Multicenter PET image harmonization using generative adversarial networks.

PURPOSE: To improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches. METHODS: GAN-harmonization was developed to harmonize whole-body PET scans to perform image style and texture translation between different centers and scanners. GAN-harmonization was evaluated by application to two retrospectively collected open datasets and different tasks. First, GAN-harmonization was performed on a dual-center lung cancer cohort (127 female, 138 male) where the reproducibility of radiomic features in healthy liver tissue was evaluated. Second, GAN-harmonization was applied to a head and neck cancer cohort (43 female, 154 male) acquired from three centers. Here, the clinical impact of GAN-harmonization was analyzed by predicting the development of distant metastases using a logistic regression model incorporating first-order statistics and texture features from baseline 18F-FDG PET before and after harmonization. RESULTS: Image quality remained high (structural similarity: left kidney ≥ 0.800, right kidney ≥ 0.806, liver ≥ 0.780, lung ≥ 0.838, spleen ≥ 0.793, whole-body ≥ 0.832) after image harmonization across all utilized datasets. Using GAN-harmonization, inter-site reproducibility of radiomic features in healthy liver tissue increased at least by ≥ 5 ± 14% (first-order), ≥ 16 ± 7% (GLCM), ≥ 19 ± 5% (GLRLM), ≥ 16 ± 8% (GLSZM), ≥ 17 ± 6% (GLDM), and ≥ 23 ± 14% (NGTDM). In the head and neck cancer cohort, the outcome prediction improved from AUC 0.68 (95% CI 0.66-0.71) to AUC 0.73 (0.71-0.75) by application of GAN-harmonization. CONCLUSIONS: GANs are capable of performing image harmonization and increase reproducibility and predictive performance of radiomic features derived from different centers and scanners.

Examining the Relationship and Prognostic Significance of Cell-Free DNA Levels and the PSMA-Positive Tumor Volume in Men with Prostate Cancer: A Retrospective-Prospective [68Ga]Ga-PSMA-11 PET/CT Study.

Functional imaging with prostate-specific membrane antigen (PSMA) ligands has emerged as the standard imaging method for prostate cancer (PCA). In parallel, the analysis of blood-derived, cell-free DNA (cfDNA) has been shown to be a promising quantitative biomarker of PCA aggressiveness and patient outcome. This study aimed to evaluate the relationship and prognostic value of cfDNA concentrations and the PSMA-positive tumor volume (PSMA-TV) in men with PCA undergoing [68Ga]Ga-PSMA-11 PET/CT imaging. Methods: We recruited 148 men with histologically proven PCA (mean age, 70.7 ± 7.7 y) who underwent [68Ga]Ga-PSMA-11 PET/CT (184.9 ± 18.9 MBq) and blood sampling between March 2019 and August 2021. Among these, 74 (50.0%) had hormone-sensitive PCA and 74 (50.0%) had castration-resistant PCA (CRPC). All patients provided written informed consent before blood sample collection and imaging. The cfDNA was extracted and quantified, and PSMA-expressing tumor lesions were delineated to extract the PSMA-TVs. The Spearman coefficient assessed correlations between PSMA-TV and cfDNA concentrations and cfDNA's relation with clinical parameters. The Kruskal-Wallis test examined the mean cfDNA concentration differences based on PSMA-TV quartiles for significantly correlated patient groups. Log-rank and multivariate Cox regression analyses evaluated the prognostic significance of high and low cfDNA and PSMA-TV levels for overall survival. Results: Weak positive correlations were found between cfDNA concentration and PSMA-TV in the overall group (r = 0.16, P = 0.049) and the CRPC group (r = 0.31, P = 0.007) but not in hormone-sensitive PCA patients (r = -0.024, P = 0.837). In the CRPC cohort, cfDNA concentrations significantly differed between PSMA-TV quartiles 4 and 1 (P = 0.002) and between quartiles 4 and 2 (P = 0.016). Survival outcomes were associated with PSMA-TV (P < 0.0001, P = 0.004) but not cfDNA (P = 0.174, P = 0.12), as per the log-rank and Cox regression analysis. Conclusion: These findings suggest that cfDNA might serve as a biomarker of advanced, aggressive CRPC but does not reliably reflect total tumor burden or prognosis. In comparison, [68Ga]Ga-PSMA-11 PET/CT provides a highly granular and prognostic assessment of tumor burden across the spectrum of PCA disease progression.

A Possible Perspective of Recultivation with Arbuscular Mycorrhiza-Inoculated Drought-Tolerant Herbaceous Plants.

Using native species for urban green space is rather important nowadays. Plant cover on soil is necessary for agronomical and architectural investments as well as conservational programs, which all need minimal maintenance and have to be cost efficient. Commercially available seed mixtures for grasslands and lawns include species that partly originated from other mesoclimatic zones, and thus they may not be able to survive in the long-term, nor will they be adventive to the local ecosystem. With a focus on climate change, the most arid part of the Pannon geographical region was selected (near Törökszentmiklós in Nagykunság, Hungarian Great Plain). The local flora has adapted effectively to the environment; therefore, many species growing there were candidates for this study. Annuals and herbaceous perennials were investigated with respect to harvestability, reproducibility, decorativity, seed production, seed morphological characters (size, mass) and germination features. The selected 20 taxa were inoculated with INOQ Agri mycorrhiza (Rhizophagus irregularis) to increase the drought tolerance and biomass of the plants. Mycorrhizal frequency was significantly different among the taxa, reflecting various responses to the symbiotic interaction and possibly various mycorrhizal dependence of the plant species examined. We did not observe significantly higher colonization rate in most cases of the samples with artificial inoculation treatment. We conclude that the degraded mowed lawn soil that we used could contain propagules of AM fungi in a sufficient amount, so in the artificial grassland restorations, the additional AM inoculation treatment is not necessary to achieve a higher AM colonization rate.

Enhancing Interoperability and Harmonisation of Nuclear Medicine Image Data and Associated Clinical Data.

Nuclear imaging techniques such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) in combination with computed tomography (CT) are established imaging modalities in clinical practice, particularly for oncological problems. Due to a multitude of manufacturers, different measurement protocols, local demographic or clinical workflow variations as well as various available reconstruction and analysis software, very heterogeneous datasets are generated. This review article examines the current state of interoperability and harmonisation of image data and related clinical data in the field of nuclear medicine. Various approaches and standards to improve data compatibility and integration are discussed. These include, for example, structured clinical history, standardisation of image acquisition and reconstruction as well as standardised preparation of image data for evaluation. Approaches to improve data acquisition, storage and analysis will be presented. Furthermore, approaches are presented to prepare the datasets in such a way that they become usable for projects applying artificial intelligence (AI) (machine learning, deep learning, etc.). This review article concludes with an outlook on future developments and trends related to AI in nuclear medicine, including a brief research of commercial solutions.

PADAPT 1.0 - the Pannonian Dataset of Plant Traits.

The existing plant trait databases' applicability is limited for studies dealing with the flora and vegetation of the eastern and central part of Europe and for large-scale comparisons across regions, mostly because their geographical data coverage is limited and they incorporate records from several different sources, often from regions with markedly different climatic conditions. These problems motivated the compilation of a regional dataset for the flora of the Pannonian region (Eastern Central Europe). PADAPT, the Pannonian Dataset of Plant Traits relies on regional data sources and collates data on 54 traits and attributes of the plant species of the Pannonian region. The current version covers approximately 90% of the species of the region and consists of 126,337 records on 2745 taxa. By including species of the eastern part of Europe not covered by other databases, PADAPT can facilitate studying the flora and vegetation of the eastern part of the continent. Although data coverage is far from complete, PADAPT meets the longstanding need for a regional database of the Pannonian flora.

DEBI-NN: Distance-encoding biomorphic-informational neural networks for minimizing the number of trainable parameters.

Modern artificial intelligence (AI) approaches mainly rely on neural network (NN) or deep NN methodologies. However, these approaches require large amounts of data to train, given, that the number of their trainable parameters has a polynomial relationship to their neuron counts. This property renders deep NNs challenging to apply in fields operating with small, albeit representative datasets such as healthcare. In this paper, we propose a novel neural network architecture which trains spatial positions of neural soma and axon pairs, where weights are calculated by axon-soma distances of connected neurons. We refer to this method as distance-encoding biomorphic-informational (DEBI) neural network. This concept significantly minimizes the number of trainable parameters compared to conventional neural networks. We demonstrate that DEBI models can yield comparable predictive performance in tabular and imaging datasets, where they require a fraction of trainable parameters compared to conventional NNs, resulting in a highly scalable solution.

Disruption of the Schizosaccharomyces japonicus lig4 Disturbs Several Cellular Processes and Leads to a Pleiotropic Phenotype.

Gene targeting is a commonly used method to reveal the function of genes. Although it is an attractive tool for molecular studies, it can frequently be a challenge because its efficiency can be low and it requires the screening of a large number of transformants. Generally, these problems originate from the elevated level of ectopic integration caused by non-homologous DNA end joining (NHEJ). To eliminate this problem, NHEJ-related genes are frequently deleted or disrupted. Although these manipulations can improve gene targeting, the phenotype of the mutant strains raised the question of whether mutations have side effects. The aim of this study was to disrupt the lig4 gene in the dimorphic fission yeast, S. japonicus, and investigate the phenotypic changes of the mutant strain. The mutant cells have shown various phenotypic changes, such as increased sporulation on complete medium, decreased hyphal growth, faster chronological aging, and higher sensitivity to heat shock, UV light, and caffeine. In addition, higher flocculation capacity has been observed, especially at lower sugar concentrations. These changes were supported by transcriptional profiling. Many genes belonging to metabolic and transport processes, cell division, or signaling had altered mRNA levels compared to the control strain. Although the disruption improved the gene targeting, we assume that the lig4 inactivation can cause unexpected physiological side effects, and we have to be very careful with the manipulations of the NHEJ-related genes. To reveal the exact mechanisms behind these changes, further investigations are required.

Characterization of Zygosaccharomyces lentus Yeast in Hungarian Botrytized Wines.

Tokaj botrytized sweet wines are traditionally aged for several years in wood barrels or bottles. As they have significant residual sugar content, they are exposed to microbial contamination during ageing. Osmotolerant wine-spoilage yeasts are most commonly found in the Tokaj wine-growing region in the species Starmerella spp. and Zygosaccharomyces spp. For the first time, Z. lentus yeasts were isolated from post-fermented botrytized wines. Our physiological studies confirmed that these yeast strains are osmotolerant, with high sulphur tolerance and 8% v/v alcohol tolerance, and that they grow well at cellar temperature in acidic conditions. Low ß-glucosidase and sulphite reductase activities were observed, whereas protease, cellulase, and α-arabinofuranosidase extracellular enzyme activities were not detected. Molecular biology analyses carried out by RFLP analysis of mtDNA revealed no remarkable differences between strains, while microsatellite-primed-PCR fingerprinting of the (GTG)5 microsatellite and examination of chromosomal pattern revealed considerable diversity. The fermentative vigour of the tested Z. lentus strains was found to be significantly lower compared to the control Saccharomyces cerevisiae (Lalvin EC1118). It can be concluded that Z. lentus is a potential spoilage yeast in oenology which may be responsible for the initiation of secondary fermentation of wines during ageing.

Sex-specific radiomic features of L-[S-methyl-11C] methionine PET in patients with newly-diagnosed gliomas in relation to IDH1 predictability.

Introduction: Amino-acid positron emission tomography (PET) is a validated metabolic imaging approach for the diagnostic work-up of gliomas. This study aimed to evaluate sex-specific radiomic characteristics of L-[S-methyl-11Cmethionine (MET)-PET images of glioma patients in consideration of the prognostically relevant biomarker isocitrate dehydrogenase (IDH) mutation status. Methods: MET-PET of 35 astrocytic gliomas (13 females, mean age 41 ± 13 yrs. and 22 males, mean age 46 ± 17 yrs.) and known IDH mutation status were included. All patients underwent radiomic analysis following imaging biomarker standardization initiative (IBSI)-conform guidelines both from standardized uptake value (SUV) and tumor-to-background ratio (TBR) PET values. Aligned Monte Carlo (MC) 100-fold split was utilized for SUV and TBR dataset pairs for both sex and IDH-specific analysis. Borderline and outlier scores were calculated for both sex and IDH-specific MC folds. Feature ranking was performed by R-squared ranking and Mann-Whitney U-test together with Bonferroni correction. Correlation of SUV and TBR radiomics in relation to IDH mutational status in male and female patients were also investigated. Results: There were no significant features in either SUV or TBR radiomics to distinguish female and male patients. In contrast, intensity histogram coefficient of variation (ih.cov) and intensity skewness (stat.skew) were identified as significant to predict IDH +/-. In addition, IDH+ females had significant ih.cov deviation (0.031) and mean stat.skew (-0.327) differences compared to IDH+ male patients (0.068 and -0.123, respectively) with two-times higher standard deviations of the normal brain background MET uptake as well. Discussion: We demonstrated that female and male glioma patients have significantly different radiomic profiles in MET PET imaging data. Future IDH prediction models shall not be built on mixed female-male cohorts, but shall rely on sex-specific cohorts and radiomic imaging biomarkers.

Machine learning predictive performance evaluation of conventional and fuzzy radiomics in clinical cancer imaging cohorts.

BACKGROUND: Hybrid imaging became an instrumental part of medical imaging, particularly cancer imaging processes in clinical routine. To date, several radiomic and machine learning studies investigated the feasibility of in vivo tumor characterization with variable outcomes. This study aims to investigate the effect of recently proposed fuzzy radiomics and compare its predictive performance to conventional radiomics in cancer imaging cohorts. In addition, lesion vs. lesion+surrounding fuzzy and conventional radiomic analysis was conducted. METHODS: Previously published 11C Methionine (MET) positron emission tomography (PET) glioma, 18F-FDG PET/computed tomography (CT) lung, and 68GA-PSMA-11 PET/magneto-resonance imaging (MRI) prostate cancer retrospective cohorts were included in the analysis to predict their respective clinical endpoints. Four delineation methods including manually defined reference binary (Ref-B), its smoothed, fuzzified version (Ref-F), as well as extended binary (Ext-B) and its fuzzified version (Ext-F) were incorporated to extract imaging biomarker standardization initiative (IBSI)-conform radiomic features from each cohort. Machine learning for the four delineation approaches was performed utilizing a Monte Carlo cross-validation scheme to estimate the predictive performance of the four delineation methods. RESULTS: Reference fuzzy (Ref-F) delineation outperformed its binary delineation (Ref-B) counterpart in all cohorts within a volume range of 938-354987 mm3 with relative cross-validation area under the receiver operator characteristics curve (AUC) of +4.7-10.4. Compared to Ref-B, the highest AUC performance difference was observed by the Ref-F delineation in the glioma cohort (Ref-F: 0.74 vs. Ref-B: 0.70) and in the prostate cohort by Ref-F and Ext-F (Ref-F: 0.84, Ext-F: 0.86 vs. Ref-B: 0.80). In addition, fuzzy radiomics decreased feature redundancy by approx. 20%. CONCLUSIONS: Fuzzy radiomics has the potential to increase predictive performance particularly in small lesion sizes compared to conventional binary radiomics in PET. We hypothesize that this effect is due to the ability of fuzzy radiomics to model partial volume effects and delineation uncertainties at small lesion boundaries. In addition, we consider that the lower redundancy of fuzzy radiomic features supports the identification of imaging biomarkers in future studies. Future studies shall consider systematically analyzing lesions and their surroundings with fuzzy and binary radiomics.

Radiogenomic markers enable risk stratification and inference of mutational pathway states in head and neck cancer.

PURPOSE: Head and neck squamous cell carcinomas (HNSCCs) are a molecularly, histologically, and clinically heterogeneous set of tumors originating from the mucosal epithelium of the oral cavity, pharynx, and larynx. This heterogeneous nature of HNSCC is one of the main contributing factors to the lack of prognostic markers for personalized treatment. The aim of this study was to develop and identify multi-omics markers capable of improved risk stratification in this highly heterogeneous patient population. METHODS: In this retrospective study, we approached this issue by establishing radiogenomics markers to identify high-risk individuals in a cohort of 127 HNSCC patients. Hybrid in vivo imaging and whole-exome sequencing were employed to identify quantitative imaging markers as well as genetic markers on pathway-level prognostic in HNSCC. We investigated the deductibility of the prognostic genetic markers using anatomical and metabolic imaging using positron emission tomography combined with computed tomography. Moreover, we used statistical and machine learning modeling to investigate whether a multi-omics approach can be used to derive prognostic markers for HNSCC. RESULTS: Radiogenomic analysis revealed a significant influence of genetic pathway alterations on imaging markers. A highly prognostic radiogenomic marker based on cellular senescence was identified. Furthermore, the radiogenomic biomarkers designed in this study vastly outperformed the prognostic value of markers derived from genetics and imaging alone. CONCLUSION: Using the identified markers, a clinically meaningful stratification of patients is possible, guiding the identification of high-risk patients and potentially aiding in the development of effective targeted therapies.

The Benefits and Cost-Effectiveness of Arteriovenous (AV) Fistula Screening in Haemodialysis Patients.

Background Ultrasound (US) monitoring of arteriovenous fistulas (AVFs) presents contradictory findings. These differences may be attributed to variances in the chosen surveillance strategy, the specific type of fistula being monitored, and the precise technique used for ultrasound scanning. In this study, we are trying to assess the benefits and cost-effectiveness of US scanning of AVF. Patients and methods This was a descriptive, retrospective, and observational study. The study sample consisted of patients diagnosed with end-stage renal disease (ESRD) on hemodialysis who had AVF for dialysis either by native vein or using prosthetic grafts. We excluded all the patients whose fistula failed to mature, failed to attend the surveillance scan at six weeks, or had absent records or incomplete data. We retrieved the data of the patients who underwent AVF creation at Glan Clwyd Hospital between April 2020 and April 2023. The data was analysed using statistical software (SPSS) version 21 (IBM Corp., Armonk, NY, USA). Results Ninety-eight patients were studied. Stenosis 43.9% (n = 43) was the predominant complication, followed by thrombosis (15.3%; n = 15) while the remaining complications (bleeding, pseudoaneurysm) were less prominent. On the other hand, a total of 37.8% (n = 37) did not experience any complications. Primary patency ranged from 2 to 87 months with a mean of 9 ± 13.2 months SD, and secondary patency ranged from 1 to 24 months with a mean of 1.3 ± 3.9 months SD. The mean cost of a surveillance scan for AVF is 2520 USD, and the mean cost of intervention is 1332 + 1258 USD SD. Out of all the patients, 52 (53%) underwent intervention to salvage the AVF, 2 (2%) received open surgical intervention, and 50 (51%) underwent endovascular intervention. Considering the AVF failure to work, 29.6% (n = 29) had fistulas that failed to work, and 70.4% (n = 69) were still working. Conclusion Routine duplex scanning in six-month periods to diagnose failing AV fistulas is not cost-effective when compared to diagnosing failing or failed AV fistulas based on clinical symptoms.

Automated data preparation for in vivo tumor characterization with machine learning.

Background: This study proposes machine learning-driven data preparation (MLDP) for optimal data preparation (DP) prior to building prediction models for cancer cohorts. Methods: A collection of well-established DP methods were incorporated for building the DP pipelines for various clinical cohorts prior to machine learning. Evolutionary algorithm principles combined with hyperparameter optimization were employed to iteratively select the best fitting subset of data preparation algorithms for the given dataset. The proposed method was validated for glioma and prostate single center cohorts by 100-fold Monte Carlo (MC) cross-validation scheme with 80-20% training-validation split ratio. In addition, a dual-center diffuse large B-cell lymphoma (DLBCL) cohort was utilized with Center 1 as training and Center 2 as independent validation datasets to predict cohort-specific clinical endpoints. Five machine learning (ML) classifiers were employed for building prediction models across all analyzed cohorts. Predictive performance was estimated by confusion matrix analytics over the validation sets of each cohort. The performance of each model with and without MLDP, as well as with manually-defined DP were compared in each of the four cohorts. Results: Sixteen of twenty established predictive models demonstrated area under the receiver operator characteristics curve (AUC) performance increase utilizing the MLDP. The MLDP resulted in the highest performance increase for random forest (RF) (+0.16 AUC) and support vector machine (SVM) (+0.13 AUC) model schemes for predicting 36-months survival in the glioma cohort. Single center cohorts resulted in complex (6-7 DP steps) DP pipelines, with a high occurrence of outlier detection, feature selection and synthetic majority oversampling technique (SMOTE). In contrast, the optimal DP pipeline for the dual-center DLBCL cohort only included outlier detection and SMOTE DP steps. Conclusions: This study demonstrates that data preparation prior to ML prediction model building in cancer cohorts shall be ML-driven itself, yielding optimal prediction models in both single and multi-centric settings.

Positron range in combination with point-spread-function correction: an evaluation of different implementations for [124I]-PET imaging.

AIM: To evaluate the effect of combining positron range correction (PRC) with point-spread-function (PSF) correction and to compare different methods of implementation into iterative image reconstruction for 124I-PET imaging. MATERIALS AND METHODS: Uniform PR blurring kernels of 124I were generated using the GATE (GEANT4) framework in various material environments (lung, water, and bone) and matched to a 3D matrix. The kernels size was set to 11 × 11 × 11 based on the maximum PR in water and the voxel size of the PET system. PET image reconstruction was performed using the standard OSEM algorithm, OSEM with PRC implemented before the forward projection (OSEM+PRC simplified) and OSEM with PRC implemented in both forward- and back-projection steps (full implementation) (OSEM+PRC). Reconstructions were repeated with resolution recovery, point-spread function (PSF) included. The methods and kernel variation were validated using different phantoms filled with 124I acquired on a Siemens mCT PET/CT system. The data was evaluated for contrast recovery and image noise. RESULTS: Contrast recovery improved by 2-10% and 4-37% with OSEM+PRC simplified and OSEM+PRC, respectively, depending on the sphere size of the NEMA IQ phantom. Including PSF in the reconstructions further improved contrast by 4-19% and 3-16% with the PSF+PRC simplified and PSF+PRC, respectively. The benefit of PRC was more pronounced within low-density material. OSEM-PRC and OSEM-PSF as well as OSEM-PSF+PRC in its full- and simplified implementation showed comparable noise and convergence. OSEM-PRC simplified showed comparably faster convergence but at the cost of increased image noise. CONCLUSIONS: The combination of the PSF and PRC leads to increased contrast recovery with reduced image noise compared to stand-alone PSF or PRC reconstruction. For OSEM-PRC reconstructions, a full implementation in the reconstruction is necessary to handle image noise. For the combination of PRC with PSF, a simplified PRC implementation can be used to reduce reconstruction times.

Multi-lesion radiomics of PET/CT for non-invasive survival stratification and histologic tumor risk profiling in patients with lung adenocarcinoma.

OBJECTIVES: This study investigates the ability of machine learning (ML) models trained on clinical data and 2-deoxy-2-[18F]fluoro-D-glucose(FDG) positron emission tomography/computed tomography (PET/CT) radiomics to predict overall survival (OS), tumor grade (TG), and histologic growth pattern risk (GPR) in lung adenocarcinoma (LUAD) patients. METHODS: A total of 421 treatment-naive patients with histologically-proven LUAD and available FDG PET/CT imaging were retrospectively included. Four cohorts were assessed for predicting 4-year OS (n = 276), 3-year OS (n = 280), TG (n = 298), and GPR (n = 265). FDG-avid lesions were delineated, and 2082 radiomics features were extracted and combined with endpoint-specific clinical parameters. ML models were built for the prediction of 4-year OS (M4OS), 3-year OS (M3OS), tumor grading (MTG), and histologic growth pattern risk (MGPR). A 100-fold Monte Carlo cross-validation with 80:20 training to validation split was employed as a performance evaluation for all models. The association between the M4OS and M3OS predictions with OS was assessed by the Kaplan-Meier survival analysis. RESULTS: The area under the receiver operator characteristics curve (AUC) was the highest for M4OS (AUC 0.88, 95% confidence interval (CI) 86.7-88.7), followed by M3OS (AUC 0.84, CI 82.9-84.9), while MTG and MGPR performed equally well (AUC 0.76, CI 74.4-77.9, CI 74.6-78, respectively). Predictions of M4OS (hazard ratio (HR) -2.4, CI -2.47 to -1.64, p < 0.05) and M3OS (HR -2.36, CI -2.79 to -1.93, p < 0.05) were independently associated with OS. CONCLUSION: ML models are able to predict long-term survival outcomes in LUAD patients with high accuracy. Furthermore, histologic grade and predominant growth pattern risk can be predicted with satisfactory accuracy. KEY POINTS: • Machine learning models trained on pre-therapeutic PET/CT radiomics enable highly accurate long-term survival prediction of patients with lung adenocarcinoma. • Highly accurate survival predictions are achieved in lung adenocarcinoma patients despite heterogenous histologies and treatment regimens. • Radiomic machine learning models are able to predict lung adenocarcinoma tumor grade and histologic growth pattern risk with satisfactory accuracy.

A multi-modality physical phantom for mimicking tumor heterogeneity patterns in PET/CT and PET/MRI.

BACKGROUND: Hybrid imaging (e.g., positron emission tomography [PET]/computed tomography [CT], PET/magnetic resonance imaging [MRI]) helps one to visualize and quantify morphological and physiological tumor characteristics in a single study. The noninvasive characterization of tumor heterogeneity is essential for grading, treatment planning, and following-up oncological patients. However, conventional (CONV) image-based parameters, such as tumor diameter, tumor volume, and radiotracer activity uptake, are insufficient to describe tumor heterogeneities. Here, radiomics shows promise for a better characterization of tumors. Nevertheless, the validation of such methods demands imaging objects capable of reflecting heterogeneities in multi-modality imaging. We propose a phantom to simulate tumor heterogeneity repeatably in PET, CT, and MRI. METHODS: The phantom consists of three 50-ml plastic tubes filled partially with acrylic spheres of S1: 1.6 mm, S2: 50%(1.6 mm)/50%(6.3 mm), or S3: 6.3-mm diameter. The spheres were fixed to the bottom of each tube by a plastic grid, yielding one sphere free homogeneous region and one heterogeneous (S1, S2, or S3) region per tube. A 3-tube phantom and its replica were filled with a fluorodeoxyglucose (18F) solution for test-retest measurements in a PET/CT Siemens TPTV and a PET/MR Siemens Biograph mMR system. A number of 42 radiomic features (10 first order and 32 texture features) were calculated for each phantom region and imaging modality. Radiomic features stability was evaluated through coefficients of variation (COV) across phantoms and scans for PET, CT, and MRI. Further, the Wilcoxon test was used to assess the capability of stable features to discriminate the simulated phantom regions. RESULTS: The different patterns (S1-S3) did present visible heterogeneity in all imaging modalities. However, only for CT and MRI, a clear visual difference was present between the different patterns. Across all phantom regions in PET, CT, and MR images, 10, 16, and 21 features out of 42 evaluated features in total had a COV of 10% or less. In particular, CONV, histogram, and gray-level run length matrix features showed high repeatability for all the phantom regions and imaging modalities. Several of repeatable texture features allowed the image-based discrimination of the different phantom regions (p < 0.05). However, depending on the feature, different pattern discrimination capabilities were found for the different imaging modalities. CONCLUSION: The proposed phantom appears suitable for simulating heterogeneities in PET, CT, and MRI. We demonstrate that it is possible to select radiomic features for the readout of the phantom. Most of these features had been shown to be relevant in previous clinical studies.

Two-Year Event-Free Survival Prediction in DLBCL Patients Based on In Vivo Radiomics and Clinical Parameters.

Purpose: For the identification of high-risk patients in diffuse large B-cell lymphoma (DLBCL), we investigated the prognostic significance of in vivo radiomics derived from baseline [18F]FDG PET/CT and clinical parameters. Methods: Pre-treatment [18F]FDG PET/CT scans of 85 patients diagnosed with DLBCL were assessed. The scans were carried out in two clinical centers. Two-year event-free survival (EFS) was defined. After delineation of lymphoma lesions, conventional PET parameters and in vivo radiomics were extracted. For 2-year EFS prognosis assessment, the Center 1 dataset was utilized as the training set and underwent automated machine learning analysis. The dataset of Center 2 was utilized as an independent test set to validate the established predictive model built by the dataset of Center 1. Results: The automated machine learning analysis of the Center 1 dataset revealed that the most important features for building 2-year EFS are as follows: max diameter, neighbor gray tone difference matrix (NGTDM) busyness, total lesion glycolysis, total metabolic tumor volume, and NGTDM coarseness. The predictive model built on the Center 1 dataset yielded 79% sensitivity, 83% specificity, 69% positive predictive value, 89% negative predictive value, and 0.85 AUC by evaluating the Center 2 dataset. Conclusion: Based on our dual-center retrospective analysis, predicting 2-year EFS built on imaging features is feasible by utilizing high-performance automated machine learning.

Analysis of Cross-Combinations of Feature Selection and Machine-Learning Classification Methods Based on [18F]F-FDG PET/CT Radiomic Features for Metabolic Response Prediction of Metastatic Breast Cancer Lesions.

BACKGROUND: This study aimed to identify optimal combinations between feature selection methods and machine-learning classifiers for predicting the metabolic response of individual metastatic breast cancer lesions, based on clinical variables and radiomic features extracted from pretreatment [18F]F-FDG PET/CT images. METHODS: A total of 48 patients with confirmed metastatic breast cancer, who received different treatments, were included. All patients had an [18F]F-FDG PET/CT scan before and after the treatment. From 228 metastatic lesions identified, 127 were categorized as responders (complete or partial metabolic response) and 101 as non-responders (stable or progressive metabolic response), by using the percentage changes in SULpeak (peak standardized uptake values normalized for body lean body mass). The lesion pool was divided into training (n = 182) and testing cohorts (n = 46); for each lesion, 101 image features from both PET and CT were extracted (202 features per lesion). These features, along with clinical and pathological information, allowed the prediction model's construction by using seven popular feature selection methods in cross-combination with another seven machine-learning (ML) classifiers. The performance of the different models was investigated with the receiver-operating characteristic curve (ROC) analysis, using the area under the curve (AUC) and accuracy (ACC) metrics. RESULTS: The combinations, least absolute shrinkage and selection operator (Lasso) + support vector machines (SVM), or random forest (RF) had the highest AUC in the cross-validation, with 0.93 ± 0.06 and 0.92 ± 0.03, respectively, whereas Lasso + neural network (NN) or SVM, and mutual information (MI) + RF, had the higher AUC and ACC in the validation cohort, with 0.90/0.72, 0.86/0.76, and 87/85, respectively. On average, the models with Lasso and models with SVM had the best mean performance for both AUC and ACC in both training and validation cohorts. CONCLUSIONS: Image features obtained from a pretreatment [18F]F-FDG PET/CT along with clinical vaiables could predict the metabolic response of metastatic breast cancer lesions, by their incorporation into predictive models, whose performance depends on the selected combination between feature selection and ML classifier methods.

Molecular and Cytogenetic Analysis of rDNA Evolution in Crepis Sensu Lato.

Although Crepis was the first model plant group in which chromosomal changes were considered to play an important role in speciation, their chromosome structure and evolution have been barely investigated using molecular cytogenetic methods. The aim of the study was to provide a better understanding of the patterns and directions of Crepis chromosome evolution, using comparative analyses of rDNA loci number and localisation. The chromosome base number and chromosomal organisation of 5S and 35S rDNA loci were analysed in the phylogenetic background for 39 species of Crepis, which represent the evolutionary lineages of Crepis sensu stricto and Lagoseris, including Lapsana communis. The phylogenetic relationships among all the species were inferred from nrITS and newly obtained 5S rDNA NTS sequences. Despite high variations in rDNA loci chromosomal organisation, most species had a chromosome with both rDNA loci within the same (usually short) chromosomal arm. The comparative analyses revealed several independent rDNA loci number gains and loci repositioning that accompanied diversification and speciation in Crepis. Some of the changes in rDNA loci patterns were reconstructed for the same evolutionary lineages as descending dysploidy.