in individual brains based only on DTI data. Our experiment results show that the average ROI prediction error is around 3.94 mm, in comparison with benchmark data provided by working memory and visual task-based fMRI. Our work demonstrated that fiber bundle shape models derived from DTI data are good predictors of functional cortical ROIs.
brain network; diffusion tensor imaging; fMRI; ROI prediction; shape analysis
Tamper localization and recovery watermarking scheme can be used to detect manipulation and recover tampered images. In this paper, a tamper localization and lossless recovery scheme that used region of interest (ROI) segmentation and multilevel authentication was proposed. The watermarked images had a high average peak signal-to-noise ratio of 48.7 dB and the results showed that tampering was successfully localized and tampered area was exactly recovered. The usage of ROI segmentation and multilevel authentication had significantly reduced the time taken by approximately 50 % for the tamper localization and recovery processing.
Lossless compression; Tamper localization; Recovery; Medical image; Watermarking
We compared results from various methods of analysis of diffusion tensor imaging (DTI) data from a single data set consisting of 10 healthy adolescents.
All subjects were imaged on a single 3T MRI system (single-shot echo-planar imaging (EPI) pulse sequence, b value 1000). We measured fractional anisotropy (FA), apparent diffusion coefficient (ADC), axial diffusivity and radial diffusivity values using 64 pixel rectangular regions of interest (ROIs) in the right-side, midline and left-side of the central portion of the splenium of the corpus callosum for fixed (i.e., at same sites in all subjects) and targeted (i.e., at sites of highest FA values) locations, We compared results with those obtained using 64 pixel oval ROIs and 100 pixel rectangular ROIs in same locations. Finally, we compared results from ROI-based methods and from tractography. All comparisons used the Wilcoxon signed rank test and the intraclass correlation of individual values.
Compared to tractography, the average of mean ROI-based values was significantly higher for fixed FA (14%) and targeted FA (39%) values and significantly lower for ADC (16%) and radial diffusivity (38%) values. For solely ROI-based comparisons, significant differences were found in the following comparisons: 64 pixel ROI vs. 100 pixel ROI, oval ROI vs. rectangular ROI, targeted FA left of midline vs. mean targeted FA value, and targeted ROI right of midline vs. mean targeted FA value.
Markedly different values were obtained when using either ROI-based or tractography-based techniques, or ROI analysis techniques that differ only relatively slightly.
Over the past few years, the billows of the digital trends and the exploding growth of electronic networks, such as worldwide web, global mobility networks, etc., have drastically changed our daily lifestyle. In view of the widespread applications of digital images, medical images, which are produced by a wide variety of medical appliances, are stored in digital form gradually. These digital images are very easy to be modified imperceptively by malicious intruders for illegal purposes. The well-known adage that “seeing is believing” seems not always a changeless truth. Therefore, protecting images from being altered becomes an important issue. Based on the lossless data-embedding techniques, two detection and restoration systems are proposed to cope with forgery of medical images in this paper. One of them has the ability to recover the whole blocks of the image and the other enables to recover only a particular region where a physician will be interested in, with a better visual quality. Without the need of comparing with the original image, these systems have a great advantage of detecting and locating forged parts of the image with high possibility. And then it can also restore the counterfeited parts. Furthermore, once an image is announced authentic, the original image can be derived from the stego-image losslessly. The experimental results show that the restored version of a tampered image in the first method is extremely close to the original one. As to the second method, the region of interest selected by a physician can be recovered without any loss, when it is tampered.
Tamper detection; restoring; wavelet; reversible data embedding
Localization of cortical regions of interests (ROIs) in structural neuroimaging data such as diffusion tensor imaging (DTI) and T1-weighted MRI images has significant importance in basic and clinical neurosciences. However, this problem is considerably challenging due to the lack of quantitative mapping between brain structure and function, which relies on the availability of multimodal training data including benchmark task-based functional MRI (fMRI) images and effective machine learning algorithms. This paper presents a novel joint modeling approach that learns predictive models of ROIs from concurrent task-based fMRI, DTI, and T1-weighted MRI datasets. In particular, the effective generalized multiple kernel learning (GMKL) algorithm and ROI coordinate principal component analysis (PCA) model are employed to infer the intrinsic relationships between anatomical T1-weighted MRI /connectional DTI features and task-based fMRI-derived functional ROIs. Then, these predictive models of cortical ROIs are evaluated by cross-validation studies, independent datasets, and reproducibility studies. Experimental results are promising. We envision that these predictive models can be potentially applied in many scenarios that have only DTI and/or T1-weighted MRI data, but without task-based fMRI data.
DTI; T1-weighted MRI; fMRI; connectivity; functional cortical ROIs
For the diagnosis of breast cancer using magnetic resonance imaging (MRI), one of the most important parameters is the analysis of contrast enhancement. A threedimensional MR sequence is applied before and five times after bolus injection of paramagnetic contrast medium (Gd-DTPA). The dynamics of absorption are described by a time/intensity enhancement curve, which reports the mean intensity of the MR signal in a small region of interest (ROI) for about 8 minutes after contrast injection. The aim of our study was to use an artificial neural network to automatically classify the enhancement curves as “benign” or “malignant.” We used a classic feed-forward back-propagation neural network, with three layers: five input nodes, two hidden nodes, and one output node. The network has been trained with 26 pathologic curves (10 invasive carcinoma [K], two carcinoma-in-situ [DCIS], and 14 benign lesion [B]). The trained network has been tested with 58 curves (36 K, one DCIS, 21 B). The network was able to correctly identify the test curves with a sensitivity of 76% and a specificity of 90%. For comparison, the same set of curves was analyzed separately by two radiologists (a breast MR expert and a resident radiologist). The first correctly interpreted the curves with a sensitivity of 76% and a specificity of 90%, while the second scored 59% for sensitivity and 90% for specificity. These results demonstrate that a trained neural network recognizes the pathologic curves at least as well as an expert radiologist. This algorithm can help the radiologist attain rapid and affordable screening of a large number of ROIs. A complete automatic computer-aided diagnosis support system should find a number of potentially interesting ROIs and automatically analyze the enhancement curves for each ROI by neural networks, reporting to the radiologist only the potentially pathologic ROIs for a more accurate, manual, repeated evaluation.
Activity of disease in patients with multiple sclerosis (MS) is monitored by detecting and delineating hyper-intense lesions on MRI scans. The Minimum Area Contour Change (MACC) algorithm has been created with two main goals: a) to improve inter-operator agreement on outlining regions of interest (ROIs) and b) to automatically propagate longitudinal ROIs from the baseline scan to a follow-up scan.
The MACC algorithm first identifies an outer bound for the solution path, forms a high number of iso-contour curves based on equally spaced contour values, and then selects the best contour value to outline the lesion. The MACC software was tested on a set of 17 FLAIR MRI images evaluated by a pair of human experts and a longitudinal dataset of 12 pairs of T2-weighted Fluid Attenuated Inversion Recovery (FLAIR) images that had lesion analysis ROIs drawn by a single expert operator.
In the tests where two human experts evaluated the same MRI images, the MACC program demonstrated that it could markedly reduce inter-operator outline error. In the longitudinal part of the study, the MACC program created ROIs on follow-up scans that were in close agreement to the original expert’s ROIs. Finally, in a post-hoc analysis of 424 follow-up scans 91% of propagated MACC were accepted by an expert and only 9% of the final accepted ROIS had to be created or edited by the expert.
When used with an expert operator's verification of automatically created ROIs, MACC can be used to improve inter- operator agreement and decrease analysis time, which should improve data collected and analyzed in multicenter clinical trials.
Multiple sclerosis; Detection error; Outline error; Rater agreement; Operator agreement; Metric; Jaccard index; Similarity index; Kappa; Lesion; Assessment; Minimum area contour change
To assess the influence of region of interest (ROI) size and positioning on tumour ADC measurements and interobserver variability in patients with locally advanced rectal cancer (LARC).
Forty-six LARC patients were retrospectively included. Patients underwent MRI including DWI (b0,500,1000) before and 6–8 weeks after chemoradiation (CRT). Two readers measured mean tumour ADCs (pre- and post-CRT) according to three ROI protocols: whole-volume, single-slice or small solid samples. The three protocols were compared for differences in ADC, SD and interobserver variability (measured as the intraclass correlation coefficient; ICC).
ICC for the whole-volume ROIs was excellent (0.91) pre-CRT versus good (0.66) post-CRT. ICCs were 0.53 and 0.42 for the single-slice ROIs versus 0.60 and 0.65 for the sample ROIs. Pre-CRT ADCs for the sample ROIs were significantly lower than for the whole-volume or single-slice ROIs. Post-CRT there were no significant differences between the whole-volume ROIs and the single-slice or sample ROIs, respectively. The SDs for the whole-volume and single-slice ROIs were significantly larger than for the sample ROIs.
ROI size and positioning have a considerable influence on tumour ADC values and interobserver variability. Interobserver variability is worse after CRT. ADCs obtained from the whole tumour volume provide the most reproducible results.
• ROI size and positioning influence tumour ADC measurements in rectal cancer
• ROI size and positioning influence interobserver variability of tumour ADC measurements
• ADC measurements of the whole tumour volume provide the most reproducible results
• Tumour ADC measurements are more reproducible before, rather than after, chemoradiation treatment
• Variations caused by ROI size and positioning should be taken into account when using ADC as a biomarker for tumour response
Diffusion magnetic resonance imaging; Rectal neoplasms; Observer variation; Methodology; Apparent diffusion coefficient
Owning to its clinical accessibility, T1-weighted MRI (Magnetic Resonance Imaging) has been extensively studied in the past decades for prediction of Alzheimer's disease (AD) and mild cognitive impairment (MCI). The volumes of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) are the most commonly used measurements, resulting in many successful applications. It has been widely observed that disease-induced structural changes may not occur at isolated spots, but in several inter-related regions. Therefore, for better characterization of brain pathology, we propose in this paper a means to extract inter-regional correlation based features from local volumetric measurements. Specifically, our approach involves constructing an anatomical brain network for each subject, with each node representing a Region of Interest (ROI) and each edge representing Pearson correlation of tissue volumetric measurements between ROI pairs. As second order volumetric measurements, network features are more descriptive but also more sensitive to noise. To overcome this limitation, a hierarchy of ROIs is used to suppress noise at different scales. Pairwise interactions are considered not only for ROIs with the same scale in the same layer of the hierarchy, but also for ROIs across different scales in different layers. To address the high dimensionality problem resulting from the large number of network features, a supervised dimensionality reduction method is further employed to embed a selected subset of features into a low dimensional feature space, while at the same time preserving discriminative information. We demonstrate with experimental results the efficacy of this embedding strategy in comparison with some other commonly used approaches. In addition, although the proposed method can be easily generalized to incorporate other metrics of regional similarities, the benefits of using Pearson correlation in our application are reinforced by the experimental results. Without requiring new sources of information, our proposed approach improves the accuracy of MCI prediction from (of conventional volumetric features) to (of hierarchical network features), evaluated using data sets randomly drawn from the ADNI (Alzheimer's Disease Neuroimaging Initiative) dataset.
Neurofeedback delivered via real-time functional magnetic resonance imaging (rtfMRI) is a promising therapeutic technique being explored to facilitate self-regulation of craving in nicotine-dependent cigarette smokers. The current study examined the role of nicotine-dependence severity and the efficacy of multiple visits of neurofeedback from a single region of interest (ROI) in the anterior cingulate cortex (ACC) on craving reduction.
Nine nicotine-dependent cigarette smokers participated in three rtfMRI visits that examined cue-induced craving and brain activation. Severity of nicotine dependence was assessed with the Fagerström Test for Nicotine Dependence. When viewing smoking-related images with instructions to “crave,” patient-tailored ROIs were generated in the vicinity of the ACC. Activity levels from the ROI were fed back while participants viewed smoking cues with the instruction to reduce craving.
Neurofeedback from a single ROI in the ACC led to consistent decreases in self-reported craving and activation in the ACC across the three visits. Dependence severity predicted response to neurofeedback at Visit 3.
This study builds upon previous rtfMRI studies on the regulation of nicotine craving in demonstrating that feedback from the ACC can reduce activation to smoking cues across three separate visits. Individuals with lower nicotine-dependence severity were more successful in reducing ACC activation over time. These data highlight the need to consider dependence severity in developing more individualized neurofeedback methods.
Hemodynamic impairment in one hemisphere has been shown to trigger atypical ipsilateral motor activation in the opposite hemisphere on functional magnetic resonance imaging (fMRI). We hypothesized that reversing the hypoperfusion would normalize the motor activation pattern.
We studied 4 patients with high-grade stenosis and impaired VMR but no stroke. Change in fMRI motor activation pattern pre- and post-VMR normalization was compared with 7 healthy controls scanned at an interval of three months using voxel-wise statistical parametric maps and Region of Interest (ROI) analysis. fMRI was performed at 1.5T, 128×128 matrix, 19cm2FOV, slice-thickness= 4.5mm/0skip, TR=4000, slices=25, voxel dimensions 1.5×1.5×4.5mm.Subjects performed a repetitive hand closure task in synchrony with 1Hz metronome tone. We used repeated-measures ANOVA to compute the interaction between group (patients/controls) and time by obtaining the average BOLD-signal of 3 motor ROIs in each hemisphere.
Two patients normalized their VMR after spontaneous resolution of dissection, and 2 following revascularization procedures. Both voxel-wise statistical maps and ROI analysis showed that VMR normalization was associated in each case with a reduction in the atypical activation in the hemisphere opposite to the previously hypoperfused hemisphere (p<.0001).
In the presence of a physiologic stressor such as hypoperfusion, the brain is capable of dynamic functional reorganization to the opposite hemisphere that is reversible when normal blood flow is restored. These findings are important to our understanding of the clinical consequences of hemodynamic failure and the role of the ipsilateral hemisphere in maintaining normal neurological function.
Breast cancer continues to be a significant public health problem in the world. Early detection is the key for improving breast cancer prognosis. In this way, magnetic resonance imaging (MRI) is emerging as a powerful tool for the detection of breast cancer. Breast MRI presently has two major challenges. First, its specificity is relatively poor, and it detects many false positives (FPs). Second, the method involves acquiring several high-resolution image volumes before, during, and after the injection of a contrast agent. The large volume of data makes the task of interpretation by the radiologist both complex and time-consuming. These challenges have led to the development of the computer-aided detection systems to improve the efficiency and accuracy of the interpretation process. Detection of suspicious regions of interests (ROIs) is a critical preprocessing step in dynamic contrast-enhanced (DCE)-MRI data evaluation. In this regard, this paper introduces a new automatic method to detect the suspicious ROIs for breast DCE-MRI based on region growing. The results indicate that the proposed method is thoroughly able to identify suspicious regions (accuracy of 75.39 ± 3.37 on PIDER breast MRI dataset). Furthermore, the FP per image in this method is averagely 7.92, which shows considerable improvement comparing to other methods like ROI hunter.
Breast cancer; learning automata; local binary pattern; magnetic resonance imaging; region of interest detection
Voxel-based morphometry (VBM) and automated lobar region of interest (ROI) volumetry are comprehensive and fast methods to detect differences in overall brain anatomy on magnetic resonance images. However, VBM and automated lobar ROI volumetry have detected dissimilar gray matter differences within identical image sets in our own experience and in previous reports. To gain more insight into how diverging results arise and to attempt to establish whether one method is superior to the other, we investigated how differences in spatial scale and in the need to statistically correct for multiple spatial comparisons influence the relative sensitivity of either technique to group differences in gray matter volumes. We assessed the performance of both techniques on a small dataset containing simulated gray matter deficits and additionally on a dataset of 22q11-deletion syndrome patients with schizophrenia (22q11DS-SZ) vs. matched controls. VBM was more sensitive to simulated focal deficits compared to automated ROI volumetry, and could detect global cortical deficits equally well. Moreover, theoretical calculations of VBM and ROI detection sensitivities to focal deficits showed that at increasing ROI size, ROI volumetry suffers more from loss in sensitivity than VBM. Furthermore, VBM and automated ROI found corresponding GM deficits in 22q11DS-SZ patients, except in the parietal lobe. Here, automated lobar ROI volumetry found a significant deficit only after a smaller subregion of interest was employed. Thus, sensitivity to focal differences is impaired relatively more by averaging over larger volumes in automated ROI methods than by the correction for multiple comparisons in VBM. These findings indicate that VBM is to be preferred over automated lobar-scale ROI volumetry for assessing gray matter volume differences between groups.
PMID: 19619660 CAMSID: cams1805
A hybrid SPECT/CT system provides accurate coregistration of functional and morphological images. CT-guided region of interest (ROI) for semiquantifying striatal dopamine transporter (DAT) availability may be a feasible method. We therefore assessed the intra- and interobserver reproducibility of manual SPECT and CT-guided ROI methods and compared their semiquantitative data with data from MRI-guided ROIs. We enrolled twenty-eight patients who underwent Tc-99m TRODAT-1 brain SPECT/CT and brain MRI. ROIs of the striatal, caudate, putamen, and occipital cortex were manually delineated on the SPECT, CT, and MRI. ROIs from CT and MRI were transferred to the coregistered SPECT for semiquantification. The striatal, caudate, and putamen nondisplaceable binding potential (BPND) were calculated. Using CT-guided ROIs had higher intra- and interobserver concordance correlation coefficients, closer Bland-Altman biases to zero, and narrower limits of agreement than using manual SPECT ROIs. The correlation coefficients of striatal, caudate, and putamen BPND were good between manual SPECT and MRI-guided ROI methods and even better between CT-guided and MRI-guided ROI methods. Conclusively, CT-guided ROI delineation for semiquantifying striatal DAT availability in a hybrid SPECT/CT system is highly reproducible, and the semiquantitative data correlate well with data from MRI-guided ROIs.
This paper presents a method for selecting Regions of Interest (ROI) in brain Magnetic Resonance Imaging (MRI) for diagnostic purposes, using statistical learning and vector quantization techniques. The proposed method models the distribution of GM and WM tissues grouping the voxels belonging to each tissue in ROIs associated to a specific neurological disorder. Tissue distribution of normal and abnormal images is modelled by a Self-Organizing map (SOM), generating a set of representative prototypes, and the receptive field (RF) of each SOM prototype defines a ROI. Moreover, the proposed method computes the relative importance of each ROI by means of its discriminative power. The devised method has been assessed using 818 images from the Alzheimer's disease Neuroimaging Initiative (ADNI) which were previously segmented through Statistical Parametric Mapping (SPM). The proposed algorithm was used over these images to parcel ROIs associated to the Alzheimer's Disease (AD). Additionally, this method can be used to extract a reduced set of discriminative features for classification, since it compresses discriminative information contained in the brain. Voxels marked by ROIs which were computed using the proposed method, yield classification results up to 90% of accuracy for controls (CN) and Alzheimer's disease (AD) patients, and 84% of accuracy for Mild Cognitive Impairment (MCI) and AD patients.
We created a spatial probability atlas of schizophrenia to provide information about the neuroanatomic variability of brain regions of patients with the disorder. Probability maps of 16 regions of interest (ROIs) were constructed by taking manually parcellated ROIs from subjects’ magnetic resonance images (MRIs) and linearly transforming them into Talairach space using the Montreal Neurological Institute (MNI) template. ROIs included temporal, parietal, and prefrontal cortex subregions, with a principal focus on temporal lobe structures. Subject Ns ranged from 11 to 28 for the different ROIs. Our global measure of the spatial distribution of the transformed ROI was the sum of voxels with 50% overlap among subjects. The superior temporal gyrus (STG) and fusiform gyrus (FG) had lower values for schizophrenic subjects than for normal controls, suggestive of greater spatial variability for these ROIs in schizophrenic subjects. For the computation of statistical significance of group differences in portions of the ROI, we used voxel-wise comparisons and Fisher's exact test. First-episode schizophrenic patients compared with controls showed lower probability (P < 0.05) at dorso-posterior areas of planum temporale and Heschl's gyrus, lateral and anterior regions in the left hippocampus (HIPP), and dorsolateral regions of fusiform gyrus. Importantly, most ROIs of schizophrenic subjects showed a significantly lower spatial overlap than controls, even after nonlinear spatial normalization, suggesting a greater heterogeneity in the spatial distribution of ROIs. There is consequently a need for caution in neuroimaging studies where data from schizophrenic subjects are normalized to a particular stereotaxic coordinate system based on healthy controls. Apparent group differences in activation may simply reflect a greater heterogeneity of spatial distribution in schizophrenia.
MRI; Schizophrenia; Brain
The rationale for multi-modality imaging is to integrate the strengths of different imaging technologies while reducing the shortcomings of an individual modality. The work presented here proposes a limited-field-of-view (LFOV) SPECT reconstruction technique that can be implemented on a multi-modality MR/SPECT system that can be used to obtain simultaneous MRI and SPECT images for small animal imaging. The reason for using a combined MR/SPECT system in this work is to eliminate any possible misregistration between the two sets of images when MR images are used as a priori information for SPECT. In nuclear imaging the target area is usually smaller than the entire object; thus, focusing the detector on the LFOV results in various advantages including the use of a smaller nuclear detector (less cost), smaller reconstruction region (faster reconstruction) and higher spatial resolution when used in conjunction with pinhole collimators with magnification. The MR/SPECT system can be used to choose a region of interest (ROI) for SPECT. A priori information obtained by the full field-of-view (FOV) MRI combined with the preliminary SPECT image can be used to reduce the dimensions of the SPECT reconstruction by limiting the computation to the smaller FOV while reducing artifacts resulting from the truncated data. Since the technique is based on SPECT imaging within the LFOV it will be called the keyhole SPECT (K-SPECT) method. At first MRI images of the entire object using a larger FOV are obtained to determine the location of the ROI covering the target organ. Once the ROI is determined, the animal is moved inside the radiofrequency (rf) coil to bring the target area inside the LFOV and then simultaneous MRI and SPECT are performed. The spatial resolution of the SPECT image is improved by employing a pinhole collimator with magnification >1 by having carefully calculated acceptance angles for each pinhole to avoid multiplexing. In our design all the pinholes are focused to the center of the LFOV. K-SPECT reconstruction is accomplished by generating an adaptive weighting matrix using a priori information obtained by simultaneously acquired MR images and the radioactivity distribution obtained from the ROI region of the SPECT image that is reconstructed without any a priori input. Preliminary results using simulations with numerical phantoms show that the image resolution of the SPECT image within the LFOV is improved while minimizing artifacts arising from parts of the object outside the LFOV due to the chosen magnification and the new reconstruction technique. The root-mean-square-error (RMSE) in the out-of-field artifacts was reduced by 60% for spherical phantoms using the K-SPECT reconstruction technique and by 48.5–52.6% for the heart in the case with the MOBY phantom. The KSPECT reconstruction technique significantly improved the spatial resolution and quantification while reducing artifacts from the contributions outside the LFOV as well as reducing the dimension of the reconstruction matrix.
Diffusion-weighted magnetic resonance imaging (DW-MRI) is different from conventional diagnostic methods and has the potential to delineate the microscopic anatomy of a target tissue or organ. The purpose of our study was to evaluate the value of DW-MRI in the diagnosis of benign and malignant breast masses, which would help the clinical surgeon to decide the scope and pattern of operation.
A total of 52 female patients with palpable solid breast masses received breast MRI scans using routine sequences, dynamic contrast-enhanced imaging, and diffusion-weighted echo-planar imaging at b values of 400, 600, and 800 s/mm2, respectively. Two regions of interest (ROIs) were plotted, with a smaller ROI for the highest signal and a larger ROI for the overall lesion. Apparent diffusion coefficient (ADC) values were calculated at three different b values for all detectable lesions and from two different ROIs. The sensitivity, specificity, positive predictive value, and positive likelihood ratio of DW-MRI were determined for comparison with histological results.
A total of 49 (49/52, 94.2%) lesions were detected using DW-MRI, including 20 benign lesions (two lesions detected in the same patient) and 29 malignant lesions. Benign lesion had a higher mean ADC value than their malignant counterparts, regardless of b value. According to the receiver operating characteristic (ROC) curve, the smaller-range ROI was more effective in differentiation between benign and malignant lesions. The area under the ROC curve was the largest at a b value of 800 s/mm2. With a threshold ADC value at 1.23 × 10−3 mm2/s, DW-MRI achieved a sensitivity of 82.8%, specificity of 90.0%, positive predictive value of 92.3%, and positive likelihood ratio of 8.3 for differentiating benign and malignant lesions.
DW-MRI is an accurate diagnostic tool for differentiation between benign and malignant breast lesions, with an optimal b value of 800 s/mm2. A smaller-range ROI focusing on the highest signal has a better differential value.
breast lesions; b value; differential diagnosis; diffusion-weighted imaging; magnetic resonance imaging