Technical note: Rapid and high-resolution deep learning-based radiopharmaceutical imaging with 3D-CZT Compton camera and sparse projection data

BACKGROUND

The Compton camera (CC) has great potential in nuclear medicine imaging due to the high detection efficiency and the ability to simultaneously detect multi-energy radioactive sources. However, the finite resolution of the detectors will degrade the images that the real-world CC can obtain. Besides, the CC sometimes can be limited by the detection efficiency, leading to difficulty in using sparse projection data to realize high-resolution reconstruction with short-time measurement, which limits its clinical application for real-time or rapid radiopharmaceutical imaging.

PURPOSE

To overcome the difficulty and promote the usage of the CC in radiopharmaceutical imaging, we present a deep learning (DL)-based CC reconstruction method to realize rapid and high-resolution imaging with short-time measurement.

METHODS

We developed a DL-based algorithm MCBP-CCnet via Monte Carlo sampling-based back projection and a dedicated convolutional neural network, called CC-Net, to realize the rapid and high-resolution reconstruction with sparse projection data. A CC prototype based on a single three-dimensional position-sensitive CdZnTe (3D-CZT) detector was used to demonstrate the feasibility of our proposed method. The simulations and experiments of radiopharmaceutical imaging used the 3D-CZT CC and [¹⁸ F]NaF. A 3D-printing mouse phantom was also further used to evaluate the performance of the proposed method in animal molecular imaging.

RESULTS

The simulation and experimental results showed that the proposed method could realize the images reconstruction within 5 s for list-mode projection data and realized a rapid reconstruction within 35 s for experimental radiopharmaceutical imaging based on the 3D-printing mouse phantom, as well as realized the high-resolution imaging with an accuracy of within 0.78 mm in terms of the sparse projection data that only contained hundreds of events. Besides, the deviations between the reconstructed radiative activities and the exact values were less than 1.51%.

CONCLUSION

The results demonstrated that the proposed method could realize the rapid and high-resolution CC reconstruction with sparse projection data obtained by the 3D-CZT CC and realize the high-resolution radiopharmaceutical imaging. The study in this paper also demonstrated the potential and feasibility of future applications of a 3D-CZT CC for real-time high-resolution radiopharmaceutical imaging with short-time measurement.

Redox Monitoring in Nuclear Medical Imaging

Significance: The imbalance in redox homeostasis is known as oxidative stress, which is relevant to many diseases such as cancer, arteriosclerosis, and neurodegenerative disorders. Overproduction of reactive oxygen species (ROS) is one of the factors that trigger the redox state imbalance in vivo. The ROS have high reactivity and impair biomolecules, whereas antioxidants and antioxidant enzymes, such as ascorbate and glutathione, reduce the overproduction of ROS to rectify the redox imbalance. Owing to this, redox monitoring tools have been developed to understand the redox fluctuations in oxidative stress-related diseases. Recent Advances: In an attempt to monitor redox substances, including ROS and radical species, versatile modalities have been developed, such as electron spin resonance, chemiluminescence, and fluorescence. In particular, many fluorescent probes have been developed that are selective for ROS. This has significantly contributed to understanding the relevance of ROS in disease onset and progression. Critical Issues: To date, the dynamics of ROS and radical fluctuation in in vivo redox states remain unclear, and there are a few methods for the in vivo detection of redox fluctuations. Future Directions: In this review, we summarize the development of radiolabeled probes for monitoring redox-relevant species by nuclear medical imaging that is applicable in vivo. In the future, translational research is likely to be advanced through the development of highly sensitive and in vivo applicable detection methods, such as nuclear medical imaging, to clarify the underlying dynamics of ROS, radicals, and redox substances in many diseases. Antioxid. Redox Signal. 36, 797-810.

A review of the application of machine learning in molecular imaging

Molecular imaging (MI) is a science that uses imaging methods to reflect the changes of molecular level in living state and conduct qualitative and quantitative studies on its biological behaviors in imaging. Optical molecular imaging (OMI) and nuclear medical imaging are two key research fields of MI. OMI technology refers to the optical information generated by the imaging target (such as tumors) due to drug intervention and other reasons. By collecting the optical information, researchers can track the motion trajectory of the imaging target at the molecular level. Owing to its high specificity and sensitivity, OMI has been widely used in preclinical research and clinical surgery. Nuclear medical imaging mainly detects ionizing radiation emitted by radioactive substances. It can provide molecular information for early diagnosis, effective treatment and basic research of diseases, which has become one of the frontiers and hot topics in the field of medicine in the world today. Both OMI and nuclear medical imaging technology require a lot of data processing and analysis. In recent years, artificial intelligence technology, especially neural network-based machine learning (ML) technology, has been widely used in MI because of its powerful data processing capability. It provides a feasible strategy to deal with large and complex data for the requirement of MI. In this review, we will focus on the applications of ML methods in OMI and nuclear medical imaging.

A Radiolabeled Self-assembled Nanoparticle Probe for Diagnosis of Lung-Metastatic Melanoma

Melanoma is a highly malignant skin cancer that frequently metastasizes to the lung, bone, and brain at an early phase. Therefore, noninvasive detection of metastasized melanoma could be beneficial to determine suitable therapeutic strategies. We previously reported a biocompatible ternary anionic complex composed of plasmid DNA (pDNA), polyethyleneimine (PEI), and γ-polyglutamic acid (γ-PGA) based on an electrostatic interaction, which was highly taken up by melanoma cells (B16-F10), even if it was negatively charged. Here, we developed a radiolabeled γ-PGA complex by using indium-111 (111In)-labeled polyamidoamine dendrimer (4th generation; G4) instead of pDNA and iodine-125 (125I)-labeled PEI instead of native PEI, and evaluated its effectiveness as a melanoma-targeted imaging probe. This ternary complex was synthesized at a theoretical charge ratio; carboxyl groups of 111In-diethylenetriaminepentaacetic acid (DTPA)-G4 : amino groups of 125I-PEI : carboxyl groups of γ-PGA was 1 : 8 : 16, and the size and zeta potential were approximately 29 nm and -33 mV, respectively. This complex was taken up by B16-F10 cells with time. Furthermore, a biodistribution study, using normal mice, demonstrated its accumulation in the liver, spleen, and lung, where macrophage cells are abundant. Almost the same level of radioactivity derived from both 111In and 125I was observed in these organs at an early phase after probe injection. Compared with the normal mice, significantly higher lung-to-blood ratios of radioactivity were observed in the B16-F10-lung metastatic cancer model. In conclusion, the radiolabeled γ-PGA complex would hold potentialities for nuclear medical imaging of lung metastatic melanoma.