Nabile M. Safdar

Personalized assessment of craniosynostosis via statistical shape modeling

We present a technique for the computational analysis of craniosynostosis from CT images. Our fully automatic methodology uses a statistical shape model to produce diagnostic features tailored to the anatomy of the subject. We propose a computational anatomy approach for measuring shape abnormality in terms of the closest case from a multi-atlas of normal cases. Although other authors have tackled malformation characterization for craniosynostosis in the past, our approach involves several novel contributions (automatic labeling of cranial regions via graph cuts, identification of the closest morphology to a subject using a multi-atlas of normal anatomy, detection of suture fusion, registration using masked regions and diagnosis via classification using quantitative measures of local shape and malformation). Using our automatic technique we obtained for each subject an index of cranial suture fusion, and deformation and curvature discrepancy averages across five cranial bones and six suture regions. Significant differences between normal and craniosynostotic cases were obtained using these characteristics. Machine learning achieved a 92.7% sensitivity and 98.9% specificity for diagnosing craniosynostosis automatically, values comparable to those achieved by trained radiologists. The probability of correctly classifying a new subject is 95.7%.

Handoffs between radiologists and patients: threat or opportunity?

Radiologists, referring physicians, and patients all have certain legal rights regarding access to medical records, including imaging data. The degree of patient access is likely to increase with the growing adoption of patient portals and personal health records. In addition, referring physicians and radiologists have a collective responsibility to ensure that important findings are transferred appropriately between their practices. In some cases when this is not possible, communicating directly with patients is the best way to protect the interests of both patients and radiologists. Even when not required, some radiologists have extensive experience communicating results directly to patients. Direct communication of radiology results to patients may present an opportunity to satisfy patients and reassert the importance of the physician-patient relationship in radiology.

Segmentation of kidney in 3D-ultrasound images using Gabor-based appearance models

This paper presents a new segmentation method for 3D ultrasound images of the pediatric kidney. Based on the popular active shape models, the algorithm is tailored to deal with the particular challenges raised by US images. First, a weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. Second, an orientation correction approach is used to create a Gabor-based appearance model for each landmark at different scales. This multiscale characteristic is incorporated into the segmentation algorithm, creating a hierarchical approach where different appearance models are considered as the segmentation process evolves. The performance of the algorithm was evaluated on a dataset of 14 cases, both healthy and pathological, obtaining an average Dices coefficient of 0.85, an average point-to-point distance of 4.07 mm, and 0.12 average relative volume difference.

Automatic Analysis of Pediatric Renal Ultrasound Using Shape, Anatomical and Image Acquisition Priors

In this paper we present a segmentation method for ultrasound (US) images of the pediatric kidney, a difficult and barely studied problem. Our method segments the kidney on 2D sagittal US images and relies on minimal user intervention and a combination of improvements made to the Active Shape Model (ASM) framework. Our contributions include particle swarm initialization and profile training with rotation correction. We also introduce our methodology for segmentation of the kidneys collecting system (CS), based on graph-cuts (GC) with intensity and positional priors. Our intensity model corrects for intensity bias by comparison with other biased versions of the most similar kidneys in the training set. We prove significant improvements (p < 0.001) with respect to classic ASM and GC for kidney and CS segmentation, respectively. We use our semi-automatic method to compute the hydronephrosis index (HI) with an average error of 2.67 +/- 5.22 percentage points similar to the error of manual HI between different operators of 2.31 +/- 4.54 percentage points.

A prototype body-mounted MRI-compatible robot for needle guidance in shoulder arthrography

A novel compact and lightweight patient-mounted MRI-compatible robot has been designed for MRI image-guided interventions. This robot is intended to enable MRI-guided needle placement as done in shoulder arthrography. The robot could make needle placement more accurate and simplify the current workflow by converting the traditional two-stage arthrography procedure (fluoroscopy-guided needle insertion followed by a diagnostic MRI scan) to a one-stage procedure (streamlined workflow all in MRI suite). The robot has 4 degrees of freedom (DOF), two for orientation of the needle and two for needle positioning. The mechanical design was based on several criteria including rigidity, MRI compatibility, compact design, sterilizability, and adjustability. The proposed workflow is discussed and initial MRI compatibility experiments are presented. The results show that artifacts in the region of interest are minimal and that MRI images of the shoulder were not adversely affected by placing the robot on a human volunteer.

Vision and quality in the digital imaging environment: how much does the visual acuity of radiologists vary at an intermediate distance?

OBJECTIVE The purpose of this study was to examine the intermediate-distance visual acuity of a cross section of radiologists and to identify variation in visual acuity during a typical workday. SUBJECTS AND METHODS Forty-eight radiologists completed a brief survey before undergoing visual acuity testing, with corrective lenses if routinely used, at three times of the day. Testing was performed with modified versions of a U.S. Federal Aviation Administration visual acuity test instrument. RESULTS The mean acuity of radiologists across all measurements was 20/15 (logarithm of the minimum angle of resolution [logMAR], -0.109 +/- 0.105 [SD]). Visual acuity ranged from 20/30 to 20/10 (logMAR, 0.176 to -0.301). Mean visual acuity in the morning session was approximately 20/16 (logMAR, -0.0856). This value was statistically significantly lower than the mean visual acuity in both the early afternoon (logMAR, -0.124; p = 0.003) and the late afternoon (logMAR, -0.118; p = 0.015), both of which were approximately 20/15. This change was within the expected test-retest variability of Snellen acuity measurements. CONCLUSION Although a statistically significant difference was detected between the visual acuity of radiologists in the morning and acuity in other parts of the day, this difference was relatively modest and within previously published ranges of variability for similar visual acuity tests. It is unlikely that such variation in visual acuity among radiologists influences diagnostic performance. Not every radiologist had 20/20 vision, a few needed visual correction, and more than a few had not undergone a thorough eye examination for as many as 15 years before the study.

What's in a Name? Accurately Diagnosing Metopic Craniosynostosis Using a Computational Approach.

Background: The metopic suture is unlike other cranial sutures in that it normally closes in infancy. Consequently, the diagnosis of metopic synostosis depends primarily on a subjective assessment of cranial shape. The purpose of this study was to create a simple, reproducible radiographic method to quantify forehead shape and distinguish trigonocephaly from normal cranial shape variation. Methods: Computed tomography scans were acquired for 92 control patients (mean age, 4.2 ± 3.3 months) and 18 patients (mean age, 6.2 ± 3.3 months) with a diagnosis of metopic synostosis. A statistical model of the normal cranial shape was constructed, and deformation fields were calculated for patients with metopic synostosis. Optimal and divergence (simplified) interfrontal angles (IFA) were defined based on the three points of maximum average deformation on the frontal bones and metopic suture, respectively. Statistical analysis was performed to assess the accuracy and reliability of the diagnostic procedure. Results: The optimal interfrontal angle was found to be significantly different between the synostosis (116.5 ± 5.8 degrees; minimum, 106.8 degrees; maximum, 126.6 degrees) and control (136.7 ± 6.2 degrees; minimum, 123.8 degrees; maximum, 169.3 degrees) groups (p < 0.001). Divergence interfrontal angles were also significantly different between groups. Accuracy, in terms of available clinical diagnosis, for the optimal and divergent angles, was 0.981 and 0.954, respectively. Conclusions: Cranial shape analysis provides an objective and extremely accurate measure by which to diagnose abnormal interfrontal narrowing, the hallmark of metopic synostosis. The simple planar angle measurement proposed is reproducible and accurate, and can eliminate diagnostic subjectivity in this disorder. CLINICAL QUESTION/LEVEL OF EVIDENCE: Diagnostic, IV.

Renal Segmentation From 3D Ultrasound via Fuzzy Appearance Models and Patient-Specific Alpha Shapes

Ultrasound (US) imaging is the primary imaging modality for pediatric hydronephrosis, which manifests as the dilation of the renal collecting system (CS). In this paper, we present a new framework for the segmentation of renal structures, kidney and CS, from 3DUS scans. First, the kidney is segmented using an active shape model-based approach, tailored to deal with the challenges raised by US images. A weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. The model is completed with a new fuzzy appearance model and a multi-scale omnidirectional Gabor-based appearance descriptor. Next, the CS is segmented using an active contour formulation, which combines contour- and intensity-based terms. The new positive alpha detector presented here allows to control the propagation process by means of a patient-specific stopping function created from the bands of adipose tissue within the kidney. The performance of the new segmentation approach was evaluated on a dataset of 39 cases, showing an average Dices coefficient of 0.86±0.05 for the kidney, and 0.74 ± 0.10 for the CS segmentation, respectively. These promising results demonstrate the potential utility of this framework for the US-based assessment of the severity of pediatric hydronephrosis.

Informatics Leaders in Radiology: Who They Are and Why You Need Them

IT in health care has evolved rapidly over the past 20 years. The rise of the computer is at the core of these changes. Most agree that although these technologies have revolutionized the practice of medicine, they have additionally fostered a data revolution that is simultaneously useful and disruptive. The effective use and implementation of the right IT tools are critical to the success of the imaging profession. This article serves as a guideline to radiologists on how to build an effective IT division within an imaging enterprise from the perspective of leadership, management, and human resources. We address the process for building an IT team from the ground up and also provide recommendations for modifying an existing IT group to make it more effective. Paramount to this discussion is the concept of the imaging informatics professional and the advantage this type of training brings to a radiology department. In addition, we focus on the critical role of the physician informaticist as a liaison to bridge gaps among the IT, medical, and administrative functions in an organization.

Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction

In this paper we present a segmentation method for 2D ultrasound images of the pediatric kidney. Our method relies on minimal user intervention and produces accurate segmentations thanks to a combination of improvements made to the Active Shape Model (ASM) framework. The initialization of the ASM module is based on a Covariance Matrix Adaptation Evolution Strategy (CMA-ES) genetic algorithm that optimizes the pose and the main shape variation modes of the kidney shape model. In order to account for the image formation process in ultrasound, the appearance model is obtained not according to the anatomically corresponding contour landmarks, but to those that exhibit a similar angle of incidence with respect to the wavefront traveling from the probe. The results indicate a median Dices coefficient of 90.2% and a relative area difference of 10.8% for segmentation of a set of 80 kidney images.