Automated profiling of gene function during embryonic development.

Systematic functional profiling of the gene set that directs embryonic development is an important challenge. To tackle this challenge, we used 4D imaging of C. elegans embryogenesis to capture the effects of 500 gene knockdowns and developed an automated approach to compare developmental phenotypes. The automated approach quantifies features-including germ layer cell numbers, tissue position, and tissue shape-to generate temporal curves whose parameterization yields numerical phenotypic signatures. In conjunction with a new similarity metric that operates across phenotypic space, these signatures enabled the generation of ranked lists of genes predicted to have similar functions, accessible in the PhenoBank web portal, for ∼25% of essential development genes. The approach identified new gene and pathway relationships in cell fate specification and morphogenesis and highlighted the utilization of specialized energy generation pathways during embryogenesis. Collectively, the effort establishes the foundation for comprehensive analysis of the gene set that builds a multicellular organism.

ChIP-AP: an integrated analysis pipeline for unbiased ChIP-seq analysis.

Chromatin immunoprecipitation coupled with sequencing (ChIP-seq) is a technique used to identify protein-DNA interaction sites through antibody pull-down, sequencing and analysis; with enrichment 'peak' calling being the most critical analytical step. Benchmarking studies have consistently shown that peak callers have distinct selectivity and specificity characteristics that are not additive and seldom completely overlap in many scenarios, even after parameter optimization. We therefore developed ChIP-AP, an integrated ChIP-seq analysis pipeline utilizing four independent peak callers, which seamlessly processes raw sequencing files to final result. This approach enables (1) better gauging of peak confidence through detection by multiple algorithms, and (2) more thoroughly surveys the binding landscape by capturing peaks not detected by individual callers. Final analysis results are then integrated into a single output table, enabling users to explore their data by applying selectivity and sensitivity thresholds that best address their biological questions, without needing any additional reprocessing. ChIP-AP therefore presents investigators with a more comprehensive coverage of the binding landscape without requiring additional wet-lab observations.

Advanced Myocardial MRI Tissue Characterization Combining Contrast Agent-Free T1-Rho Mapping With Fully Automated Analysis.

BACKGROUND: Myocardial T1-rho (T1ρ) mapping is a promising method for identifying and quantifying myocardial injuries without contrast agents, but its clinical use is hindered by the lack of dedicated analysis tools. PURPOSE: To explore the feasibility of clinically integrated artificial intelligence-driven analysis for efficient and automated myocardial T1ρ mapping. STUDY TYPE: Retrospective. POPULATION: Five hundred seventy-three patients divided into a training (N = 500) and a test set (N = 73) including ischemic and nonischemic cases. FIELD STRENGTH/SEQUENCE: Single-shot bSSFP T1ρ mapping sequence at 1.5 T. ASSESSMENT: The automated process included: left ventricular (LV) wall segmentation, right ventricular insertion point detection and creation of a 16-segment model for segmental T1ρ value analysis. Two radiologists (20 and 7 years of MRI experience) provided ground truth annotations. Interobserver variability and segmentation quality were assessed using the Dice coefficient with manual segmentation as reference standard. Global and segmental T1ρ values were compared. Processing times were measured. STATISTICAL TESTS: Intraclass correlation coefficients (ICCs) and Bland-Altman analysis (bias ±2SD); Paired Student's t-tests and one-way ANOVA. A P value <0.05 was considered significant. RESULTS: The automated approach significantly reduced processing time (3 seconds vs. 1 minute 51 seconds ± 22 seconds). In the test set, automated LV wall segmentation closely matched manual results (Dice 81.9% ± 9.0) and closely aligned with interobserver segmentation (Dice 82.2% ± 6.5). Excellent ICCs were achieved on a patient basis (0.94 [95% CI: 0.91 to 0.96]) with bias of -0.93 cm2 ± 6.60. There was no significant difference in global T1ρ values between manual (54.9 msec ± 4.6; 95% CI: 53.8 to 56.0 msec, range: 46.6-70.9 msec) and automated processing (55.4 msec ± 5.1; 95% CI: 54.2 to 56.6 msec; range: 46.4-75.1 msec; P = 0.099). The pipeline demonstrated a high level of agreement with manual-derived T1ρ values at the patient level (ICC = 0.85; bias +0.52 msec ± 5.18). No significant differences in myocardial T1ρ values were found between methods across the 16 segments (P = 0.75). DATA CONCLUSION: Automated myocardial T1ρ mapping shows promise for the rapid and noninvasive assessment of heart disease. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 1.

Automated quantitative evaluation of fetal atrioventricular annular plane systolic excursion before and after intrauterine blood transfusion in pregnancies affected by red blood cell alloimmunization.

INTRODUCTION: Maternal red blood cell alloimmunization during pregnancy can lead to hemolysis and various degrees of fetal anemia, which can be treated with intrauterine blood transfusion (IUT) to prevent adverse outcomes. Knowledge about fetal myocardial function and adaptation is limited. The aim of the present study was to measure fetal atrioventricular plane displacement before and after IUT and compare these measurements with previously established reference ranges. MATERIAL AND METHODS: An observational study was conducted on pregnant women affected by red blood cell alloimmunization. Fetal echocardiography was performed before and after IUT. The atrioventricular plane displacement of the left and right ventricular walls and interventricular septum, described as mitral, septal, and tricuspid annular plane systolic excursion (MAPSE, SAPSE, and TAPSE, respectively), was assessed using color tissue Doppler imaging with automated analysis software. A Mann-Whitney U test was used to compare the z scores to the normal mean before and after IUT. RESULTS: Twenty-seven fetuses were included. The mean z score for pre-IUT MAPSE was significantly increased compared with the reference ranges, +0.46 (95% confidence interval [CI] +0.17 to +0.75; p = 0.039), while the mean z scores for post-IUT SAPSE and TAPSE were significantly decreased, -0.65 (95% CI -1.11 to -0.19; p < 0.001) and -0.60 (95% CI -1.04 to -0.17; p = 0.003), respectively. The difference in atrioventricular plane displacement z scores before and after IUT was statistically significant in all three locations. The median difference between the pre-IUT and post-IUT z scores was -0.66 (95% CI -1.03 to -0.33, p < 0.001) for MAPSE, -1.05 (95% CI -1.43 to -0.61, p < 0.001) for SAPSE, and -0.60 (95% CI -1.19 to -0.01, p = 0.046) for TAPSE. CONCLUSIONS: This study suggests that atrioventricular plane displacement, when determined using automated analysis software, may represent a quantitative parameter, describing fetal myocardial function and adaptation before and after IUT.

The Evolving Landscape of Flowcytometric Minimal Residual Disease Monitoring in B-Cell Precursor Acute Lymphoblastic Leukemia.

Detection of minimal residual disease (MRD) is a major independent prognostic marker in the clinical management of pediatric and adult B-cell precursor Acute Lymphoblastic Leukemia (BCP-ALL), and risk stratification nowadays heavily relies on MRD diagnostics. MRD can be detected using flow cytometry based on aberrant expression of markers (antigens) during malignant B-cell maturation. Recent advances highlight the significance of novel markers (e.g., CD58, CD81, CD304, CD73, CD66c, and CD123), improving MRD identification. Second and next-generation flow cytometry, such as the EuroFlow consortium's eight-color protocol, can achieve sensitivities down to 10-5 (comparable with the PCR-based method) if sufficient cells are acquired. The introduction of targeted therapies (especially those targeting CD19, such as blinatumomab or CAR-T19) introduces several challenges for flow cytometric MRD analysis, such as the occurrence of CD19-negative relapses. Therefore, innovative flow cytometry panels, including alternative B-cell markers (e.g., CD22 and CD24), have been designed. (Semi-)automated MRD assessment, employing machine learning algorithms and clustering tools, shows promise but does not yet allow robust and sensitive automated analysis of MRD. Future directions involve integrating artificial intelligence, further automation, and exploring multicolor spectral flow cytometry to standardize MRD assessment and enhance diagnostic and prognostic robustness of MRD diagnostics in BCP-ALL.

Comparison of qualitative and fully automated quantitative tools for classifying severity of white matter hyperintensity.

OBJECTIVE: In this study, we aimed to compare the Fazekas scoring system and quantitative white matter hyperintensity volume in the classification of white matter hyperintensity severity using a fully automated analysis software to investigate the reliability of quantitative evaluation. MATERIALS AND METHODS: Patients with suspected cognitive impairment who underwent medical examinations at our institution between January 2010 and May 2021 were retrospectively examined. White matter hyperintensity volumes were analyzed using fully automated analysis software and Fazekas scoring (scores 0-3). Using one-way analysis of variance, white matter hyperintensity volume differences across Fazekas scores were assessed. We employed post-hoc pairwise comparisons to compare the differences in the mean white matter hyperintensity volume between each Fazekas score. Spearman's rank correlation test was used to investigate the association between Fazekas score and white matter hyperintensity volume. RESULTS: Among the 839 patients included in this study, Fazekas scores 0, 1, 2, and 3 were assigned to 68, 198, 217, and 356 patients, respectively. White matter hyperintensity volumes significantly differed according to Fazekas score (F=623.5, p<0.001). Post-hoc pairwise comparisons revealed significant differences in mean white matter hyperintensity volume between all Fazekas scores (p<0.05). We observed a significantly positive correlation between the Fazekas scores and white matter hyperintensity volume (R=0.823, p<0.01). CONCLUSIONS: Quantitative white matter hyperintensity volume and the Fazekas scores are highly correlated and may be used as indicators of white matter hyperintensity severity. In addition, quantitative analysis may be more effective in classifying advanced white matter hyperintensity lesions than the Fazekas classification.

[Preliminary Study on the Identification of Aerobic Vaginitis by Artificial Intelligence Analysis System]. / 人工智能分析系统对需氧菌性阴道炎的判读方法初探.

Objective: To develop an artificial intelligence vaginal secretion analysis system based on deep learning and to evaluate the accuracy of automated microscopy in the clinical diagnosis of aerobic vaginitis (AV). Methods: In this study, the vaginal secretion samples of 3769 patients receiving treatment at the Department of Obstetrics and Gynecology, West China Second Hospital, Sichuan University between January 2020 and December 2021 were selected. Using the results of manual microscopy as the control, we developed the linear kernel SVM algorithm, an artificial intelligence (AI) automated analysis software, with Python Scikit-learn script. The AI automated analysis software could identify leucocytes with toxic appearance and parabasal epitheliocytes (PBC). The bacterial grading parameters were reset using standard strains of lactobacillus and AV common isolates. The receiver operating characteristic (ROC) curve analysis was used to determine the cut-off value of AV evaluation results for different scoring items were obtained by using the results of manual microscopy as the control. Then, the parameters of automatic AV identification were determined and the automatic AV analysis scoring method was initially established. Results: A total of 3769 vaginal secretion samples were collected. The AI automated analysis system incorporated five parameters and each parameter incorporated three severity scoring levels. We selected 1.5 µm as the cut-off value for the diameter between Lactobacillus and common AV bacterial isolates. The automated identification parameter of Lactobacillus was the ratio of bacteria ≥1.5 µm to those <1.5 µm. The cut-off scores were 2.5 and 0.5, In the parameter of white blood cells (WBC), the cut-off value of the absolute number of WBC was 103 µL－1 and the cut-off value of WBC-to-epithelial cell ratio was 10. The automated identification parameter of toxic WBC was the ratio of toxic WBC toWBC and the cut-off values were 1% and 15%. The parameter of background flora was bacteria<1.5 µm and the cut-off values were 5×103 µL－1 and 3×104 µL－1. The parameter of the parabasal epitheliocytes was the ratio of PBC to epithelial cells and the cut-off values were 1% and 10%. The agreement rate between the results of automated microscopy and those of manual microscopy was 92.5%. Out of 200 samples, automated microscopy and manual microscopy produced consistent scores for 185 samples, while the results for 15 samples were inconsistent. Conclusion: We developed an AI recognition software for AV and established an automated vaginal secretion microscopy scoring system for AV. There was good overall concordance between automated microscopy and manual microscopy. The AI identification software for AV can complete clinical lab examination with rather high objectivity, sensitivity, and efficiency, markedly reducing the workload of manual microscopy.

High-resolution analysis of the cytosolic Ca2+ events in ß cell collectives in situ.

The release of peptide hormones is predominantly regulated by a transient increase in cytosolic Ca2+ concentration ([Ca2+]c). To trigger exocytosis, Ca2+ ions enter the cytosol from intracellular Ca2+ stores or from the extracellular space. The molecular events of late stages of exocytosis, and their dependence on [Ca2+]c, were extensively described in isolated single cells from various endocrine glands. Notably, less work has been done on endocrine cells in situ to address the heterogeneity of [Ca2+]c events contributing to a collective functional response of a gland. For this, ß cell collectives in a pancreatic islet are particularly well suited as they are the smallest, experimentally manageable functional unit, where [Ca2+]c dynamics can be simultaneously assessed on both cellular and collective level. Here, we measured [Ca2+]c transients across all relevant timescales, from a subsecond to a minute time range, using high-resolution imaging with a low-affinity Ca2+ sensor. We quantified the recordings with a novel computational framework for automatic image segmentation and [Ca2+]c event identification. Our results demonstrate that under physiological conditions the duration of [Ca2+]c events is variable, and segregated into three reproducible modes, subsecond, second, and tens of seconds time range, and are a result of a progressive temporal summation of the shortest events. Using pharmacological tools we show that activation of intracellular Ca2+ receptors is both sufficient and necessary for glucose-dependent [Ca2+]c oscillations in ß cell collectives, and that a subset of [Ca2+]c events could be triggered even in the absence of Ca2+ influx across the plasma membrane. In aggregate, our experimental and analytical platform was able to readily address the involvement of intracellular Ca2+ receptors in shaping the heterogeneity of [Ca2+]c responses in collectives of endocrine cells in situ.NEW & NOTEWORTHY Physiological glucose or ryanodine stimulation of ß cell collectives generates a large number of [Ca2+]c events, which can be rapidly assessed with our newly developed automatic image segmentation and [Ca2+]c event identification pipeline. The event durations segregate into three reproducible modes produced by a progressive temporal summation. Using pharmacological tools, we show that activation of ryanodine intracellular Ca2+ receptors is both sufficient and necessary for glucose-dependent [Ca2+]c oscillations in ß cell collectives.

Multiscale quantification of morphological heterogeneity with creation of a predictor of longer survival in glioblastoma.

Intratumor heterogeneity is a main cause of the dismal prognosis of glioblastoma (GBM). Yet, there remains a lack of a uniform assessment of the degree of heterogeneity. With a multiscale approach, we addressed the hypothesis that intratumor heterogeneity exists on different levels comprising traditional regional analyses, but also innovative methods including computer-assisted analysis of tumor morphology combined with epigenomic data. With this aim, 157 biopsies of 37 patients with therapy-naive IDH-wildtype GBM were analyzed regarding the intratumor variance of protein expression of glial marker GFAP, microglia marker Iba1 and proliferation marker Mib1. Hematoxylin and eosin stained slides were evaluated for tumor vascularization. For the estimation of pixel intensity and nuclear profiling, automated analysis was used. Additionally, DNA methylation profiling was conducted separately for the single biopsies. Scoring systems were established to integrate several parameters into one score for the four examined modalities of heterogeneity (regional, cellular, pixel-level and epigenomic). As a result, we could show that heterogeneity was detected in all four modalities. Furthermore, for the regional, cellular and epigenomic level, we confirmed the results of earlier studies stating that a higher degree of heterogeneity is associated with poorer overall survival. To integrate all modalities into one score, we designed a predictor of longer survival, which showed a highly significant separation regarding the OS. In conclusion, multiscale intratumor heterogeneity exists in glioblastoma and its degree has an impact on overall survival. In future studies, the implementation of a broadly feasible heterogeneity index should be considered.

A deep learning system for quantitative assessment of microvascular abnormalities in nailfold capillary images.

OBJECTIVES: Nailfold capillaroscopy is key to timely diagnosis of SSc, but is often not used in rheumatology clinics because the images are difficult to interpret. We aimed to develop and validate a fully automated image analysis system to fill this gap. METHODS: We mimicked the image interpretation strategies of SSc experts, using deep learning networks to detect each capillary in the distal row of vessels and make morphological measurements. We combined measurements from multiple fingers to give a subject-level probability of SSc.We trained the system using high-resolution images from 111 subjects (group A) and tested on images from subjects not in the training set: 132 imaged at high-resolution (group B); 66 imaged with a low-cost digital microscope (group C). Roughly half of each group had confirmed SSc, and half were healthy controls or had primary RP ('normal'). We also estimated the performance of SSc experts. RESULTS: We compared automated SSc probabilities with the known clinical status of patients (SSc versus 'normal'), generating receiver operating characteristic curves (ROCs). For group B, the area under the ROC (AUC) was 97% (94-99%) [median (90% CI)], with equal sensitivity/specificity 91% (86-95%). For group C, the AUC was 95% (88-99%), with equal sensitivity/specificity 89% (82-95%). SSc expert consensus achieved sensitivity 82% and specificity 73%. CONCLUSION: Fully automated analysis using deep learning can achieve diagnostic performance at least as good as SSc experts, and is sufficiently robust to work with low-cost digital microscope images.

Lung ultrasound compared to computed tomography detection and automated quantification of systemic sclerosis-associated interstitial lung disease: preliminary study.

Lung ultrasound (LUS) is a promising tool for detecting systemic sclerosis-associated interstitial lung disease (SSc-ILD). Currently, consensus on the best LUS findings and execution technique is lacking. OBJECTIVES: To compare qualitative and quantitative assessment of B-lines and pleural line (PL) alterations in SSc-ILD with chest computed tomography (CT) analysis. METHODS: During 2021-2022, consecutive SSc patients according to 2013 ACR/EULAR classification criteria underwent pulmonary functional tests (PFTs). On the same day, if a CT was performed over a ± 6 months period, LUS was performed by two certified blinded operators using a 14-scans method. The ≥10 B-lines cut-off proposed by Tardella and the Fairchild's PL criteria fulfilment were selected as qualitative findings. As quantitative assessment, total B-lines number and the quantitative PL score adapted from the semi-quantitative Pinal-Fernandez score were collected. CT scans were evaluated by two thoracic radiologists for ILD presence, with further processing by automated texture analysis software (qCT). RESULTS: 29 SSc patients were enrolled. Both qualitative LUS scores were significantly associated to ILD presence on CT, with Fairchild's PL criteria resulting in slightly more accuracy. Results were confirmed on multivariate analysis. All qualitative and quantitative LUS findings were found to be significantly associated with qCT ILD extension and radiological abnormalities. Mid and basal PL quantitative score correlated with mid and basal qCT ILD extents. Both B-lines and PL alterations differently correlated with PFTs and clinical variables. CONCLUSION: This preliminary study suggests the utility of a comprehensive LUS assessment for SSc-ILD detection compared with CT and qCT.

ModularImageAnalysis (MIA): Assembly of modularised image and object analysis workflows in ImageJ.

ModularImageAnalysis (MIA) is an ImageJ plugin providing a code-free graphical environment in which complex automated analysis workflows can be constructed and distributed. The broad range of included modules cover all stages of a typical analysis workflow, from image loading through image processing, object detection, extraction of measurements, measurement-based filtering, visualisation and data exporting. MIA provides out-of-the-box compatibility with many advanced image processing plugins for ImageJ including Bio-Formats, DeepImageJ, MorphoLibJ and TrackMate, allowing these tools and their outputs to be directly incorporated into analysis workflows. By default, modules support spatially calibrated 5D images, meaning measurements can be acquired in both pixel and calibrated units. A hierarchical object relationship model allows for both parent-child (one-to-many) and partner (many-to-many) relationships to be established. These relationships underpin MIA's ability to track objects through time, represent complex spatial relationships (e.g. topological skeletons) and measure object distributions (e.g. count puncta per cell). MIA features dual graphical interfaces: the 'editing view' offers access to the full list of modules and parameters in the workflow, while the simplified 'processing view' can be configured to display only a focused subset of controls. All workflows are batch-enabled by default, with image files within a specified folder being processed automatically and exported to a single spreadsheet. Beyond the included modules, functionality can be extended both internally, through integration with the ImageJ scripting interface, and externally, by developing third-party Java modules that extend the core MIA framework. Here we describe the design and functionality of MIA in the context of a series of real-world example analyses.

Analysis of urinary oligosaccharide excretion patterns by UHPLC/HRAM mass spectrometry for screening of lysosomal storage disorders.

Oligosaccharidoses, sphingolipidoses and mucolipidoses are lysosomal storage disorders (LSDs) in which defective breakdown of glycan-side chains of glycosylated proteins and glycolipids leads to the accumulation of incompletely degraded oligosaccharides within lysosomes. In metabolic laboratories, these disorders are commonly diagnosed by thin-layer chromatography (TLC) but more recently also mass spectrometry-based approaches have been published. To expand the possibilities to screen for these diseases, we developed an ultra-high-performance liquid chromatography (UHPLC) with a high-resolution accurate mass (HRAM) mass spectrometry (MS) screening platform, together with an open-source iterative bioinformatics pipeline. This pipeline generates comprehensive biomarker profiles and allows for extensive quality control (QC) monitoring. Using this platform, we were able to identify α-mannosidosis, ß-mannosidosis, α-N-acetylgalactosaminidase deficiency, sialidosis, galactosialidosis, fucosidosis, aspartylglucosaminuria, GM1 gangliosidosis, GM2 gangliosidosis (M. Sandhoff) and mucolipidosis II/III in patient samples. Aberrant urinary oligosaccharide excretions were also detected for other disorders, including NGLY1 congenital disorder of deglycosylation, sialic acid storage disease, MPS type IV B and GSD II (Pompe disease). For the latter disorder, we identified heptahexose (Hex7), as a potential urinary biomarker, in addition to glucose tetrasaccharide (Glc4), for the diagnosis and monitoring of young onset cases of Pompe disease. Occasionally, so-called "neonate" biomarker profiles were observed in young patients, which were probably due to nutrition. Our UHPLC/HRAM-MS screening platform can easily be adopted in biochemical laboratories and allows for simple and robust screening and straightforward interpretation of the screening results to detect disorders in which aberrant oligosaccharides accumulate.

Differentiating between epileptic and functional/dissociative seizures using semantic content analysis of transcripts of routine clinic consultations.

The common causes of Transient Loss of Consciousness (TLOC) are syncope, epilepsy, and functional/dissociative seizures (FDS). Simple, questionnaire-based decision-making tools for non-specialists who may have to deal with TLOC (such as clinicians working in primary or emergency care) reliably differentiate between patients who have experienced syncope and those who have had one or more seizures but are more limited in their ability to differentiate between epileptic seizures and FDS. Previous conversation analysis research has demonstrated that qualitative expert analysis of how people talk to clinicians about their seizures can help distinguish between these two TLOC causes. This paper investigates whether automated language analysis - using semantic categories measured by the Linguistic Inquiry and Word Count (LIWC) toolkit - can contribute to the distinction between epilepsy and FDS. Using patient-only talk manually transcribed from recordings of 58 routine doctor-patient clinic interactions, we compared the word frequencies for 21 semantic categories and explored the predictive performance of these categories using 5 different machine learning algorithms. Machine learning algorithms trained using the chosen semantic categories and leave-one-out cross-validation were able to predict the diagnosis with an accuracy of up to 81%. The results of this proof of principle study suggest that the analysis of semantic variables in seizure descriptions could improve clinical decision tools for patients presenting with TLOC.

Automated image quality assessment of mammography phantoms: a systematic review.

BACKGROUND: Computerized image analysis is a viable technique for evaluating image quality as a complement to human observers. PURPOSE: To systematically review the image analysis software used in the assessment of 2D image quality using mammography phantoms. MATERIAL AND METHODS: A systematic search of multiple databases was performed from inception to July 2020 for articles that incorporated computerized analysis of 2D images of physical mammography phantoms to determine image quality. RESULTS: A total of 26 studies were included, 12 were carried out using direct digital imaging and 14 using screen film mammography. The ACR phantom (model-156) was the most frequently evaluated phantom, possibly due to the lack of accepted standard software. In comparison to the inter-observer variations, the computerized image analysis was more consistent in scoring test objects. The template matching method was found to be one of the most reliable algorithms, especially for high-contrast test objects, while several algorithms found low-contrast test objects to be harder to distinguish due to the smaller contrast variations between test objects and their backgrounds. This was particularly true for small object sizes. CONCLUSION: Image analysis software was in agreement with human observers but demonstrated higher consistency and reproducibility of quality evaluation. Additionally, using computerized analysis, several quantitative metrics such as contrast-to-noise ratio (CNR) and the signal-to-noise ratio (SNR) could be used to complement the conventional scoring method. Implementing a computerized approach for monitoring image quality over time would be crucial to detect any deteriorating mammography system before clinical images are impacted.

Long-Term Prognostic Value of Automated Measurements in Nuclear Cardiology: Comparisons with Expert Scoring.

Background and Objectives: Automated methods for the analysis of myocardial perfusion studies have been incorporated into clinical practice, but they are currently used as adjuncts to the visual interpretation. We aimed to investigate the role of automated measurements of summed stress score (SSS), summed rest score (SRS), and summed difference score (SDS) as long-term prognostic markers of morbidity and mortality, in comparison to the prognostic value of expert reading. Materials and Methods: The study was conducted at the Nuclear Medicine Laboratory of the University of Thessaly, in Larissa, Greece. A total of 378 consecutive patients with known or suspected coronary artery disease were enrolled in the study. All participants were referred to our laboratory for the performance of stress/rest myocardial perfusion single photon emission computed tomography. Automated measurements of SSS, SRS, and SDS were obtained by Emory Cardiac Toolbox (ECTb (Version 3.0), Emory University, Atlanta, GA, USA), Myovation (MYO, Xeleris version 3.05, GE Healthcare, Chicago, IL, USA), and Quantitative Perfusion SPECT (QPS (Version 4.0), Cedars-Sinai Medical Center, Los Angeles, CA, USA) software packages. Follow-up data were recorded after phone contacts, as well as through review of hospital records. Results: Expert scoring of SSS and SDS had significantly greater prognostic ability in comparison to all software packages (p < 0.001 for all comparisons). Similarly, ECTb-obtained SRS measurements had significantly lower prognostic ability in comparison to expert scoring (p < 0.001), while expert scoring of SRS showed significantly higher prognostic ability compared to MYO (p = 0.018) and QPS (p < 0.001). Conclusions: Despite the useful contribution of automated analyses in the interpretation of myocardial perfusion studies, expert reading should continue to have a crucial role, not only in clinical decision making, but also in the assessment of prognosis.

Efficient automatic 3D segmentation of cell nuclei for high-content screening.

BACKGROUND: High-content screening (HCS) is a pre-clinical approach for the assessment of drug efficacy. On modern platforms, it involves fluorescent image capture using three-dimensional (3D) scanning microscopy. Segmentation of cell nuclei in 3D images is an essential prerequisite to quantify captured fluorescence in cells for screening. However, this segmentation is challenging due to variabilities in cell confluency, drug-induced alterations in cell morphology, and gradual degradation of fluorescence with the depth of scanning. Despite advances in algorithms for segmenting nuclei for HCS, robust 3D methods that are insensitive to these conditions are still lacking. RESULTS: We have developed an algorithm which first generates a 3D nuclear mask in the original images. Next, an iterative 3D marker-controlled watershed segmentation is applied to downsized images to segment adjacent nuclei under the mask. In the last step, borders of segmented nuclei are adjusted in the original images based on local nucleus and background intensities. The method was developed using a set of 10 3D images. Extensive tests on a separate set of 27 3D images containing 2,367 nuclei demonstrated that our method, in comparison with 6 reference methods, achieved the highest precision (PR = 0.97), recall (RE = 0.88) and F1-score (F1 = 0.93) of nuclei detection. The Jaccard index (JI = 0.83), which reflects the accuracy of nuclei delineation, was similar to that yielded by all reference approaches. Our method was on average more than twice as fast as the reference method that produced the best results. Additional tests carried out on three stacked 3D images comprising heterogenous nuclei yielded average PR = 0.96, RE = 0.84, F1 = 0.89, and JI = 0.80. CONCLUSIONS: The high-performance metrics yielded by the proposed approach suggest that it can be used to reliably delineate nuclei in 3D images of monolayered and stacked cells exposed to cytotoxic drugs.

Automated identification of maximal differential cell populations in flow cytometry data.

We introduce a new cell population score called SpecEnr (specific enrichment) and describe a method that discovers robust and accurate candidate biomarkers from flow cytometry data. Our approach identifies a new class of candidate biomarkers we define as driver cell populations, whose abundance is associated with a sample class (e.g., disease), but not as a result of a change in a related population. We show that the driver cell populations we find are also easily interpretable using a lattice-based visualization tool. Our method is implemented in the R package flowGraph, freely available on GitHub (github.com/aya49/flowGraph) and on BioConductor.

An [18F]FDG-PET/CT deep learning method for fully automated detection of pathological mediastinal lymph nodes in lung cancer patients.

PURPOSE: The identification of pathological mediastinal lymph nodes is an important step in the staging of lung cancer, with the presence of metastases significantly affecting survival rates. Nodes are currently identified by a physician, but this process is time-consuming and prone to errors. In this paper, we investigate the use of artificial intelligence-based methods to increase the accuracy and consistency of this process. METHODS: Whole-body 18F-labelled fluoro-2-deoxyglucose ([18F]FDG) positron emission tomography/computed tomography ([18F]FDG-PET/CT) scans (Philips Gemini TF) from 134 patients were retrospectively analysed. The thorax was automatically located, and then slices were fed into a U-Net to identify candidate regions. These regions were split into overlapping 3D cubes, which were individually predicted as positive or negative using a 3D CNN. From these predictions, pathological mediastinal nodes could be identified. A second cohort of 71 patients was then acquired from a different, newer scanner (GE Discovery MI), and the performance of the model on this dataset was tested with and without transfer learning. RESULTS: On the test set from the first scanner, our model achieved a sensitivity of 0.87 (95% confidence intervals [0.74, 0.94]) with 0.41 [0.22, 0.71] false positives/patient. This was comparable to the performance of an expert. Without transfer learning, on the test set from the second scanner, the corresponding results were 0.53 [0.35, 0.70] and 0.24 [0.10, 0.49], respectively. With transfer learning, these metrics were 0.88 [0.73, 0.97] and 0.69 [0.43, 1.04], respectively. CONCLUSION: Model performance was comparable to that of an expert on data from the same scanner. With transfer learning, the model can be applied to data from a different scanner. To our knowledge it is the first study of its kind to go directly from whole-body [18F]FDG-PET/CT scans to pathological mediastinal lymph node localisation.

Green Extraction Processes for Complex Samples from Vegetable Matrices Coupled with On-Line Detection System: A Critical Review.

The detection of analytes in complex organic matrices requires a series of analytical steps to obtain a reliable analysis. Sample preparation can be the most time-consuming, prolonged, and error-prone step, reducing the reliability of the investigation. This review aims to discuss the advantages and limitations of extracting bioactive compounds, sample preparation techniques, automation, and coupling with on-line detection. This review also evaluates all publications on this topic through a longitudinal bibliometric analysis, applying statistical and mathematical methods to analyze the trends, perspectives, and hot topics of this research area. Furthermore, state-of-the-art green extraction techniques for complex samples from vegetable matrices coupled with analysis systems are presented. Among the extraction techniques for liquid samples, solid-phase extraction was the most common for combined systems in the scientific literature. In contrast, for on-line extraction systems applied for solid samples, supercritical fluid extraction, ultrasound-assisted extraction, microwave-assisted extraction, and pressurized liquid extraction were the most frequent green extraction techniques.