搜索结果：Skeletal radiology

LLM based copilot assistants are useful in everyday tasks. There is a proliferation in the exploration of AI assistant use cases to support radiology workflows in a reliable manner. In this work, we present RadPhi-3, a Small Language Model instruction tuned from Phi-3-mini-4k-instruct with 3.8B parameters to assist with various tasks in radiology workflows. While impression summary generation has been the primary task which has been explored in prior works w.r.t radiology reports of Chest X-rays, we also explore other useful tasks like change summary generation comparing the current radiology report and its prior report, section extraction from radiology reports, tagging the reports with various pathologies and tubes, lines or devices present in them etc. In-addition, instruction tuning RadPhi-3 involved learning from a credible knowledge source used by radiologists, Radiopaedia.org. RadPhi-3 can be used both to give reliable answers for radiology related queries as well as perform useful tasks related to radiology reports. RadPhi-3 achieves SOTA results on the RaLEs radiology report generation benchmark.

Skeletal reaction models are derived for a four-component gasoline surrogate model via an instantaneous local sensitivity analysis technique. The sensitivities of the species mass fractions and the temperature with respect to the reaction rates are estimated by a reduced-order modeling (ROM) methodology. Termed "implicit time-dependent basis CUR (implicit TDB-CUR)," this methodology is based on the CUR matrix decomposition and incorporates implicit time integration for evolving the bases. The estimated sensitivities are subsequently analyzed to develop skeletal reaction models with a fully automated procedure. The 1389-species gasoline surrogate model developed at Lawrence Livermore National Laboratory (LLNL) is selected as the detailed kinetics model. The skeletal reduction procedure is applied to this model in a zero-dimensional constant-pressure reactor over a wide range of initial conditions. The performances of the resulting skeletal models are appraised by comparison against the results via the LLNL detailed model, and also predictions via other skeletal models. Two new skeletal models are developed consisting of 679 and 494 species, respectively. The first is an alternative

Skeletal editing enables precise structural modifications of molecules at late stages of a synthetic sequence, with applications in drug discovery and materials science. We recently demonstrated skeletal editing on the single-molecule scale. Voltage pulses applied by the tip of a scanning probe microscope to an oxygen-containing seven-membered heterocycle led to both oxygen deletion and ring-contraction rearrangement reactions. An open question is whether selective skeletal editing of a heterocyclic core can be achieved by an appropriate choice of the heteroatom. Here, we show that tip-induced reactions of an analogous sulfur-containing seven-membered ring results in sulfur deletion in virtually all cases. Our results demonstrate that the combination of tip-induced chemistry and heteroatom selection in the molecular design is a powerful strategy for single-molecule skeletal editing, with the potential to enable diverse structural transformations of heterocyclic frameworks.

Skeletal polyhedra are discrete connected structures consisting of finite (planar or skew) or infinite (linear, planar, or spatial) polygons as faces, with two faces on each edge and a circular vertex figure at each vertex. The present paper describes the blueprint for the snub construction and shows that it can be applied to both regular and chiral skeletal polyhedra in ordinary space. The resulting skeletal snub polyhedra are vertex-transitive and highly locally symmetric. Their properties - from a combinatorial, topological, and geometric perspective - are described and illustrated on some particularly interesting examples. We examine when the construction yields uniform skeletal polyhedra and discuss the completeness of our list of generated structures.

Small Language Models (SLMs) have shown remarkable performance in general domain language understanding, reasoning and coding tasks, but their capabilities in the medical domain, particularly concerning radiology text, is less explored. In this study, we investigate the application of SLMs for general radiology knowledge specifically question answering related to understanding of symptoms, radiological appearances of findings, differential diagnosis, assessing prognosis, and suggesting treatments w.r.t diseases pertaining to different organ systems. Additionally, we explore the utility of SLMs in handling text-related tasks with respect to radiology reports within AI-driven radiology workflows. We fine-tune Phi-2, a SLM with 2.7 billion parameters using high-quality educational content from Radiopaedia, a collaborative online radiology resource. The resulting language model, RadPhi-2-Base, exhibits the ability to address general radiology queries across various systems (e.g., chest, cardiac). Furthermore, we investigate Phi-2 for instruction tuning, enabling it to perform specific tasks. By fine-tuning Phi-2 on both general domain tasks and radiology-specific tasks related to chest

This paper presents a data-driven approach, referred to as Quantized Skeletal Learning (QSL), for generating skeletal mechanisms. The approach has two key components: (1) a weight vector that can be used to eliminate relatively unimportant species and reactions, and (2) an end-to-end differentiable program whose loss-function gradients, with respect to the weight vector, can be used to adjust those weights. To promote sparsity in the weight vector -- and to reduce the influence of certain reactions or species to zero -- an $l_1$-regularized objective is employed alongside the standard mean squared error loss, thus removing the least important components. The proposed QSL approach is validated by generating skeletal mechanisms for methane and ethylene based on the GRI 3.0 and USC II mechanisms, respectively, demonstrating effectiveness in deriving skeletal mechanisms with various levels of fidelity. Two variants of QSL, designated as QSL-R and QSL-S, are tested; these focus on eliminating reactions and species, respectively. Analysis of ignition delay times and species mass fractions demonstrate QSL's capabilities to reliably and efficiently extract data-driven skeletal mechanisms o

Due to their tunable material properties, sorptive materials have a wide range of applications in energy storage, water treatment, carbon capture, analytical chemistry, and more. One crucial factor in determining the effectiveness of such materials is their skeletal density, or "true density" because it is often used to calculate key metrics, such as storage capacities. In this paper, we present skeletal density measurements through helium pycnometry for several types of adsorbent carbon materials derived from either corncob, sawdust, coffee grounds, polyvinylidene chloride (PVDC), graphitic carbon nitride (GCN), or metal organic frameworks (MOFs). The measured skeletal density of sawdust-based activated carbon was 2.02 +/- 0.05 g/$cm^{ 3}$. The measured skeletal density of coffee-based activated carbon was 2.23 +/- 0.06 $cm^{ 3}$. We also expound upon the impact that skeletal density has upon hydrogen excess adsorption measurements and other calculated engineering quantities. If a skeletal density is underestimated by 10%, it can affect the room temperature excess adsorption by at least 5% at 100 bar and by 7% at 200 bar, depending on the material type.

A novel methodology is developed to extract accurate skeletal reaction models for nuclear combustion. Local sensitivities of isotope mass fractions with respect to reaction rates are modeled based on the forced optimally time-dependent (f-OTD) scheme. These sensitivities are then analyzed temporally to generate skeletal models. The methodology is demonstrated by conducting skeletal reduction of constant density and temperature burning of carbon and oxygen relevant to SNe Ia. The 495-isotopes Torch model is chosen as the detailed reaction network. A map of maximum production of $^{56}\text{Ni}$ in SNe Ia is produced for different temperatures, densities, and proton to neutron ratios. The f-OTD simulations and the sensitivity analyses are then performed with initial conditions from this map. A series of skeletal models are derived and their performances are assessed by comparison against currently existing skeletal models. Previous models have been constructed intuitively by assuming the dominance of $α$-chain reactions. The comparison of the newly generated skeletal models against previous models is based on the predicted energy release and $^{44}\text{Ti}$ and $^{56}\text{Ni}$ abun

Skeletal call-by-need is an optimization of call-by-need evaluation also known as "fully lazy sharing": when the duplication of a value has to take place, it is first split into "skeleton", which is then duplicated, and "flesh" which is instead kept shared. Here, we provide two cost analyses of skeletal call-by-need. Firstly, we provide a family of terms showing that skeletal call-by-need can be asymptotically exponentially faster than call-by-need in both time and space; it is the first such evidence, to our knowledge. Secondly, we prove that skeletal call-by-need can be implemented efficiently, that is, with bi-linear overhead. This result is obtained by providing a new smooth presentation of ideas by Shivers and Wand for the reconstruction of skeletons, which is then smoothly plugged into the study of an abstract machine following the distillation technique by Accattoli et al.

In recent years, the field of radiology has increasingly harnessed the power of artificial intelligence (AI) to enhance diagnostic accuracy, streamline workflows, and improve patient care. Large language models (LLMs) have emerged as particularly promising tools, offering significant potential in assisting radiologists with report generation, clinical decision support, and patient communication. This paper presents an advanced radiology-focused large language model: MGH Radiology Llama. It is developed using the Llama 3 70B model, building upon previous domain-specific models like Radiology-GPT and Radiology-Llama2. Leveraging a unique and comprehensive dataset from Massachusetts General Hospital, comprising over 6.5 million de-identified medical reports across various imaging modalities, the model demonstrates significant improvements in generating accurate and clinically relevant radiology impressions given the corresponding findings. Our evaluation, incorporating both traditional metrics and a GPT-4-based assessment, highlights the enhanced performance of this work over general-purpose LLMs.

This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning. Radiology-Llama2 is based on the Llama2 architecture and further trained on a large dataset of radiology reports to generate coherent and clinically useful impressions from radiological findings. Quantitative evaluations using ROUGE metrics on the MIMIC-CXR and OpenI datasets demonstrate that Radiology-Llama2 achieves state-of-the-art performance compared to other generative language models, with a Rouge-1 score of 0.4834 on MIMIC-CXR and 0.4185 on OpenI. Additional assessments by radiology experts highlight the model's strengths in understandability, coherence, relevance, conciseness, and clinical utility. The work illustrates the potential of localized language models designed and tuned for specialized domains like radiology. When properly evaluated and deployed, such models can transform fields like radiology by automating rote tasks and enhancing human expertise.

Recent advances in deep learning have enabled researchers to explore tasks at the intersection of computer vision and natural language processing, such as image captioning, visual question answering, visual dialogue, and visual language navigation. Taking inspiration from image captioning, the task of radiology report generation aims at automatically generating radiology reports by having a comprehensive understanding of medical images. However, automatically generating radiology reports from medical images is a challenging task due to the complexity, diversity, and nature of medical images. In this paper, we outline the design of a robust radiology report generation system by integrating different modules and highlighting best practices drawing upon lessons from our past work and also from relevant studies in the literature. We also discuss the impact of integrating different components to form a single integrated system. We believe that these best practices, when implemented, could improve automatic radiology report generation, augment radiologists in decision making, and expedite diagnostic workflow, in turn improve healthcare and save human lives.

There has been debate for over 70-years about whether active skeletal muscle is dynamically stable at lengths greater than its optimal length. The stability of computational muscle models is a critical issue, as it directly affects our ability to simulate muscle deformation across different operating lengths, especially at lengths where muscles are known to remain functional despite model-predicted instabilities. In this study, we revisit the question of dynamical stability of ODE-based models of skeletal muscle. In particular, we investigate whether activation-independent tissue properties can provide stability to contractions along the dip region of the total force-length curve. First, using a combination of analytical tools (eigenvalue analysis and non-dimensionalization) and numerical simulations, we confirm that traditional Hill-type muscle models can display divergent dynamics in this region. Then, we propose a stabilized version of a 1D Hill-type muscle model that incorporates the 3D nature of skeletal muscle deformation. This results in a completely convex force-length relationship that can bring robustness to numerical simulations, while preserving the computational effici

We introduce Radiology-GPT, a large language model for radiology. Using an instruction tuning approach on an extensive dataset of radiology domain knowledge, Radiology-GPT demonstrates superior performance compared to general language models such as StableLM, Dolly and LLaMA. It exhibits significant versatility in radiological diagnosis, research, and communication. This work serves as a catalyst for future developments in clinical NLP. The successful implementation of Radiology-GPT is indicative of the potential of localizing generative large language models, specifically tailored for distinctive medical specialties, while ensuring adherence to privacy standards such as HIPAA. The prospect of developing individualized, large-scale language models that cater to specific needs of various hospitals presents a promising direction. The fusion of conversational competence and domain-specific knowledge in these models is set to foster future development in healthcare AI. A demo of Radiology-GPT is available at https://huggingface.co/spaces/allen-eric/radiology-gpt.

The principal left ideal graph of a semigroup is a simple graph whose vertices are the non-zero elements of the semigroup, and two vertices are adjacent if their principal left ideals intersect non-trivially. In this paper, we study the structure of the principal ideal graphs of inverse semigroups, particularly symmetric inverse semigroups. We also introduce the concept of skeletal of a graph and show that the principal ideal graph of an inverse semigroup has a skeletal, which is a simple graph with vertex set as $\mathcal{L}$ classes of non-zero elements. It is also proved that the principal ideal graph of symmetric inverse semigroups has a skeletal which is isomorphic to the intersection graph on the power set of a non-empty set.

At the heart of radiological practice is the challenge of integrating complex imaging data with clinical information to produce actionable insights. Nuanced application of language is key for various activities, including managing requests, describing and interpreting imaging findings in the context of clinical data, and concisely documenting and communicating the outcomes. The emergence of large language models (LLMs) offers an opportunity to improve the management and interpretation of the vast data in radiology. Despite being primarily general-purpose, these advanced computational models demonstrate impressive capabilities in specialized language-related tasks, even without specific training. Unlocking the potential of LLMs for radiology requires basic understanding of their foundations and a strategic approach to navigate their idiosyncrasies. This review, drawing from practical radiology and machine learning expertise and recent literature, provides readers insight into the potential of LLMs in radiology. It examines best practices that have so far stood the test of time in the rapidly evolving landscape of LLMs. This includes practical advice for optimizing LLM characteristic

Radiology report generation aims to automatically provide clinically meaningful descriptions of radiology images such as MRI and X-ray. Although great success has been achieved in natural scene image captioning tasks, radiology report generation remains challenging and requires prior medical knowledge. In this paper, we propose PromptRRG, a method that utilizes prompt learning to activate a pretrained model and incorporate prior knowledge. Since prompt learning for radiology report generation has not been explored before, we begin with investigating prompt designs and categorise them based on varying levels of knowledge: common, domain-specific and disease-enriched prompts. Additionally, we propose an automatic prompt learning mechanism to alleviate the burden of manual prompt engineering. This is the first work to systematically examine the effectiveness of prompt learning for radiology report generation. Experimental results on the largest radiology report generation benchmark, MIMIC-CXR, demonstrate that our proposed method achieves state-of-the-art performance. Code will be available upon the acceptance.

Skeletal editing of cyclic molecules has garnered considerable attention in the context of drug discovery and green chemistry, with notable examples in solution-phase synthesis. Here, we extend the scope of skeletal editing to the single-molecule scale. We demonstrate tip-induced oxygen deletion and ring contraction of an oxygen-containing seven-membered ring on bilayer NaCl films to generate molecules containing the perylene skeleton. The products were identified and characterized by atomic force and scanning tunneling microscopies, which provided access to bond-resolved molecular structures and orbital densities. Insights into the reaction mechanisms were obtained by density functional theory calculations. Our work expands the toolbox of tip-induced chemistry for single-molecule synthesis.

The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the text-based applications for radiology reports, comparing against state-of-the-art (SOTA) radiology-specific models. Exploring various prompting strategies, we evaluated GPT-4 on a diverse range of common radiology tasks and we found GPT-4 either outperforms or is on par with current SOTA radiology models. With zero-shot prompting, GPT-4 already obtains substantial gains ($\approx$ 10% absolute improvement) over radiology models in temporal sentence similarity classification (accuracy) and natural language inference ($F_1$). For tasks that require learning dataset-specific style or schema (e.g. findings summarisation), GPT-4 improves with example-based prompting and matches supervised SOTA. Our extensive error analysis with a board-certified radiologist shows GPT-4 has a sufficient level of radiology knowledge with only occasional errors in complex context that require nuanced domain know