Deep Learning Body Region Classification of MRI and CT Examinations.

This study demonstrates the high performance of deep learning in identification of body regions covering the entire human body from magnetic resonance (MR) and computed tomography (CT) axial images across diverse acquisition protocols and modality manufacturers. Pixel-based analysis of anatomy contained in image sets can provide accurate anatomic labeling. For this purpose, a convolutional neural network (CNN)-based classifier was developed to identify body regions in CT and MRI studies. Seventeen CT (18 MRI) body regions covering the entire human body were defined for the classification task. Three retrospective datasets were built for the AI model training, validation, and testing, with a balanced distribution of studies per body region. The test datasets originated from a different healthcare network than the train and validation datasets. Sensitivity and specificity of the classifier was evaluated for patient age, patient sex, institution, scanner manufacturer, contrast, slice thickness, MRI sequence, and CT kernel. The data included a retrospective cohort of 2891 anonymized CT cases (training, 1804 studies; validation, 602 studies; test, 485 studies) and 3339 anonymized MRI cases (training, 1911 studies; validation, 636 studies; test, 792 studies). Twenty-seven institutions from primary care hospitals, community hospitals, and imaging centers contributed to the test datasets. The data included cases of all sexes in equal proportions and subjects aged from 18 years old to + 90 years old. Image-level weighted sensitivity of 92.5% (92.1-92.8) for CT and 92.3% (92.0-92.5) for MRI and weighted specificity of 99.4% (99.4-99.5) for CT and 99.2% (99.1-99.2) for MRI were achieved. Deep learning models can classify CT and MR images by body region including lower and upper extremities with high accuracy.

Computed Tomography Image Compressibility and Limitations of Compression Ratio-Based Guidelines.

Finding optimal compression levels for diagnostic imaging is not an easy task. Significant compressibility variations exist between modalities, but little is known about compressibility variations within modalities. Moreover, compressibility is affected by acquisition parameters. In this study, we evaluate the compressibility of thousands of computed tomography (CT) slices acquired with different slice thicknesses, exposures, reconstruction filters, slice collimations, and pitches. We demonstrate that exposure, slice thickness, and reconstruction filters have a significant impact on image compressibility due to an increased high frequency content and a lower acquisition signal-to-noise ratio. We also show that compression ratio is not a good fidelity measure. Therefore, guidelines based on compression ratio should ideally be replaced with other compression measures better correlated with image fidelity. Value-of-interest (VOI) transformations also affect the perception of quality. We have studied the effect of value-of-interest transformation and found significant masking of artifacts when window is widened.

Teaching DICOM by problem solving.

The Digital Imaging and Communications in Medicine (DICOM) is the standard for encoding and communicating medical imaging information. It is used in radiology as well as in many other imaging domains such as ophthalmology, dentistry, and pathology. DICOM information objects are used to encode medical images or information about the images. Their usage outside of the imaging department is increasing, especially with the sharing of medical images within Electronic Health Record systems. However, learning DICOM is long and difficult because it defines and uses many specific abstract concepts that relate to each other. In this paper, we present an approach, based on problem solving, for teaching DICOM as part of a graduate course on healthcare information. The proposed approach allows students with diversified background and no software development experience to grasp a large breadth of knowledge in a very short time.

Using JPEG 2000 interactive protocol to stream a large image or a large image set.

The electronic health record (EHR) is expected to improve the quality of care by enabling access to relevant information at the diagnostic decision moment. During deployment efforts for including images in the EHR, a main challenge has come up from the need to compare old images with current ones. When old images reside in a different system, they need to be imported for visualization which leads to a problem related to persistency management and information consistency. A solution consisting in avoiding image import is achievable with image streaming. In this paper we present, evaluate, and discuss two medical-specific streaming use cases: displaying a large image such as a digital mammography image and displaying a large set of relatively small images such as a large CT series.

Compressibility variations of JPEG2000 compressed computed tomography.

Compression is increasingly used in medical applications to enable efficient and universally accessible electronic health records. However, lossy compression introduces artifacts that can alter diagnostic accuracy, interfere with image processing algorithms and cause liability issues in cases of diagnostic errors. Compression guidelines were introduced to mitigate these issues and foster the use of modern compression algorithms with diagnostic imaging. However, these guidelines are usually defined as maximum compression ratios for each imaging protocol and do not take compressibility variations due to image content into account. In this paper we have evaluated the compressibility of thousands of computed tomography slices of an anthropomorphic thoracic phantom acquired with different parameters. We have shown that exposure, slice thickness and reconstruction filters have a significant impact on compressibility suggesting that guidelines based solely on compression ratios may be inadequate.