Automated echocardiographic left ventricular dimension assessment in dogs using artificial intelligence: Development and validation.

BACKGROUND: Artificial intelligence (AI) could improve accuracy and reproducibility of echocardiographic measurements in dogs. HYPOTHESIS: A neural network can be trained to measure echocardiographic left ventricular (LV) linear dimensions in dogs. ANIMALS: Training dataset: 1398 frames from 461 canine echocardiograms from a single specialist center. VALIDATION: 50 additional echocardiograms from the same center. METHODS: Training dataset: a right parasternal 4-chamber long axis frame from each study, labeled by 1 of 18 echocardiographers, marking anterior and posterior points of the septum and free wall. VALIDATION DATASET: End-diastolic and end-systolic frames from 50 studies, annotated twice (blindly) by 13 experts, producing 26 measurements of each site from each frame. The neural network also made these measurements. We quantified its accuracy as the deviation from the expert consensus, using the individual-expert deviation from consensus as context for acceptable variation. The deviation of the AI measurement away from the expert consensus was assessed on each individual frame and compared with the root-mean-square-variation of the individual expert opinions away from that consensus. RESULTS: For the septum in end-diastole, individual expert opinions deviated by 0.12 cm from the consensus, while the AI deviated by 0.11 cm (P = .61). For LVD, the corresponding values were 0.20 cm for experts and 0.13 cm for AI (P = .65); for the free wall, experts 0.20 cm, AI 0.13 cm (P < .01). In end-systole, there were no differences between individual expert and AI performances. CONCLUSIONS AND CLINICAL IMPORTANCE: An artificial intelligence network can be trained to adequately measure linear LV dimensions, with performance indistinguishable from that of experts.

Host specificity of a parasitic fluke: is Posthodiplostomum minimum a centrarchid-infecting generalist or specialist?

Parasite host specificity has important implications for species diversity estimates, food web dynamics, and host shifts. "White grub" is the metacercaria stage of a fluke ( Posthodiplostomum minimum ) that occurs in many fish species, but no attempt has been made to quantify variation in host use by this worm. Here we used 2 approaches to evaluate host specificity within the strain that infects centrarchids ( P. minimum centrarchi). First, we measured parasite loads in 2 centrarchid hosts, bluegill ( Lepomis macrochirus ) and white crappie ( Pomoxis annularis ), from Spring Lake in McDonough County, Illinois. We found that infection levels differed significantly between these hosts. Prevalence in bluegill was 100% and the median intensity was 940 metacercariae, but only 57% of white crappie were infected (median intensity = 4). Site specificity of white grub also differed significantly between the 2 hosts. In bluegills, kidneys were most heavily infected, whereas in white crappies, livers harbored the most worms. We also performed a literature survey of P. minimum prevalence estimates from 14 centrarchid species from other localities. We calculated the mean white grub prevalence for each host species and used this to calculate STD*, a quantitative index of host specificity. STD* was 1.33, significantly closer to the value for a specialist (STD* = 1.00) than a generalist (STD* = 2.00). This reflects the fact that P. minimum prevalence is higher in Lepomis species than it is in centrarchids outside this genus. These data show that P. minimum centrarchi specializes on Lepomis species, but the causes of this specialization are unknown. This worm may be a single species that differs in host use due to ecological or physiological host differences, or it may be a complex of species that vary in host use for similar reasons. Genetic data are required to evaluate these possibilities.