Incorporation of an iterative, linear segmentation routine into a mammographic mass CAD system

In previous research, we have developed a computer-aided detection (CAD) system designed to detect masses in mammograms. The previous version of our system employed a simple but imprecise method to localize the masses. In this research, we present a more robust segmentation routine for use with mammographic masses. Our hypothesis is that by more accurately describing the morphology of the masses, we can improve the CAD system's ability to distinguish masses from other mammographic structures. To test this hypothesis, we incorporated the new segmentation routine into our CAD system and examined the change in performance. The developed iterative, linear segmentation routine is a gray level-based procedure. Using the identified regions from the previous CAD system as the initial seeds, the new segmentation algorithm refines the suspicious mass borders by making estimates of the interior and exterior pixels. These estimates are then passed to a linear discriminant, which determines the optimal threshold between the interior and exterior pixels. After applying the threshold and identifying the object's outline, two constraints on the border are applied to reduce the influence of background noise. After the border is constrained, the process repeats until a stopping criterion is reached. The segmentation routine was tested on a study database of 183 mammographic images extracted from the Digital Database for Screening Mammography. Eighty-three of the images contained 50 malignant and 50 benign masses; 100 images contained no masses. The previously developed CAD system was used to locate a set of suspicious regions of interest (ROIs) within the images. To assess the performance of the segmentation algorithm, a set of 20 features was measured from the suspicious regions before and after the application of the developed segmentation routine. Receiver operating characteristic (ROC) analysis was employed on the ROIs to examine the discriminatory capabilities of each individual feature before and after the segmentation routine. A statistically significant performance increase was found in many of the individual features, particularly those describing the mass borders. To examine how the incorporation of the segmentation routine affected the performance of the overall CAD system, free-response ROC (FROC) analysis was employed. When considering only malignant masses, the FROC performance of the system with the segmentation routine appeared better than the previous system. When detecting 90% of the malignant masses, the previous system achieved 4.9 false positives per image (FPpI) compared to the post-segmentation system's 4.2 FPpI. At 80% sensitivity, the respective FPpI were 3.5 and 1.6.     

Performance of a completely automated system for monitoring CMV DNA in plasma

BackgroundCompletely automated systems for monitoring CMV-DNA in plasma samples are now available.ObjectivesEvaluate analytical and clinical performances of the VERIS™/MDx System CMV Assay^®.Study designAnalytical performance was assessed using quantified quality controls. Clinical performance was assessed by comparison with the COBAS^® Ampliprep™/COBAS^® Taqman CMV test using 169 plasma samples that had tested positive with the in-house technique in whole blood.ResultsThe specificity of the VERIS™/MDx System CMV Assay^® was 99% [CI 95%: 97.7–100]. Intra-assay reproducibilities were 0.03, 0.04, 0.05 and 0.04 log₁₀ IU/ml (means 2.78, 3.70, 4.64 and 5.60 log₁₀ IU/ml) for expected values of 2.70, 3.70, 4.70 and 5.70 log₁₀ IU/ml. The inter-assay reproducibilities were 0.12 and 0.08 (means 6.30 and 2.85 log₁₀ IU/ml) for expected values of 6.28 and 2.80 log₁₀ IU/ml. The lower limit of detection was 14.6 IU/ml, and the assay was linear from 2.34 to 5.58 log₁₀ IU/ml. The results for the positive samples were concordant (r = 0.71, p < 0.0001; slope of Deming regression 0.79 [CI 95%: 0.56–1.57] and y-intercept 0.79 [CI 95%: 0.63–0.95]). The VERIS™/MDx System CMV Assay^® detected 18 more positive samples than did the COBAS^® Ampliprep™/COBAS^® Taqman CMV test and the mean virus load were higher (0.41 log₁₀ IU/ml). Patient monitoring on 68 samples collected from 17 immunosuppressed patients showed similar trends between the two assays. As secondary question, virus loads detected by the VERIS™/MDx System CMV Assay^® were compared to those of the in-house procedure on whole blood. The results were similar between the two assays (−0.09 log₁₀ IU/ml) as were the patient monitoring trends.ConclusionThe performances of the VERIS™/MDx System CMV Assay^® facilitated its routine use in monitoring CMV-DNA loads in plasma samples.     

Combining two mammographic projections in a computer aided mass detection method

A method is presented to improve computer aided detection (CAD) results for masses in mammograms by fusing information obtained from two views of the same breast. It is based on a previously developed approach to link potentially suspicious regions in mediolateral oblique (MLO) and craniocaudal (CC) views. Using correspondence between regions, we extended our CAD scheme by building a cascaded multiple-classifier system, in which the last stage computes suspiciousness of an initially detected region conditional on the existence and similarity of a linked candidate region in the other view. We compared the two-view detection system with the single-view detection method using free-response receiver operating characteristic (FROC) analysis and cross validation. The dataset used in the evaluation consisted of 948 four-view mammograms, including 412 cancer cases with a mass, architectural distortion, or asymmetry. A statistically significant improvement was found in the lesion based detection performance. At a false positive (FP) rate of 0.1 FP/image, the lesion sensitivity improved from 56% to 61%. Case based sensitivity did not improve.     

A completely automated closed-field maze series for rats

Although a sensitive indicator of learning impairment, the Hebb-Williams serial maze remains impractical for many physiological studies because of a tedious observer scoring procedure. A simple, completely automated closed-field maze test series for rats is described, which overcomes this problem. Animal movements across a maze field of insulated floor plates are monitored by a transistor amplifying-detection circuit. Data are presented comparing automated scoring with the manual scoring method of Rabinovitch and Rosvold [8]. Complete automation eliminates observer involvement and provides a reliable and inexpensive means for testing large number of animals. Further modification of the system permits analysis of the direction in animal movements.     

Using database matches with for HMMGene for automated gene detection in Drosophila

The application of the gene finder HMMGene to the Adh region of the Drosophila melanogaster is described, and the prediction results are analyzed. HMMGene is based on a probabilistic model called a hidden Markov model, and the probabilistic framework facilitates the inclusion of database matches of varying degrees of certainty. It is shown that database matches clearly improve the performance of the gene finder. For instance, the sensitivity for coding exons predicted with both ends correct grows from 62% to 70% on a high-quality test set, when matches to proteins, cDNAs, repeats, and transposons are included. The specificity drops more than the sensitivity increases when ESTs are used. This is due to the high noise level in EST matches, and it is discussed in more detail why this is and how it might be improved.     

A statistical methodology for mammographic density detection

A statistical methodology is presented based on a chi-square probability analysis that allows the automated discrimination of radiolucent tissue (fat) from radiographic densities (fibroglandular tissue) in digitized mammograms. The method is based on earlier work developed at this facility that shows mammograms may be considered as evolving from a linear filtering operation where a random input field is passed through a 1/f filtering process. The filtering process is reversible which allows the solution of the input field with knowledge obtained from the raw image (the output). The input field solution is analogous to a prewhitening technique or deconvolution. This field contains all the information of the raw image in a much simplified format that can be approximated and analyzed with parametric methods. In the work presented here evidence indicates that there are two random events occurring in the input field with differing variances: (1) one relating to fat tissue with the smaller variance, and (2) the second relating to all other tissue with the larger variance. A statistical comparison of the variances is made by scanning the image with a small search window. A relaxation method allows for making a reliable estimate of the smaller variance which is considered as the global reference. If a local variance deviates significantly from the reference variance, based on chi-square analysis, it is labeled as nonfat; otherwise it is labeled as fat. This statistical test procedure results in a region by region continuous labeling of fat and nonfat tissue across the image. In the work presented here, the emphasis is on the methodology development with supporting preliminary results that are very encouraging. It is widely accepted that mammographic density is a breast cancer risk factor. An important application of this work is to incorporate density-based risk analysis into the ongoing statistical-based detection work developed at this facility. Additional applications include risk analysis dependent on either percentages or total amounts of fat or dense tissue. This work may be considered as the initial step in introducing many of the known breast cancer risk factors into the actual image data analysis.     

False-positive reduction in CAD mass detection using a competitive classification strategy

High false-positive (FP) rate remains to be one of the major problems to be solved in CAD study because too many false-positively cued signals will potentially degrade the performance of detecting true-positive regions and increase the call-back rate in CAD environment. In this paper, we proposed a novel classification method for FP reduction, where the conventional "hard" decision classifier is cascaded with a "soft" decision classification with the objective to reduce false-positives in the cases with multiple FPs retained after the "hard" decision classification. The "soft" classification takes a competitive classification strategy in which only the "best" ones are selected from the pre-classified suspicious regions as the true mass in each case. A neural network structure is designed to implement the proposed competitive classification. Comparative studies of FP reduction on a database of 79 images by a "hard" decision classification and a combined "hard"-"soft" classification method demonstrated the efficiency of the proposed classification strategy. For example, for the high FP sub-database which has only 31.7% of total images but accounts for 63.5% of whole FPs generated in single "hard" classification, the FPs can be reduced for 56% (from 8.36 to 3.72 per image) by using the proposed method at the cost of 1% TP loss (from 69% to 68%) in whole database, while it can only be reduced for 27% (from 8.36 to 6.08 per image) by simply increasing the threshold of "hard" classifier with a cost of TP loss as high as 14% (from 69% to 55%). On the average in whole database, the FP reduction by hybrid "hard"-"soft" classification is 1.58 per image as compared to 1.11 by "hard" classification at the TP costs described above. Because the cases with high dense tissue are of higher risk of cancer incidence and false-negative detection in mammogram screening, and usually generate more FPs in CAD detection, the method proposed in this paper will be very helpful in improving the performance of early detection of breast cancer with CAD.     

An automated pontine-wave detection system

STUDY OBJECTIVES: Pontine-waves (P-waves), the pontine component of ponto-geniculo-occipital waves, represent a close marker of brainstem phasic events and are associated with cardiorespiratory changes in sleep. Because visual scoring is subjective and cumbersome, we developed an automated P-wave analysis system, which could detect and classify P-waves as clusters or as isolated events in bipolar recordings of the pontine electroencephalogram (EEG) of conscious rats. DESIGN: A computer algorithm was developed to extract and normalize each half-wave of the pontine EEG according to the background noise level. Candidate events for different P-wave patterns (uniphasic, biphasic, and triphasic) were compared to a corresponding set of amplitude and duration thresholds to identify P-waves and to reject artifacts. PARTICIPANTS: Ten adult male Sprague-Dawley rats were instrumented for chronic polysomnography. MEASUREMENTS AND RESULTS: Two human experts manually scored each recording, and their consensus score was used as the "gold standard" for algorithm optimization and validation. The algorithm's scoring thresholds were optimized on a training set of 5 six-hour polysomnographic records, yielding 96.8% accuracy and 97.7% sensitivity versus human consensus scoring. Validation of the algorithm, using the optimized threshold values, was conducted using a set of 5 independent recordings, resulting in 94.8% accuracy and 94.7% sensitivity versus human consensus scoring. CONCLUSIONS: We have developed and validated an automated system for detection and classification of P-waves in conscious rats with advantages over human scoring, including increased speed and perfect reliability.     

Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions

We are using Bayesian artificial neural networks (BANNs) to classify mammographic masses in schemes for computer-aided diagnosis, and we are extending this methodology to a three-class classification task. We investigated whether a BANN can estimate ideal observer decision variables to distinguish malignant, benign, and false-positive computer detections. Five features were calculated for 63 malignant and 29 benign computer-detected mass lesions, and for 1049 false-positive computer detections, in 440 mammograms randomly divided into a training and testing set. A BANN was trained on the training set features and applied to the testing set features. We then used a known relation between three-class ideal observer decision variables and that used by a two-class ideal observer when two of three classes are grouped into one class, giving one decision variable for distinguishing malignant from nonmalignant detections, and a second for distinguishing true-positive from false-positive computer detections. For comparison, we grouped the training data into two classes in the same two ways and trained two-class BANNs for these two tasks. The three-class BANN decision variables were essentially identical in performance to the specifically trained two-class BANNs, with the average difference in area under the ROC curves being less than 0.0035 and no differences in area being statistically significant. Thus, the BANN outputs obey the same theoretical relationship as do the three-class and two-class ideal observer decision variables, which is consistent with the claim that the three-class BANN output can provide good estimates of the decision variables used by a three-class ideal observer.     

A CAD system for nodule detection in low-dose lung CTs based on region growing and a new active contour model

A computer-aided detection (CAD) system for the selection of lung nodules in computer tomography (CT) images is presented. The system is based on region growing (RG) algorithms and a new active contour model (ACM), implementing a local convex hull, able to draw the correct contour of the lung parenchyma and to include the pleural nodules. The CAD consists of three steps: (1) the lung parenchymal volume is segmented by means of a RG algorithm; the pleural nodules are included through the new ACM technique; (2) a RG algorithm is iteratively applied to the previously segmented volume in order to detect the candidate nodules; (3) a double-threshold cut and a neural network are applied to reduce the false positives (FPs). After having set the parameters on a clinical CT, the system works on whole scans, without the need for any manual selection. The CT database was recorded at the Pisa center of the ITALUNG-CT trial, the first Italian randomized controlled trial for the screening of the lung cancer. The detection rate of the system is 88.5% with 6.6 FPs/CT on 15 CT scans (about 4700 sectional images) with 26 nodules: 15 internal and 11 pleural. A reduction to 2.47 FPs/CT is achieved at 80% efficiency.     

A method for determination of optimal image enhancement for the detection of mammographic abnormalities

We present a paradigm for empirical evaluation of digital image enhancement algorithms for mammography that uses psychophysical methods for implementation and analysis of a clinically relevant detection task. In the experiment, the observer is asked to detect and assign to a quadrant, or indicate the absence of, a simulated mammographic structure characteristic of cancer embedded in a background image of normal breast tissue. Responses are indicated interactively on a computer workstation. The parameter values for the enhancement applied to the composite image may be varied on each trial, and structure detection performance is estimated for each enhancement condition. Preliminary investigations have provided insight into an appropriate viewing duration, and furthermore, suggest that nonradiologists may be used under this methodology for the tasks investigated thus far, for predicting parameter values for clinical investigation. We are presently using this method in evaluating several contrast enhancement algorithms of possible benefit in mammography. These methods enable an objective, clinically relevant evaluation, for the purpose of optimal parameter determination or performance assessment, of digital image-processing methods potentially used in mammography.     

A magnetic tape database for a real-time medical information system.

The activity profile of a file of General Practitioners' Medical Records is such that the cost of storage medium must be carefully balanced against the worst possible access time in the case of emergencies. The acceptable use of a magnetic tape data base in a Real-Time Medical Information System is analyzed, and the practical experience of operating such a system is summarised. Possible extensions to the scheme for use with larger data bases are outlined.     

自动巢式多重PCR系统在呼吸道感染病例中快速检测呼吸道病原体的应用

目的 探讨自动巢式多重PCR系统在呼吸道感染病原体快速诊断中的应用价值.方法 2016年11月至2017年3月收集120例呼吸道感染患者的呼吸道标本和临床流行病学资料,利用自动巢式多重PCR系统对120份鼻咽拭子标本进行病原检测,对检测结果和临床资料进行统计学分析.结果 120份标本中单一病原检出68份,2种及2种以上病原混合检出22份,总检出率为75.0％(90/120),检出结果中以甲型流感病毒、呼吸道合胞病毒、百日咳杆菌为主.结论 自动巢式多重PCR系统敏感度高、特异性强,对呼吸道感染患者的病原学快速诊断具有重要价值.     

Validation of a digital mammographic unit model for an objective and highly automated clinical image quality assessment

In mammography, image quality assessment has to be directly related to breast cancer indicator (e.g. microcalcifications) detectability. Recently, we proposed an X-ray source/digital detector (XRS/DD) model leading to such an assessment. This model simulates very realistic contrast-detail phantom (CDMAM) images leading to gold disc (representing microcalcifications) detectability thresholds that are very close to those of real images taken under the simulated acquisition conditions. The detection step was performed with a mathematical observer. The aim of this contribution is to include human observers into the disc detection process in real and virtual images to validate the simulation framework based on the XRS/DD model. Mathematical criteria (contrast-detail curves, image quality factor, etc.) are used to assess and to compare, from the statistical point of view, the cancer indicator detectability in real and virtual images. The quantitative results given in this paper show that the images simulated by the XRS/DD model are useful for image quality assessment in the case of all studied exposure conditions using either human or automated scoring. Also, this paper confirms that with the XRS/DD model the image quality assessment can be automated and the whole time of the procedure can be drastically reduced. Compared to standard quality assessment methods, the number of images to be acquired is divided by a factor of eight.     

Evaluation of a rapid and completely automated real-time reverse transcriptase PCR assay for diagnosis of enteroviral meningitis

Nucleic acid amplification tests (NAATs) for enterovirus RNA in cerebrospinal fluid (CSF) have emerged as the new gold standard for diagnosis of enteroviral meningitis, and their use can improve the management and decrease the costs for caring for children with enteroviral meningitis. The Xpert EV assay (Cepheid, Sunnyvale, CA) is a rapid, fully automated real-time PCR test for the detection of enterovirus RNA that was approved by the U.S. Food and Drug Administration for in vitro diagnostic use in March 2007. In this multicenter trial we established the clinical performance characteristics of the Xpert EV assay in patients presenting with meningitis symptoms relative to clinical truth. Clinical truth for enteroviral meningitis was defined as clinical evidence of meningitis, the absence of another detectable pathogen in CSF, and detection of enterovirus in CSF either by two reference NAATs or by viral culture. A total of 199 prospectively and 235 retrospectively collected specimens were eligible for inclusion in this study. The overall prevalence of enteroviral meningitis was 26.04%. The Xpert EV assay had a sensitivity of 94.69% (90% confidence interval [CI] = 89.79 to 97.66%), specificity of 100% (90% CI = 99.07 to 100%), positive predictive value of 100%, negative predictive value of 98.17, and an accuracy of 98.62% relative to clinical truth. The Xpert EV assay demonstrated a high degree of accuracy for diagnosis of enteroviral meningitis. The simplicity and on-demand capability of the Xpert EV assay should prove to be a valuable adjunct to the evaluation of suspected meningitis cases.