Kibo Ote

Objective . Scintillation detectors with excellent timing resolution enable more precise localization of radiation sources in positron emission tomography, leading to substantial improvements in diagnostic capability for diseases such as cancer and dementia. At the timing precision required for such applications at the picosecond scale, detector performance is governed by the dynamics of scintillation photons generated within the detector and their subsequent detection processes. However, detector signals have conventionally been treated only as collective responses of many photons due to structural constraints inherent to photodetectors. In this study, we overcome this fundamental limitation using deep learning framework. Approach . The proposed method estimates photon-by-photon arrival times directly from detector waveforms without requiring any modification to the detector structure; the method operates on an event-by-event basis without ground-truth labels by integrating an unsupervised learning framework with a physically informed detector-response model. Main results . Through comprehensive validation combining Monte Carlo simulation and experimental measurements across various detector configurations, we experimentally demonstrate improved timing resolution, visualized depth-of-interaction-dependent photon transport, and classified Cherenkov and scintillation photons based on the estimated photon-level timing information using a unified deep learning-based framework. Significance . These results provide experimental access to photon dynamics, bridging the gap between theoretical modeling and experimental observation, and they open a new data-driven pathway for discovery in detector physics and optimization.

Objective . Accurate attenuation correction (AC) is critical in quantitative brain positron emission tomography (PET) imaging. Conventional computed tomography (CT)-based AC methods increase radiation exposure and workflow complexity, and thereby create barriers to the widespread adoption of dedicated brain PET scanners. Deep-learning-based AC, although promising, frequently lacks generalizability to tracers that are not included in the training dataset. This domain-shift problem implies that, in practice, separate models might be needed for each tracer or clinical indication, which is impractical, especially for newly developed tracers and rare diseases where training data are scarce. This study aimed to develop a tracer-agnostic deep-learning approach for a CT-free AC framework. Approach . The proposed method employed a denoising diffusion probabilistic model to generate pseudo-transmission CT images from non-AC PET images. Two simple strategies were introduced to enhance cross-tracer generalizability: a visual-transformation module that synthesizes diverse tracer-dependent contrasts, and slice-positional embeddings to maintain anatomical continuity. The model was trained on 181 [ ¹⁸ F]FDG datasets and comprehensively evaluated in 14 multi-tracer datasets acquired on a dedicated brain PET scanner. Main results . The proposed method outperformed the emission-segmented AC and conventional U-Net models and achieved superior generation accuracy and regional bias within 10% across all tracers. Robust generalizability was demonstrated in tracers with diverse uptake patterns and acquisition protocols. Significance . This CT-free AC approach achieves quantitative accuracy comparable to that of CT-based correction while eliminating additional scans, reducing radiation exposure, and simplifying the workflow. This tracer-independent design supports the early evaluation of novel tracers and their broad clinical adoption in brain-PET imaging.

Objective. Positron emission tomography (PET) is affected by statistical noise due to constraints on tracer dose and scan duration, impacting both diagnostic performance and quantitative accuracy. While deep learning-based PET denoising methods have been used to improve image quality, they may introduce over-smoothing, which can obscure critical structural details and compromise quantitative accuracy. We propose a method for making a deep learning solution more reliable and apply it to the conditional deep image prior (DIP). Approach. We introduce the idea of stability information in the optimization process of conditional DIP, enabling the identification of unstable regions within the network’s optimization trajectory. Our method incorporates a stability map, which is derived from multiple intermediate outputs of a moderate neural network at different optimization steps. The final denoised PET image is then obtained by computing a linear combination of the DIP output and the original reconstructed PET image, weighted by the stability map. Main results. We employed eight high-resolution brain PET datasets for comparison. Our method effectively reduces background noise while preserving small structure details in brain [¹⁸F]FDG PET images. Comparative analysis demonstrated that our approach outperformed existing methods in terms of peak-to-valley ratio and background noise suppression across various low-dose levels. Additionally, region-of-interest analysis confirmed that the proposed method maintains quantitative accuracy without introducing under- or over-estimation. Furthermore, we applied our method to full-dose PET data to assess its impact on image quality. The results revealed that the proposed method significantly reduced background noise while preserving the peak-to-valley ratio at a level comparable to that of unfiltered full-dose PET images. Significance. The proposed method introduces a robust approach to deep learning-based PET denoising, enhancing its reliability and preserving quantitative accuracy. Furthermore, this strategy can potentially advance performance in high-sensitivity PET scanners and surpass the limit of image quality inherent to PET scanners.

Convergence of the block iterative method in image reconstruction for positron emission tomography (PET) requires careful control of relaxation parameters, which is a challenging task. The automatic determination of relaxation parameters for list-mode reconstructions also remains challenging. Therefore, a different approach would be desirable. In this study, we propose a list-mode maximum likelihood Dykstra-like splitting PET reconstruction (LM-MLDS) that reduces the limit-cycle amplitude by adding the distance from an initial image as a penalty term into an objective function. LM-MLDS uses a two-step approach because its performance depends on the quality of the initial image. The first step uses a uniform image as the initial image, whereas the second step uses a reconstructed image after one main iteration as the initial image. In a simulation study, LM-MLDS provided a better tradeoff curve between noise and contrast than the other methods. In a clinical study, LM-MLDS removed the false hotspots at the edge of the axial field of view and improved the image quality of slices covering the top of the head to the cerebellum. List-mode proximal splitting reconstruction is useful not only for optimizing nondifferential functions but also for mitigating the limit-cycle phenomenon in block iterative methods.

Bismuth germanate (BGO) has been receiving attention again because it is a potential scintillator for future time-of-flight positron emission tomography. Owing to its optical properties, BGO emits a relatively large number of Cherenkov photons after 511 keV gamma-ray interactions, which can enable good coincidence time resolution. Nonetheless, optimally exploiting the Cherenkov emissions can be confounded by scintillation emissions. Thus, we propose a method efficiently emphasizing Cherenkov photon from a detector waveform by deconvolving a single photon response of photodetector. As a proof-of-concept, we perform the deconvolution, and a probability density function (PDF) of BGO was obtained, which is compared to a conventional time correlated single photon counting method. Furthermore, we investigate if the proposed deconvolution can emphasize a faint Cherenkov signal. Consequently, the PDF obtained by the proposed deconvolution shows a good agreement with that obtained using a conventional time correlated single photon counting methods. A coincidence time resolution obtained using the proposed deconvolution is improved by 12% and 43% in FWHM compared to a voltage-based leading edge discriminator for with and without high-frequency readout electronics, respectively. Thus, the proposed deconvolution method can efficiently emphasize Cherenkov photon by lowering the threshold level and improve the timing performance of BGO-based detectors.

Objective. This study aims to introduce a novel back projection-induced U-Net-shaped architecture, called ReconU-Net, based on the original U-Net architecture for deep learning-based direct positron emission tomography (PET) image reconstruction. Additionally, our objective is to visualize the behavior of direct PET image reconstruction by comparing the proposed ReconU-Net architecture with the original U-Net architecture and existing DeepPET encoder–decoder architecture without skip connections. Approach . The proposed ReconU-Net architecture uniquely integrates the physical model of the back projection operation into the skip connection. This distinctive feature facilitates the effective transfer of intrinsic spatial information from the input sinogram to the reconstructed image via an embedded physical model. The proposed ReconU-Net was trained using Monte Carlo simulation data from the Brainweb phantom and tested on both simulated and real Hoffman brain phantom data. Main results . The proposed ReconU-Net method provided better reconstructed image in terms of the peak signal-to-noise ratio and contrast recovery coefficient than the original U-Net and DeepPET methods. Further analysis shows that the proposed ReconU-Net architecture has the ability to transfer features of multiple resolutions, especially non-abstract high-resolution information, through skip connections. Unlike the U-Net and DeepPET methods, the proposed ReconU-Net successfully reconstructed the real Hoffman brain phantom, despite limited training on simulated data. Significance . The proposed ReconU-Net can improve the fidelity of direct PET image reconstruction, even with small training datasets, by leveraging the synergistic relationship between data-driven modeling and the physics model of the imaging process.

Direct positron emission imaging (dPEI), which does not require a mathematical reconstruction step, is a next-generation molecular imaging modality. To maximize the practical applicability of the dPEI system to clinical practice, we introduce a novel reconstruction-free image-formation method called direct μ _Compton imaging, which directly localizes the interaction position of Compton scattering from the annihilation photons in a three-dimensional space by utilizing the same compact geometry as that for dPEI, involving ultrafast time-of-flight radiation detectors. This unique imaging method not only provides the anatomical information about an object but can also be applied to attenuation correction of dPEI images. Evaluations through Monte Carlo simulation showed that functional and anatomical hybrid images can be acquired using this multimodal imaging system. By fusing the images, it is possible to simultaneously access various object data, which ensures the synergistic effect of the two imaging methodologies. In addition, attenuation correction improves the quantification of dPEI images. The realization of the whole reconstruction-free imaging system from image generation to quantitative correction provides a new perspective in molecular imaging.

Objective . Deep image prior (DIP) has recently attracted attention owing to its unsupervised positron emission tomography (PET) image reconstruction method, which does not require any prior training dataset. In this paper, we present the first attempt to implement an end-to-end DIP-based fully 3D PET image reconstruction method that incorporates a forward-projection model into a loss function. Approach . A practical implementation of a fully 3D PET image reconstruction could not be performed at present because of a graphics processing unit memory limitation. Consequently, we modify the DIP optimization to a block iteration and sequential learning of an ordered sequence of block sinograms. Furthermore, the relative difference penalty (RDP) term is added to the loss function to enhance the quantitative accuracy of the PET image. Main results . We evaluated our proposed method using Monte Carlo simulation with [ ¹⁸ F]FDG PET data of a human brain and a preclinical study on monkey-brain [ ¹⁸ F]FDG PET data. The proposed method was compared with the maximum-likelihood expectation maximization (EM), maximum a posteriori EM with RDP, and hybrid DIP-based PET reconstruction methods. The simulation results showed that, compared with other algorithms, the proposed method improved the PET image quality by reducing statistical noise and better preserved the contrast of brain structures and inserted tumors. In the preclinical experiment, finer structures and better contrast recovery were obtained with the proposed method. Significance. The results indicated that the proposed method could produce high-quality images without a prior training dataset. Thus, the proposed method could be a key enabling technology for the straightforward and practical implementation of end-to-end DIP-based fully 3D PET image reconstruction.

Deep image prior (DIP) has been successfully applied to positron emission tomography (PET) image restoration, enabling represent implicit prior using only convolutional neural network architecture without training dataset, whereas the general supervised approach requires massive low- and high-quality PET image pairs. To answer the increased need for PET imaging with DIP, it is indispensable to improve the performance of the underlying DIP itself. Here, we propose a self-supervised pre-training model to improve the DIP-based PET image denoising performance. Our proposed pre-training model acquires transferable and generalizable visual representations from only unlabeled PET images by restoring various degraded PET images in a self-supervised approach. We evaluated the proposed method using clinical brain PET data with various radioactive tracers ($^{18}$F-florbetapir, $^{11}$C-Pittsburgh compound-B, $^{18}$F-fluoro-2-deoxy-D-glucose, and $^{15}$O-CO$_{2}$) acquired from different PET scanners. The proposed method using the self-supervised pre-training model achieved robust and state-of-the-art denoising performance while retaining spatial details and quantification accuracy compared to other unsupervised methods and pre-training model. These results highlight the potential that the proposed method is particularly effective against rare diseases and probes and helps reduce the scan time or the radiotracer dose without affecting the patients.

List-mode positron emission tomography (PET) image reconstruction is an important tool for PET scanners with many lines-of-response and additional information such as time-of-flight and depth-of-interaction. Deep learning is one possible solution to enhance the quality of PET image reconstruction. However, the application of deep learning techniques to list-mode PET image reconstruction has not been progressed because list data is a sequence of bit codes and unsuitable for processing by convolutional neural networks (CNN). In this study, we propose a novel list-mode PET image reconstruction method using an unsupervised CNN called deep image prior (DIP) which is the first trial to integrate list-mode PET image reconstruction and CNN. The proposed list-mode DIP reconstruction (LM-DIPRecon) method alternatively iterates the regularized list-mode dynamic row action maximum likelihood algorithm (LM-DRAMA) and magnetic resonance imaging conditioned DIP (MR-DIP) using an alternating direction method of multipliers. We evaluated LM-DIPRecon using both simulation and clinical data, and it achieved sharper images and better tradeoff curves between contrast and noise than the LM-DRAMA, MR-DIP and sinogram-based DIPRecon methods. These results indicated that the LM-DIPRecon is useful for quantitative PET imaging with limited events while keeping accurate raw data information. In addition, as list data has finer temporal information than dynamic sinograms, list-mode deep image prior reconstruction is expected to be useful for 4D PET imaging and motion correction.