Preliminary Detection Research Articles

A metagenomic investigation of phytoplasma diversity in Australian vegetable growing regions.

In this study, metagenomic sequence data was used to investigate the phytoplasma taxonomic diversity in vegetable-growing regions across Australia. Metagenomic sequencing was performed on 195 phytoplasma-positive samples, originating either from historic collections (n=46) or during collection efforts between January 2015 and June 2022 (n=149). The sampled hosts were classified as crop (n=155), weed (n=24), ornamental (n=7), native plant (n=6), and insect (n=3) species. Most samples came from Queensland (n=78), followed by Western Australia (n=46), the Northern Territory (n=32), New South Wales (n=17), and Victoria (n=10). Of the 195 draft phytoplasma genomes, 178 met our genome criteria for comparison using an average nucleotide identity approach. Ten distinct phytoplasma species were identified and could be classified within the 16SrII, 16SrXII (PCR only), 16SrXXV, and 16SrXXXVIII phytoplasma groups, which have all previously been recorded in Australia. The most commonly detected phytoplasma taxa in this study were species and subspecies classified within the 16SrII group (n=153), followed by strains within the 16SrXXXVIII group ('Ca. Phytoplasma stylosanthis'; n=6). Several geographic- and host-range expansions were reported, as well as mixed phytoplasma infections of 16SrII taxa and 'Ca. Phytoplasma stylosanthis'. Additionally, six previously unrecorded 16SrII taxa were identified, including five putative subspecies of 'Ca. Phytoplasma australasiaticum' and a new putative 16SrII species. PCR and sequencing of the 16S rRNA gene was a suitable triage tool for preliminary phytoplasma detection. Metagenomic sequencing, however, allowed for higher-resolution identification of the phytoplasmas, including mixed infections, than was afforded by only direct Sanger sequencing of the 16S rRNA gene. Since the metagenomic approach theoretically obtains sequences of all organisms in a sample, this approach was useful to confirm the host family, genus, and/or species. In addition to improving our understanding of the phytoplasma species that affect crop production in Australia, the study also significantly expands the genomic sequence data available in public sequence repositories to contribute to phytoplasma molecular epidemiology studies, revision of taxonomy, and improved diagnostics.

Molecular epidemiology and phylogenetic analysis of feline calicivirus in Kunshan, China

Feline calicivirus (FCV) is a highly contagious virus in cats, which typically causes respiratory tract and oral infections. Despite vaccination against FCV being a regular practice in China, new FCV cases still occur. Antigenic diversity of FCV hinders the effective control by vaccination. This is first report which aims to investigate the molecular epidemiology and molecular characteristics of FCV in Kunshan, China. The nasopharyngeal swabs were collected from cats showing variable clinical signs from different animal clinics in Kunshan from 2022 to 2023. Preliminary detection and sequencing of the FCV capsid gene were performed to study genetic diversity and evolutionary characteristics. FCV-RNA was identified in 52 (26%) of the samples using RT-PCR. A significant association was found between FCV-positive detection rate, age, gender, vaccination status and living environment, while a non-significant association was found with breed of cats. Nucleotide analysis revealed two genotypes, GI and GII. GII predominated in Kunshan, with diverse strains and amino acid variations potentially affecting vaccination efficacy and FCV detection. Notably, analysis pinpointed certain strains’ association with FCV-virulent systemic disease pathotypes. This investigation sheds light on FCV dynamics, which may aid in developing better prevention strategies and future vaccine designs against circulating FCV genotypes.

Reliability of river fleet vessels hull elements

Improving the process of fault detection of metal ship hull elements by using a probabilistic approach is considered in the paper. The most labor-intensive part of the defect detection report, namely, measurement and assessment of hull structures individual elements wear, accounting for more than 90 % of the total measurements, is reviewed. Defect detection of a ship hull means the examination, measurement and assessment of defects in each element of the ship hull in order to establish method and volumes of repairs that ensure its reliable operation until the next survey under specified operating conditions. The necessity of carrying out a preliminary calculation stage for defect detection is substantiated. It allows you to significantly reduce the number of measurements of hull structures elements, which will have a positive effect on reducing the cost of repair both due to a smaller number of measurements and the duration of repairs. It has been proved that using the probability approach to predict the residual thickness of individual elements also takes into account the effect on the total strength, which guarantees the reliability of the ship hull in operation. Tables to assess the technical condition of individual hull elements based on their level of wear have been developed, and a method for filling them has improved. The tables are made in two versions, namely, paper and electronic, the most convenient for a specific user — the designer of the defect detection report tables. A test example of using the electronic tables for assessing technical condition by wear level, which proves that the predicted residual thicknesses obtained by calculation will in all cases, be less, than similar ones obtained from measurements results, is carried out using a representative vessel. This proves the reliability and feasibility of using the preliminary defect detection stage, which is essentially an analogue of the concept of the zero stage in ship repair. Using the probability approach to determine the residual thicknesses will allow you not only to reduce the costs of defect detection of the hull itself, but also at early stages (before placing the ship on a slip or dock) to reduce the volume of hull structures repairs, and to choose the most appropriate and effective method of repair.

Computational Pathology for Prediction of Isocitrate Dehydrogenase Gene Mutation from Whole Slide Images in Adult Patients with Diffuse Glioma

Isocitrate dehydrogenase gene (IDH) mutation is one of the most important molecular markers of glioma. Accurate detection of IDH status is a crucial step for integrated diagnosis of adult-type diffuse gliomas. Herein, a clustering-based hybrid of a convolutional neural network and a vision transformer deep learning model was developed to detect IDH mutation status from annotation-free hematoxylin and eosin-stained whole slide pathologic images of 2275 adult patients with diffuse gliomas. For comparison, a pure convolutional neural network, a pure vision transformer, and a classic multiple-instance learning model were also assessed. The hybrid model achieved an area under the receiver operating characteristic curve of 0.973 in the validation set and 0.953 in the external test set, outperforming the other models. The hybrid model's ability in IDH detection between difficult subgroups with different IDH status but shared histologic features, achieving areas under the receiver operating characteristic curve ranging from 0.850 to 0.985 in validation and test sets. These data suggest that the proposed hybrid model has a potential to be used as a computational pathology tool for preliminary rapid detection of IDH mutation from whole slide images in adult patients with diffuse gliomas.

Theoretical insights into photoinduced excited‐state behaviors for the novel CHPPhl fluorophore: Effects of solvent polarity

AbstractInspired by the distinguished photochemical and photophysical properties of novel hydroxyl‐substituted tetraphenylimidazole (HPI) derivatives that could be potentially applied across various disciplines, in this work, effects of solvent polarity on excited‐state hydrogen bond effects and excited‐state intramolecular proton transfer (ESIPT) reaction of 3‐(6,9‐Diphenyl‐1H‐phenanthro[9,10‐d]imidazole‐2‐yl)‐9‐phenyl‐9H‐carbazol‐4‐ol (CHPPhl) are focused. By comparing the structural changes and infrared (IR) vibrational spectra of the E‐HBT fluorophore in polar acetone, moderate polar tetrahydrofuran and non‐polar hexane solvents, combined with the preliminary detection of hydrogen bond interaction by core–valence bifurcation (CVB) index, we can conclude that the hydrogen bond could be strengthened in S1 state, which is favorable for the occurrence of ESIPT reactions. The charge recombination behavior of hydrogen bond induced by photoexcitation also further illustrates this point. Via constructing potential energy curves (PECs) based on restrictive optimization and searching transition state (TS) form, we confirm change of surrounding solvent polarity has a regulatory effect on the ESIPT behavior for CHPPhl; that is, the lower the solvent polarity is more conducive to the ESIPT reaction.

Theoretical investigation into the effect of atomic electronegativity related chalcogen on ESIPT behaviour for the novel biphenyl-modified 2-(2’-hydroxyphenyl)benzothiazole compounds

Inspired by the remarkable photochemical and photophysical properties of novel 2-(2’-hydroxyphenyl)benzothiazole (HBT) derivatives that could be potentially applied across various disciplines, in this work, effects of atomic electronegativity of chalcogen elements on excited state hydrogen bond effects and excited state intramolecular proton transfer (ESIPT) reaction of the biphenyl-modified HBT derivatives (i.e. HBT-HH-O, HBT-HH-S and HBT-HH-Se) are focused. By comparing the structural changes and infrared (IR) vibrational spectra of the HBT-HH fluorophores in toluene solvent, combined with the preliminary detection of hydrogen bond interaction by core-valence bifurcation (CVB) index, we can conclude that the hydrogen bond could be strengthened in S1 state, which is favourable for the occurrence of ESIPT reactions. The charge recombination behaviour of hydrogen bond induced by photoexcitation also further illustrates this point. Via constructing potential energy curves (PECs) based on restrictive optimisation and searching transition state (TS) form, we confirm the variations of atomic electronegativity of chalcogen have the regulatory effect on the ESIPT behaviour for HBT-HH derivatives, that is, the lower the atomic electronegativity is more conducive to the ESIPT reaction.

Molecular characterization of canine parvovirus type 2 (CPV2) reveals a high prevalence of the CPV2c genotype among dogs suffering from diarrhea

AbstractCanine parvovirus 2 (CPV-2) is a highly contagious virus in dogs that typically causes hemorrhagic enteritis and a high mortality rate in unvaccinated puppies. The genetic variability and antigenic diversity of CPV-2 hinder its effective prevention of infection by vaccination. To investigate the epidemiology and genetic characteristics of CPV-2 in China, rectal swabs from affected dogs were collected from different animal clinics in Kunshan from 2022 to 2023. Preliminary detection and capsid gene sequencing of CPV-2 were performed using previously described primers and protocols. The overall detection rate for CPV-2 was 16.5% (33/200). A significant association was found between the CPV-2-positivity and clinical signs, age, breed and vaccination status. Sequence analysis revealed the presence of CPV-2c genotypes in all positive samples, which were genetically similar to other Asian CPV-2c strains. Notably, four key mutations (A5G, F267Y, Y324I and Q370R) were detected in all isolates, and one novel mutation (I447M) was detected in three CPV-2 isolates. These mutations in the CPV-2 strains could impact vaccine efficacy and the effectiveness of the virus immune evasion. Surprisingly, no recombination events were observed between the identified CPV-2c strains and reference strains from China. Our data revealed that amino acid residues 324, 426 and 440 of VP2 may under strong selection pressure. This pattern of genetic variation in the CPV-2 lineage warrants continuous laboratory-based surveillance programs in other parts of China to better understand the pattern of seasonal distribution and association between emerging genotypes and the intensity of disease severity.

Self-assembly of simple Schiff base ligand into unique saddle-type [4x4] tetranuclear architecture and its application as selective voltammetric dopamine sensor in aqueous conditions

Dopamine, a crucial catecholamine neurotransmitter, plays essential roles in the operation of the central nervous system in humans. Disrupted dopamine release is associated with neurological disorders and depression, therefore monitoring of dopamine levels is imperative for preliminary disease detection. Development of sensitive and selective sensors for neurotransmitters that function under aqueous conditions is however still challenging, mostly due to the complexity of hybrid nanomaterials that are interacting with the electrode. Here we provide a coordination compound constructed from simple substrates, where subcomponent self-assembly leads to a unique, discrete [4 × 4] saddle-type complex [Cu4(L-H)4(BF4)2(MeOH)2](BF4)2, which was characterized by ESI-MS and FT-IR techniques, including single crystal X-ray diffraction. The Cu4L4 complex was subsequently used for modification of the bare Au electrode based on its accumulation on the electrode surface. The new voltammetric sensor (Au/complex) was applied for dopamine detection alone and in the presence of interfering ascorbic acid by using the Differential Pulse Voltammetry (DPV) techniques under aqueous conditions. In the linear dynamic range (LDR) range from 0.0001 mM to 0.75 mM the dependence of the peak current on dopamine concentration satisfied the following linear regression equation: ip [mA] = 17∙10−2cDA [mM] + 8∙10−2 (R2 = 0.998). Moreover, the excellent limit of dopamine detection (LOD) and the limit of its quantification (LOQ) were established at the level of 5.4 nM and 18.0 nM with accomplished high sensitivity 0.17 A M−1, repeatability as well as reproducibility. Clear separation of the voltammetric signal of dopamine from this one of ascorbic acid, even in the presence of a 100-fold excess of interfering ions found in water, consequently proves that the new prepared sensor can be used as an excellent analytical tool for selective detection of dopamine and ascorbic acid coexisting in the tested samples.

Effects of hydroxychromone rings with chalcogen atoms on ESIPT for 3-hydroxy-2-(5-(5-(5-(3-hydroxy-4-oxo-4H-chromen-2-yl)thiophen-2-yl)thiophen-2-yl)thiophen-2-yl)-4H-chromen-4-one derivatives: A theoretical study

Inspired by fascinating photochemical and photophysical characteristics of novel organic molecules with chalcogenide substitution, this study focuses on exploring the effects of atomic electronegativity of chalcogens (O, S, and Se) on hydrogen bond interactions and proton transfer reaction mechanisms for 3-hydroxy-2-(5-(5-(5-(3-hydroxy-4-oxo-4H-chromen-2-yl)thiophen-2-yl)thiophen-2-yl)thiophen-2-yl)-4H-chromen-4-one (FT). By comparing structural changes and infrared (IR) spectra, combined with preliminary detection of hydrogen bond interaction by core-valence bifurcation (CVB) index, we conclude S1-state hydrogen bond is strengthened, which is favorable for occurrence of ESIPT reaction. Charge recombination and constructed potential energy surfaces (PESs) reveal atomic electronegativity has a regulatory effect on ESIPT behavior for FT derivatives.

Novel graph-based machine-learning technique for viral infectious diseases: application to influenza and hepatitis diseases

Background Most infectious diseases are caused by viruses, fungi, bacteria and parasites. Their ability to easily infect humans and trigger large-scale epidemics makes them a public health concern. Methods for early detection of these diseases have been developed; however, they are hindered by the absence of a unified, interoperable and reusable model. This study seeks to create a holistic and real-time model for swift, preliminary detection of infectious diseases using symptoms and additional clinical data. Materials and methods In this study, we present a medical knowledge graph (MKG) that leverages multiple data sources to analyse connections between different nodes. Medical ontologies were used to enhance the MKG. We applied various graph algorithms to extract key features. The performance of multiple machine-learning (ML) techniques for influenza and hepatitis detection was assessed, selecting multi-layer perceptron (MLP) and random forest (RF) models due to their superior outcomes. The hyperparameters of both graph-based ML models were automatically fine-tuned. Results Both the graph-based MLP and RF models showcased the least loss and error rates, along with the most specific, accurate recall, precision and F1 scores. Their Matthews correlation coefficients were also optimal. When compared with existing ML techniques and findings from the literature, these graph-based ML models manifested superior detection accuracy. Conclusions The graph-based MLP and RF models effectively diagnosed influenza and hepatitis, respectively. This underlines the potential of graph data science in enhancing ML model performance and uncovering concealed relationships in the MKG.

Colorimetric sensor and visual enzyme sheets for sensitive detection of dimethoate residue in vegetables based on laccase-like activity of coral-like silver citrate

The overutilization of dimethoate may lead to its deposition in both the environment and crops, which potentially induces neurological, respiratory, and hepatic abnormalities upon absorption by organisms. Colorimetry can accurately determine dimethoate, but there are still many challenges in the rapid, convenient, and point-of-care detection. Herein, based on the inhibitory effect of dimethoate on the laccase activity of silver citrate (AgCit), a smartphone-assisted colorimetric sensor and rapid detection enzyme sheets were constructed. It was demonstrated that dimethoate could adsorb on the surface of AgCit and inhibit the production of semiquinone radicals in the reaction system. Then, the AgCit laccase activity was inhibited, causing the colorimetry sensor and the enzyme sheets turned light red or even colorless. The constructed sensor has higher sensitivity and the limit of detection for dimethoate is 1.0 μg⋅L−1. Moreover, the developed enzyme sheets have good selectivity and specificity, and display the detection results within 5 min. Thus, the colorimetric sensor and the constructed enzyme sheets are expected to be used for large-scale preliminary detection of dimethoate residues in actual agricultural products.

Effects of substituted chalcogen atoms on excited state reaction for 1-(benzo[d]thiazol-2-yl)-6-substituted-naphthalen-2-ol derivatives

Inspired by the brilliant photophysical properties of novel organic molecules containing chalcogenide substitution, in this work, effects of atomic electronegativity of chalcogen (O, S and Se) on hydrogen bond interactions and proton transfer (PT) reaction are focused. We present the characteristic CN-BTN is the main objective to explore the influence of atomic electronegativity on the hydrogen bond interaction and excited state intramolecular proton transfer (ESIPT) behaviour by photoexcitation. By comparing the structural changes and infrared (IR) vibrational spectra of the CN-BTN derivatives (CN-BTN-O, CN-BTN-S and CN-BTN-Se) fluorophores in S0 and S1 states, combined with the preliminary detection of hydrogen bond interaction by core-valence bifurcation (CVB) index, we can conclude that hydrogen bond is strengthened in S1 state, which is favourable for the occurrence of ESIPT reaction. The charge recombination behaviour of hydrogen bond induced by photoexcitation also further illustrates this point. Via constructing potential energy curves (PECs) based on restrictive optimisation and searching transition state (TS) configuration, we finally clarify the ESIPT mechanism for CN-BTN derivatives. Specially, we confirm change of atomic electronegativity has a regulatory effect on the ESIPT behaviour of CN-BTN derivatives, that is, the lower the atomic electronegativity is more conducive to the ESIPT reaction.

A sensitive Raman spectroscopy sensor for determination cardiac troponin I based on proteolytic peptide magnetic imprinting technology

This paper proposes a selective strategy for quantitative detecting cardiac troponin I (cTnI) in clinical serum samples by using Raman spectroscopy combined with magnetic molecularly imprinted polymers (MMIPs). The signature peptide was selected as a template for molecular imprinting due to its chemical stability and small molecular mass. MMIPs were synthetized with the signature peptide as template and methylacrylic acid as monomer in presence of vinyl-modified magnetic particles. MMIPs with high magnetic character and adsorption properties were able to be stained by Coomassie Brilliant Blue G-250 after the target template was specifically captured, which showing a characteristic absorption peak at Raman shift 1610 cm−1. The Raman signal intensity at 1610 cm−1 showed a linear relationship in the 0.01 to 100 ng·mL−1 concentration range. The recovery of cTnI in serum were 92.7–111.2 % with relative standard deviation in the range of 2.51 % to 8.52 %. This paper has important practical application for preliminary rapid detection of cTnI in clinical serum samples.

A noninvasive multianalytical approach establishment for risk assessment and gastric cancer screening.

Effective screening and early detection are critical to improve the prognosis of gastric cancer (GC). Our study aims to explore noninvasive multianalytical biomarkers and construct integrative models for preliminary risk assessment and GC detection. Whole genomewide methylation marker discovery was conducted with CpG tandems target amplification (CTTA) in cfDNA from large asymptomatic screening participants in a high-risk area of GC. The methylation and mutation candidates were validated simultaneously using one plasma from patients at various gastric lesion stages by multiplex profiling with Mutation Capsule Plus (MCP). Helicobacter pylori specific antibodies were detected with a recomLine assay. Integrated models were constructed and validated by the combination of multianalytical biomarkers. A total of 146 and 120 novel methylation markers were found in CpG islands and promoter regions across the genome with CTTA. The methylation markers together with the candidate mutations were validated with MCP and used to establish a 133-methylation-marker panel for risk assessment of suspicious precancerous lesions and GC cases and a 49-methylation-marker panel as well as a 144-amplicon-mutation panel for GC detection. An integrated model comprising both methylation and specific antibody panels performed better for risk assessment than a traditional model (AUC, 0.83 and 0.63, P < .001). A second model for GC detection integrating methylation and mutation panels also outperformed the traditional model (AUC, 0.82 and 0.68, P = .005). Our study established methylation, mutation and H. pylori-specific antibody panels and constructed two integrated models for risk assessment and GC screening. Our findings provide new insights for a more precise GC screening strategy in the future.

Deep learning with data preprocessing methods for water quality prediction in ultrafiltration

Ultrafiltration (UF) has been widely used to remove colloidal substances and suspended solids in feed water. However, UF membrane breakage can lead to downstream impurities flow, hindering subsequent filtration such as reverse osmosis. Preliminary detection for abnormal water quality after UF is vital for cost-efficient operations, but current predictive models lack accuracy. This study investigated the predictive models using deep learning algorithms, specifically convolutional neural network (CNN) and long short-term memory (LSTM) structures. One month of data was provided from a UF system in a real seawater desalination plant. Unfortunately, conventional CNN and LSTM models struggled to predict sudden turbidity spikes caused by UF membrane damage (R2 < 0.2351). To address this challenge, we proposed a novel approach coupling wavelet signals and raw data. This technique enriched turbidity data with abundant waveform signals, resulting in a significant improvement in predictive accuracy (R2 < 0.9203). Shapley additive explanation demonstrated that the wavelet signals emphasized turbidity spikes, helping models in recognizing the extent of changes. This outcome of this study is the development of highly accurate predictive models for outflow turbidity after UF. These models will enhance the safety and efficiency of UF and subsequent filtration systems, improving their overall performance.

Infrared small target detection based on multi-perception of target features

The rapid and efficient detection of infrared dim and small targets in complex backgrounds is a critical area of research in infrared image processing. When confronted with limited target features, it becomes vital to mine and construct additional features in order to accurately differentiate the target from the surrounding background and noise. This paper presents a novel small infrared target detection method based on multi-perception of target features which involves four main stages. First, two new target features are constructed to reduce the similarity between the target and noise and smooth the background. Second, two designed filters are applied to enhance the significance of the target and achieve preliminary detection. Third, structure tensor analysis is used to remove the significant background edge regions and perceive targets with strong corner characteristics. Finally, pseudo targets are eliminated by utilizing target candidate areas to achieve the final detection. Experimental results demonstrate that this method is faster and more robust compared to existing detection algorithms, with superior adaptability and detection performance.

DiabeticSense: A Non-Invasive, Multi-Sensor, IoT-Based Pre-Diagnostic System for Diabetes Detection Using Breath.

Diabetes mellitus is a widespread chronic metabolic disorder that requires regular blood glucose level surveillance. Current invasive techniques, such as finger-prick tests, often result in discomfort, leading to infrequent monitoring and potential health complications. The primary objective of this study was to design a novel, portable, non-invasive system for diabetes detection using breath samples, named DiabeticSense, an affordable digital health device for early detection, to encourage immediate intervention. The device employed electrochemical sensors to assess volatile organic compounds in breath samples, whose concentrations differed between diabetic and non-diabetic individuals. The system merged vital signs with sensor voltages obtained by processing breath sample data to predict diabetic conditions. Our research used clinical breath samples from 100 patients at a nationally recognized hospital to form the dataset. Data were then processed using a gradient boosting classifier model, and the performance was cross-validated. The proposed system attained a promising accuracy of 86.6%, indicating an improvement of 20.72% over an existing regression technique. The developed device introduces a non-invasive, cost-effective, and user-friendly solution for preliminary diabetes detection. This has the potential to increase patient adherence to regular monitoring.

Research on broiler health status recognition method based on improved YOLOv5

Caged broilers, reared extensively, necessitate timely health assessment to mitigate farming losses. Therefore, accurate detection of broiler health status holds a pivotal role in averting avian disease propagation. In this study, we propose a method for broiler health recognition using YOLOv5′s original structure, augmented with the lightweight mobile-EMO network model. Initially, we replace YOLOv5′s backbone convolutional, pooling, and connectivity layers with the EMO module, except the decoupling header. This substitution crafts an efficient model, amplifying overall performance. The EMO module introduces iRMB, a more effective feature extraction technique capturing diverse-scale feature information. Moreover, a continuous activation function supplants the conventional ReLU, enhancing feature expression. Further, EMO integrates 1×1 inflated convolution and windowed sub-attention, augmenting network performance. Additionally, we employ the SPPF module instead of SPP, replacing Detect with Decoupled Detect, constructing an advanced YOLOv5 network for broiler health state recognition. Through training and evaluation, a deep learning model is formulated, discerning caged broiler health. Experimental outcomes reveal that, even under intricate conditions, health detection attains a 0.959 recall rate, 0.956 accuracy, and 0.978 average accuracy. In comparison with basic YOLOv5, this method heightens average accuracy by 1.5%. Compared to YOLOv7 and YOLOv8, average accuracy increases by 3.1% and 1.8% correspondingly. The proposed approach fosters preliminary intelligent health detection, curbing manual intervention, lowering breeding costs, augmenting farming economics, and referencing health intelligent detection in broiler breeding.

Joint two-stage convolutional neural networks for intracranial aneurysms detection on 3D TOF-MRA

Objective. This study aims to develop a three-dimensional convolutional neural network utilizing computer-aided diagnostic technology to facilitate the detection of intracranial aneurysms and automatically assess their location and extent, thereby enhancing the efficiency of radiologists, and streamlining clinical workflows. Approach. A retrospective study was conducted, proposing a joint segmentation and classification network (JSCD-Net) that employs 3D time-of-flight magnetic resonance angiography images for preliminary detection of aneurysms and the minimization of false positives. Specifically, the U-Net++ network was utilized for pre-detection of aneurysms. This was followed by the creation of a multi-path network, co-trained with U-Net++ to correct the results of the first stage to further reduce the rate of false positives. Model effectiveness and robustness were evaluated using sensitivity and false positive analyses on internal and external datasets. A cross-validated free-response receiver operating characteristic curve was also plotted. Main results. JSCD-Net demonstrated a sensitivity of 91.2% (31 of 34; 95% CI: 77.0, 97.0) with an average of 3.55 false positives per scan on the internal test set. For the external test set, it identified 97.2% (70 of 72; 95% CI: 90.4, 99.2) of aneurysms with an average of 2.7 false positives per scan. Significance. When compared with the existing studies, the proposed model shows high sensitivity in detecting intracranial aneurysms with a reasonable number of false positives per case. This result emphasizes the model’s potential as a valuable tool in aiding clinical diagnoses.

A supervised approach for the detection of AM-FM signals’ interference regions in spectrogram images

Ridge curves retrieval in time–frequency (TF) domains is fundamental in many application fields as they convey most of information concerning the instantaneous frequencies of non-stationary signals. However, it represents a very hard task in the case of multicomponent signals having non-separable modes as they generate interference in TF domains. A preliminary detection of these interference regions may be then useful for the definition of effective strategies for ridge curve recovery. This paper introduces SIID-CNN (Spectrogram Image Interference Detection via CNN), that is a novel approach based on machine learning for the automatic detection of interference regions in spectrogram images. Each spectrogram sample is suitably classified as interference, single mode or background by accounting for its relative information. Some critical problems, such as the training set size and the type of examples to use for populating the training set, are dealt with. Experimental results show that a local linear model for spectrogram image and a small training set can guarantee good classification rates for a wide class of non-stationary signals, even in the presence of moderate noise.