Citations

Abstract The prevalence of steatotic liver disease (SLD) is rising globally, presenting a significant public health challenge. While non-contrast computed tomography (CT) scans hold promise for the opportunistic detection of SLD, their full potential has not been systematically explored. Clinical indicators, such as serum data, are crucial for monitoring the progression of SLD. We introduce a novel Multimodal AI for Opportunistic Steatotic Liver Disease Screening (MAOSS), which integrates demographic data, serum tests, conventional CT biomarkers, and deep learning-derived CT image features to enhance model performance and explainability. MAOSS employs an innovative learning strategy, trained on a large-scale dataset (n = 1,783) encompassing both histopathologically-confirmed SLD and radiologically-reported steatosis cases. The model underwent extensive retrospective validation using steatosis grades derived from both histology and MRI-PDFF across internal and external datasets (n = 913), as well as real-world patient data (n = 18,504). It accurately detected mild to severe steatosis (≥ S1) with AUCs ranging from 0.903 to 0.929. Notably, MAOSS significantly improved the overall AUC for radiologists (n = 11) from 0.709 to 0.798 (p < 0.001). Furthermore, MAOSS was applied to optimize the standard clinical pathway for a simulated primary risk screening of SLD patients (n = 1,192), resulting in the identification of 31% more patients at risk of steatohepatitis and liver fibrosis progression, highlighting its potential to enhance SLD detection and management.

Background/Objectives: Stereotactic body radiation therapy (SBRT) for skull base reirradiation is particularly challenging, as patients have already received substantial radiation doses to the region, and nearby normal organs may have approached their tolerance limit from prior treatments. In this study, we reviewed the characteristics and capabilities of four advanced external beam radiation delivery systems and four modern treatment planning systems and evaluated the treatment plan quality of each technique using skull base reirradiation patient cases. Methods: SBRT plans were generated for sixteen skull base reirradiation patients using four modalities: the GK plan for the Elekta Leksell Gamma Knife Perfexion/ICON, the CyberKnife (CK) plan for the Accuray CyberKnife, the intensity-modulated proton therapy (IMPT) plan for the Hitachi ProBeat-FR proton therapy machine, and the volumetric-modulated arc therapy (VMAT) plan for the Varian TrueBeam STx. These plans were evaluated and compared using two novel gradient indices in addition to traditional dosimetry metrics for targets and organs at risk (OARs). The steepest border gradient quantified the percent prescription dose fall-off per millimeter at the boundary between the target and adjacent critical structures. This gradient index highlighted the system’s ability to spare nearby critical OARs. The volume gradient assessed the extent of dose spread outside the target toward the patient’s body. Results: All plans achieved comparable target coverage and conformity, while IMPT and VMAT demonstrated significantly better uniformity. The GK plans exhibited the highest border gradient, up to 20.9%/mm, followed by small-spot-size IMPT plans and CK plans. Additionally, IMPT plans showed the benefit of reduced dose spread in low-dose regions and the lowest maximum and mean doses to the brainstem and carotid artery. Conclusions: The advanced external beam radiotherapy modalities evaluated in this study are well-suited for SBRT in skull base reirradiation, which demands precise targeting of tumors with highly conformal doses and steep dose gradients to protect nearby normal structures.

Purpose: This study compares the performance of small, fine-tuned LLMs with the large original models on two radiation oncology clinical tasks: treatment modality selection and ICD-10 code prediction. Methods: We used data of 403 treatment modality selection cases and 377 ICD-10 code prediction cases. The models used were fine-tuned LLaMA 2 7B and Mistral 7B, as well as the larger LLaMA 3.1 70B and 405B models for comparison. We evaluated the accuracy of all models on these two tasks. Results: Both fine-tuned LLaMA 2 7B and Mistral 7B outperformed LLaMA 3.1 70B and 405B in treatment modality selection task. The fine-tuned LLaMA 2 7B and Mistral 7B models achieved accuracy comparable to the larger models in ICD-10 code prediction. Conclusions: Small models, fine-tuned with radiation oncology data, can achieve performance comparable to-or even surpass-that of larger models.

AbstractPurposeThe time structures of proton spot delivery in proton pencil beam scanning (PBS) radiation therapy are essential in many clinical applications. This study aims to characterize the time structures of proton PBS delivered by both synchrotron and synchrocyclotron accelerators using a non‐invasive technique based on scattered particle tracking.MethodsA pixelated semiconductor detector, AdvaPIX‐Timepix3, with a temporal resolution of 1.56 ns, was employed to measure time of arrival of secondary particles generated by a proton beam. The detector was placed laterally to the high‐flux area of the beam in order to allow for single particle detection and not interfere with the treatment. The detector recorded counts of radiation events, their deposited energy and the timestamp associated with the single events. Individual recorded events and their temporal characteristics were used to analyze beam time structures, including energy layer switch time, magnet switch time, spot switch time, and the scanning speeds in the x and y directions. All the measurements were repeated 30 times on three dates, reducing statistical uncertainty.ResultsThe uncertainty of the measured energy layer switch times, magnet switch time, and the spot switch time were all within 1% of average values. The scanning speeds uncertainties were within 1.5% and are more precise than previously reported results. The measurements also revealed continuous sub‐milliseconds proton spills at a low dose rate for the synchrotron accelerator and radiofrequency pulses at 7 µs and 1 ms repetition time for the synchrocyclotron accelerator.ConclusionThe AdvaPIX‐Timepix3 detector can be used to directly measure and monitor time structures on microseconds scale of the PBS proton beam delivery. This method yielded results with high precision and is completely independent of the machine log files.

Abstract In radiotherapy, 2D orthogonally projected kV images are used for patient alignment when 3D-on-board imaging(OBI) unavailable. But tumor visibility is constrained due to the projection of patient’s anatomy onto a 2D plane, potentially leading to substantial setup errors. In treatment room with 3D-OBI such as cone beam CT(CBCT), the field of view(FOV) of CBCT is limited with unnecessarily high imaging dose, thus unfavorable for pediatric patients. A solution to this dilemma is to reconstruct 3D CT from kV images obtained at the treatment position. Here, we propose a dual-models framework built with hierarchical ViT blocks. Unlike a proof-of-concept approach, our framework considers kV images as the solo input and can synthesize accurate, full-size 3D CT in real time(within milliseconds). We demonstrate the feasibility of the proposed approach on 10 patients with head and neck(H\&N) cancer using image quality(MAE:<45HU), dosimetric accuracy(Gamma passing rate(2%/2mm/10%):>97%) and patient position uncertainty(shift error:<0.4mm). The proposed framework can generate accurate 3D CT faithfully mirroring real-time patient position, thus significantly improving patient setup accuracy, keeping imaging dose minimum, and maintaining treatment veracity.

Optical imaging is an ancient branch of imaging dating back to thousands of years. Radiographic imaging and tomography (RadIT), including the first use of X-rays by Wilhelm Röntgen, and then, γ -rays, energetic charged particles, neutrons, etc. are about 130 years young. The synergies between optical and radiographic imaging can be cast in the framework of these building blocks: Physics, Sources, Detectors, Methods , and Data Science , as described in Appl. Opt. 61 , RDS1 ( 2022 ) APOPAI 0003-6935 10.1364/AO.455628 . Optical imaging has expanded to include three-dimensional (3D) tomography (including holography), due in to part the invention of optical (including infrared) lasers. RadIT are intrinsically 3D because of the penetrating power of ionizing radiation. Both optical imaging and tomography (OIT) and RadIT are evolving into even higher dimensional regimes, such as time-resolved tomography (4D) and temporarily and spectroscopically resolved tomography (4D + ). Further advances in OIT and RadIT will continue to be driven by desires for higher information yield, higher resolutions, and higher probability models with reduced uncertainties. Synergies in quantum physics, laser-driven sources, low-cost detectors, data-driven methods, automated processing of data, and artificially intelligent data acquisition protocols will be beneficial to both branches of imaging in many applications. These topics, along with an overview of the Radiography, Applied Optics, and Data Science virtual feature issue, are discussed here.

Abstract Background Efficient and accurate delineation of organs at risk (OARs) is a critical procedure for treatment planning and dose evaluation. Deep learning‐based auto‐segmentation of OARs has shown promising results and is increasingly being used in radiation therapy. However, existing deep learning‐based auto‐segmentation approaches face two challenges in clinical practice: generalizability and human‐AI interaction. A generalizable and promptable auto‐segmentation model, which segments OARs of multiple disease sites simultaneously and supports on‐the‐fly human‐AI interaction, can significantly enhance the efficiency of radiation therapy treatment planning. Purpose Meta's segment anything model (SAM) was proposed as a generalizable and promptable model for next‐generation natural image segmentation. We further evaluated the performance of SAM in radiotherapy segmentation. Methods Computed tomography (CT) images of clinical cases from four disease sites at our institute were collected: prostate, lung, gastrointestinal, and head & neck. For each case, we selected the OARs important in radiotherapy treatment planning. We then compared both the Dice coefficients and Jaccard indices derived from three distinct methods: manual delineation (ground truth), automatic segmentation using SAM's ’segment anything’ mode, and automatic segmentation using SAM's ‘box prompt’ mode that implements manual interaction via live prompts during segmentation. Results Our results indicate that SAM's segment anything mode can achieve clinically acceptable segmentation results in most OARs with Dice scores higher than 0.7. SAM's box prompt mode further improves Dice scores by 0.1∼0.5. Similar results were observed for Jaccard indices. The results show that SAM performs better for prostate and lung, but worse for gastrointestinal and head & neck. When considering the size of organs and the distinctiveness of their boundaries, SAM shows better performance for large organs with distinct boundaries, such as lung and liver, and worse for smaller organs with less distinct boundaries, like parotid and cochlea. Conclusions Our results demonstrate SAM's robust generalizability with consistent accuracy in automatic segmentation for radiotherapy. Furthermore, the advanced box‐prompt method enables the users to augment auto‐segmentation interactively and dynamically, leading to patient‐specific auto‐segmentation in radiation therapy. SAM's generalizability across different disease sites and different modalities makes it feasible to develop a generic auto‐segmentation model in radiotherapy.

Abstract Purpose . To enhance an in-house graphic-processing-unit accelerated virtual particle (VP)-based Monte Carlo (MC) proton dose engine (VPMC) to model aperture blocks in both dose calculation and optimization for pencil beam scanning proton therapy (PBSPT)-based stereotactic radiosurgery (SRS). Methods and materials . A module to simulate VPs passing through patient-specific aperture blocks was developed and integrated in VPMC based on simulation results of realistic particles (primary protons and their secondaries). To validate the aperture block module, VPMC was first validated by an opensource MC code, MCsquare, in eight water phantom simulations with 3 cm thick brass apertures: four were with aperture openings of 1, 2, 3, and 4 cm without a range shifter, while the other four were with same aperture opening configurations with a range shifter of 45 mm water equivalent thickness. Then, VPMC was benchmarked with MCsquare and RayStation MC for 10 patients with small targets (average volume 8.4 c.c. with range of 0.4–43.3 c.c.). Finally, 3 typical patients were selected for robust optimization with aperture blocks using VPMC. Results . In the water phantoms, 3D gamma passing rate (2%/2 mm/10%) between VPMC and MCsquare was 99.71 ± 0.23%. In the patient geometries, 3D gamma passing rates (3%/2 mm/10%) between VPMC/MCsquare and RayStation MC were 97.79 ± 2.21%/97.78 ± 1.97%, respectively. Meanwhile, the calculation time was drastically decreased from 112.45 ± 114.08 s (MCsquare) to 8.20 ± 6.42 s (VPMC) with the same statistical uncertainties of ~0.5%. The robustly optimized plans met all the dose–volume-constraints (DVCs) for the targets and OARs per our institutional protocols. The mean calculation time for 13 influence matrices in robust optimization by VPMC was 41.6 s and the subsequent on-the-fly ‘trial-and-error’ optimization procedure took only 71.4 s on average for the selected three patients. Conclusion . VPMC has been successfully enhanced to model aperture blocks in dose calculation and optimization for the PBSPT-based SRS.