New AI Framework Rapidly Converts Dose Plans to Deliverable Proton Spot Maps for Prostate Cancer Treatment
Researchers have developed GenSpot, a two-stage deep learning framework that automatically converts CT scans and dose distributions into machine-deliverable proton spot maps for prostate stereotactic body radiation therapy (SBRT). The system uses a physics-informed representation and a 3D neural network architecture trained on over 1,000 treatment fields from 259 patients. If validated more broadly, the approach could accelerate automated proton therapy planning and adaptive replanning workflows.
GenSpot is a two-stage computational framework designed to bridge a key gap in pencil beam scanning (PBS) proton therapy: the difficulty of converting predicted 3D dose distributions into clinically deliverable proton spot maps (PSMs). The first stage employs a 3D SwinUNETR neural network to predict a physics-informed projected proton spot map (PrPSM) from CT and dose inputs, aligning spot data with the CT/dose grid using water equivalent thickness and percent depth dose (PDD) information. The second stage reconstructs field-specific PSMs via column-wise nonnegative Lasso regression using precomputed PDD curves. Trained and tested on 1,036 fields from 259 prostate SBRT plans, GenSpot achieved a Monte Carlo dose mean absolute error of 0.07 ± 0.03 Gy in non-zero dose regions and gamma passing rates of 0.90 at the field level and 0.97 at the plan level. Composite dose-volume histogram differences were within 1 Gy for targets and organs at risk, though a modest high-dose increase was observed in the clinical target volume. Critically, the full prediction and reconstruction pipeline averaged just 0.02 seconds and 2.1 seconds per field respectively, suggesting strong potential for real-time adaptive replanning applications. The authors note that broader multi-institutional validation is needed before clinical deployment.
What's missing
The study is limited to a single institution and a single disease site (prostate), so generalizability to other cancer types, anatomical sites, or treatment machines is unknown. Long-term clinical outcomes or dosimetric consequences of the modest CTV high-dose increase observed are not assessed.
What different sources said
- arXiv physicsCenter
A Two-Stage Framework for Fast Proton Spot Map Generation in Pencil Beam Scanning Prostate SBRT Planning
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.