Deep Learning Detection of Aneurysm Clips for Magnetic Resonance Imaging Safety.

Flagging the presence of metal devices before a head MRI scan is essential to allow appropriate safety checks. There is an unmet need for an automated system which can flag aneurysm clips prior to MRI appointments. We assess the accuracy with which a machine learning model can classify the presence or absence of an aneurysm clip on CT images. A total of 280 CT head scans were collected, 140 with aneurysm clips visible and 140 without. The data were used to retrain a pre-trained image classification neural network to classify CT localizer images. Models were developed using fivefold cross-validation and then tested on a holdout test set. A mean sensitivity of 100% and a mean accuracy of 82% were achieved. Predictions were explained using SHapley Additive exPlanations (SHAP), which highlighted that appropriate regions of interest were informing the models. Models were also trained from scratch to classify three-dimensional CT head scans. These did not exceed the sensitivity of the localizer models. This work illustrates an application of computer vision image classification to enhance current processes and improve patient safety.

Neural Network Detection of Pacemakers for MRI Safety.

Flagging the presence of cardiac devices such as pacemakers before an MRI scan is essential to allow appropriate safety checks. We assess the accuracy with which a machine learning model can classify the presence or absence of a pacemaker on pre-existing chest radiographs. A total of 7973 chest radiographs were collected, 3996 with pacemakers visible and 3977 without. Images were identified from information available on the radiology information system (RIS) and correlated with report text. Manual review of images by two board certified radiologists was performed to ensure correct labeling. The data set was divided into training, validation, and a hold-back test set. The data were used to retrain a pre-trained image classification neural network. Final model performance was assessed on the test set. Accuracy of 99.67% on the test set was achieved. Re-testing the final model on the full training and validation data revealed a few additional misclassified examples which are further analyzed. Neural network image classification could be used to screen for the presence of cardiac devices, in addition to current safety processes, providing notification of device presence in advance of safety questionnaires. Computational power to run the model is low. Further work on misclassified examples could improve accuracy on edge cases. The focus of many healthcare applications of computer vision techniques has been for diagnosis and guiding management. This work illustrates an application of computer vision image classification to enhance current processes and improve patient safety.

Artificial intelligence in the diagnosis of Parkinson's disease from ioflupane-123 single-photon emission computed tomography dopamine transporter scans using transfer learning.

OBJECTIVE: The objective of this study was to identify the extent to which artificial intelligence could be used in the diagnosis of Parkinson's disease from ioflupane-123 (¹²³I) single-photon emission computed tomography (SPECT) dopamine transporter scans using transfer learning. MATERIALS AND METHODS: A data set of 54 normal and 54 abnormal ¹²³I SPECT scans was amplified 44-fold using a process of image augmentation. This resulted in a training set of 2376 normal and 2376 abnormal images. This was used to retrain the top layer of the Inception v3 network. The resulting neural network functioned as a classifier for new ¹²³I SPECT scans as either normal or abnormal. A completely separate set of 45 ¹²³I SPECT scans were used for final testing of the network. RESULTS: The area under the receiver-operator curve in final testing was 0.87. This corresponded to a test sensitivity of 96.3%, a specificity of 66.7%, a positive predictive value of 81.3% and a negative predictive value of 92.3%, using an optimum diagnostic threshold. CONCLUSION: This study has provided proof of concept for the use of transfer learning, from convolutional neural networks pretrained on nonmedical images, for the interpretation of ¹²³I SPECT scans. This has been shown to be possible in this study even with a very small sample size. This technique is likely to be applicable to many areas of diagnostic imaging.

Pimecrolimus cream 1%: a potential new treatment for chronic hand dermatitis.

A multicenter, randomized, vehicle-controlled, 3-week study was conducted in patients with chronic hand dermatitis (HD) of various etiologies and locations to identify subgroups particularly responsive to twice-daily application of pimecrolimus cream 1% with overnight occlusion. A total of 294 patients were randomized to the study. By the final visit on day 22, there was a trend toward greater clearance in patients who received pimecrolimus than in those treated with vehicle cream. An analysis of treatment success by various stratification factors was performed, and it was found that palmar involvement had notable impact on response (P = .033). Patients in the pimecrolimus group continued to improve throughout the study; however, in the vehicle group, improvement plateaued after 15 days. Pimecrolimus was well tolerated, with a low rate of application-site reactions such as burning. Pimecrolimus cream 1%, when used twice daily with overnight occlusion, may be of benefit in the management of chronic HD.

Safety and efficacy of nonsteroid pimecrolimus cream 1% in the treatment of atopic dermatitis in infants.

OBJECTIVE: The safety and efficacy of a 1% cream formulation of pimecrolimus, a selective, nonsteroid immunomodulator, was studied in infants with atopic dermatitis (AD). METHODS: During a 6-week double-blind phase, 186 infants with mild/moderate AD were randomly assigned to twice-daily pimecrolimus cream 1% or vehicle. All patients were subsequently treated with open-label pimecrolimus for 20 weeks. RESULTS: At the end of the double-blind phase, 54.5% and 23.8% of patients in the pimecrolimus and vehicle groups, respectively, were clear or almost clear of AD (P <.001). Similar improvements were observed in the Eczema Area and Severity Index, pruritus assessment, and the care giver's assessment. By the first return visit, 69.9% and 36.5% of pimecrolimus and vehicle-treated patients, respectively, achieved absent or mild pruritus. Efficacy during the double-blind phase was maintained throughout the open-label phase. Vehicle-treated patients transferring to open-label pimecrolimus rapidly achieved disease control comparable to those receiving continuous pimecrolimus. There were no significant differences between groups in application site reactions or skin infections. Most adverse events were mild or moderate and unrelated to treatment. CONCLUSIONS: Pimecrolimus was safe in infants with AD, with rapid and sustained efficacy. Pimecrolimus holds promise as a valuable new treatment option for the youngest patients with AD.

Long-term management of atopic dermatitis in infants with topical pimecrolimus, a nonsteroid anti-inflammatory drug.

BACKGROUND: Pimecrolimus cream 1% (Elidel, SDZ ASM 981), a nonsteroid selective inhibitor of inflammatory cytokines, is effective in the treatment of atopic dermatitis (AD). In this study we compared early intervention with pimecrolimus cream with treatment with a vehicle control. OBJECTIVE: The purpose of this investigation was to assess whether early treatment in infants of AD signs/symptoms with pimecrolimus could influence long-term outcome by preventing disease flares. METHODS: In this 1-year, double-blind controlled study, 251 infants aged 3 to 23 months with AD were randomized 4:1 to a pimecrolimus-based regimen (n = 204) or a conventional treatment regimen (n = 47). Both groups used emollients for dry skin. Early AD signs and symptoms were treated either with pimecrolimus cream to prevent flares or, in the control group, with vehicle. Vehicle was used to maintain blinding conditions. In the event of flares, moderately potent corticosteroid was permitted in both groups. The primary efficacy end point was the incidence of flares at 6 months. RESULTS: Pimecrolimus significantly reduced the incidence of flares compared with control treatment (P <.001), with 67.6% versus 30.4% of patients completing 6 months with no flare and 56.9% versus 28.3% completing 12 months with no flare. Overall corticosteroid use was substantially lower in the pimecrolimus group: 63.7% versus 34.8% of patients did not use corticosteroids at all during the study. Pimecrolimus was also more effective than control treatment in the long-term control of pruritus and the signs of AD. There were no clinically significant differences in incidence of adverse events between the 2 treatment groups. CONCLUSIONS: Treatment with pimecrolimus of early signs and symptoms significantly modified the disease course in infants by reducing the incidence of flares and improving overall control of AD. Pimecrolimus was safe and well tolerated.