RESUMO
Pigeons' unexpected competence in learning to categorize unseen histopathological images has remained an unexplained discovery for almost a decade (Levensonet al2015PLoS One10e0141357). Could it be that knowledge transferred from their bird's-eye views of the earth's surface gleaned during flight contributes to this ability? Employing a simulation-based verification strategy, we recapitulate this biological phenomenon with a machine-learning analog. We model pigeons' visual experience during flight with the self-supervised pre-training of a deep neural network on BirdsEyeViewNet; our large-scale aerial imagery dataset. As an analog of the differential food reinforcement performed in Levensonet al's study 2015PLoS One10e0141357), we apply transfer learning from this pre-trained model to the same Hematoxylin and Eosin (H&E) histopathology and radiology images and tasks that the pigeons were trained and tested on. The study demonstrates that pre-training neural networks with bird's-eye view data results in close agreement with pigeons' performance. These results support transfer learning as a reasonable computational model of pigeon representation learning. This is further validated with six large-scale downstream classification tasks using H&E stained whole slide image datasets representing diverse cancer types.
Assuntos
Columbidae , Neoplasias , Redes Neurais de Computação , Animais , Columbidae/fisiologia , Neoplasias/patologia , Neoplasias/diagnóstico por imagem , Aprendizado de Máquina , Voo Animal/fisiologiaRESUMO
In the past few years COVID-19 posed a huge threat to healthcare systems around the world. One of the first waves of the pandemic hit Northern Italy severely resulting in high casualties and in the near breakdown of primary care. Due to these facts, the Covid CXR Hackathon-Artificial Intelligence for Covid-19 prognosis: aiming at accuracy and explainability challenge had been launched at the beginning of February 2022, releasing a new imaging dataset with additional clinical metadata for each accompanying chest X-ray (CXR). In this article we summarize our techniques at correctly diagnosing chest X-ray images collected upon admission for severity of COVID-19 outcome. In addition to X-ray imagery, clinical metadata was provided and the challenge also aimed at creating an explainable model. We created a best-performing, as well as, an explainable model that makes an effort to map clinical metadata to image features whilst predicting the prognosis. We also did many ablation studies in order to identify crucial parts of the models and the predictive power of each feature in the datasets. We conclude that CXRs at admission do not help the predicting power of the metadata significantly by itself and contain mostly information that is also mutually present in the blood samples and other clinical factors collected at admission.
Assuntos
Inteligência Artificial , COVID-19 , Humanos , COVID-19/diagnóstico por imagem , Metadados , Raios X , HospitalizaçãoRESUMO
Laser-induced damage threshold is a fundamental figure of merit of femtosecond optical components used in large-scale laser systems. We tested a series of ultrafast mirrors featuring high band-gap dielectric materials as well as improved design and coating techniques. In a broad range of the damage test pulse train involving between 10 and 100,000 pulses (40 fs, 800 nm), pure dielectric high reflectors exhibit around 1.5 J/cm2 and hybrid Ag-multilayer mirrors can exhibit well above 1.2 J/cm2 damage threshold. In addition, a reference antireflection coating exceeded 2 J/cm2. Damage threshold dependence on the number of pulses was similar for all optics involved.