Computer-aided diagnosis with a convolutional neural network algorithm for automated detection of urinary tract stones on plain X-ray

Abstract

Background Recent increased use of medical images induces further burden of their interpretation for physicians. A plain X-ray is a low-cost examination that has low-dose radiation exposure and high availability, although diagnosing urolithiasis using this method is not always easy. Since the advent of a convolutional neural network via deep learning in the 2000s, computer-aided diagnosis (CAD) has had a great impact on automatic image analysis in the urological field. The objective of our study was to develop a CAD system with deep learning architecture to detect urinary tract stones on a plain X-ray and to evaluate the model’s accuracy. Methods We collected plain X-ray images of 1017 patients with a radio-opaque upper urinary tract stone. X-ray images (n = 827 and 190) were used as the training and test data, respectively. We used a 17-layer Residual Network as a convolutional neural network architecture for patch-wise training. The training data were repeatedly used until the best model accuracy was achieved within 300 runs. The F score, which is a harmonic mean of the sensitivity and positive predictive value (PPV) and represents the balance of the accuracy, was measured to evaluate the model’s accuracy. Results Using deep learning, we developed a CAD model that needed 110 ms to provide an answer for each X-ray image. The best F score was 0.752, and the sensitivity and PPV were 0.872 and 0.662, respectively. When limited to a proximal ureter stone, the sensitivity and PPV were 0.925 and 0.876, respectively, and they were the lowest at mid-ureter. Conclusion CAD of a plain X-ray may be a promising method to detect radio-opaque urinary tract stones with satisfactory sensitivity although the PPV could still be improved. The CAD model detects urinary tract stones quickly and automatically and has the potential to become a helpful screening modality especially for primary care physicians for diagnosing urolithiasis. Further study using a higher volume of data would improve the diagnostic performance of CAD models to detect urinary tract stones on a plain X-ray.

Deep Learning Model for Computer-Aided Diagnosis of Urolithiasis Detection from Kidney–Ureter–Bladder Images

“…The sensitivity, precision, and F1-measure of our method were 0.964, 1, and 0.982 on the testing set, respectively. Another CNN-based deep learning model [ 29 ] trained to detect kidney stones in pre-processed plain film X-ray images was also used for comparison, and the sensitivity, precision, and F1-measure of this model were 0.985, 0.762, and 0.862, respectively, as shown in Table 3 . Therefore, the performance of the proposed method was superior.…”

“…Finally, patches with a size of 100 × 100 pixels were cropped from the pre-processed X-ray plain films. Patches containing a stone were cropped with the stone at the center, whereas patches without a stone were randomly cropped from the pre-processed plain film X-ray images [ 29 ].…”

“…The application of CAD to X-ray examinations has also yielded impressive results. For example, a CNN model trained to diagnose urinary tract stones from plain film X-ray imaging using pre-processed images showed a sensitivity of 89.6% and PPV of 56.9% for kidney stones [ 29 ].…”

Artificial intelligence in endourology: emerging technology for individualized care

“…Others have developed similar CNN and deep learning models to detect urinary stones on preoperative CT with excellent sensitivity (94%), specificity (96%), and accuracy (95%) (Table 2) [12,13]. The feasibility of artificial intelligence-based stone detection on ultrasound and kidney, ureter, bladder radiograph have also been demonstrated, with varying performance (Table 2) [14,15]. Machine learning has been used to further perform more sophisticated image interpretation.…”

CheXRelNet: An Anatomy-Aware Model for Tracking Longitudinal Relationships Between Chest X-Rays

“…arXiv:2208.03873v1 [cs.CV] 8 Aug 2022 can be time-consuming, these challenges contribute to the delays in detecting findings and providing exemplary patient clinical management plans. Though there has been substantial progress in radiology such as disease diagnostics [20,4,18,11], medical image segmentation [14,21,8,19], etc., more complex reasoning tasks remain fairly unexplored. For example, despite significant progress in the application of machine learning in chest radiograph medical diagnosis, detecting longitudinal change between CXRs has attracted limited attention.…”