Automatic X-ray landmark detection and shape segmentation via data-driven joint estimation of image displacements

In this paper, we propose a new method for fully-automatic landmark detection and shape segmentation in X-ray images. To detect landmarks, we estimate the displacements from some randomly sampled image patches to the (unknown) landmark positions, and then we integrate these predictions via a voting scheme. Our key contribution is a new algorithm for estimating these displacements. Different from other methods where each image patch independently predicts its displacement, we jointly estimate the displacements from all patches together in a data driven way, by considering not only the training data but also geometric constraints on the test image. The displacements estimation is formulated as a convex optimization problem that can be solved efficiently. Finally, we use the sparse shape composition model as the a priori information to regularize the landmark positions and thus generate the segmented shape contour. We validate our method on X-ray image datasets of three different anatomical structures: complete femur, proximal femur and pelvis. Experiments show that our method is accurate and robust in landmark detection, and, combined with the shape model, gives a better or comparable performance in shape segmentation compared to state-of-the art methods. Finally, a preliminary study using CT data shows the extensibility of our method to 3D data.

Automatic Reduction of Artifacts in EEG-Signals

Electroencephalograms (EEG) are often contaminated with high amplitude artifacts limiting the usability of data. Methods that reduce these artifacts are often restricted to certain types of artifacts, require manual interaction or large training data sets. Within this paper we introduce a novel method, which is able to eliminate many different types of artifacts without manual intervention. The algorithm first decomposes the signal into different sub-band signals in order to isolate different types of artifacts into specific frequency bands. After signal decomposition with principal component analysis (PCA) an adaptive threshold is applied to eliminate components with high variance corresponding to the dominant artifact activity. Our results show that the algorithm is able to significantly reduce artifacts while preserving the EEG activity. Parameters for the algorithm do not have to be identified for every patient individually making the method a good candidate for preprocessing in automatic seizure detection and prediction algorithms.

Fully automatic X-ray image segmentation via joint estimation of image displacements.

We propose a new method for fully-automatic landmark detection and shape segmentation in X-ray images. Our algorithm works by estimating the displacements from image patches to the (unknown) landmark positions and then integrating them via voting. The fundamental contribution is that, we jointly estimate the displacements from all patches to multiple landmarks together, by considering not only the training data but also geometric constraints on the test image. The various constraints constitute a convex objective function that can be solved efficiently. Validated on three challenging datasets, our method achieves high accuracy in landmark detection, and, combined with statistical shape model, gives a better performance in shape segmentation compared to the state-of-the-art methods.

Evaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge

Cephalometric analysis is an essential clinical and research tool in orthodontics for the orthodontic analysis and treatment planning. This paper presents the evaluation of the methods submitted to the Automatic Cephalometric X-Ray Landmark Detection Challenge, held at the IEEE International Symposium on Biomedical Imaging 2014 with an on-site competition. The challenge was set to explore and compare automatic landmark detection methods in application to cephalometric X-ray images. Methods were evaluated on a common database including cephalograms of 300 patients aged six to 60 years, collected from the Dental Department, Tri-Service General Hospital, Taiwan, and manually marked anatomical landmarks as the ground truth data, generated by two experienced medical doctors. Quantitative evaluation was performed to compare the results of a representative selection of current methods submitted to the challenge. Experimental results show that three methods are able to achieve detection rates greater than 80% using the 4 mm precision range, but only one method achieves a detection rate greater than 70% using the 2 mm precision range, which is the acceptable precision range in clinical practice. The study provides insights into the performance of different landmark detection approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.

Use of Extended Characteristics of Locomotion and Feeding Behavior for Automated Identification of Lame Dairy Cows.

This study was carried out to detect differences in locomotion and feeding behavior in lame (group L; n = 41; gait score ≥ 2.5) and non-lame (group C; n = 12; gait score ≤ 2) multiparous Holstein cows in a cross-sectional study design. A model for automatic lameness detection was created, using data from accelerometers attached to the hind limbs and noseband sensors attached to the head. Each cow's gait was videotaped and scored on a 5-point scale before and after a period of 3 consecutive days of behavioral data recording. The mean value of 3 independent experienced observers was taken as a definite gait score and considered to be the gold standard. For statistical analysis, data from the noseband sensor and one of two accelerometers per cow (randomly selected) of 2 out of 3 randomly selected days was used. For comparison between group L and group C, the T-test, the Aspin-Welch Test and the Wilcoxon Test were used. The sensitivity and specificity for lameness detection was determined with logistic regression and ROC-analysis. Group L compared to group C had significantly lower eating and ruminating time, fewer eating chews, ruminating chews and ruminating boluses, longer lying time and lying bout duration, lower standing time, fewer standing and walking bouts, fewer, slower and shorter strides and a lower walking speed. The model considering the number of standing bouts and walking speed was the best predictor of cows being lame with a sensitivity of 90.2% and specificity of 91.7%. Sensitivity and specificity of the lameness detection model were considered to be very high, even without the use of halter data. It was concluded that under the conditions of the study farm, accelerometer data were suitable for accurately distinguishing between lame and non-lame dairy cows, even in cases of slight lameness with a gait score of 2.5.

A Fully Automatic Calibration Framework for Navigated Ultrasound Imaging

Navigated ultrasound (US) imaging is used for the intra-operative acquisition of 3D image data during imageguided surgery. The presented approach includes the design of a compact and easy to use US calibration device and its integration into a software application for navigated liver surgery. User interaction during the calibration process is minimized through automatic detection of the calibration process followed by automatic image segmentation, calculation of the calibration transform and validation of the obtained result. This leads to a fast, interaction-free and fully automatic calibration procedure enabling intra-operative

Determination of free and total valproic acid in human plasma by capillary electrophoresis with contactless conductivity detection

A new approach for the determination of free and total valproic acid in small samples of 140 μL human plasma based on capillary electrophoresis with contactless conductivity detection is proposed. A dispersive liquid-liquid microextraction technique was employed in order to remove biological matrices prior to instrumental analysis. The free valproic acid was determined by isolating free valproic acid from protein-bound valproic acid by ultrafiltration under centrifugation of 100 μL sample. The filtrate was acidified to turn valproic acid into its protonated neutral form and then extracted. The determination of total valproic acid was carried out by acidifying 40 μL untreated plasma to release the protein-bound valproic acid prior to extraction. A solution consisting of 10 mM histidine, 10 mM 3-(N-morpholino)propanesulfonic acid and 10 μM hexadecyltrimethylammonium bromide of pH 6.5 was used as background electrolyte for the electrophoretic separation. The method showed good linearity in the range of 0.4-300 μg/mL with a correlation coefficient of 0.9996. The limit of detection was 0.08 μg/mL, and the reproducibility of the peak area was excellent (RSD=0.7-3.5%, n=3, for the concentration range from 1 to 150 μg/mL). The results for the free and total valproic acid concentration in human plasma were found to be comparable to those obtained with a standard immunoassay. The corresponding correlation coefficients were 0.9847 for free and 0.9521 for total valproic acid.

Milk cortisol concentration in automatic milking systems compared with auto-tandem milking parlors

Milk cortisol concentration was determined under routine management conditions on 4 farms with an auto-tandem milking parlor and 8 farms with 1 of 2 automatic milking systems (AMS). One of the AMS was a partially forced (AMSp) system, and the other was a free cow traffic (AMSf) system. Milk samples were collected for all the cows on a given farm (20 to 54 cows) for at least 1 d. Behavioral observations were made during the milking process for a subset of 16 to 20 cows per farm. Milk cortisol concentration was evaluated by milking system, time of day, behavior during milking, daily milk yield, and somatic cell count using linear mixed-effects models. Milk cortisol did not differ between systems (AMSp: 1.15 +/- 0.07; AMSf: 1.02 +/- 0.12; auto-tandem parlor: 1.01 +/- 0.16 nmol/L). Cortisol concentrations were lower in evening than in morning milkings (1.01 +/- 0.12 vs. 1.24 +/- 0.13 nmol/L). The daily periodicity of cortisol concentration was characterized by an early morning peak and a late afternoon elevation in AMSp. A bimodal pattern was not evident in AMSf. Finally, milk cortisol decreased by a factor of 0.915 in milking parlors, by 0.998 in AMSp, and increased by a factor of 1.161 in AMSf for each unit of ln(somatic cell count/1,000). We conclude that milking cows in milking parlors or AMS does not result in relevant stress differences as measured by milk cortisol concentrations. The biological relevance of the difference regarding the daily periodicity of milk cortisol concentrations observed between the AMSp and AMSf needs further investigation.

Detection of smuggled cocaine in cargo using MDCT

OBJECTIVE: Smuggling dissolved drugs, especially cocaine, in bottled liquids is an ongoing problem at borders. Common fluoroscopy of packages at the border cannot detect contaminated liquids. The objective of our study was to develop an MDCT screening method to detect cocaine-containing vessels that are hidden between uncontaminated ones in a shipment. MATERIALS AND METHODS: Studies were performed on three wine bottles containing cocaine solutions that were confiscated at the Swiss border. Reference values were obtained by scans of different sorts of commercially available wine and aqueous solutions of dissolved sugar. All bottles were scanned using MDCT, and data evaluation was performed by measuring the mean peak of Hounsfield units. To verify the method, simulated testing was performed. RESULTS: Using measurements of the mean peak of Hounsfield units enables the detection of dissolved cocaine in wine bottles in a noninvasive and rapid fashion. Increasing opacity corresponds well with the concentration of dissolved cocaine. Simulated testing showed that it is possible to distinguish between cocaine-contaminated and uncontaminated wine bottles. CONCLUSION: The described method is an efficacious screening method to detect cocaine-contaminated bottles that are hidden between untreated bottles in cargo. The noninvasive examination of cargo allows a questionable delivery to be tracked without arousing the suspicion of the smugglers.

Detecting offsets in GPS time series: first results from the Detection of Offsets in GPS Experiment

The accuracy of Global Positioning System (GPS) time series is degraded by the presence of offsets. To assess the effectiveness of methods that detect and remove these offsets, we designed and managed the Detection of Offsets in GPS Experiment. We simulated time series that mimicked realistic GPS data consisting of a velocity component, offsets, white and flicker noises (1/f spectrum noises) composed in an additive model. The data set was made available to the GPS analysis community without revealing the offsets, and several groups conducted blind tests with a range of detection approaches. The results show that, at present, manual methods (where offsets are hand picked) almost always give better results than automated or semi‒automated methods (two automated methods give quite similar velocity bias as the best manual solutions). For instance, the fifth percentile range (5% to 95%) in velocity bias for automated approaches is equal to 4.2 mm/year (most commonly ±0.4 mm/yr from the truth), whereas it is equal to 1.8 mm/yr for the manual solutions (most commonly 0.2 mm/yr from the truth). The magnitude of offsets detectable by manual solutions is smaller than for automated solutions, with the smallest detectable offset for the best manual and automatic solutions equal to 5 mm and 8 mm, respectively. Assuming the simulated time series noise levels are representative of real GPS time series, robust geophysical interpretation of individual site velocities lower than 0.2–0.4 mm/yr is therefore certainly not robust, although a limit of nearer 1 mm/yr would be a more conservative choice. Further work to improve offset detection in GPS coordinates time series is required before we can routinely interpret sub‒mm/yr velocities for single GPS stations.

Software-based detection of atrial fibrillation in long-term ECGs

Background Atrial fibrillation (AF) is common and may have severe consequences. Continuous long-term electrocardiogram (ECG) is widely used for AF screening. Recently, commercial ECG analysis software was launched, which automatically detects AF in long-term ECGs. It has been claimed that such tools offer reliable AF screening and save time for ECG analysis. However, this has not been investigated in a real-life patient cohort. Objective To investigate the performance of automatic software-based screening for AF in long-term ECGs. Methods Two independent physicians manually screened 22,601 hours of continuous long-term ECGs from 150 patients for AF. Presence, number, and duration of AF episodes were registered. Subsequently, the recordings were screened for AF by an established ECG analysis software (Pathfinder SL), and its performance was validated against the thorough manual analysis (gold standard). Results Sensitivity and specificity for AF detection was 98.5% (95% confidence interval 91.72%–99.96%) and 80.21% (95% confidence interval 70.83%–87.64%), respectively. Software-based AF detection was inferior to manual analysis by physicians (P < .0001). Median AF duration was underestimated (19.4 hours vs 22.1 hours; P < .001) and median number of AF episodes was overestimated (32 episodes vs 2 episodes; P < .001) by the software. In comparison to extensive quantitative manual ECG analysis, software-based analysis saved time (2 minutes vs 19 minutes; P < .001). Conclusion Owing to its high sensitivity and ability to save time, software-based ECG analysis may be used as a screening tool for AF. An additional manual confirmatory analysis may be required to reduce the number of false-positive findings.