This paper introduces an efficient sub-model ensemble framework aimed at enhancing the interpretability of medical deep learning models, thus increasing their clinical applicability. By generating uncertainty maps, this framework enables end-users to evaluate the reliability of model outputs. We developed a strategy to generate diverse models from a single well-trained checkpoint, facilitating the training of a model family. This involves producing multiple outputs from a single input, fusing them into a final output, and estimating uncertainty based on output disagreements. Implemented using U-Net and UNETR models for segmentation and synthesis tasks, this approach was tested on CT body segmentation and MR-CT synthesis datasets. It achieved a mean Dice coefficient of 0.814 in segmentation and a Mean Absolute Error of 88.17 HU in synthesis, improved from 89.43 HU by pruning. Additionally, the framework was evaluated under image corruption and data undersampling, maintaining correlation between uncertainty and error, which highlights its robustness. These results suggest that the proposed approach not only maintains the performance of well-trained models but also enhances interpretability through effective uncertainty estimation, applicable to both convolutional and transformer models in a range of imaging tasks.

Vision Transformer shows great superiority in medical image segmentation due to the ability to learn long-range dependency. For medical image segmentation from 3-D data, such as computed tomography (CT), existing methods can be broadly classified into 2-D-based and 3-D-based methods. One key limitation in 2-D-based methods is that the intraslice information is ignored, while the limitation in 3-D-based methods is the high computation cost and memory consumption, resulting in a limited feature representation for inner slice information. During the clinical examination, radiologists primarily use the axial plane and then routinely review both axial and coronal planes to form a 3-D understanding of anatomy. Motivated by this fact, our key insight is to design a hybrid model that can first learn fine-grained inner slice information and then generate a 3-D understanding of anatomy by incorporating 3-D information. We present a novel Hybrid Residual TransFormer (HResFormer) for 3-D medical image segmentation. Building upon standard 2-D and 3-D Transformer backbones, HResFormer involves two novel key designs: 1) a Hybrid Local-Global fusion Module (HLGM) to effectively and adaptively fuse inner slice information from 2-D Transformers and intraslice information from 3-D volumes for 3-D Transformers with local fine-grained and global long-range representation and 2) residual learning of the hybrid model, which can effectively leverage the inner slice and intraslice information for better 3-D understanding of anatomy. Experiments show that our HResFormer outperforms prior art on widely used medical image segmentation benchmarks. This article sheds light on an important but neglected way to design Transformers for 3-D medical image segmentation.

Photon Counting CT (PCCT) offers advanced imaging capabilities with potential for substantial radiation dose reduction; however, achieving this without compromising image quality remains a challenge due to increased noise at lower doses. This study aims to evaluate the effectiveness of a deep learning (DL)-based denoising algorithm in maintaining diagnostic image quality in whole-body PCCT imaging at reduced radiation levels, using real intraindividual cadaveric scans. Twenty-four cadaveric human bodies underwent whole-body CT scans on a PCCT scanner (NAEOTOM Alpha, Siemens Healthineers) at four different dose levels (100%, 50%, 25%, and 10% mAs). Each scan was reconstructed using both QIR level 2 and a DL algorithm (ClariCT.AI, ClariPi Inc.), resulting in 192 datasets. Objective image quality was assessed by measuring CT value stability, image noise, and contrast-to-noise ratio (CNR) across consistent regions of interest (ROIs) in the liver parenchyma. Two radiologists independently evaluated subjective image quality based on overall image clarity, sharpness, and contrast. Inter-rater agreement was determined using Spearman's correlation coefficient, and statistical analysis included mixed-effects modeling to assess objective and subjective image quality. Objective analysis showed that the DL denoising algorithm did not significantly alter CT values (p ≥ 0.9975). Noise levels were consistently lower in denoised datasets compared to the Original (p < 0.0001). No significant differences were observed between the 25% mAs denoised and the 100% mAs original datasets in terms of noise and CNR (p ≥ 0.7870). Subjective analysis revealed strong inter-rater agreement (r ≥ 0.78), with the 50% mAs denoised datasets rated superior to the 100% mAs original datasets (p < 0.0001) and no significant differences detected between the 25% mAs denoised and 100% mAs original datasets (p ≥ 0.9436). The DL denoising algorithm maintains image quality in PCCT imaging while enabling up to a 75% reduction in radiation dose. This approach offers a promising method for reducing radiation exposure in clinical PCCT without compromising diagnostic quality.

To address the challenges of verifying MR-based attenuation correction (MRAC) in PET/MR due to CT positional mismatches and alignment issues, this study utilized a flatbed insert and arms-down positioning during PET/CT scans to achieve precise MR-CT matching for accurate MRAC evaluation. A validation dataset of 21 patients underwent whole-body [¹⁸F]FDG PET/CT followed by [¹⁸F]FDG PET/MR. A flatbed insert ensured consistent positioning, allowing direct comparison of four MRAC methods-four-tissue and five-tissue models with discrete and continuous μ-maps-against CT-based attenuation correction (CTAC). A deep learning-based framework, trained on a dataset of 300 patients, was used to generate synthesized-CTs from MR images, forming the basis for all MRAC methods. Quantitative analyses were conducted at the whole-body, region of interest, and lesion levels, with lesion-distance analysis evaluating the impact of bone proximity on standardized uptake value (SUV) quantification. Distinct differences were observed among MRAC methods in spine and femur regions. Joint histogram analysis showed MRAC-4 (continuous μ-map) closely aligned with CTAC. Lesion-distance analysis revealed MRAC-4 minimized bone-induced SUV interference (r = 0.01, p = 0.8643). However, tissues prone to bone segmentation interference, such as the spine and liver, exhibited greater SUV variability and lower reproducibility in MRAC-4 compared to MRAC-2 (2D bone segmentation, discrete μ-map) and MRAC-3 (3D bone segmentation, discrete μ-map). Using a flatbed insert, this study validated MRAC with high precision. Continuous μ-value MRAC method (MRAC-4) demonstrated superior accuracy and minimized bone-related SUV errors but faced challenges in reproducibility, particularly in bone-rich regions.

Whole-body PET imaging plays an essential role in cancer diagnosis and treatment but suffers from low image quality. Traditional deep learning-based denoising methods work well for a specific acquisition but are less effective in handling diverse PET protocols. In this study, we proposed and validated a 3D Denoising Diffusion Probabilistic Model (3D DDPM) as a robust and universal solution for whole-body PET image denoising. The proposed 3D DDPM gradually injected noise into the images during the forward diffusion phase, allowing the model to learn to reconstruct the clean data during the reverse diffusion process. A 3D convolutional network was trained using high-quality data from the Biograph Vision Quadra PET/CT scanner to generate the score function, enabling the model to capture accurate PET distribution information extracted from the total-body datasets. The trained 3D DDPM was evaluated on datasets from four scanners, four tracer types, and six dose levels representing a broad spectrum of clinical scenarios. The proposed 3D DDPM consistently outperformed 2D DDPM, 3D UNet, and 3D GAN, demonstrating its superior denoising performance across all tested conditions. Additionally, the model's uncertainty maps exhibited lower variance, reflecting its higher confidence in its outputs. The proposed 3D DDPM can effectively handle various clinical settings, including variations in dose levels, scanners, and tracers, establishing it as a promising foundational model for PET image denoising. The trained 3D DDPM model of this work can be utilized off the shelf by researchers as a whole-body PET image denoising solution. The code and model are available at https://github.com/Miche11eU/PET-Image-Denoising-Using-3D-Diffusion-Model .

This study aims to develop and validate a deep learning framework designed to eliminate the second CT scan of dual-tracer total-body PET/CT imaging. We retrospectively included three cohorts of 247 patients who underwent dual-tracer total-body PET/CT imaging on two separate days (time interval:1-11 days). Out of these, 167 underwent [⁶⁸Ga]Ga-DOTATATE/[¹⁸F]FDG, 50 underwent [⁶⁸Ga]Ga-PSMA-11/[¹⁸F]FDG, and 30 underwent [⁶⁸Ga]Ga-FAPI-04/[¹⁸F]FDG. A deep learning framework was developed that integrates a registration generative adversarial network (RegGAN) with non-rigid registration techniques. This approach allows for the transformation of attenuation-correction CT (ACCT) images from the first scan into pseudo-ACCT images for the second scan, which are then used for attenuation and scatter correction (ASC) of the second tracer PET images. Additionally, the derived registration transform facilitates dual-tracer image fusion and analysis. The deep learning-based ASC PET images were evaluated using quantitative metrics, including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) across the whole body and specific regions. Furthermore, the quantitative accuracy of PET images was assessed by calculating standardized uptake value (SUV) bias in normal organs and lesions. The MAE for whole-body pseudo-ACCT images ranged from 97.64 to 112.59 HU across four tracers. The deep learning-based ASC PET images demonstrated high similarity to the ground-truth PET images. The MAE of SUV for whole-body PET images was 0.06 for [⁶⁸Ga]Ga-DOTATATE, 0.08 for [⁶⁸Ga]Ga-PSMA-11, 0.06 for [⁶⁸Ga]Ga-FAPI-04, and 0.05 for [¹⁸F]FDG, respectively. Additionally, the median absolute percent deviation of SUV was less than 2.6% for all normal organs, while the mean absolute percent deviation of SUV was less than 3.6% for lesions across four tracers. The proposed deep learning framework, combining RegGAN and non-rigid registration, shows promise in reducing CT radiation dose for dual-tracer total-body PET/CT imaging, with successful validation across multiple tracers.

This study aimed to develop and evaluate a deep-learning model for attenuation and scatter correction in whole-body 64Cu-based PET imaging. A swinUNETR model was implemented using the MONAI framework. Whole-body PET-nonAC and PET-CTAC image pairs were used for training, where PET-nonAC served as the input and PET-CTAC as the output. Due to the limited number of Cu-based PET/CT images, a model pre-trained on 51 Ga-PSMA PET images was fine-tuned on 15 Cu-based PET images via transfer learning. The model was trained without freezing layers, adapting learned features to the Cu-based dataset. For testing, six additional Cu-based PET images were used, representing 1-h, 12-h, and 48-h time points, with two images per group. The model performed best at the 12-h time point, with an MSE of 0.002 ± 0.0004 SUV², PSNR of 43.14 ± 0.08 dB, and SSIM of 0.981 ± 0.002. At 48 h, accuracy slightly decreased (MSE = 0.036 ± 0.034 SUV²), but image quality remained high (PSNR = 44.49 ± 1.09 dB, SSIM = 0.981 ± 0.006). At 1 h, the model also showed strong results (MSE = 0.024 ± 0.002 SUV², PSNR = 45.89 ± 5.23 dB, SSIM = 0.984 ± 0.005), demonstrating consistency across time points. Despite the limited size of the training dataset, the use of fine-tuning from a previously pre-trained model yielded acceptable performance. The results demonstrate that the proposed deep learning model can effectively generate PET-DLAC images that closely resemble PET-CTAC images, with only minor errors.

The potential of Large Language Models (LLMs) in enhancing a variety of natural language tasks in clinical fields includes medical imaging reporting. This pilot study examines the efficacy of a retrieval-augmented generation (RAG) LLM system considering zero-shot learning capability of LLMs, integrated with a comprehensive database of PET reading reports, in improving reference to prior reports and decision making. We developed a custom LLM framework with retrieval capabilities, leveraging a database of over 10 years of PET imaging reports from a single center. The system uses vector space embedding to facilitate similarity-based retrieval. Queries prompt the system to generate context-based answers and identify similar cases or differential diagnoses. From routine clinical PET readings, experienced nuclear medicine physicians evaluated the performance of system in terms of the relevance of queried similar cases and the appropriateness score of suggested potential diagnoses. The system efficiently organized embedded vectors from PET reports, showing that imaging reports were accurately clustered within the embedded vector space according to the diagnosis or PET study type. Based on this system, a proof-of-concept chatbot was developed and showed the framework's potential in referencing reports of previous similar cases and identifying exemplary cases for various purposes. From routine clinical PET readings, 84.1% of the cases retrieved relevant similar cases, as agreed upon by all three readers. Using the RAG system, the appropriateness score of the suggested potential diagnoses was significantly better than that of the LLM without RAG. Additionally, it demonstrated the capability to offer differential diagnoses, leveraging the vast database to enhance the completeness and precision of generated reports. The integration of RAG LLM with a large database of PET imaging reports suggests the potential to support clinical practice of nuclear medicine imaging reading by various tasks of AI including finding similar cases and deriving potential diagnoses from them. This study underscores the potential of advanced AI tools in transforming medical imaging reporting practices.

Objective: While recent advances in text-conditioned generative models have enabled the synthesis of realistic medical images, progress has been largely confined to 2D modalities such as chest X-rays. Extending text-to-image generation to volumetric Computed Tomography (CT) remains a significant challenge, due to its high dimensionality, anatomical complexity, and the absence of robust frameworks that align vision-language data in 3D medical imaging. Methods: We introduce a novel architecture for Text-to-CT generation that combines a latent diffusion model with a 3D contrastive vision-language pretraining scheme. Our approach leverages a dual-encoder CLIP-style model trained on paired CT volumes and radiology reports to establish a shared embedding space, which serves as the conditioning input for generation. CT volumes are compressed into a low-dimensional latent space via a pretrained volumetric VAE, enabling efficient 3D denoising diffusion without requiring external super-resolution stages. Results: We evaluate our method on the CT-RATE dataset and conduct a comprehensive assessment of image fidelity, clinical relevance, and semantic alignment. Our model achieves competitive performance across all tasks, significantly outperforming prior baselines for text-to-CT generation. Moreover, we demonstrate that CT scans synthesized by our framework can effectively augment real data, improving downstream diagnostic performance. Conclusion: Our results show that modality-specific vision-language alignment is a key component for high-quality 3D medical image generation. By integrating contrastive pretraining and volumetric diffusion, our method offers a scalable and controllable solution for synthesizing clinically meaningful CT volumes from text, paving the way for new applications in data augmentation, medical education, and automated clinical simulation.