ObjectivesTo assess the recall of a deep learning (DL) method to automatically detect kidney stones composition from digital photographs of stones. Materials and MethodsA total of 63 human kidney stones of varied compositions were obtained from a stone laboratory including calcium oxalate monohydrate (COM), uric acid (UA), magnesium ammonium phosphate hexahydrate (MAPH/struvite), calcium hydrogen phosphate dihydrate (CHPD/brushite), and cystine stones. At least two images of the stones, both surface and inner core, were captured on a digital camera for all stones. A deep convolutional neural network (CNN), ResNet-101 (ResNet, Microsoft), was applied as a multi-class classification model, to each image. This model was assessed using leaveone-out cross-validation with the primary outcome being network prediction recall. ResultsThe composition prediction recall for each composition was as follows: UA 94% (n = 17), COM 90% (n = 21), MAPH/ struvite 86% (n = 7), cystine 75% (n = 4), CHPD/brushite 71% (n = 14). The overall weighted recall of the CNNs composition analysis was 85% for the entire cohort. Specificity and precision for each stone type were as follows: UA (97.83%, 94.12%), COM (97.62%, 95%), struvite (91.84%, 71.43%), cystine (98.31%, 75%), and brushite (96.43%, 75%). ConclusionDeep CNNs can be used to identify kidney stone composition from digital photographs with good recall. Future work is needed to see if DL can be used for detecting stone composition during digital endoscopy. This technology may enable integrated endoscopic and laser systems that automatically provide laser settings based on stone composition recognition with the goal to improve surgical efficiency.

No abstract

Purpose:Black men have the highest incidence and mortality from prostate cancer (PCa) and lower quality of life compared to other U.S. racial groups. Additionally, more Latinx men are diagnosed with advanced disease and fewer receive guideline-concordant care. As many men seek medical information online, high-quality information targeting diverse populations may mitigate disparities. We examined racial/ethnic representation and information quality in online PCa content.Materials and Methods:We retrieved 150 websites and 150 videos about “prostate cancer” using the most widely used search engine (Google) and social network (YouTube). We assessed quality of health information, reading level, perceived race/ethnicity of people featured in the content and discussion of racial/ethnic disparities.Results:Among 81 websites and 127 videos featuring people, 37% and 24% had perceived Black representation, and racial/ethnic disparities were discussed in 27% and 17%, respectively. Among 1,526 people featured, 9% and 1% were perceived as Black and Latinx, respectively. No content with Black or Latinx representation was high quality, understandable, actionable and at the recommended reading level.Conclusions:Black and Latinx adults are underrepresented in online PCa content. Online media have significant potential for public education and combating health disparities. However, most PCa content lacks diversity and is not readily understandable.

Purpose: We performed in vitro studies to assess the relationship of pulse frequency on stone ablation during contact laser lithotripsy and determine if there is a threshold after which its effect on lithotripsy is limited. Methods: BegoStones were fragmented using a Ho:YAG laser (P120 Moses) and a 230 lm fiber at 0.5 J on long pulse (LP) and Moses distance (MD) modes in contact with the stone. The relationship between the number of pulses (1-40 Hz) on stone crater volume was assessed using three-dimensional confocal microscopy and nonlinear-segmented regression. To simulate a painting technique, we assessed fragmentation (mg/second) at 20, 40, and 60 Hz, with the fiber moving at a speed of 1 and 3 mm/second, respectively. High-speed imaging was used to record ablation. Results: When the laser fiber was fixed, after 13.0 (LP) and 15.4 (MD) pulses, greater pulse frequency did not lead to a significant increase in stone crater volume. Fragmentation was greatest at higher frequencies and faster fiber speed. Increasing the frequency from 20 to 60 Hz at 3 mm/second increased fragmentation by 82% and 61% for LP and MD modes, respectively. Using high-speed data, if the laser fiber is moving at 1 mm/second, a hypothetical frequency threshold for ablation was calculated to be 52 and 61.6 Hz for LP and MD modes, respectively. Conclusion: Increasing the fiber speed increases stone ablation when using high frequency settings. When the fiber is fixed there is a threshold after which increasing the pulse frequency leads to minimal gain in ablation. The exact value for threshold when the fiber is moving needs further study. Our study serves to provide insight for parameter selection and safety of laser lithotripsy for dusting technique.

No abstract