Automatic classification of DMSA scans using an artificial neural network

Differentiation between normal and abnormal kidneys using 99mTc-DMSA SPECT with deep learning in paediatric patients

AIM

To investigate the feasibility of using deep learning (DL) to differentiate normal from abnormal (or scarred) kidneys using technetium-99m dimercaptosuccinic acid (99mTc-DMSA) single-photon-emission computed tomography (SPECT) in paediatric patients.

MATERIAL AND METHODS

Three hundred and one 99mTc-DMSA renal SPECT examinations were reviewed retrospectively. The 301 patients were split randomly into 261, 20, and 20 for training, validation, and testing data, respectively. The DL model was trained using three-dimensional (3D) SPECT images, two-dimensional (2D) maximum intensity projections (MIPs), and 2.5-dimensional (2.5D) MIPs (i.e., transverse, sagittal, and coronal views). Each DL model was trained to determine renal SPECT images into either normal or abnormal. Consensus reading results by two nuclear medicine physicians served as the reference standard.

RESULTS

The DL model trained by 2.5D MIPs outperformed that trained by either 3D SPECT images or 2D MIPs. The accuracy, sensitivity, and specificity of the 2.5D model for the differentiation between normal and abnormal kidneys were 92.5%, 90% and 95%, respectively.

CONCLUSION

The experimental results suggest that DL has the potential to differentiate normal from abnormal kidneys in children using 99mTc-DMSA SPECT imaging.

Prediction of Recurrent Urinary Tract Infection in Paediatric Patients by Deep Learning Analysis of 99mTc-DMSA Renal Scan

Purpose: Tc-99m dimercaptosuccinic acid (^99mTc-DMSA) renal scan is an important tool for the assessment of childhood urinary tract infection (UTI), vesicoureteral reflux (VUR), and renal scarring. We evaluated whether a deep learning (DL) analysis of ^99mTc-DMSA renal scans could predict the recurrence of UTI better than conventional clinical factors. Methods: the subjects were 180 paediatric patients diagnosed with UTI, who underwent immediate post-therapeutic ^99mTc-DMSA renal scans. The primary outcome was the recurrence of UTI during the follow-up period. For the DL analysis, a convolutional neural network (CNN) model was used. Age, sex, the presence of VUR, the presence of cortical defects on the ^99mTc-DMSA renal scan, split renal function (SRF), and DL prediction results were used as independent factors for predicting recurrent UTI. The diagnostic accuracy for predicting recurrent UTI was statistically compared between independent factors. Results: The sensitivity, specificity and accuracy for predicting recurrent UTI were 44.4%, 88.9%, and 82.2% by the presence of VUR; 44.4%, 76.5%, and 71.7% by the presence of cortical defect; 74.1%, 80.4%, and 79.4% by SRF (optimal cut-off = 45.93%); and 70.4%, 94.8%, and 91.1% by the DL prediction results. There were no significant differences in sensitivity between all independent factors (p > 0.05, for all). The specificity and accuracy of the DL prediction results were significantly higher than those of the other factors. Conclusion: DL analysis of ^99mTc-DMSA renal scans may be useful for predicting recurrent UTI in paediatric patients. It is an efficient supportive tool to predict poor prognosis without visually demonstrable cortical defects in ^99mTc-DMSA renal scans.

A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis

BACKGROUND

Deep learning offers considerable promise for medical diagnostics. We aimed to evaluate the diagnostic accuracy of deep learning algorithms versus health-care professionals in classifying diseases using medical imaging.

METHODS

In this systematic review and meta-analysis, we searched Ovid-MEDLINE, Embase, Science Citation Index, and Conference Proceedings Citation Index for studies published from Jan 1, 2012, to June 6, 2019. Studies comparing the diagnostic performance of deep learning models and health-care professionals based on medical imaging, for any disease, were included. We excluded studies that used medical waveform data graphics material or investigated the accuracy of image segmentation rather than disease classification. We extracted binary diagnostic accuracy data and constructed contingency tables to derive the outcomes of interest: sensitivity and specificity. Studies undertaking an out-of-sample external validation were included in a meta-analysis, using a unified hierarchical model. This study is registered with PROSPERO, CRD42018091176.

FINDINGS

Our search identified 31 587 studies, of which 82 (describing 147 patient cohorts) were included. 69 studies provided enough data to construct contingency tables, enabling calculation of test accuracy, with sensitivity ranging from 9·7% to 100·0% (mean 79·1%, SD 0·2) and specificity ranging from 38·9% to 100·0% (mean 88·3%, SD 0·1). An out-of-sample external validation was done in 25 studies, of which 14 made the comparison between deep learning models and health-care professionals in the same sample. Comparison of the performance between health-care professionals in these 14 studies, when restricting the analysis to the contingency table for each study reporting the highest accuracy, found a pooled sensitivity of 87·0% (95% CI 83·0-90·2) for deep learning models and 86·4% (79·9-91·0) for health-care professionals, and a pooled specificity of 92·5% (95% CI 85·1-96·4) for deep learning models and 90·5% (80·6-95·7) for health-care professionals.

INTERPRETATION

Our review found the diagnostic performance of deep learning models to be equivalent to that of health-care professionals. However, a major finding of the review is that few studies presented externally validated results or compared the performance of deep learning models and health-care professionals using the same sample. Additionally, poor reporting is prevalent in deep learning studies, which limits reliable interpretation of the reported diagnostic accuracy. New reporting standards that address specific challenges of deep learning could improve future studies, enabling greater confidence in the results of future evaluations of this promising technology.

FUNDING

None.