Strategies for Implementing Machine Learning Algorithms in the Clinical Practice of Radiology.

Despite recent advancements in machine learning (ML) applications in health care, there have been few benefits and improvements to clinical medicine in the hospital setting. To facilitate clinical adaptation of methods in ML, this review proposes a standardized framework for the step-by-step implementation of artificial intelligence into the clinical practice of radiology that focuses on three key components: problem identification, stakeholder alignment, and pipeline integration. A review of the recent literature and empirical evidence in radiologic imaging applications justifies this approach and offers a discussion on structuring implementation efforts to help other hospital practices leverage ML to improve patient care. Clinical trial registration no. 04242667 © RSNA, 2024 Supplemental material is available for this article.

SynthA1c: Towards Clinically Interpretable Patient Representations for Diabetes Risk Stratification.

Early diagnosis of Type 2 Diabetes Mellitus (T2DM) is crucial to enable timely therapeutic interventions and lifestyle modifications. As the time available for clinical office visits shortens and medical imaging data become more widely available, patient image data could be used to opportunistically identify patients for additional T2DM diagnostic workup by physicians. We investigated whether image-derived phenotypic data could be leveraged in tabular learning classifier models to predict T2DM risk in an automated fashion to flag high-risk patients without the need for additional blood laboratory measurements. In contrast to traditional binary classifiers, we leverage neural networks and decision tree models to represent patient data as 'SynthA1c' latent variables, which mimic blood hemoglobin A1c empirical lab measurements, that achieve sensitivities as high as 87.6%. To evaluate how SynthA1c models may generalize to other patient populations, we introduce a novel generalizable metric that uses vanilla data augmentation techniques to predict model performance on input out-of-domain covariates. We show that image-derived phenotypes and physical examination data together can accurately predict diabetes risk as a means of opportunistic risk stratification enabled by artificial intelligence and medical imaging. Our code is available at https://github.com/allisonjchae/DMT2RiskAssessment.

A Path Towards Clinical Adaptation of Accelerated MRI.

Accelerated MRI reconstructs images of clinical anatomies from sparsely sampled signal data to reduce patient scan times. While recent works have leveraged deep learning to accomplish this task, such approaches have often only been explored in simulated environments where there is no signal corruption or resource limitations. In this work, we explore augmentations to neural network MRI image reconstructors to enhance their clinical relevancy. Namely, we propose a ConvNet model for detecting sources of image artifacts that achieves a classifier F 2 score of 79.1%. We also demonstrate that training reconstructors on MR signal data with variable acceleration factors can improve their average performance during a clinical patient scan by up to 2%. We offer a loss function to overcome catastrophic forgetting when models learn to reconstruct MR images of multiple anatomies and orientations. Finally, we propose a method for using simulated phantom data to pre-train reconstructors in situations with limited clinically acquired datasets and compute capabilities. Our results provide a potential path forward for clinical adaptation of accelerated MRI.

Ultrasound-controllable engineered bacteria for cancer immunotherapy.

Rapid advances in synthetic biology are driving the development of genetically engineered microbes as therapeutic agents for a multitude of human diseases, including cancer. The immunosuppressive microenvironment of solid tumors, in particular, creates a favorable niche for systemically administered bacteria to engraft and release therapeutic payloads. However, such payloads can be harmful if released outside the tumor in healthy tissues where the bacteria also engraft in smaller numbers. To address this limitation, we engineer therapeutic bacteria to be controlled by focused ultrasound, a form of energy that can be applied noninvasively to specific anatomical sites such as solid tumors. This control is provided by a temperature-actuated genetic state switch that produces lasting therapeutic output in response to briefly applied focused ultrasound hyperthermia. Using a combination of rational design and high-throughput screening we optimize the switching circuits of engineered cells and connect their activity to the release of immune checkpoint inhibitors. In a clinically relevant cancer model, ultrasound-activated therapeutic microbes successfully turn on in situ and induce a marked suppression of tumor growth. This technology provides a critical tool for the spatiotemporal targeting of potent bacterial therapeutics in a variety of biological and clinical scenarios.