Connectome, the complete wiring diagram of the nervous system of an organism, is the biological substrate of the mind. While biological neural networks are crucial to the understanding of neural computation mechanisms, recent artificial neural networks (ANNs) have been developed independently from the study of real neural networks. Computational scientists are searching for various ANN architectures to improve machine learning since the architectures are associated with the accuracy of ANNs. A recent study used the hermaphrodite Caenorhabditis elegans (C. elegans) connectome for image classification tasks, where the edge directions were changed to construct a directed acyclic graph (DAG). In this study, we used the whole-animal connectomes of C. elegans hermaphrodite and male to construct a DAG that preserves the chief information flow in the connectomes and trained them for image classification of MNIST and fashion-MNIST datasets. The connectome-inspired neural networks exhibited over 99.5% and 92.6% of accuracy for MNIST and fashion-MNIST datasets, respectively, which increased from the previous study. Together, we conclude that realistic biological neural networks provide the basis of a plausible ANN architecture. This study suggests that biological networks can provide new inspiration to improve artificial intelligences (AIs).

Objective: The diagnostic accuracy of novice residents in evaluating the scrotal pathology by point-of-care (POC) ultrasonography(US) was compared with that by the conventional US to determine the level of experience required toachieve competency. Methods: Three novice residents underwent a one-day training course on identifying scrotal pathologies using POC US.They performed POC US on patients with an acute scrotum to identify five pathological findings. The diagnosis was confirmedby conventional scrotal US. The sensitivity and specificity of POC US by novice residents were calculated, and thechanges in sensitivity and specificity over time were observed. Results: Sixty-two patients were included; the overall sensitivity and specificity were 76.7% (95% confidence interval [CI],61.3%-88.2%) and 78.9% (95% CI, 54.4%-93.9%), respectively. Decreased blood flow in the testicle showed very goodspecificity (100%; 95% CI, 93.8%-100.0%). The sensitivity and accuracy were variable at first 18 scans of each resident,but increased after 18 scans and were maintained over time. Conclusion Although the diagnostic accuracy of novice residents in evaluating the scrotal pathology using POC US wasvariable at first, the accuracy improved over time, especially after 18 scans of each resident. Nevertheless, larger, longtermresearch is needed to confirm the results of this study.