Abstract: In a method for enhancing localized delivery of a diagnostic or therapeutic agent using focused ultrasound (FUS), ultrasound-controllable drug carriers are administered into a blood vessel. Each drug carrier comprises an ultrasound-sensitive microbubble loaded with the diagnostic or therapeutic agent. The drug carriers are aggregated inside the vessel both along a radial direction and a longitudinal direction by application of an aggregation FUS sequence. Subsequently the diagnostic or therapeutic agent is released from the drug carriers by application of an uncaging FUS sequence. The aggregation and uncaging sequences are applied using FUS below a threshold power level such that harmful cavitation is avoided, as evidenced by the absence of broadband emissions and preferably non-integer harmonics from an emission spectrum of the drug carriers. Thereby damage to the vasculature by the FUS sequence is avoided.

Abstract: Systems, methods, and machine-readable instructions stored on machine-readable media are disclosed for analyzing an image for vulnerabilities. A repository is provided to a development stage of a development pipeline. An image associated with the repository is built. A list of dependencies and versions of the dependencies used in the building of the image is identified. The image is analyzed for vulnerabilities based on the identified list of dependences and the versions of the dependencies used in the building of the image. A report is provided based on the analysis.

Abstract: A processing device can establish a machine learning model to produce software dependency recommendations. The model can be periodically retrained to update its knowledge of available dependencies. The software dependencies can be incorporated into software by developers who receive the selection or automatically by an intelligent software development platform. A processing device can train the model by assembling sparse user data based on feedback corresponding to software dependencies to produce a vector of preferences for each user. The processing device can also generate a latent vector of attributes for each software dependency. The processing device can then apply matrix factorization to the vectors to produce a behavior matrix that is used to train the machine learning model.

Abstract: A processing device can establish a machine learning model to produce software dependency recommendations. The model can be periodically retrained to update its knowledge of available dependencies. The software dependencies can be incorporated into software by developers who receive the selection or automatically by an intelligent software development platform. A processing device can train the model by assembling sparse user data based on feedback corresponding to software dependencies to produce a vector of preferences for each user. The processing device can also generate a latent vector of attributes for each software dependency. The processing device can then apply matrix factorization to the vectors to produce a behavior matrix that is used to train the machine learning model.

Abstract: Systems, methods, and machine-readable instructions stored on machine-readable media are disclosed for analyzing an image for vulnerabilities. A repository is provided to a development stage of a development pipeline. An image associated with the repository is built. A list of dependencies and versions of the dependencies used in the building of the image is identified. The image is analyzed for vulnerabilities based on the identified list of dependences and the versions of the dependencies used in the building of the image. A report is provided based on the analysis.