Comparison of diagnostic accuracy of plain film radiographs between original film and smartphone capture: a pilot study

Diagnostic accuracy and reliability of smartphone captured radiologic images communicated via WhatsApp®

INTRODUCTION

Sending radiographic images as instant messages have become a common means of communication between physicians, aiding in triaging and transfer decision-making in emergencies. While use of technology is increasing, this is not the case for the underserved or rural areas of South Africa with no picture archiving and communications system or advanced hardware in place. In these areas, the medical staffing population have nearly universal access to smartphones and could benefit from the ability to share images quickly and easily with trained radiologists. South African data on diagnostic reliability of smartphone captured radiology images is lacking. The objective of the study was to determine the accuracy and reliability of diagnoses made on radiologic images captured with smartphone compared to radiologic images on picture archiving and communication system(PACS).

METHODS

A cross-sectional study was conducted with radiographs from June 2018 to July 2019 selected from the PACS system at Pelonomi Tertiary Hospital. Images were displayed on PACS computer screen and captured by principal researcher using a smartphone. Five radiology registrars received the images via WhatsApp® and reviewed them on smartphones. After three weeks, registrars viewed images in random order on PACS stations. McNemar's test was used to compare the diagnostic accuracy of smartphone vs PACS and Kappa values calculated for agreement. Reliability was assessed by analysing the results of different registrars and diagnoses separately.

RESULTS

135 X-rays, representative of common emergency conditions, were selected. For all registrars, PACS accuracy was generally higher than smartphone accuracy. The Kappa values all indicated fair to moderate agreement between smartphone and PACS diagnosis.

CONCLUSION

Capturing radiographic images using at least 12-megapixel smartphone and sharing them via WhatsApp® is a reliable method that can be used with a high degree of confidence in emergencies to aid clinical decision making. This method of viewing medical imaging is however not a substitution for images viewed on PACS.

Your mileage may vary: impact of data input method for a deep learning bone age app's predictions

OBJECTIVE

The purpose of this study was to evaluate agreement in predictions made by a bone age prediction application ("app") among three data input methods.

METHODS

The 16Bit Bone Age app is a browser-based deep learning application for predicting bone age on pediatric hand radiographs; recommended data input methods are direct image file upload or smartphone-capture of image. We collected 50 hand radiographs, split equally among 5 bone age groups. Three observers used the 16Bit Bone Age app to assess these images using 3 different data input methods: (1) direct image upload, (2) smartphone photo of image in radiology reading room, and (3) smartphone photo of image in a clinic.

RESULTS

Interobserver agreement was excellent for direct upload (ICC = 1.00) and for photos in reading room (ICC = 0.96) and good for photos in clinic (ICC = 0.82), respectively. Intraobserver agreement for the entire test set across the 3 data input methods was variable with ICCs of 0.95, 0.96, and 0.57 for the 3 observers, respectively.

DISCUSSION

Our findings indicate that different data input methods can result in discordant bone age predictions from the 16Bit Bone Age app. Further study is needed to determine the impact of data input methods, such as smartphone image capture, on deep learning app performance and accuracy.

What Is the Best Way for Patients to Take Photographs of Medical Images (Radiographs, CT, and MRI) Using a Smartphone?

BACKGROUND

Teleradiology has become one of the most important approaches to virtual clinical diagnosis; its importance has only grown during the coronavirus 2019 pandemic. In developing countries, asking patients to take photographs of their images using a smartphone can facilitate the process and help keep its costs down. However, the images taken by patients with smartphones often are of poor quality, and there is no regulation or standard instruction about how to use smartphones to take photographs of medical examination images effectively. These problems limit the use of smartphones in remote diagnosis and treatment.

QUESTIONS/PURPOSES

To formulate a set of guidelines for the most appropriate and effective use of smartphones to capture images (radiographs, CT images, and MR images), and to determine whether these guidelines are more effectively adopted by patients of differing ages and genders.

METHODS

In this prospective study, a set of step-by-step instructions was created with the goal of helping patients take better smartphone photographs of orthopaedic diagnostic images for transfer to telemedicine services. Following the advice of surgeons, experts in smartphone technology, imaging experts, and suggestions from patients, the instructions were modified based on clinical experience and finalized with the goals of simplicity, clarity, and convenience. Potentially eligible patients were older than 18 years, had no cognitive impairment, and used smart phones. Based on that, 256 participants (patients or their relatives and friends) who visited the orthopaedic department of our hospital from June to October 2020 potentially qualified for this study. A total of 11% (29) declined to participate, leaving 89% (227) for analysis here. Their mean age was 36 ± 11 years, 50% were women (113 of 227), and the patient himself/herself represented in 34% (78 of 227) of participants while relatives or friends of patients made up 66% (149 of 227) of the group. In this study, the diagnoses included spinal stenosis (47% [107 of 227]), disc herniation without spinal stenosis (31% [71 of 227]), vertebral fractures (14% [32 of 227]), and other (7% [17 of 227]). Each study participant first took photographs of their original medical images based on their own knowledge of how to use the smartphone camera function; each participant then took pictures of their original images again after receiving our instructional guidance. Three senior spine surgeons (YZ, TQL, TCM) in our hospital analyzed, in a blinded manner, the instructed and uninstructed imaging files based on image clarity (the content of the image is complete, the text information in the image is clearly visible, there is neither reflection nor shadow in the image) and image position (it is not tilted, curled, inverted, or reversed). If either of these conditions was not satisfied, the picture quality was deemed unacceptable; two of three judges' votes determined the outcome. Interobserver reliability with kappa values for the three judges were 0.89 (YZ versus TQL), 0.92 (YZ versus TCM), and 0.90 (TQL versus TCM).

RESULTS

In this study, the overall proportion of smartphone medical images deemed satisfactory increased from 40% (91 of 227) for uninstructed participants to 86% (196 of 227) for instructed participants (risk ratio 2.15 [95% CI 1.82 to 2.55]; p<0.001). The proportion of acceptable-quality images in different age groups improved after instruction, except for in patients aged 51 years or older (3 of 17 uninstructed participants versus 8 of 17 instructed participants; RR 2.67 [95% CI 0.85 to 8.37]; p = 0.07). The proportion of acceptable-quality images in both genders improved after instruction, but there was no difference between the genders.

CONCLUSION

We believe our guidelines for patients who wish to take smartphone photographs of their medical images will decrease image transmission cost and facilitate orthopaedic telemedicine consultations. However, it appears that patients older than 50 years are more likely to have difficulty with this approach, and if so, they may benefit from more hands-on assistance from clinic staff or younger relatives or friends. The degree to which our findings are culture-specific should be verified by other studies in other settings, but on the face of it, there is little reason to believe our findings would not generalize to a reasonable degree. Other studies in more heterogeneous populations should also evaluate factors related to levels of educational attainment and wealth differences, but in the meantime, our findings can give clinical teams an idea of which patients may need a little extra assistance.

LEVEL OF EVIDENCE

Level II, therapeutic study.

Diagnostic concordance between mobile interfaces and conventional workstations for emergency imaging assessment

INTRODUCTION

Mobile devices and software are now available with sufficient computing power, speed and complexity to allow for real-time interpretation of radiology exams. In this paper, we perform a multivariable user study that investigates concordance of image-based diagnoses provided using mobile devices on the one hand and conventional workstations on the other hand.

METHODS

We performed a between-subjects task-analysis using CT, MRI and radiography datasets. Moreover, we investigated the adequacy of the screen size, image quality, usability and the availability of the tools necessary for the analysis. Radiologists, members of several teams, participated in the experiment under real work conditions. A total of 64 studies with 93 main diagnoses were analyzed.

RESULTS

Our results showed that 56 cases were classified with complete concordance (87.69%), 5 cases with almost complete concordance (7.69%) and 1 case (1.56%) with partial concordance. Only 2 studies presented discordance between the reports (3.07%). The main reason to explain the cause of those disagreements was the lack of multiplanar reconstruction tool in the mobile viewer. Screen size and image quality had no direct impact on the mobile diagnosis process.

CONCLUSION

We concluded that for images from emergency modalities, a mobile interface provides accurate interpretation and swift response, which could benefit patients' healthcare.

Digitizing an Analog Radiography Teaching File Under Time Constraint: Trade-Offs in Efficiency and Image Quality

We digitized the radiography teaching file at Black Lion Hospital (Addis Ababa, Ethiopia) during a recent trip, using a standard digital camera and a fluorescent light box. Our goal was to photograph every radiograph in the existing library while optimizing the final image size to the maximum resolution of a high quality tablet computer, preserving the contrast resolution of the radiographs, and minimizing total library file size. A secondary important goal was to minimize the cost and time required to take and process the images. Three workers were able to efficiently remove the radiographs from their storage folders, hang them on the light box, operate the camera, catalog the image, and repack the radiographs back to the storage folder. Zoom, focal length, and film speed were fixed, while aperture and shutter speed were manually adjusted for each image, allowing for efficiency and flexibility in image acquisition. Keeping zoom and focal length fixed, which kept the view box at the same relative position in all of the images acquired during a single photography session, allowed unused space to be batch-cropped, saving considerable time in post-processing, at the expense of final image resolution. We present an analysis of the trade-offs in workflow efficiency and final image quality, and demonstrate that a few people with minimal equipment can efficiently digitize a teaching file library.

Mobile devices and their prospective future role in emergency radiology

Mobile devices, wireless networks and software have significantly evolved since the late 1990s and are now available with sufficient computing power, speed and complexity to allow real-time interpretation of radiology studies. Emergency radiology (ER)'s time-sensitive nature would seem to be an excellent match for study interpretation using mobile devices, allowing the radiologist to read studies anywhere, at any time. While suitable for use by the radiologist outside of the hospital, or clinicians and surgeons at the bedside or in the operating room, these devices do have limitations, and regulatory approval for in-hospital diagnostic use is limited. In the ER setting, we suggest that the best use of mobile devices is to be available to consult directly with patients about their imaging findings and to the clinical team during rounds and at handover. This will bring the radiologist to the clinician and patient, helping us to better understand the patient's presentation, educate both the physician and patient and increase the visibility and value of the radiologist as a member of the clinical care team.