Semiautomatic Evaluation of Tricuspid Annular Plane Systolic Excursion from Two Dimensional Echocardiographic Images.

BACKGROUND: Tricuspid annular plane systolic excursion (TAPSE) has emerged as a reliable marker of right ventricular (RV) systolic function. Recently, TAPSE derived using 2D images (2D-TAPSE) was shown to correlate with M-mode TAPSE (MM-TAPSE). We have developed a novel technique for semiautomatic evaluation of TAPSE (SA-TAPSE). The purpose of this study was to determine the accuracy of this novel technique and validate it on normal hearts and pulmonary hypertension (PH). METHODS: A total of 110 patients (56 with normal heart and 54 with PH) were retrospectively identified for analysis. The semiautomatic algorithm tracked the lateral tricuspid valve hinge point (TVHP) and the apex in the apical 4-chamber view. SA-TAPSE was calculated as displacement of the TVHP in end-diastole (ED) and end-systole (ES). The same points were manually identified to derive 2D-TAPSE. RESULTS: The system was able to accurately identify ED and ES in 304/330 heartbeats within three cardiac frames. The automatically identified TVHP points were within 1.2 ± 0.7 mm from the manually identified points. Intra-class correlation between SA-TAPSE and 2D-TAPSE was 0.96 (95% CI 0.93-0.98) for normal hearts and 0.92 (95% CI 0.87-0.96) for those with PH. Bland-Altman analysis showed a strong agreement between SA-TAPSE and 2D-TAPSE for normal hearts and those with PH. CONCLUSION: Using the novel custom-made software, SA-TAPSE could be measured in majority of our patients and was accurate when applied to normal hearts and those with PH. Future work will focus on fully automating the system for a rapid retrospective analysis of TAPSE.

A novel technology for automatically obtaining digital facial photographs near-simultaneously with portable radiographs.

Our objective is to design, implement, and phantom-test a device to automatically obtain point-of-care patient photographs along with portable radiographs. Such photographs could help with detection of wrong-patient errors. Our device consists of a camera controller (CC) and a camera that can be mounted on a portable conventional radiography (CR) machine. Radiation from the CR machine triggers an identification module (IM) embedded in the CR cassette. The IM then sends the cassette identifier--Plate_ID--to the CC along with a trigger to activate the camera. This trigger ensures simultaneous acquisition of radiograph and photograph, and the Plate_ID along with a time stamp ensures binding of the two images. We conducted phantom tests to determine if clinical portable radiography exposure settings (90 to 120 kVp and exposure time ranging from 0.63 to 8.0 ms) are sufficient to trigger the IM. Phantom experiments demonstrate acceptable sensor performance for clinical portable radiography exposures. Simultaneous acquisition of photographs is achieved by integrating a low-cost identification module containing a scintillator-detector into the radiographic cassette. Incident X-rays activate the scintillator-detector triggering photograph acquisition by a camera controller.

Increasing rate of detection of wrong-patient radiographs: use of photographs obtained at time of radiography.

OBJECTIVE: The objective of our study was to evaluate whether facial and chest photographs obtained simultaneously with radiographs increase radiologists' detection rate of labeling errors. MATERIALS AND METHODS: We obtained simultaneous portable radiographs and photographs of 34 patients. We generated 88 pairs of chest radiographs (one recent radiograph, one prior radiograph) and compiled a set of 20 pairs for reader review. Two, three, or four mismatched pairs (i.e., pairs containing radiographs of different patients) were introduced into each list. Ten radiologist readers blinded to the presence of mismatches interpreted the 20 radiograph pairs. Readers then reviewed a second set of 20 pairs containing mismatches but photographs of the patients obtained at the time of imaging were attached to the radiographs. Readers were not instructed regarding the purpose of the photographs. The mismatch detection rate and time for interpretation was recorded for both sessions. The two-tailed Fisher exact test was used to evaluate differences in mismatch detection rates between sessions, with a p value of less than 0.05 being considered significant. RESULTS: The error detection rates without (3/24 = 12.5%) and with (16/25 = 64%) photographs significantly differed (p = 0.0003). The average interpretation times without and with photographs were 35.73 and 26.51 minutes, respectively (two-tailed Student t test, p = 0.1165). CONCLUSION: The use of photographs increased the detection of errors without a concomitant increase in film interpretation time, which may translate into improvements in patient safety without an increase in interpretation time.

Integrating patient digital photographs with medical imaging examinations.

We introduce the concept, benefits, and general architecture for acquiring, storing, and displaying digital photographs along with medical imaging examinations. We also discuss a specific implementation built around an Android-based system for simultaneously acquiring digital photographs along with portable radiographs. By an innovative application of radiofrequency identification technology to radiographic cassettes, the system is able to maintain a tight relationship between these photographs and the radiographs within the picture archiving and communications system (PACS) environment. We provide a cost analysis demonstrating the economic feasibility of this technology. Since our architecture naturally integrates with patient identification methods, we also address patient privacy issues.

"PINOT": time-resolved parallel magnetic resonance imaging with a reduced dynamic field of view.

This article introduces a novel method named "Parallel Imaging and Noquist in Tandem" (PINOT) for accelerated image acquisition of cine cardiac magnetic resonance imaging. This method combines two prior information formalisms, the SPACE-RIP implementation of parallel imaging and the Noquist method for reduced-data image reconstruction with prior knowledge of static and dynamic regions in the field of view. The general theory is presented, and supported by results from experiments using time-resolved two-dimensional simulation data and retrospectively sub-sampled magnetic resonance imaging data with acceleration factors around 4. A signal-to-noise ratio analysis and a comparison study with TSENSE and k-t SENSE show that PINOT performs favorably in preserving edge detail, at a cost in signal-to-noise ratio and computational complexity.

Hemodynamic predictors of aortic dilatation in bicuspid aortic valve by velocity-encoded cardiovascular magnetic resonance.

BACKGROUND: Congenital bicuspid aortic valve (BAV) is a significant risk factor for serious complications including valve dysfunction, aortic dilatation, dissection, and sudden death. Clinical tools for identification and monitoring of BAV patients at high risk for development of aortic dilatation, an early complication, are not available. METHODS: This paper reports an investigation in 18 pediatric BAV patients and 10 normal controls of links between abnormal blood flow patterns in the ascending aorta and aortic dilatation using velocity-encoded cardiovascular magnetic resonance. Blood flow patterns were quantitatively expressed in the angle between systolic left ventricular outflow and the aortic root channel axis, and also correlated with known biochemical markers of vessel wall disease. RESULTS: The data confirm larger ascending aortas in BAV patients than in controls, and show more angled LV outflow in BAV (17.54 +/- 0.87 degrees) than controls (10.01 +/- 1.29) (p = 0.01). Significant correlation of systolic LV outflow jet angles with dilatation was found at different levels of the aorta in BAV patients STJ: r = 0.386 (N = 18, p = 0.048), AAO: r = 0.536 (N = 18, p = 0.022), and stronger correlation was found with patients and controls combined into one population: SOV: r = 0.405 (N = 28, p = 0.033), STJ: r = 0.562 (N = 28, p = 0.002), and AAO r = 0.645 (N = 28, p < 0.001). Dilatation and the flow jet angle were also found to correlate with plasma levels of matrix metallo-proteinase 2. CONCLUSIONS: The results of this study provide new insights into the pathophysiological processes underlying aortic dilatation in BAV patients. These results show a possible path towards the development of clinical risk stratification protocols in order to reduce morbidity and mortality for this common congenital heart defect.

CATARACTS: Challenge on automatic tool annotation for cataRACT surgery.

Surgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow analysis, with potential applications in report generation, surgical training and even real-time decision support. Most existing tool annotation algorithms focus on laparoscopic surgeries. However, with 19 million interventions per year, the most common surgical procedure in the world is cataract surgery. The CATARACTS challenge was organized in 2017 to evaluate tool annotation algorithms in the specific context of cataract surgery. It relies on more than nine hours of videos, from 50 cataract surgeries, in which the presence of 21 surgical tools was manually annotated by two experts. With 14 participating teams, this challenge can be considered a success. As might be expected, the submitted solutions are based on deep learning. This paper thoroughly evaluates these solutions: in particular, the quality of their annotations are compared to that of human interpretations. Next, lessons learnt from the differential analysis of these solutions are discussed. We expect that they will guide the design of efficient surgery monitoring tools in the near future.

X-ray scatter correction method for dedicated breast computed tomography: improvements and initial patient testing.

A previously proposed x-ray scatter correction method for dedicated breast computed tomography was further developed and implemented so as to allow for initial patient testing. The method involves the acquisition of a complete second set of breast CT projections covering 360° with a perforated tungsten plate in the path of the x-ray beam. To make patient testing feasible, a wirelessly controlled electronic positioner for the tungsten plate was designed and added to a breast CT system. Other improvements to the algorithm were implemented, including automated exclusion of non-valid primary estimate points and the use of a different approximation method to estimate the full scatter signal. To evaluate the effectiveness of the algorithm, evaluation of the resulting image quality was performed with a breast phantom and with nine patient images. The improvements in the algorithm resulted in the avoidance of introduction of artifacts, especially at the object borders, which was an issue in the previous implementation in some cases. Both contrast, in terms of signal difference and signal difference-to-noise ratio were improved with the proposed method, as opposed to with the correction algorithm incorporated in the system, which does not recover contrast. Patient image evaluation also showed enhanced contrast, better cupping correction, and more consistent voxel values for the different tissues. The algorithm also reduces artifacts present in reconstructions of non-regularly shaped breasts. With the implemented hardware and software improvements, the proposed method can be reliably used during patient breast CT imaging, resulting in improvement of image quality, no introduction of artifacts, and in some cases reduction of artifacts already present. The impact of the algorithm on actual clinical performance for detection, diagnosis and other clinical tasks in breast imaging remains to be evaluated.

A multiobserver study of the effects of including point-of-care patient photographs with portable radiography: a means to detect wrong-patient errors.

RATIONALE AND OBJECTIVES: To evaluate whether the presence of facial photographs obtained at the point-of-care of portable radiography leads to increased detection of wrong-patient errors. MATERIALS AND METHODS: In this institutional review board-approved study, 166 radiograph-photograph combinations were obtained from 30 patients. Consecutive radiographs from the same patients resulted in 83 unique pairs (ie, a new radiograph and prior, comparison radiograph) for interpretation. To simulate wrong-patient errors, mismatched pairs were generated by pairing radiographs from different patients chosen randomly from the sample. Ninety radiologists each interpreted a unique randomly chosen set of 10 radiographic pairs, containing up to 10% mismatches (ie, error pairs). Radiologists were randomly assigned to interpret radiographs with or without photographs. The number of mismatches was identified, and interpretation times were recorded. RESULTS: Ninety radiologists with 21 ± 10 (mean ± standard deviation) years of experience were recruited to participate in this observer study. With the introduction of photographs, the proportion of errors detected increased from 31% (9 of 29) to 77% (23 of 30; P = .006). The odds ratio for detection of error with photographs to detection without photographs was 7.3 (95% confidence interval: 2.29-23.18). Observer qualifications, training, or practice in cardiothoracic radiology did not influence sensitivity for error detection. There is no significant difference in interpretation time for studies without photographs and those with photographs (60 ± 22 vs. 61 ± 25 seconds; P = .77). CONCLUSIONS: In this observer study, facial photographs obtained simultaneously with portable chest radiographs increased the identification of any wrong-patient errors, without substantial increase in interpretation time. This technique offers a potential means to increase patient safety through correct patient identification.

Evaluation of performance metrics for histopathological image classifier optimization.

Clinical decision support systems use image processing and machine learning methods to objectively predict cancer in histopathological images. Integral to the development of machine learning classifiers is the ability to generalize from training data to unseen future data. A classification model's ability to accurately predict class label for new unseen data is measured by performance metrics, which also informs the classifier model selection process. Based on our research, commonly used metrics in literature (such as accuracy, ROC curve) do not accurately reflect the trained model's robustness. To the best of our knowledge, no research has been conducted to quantitatively compare performance metrics in the context of cancer prediction in histopathological images. In this paper, we evaluate various performance metrics and show that the Lift metric has the highest correlation between internal and external validation sets of a nested cross validation pipeline (R(2) = 0.57). Thus, we demonstrate that the Lift metric best generalizes classifier performance among the 23 metrics that were evaluated. Using the lift metric, we develop a classifier with a misclassification rate of 0.25 (4-class classifier) for data that the model was not trained on (external validation).

Optimal sampling for "Noquist" reduced-data cine magnetic resonance imaging.

PURPOSE: To analyze and optimize the signal-to-noise ratio (SNR) for the "Noquist" method for acceleration of cine magnetic resonance imaging in the presence of partially static field of view, designing practical methods for selection of optimal or near-optimal sample sets to allow reliable application of the method for variable image dimensions. METHODS: To investigate the impact of the Noquist method and its experimental parameters on the SNR in the image reconstructed from reduced data, and to explore optimization of methods for highest SNR stability, three different optimization parameters have been selected: the condition of the forward matrix (R(cond)) as it defines the propagation of noise into the reconstructed image, and the maximum (Φ(maxD)) and the mean (Φ(meanD)) linear noise amplification factor of the dynamic field-of-view (FOV) region. As SNR in a Noquist reconstruction is often not uniform across the FOV and since dynamic regions may contain the part of the image more clinically relevant, primarily these noise levels are targeted for optimization. Using these three optimization parameters, three experiments were conducted: characterization of Noquist SNR properties as a function of important image size parameters; for sufficiently small image dimensions, employment of exhaustive search using lexicographical algorithms to visit all possibilities under the cine imaging constraint that equal numbers of views are acquired at each time point of the sequence; and, departing from an hypothetically optimal pattern, generation and evaluation of SNR characteristics of a series of random variations to that optimal pattern. RESULTS: The impact of favorable sparse data selection is illustrated, and SNR properties are characterized as a function of relevant acquisition parameters. Optimal data selection is investigated by exhaustive methods for small image sizes, and compared with algorithmic selection patterns. Observations from these experiments are confirmed by further studies on data selection for realistic image dimensions and an optimal selection algorithm is proposed. Sixty-four cases of small image sizes were analyzed through exhaustive search with a total of 527 984 141 matrix inversions called in the process, evaluating several SNR parameters for each case. An algorithm, named "Stairwell," that permits to design image dimensions with optimal SNR characteristics is presented, evaluated and compared with cases analyzed through exhaustive search. In 71.9% of the cases exhaustively studied, the Stairwell algorithm yielded optimal solutions. For no case did the deviation from optimum exceed 3.2% (R(cond)), 1.0% (Φ(meanD)), and 4.9% (Φ(maxD)). CONCLUSIONS: We have demonstrated SNR-optimality of the "Stairwell" selection algorithm for small image dimensions, and performed additional experiments which all support hypothesized optimality of the algorithm for any image dimensions that satisfy certain symmetry constraints for Noquist reduced-data cine MR imaging. Furthermore, we have presented overall SNR characteristics associated with use of the Noquist method by this algorithm for practical clinical image dimensions. Additionally, observations from our optimization experiments allow us to formulate recommendations for dimensioning Noquist image acquisition parameters which guarantee stable inversion. Moreover, these results allow prediction of the anticipated SNR properties of the reconstruction for given image dimensions (S,D,T), relative to SNR in a conventional full-grid acquisition.

Implementation and validation of localized constant-time correlated spectroscopy (LCT-COSY) on a clinical 3T MRI scanner for investigation of muscle metabolism.

PURPOSE: To implement and evaluate a novel single-volume two-dimensional localized constant-time-based correlated spectroscopy (2D LCT-COSY) sequence on a clinical 3T MR scanner. This sequence exhibits homonuclear decoupling along the F1 dimension, leading to improved spectral resolution compared to that of non-constant-time localized correlated spectroscopy (L-COSY). MATERIALS AND METHODS: A GE 3T MR scanner equipped with a quadrature transmit and receive extremity coil was used in this study. The 2D LCT-COSY sequence was programmed using General Electric's EPIC compiler. Simulations for a two-spin 1/2 system were performed using GAMMA libraries to evaluate the theoretical performance of the sequences, and were also compared with corresponding phantom experiments using trans-cinnamic acid. Finally, spectra were acquired from the soleus muscle of healthy volunteers in order to evaluate performance in vivo. RESULTS: Simulations and experimental results confirmed the improved spectral resolution of LCT-COSY over L-COSY, as well as its homonuclear decoupling performance. The behavior of resonance amplitudes as a function of evolution time in the experiment also was appropriately reflected by the simulation. Corresponding results were obtained for the in vivo muscle spectra, in which separation of overlapping olefinic and allylic methylene protons from the intra- and extramyocellular lipids (IMCL and EMCL, respectively) was achieved. CONCLUSION: Simulations and experimental results in vitro and in vivo demonstrate the strengths of LCT-COSY. This technique can be implemented on systems of any field strength, and has the potential to separate overlapping metabolites in tissue when employed on high-field clinical MRI scanners equipped for proton spectroscopy.