AI co-pilot: content-based image retrieval for the reading of rare diseases in chest CT.

The aim of the study was to evaluate the impact of the newly developed Similar patient search (SPS) Web Service, which supports reading complex lung diseases in computed tomography (CT), on the diagnostic accuracy of residents. SPS is an image-based search engine for pre-diagnosed cases along with related clinical reference content ( https://eref.thieme.de ). The reference database was constructed using 13,658 annotated regions of interest (ROIs) from 621 patients, comprising 69 lung diseases. For validation, 50 CT scans were evaluated by five radiology residents without SPS, and three months later with SPS. The residents could give a maximum of three diagnoses per case. A maximum of 3 points was achieved if the correct diagnosis without any additional diagnoses was provided. The residents achieved an average score of 17.6 ± 5.0 points without SPS. By using SPS, the residents increased their score by 81.8% to 32.0 ± 9.5 points. The improvement of the score per case was highly significant (p = 0.0001). The residents required an average of 205.9 ± 350.6 s per case (21.9% increase) when SPS was used. However, in the second half of the cases, after the residents became more familiar with SPS, this increase dropped to 7%. Residents' average score in reading complex chest CT scans improved by 81.8% when the AI-driven SPS with integrated clinical reference content was used. The increase in time per case due to the use of the SPS was minimal.

bFGF-containing electrospun gelatin scaffolds with controlled nano-architectural features for directed angiogenesis.

Current therapeutic angiogenesis strategies are focused on the development of biologically responsive scaffolds that can deliver multiple angiogenic cytokines and/or cells in ischemic regions. Herein, we report on a novel electrospinning approach to fabricate cytokine-containing nanofibrous scaffolds with tunable architecture to promote angiogenesis. Fiber diameter and uniformity were controlled by varying the concentration of the polymeric (i.e. gelatin) solution, the feed rate, needle to collector distance, and electric field potential between the collector plate and injection needle. Scaffold fiber orientation (random vs. aligned) was achieved by alternating the polarity of two parallel electrodes placed on the collector plate thus dictating fiber deposition patterns. Basic fibroblast growth factor (bFGF) was physically immobilized within the gelatin scaffolds at variable concentrations and human umbilical vein endothelial cells (HUVEC) were seeded on the top of the scaffolds. Cell proliferation and migration was assessed as a function of growth factor loading and scaffold architecture. HUVECs successfully adhered onto gelatin B scaffolds and cell proliferation was directly proportional to the loading concentrations of the growth factor (0-100 bFGF ng/mL). Fiber orientation had a pronounced effect on cell morphology and orientation. Cells were spread along the fibers of the electrospun scaffolds with the aligned orientation and developed a spindle-like morphology parallel to the scaffold's fibers. In contrast, cells seeded onto the scaffolds with random fiber orientation, did not demonstrate any directionality and appeared to have a rounder shape. Capillary formation (i.e. sprouts length and number of sprouts per bead), assessed in a 3-D in vitro angiogenesis assay, was a function of bFGF loading concentration (0 ng, 50 ng and 100 ng per scaffold) for both types of electrospun scaffolds (i.e. with aligned or random fiber orientation).