PET/CT imaging of head-and-neck and pancreatic cancer in humans by targeting the “Cancer Integrin” αvβ6 with Ga-68-Trivehexin

Purpose To develop a new probe for the αvβ6-integrin and assess its potential for PET imaging of carcinomas. Methods Ga-68-Trivehexin was synthesized by trimerization of the optimized αvβ6-integrin selective cyclic nonapeptide Tyr2 (sequence: c[YRGDLAYp(NMe)K]) on the TRAP chelator core, followed by automated labeling with Ga-68. The tracer was characterized by ELISA for activities towards integrin subtypes αvβ6, αvβ8, αvβ3, and α5β1, as well as by cell binding assays on H2009 (αvβ6-positive) and MDA-MB-231 (αvβ6-negative) cells. SCID-mice bearing subcutaneous xenografts of the same cell lines were used for dynamic (90 min) and static (75 min p.i.) µPET imaging, as well as for biodistribution (90 min p.i.). Structure–activity-relationships were established by comparison with the predecessor compound Ga-68-TRAP(AvB6)3. Ga-68-Trivehexin was tested for in-human PET/CT imaging of HNSCC, parotideal adenocarcinoma, and metastatic PDAC. Results Ga-68-Trivehexin showed a high αvβ6-integrin affinity (IC50 = 0.047 nM), selectivity over other subtypes (IC50-based factors: αvβ8, 131; αvβ3, 57; α5β1, 468), blockable uptake in H2009 cells, and negligible uptake in MDA-MB-231 cells. Biodistribution and preclinical PET imaging confirmed a high target-specific uptake in tumor and a low non-specific uptake in other organs and tissues except the excretory organs (kidneys and urinary bladder). Preclinical PET corresponded well to in-human results, showing high and persistent uptake in metastatic PDAC and HNSCC (SUVmax = 10–13) as well as in kidneys/urine. Ga-68-Trivehexin enabled PET/CT imaging of small PDAC metastases and showed high uptake in HNSCC but not in tumor-associated inflammation. Conclusions Ga-68-Trivehexin is a valuable probe for imaging of αvβ6-integrin expression in human cancers.

Automated Labeling of Chest X-ray Images using a Quantitative Explainable Atlas-Based AI Model

The inability to accurately, efficiently label large, open-access medical imaging datasets limits the widespread implementation of artificial intelligence models in healthcare. There have been few attempts, however, to automate the annotation of such public databases; one approach, for example, focused on labor-intensive, manual labeling of subsets of these datasets to be used to train new models. In this study, we describe a method for standardized, automated labeling based on similarity to a previously validated, explainable AI model (xAI), using an atlas-based approach, for which the user can specify a quantitative threshold for a desired level of accuracy, the “probability-of-similarity” (pSim) metric. We showed that our xAI model, by calculating the pSim values for each feature based on comparison to its training-set derived reference atlas, could automatically label the external datasets to a user-selected, high level of accuracy, equaling or exceeding that of human experts.

PET/CT Imaging of Head-and-Neck and Pancreatic Cancer in Humans by Targeting the "Cancer Integrin" αvβ6 with Ga-68-Trivehexin

PurposeTo develop a new probe for the αvβ6-integrin and assess its potential for PET imaging of carcinomas.MethodsGa-68-Trivehexin was synthesized by trimerization of an optimized αvβ6-integrin selective cyclicnonapeptide on the TRAP chelator core and automated labeling with Ga-68. The tracer wascharacterized by ELISA for activities towards integrin subtypes αvβ6, αvβ8, αvβ3, and α5β1, as well asby cell binding assays on H2009 (αvβ6-positive) and MDA-MB-231 (αvβ6-negative) cells. SCID micebearing subcutaneous xenografts of the same cell lines were used for dynamic (90 min) and static(75 min p.i.) μPET imaging, as well as for biodistribution (90 min p.i.). Structure-activity-relationshipswere established by comparison with the predecessor compound Ga-68-TRAP(AvB6)3. Ga-68-Trivehexin was tested for in-human PET/CT imaging of HNSCC, parotideal adenocarcinoma, andPDAC.ResultsGa-68-Trivehexin showed a high αvβ6-integrin affinity (IC50 = 0.033 nM), selectivity over othersubtypes (IC50-based factors: αvβ8, 188; αvβ3, 82; α5β1, 667), blockable uptake in H2009 cells, andnegligible uptake in MDA-MB-231 cells. Biodistribution and preclinical PET imaging confirmed a hightarget-specific uptake in tumor and a low non-specific uptake in other organs and tissues except theexcretory organs (kidneys and urinary bladder). Preclinical PET corresponded well to in-human results,showing high and persistent uptake in metastatic PDAC and HNSCC (SUVmax = 10–13) as well as inkidneys/urine. Ga-68-Trivehexin enabled PET/CT imaging of small PDAC metastases and showed highuptake in HNSCC but not in tumor-associated inflammation.ConclusionsGa-68-Trivehexin is a valuable probe for imaging of αvβ6-integrin expression in human cancers.

High performance machine learning models can fully automate labeling of camera trap images for ecological analyses

Ecological data are increasingly collected over vast geographic areas using arrays of digital sensors. Camera trap arrays have become the ‘gold standard’ method for surveying many terrestrial mammals and birds, but these arrays often generate millions of images that are challenging to process. This causes significant latency between data collection and subsequent inference, which can impede conservation at a time of ecological crisis. Machine learning algorithms have been developed to improve camera trap data processing speeds, but these models are not considered accurate enough for fully automated labeling of images.Here, we present a new approach to building and testing a high performance machine learning model for fully automated labeling of camera trap images. As a case-study, the model classifies 26 Central African forest mammal and bird species (or groups). The model was trained on a relatively small dataset (c.300,000 images) but generalizes to fully independent data and outperforms humans in several respects (e.g. detecting ‘invisible’ animals). We show how the model’s precision and accuracy can be evaluated in an ecological modeling context by comparing species richness, activity patterns (n = 4 species tested) and occupancy (n = 4 species tested) derived from machine learning labels with the same estimates derived from expert labels.Results show that fully automated labels can be equivalent to expert labels when calculating species richness, activity patterns (n = 4 species tested) and estimating occupancy (n = 3 of 4 species tested) in completely out-of-sample test data (n = 227 camera stations, n = 23868 images). Simple thresholding (discarding uncertain labels) improved the model’s performance when calculating activity patterns and estimating occupancy, but did not improve estimates of species richness.We provide the user-community with a multi-platform, multi-language user interface for running the model offline, and conclude that high performance machine learning models can fully automate labeling of camera trap data.

How to Construct a Power Knowledge Graph with Dispatching Data?

Knowledge graph is a kind of semantic network for information retrieval. How to construct a knowledge graph that can serve the power system based on the behavior data of dispatchers is a hot research topic in the area of electric power artificial intelligence. In this paper, we propose a method to construct the dispatch knowledge graph for the power grid. By leveraging on dispatch data from the power domain, this method first extracts entities and then identifies dispatching behavior relationship patterns. More specifically, the method includes three steps. First, we construct a corpus of power dispatching behaviors by semi-automated labeling. And then, we propose a model, called the BiLSTM-CRF model, to extract entities and identify the dispatching behavior relationship patterns. Finally, we construct a knowledge graph of power dispatching data. The knowledge graph provides an underlying knowledge model for automated power dispatching and related services and helps dispatchers perform better power dispatch knowledge retrieval and other operations during the dispatch process.