PubMed Health⌕ Search

Biomedical subjects

Kelly H Zou

Publications and source records attributed to Kelly H Zou.

At least 37 records · Page 2Linked to original sources

Telomerase activity predicts malignancy in percutaneous image-guided needle biopsy specimens of the abdomen and pelvis.

PURPOSE: To determine prospectively if assessment of telomerase activity in percutaneous needle biopsy specimens improves sensitivity and specificity in the diagnosis of abdominal and pelvic malignancy. MATERIALS AND METHODS: The study was approved by the institutional review board, and written informed consent was obtained from all patients. A prospective double-blinded design was used to assess telomerase activity in abdominal and pelvic biopsy specimens from 99 patients (64 men, 35 women; age range, 22-87 years). After the clinical sample was retrieved, a study specimen from an extra needle pass was divided and independently analyzed for cytologic characteristics and telomerase activity. The final diagnosis was based on chart review at a minimum 1-year follow-up. Statistical analyses included sensitivity, specificity, and accuracy of cytologic examination and/or telomerase activity in predicting malignancy. RESULTS: Data from study specimens indicated that the sensitivity, specificity, and accuracy of telomerase activity (n=99) in predicting malignancy were 55%, 79%, and 60%, respectively. For cytologic examination (n=86), the sensitivity, specificity, and accuracy in predicting malignancy were 74%, 94%, and 78%, respectively. Combining the two tests (n=86) and classifying a positive reading with either test as malignant improved sensitivity (83%) (P <.05) without altering specificity (76%). In 20 patients who had clinical sample reports that were classified as indeterminate, telomerase activity (n=20) yielded a higher sensitivity (62%) (P <.05) and similar specificity (86%) compared with cytologic examination (n=15), which yielded a sensitivity of 11% and a specificity of 83%. CONCLUSION: In percutaneous biopsy specimens of the abdomen and pelvis, the combination of cytologic examination and telomerase activity yielded an increased sensitivity in predicting malignancy. In addition, assessing telomerase activity can help identify cancer even when cytologic results are indeterminate.

Abdominal Neoplasms↗

Reproducibility of functional MR imaging: preliminary results of prospective multi-institutional study performed by Biomedical Informatics Research Network.

PURPOSE: To prospectively investigate the factors--including subject, brain hemisphere, study site, field strength, imaging unit vendor, imaging run, and examination visit--affecting the reproducibility of functional magnetic resonance (MR) imaging activations based on a repeated sensory-motor (SM) task. MATERIALS AND METHODS: The institutional review boards of all participating sites approved this HIPAA-compliant study. All subjects gave informed consent. Functional MR imaging data were repeatedly acquired from five healthy men aged 20-29 years who performed the same SM task at 10 sites. Five 1.5-T MR imaging units, four 3.0-T units, and one 4.0-T unit were used. The subjects performed bilateral finger tapping on button boxes with a 3-Hz audio cue and a reversing checkerboard. In a block design, 15-second epochs of alternating baseline and tasks yielded 85 acquisitions per run. Functional MR images were acquired with block-design echo-planar or spiral gradient-echo sequences. Brain activation maps standardized in a unit-sphere for the left and right hemispheres of each subject were constructed. Areas under the receiver operating characteristic curve, intraclass correlation coefficients, multiple regression analysis, and paired Student t tests were used for statistical analyses. RESULTS: Significant factors were subject (P < .005), k-space (P < .005), and field strength (P = .02) for sensitivity and subject (P = .03) and k-space (P = .05) for specificity. At 1.5-T MR imaging, mean sensitivities ranged from 7% to 32% and mean specificities were higher than 99%. At 3.0 T, mean sensitivities and specificities ranged from 42% to 85% and from 96% to 99%, respectively. At 4.0 T, mean sensitivities and specificities ranged from 41% to 73% and from 95% to 99%, respectively. Mean areas under the receiver operating characteristic curve (+/- their standard errors) were 0.77 +/- 0.05 at 1.5 T, 0.90 +/- 0.09 at 3.0 T, and 0.95 +/- 0.02 at 4.0 T, with significant differences between the 1.5- and 3.0-T examinations and between the 1.5- and 4.0-T examinations (P < .01 for both comparisons). Intraclass correlation coefficients ranged from 0.49 to 0.71. CONCLUSION: MR imaging at 3.0- and 4.0-T yielded higher reproducibility across sites and significantly better results than 1.5-T imaging. The effects of subject, k-space, and field strength on examination reproducibility were significant.

Adult↗

Capturing intraoperative deformations: research experience at Brigham and Women's Hospital.

During neurosurgical procedures the objective of the neurosurgeon is to achieve the resection of as much diseased tissue as possible while achieving the preservation of healthy brain tissue. The restricted capacity of the conventional operating room to enable the surgeon to visualize critical healthy brain structures and tumor margin has lead, over the past decade, to the development of sophisticated intraoperative imaging techniques to enhance visualization. However, both rigid motion due to patient placement and nonrigid deformations occurring as a consequence of the surgical intervention disrupt the correspondence between preoperative data used to plan surgery and the intraoperative configuration of the patient's brain. Similar challenges are faced in other interventional therapies, such as in cryoablation of the liver, or biopsy of the prostate. We have developed algorithms to model the motion of key anatomical structures and system implementations that enable us to estimate the deformation of the critical anatomy from sequences of volumetric images and to prepare updated fused visualizations of preoperative and intraoperative images at a rate compatible with surgical decision making. This paper reviews the experience at Brigham and Women's Hospital through the process of developing and applying novel algorithms for capturing intraoperative deformations in support of image guided therapy.

Algorithms↗

Electrocardiographically gated 16-section CT of the thorax: cardiac motion suppression.

Thirty patients underwent 16-section multi-detector row computed tomographic (CT) angiography of the thorax with retrospective electrocardiographic gating. Institutional review board approval was obtained for retrospective analysis of CT scan data and records; patient informed consent was not required. Images reconstructed at six different time points (0%, 20%, 40%, 50%, 60%, 80%) within the R-R interval on the electrocardiogram were analyzed by two radiologists for diagnostic quality, to identify suitable reconstruction intervals for optimal suppression of cardiac motion. Five regions of interest (left coronary artery, aortic root, ascending and descending aorta, pulmonary arteries) were evaluated. Best image quality was achieved by referencing image reconstruction to middiastole (50%-60%) for the left coronary artery, aortic root, and ascending aorta. The pulmonary arteries are best displayed during mid- to late diastole (80%).

Adult↗

Three validation metrics for automated probabilistic image segmentation of brain tumours.

The validity of brain tumour segmentation is an important issue in image processing because it has a direct impact on surgical planning. We examined the segmentation accuracy based on three two-sample validation metrics against the estimated composite latent gold standard, which was derived from several experts' manual segmentations by an EM algorithm. The distribution functions of the tumour and control pixel data were parametrically assumed to be a mixture of two beta distributions with different shape parameters. We estimated the corresponding receiver operating characteristic curve, Dice similarity coefficient, and mutual information, over all possible decision thresholds. Based on each validation metric, an optimal threshold was then computed via maximization. We illustrated these methods on MR imaging data from nine brain tumour cases of three different tumour types, each consisting of a large number of pixels. The automated segmentation yielded satisfactory accuracy with varied optimal thresholds. The performances of these validation metrics were also investigated via Monte Carlo simulation. Extensions of incorporating spatial correlation structures using a Markov random field model were considered.

Algorithms↗

Three-dimensional magnetic resonance imaging technique for myocardial-delayed hyperenhancement: a comparison with the two-dimensional technique.

PURPOSE: To compare two-dimensional and three-dimensional techniques in the detection of myocardial infarction (MI) and in the grading transmural extent (TE). MATERIALS AND METHODS: Twelve patients with clinically proven MI were examined using two-dimensional and three-dimensional techniques with cardiac-gated, breath-hold, T1-weighted gradient echo sequence with an inversion recovery pulse following gadopentetate dimeglumine (Gd-DTPA) at 0.2 mmol/kg. Contrast-to-noise, signal-to-noise, and signal intensity ratios (CNR, SNR, and SIR, respectively) were derived and compared for each technique. RESULTS: From two-dimensional to three-dimensional, statistical significant difference was found in the mean CNR (11.65 vs. 56.59; P = 0.002), SNR (18.03 vs. 76.90; P < 0.001), and SIR (3.6 vs. 6.36; P = 0.05). Intraobserver agreement (kappa) between two-dimensional and three-dimensional were R1 = 74% and R2 = 90%. Interobserver agreements between the readers were two-dimensional = 77% and three-dimensional = 79%. CONCLUSION: Mean CNR, SNR, and SIR are significantly increased in the three-dimensional technique compared to the conventional two-dimensional technique.

Adult↗

Functional MRI of auditory verbal working memory: long-term reproducibility analysis.

Although functional MRI (fMRI) has shown to be a tool with great potential to study the normal and diseased human brain, the large variability in the detected hemodynamic responses across sessions and across subjects hinders a wider application. To investigate the long-term reproducibility of fMRI activation of verbal working memory (WM), eight normal subjects performed an auditory version of the 2-back verbal WM task while fMRI images were acquired. The experiment was repeated nine times with the same settings for image acquisition and fMRI task. Data were analyzed using SPM99 program. Single-session activation maps and multi-subject session-specific activation maps were generated. Regions of interest (ROIs) associated to specific components of verbal WM were defined based on the voxels' coordinates in Talairach space. Visual observation of the multi-subject activation maps showed similar activation patterns, and quantitative analysis showed small coefficients of variance of activation within ROIs over time, suggesting small longitudinal variability of activation. Visual observation of the activation maps of individual sessions demonstrated striking variation of activation across sessions and across subjects, and quantitative analysis demonstrated larger contribution from between-subject variation to overall variation than that from within-subject variation. We concluded that by multi-subject analysis of data from a relatively small number of subjects, reasonably reproducible activation for the 2-back verbal WM paradigm can be achieved. The level of reproducibility encourages the application of this fMRI paradigm to the evaluation of cognitive changes in future investigations. The quantitative estimation of the proportions of within-subject and between-subject variabilities in the overall variability may be helpful for the design of future studies.

Acoustic Stimulation↗

What is evidence-based medicine?

RATIONALE AND OBJECTIVES: In this review article, we present the definition and useful concepts of evidence-based medicine (EBM). The principles of EBM are provided and major steps of practicing EBM are described. MATERIALS AND METHODS: We emphasize the importance of the Cochrane Collaboration (see http://www.cochrane.org), which initiated the research and practice in this area. Because it can be difficult to systematically access and review individual research studies, it is often useful to focus on a critical overview of clinical trials by conducting a meta-analysis. RESULTS: Useful literature and resources related to meta-analysis are provided. CONCLUSION: Statistical methods for evaluating radiologic diagnostic performances derived from meta-analysis are summarized, with a special focus on summary outcomes measures.

Evidence-Based Medicine↗

Statistical validation of image segmentation quality based on a spatial overlap index.

RATIONALE AND OBJECTIVES: To examine a statistical validation method based on the spatial overlap between two sets of segmentations of the same anatomy. MATERIALS AND METHODS: The Dice similarity coefficient (DSC) was used as a statistical validation metric to evaluate the performance of both the reproducibility of manual segmentations and the spatial overlap accuracy of automated probabilistic fractional segmentation of MR images, illustrated on two clinical examples. Example 1: 10 consecutive cases of prostate brachytherapy patients underwent both preoperative 1.5T and intraoperative 0.5T MR imaging. For each case, 5 repeated manual segmentations of the prostate peripheral zone were performed separately on preoperative and on intraoperative images. Example 2: A semi-automated probabilistic fractional segmentation algorithm was applied to MR imaging of 9 cases with 3 types of brain tumors. DSC values were computed and logit-transformed values were compared in the mean with the analysis of variance (ANOVA). RESULTS: Example 1: The mean DSCs of 0.883 (range, 0.876-0.893) with 1.5T preoperative MRI and 0.838 (range, 0.819-0.852) with 0.5T intraoperative MRI (P < .001) were within and at the margin of the range of good reproducibility, respectively. Example 2: Wide ranges of DSC were observed in brain tumor segmentations: Meningiomas (0.519-0.893), astrocytomas (0.487-0.972), and other mixed gliomas (0.490-0.899). CONCLUSION: The DSC value is a simple and useful summary measure of spatial overlap, which can be applied to studies of reproducibility and accuracy in image segmentation. We observed generally satisfactory but variable validation results in two clinical applications. This metric may be adapted for similar validation tasks.

Analysis of Variance↗

Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation.

Characterizing the performance of image segmentation approaches has been a persistent challenge. Performance analysis is important since segmentation algorithms often have limited accuracy and precision. Interactive drawing of the desired segmentation by human raters has often been the only acceptable approach, and yet suffers from intra-rater and inter-rater variability. Automated algorithms have been sought in order to remove the variability introduced by raters, but such algorithms must be assessed to ensure they are suitable for the task. The performance of raters (human or algorithmic) generating segmentations of medical images has been difficult to quantify because of the difficulty of obtaining or estimating a known true segmentation for clinical data. Although physical and digital phantoms can be constructed for which ground truth is known or readily estimated, such phantoms do not fully reflect clinical images due to the difficulty of constructing phantoms which reproduce the full range of imaging characteristics and normal and pathological anatomical variability observed in clinical data. Comparison to a collection of segmentations by raters is an attractive alternative since it can be carried out directly on the relevant clinical imaging data. However, the most appropriate measure or set of measures with which to compare such segmentations has not been clarified and several measures are used in practice. We present here an expectation-maximization algorithm for simultaneous truth and performance level estimation (STAPLE). The algorithm considers a collection of segmentations and computes a probabilistic estimate of the true segmentation and a measure of the performance level represented by each segmentation. The source of each segmentation in the collection may be an appropriately trained human rater or raters, or may be an automated segmentation algorithm. The probabilistic estimate of the true segmentation is formed by estimating an optimal combination of the segmentations, weighting each segmentation depending upon the estimated performance level, and incorporating a prior model for the spatial distribution of structures being segmented as well as spatial homogeneity constraints. STAPLE is straightforward to apply to clinical imaging data, it readily enables assessment of the performance of an automated image segmentation algorithm, and enables direct comparison of human rater and algorithm performance.

Algorithms↗

Practice management performance indicators in academic radiology departments.

PURPOSE: To determine the management performance indicators most frequently utilized in academic radiology departments in the United States. MATERIALS AND METHODS: This investigation met the criteria for an exemption from institutional review board approval. A cross-sectional study in which a validated national survey was sent to members of the Society of Chairmen of Academic Radiology Departments (SCARD) was conducted. The survey was designed to examine the following six categories of 28 performance indicators: (a) general organization, (b) volume and productivity, (c) radiology reporting, (d) access to examinations, (e) customer satisfaction, and (f) finance. A total of 158 variables were included in the analysis. Summary statistics, the chi(2) test, rank correlation, multiple regression analysis, and analysis of variance were used. RESULTS: A response rate of 42% (55 of 132 SCARD members) was achieved. The mean number of performance indicators used by radiology departments was 16 +/- 6.35 (standard deviation). The most frequently utilized performance indicators were as follows: (a) productivity, in terms of examination volume (78% [43 departments]) and examination volume per modality (78% [43 departments]); (b) reporting, in terms of report turnaround (82% [45 departments]) and transcription time (71% [39 departments]); (c) access, in terms of appointment access to magnetic resonance imaging (80% [44 departments]); (d) satisfaction, in terms of number of patient complaints (84% [46 departments]); and (e) finance, in terms of expenses (67% [37 departments]). Regression analysis revealed that the numbers of performance indicators in each category were statistically significant in predicting the total number of performance indicators used (P < .001 for all). Numbers of productivity and financial indicators were moderately correlated (r = 0.51). However, there were no statistically significant correlations between the numbers of performance indicators used and hospital location, hospital size, or department size (P > .4 for all). CONCLUSION: Assessing departmental performance with a wide range of management indicators is not yet an established and standardized practice in academic radiology departments in the United States. Among all indicators, productivity indicators are the most frequently used.

Academic Medical Centers↗

Decreases in ventricular volume correlate with decreases in ventricular pressure in idiopathic normal pressure hydrocephalus patients who experienced clinical improvement after implantation with adjustable valve shunts.

OBJECTIVE: This retrospective study examined whether changes in ventricular volume correspond with changes in adjustable valve pressure settings in a cohort of patients who received shunts to treat idiopathic normal pressure hydrocephalus. We also examined whether these pressure-volume curves and other patient variables would co-occur with a positive clinical response to shunting. METHODS: We selected 51 patients diagnosed with idiopathic normal pressure hydrocephalus who had undergone implantation of a Codman Hakim programmable valve (Medos S.A., Le Locle, Switzerland). Clinical data were gathered from the patients' records and clinical notes by an investigator blinded to patients' ventricular volumes. Ventricular volume was measured using 3D Slicer, an image analysis and interactive visualization software package developed and maintained at the Surgical Planning Laboratory at Brigham and Women's Hospital. RESULTS: Eighty-six percent of patients with gait disturbance at presentation showed improvement of this symptom, 70% experienced improvement in incontinence, and 69% experienced improvement in dementia. For the group showing 100% clinical improvement, the correlation coefficient of average changes in valve pressure over time (delta P/delta T) and average changes in ventricular volume over time (delta V/delta T) were high at 0.843 (P < 0.05). For the group experiencing no or only partial improvement, the correlation coefficient was 0.257 (P = 0.32), indicating no correlation between average delta V/delta T and average delta P/delta T for each patient. CONCLUSION: This was a carefully analyzed modeling study of idiopathic normal pressure hydrocephalus treatment made possible only by adjustable valve technology. With careful volumetric analysis, we found that changes in ventricular volume correlated with adjustments in valve pressure settings for those patients who improved clinically after shunting. This suggests that positive clinical responders retained parenchymal elasticity, emphasizing the importance of dynamic changes in this cohort.

Adolescent↗

Evaluation of small (</= 3 cm) renal masses with MDCT: benefits of thin overlapping reconstructions.

OBJECTIVE: Our purpose was to determine whether thin overlapping reconstructions using MDCT improve the detection and characterization of small renal masses. MATERIALS AND METHODS: Thirty-seven patients were scanned with MDCT using 2.5-mm collimation. Nephrographic phase data were reconstructed in two ways: a standard protocol (5-mm section thickness, no overlap) and an experimental protocol (3-mm section thickness, 50% overlap). Masses were detected and classified into three groups: group 1, measuring less than 20 H on both protocols (classified as cysts on both); group 2, measuring 20 H or greater on standard protocol and less than 20 H on experimental protocol (classified as cysts using experimental protocol only); and group 3, measuring 20 H or greater on both protocols (not classified as cysts using either protocol). Masses 10 mm or larger in group 3 were evaluated further for enhancement. Statistically significant differences between protocols were assessed using an analysis of counts and proportions. RESULTS: Of 175 detected lesions, 29 (17%) were detected only with the experimental protocol; all but one were smaller than 5 mm. Using the experimental protocol, of 45 masses between 5 and 10 mm, the number of masses that could be characterized as cysts increased from 13 (29%) to 38 (84%). The overall number of indeterminate lesions was reduced from 101 (69%) of 146 lesions detected with the standard protocol to 86 (53%) of 161 lesions detected with the experimental protocol. CONCLUSION: Using MDCT and thin overlapping reconstructions, renal cysts as small as 5 mm can be diagnosed with more confidence than is possible with standard reconstructions, and the overall number of indeterminate renal masses is reduced.

Adult↗

Three-dimensional assessment of MRI-guided percutaneous cryotherapy of liver metastases.

OBJECTIVE: We report our initial investigation of the use of a 3D method for assessing percutaneous tumor ablations. We hypothesized that these 3D techniques could be used to assess the technical success of ablations and that 3D metrics would be predictive of treatment response. CONCLUSION: Three-dimensional assessment of percutaneous tumor ablations provides a quantitative evaluation of the technical success of the procedure. Three-dimensional computer-based techniques can both quantify coverage of a tumor and create a virtual ablation margin for percutaneous procedures, akin to a surgical margin. Although results are preliminary, 3D metrics were useful in predicting treatment response.

Aged↗

A modified CT severity index for evaluating acute pancreatitis: improved correlation with patient outcome.

OBJECTIVE: This study was conducted to assess the correlation with patient outcome and interobserver variability of a modified CT severity index in the evaluation of patients with acute pancreatitis compared with the currently accepted CT severity index. MATERIALS AND METHODS: Of 266 consecutive patients diagnosed with acute pancreatitis during a 1-year period, 66 underwent contrast-enhanced MDCT within 1 week of the onset of symptoms. Three radiologists who were blinded to patient outcome independently scored the severity of the pancreatitis using both the currently accepted and modified CT severity indexes. The modified index included a simplified assessment of pancreatic inflammation and necrosis as well as an assessment of extrapancreatic complications. Outcome parameters included the length of hospital stay; the need for surgery or percutaneous intervention; and the occurrences of infection, organ failure, and death. For both the current and modified indexes, correlation between the severity of the pancreatitis and patient outcome was estimated using the Wilcoxon's rank sum test and Fisher's exact test. Interobserver agreement for both indexes was calculated using the kappa statistic. RESULTS: When applying the modified index, the severity of pancreatitis and the following parameters correlated more closely than when the currently accepted index was applied: the length of the hospital stay (0-34 days) (modified index [p = 0.0054-0.0714] vs current index [p = 0.0052-0.3008]); the need for surgical or percutaneous procedures (10/66 patients) (modified index [p = 0.0112] vs current index [p = 0.0324]); and the occurrence of infection (21/66 patients) (modified index [p < 1e(-10)] vs current index [p < 1e(-04)]). Significant correlation between the severity of pancreatitis and the development of organ failure (9/66 patients) was seen only using the modified index (p = 0.0024), not the current index (p = 0.0513). The interobserver agreement was similar with the modified (kappa range, 0.71-0.85) and the current (kappa range, 0.63-0.86) indexes. CONCLUSION: The modified CT severity index correlates more closely with patient outcome measures than the currently accepted CT severity index, with similar interobserver variability.

Acute Disease↗

Hypothesis testing I: proportions.

Statistical inference involves two analysis methods: estimation and hypothesis testing, the latter of which is the subject of this article. Specifically, Z tests of proportion are highlighted and illustrated with imaging data from two previously published clinical studies. First, to evaluate the relationship between nonenhanced computed tomographic (CT) findings and clinical outcome, the authors demonstrate the use of the one-sample Z test in a retrospective study performed with patients who had ureteral calculi. Second, the authors use the two-sample Z test to differentiate between primary and metastatic ovarian neoplasms in the diagnosis and staging of ovarian cancer. These data are based on a subset of cases from a multiinstitutional ovarian cancer trial conducted by the Radiologic Diagnostic Oncology Group, in which the roles of CT, magnetic resonance imaging, and ultrasonography (US) were evaluated. The statistical formulas used for these analyses are explained and demonstrated. These methods may enable systematic analysis of proportions and may be applied to many other radiologic investigations.

Diagnostic Imaging↗

Statistical validation based on parametric receiver operating characteristic analysis of continuous classification data.

RATIONALE AND OBJECTIVES: The accuracy of diagnostic test and imaging segmentation is important in clinical practice because it has a direct impact on therapeutic planning. Statistical validations of classification accuracy was conducted based on parametric receiver operating characteristic analysis, illustrated on three radiologic examples, MATERIALS AND METHODS: Two parametric models were developed for diagnostic or imaging data. Example 1: A semi-automated fractional segmentation algorithm was applied to magnetic resonance imaging of nine cases of brain tumors. The tumor and background pixel data were assumed to have bi-beta distributions. Fractional segmentation was validated against an estimated composite pixel-wise gold standard based on multi-reader manual segmentations. Example 2: The predictive value of 100 cases of spiral computed tomography of ureteral stone sizes, distributed as bi-normal after a non-linear transformation, under two treatment options received. Example 3: One hundred eighty cases had prostate-specific antigen levels measured in a prospective clinical trial. Radical prostatectomy was performed in all to provide a binary gold standard of local and advanced cancer stages. Prostate-specific antigen level was transformed and modeled by bi-normal distributions. In all examples, areas under the receiver operating characteristic curves were computed. RESULTS. The areas under the receiver operating characteristic curves were: Example 1: Fractional segmentation of magnetic resonance imaging of brain tumors: meningiomas (0.924-0.984); astrocytomas (0.786-0.986); and other low-grade gliomas (0.896-0.983). Example 3: Ureteral stone size for treatment planning (0.813). Example 2: Prostate-specific antigen for staging prostate cancer (0.768). CONCLUSION: All clinical examples yielded fair to excellent accuracy. The validation metric area under the receiver operating characteristic curves may be generalized to evaluating the performances of several continuous classifiers related to imaging.

Algorithms↗

Detection of prostate cancer by integration of line-scan diffusion, T2-mapping and T2-weighted magnetic resonance imaging; a multichannel statistical classifier.

A multichannel statistical classifier for detecting prostate cancer was developed and validated by combining information from three different magnetic resonance (MR) methodologies: T2-weighted, T2-mapping, and line scan diffusion imaging (LSDI). From these MR sequences, four different sets of image intensities were obtained: T2-weighted (T2W) from T2-weighted imaging, Apparent Diffusion Coefficient (ADC) from LSDI, and proton density (PD) and T2 (T2 Map) from T2-mapping imaging. Manually segmented tumor labels from a radiologist, which were validated by biopsy results, served as tumor "ground truth." Textural features were extracted from the images using co-occurrence matrix (CM) and discrete cosine transform (DCT). Anatomical location of voxels was described by a cylindrical coordinate system. A statistical jack-knife approach was used to evaluate our classifiers. Single-channel maximum likelihood (ML) classifiers were based on 1 of the 4 basic image intensities. Our multichannel classifiers: support vector machine (SVM) and Fisher linear discriminant (FLD), utilized five different sets of derived features. Each classifier generated a summary statistical map that indicated tumor likelihood in the peripheral zone (PZ) of the prostate gland. To assess classifier accuracy, the average areas under the receiver operator characteristic (ROC) curves over all subjects were compared. Our best FLD classifier achieved an average ROC area of 0.839(+/-0.064), and our best SVM classifier achieved an average ROC area of 0.761(+/-0.043). The T2W ML classifier, our best single-channel classifier, only achieved an average ROC area of 0.599(+/-0.146). Compared to the best single-channel ML classifier, our best multichannel FLD and SVM classifiers have statistically superior ROC performance (P=0.0003 and 0.0017, respectively) from pairwise two-sided t-test. By integrating the information from multiple images and capturing the textural and anatomical features in tumor areas, summary statistical maps can potentially aid in image-guided prostate biopsy and assist in guiding and controlling delivery of localized therapy under image guidance.

Algorithms↗