A hybrid clustering algorithm for multiple‐source resolving in bioluminescence tomography

Abstract

Bioluminescence tomography is a preclinical imaging modality to locate and quantify internal bioluminescent sources from surface measurements, which experienced rapid growth in the last 10 years. However, multiple-source resolving remains a challenging issue in BLT. In this study, it is treated as an unsupervised pattern recognition problem based on the reconstruction result, and a novel hybrid clustering algorithm combining the advantages of affinity propagation (AP) and K-means is developed to identify multiple sources automatically. Moreover, we incorporate the clustering analysis into a general multiple-source reconstruction framework, which can provide stable reconstruction and accurate resolving result without providing the number of targets. Numerical simulations and in vivo experiments on 4T1-luc2 mouse model were conducted to assess the performance of the proposed method in multiple-source resolving. The encouraging results demonstrate significant effectiveness and potential of our method in preclinical BLT applications.

Prodrug polymeric micelles integrating cancer-associated fibroblasts deactivation and synergistic chemotherapy for gastric cancer

“…Nanomedicines have attracted tremendous attention and extensively applied in the delivery of chemotherapeutic agents because of their advantages in improving the solubility of hydrophobic drugs, enhancing cellular uptake and alleviating off-target toxicities [ 47 , 48 ]. By co‑delivering multiple active drug components, nanoparticles could facilitate synergistic anticancer effect and attenuate drug resistance, as evidenced by a number of in vivo studies (Additional file 2 : Table S1).…”

X‐ray luminescence computed tomography using a hybrid proton propagation model and Lasso‐LSQR algorithm

“…For further improve performance of the hybrid DE-SP 3 model, more multiple excitation points or multispectral strategy will be conducted in the future work [35]. Moreover, the effective of the novel Lasso-LSQR algorithm will be verified in some other optical molecular tomography including bioluminescence tomography [33], excited fluorescence tomography [36], Cerenkov luminescence tomography [36], and fluorescence molecular tomography [23]. In addition, some quantitative index about fluorescence yield was not used in our research.…”

“…Lastly, based on the finite element method (FEM), a relationship between the inside bioluminescent source S and the photon flux of luminescence light Φ on the object boundary can be inferred as [33]:…”

Near-Infrared Window II Fluorescence Image-Guided Surgery of High-Grade Gliomas Prolongs the Progression-Free Survival of Patients

“…Therefore, a novel real-time imaging technique for precise intraoperative image-guided neurosurgery is urgently needed [11][12][13][14][15]. This demand has inspired the investigation of fluorescence image-guided surgery (FGS) techniques.…”