Automatic tumor segmentation using knowledge-based techniques.

A system that automatically segments and labels glioblastoma-multiforme tumors in magnetic resonance images (MRI's) of the human brain is presented. The MRI's consist of T1-weighted, proton density, and T2-weighted feature images and are processed by a system which integrates knowledge-based (KB) techniques with multispectral analysis. Initial segmentation is performed by an unsupervised clustering algorithm. The segmented image, along with cluster centers for each class are provided to a rule-based expert system which extracts the intracranial region. Multispectral histogram analysis separates suspected tumor from the rest of the intracranial region, with region analysis used in performing the final tumor labeling. This system has been trained on three volume data sets and tested on thirteen unseen volume data sets acquired from a single MRI system. The KB tumor segmentation was compared with supervised, radiologist-labeled "ground truth" tumor volumes and supervised k-nearest neighbors tumor segmentations. The results of this system generally correspond well to ground truth, both on a per slice basis and more importantly in tracking total tumor volume during treatment over time.

Thoracic outlet syndrome in a throwing athlete diagnosed with MRI and MRA.

Thoracic outlet syndrome comprises the clinical manifestations in the arm caused by compression of the neurovascular bundle as it leaves the thoracic inlet. The neurovascular bundle is composed of the subclavian artery, the subclavian vein, and the brachial plexus. The symptoms of thoracic outlet or inlet syndrome are most often caused by compression of the nerves of the brachial plexus, which is involved in up to 98% of cases; the remainder are due to vascular compression. MRI with MRA demonstrates well the anatomy of the brachial plexus as well as any vascular compression or occlusion. The relationship of the axillary and subclavian vein to the first rib and subclavius muscle also can be demonstrated. We present a college baseball player who presented with numbness in the fingers of his throwing hand when throwing a baseball. Evaluation with spin-echo and two-dimensional time-of-flight MR angiographic (MRA) imaging of the thoracic outlet region revealed obstruction of the subclavian vein with the arm abducted. To our knowledge, no such cases have been diagnosed previously with MRI.

Monitoring brain tumor response to therapy using MRI segmentation.

The performance evaluation of a semi-supervised fuzzy c-means (SFCM) clustering method for monitoring brain tumor volume changes during the course of routine clinical radiation-therapeutic and chemo-therapeutic regimens is presented. The tumor volume determined using the SFCM method was compared with the volume estimates obtained using three other methods: (a) a k nearest neighbor (kNN) classifier, b) a grey level thresholding and seed growing (ISG-SG) method and c) a manual pixel labeling (GT) method for ground truth estimation. The SFCM and kNN methods are applied to the multispectral, contrast enhanced T1, proton density, and T2 weighted, magnetic resonance images (MRI) whereas the ISG-SG and GT methods are applied only to the contrast enhanced T1 weighted image. Estimations of tumor volume were made on eight patient cases with follow-up MRI scans performed over a 32 week interval during treatment. The tumor cases studied include one meningioma, two brain metastases and five gliomas. Comparisons with manually labeled ground truth estimations showed that there is a limited agreement between the segmentation methods for absolute tumor volume measurements when using images of patients after treatment. The average intraobserver reproducibility for the SFCM, kNN and ISG-SG methods was found to be 5.8%, 6.6% and 8.9%, respectively. The average of the interobserver reproducibility of these methods was found to be 5.5%, 6.5% and 11.4%, respectively. For the measurement of relative change of tumor volume as required for the response assessment, the multi-spectral methods kNN and SFCM are therefore preferred over the seedgrowing method.

Anterior approach for CT-guided biopsy of skull base and parapharyngeal space lesions.

At our institution we use an anterior approach to biopsy of the parapharyngeal space or skull base lesions because it provides more direct access than the traditional lateral approach through the mandibular notch. The anterior approach follows a course lateral to the alveolar ridge of the maxilla and lateral pterygoid plate, and inferior to the zygomatic process of the maxilla. Biopsy was performed on 15 patients with either a skull base or a parapharyngeal space mass, none of which could be palpated externally or through the oral cavity by the ear, nose, and throat surgeon. In 12 patients the needle biopsy correlated with the surgical pathology. Three needle biopsies were nondiagnostic.

Unsupervised measurement of brain tumor volume on MR images.

We examined unsupervised methods of segmentation of MR images of the brain for measuring tumor volume in response to treatment. Two clustering methods were used: fuzzy c-means and a nonfuzzy clustering algorithm. Results were compared with volume segmentations by two supervised methods, k-nearest neighbors and region growing, and all results were compared with manual labelings. Results of individual segmentations are presented as well as comparisons on the application of the different methods with 10 data sets of patients with brain tumors. Unsupervised segmentation is preferred for measuring tumor volumes in response to treatment, as it eliminates operator dependency and may be adequate for delineation of the target volume in radiation therapy. Some obstacles need to be overcome, in particular regarding the detection of anatomically relevant tissue classes. This study shows that these improvements are possible.

Automatic magnetic resonance tissue characterization for three-dimensional magnetic resonance imaging of the brain.

Computer-assisted diagnostic systems enhance the information available from magnetic resonance imaging. Segmentations are the basis on which three-dimensional volume renderings are made. The application of a raw data-based, operator-independent (automatic), magnetic resonance segmentation technique for tissue differentiation is demonstrated. Segmentation images of vasogenic edema with gross and histopathological correlation are presented for demonstration of the technique. A pixel was classified into a tissue class based on a feature vector using unsupervised fuzzy clustering techniques as the pattern recognition method. Correlation of fuzzy segmentations and gross and histopathology were successfully performed. Based on the results of neuropathological correlation, the application of fuzzy magnetic resonance image segmentation to a patient with a brain tumor and extensive edema represents a viable technique for automatically displaying clinically important tissue differentiation. With this pattern recognition technique, it is possible to generate automatic segmentation images that display diagnostically relevant neuroanatomical and neuropathological tissue contrast information from raw magnetic resonance data for use in three-dimensional volume reconstructions.

MRI segmentation: methods and applications.

The current literature on MRI segmentation methods is reviewed. Particular emphasis is placed on the relative merits of single image versus multispectral segmentation, and supervised versus unsupervised segmentation methods. Image pre-processing and registration are discussed, as well as methods of validation. The application of MRI segmentation for tumor volume measurements during the course of therapy is presented here as an example, illustrating problems associated with inter- and intra-observer variations inherent to supervised methods.

Application of fuzzy c-means segmentation technique for tissue differentiation in MR images of a hemorrhagic glioblastoma multiforme.

The application of a raw data-based, operator-independent MR segmentation technique to differentiate boundaries of tumor from edema or hemorrhage is demonstrated. A case of a glioblastoma multiforme with gross and histopathologic correlation is presented. The MR image data set was segmented into tissue classes based on three different MR weighted image parameters (T1-, proton density-, and T2-weighted) using unsupervised fuzzy c-means (FCM) clustering algorithm technique for pattern recognition. A radiological examination of the MR images and correlation with fuzzy clustering segmentations was performed. Results were confirmed by gross and histopathology which, to the best of our knowledge, reports the first application of this demanding approach. Based on the results of neuropathologic correlation, the application of FCM MR image segmentation to several MR images of a glioblastoma multiforme represents a viable technique for displaying diagnostically relevant tissue contrast information used in 3D volume reconstruction. With this technique, it is possible to generate segmentation images that display clinically important neuroanatomic and neuropathologic tissue contrast information from raw MR image data.

Comparison of supervised MRI segmentation methods for tumor volume determination during therapy.

Two different multispectral pattern recognition methods are used to segment magnetic resonance images (MRI) of the brain for quantitative estimation of tumor volume and volume changes with therapy. A supervised k-nearest neighbor (kNN) rule and a semi-supervised fuzzy c-means (SFCM) method are used to segment MRI slice data. Tumor volumes as determined by the kNN and SFCM segmentation methods are compared with two reference methods, based on image grey scale, as a basis for an estimation of ground truth, namely: (a) a commonly used seed growing method that is applied to the contrast enhanced T1-weighted image, and (b) a manual segmentation method using a custom-designed graphical user interface applied to the same raw image (T1-weighted) dataset. Emphasis is placed on measurement of intra and inter observer reproducibility using the proposed methods. Intra- and interobserver variation for the kNN method was 9% and 5%, respectively. The results for the SFCM method was a little better at 6% and 4%, respectively. For the seed growing method, the intra-observer variation was 6% and the interobserver variation was 17%, significantly larger when compared with the multispectral methods. The absolute tumor volume determined by the multispectral segmentation methods was consistently smaller than that observed for the reference methods. The results of this study are found to be very patient case-dependent. The results for SFCM suggest that it should be useful for relative measurements of tumor volume during therapy, but further studies are required. This work demonstrates the need for minimally supervised or unsupervised methods for tumor volume measurements.

Digital mammography: M-channel quadrature mirror filters (QMFs) for microcalcification extraction.

Multiresolution methods are reported for feature extraction in breast cancer screening using digital mammography. The initial application is directed at the detection of microcalcification clusters (MCCs). Quadrature mirror filter (QMF) banks, using both two and three channel are proposed for the first time for both multiresolution decomposition and reconstruction. These filters are specifically tailored for automatic extraction of MCCs. The QMF multiresolution methods are compared to two channel tree structured wavelet transforms (TSWTs) methods previously reported. The QMF filters are preceded by an advanced tree structured nonlinear filter for noise suppression, prior to feature extraction, in order to minimize the false positive (FP) detection rate in digital mammography. The relative performance of these methods were evaluated using both simulated images and fifteen representative digitized mammograms containing biopsy proven microcalcification clusters. Similar high sensitivity (true positive (TP) detection rate (100%) and high specificity (0.6 average false positive (FP) MCC's/image) were observed, substantially better than more traditional approaches using single scale filters. The three channel QMF method, however, demonstrated better detail preservation of MCC's extracted compared to the two channel method. Detail preservation is important for the characterization of MCC's or individual microcalcifications in cancer screening.

Technology transfer in digital mammography. Report of the Joint National Cancer Institute-National Aeronautics and Space Administration workshop of May 19-20, 1993.

Digital mammography is one of the most promising novel technologies for further improvement of early detection of breast cancer, offering important potential advantages: 1) improved image quality; 2) digital image processing for improved lesion contrast; 3) computer-aided diagnosis for enhanced radiologic interpretation; and 4) teleradiology for facilitated radiologic consultation. The Diagnostic Imaging Research Branch of the National Cancer Institute (NCI) recently funded an international, multidisciplinary, multi-institutional Digital Mammography Development Group for collaborations between NCI, the academic community, and industry to facilitate the integrated development and implementation of digital mammographic systems. Currently, however, digital mammography faces a number of fundamental technological roadblocks: 1) cost-effective digital detectors and displays for imaging systems; 2) the need for novel algorithms for image processing and computer-aided diagnosis; and 3) high performance, low cost digital networks to provide an "information superhighway" for teleradiology. To solve some of these technological problems, the Diagnostic Imaging Research Branch of NCI joined efforts with the Technology Transfer Division of the National Aeronautics and Space Administration to pursue a federal technology transfer program in digital mammography. The authors discuss the findings and recommendations of the workshop entitled "Technology Transfer in Digital Mammography," which was organized and held jointly by the NCI and the National Aeronautics and Space Administration in May, 1993. Numerous innovative technologies of varying degree of promise for digital mammography were presented at the conference. In this article, specific technologies presented at the workshop by the federal and federally-supported laboratories are described, and critiques of these technologies by the leaders of the medical imaging community are presented.

Tree-structured non-linear filter and wavelet transform for microcalcification segmentation in digital mammography.

A novel algorithm was developed for computer aided diagnosis of microcalcification clusters in digital mammography. The method includes: (a) tree-structured central weighted median filters with variable shape windowing to suppress image noise but preserve image details; (b) a quasi range dispersion edge detector to increase edge contrast and definition; and (c) tree-structured wavelets for calcification segmentation. The preliminary evaluation of the method on nine mammograms showed that 100% sensitivity can be achieved at the expense of four false positive clusters per image. Research is ongoing for further optimization of the algorithm to reduce the number of false alarms and establish its clinical value.

PC-based multiparameter full-color display for tissue segmentation in MRI of adnexal masses.

OBJECTIVE: Our purpose was to apply full-color composite generation methods to multiparameter MRI to assess the ability of the technique to quantitatively segment clinically important anatomic and pathologic tissues. MATERIALS AND METHODS: With use of a personal computer with a 386 microprocessor and full-color (24 bit) graphics display capabilities, custom and commercially available image-processing softwares were applied to spatially aligned multiparameter SE MR image sets obtained from six patients undergoing diagnostic work-up for suspected adnexal or pelvic masses to generate intensity-based color composites. To quantitatively assess the ability of this technique to differentially segment anatomically and pathologically confirmed tissue types into unique color regions within the full-color spectrum, color image analysis was performed on the multiparameter color composites within each patient case, and the results were compared using 95% confidence intervals. RESULTS: Based on the results of pathologic correlation and color image analysis, the generation of full-color composites represents a feasible technique for compressing the diverse tissue contrast data present in multiparameter MR images of adnexal masses. CONCLUSION: With this technique, it is possible to generate composites that simultaneously display uniquely color-coded anatomic and pathologic tissue information within the context of partially natural-appearing images.

The futility of the chest radiograph in the febrile infant without respiratory symptoms.

OBJECTIVE: Major pediatric textbooks advocate a chest radiograph as part of the diagnostic evaluation for a sepsis workup for febrile infants less than 3 months old. Very few studies have addressed the value of performing a chest radiograph in this situation. Two studies previously published lack the numbers to statistically justify a conclusion about the need to perform a chest radiograph in the febrile infant. METHODS: Evaluated were 197 febrile infants 3 months old or less with a history, physical examination, chest radiograph, and other laboratory studies to determine the cause of their fever. This group of infants was combined with the group of infants from two similar studies published previously in the literature using cumulative meta-analysis. The combined group resulted in 617 infants. RESULTS: The combined group of infants had 361 infants who had no clinical evidence of pulmonary disease on history or physical examination. All 361 infants had normal chest radiograph. These results gave a 95% confidence interval that the chance of a positive chest radiograph in a patient with no pulmonary symptoms would occur less than 1.02% of the time. CONCLUSIONS: The generally advocated policy of obtaining a chest radiograph as part of the sepsis workup in febrile infants should be discontinued, and chest radiographs should be obtained only in febrile infants who have clinical indications of pulmonary disease.

Magnetic resonance angiography of vascular lesions causing neuro-ophthalmic deficits.

Magnetic resonance angiography (MRA) is a noninvasive, rapidly evolving technique for imaging the intra- and extracranial carotid and vertebrobasilar circulations. It may in some circumstances obviate conventional angiography and the accompanying risks associated with catheterization and contrast injection. MRA exploits the different physical properties between moving protons and stationary tissue to yield flow sensitive data in the form of anatomic images or velocity and flow measurements. Since patients with various vascular disorders may present exclusively with ophthalmologic signs and symptoms, it is expected that MRA will become more frequently utilized by ophthalmologists. The exact role of MRA in the workup of vascular disorders remains to be more precisely defined, pending the performance of additional well-controlled standardized studies. At present, MRA is utilized to complement the conventional spin-echo studies of patients with arterial and venous occlusion, vascular malformations, intracranial aneurysms, and neoplastic vascular invasion. With further refinements, it is expected that MRA will become a standard diagnostic tool for the evaluation of patients with vascular disorders.

MRI: stability of three supervised segmentation techniques.

Supervised segmentation methods from three families of pattern recognition techniques were used to segment multispectral MRI data. Studied were the maximum likelihood method (MLM), k-nearest neighbors (k-NN), and a back-propagation artificial neural net (ANN). Performance was measured in terms of execution speed, and stability for the selection of training data, namely, region of interest (ROI) selection, and interslice and interpatient classifications. MLM proved to have the smallest execution times, but demonstrated the least stability. k-NN showed the best stability for training data selection. To evaluate the segmentation techniques, multispectral images were used of normal volunteers and patients with gliomas, the latter with and without MR contrast material. All measures applied indicated that k-NN provides the best results.

Angiographic magnetic resonance color composites of the normal brain and its vasculature.

Vascular magnetic resonance imaging (MRI) has become an important noninvasive adjunct to conventional cerebral MRI studies. To detect parenchymal changes associated with vascular anomalies, optimal diagnostic evaluation requires the comparison of both spin-echo and angiographic gradient-echo MRIs. To compress image data into a single 24-bit color image possessing the combined tissue contrast characteristics of both conventional spin-echo "black-blood" images and flow-sensitive gradient-echo "bright-blood" images, the red-green-blue color model and computer-based image-processing software were used to generate composites of MRI sets in which blood appears bright red while many stationary tissues possess near-natural colors. This technique may have potential applicability to human cerebrovascular MRI.

A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain.

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms, and a supervised computational neural network. Initial clinical results are presented on normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. For a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed, with fuzz-c-means approaches being slightly preferred over feedforward cascade correlation results. Various facets of both approaches, such as supervised versus unsupervised learning, time complexity, and utility for the diagnostic process, are compared.

Composite and classified color display in MR imaging of the female pelvis.

Because of its superior soft-tissue-imaging capabilities, MRI has proved to be an excellent modality for visualizing the contents of the female pelvis. In an effort to potentially improve gynecological MRI studies, we have applied color composite techniques to sets of spin-echo and gradient-echo gray-tone MR images obtained from various individuals. For composite generation, based on tissue region of interest calculated mean pixel intensity values, various colors were applied to spatially aligned images using a DEC MicroVAX II computer with interactive digital language (IDL) so that tissue contrast patterns could be optimized in the final image. The IDL procedures, which are similar to those used in NASA's LANDSAT image processing system, allowed the generation of single composite images displaying the combined information present in a series of spatially aligned images acquired using different pulse sequences. With our composite generation techniques, it was possible to generate seminatural-appearing color images of the female pelvis that possessed enhanced conspicuity of specific tissues and fluids. For comparison with color composites, classified images were also generated based on computer recognition and statistical separation of distinct tissue intensity patterns in an image set using the maximum likelihood processing algorithm.