RSC Chem Biol. 2024 Mar 13;5(5):401-417. doi: 10.1039/d3cb00208j. eCollection 2024 May 8.

ABSTRACT

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as docking and molecular dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

PMID:38725911 | PMC:PMC11078210 | DOI:10.1039/d3cb00208j

Sci Rep. 2024 May 9;14(1):10666. doi: 10.1038/s41598-024-61396-6.

ABSTRACT

The railway rivet is one of the most important and easily damaged parts of the connection. If rivets develop cracks during the production process, their load-bearing capacity will be reduced, thereby increasing the risk of failure. Fluorescent magnetic particle flaw detection (FMPFD) is a widely used inspection method for train fasteners. Manual inspection is not only time-consuming but also prone to miss detection, therefore intelligent detection system has important application value. However, the fluorescent crack images obtained by FMPFD present challenges for intelligent detection, such as the dense, multi-scaled and uninstantiated cracks. In addition, there is limited research on fluorescent rivet crack detection. This paper adopts instance segmentation to achieve automatic cracks detection of rivets. A decentralized target center and low overlap rate labeling method is proposed, and a Gaussian-weighted correction post-processing method is introduced to improve the recall rate in the areas of dense cracks. An efficient channel spatial attention mechanism for feature extraction is proposed in order to enhance the detection of multi-scale cracks. For uninstantiated cracks, an improvement of crack detection in uninstantiated regions based on multi task feature learning is proposed, thoroughly utilizing the semantic and spatial features of the fluorescent cracks. The experimental results show that the improved methods are better than the baseline and some cutting-edge algorithms, achieving a recall rate and mAP0.5 of 86.4% and 90.3%. In addition, a single coil non-contact train rivet composite magnetization device is built for rivets that can magnetize different shapes of rivets and has universality.

PMID:38724635 | DOI:10.1038/s41598-024-61396-6

NPJ Digit Med. 2024 May 9;7(1):120. doi: 10.1038/s41746-024-01085-w.

ABSTRACT

Distribution shifts remain a problem for the safe application of regulated medical AI systems, and may impact their real-world performance if undetected. Postmarket shifts can occur for example if algorithms developed on data from various acquisition settings and a heterogeneous population are predominantly applied in hospitals with lower quality data acquisition or other centre-specific acquisition factors, or where some ethnicities are over-represented. Therefore, distribution shift detection could be important for monitoring AI-based medical products during postmarket surveillance. We implemented and evaluated three deep-learning based shift detection techniques (classifier-based, deep kernel, and multiple univariate kolmogorov-smirnov tests) on simulated shifts in a dataset of 130'486 retinal images. We trained a deep learning classifier for diabetic retinopathy grading. We then simulated population shifts by changing the prevalence of patients' sex, ethnicity, and co-morbidities, and example acquisition shifts by changes in image quality. We observed classification subgroup performance disparities w.r.t. image quality, patient sex, ethnicity and co-morbidity presence. The sensitivity at detecting referable diabetic retinopathy ranged from 0.50 to 0.79 for different ethnicities. This motivates the need for detecting shifts after deployment. Classifier-based tests performed best overall, with perfect detection rates for quality and co-morbidity subgroup shifts at a sample size of 1000. It was the only method to detect shifts in patient sex, but required large sample sizes ( > 3 0 ' 000 ). All methods identified easier-to-detect out-of-distribution shifts with small (≤300) sample sizes. We conclude that effective tools exist for detecting clinically relevant distribution shifts. In particular classifier-based tests can be easily implemented components in the post-market surveillance strategy of medical device manufacturers.

PMID:38724581 | DOI:10.1038/s41746-024-01085-w

Sci Rep. 2024 May 9;14(1):10667. doi: 10.1038/s41598-024-60996-6.

ABSTRACT

The study introduces a new online spike encoding algorithm for spiking neural networks (SNN) and suggests new methods for learning and identifying diagnostic biomarkers using three prominent deep learning neural network models: deep BiLSTM, reservoir SNN, and NeuCube. EEG data from datasets related to epilepsy, migraine, and healthy subjects are employed. Results reveal that BiLSTM hidden neurons capture biological significance, while reservoir SNN activities and NeuCube spiking dynamics identify EEG channels as diagnostic biomarkers. BiLSTM and reservoir SNN achieve 90 and 85% classification accuracy, while NeuCube achieves 97%, all methods pinpointing potential biomarkers like T6, F7, C4, and F8. The research bears implications for refining online EEG classification, analysis, and early brain state diagnosis, enhancing AI models with interpretability and discovery. The proposed techniques hold promise for streamlined brain-computer interfaces and clinical applications, representing a significant advancement in pattern discovery across the three most popular neural network methods for addressing a crucial problem. Further research is planned to study how early can these diagnostic biomarkers predict an onset of brain states.

PMID:38724576 | DOI:10.1038/s41598-024-60996-6

Microbiome. 2024 May 9;12(1):84. doi: 10.1186/s40168-024-01805-0.

ABSTRACT

BACKGROUND: Emergence of antibiotic resistance in bacteria is an important threat to global health. Antibiotic resistance genes (ARGs) are some of the key components to define bacterial resistance and their spread in different environments. Identification of ARGs, particularly from high-throughput sequencing data of the specimens, is the state-of-the-art method for comprehensively monitoring their spread and evolution. Current computational methods to identify ARGs mainly rely on alignment-based sequence similarities with known ARGs. Such approaches are limited by choice of reference databases and may potentially miss novel ARGs. The similarity thresholds are usually simple and could not accommodate variations across different gene families and regions. It is also difficult to scale up when sequence data are increasing.

RESULTS: In this study, we developed ARGNet, a deep neural network that incorporates an unsupervised learning autoencoder model to identify ARGs and a multiclass classification convolutional neural network to classify ARGs that do not depend on sequence alignment. This approach enables a more efficient discovery of both known and novel ARGs. ARGNet accepts both amino acid and nucleotide sequences of variable lengths, from partial (30-50 aa; 100-150 nt) sequences to full-length protein or genes, allowing its application in both target sequencing and metagenomic sequencing. Our performance evaluation showed that ARGNet outperformed other deep learning models including DeepARG and HMD-ARG in most of the application scenarios especially quasi-negative test and the analysis of prediction consistency with phylogenetic tree. ARGNet has a reduced inference runtime by up to 57% relative to DeepARG.

CONCLUSIONS: ARGNet is flexible, efficient, and accurate at predicting a broad range of ARGs from the sequencing data. ARGNet is freely available at https://github.com/id-bioinfo/ARGNet , with an online service provided at https://ARGNet.hku.hk . Video Abstract.

PMID:38725076 | DOI:10.1186/s40168-024-01805-0

Plant Methods. 2024 May 9;20(1):61. doi: 10.1186/s13007-024-01188-1.

ABSTRACT

Tomatoes possess significant nutritional and economic value. However, frequent diseases can detrimentally impact their quality and yield. Images of tomato diseases captured amidst intricate backgrounds are susceptible to environmental disturbances, presenting challenges in achieving precise detection and identification outcomes. This study focuses on tomato disease images within intricate settings, particularly emphasizing four prevalent diseases (late blight, gray leaf spot, brown rot, and leaf mold), alongside healthy tomatoes. It addresses challenges such as excessive interference, imprecise lesion localization for small targets, and heightened false-positive and false-negative rates in real-world tomato cultivation settings. To address these challenges, we introduce a novel method for tomato disease detection named TomatoDet. Initially, we devise a feature extraction module integrating Swin-DDETR's self-attention mechanism to craft a backbone feature extraction network, enhancing the model's capacity to capture details regarding small target diseases through self-attention. Subsequently, we incorporate the dynamic activation function Meta-ACON within the backbone network to further amplify the network's ability to depict disease-related features. Finally, we propose an enhanced bidirectional weighted feature pyramid network (IBiFPN) for merging multi-scale features and feeding the feature maps extracted by the backbone network into the multi-scale feature fusion module. This enhancement elevates detection accuracy and effectively mitigates false positives and false negatives arising from overlapping and occluded disease targets within intricate backgrounds. Our approach demonstrates remarkable efficacy, achieving a mean Average Precision (mAP) of 92.3% on a curated dataset, marking an 8.7% point improvement over the baseline method. Additionally, it attains a detection speed of 46.6 frames per second (FPS), adeptly meeting the demands of agricultural scenarios.

PMID:38725014 | DOI:10.1186/s13007-024-01188-1

BMC Pediatr. 2024 May 9;24(1):321. doi: 10.1186/s12887-024-04775-2.

ABSTRACT

BACKGROUND: Radiologic volumetric evaluation of Wilms' tumor (WT) is an important indicator to guide treatment decisions. However, due to the heterogeneity of the tumors, radiologists have main-guard differences in diagnosis that can lead to misdiagnosis and poor treatment. The aim of this study was to explore whether CT-based outlining of WT foci can be automated using deep learning.

METHODS: We included CT intravenous phase images of 105 patients with WT and double-blind outlining of lesions by two radiologists. Then, we trained an automatic segmentation model using nnUnet. The Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD95) were used to assess the performance. Next, we optimized the automatic segmentation results based on the ratio of the three-dimensional diameter of the lesion to improve the performance of volumetric assessment.

RESULTS: The DSC and HD95 was 0.83 ± 0.22 and 10.50 ± 8.98 mm. The absolute difference and percentage difference in tumor size was 72.27 ± 134.84 cm3 and 21.08% ± 30.46%. After optimization according to our method, it decreased to 40.22 ± 96.06 cm3 and 10.16% ± 9.70%.

CONCLUSION: We introduce a novel method that enhances the accuracy of predicting WT volume by integrating AI automated outlining and 3D tumor diameters. This approach surpasses the accuracy of using AI outcomes alone and has the potential to enhance the clinical evaluation of pediatric patients with WT. By intertwining AI outcomes with clinical data, this method becomes more interpretive and offers promising applications beyond Wilms tumor, extending to other pediatric diseases.

PMID:38724944 | DOI:10.1186/s12887-024-04775-2

BMC Bioinformatics. 2024 May 9;25(1):182. doi: 10.1186/s12859-024-05669-x.

ABSTRACT

BACKGROUND: The prediction of drug sensitivity plays a crucial role in improving the therapeutic effect of drugs. However, testing the effectiveness of drugs is challenging due to the complex mechanism of drug reactions and the lack of interpretability in most machine learning and deep learning methods. Therefore, it is imperative to establish an interpretable model that receives various cell line and drug feature data to learn drug response mechanisms and achieve stable predictions between available datasets.

RESULTS: This study proposes a new and interpretable deep learning model, DrugGene, which integrates gene expression, gene mutation, gene copy number variation of cancer cells, and chemical characteristics of anticancer drugs to predict their sensitivity. This model comprises two different branches of neural networks, where the first involves a hierarchical structure of biological subsystems that uses the biological processes of human cells to form a visual neural network (VNN) and an interpretable deep neural network for human cancer cells. DrugGene receives genotype input from the cell line and detects changes in the subsystem states. We also employ a traditional artificial neural network (ANN) to capture the chemical structural features of drugs. DrugGene generates final drug response predictions by combining VNN and ANN and integrating their outputs into a fully connected layer. The experimental results using drug sensitivity data extracted from the Cancer Drug Sensitivity Genome Database and the Cancer Treatment Response Portal v2 reveal that the proposed model is better than existing prediction methods. Therefore, our model achieves higher accuracy, learns the reaction mechanisms between anticancer drugs and cell lines from various features, and interprets the model's predicted results.

CONCLUSIONS: Our method utilizes biological pathways to construct neural networks, which can use genotypes to monitor changes in the state of network subsystems, thereby interpreting the prediction results in the model and achieving satisfactory prediction accuracy. This will help explore new directions in cancer treatment. More available code resources can be downloaded for free from GitHub ( https://github.com/pangweixiong/DrugGene ).

PMID:38724920 | DOI:10.1186/s12859-024-05669-x

BMC Oral Health. 2024 May 9;24(1):500. doi: 10.1186/s12903-024-04274-x.

ABSTRACT

BACKGROUND: Teeth identification has a pivotal role in the dental curriculum and provides one of the important foundations of clinical practice. Accurately identifying teeth is a vital aspect of dental education and clinical practice, but can be challenging due to the anatomical similarities between categories. In this study, we aim to explore the possibility of using a deep learning model to classify isolated tooth by a set of photographs.

METHODS: A collection of 5,100 photographs from 850 isolated human tooth specimens were assembled to serve as the dataset for this study. Each tooth was carefully labeled during the data collection phase through direct observation. We developed a deep learning model that incorporates the state-of-the-art feature extractor and attention mechanism to classify each tooth based on a set of 6 photographs captured from multiple angles. To increase the validity of model evaluation, a voting-based strategy was applied to refine the test set to generate a more reliable label, and the model was evaluated under different types of classification granularities.

RESULTS: This deep learning model achieved top-3 accuracies of over 90% in all classification types, with an average AUC of 0.95. The Cohen's Kappa demonstrated good agreement between model prediction and the test set.

CONCLUSIONS: This deep learning model can achieve performance comparable to that of human experts and has the potential to become a valuable tool for dental education and various applications in accurately identifying isolated tooth.

PMID:38724912 | DOI:10.1186/s12903-024-04274-x

BMC Med Res Methodol. 2024 May 9;24(1):108. doi: 10.1186/s12874-024-02224-3.

ABSTRACT

OBJECTIVE: Systematic literature reviews (SLRs) are critical for life-science research. However, the manual selection and retrieval of relevant publications can be a time-consuming process. This study aims to (1) develop two disease-specific annotated corpora, one for human papillomavirus (HPV) associated diseases and the other for pneumococcal-associated pediatric diseases (PAPD), and (2) optimize machine- and deep-learning models to facilitate automation of the SLR abstract screening.

METHODS: This study constructed two disease-specific SLR screening corpora for HPV and PAPD, which contained citation metadata and corresponding abstracts. Performance was evaluated using precision, recall, accuracy, and F1-score of multiple combinations of machine- and deep-learning algorithms and features such as keywords and MeSH terms.

RESULTS AND CONCLUSIONS: The HPV corpus contained 1697 entries, with 538 relevant and 1159 irrelevant articles. The PAPD corpus included 2865 entries, with 711 relevant and 2154 irrelevant articles. Adding additional features beyond title and abstract improved the performance (measured in Accuracy) of machine learning models by 3% for HPV corpus and 2% for PAPD corpus. Transformer-based deep learning models that consistently outperformed conventional machine learning algorithms, highlighting the strength of domain-specific pre-trained language models for SLR abstract screening. This study provides a foundation for the development of more intelligent SLR systems.

PMID:38724903 | DOI:10.1186/s12874-024-02224-3

BMC Med Imaging. 2024 May 9;24(1):102. doi: 10.1186/s12880-024-01277-6.

ABSTRACT

Precision and intelligence in evaluating the complexities of middle ear structures are required to diagnose auriculotemporal and ossicle-related diseases within otolaryngology. Due to the complexity of the anatomical details and the varied etiologies of illnesses such as trauma, chronic otitis media, and congenital anomalies, traditional diagnostic procedures may not yield accurate diagnoses. This research intends to enhance the diagnosis of diseases of the auriculotemporal region and ossicles by combining High-Resolution Spiral Computed Tomography (HRSCT) scanning with Deep Learning Techniques (DLT). This study employs a deep learning method, Convolutional Neural Network-UNet (CNN-UNet), to extract sub-pixel information from medical photos. This method equips doctors and researchers with cutting-edge resources, leading to groundbreaking discoveries and better patient healthcare. The research effort is the interaction between the CNN-UNet model and high-resolution Computed Tomography (CT) scans, automating activities including ossicle segmentation, fracture detection, and disruption cause classification, accelerating the diagnostic process and increasing clinical decision-making. The suggested HRSCT-DLT model represents the integration of high-resolution spiral CT scans with the CNN-UNet model, which has been fine-tuned to address the nuances of auriculotemporal and ossicular diseases. This novel combination improves diagnostic efficiency and our overall understanding of these intricate diseases. The results of this study highlight the promise of combining high-resolution CT scanning with the CNN-UNet model in otolaryngology, paving the way for more accurate diagnosis and more individualized treatment plans for patients experiencing auriculotemporal and ossicle-related disruptions.

PMID:38724896 | DOI:10.1186/s12880-024-01277-6

Eur Radiol. 2024 May 10. doi: 10.1007/s00330-024-10786-5. Online ahead of print.

ABSTRACT

OBJECTIVES: Developing a deep learning radiomics model from longitudinal breast ultrasound and sonographer's axillary ultrasound diagnosis for predicting axillary lymph node (ALN) response to neoadjuvant chemotherapy (NAC) in breast cancer.

METHODS: Breast cancer patients undergoing NAC followed by surgery were recruited from three centers between November 2016 and December 2022. We collected ultrasound images for extracting tumor-derived radiomics and deep learning features, selecting quantitative features through various methods. Two machine learning models based on random forest were developed using pre-NAC and post-NAC features. A support vector machine integrated these data into a fusion model, evaluated via the area under the curve (AUC), decision curve analysis, and calibration curves. We compared the fusion model's performance against sonographer's diagnosis from pre-NAC and post-NAC axillary ultrasonography, referencing histological outcomes from sentinel lymph node biopsy or axillary lymph node dissection.

RESULTS: In the validation cohort, the fusion model outperformed both pre-NAC (AUC: 0.899 vs. 0.786, p < 0.001) and post-NAC models (AUC: 0.899 vs. 0.853, p = 0.014), as well as the sonographer's diagnosis of ALN status on pre-NAC and post-NAC axillary ultrasonography (AUC: 0.899 vs. 0.719, p < 0.001). Decision curve analysis revealed patient benefits from the fusion model across threshold probabilities from 0.02 to 0.98. The model also enhanced sonographer's diagnostic ability, increasing accuracy from 71.9% to 79.2%.

CONCLUSION: The deep learning radiomics model accurately predicted the ALN response to NAC in breast cancer. Furthermore, the model will assist sonographers to improve their diagnostic ability on ALN status before surgery.

CLINICAL RELEVANCE STATEMENT: Our AI model based on pre- and post-neoadjuvant chemotherapy ultrasound can accurately predict axillary lymph node metastasis and assist sonographer's axillary diagnosis.

KEY POINTS: Axillary lymph node metastasis status affects the choice of surgical treatment, and currently relies on subjective ultrasound. Our AI model outperformed sonographer's visual diagnosis on axillary ultrasound. Our deep learning radiomics model can improve sonographers' diagnosis and might assist in surgical decision-making.

PMID:38724768 | DOI:10.1007/s00330-024-10786-5

Eur Radiol. 2024 May 9. doi: 10.1007/s00330-024-10771-y. Online ahead of print.

ABSTRACT

OBJECTIVE: Deep learning (DL) MRI reconstruction enables fast scan acquisition with good visual quality, but the diagnostic impact is often not assessed because of large reader study requirements. This study used existing diagnostic DL to assess the diagnostic quality of reconstructed images.

MATERIALS AND METHODS: A retrospective multisite study of 1535 patients assessed biparametric prostate MRI between 2016 and 2020. Likely clinically significant prostate cancer (csPCa) lesions (PI-RADS ≥ 4) were delineated by expert radiologists. T2-weighted scans were retrospectively undersampled, simulating accelerated protocols. DL reconstruction (DLRecon) and diagnostic DL detection (DLDetect) were developed. The effect on the partial area under (pAUC), the Free-Response Operating Characteristic (FROC) curve, and the structural similarity (SSIM) were compared as metrics for diagnostic and visual quality, respectively. DLDetect was validated with a reader concordance analysis. Statistical analysis included Wilcoxon, permutation, and Cohen's kappa tests for visual quality, diagnostic performance, and reader concordance.

RESULTS: DLRecon improved visual quality at 4- and 8-fold (R4, R8) subsampling rates, with SSIM (range: -1 to 1) improved to 0.78 ± 0.02 (p < 0.001) and 0.67 ± 0.03 (p < 0.001) from 0.68 ± 0.03 and 0.51 ± 0.03, respectively. However, diagnostic performance at R4 showed a pAUC FROC of 1.33 (CI 1.28-1.39) for DL and 1.29 (CI 1.23-1.35) for naive reconstructions, both significantly lower than fully sampled pAUC of 1.58 (DL: p = 0.024, naïve: p = 0.02). Similar trends were noted for R8.

CONCLUSION: DL reconstruction produces visually appealing images but may reduce diagnostic accuracy. Incorporating diagnostic AI into the assessment framework offers a clinically relevant metric essential for adopting reconstruction models into clinical practice.

CLINICAL RELEVANCE STATEMENT: In clinical settings, caution is warranted when using DL reconstruction for MRI scans. While it recovered visual quality, it failed to match the prostate cancer detection rates observed in scans not subjected to acceleration and DL reconstruction.

PMID:38724765 | DOI:10.1007/s00330-024-10771-y

Eur J Nucl Med Mol Imaging. 2024 May 9. doi: 10.1007/s00259-024-06737-3. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Treatment planning through the diagnostic dimension of theranostics provides insights into predicting the absorbed dose of RPT, with the potential to individualize radiation doses for enhancing treatment efficacy. However, existing studies focusing on dose prediction from diagnostic data often rely on organ-level estimations, overlooking intra-organ variations. This study aims to characterize the intra-organ theranostic heterogeneity and utilize artificial intelligence techniques to localize them, i.e. to predict voxel-wise absorbed dose map based on pre-therapy PET.

METHODS: 23 patients with metastatic castration-resistant prostate cancer treated with [177Lu]Lu-PSMA I&T RPT were retrospectively included. 48 treatment cycles with pre-treatment PET imaging and at least 3 post-therapeutic SPECT/CT imaging were selected. The distribution of PET tracer and RPT dose was compared for kidney, liver and spleen, characterizing intra-organ heterogeneity differences. Pharmacokinetic simulations were performed to enhance the understanding of the correlation. Two strategies were explored for pre-therapy voxel-wise dosimetry prediction: (1) organ-dose guided direct projection; (2) deep learning (DL)-based distribution prediction. Physical metrics, dose volume histogram (DVH) analysis, and identity plots were applied to investigate the predicted absorbed dose map.

RESULTS: Inconsistent intra-organ patterns emerged between PET imaging and dose map, with moderate correlations existing in the kidney (r = 0.77), liver (r = 0.5), and spleen (r = 0.58) (P < 0.025). Simulation results indicated the intra-organ pharmacokinetic heterogeneity might explain this inconsistency. The DL-based method achieved a lower average voxel-wise normalized root mean squared error of 0.79 ± 0.27%, regarding to ground-truth dose map, outperforming the organ-dose guided projection (1.11 ± 0.57%) (P < 0.05). DVH analysis demonstrated good prediction accuracy (R2 = 0.92 for kidney). The DL model improved the mean slope of fitting lines in identity plots (199% for liver), when compared to the theoretical optimal results of the organ-dose approach.

CONCLUSION: Our results demonstrated the intra-organ heterogeneity of pharmacokinetics may complicate pre-therapy dosimetry prediction. DL has the potential to bridge this gap for pre-therapy prediction of voxel-wise heterogeneous dose map.

PMID:38724653 | DOI:10.1007/s00259-024-06737-3

Phys Med Biol. 2024 May 9. doi: 10.1088/1361-6560/ad494f. Online ahead of print.

ABSTRACT

In this work, we aim to propose an accurate and robust spectrum estimation method by synergistically combining X-ray imaging physics with a convolutional neural network (CNN). &#xD;Approach: The approach relies on transmission measurements, and the estimated spectrum is formulated as a convolutional summation of a few model spectra generated using Monte Carlo simulation. The difference between the actual and estimated projections is utilized as the loss function to train the network. We contrasted this approach with the weighted sums of model spectra approach previously proposed. Comprehensive studies were performed to demonstrate the robustness and accuracy of the proposed approach in various scenarios. &#xD;Main results: The results show the desirable accuracy of the CNN-based method for spectrum estimation. The ME and NRMSE were -0.021 keV and 3.04% for 80kVp, and 0.006 keV and 4.44% for 100kVp, superior to the previous approach. The robustness test and experimental study also demonstrated superior performances. The CNN-based approach yielded remarkably consistent results in phantoms with various material combinations, and the CNN-based approach was robust concerning spectrum generators and calibration phantoms. &#xD;Significance: We proposed a method for estimating the real spectrum by integrating a deep learning model with real imaging physics. The results demonstrated that this method was accurate and robust in estimating the spectrum, and it is potentially helpful for broad X-ray imaging tasks.

PMID:38722545 | DOI:10.1088/1361-6560/ad494f

Int J Cardiovasc Imaging. 2024 May 9. doi: 10.1007/s10554-024-03113-y. Online ahead of print.

ABSTRACT

To assess the impact of low-dose contrast media (CM) injection protocol with deep learning image reconstruction (DLIR) algorithm on image quality in coronary CT angiography (CCTA). In this prospective study, patients underwent CCTA were prospectively and randomly assigned to three groups with different contrast volume protocols (at 320mgI/mL concentration and constant flow rate of 5ml/s). After pairing basic information, 210 patients were enrolled in this study: Group A, 0.7mL/kg (n = 70); Group B, 0.6mL/kg (n = 70); Group C, 0.5mL/kg (n = 70). All patients were examined via a prospective ECG-triggered scan protocol within one heartbeat. A high level DLIR (DLIR-H) algorithm was used for image reconstruction with a thickness and interval of 0.625mm. The CT values of ascending aorta (AA), descending aorta (DA), three main coronary arteries, pulmonary artery (PA), and superior vena cava (SVC) were measured and analyzed for objective assessment. Two radiologists assessed the image quality and diagnostic confidence using a 5-point Likert scale. The CM doses were 46.81 ± 6.41mL, 41.96 ± 7.51mL and 34.65 ± 5.38mL for Group A, B and C, respectively. The objective assessments on AA, DA and the three main coronary arteries and the overall subjective scoring showed no significant difference among the three groups (all p > 0.05). The subjective assessment proved that excellent CCTA images can be obtained from the three different contrast media protocols. There were no significant differences in intracoronary attenuation values between the higher HR subgroup and the lower HR subgroup among three groups. CCTA reconstructed with DLIR could be realized with adequate enhancement in coronary arteries, excellent image quality and diagnostic confidence at low contrast dose of a 0.5mL/kg. The use of lower tube voltages may further reduce the contrast dose requirement.

PMID:38722507 | DOI:10.1007/s10554-024-03113-y

Environ Monit Assess. 2024 May 9;196(6):527. doi: 10.1007/s10661-024-12598-y.

ABSTRACT

Understanding the connections between human activities and the natural environment depends heavily on information about land use and land cover (LULC) in the form of accurate LULC maps. Environmental monitoring using deep learning (DL) is rapidly growing to preserve a sustainable environment in the long term. For establishing effective policies, regulations, and implementation, DL can be a valuable tool for assessing environmental conditions and natural resources that will positively impact the ecosystem. This paper presents the assessment of land use and land cover change detection (LULCCD) and prediction using DL techniques for the southwestern coastal region, Goa, also known as the tourist destination of India. It consists of three components: (i) change detection (CD), (ii) quantification of LULC changes, and (iii) prediction. A new CD assessment framework, Spatio-Temporal Encoder-Decoder Self Attention Network (STEDSAN), is proposed for the LULCCD process. A dual branch encoder-decoder network is constructed using strided convolution with downsampling for the encoder and transpose convolution with upsampling for the decoder to assess the bitemporal images spatially. The self-attention (SA) mechanism captures the complex global spatial-temporal (ST) interactions between individual pixels over space-time to produce more distinct features. Each branch accepts the LULC map of 2 years as one of its inputs to determine binary and multiclass changes among the bitemporal images. The STEDSAN model determines the patterns, trends, and conversion from one LULC type to another for the assessment period from 2005 to 2018. The binary change maps were also compared with the existing state of the art (SOTA) CD methods, with STEDSAN having an overall accuracy of 94.93%. The prediction was made using an recurrent neural network (RNN) known as long short term memory network (LSTM) for the year 2025. Experiments were conducted to determine area-wise changes in several LULC classes, such as built-up (BU), crops (kharif crop (KC), rabi crop (RC), zaid crop (ZC), double/triple (D/T C)), current fallow (CF), plantation (PL), forests (evergreen forest (EF), deciduous forest (DF), degraded/scurb forest (D/SF) ), littoral swamp (LS), grassland (GL), wasteland (WL), waterbodies max (Wmx), and waterbodies min (Wmn). As per the analysis, over the period of 13 years, there has been a net increase in the amount of BU (1.25%), RC (1.17%), and D/TC( 2.42%) and a net decrease in DF (3.29%) and WL(1.44%) being the most dominant classes being changed. These findings will offer a thorough description of identifying trends in coastal areas that may incorporate methodological hints for future studies. This study will also promote handling the spatial and temporal complexity of remotely sensed data employed in categorizing the coastal LULC of a heterogeneous landscape.

PMID:38722419 | DOI:10.1007/s10661-024-12598-y

Neurosurg Rev. 2024 May 9;47(1):200. doi: 10.1007/s10143-024-02437-6.

ABSTRACT

Appropriate needle manipulation to avoid abrupt deformation of fragile vessels is a critical determinant of the success of microvascular anastomosis. However, no study has yet evaluated the area changes in surgical objects using surgical videos. The present study therefore aimed to develop a deep learning-based semantic segmentation algorithm to assess the area change of vessels during microvascular anastomosis for objective surgical skill assessment with regard to the "respect for tissue." The semantic segmentation algorithm was trained based on a ResNet-50 network using microvascular end-to-side anastomosis training videos with artificial blood vessels. Using the created model, video parameters during a single stitch completion task, including the coefficient of variation of vessel area (CV-VA), relative change in vessel area per unit time (ΔVA), and the number of tissue deformation errors (TDE), as defined by a ΔVA threshold, were compared between expert and novice surgeons. A high validation accuracy (99.1%) and Intersection over Union (0.93) were obtained for the auto-segmentation model. During the single-stitch task, the expert surgeons displayed lower values of CV-VA (p < 0.05) and ΔVA (p < 0.05). Additionally, experts committed significantly fewer TDEs than novices (p < 0.05), and completed the task in a shorter time (p < 0.01). Receiver operating curve analyses indicated relatively strong discriminative capabilities for each video parameter and task completion time, while the combined use of the task completion time and video parameters demonstrated complete discriminative power between experts and novices. In conclusion, the assessment of changes in the vessel area during microvascular anastomosis using a deep learning-based semantic segmentation algorithm is presented as a novel concept for evaluating microsurgical performance. This will be useful in future computer-aided devices to enhance surgical education and patient safety.

PMID:38722409 | DOI:10.1007/s10143-024-02437-6

J Neural Eng. 2024 May 9. doi: 10.1088/1741-2552/ad4916. Online ahead of print.

ABSTRACT

This study aims to develop and validate an end-to-end software platform, PyHFO, that streamlines the application of deep learning methodologies in detecting neurophysiological biomarkers for epileptogenic zones from EEG recordings.&#xD;&#xD;Methods: We introduced PyHFO, which enables time-efficient HFO detection algorithms like short-term energy (STE) and Montreal Neurological Institute and Hospital (MNI) detectors. It incorporates deep learning models for artifact and HFO with spike classification, designed to operate efficiently on standard computer hardware. &#xD;&#xD;Main results: The validation of PyHFO was conducted on three separate datasets: the first comprised solely of grid/strip electrodes, the second a combination of grid/strip and depth electrodes, and the third derived from rodent studies, which sampled the neocortex and hippocampus using depth electrodes. PyHFO demonstrated an ability to handle datasets efficiently, with optimization techniques enabling it to achieve speeds up to 50 times faster than traditional HFO detection applications. Users have the flexibility to employ our pre-trained deep learning model or use their EEG data for custom model training.&#xD;&#xD;Significance: PyHFO successfully bridges the computational challenge faced in applying deep learning techniques to EEG data analysis in epilepsy studies, presenting a feasible solution for both clinical and research settings. By offering a user-friendly and computationally efficient platform, PyHFO paves the way for broader adoption of advanced EEG data analysis tools in clinical practice and fosters potential for large-scale research collaborations.

PMID:38722308 | DOI:10.1088/1741-2552/ad4916

Radiol Cardiothorac Imaging. 2024 Jun;6(3):e230177. doi: 10.1148/ryct.230177.

ABSTRACT

Purpose To develop a deep learning model for increasing cardiac cine frame rate while maintaining spatial resolution and scan time. Materials and Methods A transformer-based model was trained and tested on a retrospective sample of cine images from 5840 patients (mean age, 55 years ± 19 [SD]; 3527 male patients) referred for clinical cardiac MRI from 2003 to 2021 at nine centers; images were acquired using 1.5- and 3-T scanners from three vendors. Data from three centers were used for training and testing (4:1 ratio). The remaining data were used for external testing. Cines with downsampled frame rates were restored using linear, bicubic, and model-based interpolation. The root mean square error between interpolated and original cine images was modeled using ordinary least squares regression. In a prospective study of 49 participants referred for clinical cardiac MRI (mean age, 56 years ± 13; 25 male participants) and 12 healthy participants (mean age, 51 years ± 16; eight male participants), the model was applied to cines acquired at 25 frames per second (fps), thereby doubling the frame rate, and these interpolated cines were compared with actual 50-fps cines. The preference of two readers based on perceived temporal smoothness and image quality was evaluated using a noninferiority margin of 10%. Results The model generated artifact-free interpolated images. Ordinary least squares regression analysis accounting for vendor and field strength showed lower error (P < .001) with model-based interpolation compared with linear and bicubic interpolation in internal and external test sets. The highest proportion of reader choices was "no preference" (84 of 122) between actual and interpolated 50-fps cines. The 90% CI for the difference between reader proportions favoring collected (15 of 122) and interpolated (23 of 122) high-frame-rate cines was -0.01 to 0.14, indicating noninferiority. Conclusion A transformer-based deep learning model increased cardiac cine frame rates while preserving both spatial resolution and scan time, resulting in images with quality comparable to that of images obtained at actual high frame rates. Keywords: Functional MRI, Heart, Cardiac, Deep Learning, High Frame Rate Supplemental material is available for this article. © RSNA, 2024.

PMID:38722232 | DOI:10.1148/ryct.230177