Acquisition hardware for digital imaging

Deep learning in veterinary medicine, an approach based on CNN to detect pulmonary abnormalities from lateral thoracic radiographs in cats

Thoracic radiograph (TR) is a complementary exam widely used in small animal medicine which requires a sharp analysis to take full advantage of Radiographic Pulmonary Pattern (RPP). Although promising advances have been made in deep learning for veterinary imaging, the development of a Convolutional Neural Networks (CNN) to detect specifically RPP from feline TR images has not been investigated. Here, a CNN based on ResNet50V2 and pre-trained on ImageNet is first fine-tuned on human Chest X-rays and then fine-tuned again on 500 annotated TR images from the veterinary campus of VetAgro Sup (Lyon, France). The impact of manual segmentation of TR’s intrathoracic area and enhancing contrast method on the CNN’s performances has been compared. To improve classification performances, 200 networks were trained on random shuffles of training set and validation set. A voting approach over these 200 networks trained on segmented TR images produced the best classification performances and achieved mean Accuracy, F1-Score, Specificity, Positive Predictive Value and Sensitivity of 82%, 85%, 75%, 81% and 88% respectively on the test set. Finally, the classification schemes were discussed in the light of an ensemble method of class activation maps and confirmed that the proposed approach is helpful for veterinarians.

Free DICOM-Viewers for Veterinary Medicine : Survey and Comparison of Functionality and User-Friendliness of Medical Imaging PACS-DICOM-Viewer Freeware for Specific Use in Veterinary Medicine Practices

There is increasing prevalence of digital diagnostic imaging in veterinary medicine with a progressive need to use medical imaging software. As Digital Imaging and Communications in Medicine (DICOM)-viewers for veterinary use do not require medical device approval in many countries, freeware viewers might be a practical alternative. The aim of this study was to identify and evaluate free DICOM-viewer software for veterinary purposes. The functionality and user-friendliness of various DICOM-viewers from the internet were analyzed and compared. Inclusion criteria for the evaluation were free availability, PACS (picture archiving and communication system)-connectivity, and stand-alone and client-based software. Based on this, eight viewers were found: Ginkgo CADx, Horos, K-PACS, MAYAM, MITO, OsiriX Lite, RadiAnt, Synedra personal. In these DICOM-viewers, 14 core tools were tested and rated on a score from 1 to 10 by multiple observers with different levels of training, using studies of four imaging modalities. Criteria were functionality and user-friendliness. For each viewer, the total number of a predefined set of 47 important tools was counted. The ranking based on functionality and user-friendliness of 14 core tools (mean score in brackets) was as follows: 1. Horos/OsiriX Lite (8.96), 2. RadiAnt (8.90), 3. K-PACS (8.02), 4. Synedra (7.43), 5. MAYAM (6.05), 6. Ginkgo CADx (5.53), 7. MITO (3.74). The DICOM-viewers offered between 20 and 44 tools of the predefined important tool set and are sufficient for most veterinary purposes. An increasing number of tools did not necessarily impair user-friendliness, if the user interface is well designed. Based on the results of this study, veterinarians will find suitable free DICOM-viewers for their individual needs. In combination with PACS-freeware, this allows veterinary practices to run a low-budget digital imaging environment.

Development of a zoomorphic test specimen for constancy testing on digital X-ray systems in veterinary radiology

Background

Technical failures and incorrect usage of digital X-ray systems may lead to a decreasing image quality, artefacts and a higher dose exposure of staff and patients. Although there are no regulations regarding constancy testing in veterinary radiology all operators are required to avoid unnecessary exposure. The aim of this study was to develop a reasonably inexpensive zoomorphic 3D-printed test specimen for constancy testing that allows the detection of changing image quality by visual analysis.

Primarily, a calibration curve of the attenuation factor of the 3D-printing material (ZP150) was determined. MATLAB converted every pixel value of a thorax X-ray image of a Beagle dog into an equivalent thickness of printing material. The thickness distribution was printed using a 3D-printer. This printed test specimen was additionally provided with five thin aluminium discs to simulate lung nodules.

To evaluate the usability for constancy testing 12 X-ray images of the test specimen were made. Two images (reference and control) were taken with the minimum dose in order to obtain images suitable for diagnosis purposes. Eight images were taken with a dose differing 30–140% from the reference dose by varying current–time product (mAs) or tube voltage (kVp). Two images were taken with the same parameters as the reference image but edited with different image processing. Six veterinarians (general practitioners) evaluated ten chosen structures in the X-ray images in a Visual Grading Analysis and scored the image quality of these structures for every image in comparison to the reference image. A Visual Grading Analysis Score was calculated and statistically analysed.

Results

A higher current–time product led to a negligibly better evaluation of the X-ray image. The lower the current–time product the worse the X-ray images were scored. Likewise, both increasing and decreasing of the tube voltage led to lower scores.

Conclusions

A zoomorphic test specimen can be used for constancy testing of digital X-ray systems in veterinary medicine. Especially a lower dose can be recognised due to deviation in the image quality when compared to the reference image. The 3D-printed test specimen is less expensive than test equipment used in human medicine.

Survey of veterinary specialists regarding their knowledge of radiation safety and the availability of radiation safety training

OBJECTIVE To evaluate the knowledge of various veterinary specialists regarding various radiation safety matters and determine the availability of radiation safety training. DESIGN Cross-sectional study. SAMPLE 164 radiology, 81 internal medicine, and 108 emergency and critical care (ECC) specialists. PROCEDURES An online survey was developed regarding knowledge of and training in radiation safety, and invitations were sent via email through the email lists of the veterinary internal medicine, ECC, and radiology specialty colleges. Responses were summarized, and comparisons were made between radiologists and internal medicine and ECC clinicians. RESULTS 65.5% (38 /58) of respondents from academic institutions and 30.0% (33/110) of respondents from private practices indicated that radiation safety training was mandatory at their institution for personnel who work with ionizing radiation-emitting equipment, and 80.2% (85/106) and 56.6% (77/136), respectively, had received some radiation safety training. Low proportions of radiologists and internal medicine and ECC clinicians correctly identified the effective dose of ionizing radiation associated with 3-phase esophagography and 3-phase abdominal CT. Many radiologists (92/153 [60.1%]) and nonradiologists (92/179 [51.4%]) believed that the effective doses used in veterinary practice pose no increased risk of fatal cancer to their patients. CONCLUSIONS AND CLINICAL RELEVANCE Radiation safety training, although more common in academia, was not universally available and may not meet radiography equipment license requirements for some institutions. Most radiologists, internal medicine clinicians, and ECC clinicians had a poor understanding of the amount of ionizing radiation associated with medical imaging procedures and the potential hazards to their patients.

DICOM Standard Conformance in Veterinary Medicine in Germany: a Survey of Imaging Studies in Referral Cases

In 2016, the recommendations of the DICOM Standards Committee for the use of veterinary identification DICOM tags had its 10th anniversary. The goal of our study was to survey veterinary DICOM standard conformance in Germany regarding the specific identification tags veterinarians should use in veterinary diagnostic imaging. We hypothesized that most veterinarians in Germany do not follow the guidelines of the DICOM Standards Committee. We analyzed the metadata of 488 imaging studies of referral cases from 115 different veterinary institutions in Germany by computer-aided DICOM header readout. We found that 25 (5.1%) of the imaging studies fully complied with the "veterinary DICOM standard" in this survey. The results confirmed our hypothesis that the recommendations of the DICOM Standards Committee for the consistent and advantageous use of veterinary identification tags have found minimal acceptance amongst German veterinarians. DICOM does not only enable connectivity between machines, DICOM also improves communication between veterinarians by sharing correct and valuable metadata for better patient care. Therefore, we recommend that lecturers, universities, societies, authorities, vendors, and other stakeholders should increase their effort to improve the spread of the veterinary DICOM standard in the veterinary world.

Evaluation of the ventro 20° rostral-dorsocaudal oblique radiographic projection for the investigation of canine nasal disease

OBJECTIVE

To assess the ventro 20° rostral-dorsocaudal oblique projection for canine nasal disease as an alternative to the dorsoventral intra-oral view.

MATERIALS AND METHODS

Thirty-one dogs with nasal disease underwent radiography and computed tomography with a final diagnosis of underlying cause achieved through rhinoscopy, biopsy or cytology. Three independent observers, blinded to diagnosis, reviewed the nasal radiographs on two separate occasions. Intra- and inter-observer agreement and level of confidence on radiographic diagnosis were evaluated and radiographic diagnosis was compared with computed tomography and definitive diagnosis.

RESULTS

The ventro 20° rostral-dorsocaudal oblique projection of canine nasal cavities was feasible in anaesthetised dogs and gave diagnostic quality images in most dogs. Assessment of this view showed moderate to substantial agreement with computed tomography diagnosis but gave lower confidence in diagnosis. Interpretation of this radiographic projection had substantial to almost perfect repeatability but moderate reproducibility.

CLINICAL SIGNIFICANCE

The ventro 20° rostral-dorsocaudal oblique projection may be used as a valuable initial screening tool for canine nasal pathology in practices without access to advanced imaging, although computed tomography is still likely to provide greater diagnostic information.

Pilot study of bovine interdigital cassetteless computed radiography

Twenty-one limbs of bovine cadavers (42 digits) were exposed to interdigital cassetteless imaging plate using computed radiography. The radiographic findings included exostosis, a rough planta surface, osteolysis of the apex of the distal phalanx and widening of the laminar zone between the distal phalanx and the hoof wall. All these findings were confirmed by computed tomography. The hindlimbs (19 digits) showed more changes than the forelimbs (10 digits), particularly in the lateral distal phalanx. The cassetteless computed radiography technique is expected to be an easily applicable method for the distal phalanx rather than a conventional cassette-plate and/or the film-screen cassetteless methods.

Digital radiography for the equine practitioner: basic principles and recent advances

As availability increases and cost decreases, digital radiograph systems become more common in equine practice. Technological advances provide an array of choices for the equine practitioner considering purchase. Two classes of systems are available: computed radiography and flat-panel systems (direct radiography). Image processing encompasses all manipulations performed on an image at acquisition and can have a profound effect on the final digital radiograph. Consideration should be given to the type of display monitor because many options are now available. The type of display monitor and the viewing environment have an effect on interpretation performance.

Investigation into Factors Influencing Fuji S-Value Using an Extremity Phantom

Exposure indices are provided by manufacturers to give an indication of exposure for computed radiography (CR). Although there are recommended ranges for exposure index values for various examinations, they may be affected by a number of other factors in addition to exposure. This study using an extremity phantom found collimation to be the most important factor influencing the S-value for a Fuji CR system. It is therefore essential that collimation is kept as tight as possible without excluding relevant anatomy. CR imaging plates should be processed rapidly after exposure to prevent loss of information stored in the latent image. The reliability of the S-value exposure index as an indicator of exposures can be increased with better understanding of how it works, and by practical application of this knowledge to radiography.

Abdominal computed radiography for the diagnosis of enterolithiasis in horses: 142 cases (2003?2007)

OBJECTIVE

To evaluate the sensitivity and specificity of abdominal computed radiography (CR) for the diagnosis of enterolithiasis in horses and to examine how these parameters are affected by the number and anatomic location of enteroliths and by gas distension of the gastrointestinal tract.

DESIGN

Retrospective case series.

ANIMALS

Horses ? 1 year old that underwent abdominal CR and subsequent exploratory laparotomy or postmortem examination.

PROCEDURES

3 reviewers blinded to signalment, history, clinical signs, and diagnoses separately evaluated abdominal computed radiographs of horses included in the study. Each set of radiographs was evaluated for the presence or absence of enteroliths, the amount of gas distention, and the image quality. Signalment, definitive diagnosis on the basis of findings on exploratory laparotomy or postmortem examination, and the number and location of enteroliths were obtained from medical records.

RESULTS

Of the 142 cases reviewed, 58.4% (83/142) had confirmed enterolithiasis. For the 3 reviewers, overall sensitivity was 85% and specificity was 93%. Sensitivity was lower for small colon enteroliths than for large colon enteroliths (50% and 94.5%, respectively) and was significantly affected by gas distention. Sensitivity was not significantly affected by the number of enteroliths.

CONCLUSIONS AND CLINICAL RELEVANCE

Computed radiography provided high sensitivity and high specificity for the diagnosis of enterolithiasis in horses. Caution should be exercised when the radiographic results are negative, as the sensitivity for small colon enterolithiasis was relatively low and gas distension negatively affected detection of enteroliths. Abdominal CR is indicated as a diagnostic test in horses examined for colic in geographic regions in which enterolithiasis is endemic.

Transitioning to digital radiography

OBJECTIVE

To describe the different forms of digital radiography (DR), image file formats, supporting equipment and services required for DR, storage of digital images, and teleradiology.

BACKGROUND

Purchasing a DR system is a major investment for a veterinary practice. Types of DR systems include computed radiography, charge coupled devices, and direct or indirect DR. Comparison of workflow for analog and DR is presented.

SUMMARY

On the surface, switching to DR involves the purchase of DR acquisition hardware. The X-ray machine, table and grids used in analog radiography are the same for DR. Realistically, a considerable infrastructure supports the image acquisition hardware. This infrastructure includes monitors, computer workstations, a robust computer network and internet connection, a plan for storage and back up of images, and service contracts. Advantages of DR compared with analog radiography include improved image quality (when used properly), ease of use (more forgiving to the errors of radiographic technique), speed of making a complete study (important for critically ill patients), fewer repeat radiographs, less time looking for imaging studies, less physical storage space, and the ability to easily send images for consultation.

CONCLUSIONS

With an understanding of the infrastructure requirements, capabilities and limitations of DR, an informed veterinary practice should be better able to make a sound decision about transitioning to DR.

Comparison between radiological and magnetic resonance imaging lesions in the distal border of the navicular bone with particular reference to distal border fragments and osseous cyst-like lesions

REASONS FOR PERFORMING STUDY

There are no data concerning the accuracy of conventional and computed or digital radiography for evaluation of the equine foot.

OBJECTIVES

To compare conventional film-screen and computed radiography with magnetic resonance imaging (MRI) for detection of distal border fragments of the navicular bone; and to establish which type of fragment was more likely to be detected radiologically.

METHODS

Horses were included if forelimb lameness was localised to the foot and both radiography and high-field MR images had been acquired. Horses were divided into 2 groups based on acquisition of conventional (Group A) or computed (Group B) radiographs. The presence of distal border fragments was recorded. From MR images, distal border fragments were graded based on their size and changes in signal intensity in the adjacent navicular bone. Sensitivity and specificity of conventional and computed radiography for detection of fragments were calculated using MRI as the gold standard. A Chi-squared test was used to test for associations between specific radiological and MRI findings in the distal border of the navicular bone.

RESULTS

In Group A 46 and 18 fragments were identified on MR and radiographic images, respectively; in Group B 45 and 17 fragments were seen. There was no significant difference between computed and conventional radiography. Grades 4 and 5 fragments or large-sized fragments were identified most frequently; low-grade fragments were unlikely to be observed. There was a significant correlation between radiological and MRI abnormalities of the distal border of the navicular bone.

CONCLUSIONS

Conventional and computed radiography had similar, rather low sensitivity for identification of distal border fragments of the navicular bone, but specificity was high. Large-sized and high-grade fragments were most likely to be identified radiologically.

POTENTIAL RELEVANCE

Fragments observed radiologically are likely to be associated with other pathological abnormalities of the distal border of the navicular bone.

Comparison of flat-panel digital to conventional film-screen radiography in detection of experimentally created lesions of the equine third metacarpal bone

Radiographic diagnosis of equine bone disease using digital radiography is prevalent in veterinary practice. However, the diagnostic quality of digital vs. conventional radiography has not been compared systematically. We hypothesized that digital radiography would be superior to film-screen radiography for detection of subtle lesions of the equine third metacarpal bone. Twenty-four third metacarpal bones were collected from horses euthanized for reasons other than orthopedic disease. Bones were dissected free of soft tissue and computed tomography was performed to ensure that no osseous abnormalities were present. Subtle osseous lesions were produced in the dorsal cortex of the third metacarpal bones, and the bones were radiographed in a soft tissue phantom using indirect digital and conventional radiography at standard exposures. Digital radiographs were printed onto film. Three Diplomates of the American College of Veterinary Radiology evaluated the radiographs for the presence or absence of a lesion. Receiver operator characteristic curves were constructed, and the area under these curves were compared to assess the ability of the digital and film-screen radiographic systems to detect lesions. The area under the ROC curves for film-screen and digital radiography were 0.87 and 0.90, respectively (P = 0.59). We concluded that the digital radiographic system was comparable to the film-screen system for detection of subtle lesions of the equine third metacarpal bone.

Digital radiography artifacts

Radiographic artifacts may mimic a clinical feature, impair image quality, or obscure abnormalities. With the development of digital radiography (DR), a new set of artifacts is introduced. Regardless of the technology, the classic technical errors that occur with film screen radiography still occur using DR. Artifacts created using computed radiography, DR, and incorrect image processing are discussed. Methods for correction of the artifacts are presented.