The medical imaging community has embraced Machine Learning (ML) as evidenced by the rapid increase in the number of ML models being developed, but validating and deploying these models in the clinic remains a challenge. The engineering involved in integrating and assessing the efficacy of ML models within the clinical workflow is complex. This paper presents a general-purpose, end-to-end, clinically integrated ML model deployment and validation system implemented at UCSF. Engineering and usability challenges and results from 3 use cases are presented. A generalized validation system based on free, open-source software (OSS) was implemented, connecting clinical imaging modalities, the Picture Archiving and Communication System (PACS), and an ML inference server. ML pipelines were implemented in NVIDIAs Clara Deploy framework with results and clinician feedback stored in a customized XNAT instance, separate from the clinical record but linked from within PACS. Prospective clinical validation studies of 3 ML models were conducted, with data routed from multiple clinical imaging modalities and PACS. Completed validation studies provided expert clinical feedback on model performance and usability, plus system reliability and performance metrics. Clinical validation of ML models entails assessing model performance, impact on clinical infrastructure, robustness, and usability. Study results must be easily accessible to participating clinicians but remain outside the clinical record. Building a system that generalizes and scales across multiple ML models takes the concerted effort of software engineers, clinicians, data scientists, and system administrators, and benefits from the use of modular OSS. The present work provides a template for institutions looking to translate and clinically validate ML models in the clinic, together with required resources and expected challenges.

Adapting ways to functionalize polymer materials is becoming increasingly important to their implementation in translational biomedical sciences. By tuning the mechanical, chemical, and biological qualities of these materials, their applications can be broadened, opening the door for more advanced integration into modern medical techniques. Here, we report on a method to integrate chemical functionalizations into discrete, microscale polymer structures, which are used for tissue engineering applications, for in vivo localization, and three-dimensional manipulation. Iron oxide nanoparticles were incorporated into the polymer matrix using common photolithographic techniques to create stably functional microstructures with magnetic potential. Using magnetic resonance imaging (MRI), we can promote visualization of microstructures contained in small collections, as well as facilitate the manipulation and alignment of microtopographical cues in a realistic tissue environment. Using similar polymer functionalization techniques, fluorine-containing compounds were also embedded in the polymer matrix of photolithographically fabricated microstructures. The incorporation of fluorine-containing compounds enabled highly sensitive and specific detection of microstructures in physiologic settings using fluorine MRI techniques ((19)F MRI). These functionalization strategies will facilitate more reliable noninvasive tracking and characterization of microstructured polymer implants as well as have implications for remote microstructural scaffolding alignment for three-dimensional tissue engineering applications.