Diagnosis and prognosis of abnormal cardiac scintigraphy uptake suggestive of cardiac amyloidosis using artificial intelligence: a retrospective, international, multicentre, cross-tracer development and validation study.

BACKGROUND: The diagnosis of cardiac amyloidosis can be established non-invasively by scintigraphy using bone-avid tracers, but visual assessment is subjective and can lead to misdiagnosis. We aimed to develop and validate an artificial intelligence (AI) system for standardised and reliable screening of cardiac amyloidosis-suggestive uptake and assess its prognostic value, using a multinational database of 99mTc-scintigraphy data across multiple tracers and scanners. METHODS: In this retrospective, international, multicentre, cross-tracer development and validation study, 16 241 patients with 19 401 scans were included from nine centres: one hospital in Austria (consecutive recruitment Jan 4, 2010, to Aug 19, 2020), five hospital sites in London, UK (consecutive recruitment Oct 1, 2014, to Sept 29, 2022), two centres in China (selected scans from Jan 1, 2021, to Oct 31, 2022), and one centre in Italy (selected scans from Jan 1, 2011, to May 23, 2023). The dataset included all patients referred to whole-body 99mTc-scintigraphy with an anterior view and all 99mTc-labelled tracers currently used to identify cardiac amyloidosis-suggestive uptake. Exclusion criteria were image acquisition at less than 2 h (99mTc-3,3-diphosphono-1,2-propanodicarboxylic acid, 99mTc-hydroxymethylene diphosphonate, and 99mTc-methylene diphosphonate) or less than 1 h (99mTc-pyrophosphate) after tracer injection and if patients' imaging and clinical data could not be linked. Ground truth annotation was derived from centralised core-lab consensus reading of at least three independent experts (CN, TT-W, and JN). An AI system for detection of cardiac amyloidosis-associated high-grade cardiac tracer uptake was developed using data from one centre (Austria) and independently validated in the remaining centres. A multicase, multireader study and a medical algorithmic audit were conducted to assess clinician performance compared with AI and to evaluate and correct failure modes. The system's prognostic value in predicting mortality was tested in the consecutively recruited cohorts using cox proportional hazards models for each cohort individually and for the combined cohorts. FINDINGS: The prevalence of cases positive for cardiac amyloidosis-suggestive uptake was 142 (2%) of 9176 patients in the Austrian, 125 (2%) of 6763 patients in the UK, 63 (62%) of 102 patients in the Chinese, and 103 (52%) of 200 patients in the Italian cohorts. In the Austrian cohort, cross-validation performance showed an area under the curve (AUC) of 1·000 (95% CI 1·000-1·000). Independent validation yielded AUCs of 0·997 (0·993-0·999) for the UK, 0·925 (0·871-0·971) for the Chinese, and 1·000 (0·999-1·000) for the Italian cohorts. In the multicase multireader study, five physicians disagreed in 22 (11%) of 200 cases (Fleiss' kappa 0·89), with a mean AUC of 0·946 (95% CI 0·924-0·967), which was inferior to AI (AUC 0·997 [0·991-1·000], p=0·0040). The medical algorithmic audit demonstrated the system's robustness across demographic factors, tracers, scanners, and centres. The AI's predictions were independently prognostic for overall mortality (adjusted hazard ratio 1·44 [95% CI 1·19-1·74], p<0·0001). INTERPRETATION: AI-based screening of cardiac amyloidosis-suggestive uptake in patients undergoing scintigraphy was reliable, eliminated inter-rater variability, and portended prognostic value, with potential implications for identification, referral, and management pathways. FUNDING: Pfizer.

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.

Mitochondrial polymorphism m.3017C>T of SHLP6 relates to heterothermy.

Heterothermic thermoregulation requires intricate regulation of metabolic rate and activation of pro-survival factors. Eliciting these responses and coordinating the necessary energy shifts likely involves retrograde signalling by mitochondrial-derived peptides (MDPs). Members of the group were suggested before to play a role in heterothermic physiology, a key component of hibernation and daily torpor. Here we studied the mitochondrial single-nucleotide polymorphism (SNP) m.3017C>T that resides in the evolutionarily conserved gene MT-SHLP6. The substitution occurring in several mammalian orders causes truncation of SHLP6 peptide size from twenty to nine amino acids. Public mass spectrometric (MS) data of human SHLP6 indicated a canonical size of 20 amino acids, but not the use of alternative translation initiation codons that would expand the peptide. The shorter isoform of SHLP6 was found in heterothermic rodents at higher frequency compared to homeothermic rodents (p < 0.001). In heterothermic mammals it was associated with lower minimal body temperature (T b, p < 0.001). In the thirteen-lined ground squirrel, brown adipose tissue-a key organ required for hibernation, showed dynamic changes of the steady-state transcript level of mt-Shlp6. The level was significantly higher before hibernation and during interbout arousal and lower during torpor and after hibernation. Our finding argues to further explore the mode of action of SHLP6 size isoforms with respect to mammalian thermoregulation and possibly mitochondrial retrograde signalling.

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.

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.

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.

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.

Bleeding Risk Assessment in End-Stage Kidney Disease: Validation of Existing Risk Scores and Evaluation of a Machine Learning-Based Approach.

BACKGROUND: Patients with end-stage kidney disease (ESKD) on hemodialysis (HD) are at increased risk for bleeding. However, despite relevant clinical implications regarding dialysis modalities or anticoagulation, no bleeding risk assessment strategy has been established in this challenging population. METHODS: Analyses on bleeding risk assessment models were performed in the population-based Vienna InVestigation of Atrial fibrillation and thromboemboLism in patients on hemoDialysIs (VIVALDI) study including 625 patients. In this cohort study, patients were prospectively followed for a median observation period of 3.5 years for the occurrence of major bleeding. First, performances of existing bleeding risk scores (i.e., HAS-BLED, HEMORR2HAGES, ATRIA, and four others) were evaluated in terms of discrimination and calibration. Second, four machine learning-based prediction models that included clinical, dialysis-specific, and laboratory parameters were developed and tested using Monte Carlo cross-validation. RESULTS: Of 625 patients (median age: 66 years, 37% women), 89 (14.2%) developed major bleeding, with a 1-year, 2-year, and 3-year cumulative incidence of 6.1% (95% confidence interval [CI]: 4.2-8.0), 10.3% (95% CI: 8.0-12.8), and 13.5% (95% CI: 10.8-16.2), respectively. C-statistics of the seven contemporary bleeding risk scores ranged between 0.54 and 0.59 indicating poor discriminatory performance. The HAS-BLED score showed the highest C-statistic of 0.59 (95% CI: 0.53-0.66). Similarly, all four machine learning-based predictions models performed poorly in internal validation (C-statistics ranging from 0.49 to 0.55). CONCLUSION: Existing bleeding risk scores and a machine learning approach including common clinical parameters fail to assist in bleeding risk prediction of patients on HD. Therefore, new approaches, including novel biomarkers, to improve bleeding risk prediction in patients on HD are needed.

Toward Quantitative in vivo Label-Free Tracking of Lipid Distribution in a Zebrafish Cancer Model.

Cancer cells often adapt their lipid metabolism to accommodate the increased fatty acid demand for membrane biogenesis and energy production. Upregulation of fatty acid uptake from the environment of cancer cells has also been reported as an alternative mechanism. To investigate the role of lipids in tumor onset and progression and to identify potential diagnostic biomarkers, lipids are ideally imaged directly within the intact tumor tissue in a label-free way. In this study, we investigated lipid accumulation and distribution in living zebrafish larvae developing a tumor by means of coherent anti-Stokes Raman scattering microscopy. Quantitative textural features based on radiomics revealed higher lipid accumulation in oncogene-expressing larvae compared to healthy ones. This high lipid accumulation could reflect an altered lipid metabolism in the hyperproliferating oncogene-expressing cells.

Morpho-Molecular Metabolic Analysis and Classification of Human Pituitary Gland and Adenoma Biopsies Based on Multimodal Optical Imaging.

Pituitary adenomas count among the most common intracranial tumors. During pituitary oncogenesis structural, textural, metabolic and molecular changes occur which can be revealed with our integrated ultrahigh-resolution multimodal imaging approach including optical coherence tomography (OCT), multiphoton microscopy (MPM) and line scan Raman microspectroscopy (LSRM) on an unprecedented cellular level in a label-free manner. We investigated 5 pituitary gland and 25 adenoma biopsies, including lactotroph, null cell, gonadotroph, somatotroph and mammosomatotroph as well as corticotroph. First-level binary classification for discrimination of pituitary gland and adenomas was performed by feature extraction via radiomic analysis on OCT and MPM images and achieved an accuracy of 88%. Second-level multi-class classification was performed based on molecular analysis of the specimen via LSRM to discriminate pituitary adenomas subtypes with accuracies of up to 99%. Chemical compounds such as lipids, proteins, collagen, DNA and carotenoids and their relation could be identified as relevant biomarkers, and their spatial distribution visualized to provide deeper insight into the chemical properties of pituitary adenomas. Thereby, the aim of the current work was to assess a unique label-free and non-invasive multimodal optical imaging platform for pituitary tissue imaging and to perform a multiparametric morpho-molecular metabolic analysis and classification.

Breast Tumor Characterization Using [18F]FDG-PET/CT Imaging Combined with Data Preprocessing and Radiomics.

Background: This study investigated the performance of ensemble learning holomic models for the detection of breast cancer, receptor status, proliferation rate, and molecular subtypes from [18F]FDG-PET/CT images with and without incorporating data pre-processing algorithms. Additionally, machine learning (ML) models were compared with conventional data analysis using standard uptake value lesion classification. Methods: A cohort of 170 patients with 173 breast cancer tumors (132 malignant, 38 benign) was examined with [18F]FDG-PET/CT. Breast tumors were segmented and radiomic features were extracted following the imaging biomarker standardization initiative (IBSI) guidelines combined with optimized feature extraction. Ensemble learning including five supervised ML algorithms was utilized in a 100-fold Monte Carlo (MC) cross-validation scheme. Data pre-processing methods were incorporated prior to machine learning, including outlier and borderline noisy sample detection, feature selection, and class imbalance correction. Feature importance in each model was assessed by calculating feature occurrence by the R-squared method across MC folds. Results: Cross validation demonstrated high performance of the cancer detection model (80% sensitivity, 78% specificity, 80% accuracy, 0.81 area under the curve (AUC)), and of the triple negative tumor identification model (85% sensitivity, 78% specificity, 82% accuracy, 0.82 AUC). The individual receptor status and luminal A/B subtype models yielded low performance (0.46-0.68 AUC). SUVmax model yielded 0.76 AUC in cancer detection and 0.70 AUC in predicting triple negative subtype. Conclusions: Predictive models based on [18F]FDG-PET/CT images in combination with advanced data pre-processing steps aid in breast cancer diagnosis and in ML-based prediction of the aggressive triple negative breast cancer subtype.

Transcription factors CP2 and YY1 as prognostic markers in head and neck squamous cell carcinoma: analysis of The Cancer Genome Atlas and a second independent cohort.

PURPOSE: The transcription factors YY1 and CP2 have been associated with tumor promotion and suppression in various cancers. Recently, simultaneous expression of both markers was correlated with negative prognosis in cancer. The aim of this study was to explore the expression of YY1 and CP2 in head and neck squamous cell carcinoma (HNSCC) patients and their association with survival. METHODS: First, we analyzed mRNA expression and copy number variations (CNVs) of YY1 and CP2 using "The Cancer Genome Atlas" (TCGA) with 510 HNSCC patients. Secondly, protein expression was investigated via immunohistochemistry in 102 patients, who were treated in the Vienna General Hospital, utilizing a tissue microarray. RESULTS: The median follow-up was 2.9 years (1.8-4.6) for the TCGA cohort and 10.3 years (6.5-12.8) for the inhouse tissue micro-array (TMA) cohort. The median overall survival of the TCGA cohort was decreased for patients with a high YY1 mRNA expression (4.0 vs. 5.7 years, p = 0.030, corr. p = 0.180) and high YY1-CNV (3.53 vs. 5.4 years, p = 0.0355, corr. p = 0.213). Furthermore, patients with a combined high expression of YY1 and CP2 mRNA showed a worse survival (3.5 vs. 5.4 years, p = 0.003, corr. p = 0.018). The mortality rate of patients with co-expression of YY1 and CP2 mRNA was twice as high compared to patients with low expression of one or both (HR 1.99, 95% CI 1.11-3.58, p = 0.021). Protein expression of nuclear YY1 and CP2 showed no association with disease outcome in our inhouse cohort. CONCLUSION: Our data indicate that simultaneous expression of YY1 and CP2 mRNA is associated with shorter overall survival. Thus, combined high mRNA expression might be a suitable prognostic marker for risk stratification in HNSCC patients. However, since we could not validate this finding at genomic or protein level, we hypothesize that unknown underlying mechanisms which regulate mRNA transcription of YY1 and CP2 are the actual culprits leading to a worse survival.