Inverse radon transform with deep learning: an application in cardiac motion correction.

Objective. This paper addresses performing inverse radon transform (IRT) with artificial neural network (ANN) or deep learning, simultaneously with cardiac motion correction (MC). The suggested application domain is cardiac image reconstruction in emission or transmission tomography where IRT is relevant. Our main contribution is in proposing an ANN architecture that is particularly suitable for this purpose.Approach. We validate our approach with two types of datasets. First, we use an abstract object that looks like a heart to simulate motion-blurred radon transform. With the known ground truth in hand, we then train our proposed ANN architecture and validate its effectiveness in MC. Second, we used human cardiac gated datasets for training and validation of our approach. The gating mechanism bins data over time using the electro-cardiogram (ECG) signals for cardiac motion correction.Main results. We have shown that trained ANNs can perform motion-corrected image reconstruction directly from a motion-corrupted sinogram. We have compared our model against two other known ANN-based approaches.Significance. Our method paves the way for eliminating any need for hardware gating in medical imaging.

Heavy-chain CDR3-engineered B cells facilitate in vivo evaluation of HIV-1 vaccine candidates.

V2-glycan/apex broadly neutralizing antibodies (bnAbs) recognize a closed quaternary epitope of the HIV-1 envelope glycoprotein (Env). This closed structure is necessary to elicit apex antibodies and useful to guide the maturation of other bnAb classes. To compare antigens designed to maintain this conformation, we evaluated apex-specific responses in mice engrafted with a diverse repertoire of B cells expressing the HCDR3 of the apex bnAb VRC26.25. Engineered B cells affinity matured, guiding the improvement of VRC26.25 itself. We found that soluble Env (SOSIP) variants differed significantly in their ability to raise anti-apex responses. A transmembrane SOSIP (SOSIP-TM) delivered as an mRNA-lipid nanoparticle elicited more potent neutralizing responses than multimerized SOSIP proteins. Importantly, SOSIP-TM elicited neutralizing sera from B cells engineered with the predicted VRC26.25-HCDR3 progenitor, which also affinity matured. Our data show that HCDR3-edited B cells facilitate efficient in vivo comparisons of Env antigens and highlight the potential of an HCDR3-focused vaccine approach.