Coarse Race and Ethnicity Labels Mask Granular Underdiagnosis Disparities in Deep Learning Models for Chest Radiograph Diagnosis.

See also the editorial by Nikolic in this issue.

Systematic Review of Radiology Residency Artificial Intelligence Curricula: Preparing Future Radiologists for the Artificial Intelligence Era.

OBJECTIVE: Although educating radiology trainees about artificial intelligence (AI) has become increasingly emphasized, the types of AI educational curricula are not well understood. We performed a systematic review of original studies describing curricula used to teach AI concepts and practical applications for radiology residents and fellows. MATERIALS AND METHODS: We performed a PubMed search for original studies published as of July 22, 2022, describing AI curricula geared toward radiology residents or fellows. Studies meeting inclusion criteria were evaluated for curricula design, implementation details, and outcomes. Descriptive statistics were used to summarize these curricula. RESULTS: Five studies were included describing an AI curriculum, all geared toward radiology residents. All five curricula were led by radiologists, mostly by individual academic radiology departments (4; 80%) with one led by the ACR Resident and Fellow Section. Curricula design included didactic sessions (5; 100%), assigned readings (4; 80%), hands-on learning (3; 60%), and journal clubs (3; 60%); only one had individualized learning plans. All four studies that evaluated the impact of the curricula on participants' knowledge or attitudes showed positive effects. DISCUSSION: Amid increasing recognition of the importance of AI education for radiologists-in-training, several AI curricula for radiology residents have been implemented. Although curricula designs varied and it is unclear if one type is superior, they have had a positive impact on residents' knowledge and attitudes toward AI. As AI becomes increasingly adopted in radiology, these curricula serve as models for other departments and programs to develop AI educational initiatives to prepare the next generation of radiologists for the AI era.

Different Strategies Affect Enzyme Packaging into Bacterial Outer Membrane Vesicles.

All Gram-negative bacteria are believed to produce outer membrane vesicles (OMVs), proteoliposomes shed from the outermost membrane. We previously separately engineered E. coli to produce and package two organophosphate (OP) hydrolyzing enzymes, phosphotriesterase (PTE) and diisopropylfluorophosphatase (DFPase), into secreted OMVs. From this work, we realized a need to thoroughly compare multiple packaging strategies to elicit design rules for this process, focused on (1) membrane anchors or periplasm-directing proteins (herein "anchors/directors") and (2) the linkers connecting these to the cargo enzyme; both may affect enzyme cargo activity. Herein, we assessed six anchors/directors to load PTE and DFPase into OMVs: four membrane anchors, namely, lipopeptide Lpp', SlyB, SLP, and OmpA, and two periplasm-directing proteins, namely, maltose-binding protein (MBP) and BtuF. To test the effect of linker length and rigidity, four different linkers were compared using the anchor Lpp'. Our results showed that PTE and DFPase were packaged with most anchors/directors to different degrees. For the Lpp' anchor, increased packaging and activity corresponded to increased linker length. Our findings demonstrate that the selection of anchors/directors and linkers can greatly influence the packaging and bioactivity of enzymes loaded into OMVs, and these findings have the potential to be utilized for packaging other enzymes into OMVs.