Biomed Opt Express. 2024 Apr 18;15(5):3147-3162. doi: 10.1364/BOE.519090. eCollection 2024 May 1.

ABSTRACT

Cholangiocarcinoma (CCA) poses a significant clinical challenge due to its aggressive nature and poor prognosis. While traditional diagnosis relies on color-based histopathology, hyperspectral imaging (HSI) offers rich, high-dimensional data holding potential for more accurate diagnosis. However, extracting meaningful insights from this data remains challenging. This work investigates the application of deep learning for CCA segmentation in microscopic HSI images, and introduces two novel neural networks: (1) Histogram Matching U-Net (HM-UNet) for efficient image pre-processing, and (2) Spectral Attention based Hyperspectral Image Segmentation Net (SAHIS-Net) for CCA segmentation. SAHIS-Net integrates a novel Spectral Attention (SA) module for adaptively weighing spectral information, an improved attention-aware feature enhancement (AFE) mechanism for better providing the model with more discriminative features, and a multi-loss training strategy for effective early stage feature extraction. We compare SAHIS-Net against several general and CCA-specific models, demonstrating its superior performance in segmenting CCA regions. These results highlight the potential of our approach for segmenting medical HSI images.

PMID:38855697 | PMC:PMC11161366 | DOI:10.1364/BOE.519090

Biomed Opt Express. 2024 Apr 30;15(5):3457-3479. doi: 10.1364/BOE.516481. eCollection 2024 May 1.

ABSTRACT

The measurement of retinal blood flow (RBF) in capillaries can provide a powerful biomarker for the early diagnosis and treatment of ocular diseases. However, no single modality can determine capillary flowrates with high precision. Combining erythrocyte-mediated angiography (EMA) with optical coherence tomography angiography (OCTA) has the potential to achieve this goal, as EMA can measure the absolute RBF of retinal microvasculature and OCTA can provide the structural images of capillaries. However, multimodal retinal image registration between these two modalities remains largely unexplored. To fill this gap, we establish MEMO, the first public multimodal EMA and OCTA retinal image dataset. A unique challenge in multimodal retinal image registration between these modalities is the relatively large difference in vessel density (VD). To address this challenge, we propose a segmentation-based deep-learning framework (VDD-Reg), which provides robust results despite differences in vessel density. VDD-Reg consists of a vessel segmentation module and a registration module. To train the vessel segmentation module, we further designed a two-stage semi-supervised learning framework (LVD-Seg) combining supervised and unsupervised losses. We demonstrate that VDD-Reg outperforms existing methods quantitatively and qualitatively for cases of both small VD differences (using the CF-FA dataset) and large VD differences (using our MEMO dataset). Moreover, VDD-Reg requires as few as three annotated vessel segmentation masks to maintain its accuracy, demonstrating its feasibility.

PMID:38855695 | PMC:PMC11161385 | DOI:10.1364/BOE.516481

Biomed Opt Express. 2024 Apr 19;15(5):3216-3239. doi: 10.1364/BOE.519964. eCollection 2024 May 1.

ABSTRACT

We demonstrate deep-learning neural network (NN)-based dynamic optical coherence tomography (DOCT), which generates high-quality logarithmic-intensity-variance (LIV) DOCT images from only four OCT frames. The NN model is trained for tumor spheroid samples using a customized loss function: the weighted mean absolute error. This loss function enables highly accurate LIV image generation. The fidelity of the generated LIV images to the ground truth LIV images generated using 32 OCT frames is examined via subjective image observation and statistical analysis of image-based metrics. Fast volumetric DOCT imaging with an acquisition time of 6.55 s/volume is demonstrated using this NN-based method.

PMID:38855683 | PMC:PMC11161370 | DOI:10.1364/BOE.519964

Biomed Opt Express. 2024 Apr 3;15(5):2832-2848. doi: 10.1364/BOE.519743. eCollection 2024 May 1.

ABSTRACT

We demonstrate a deep-learning-based scatterer density estimator (SDE) that processes local speckle patterns of optical coherence tomography (OCT) images and estimates the scatterer density behind each speckle pattern. The SDE is trained using large quantities of numerically simulated OCT images and their associated scatterer densities. The numerical simulation uses a noise model that incorporates the spatial properties of three types of noise, i.e., shot noise, relative-intensity noise, and non-optical noise. The SDE's performance was evaluated numerically and experimentally using two types of scattering phantom and in vitro tumor spheroids. The results confirmed that the SDE estimates scatterer densities accurately. The estimation accuracy improved significantly when compared with our previous deep-learning-based SDE, which was trained using numerical speckle patterns generated from a noise model that did not account for the spatial properties of noise.

PMID:38855681 | PMC:PMC11161371 | DOI:10.1364/BOE.519743

Biomed Opt Express. 2024 Apr 3;15(5):2811-2831. doi: 10.1364/BOE.517737. eCollection 2024 May 1.

ABSTRACT

In recent years, significant progress has been made in the field of medical image segmentation through the application of deep learning and neural networks. Numerous studies have focused on optimizing encoders to extract more comprehensive key information. However, the importance of decoders in directly influencing the final output of images cannot be overstated. The ability of decoders to effectively leverage diverse information and further refine crucial details is of paramount importance. This paper proposes a medical image segmentation architecture named STCS-Net. The designed decoder in STCS-Net facilitates multi-scale filtering and correction of information from the encoder, thereby enhancing the accuracy of extracting vital features. Additionally, an information enhancement module is introduced in skip connections to highlight essential features and improve the inter-layer information interaction capabilities. Comprehensive evaluations on the ISIC2016, ISIC2018, and Lung datasets validate the superiority of STCS-Net across different scenarios. Experimental results demonstrate the outstanding performance of STCS-Net on all three datasets. Comparative experiments highlight the advantages of our proposed network in terms of accuracy and parameter efficiency. Ablation studies confirm the effectiveness of the introduced decoder and skip connection module. This research introduces a novel approach to the field of medical image segmentation, providing new perspectives and solutions for future developments in medical image processing and analysis.

PMID:38855673 | PMC:PMC11161382 | DOI:10.1364/BOE.517737

Biomed Opt Express. 2024 Apr 3;15(5):2780-2797. doi: 10.1364/BOE.516063. eCollection 2024 May 1.

ABSTRACT

Working memory load (WML) is one of the widely applied signals in the areas of human-machine interaction. The precise evaluation of the WML is crucial for this kind of application. This study aims to propose a deep learning (DL) time series classification (TSC) model for inter-subject WML decoding. We used fNIRS to record the hemodynamic signals of 27 participants during visual working memory tasks. Traditional machine learning and deep time series classification algorithms were respectively used for intra-subject and inter-subject WML decoding from the collected blood oxygen signals. The intra-subject classification accuracy of LDA and SVM were 94.6% and 79.1%. Our proposed TAResnet-BiLSTM model had the highest inter-subject WML decoding accuracy, reaching 92.4%. This study provides a new idea and method for the brain-computer interface application of fNIRS in real-time WML detection.

PMID:38855665 | PMC:PMC11161351 | DOI:10.1364/BOE.516063

Biomed Opt Express. 2024 Apr 17;15(5):3112-3127. doi: 10.1364/BOE.515781. eCollection 2024 May 1.

ABSTRACT

Organoids, derived from human induced pluripotent stem cells (hiPSCs), are intricate three-dimensional in vitro structures that mimic many key aspects of the complex morphology and functions of in vivo organs such as the retina and heart. Traditional histological methods, while crucial, often fall short in analyzing these dynamic structures due to their inherently static and destructive nature. In this study, we leveraged the capabilities of optical coherence tomography (OCT) for rapid, non-invasive imaging of both retinal, cerebral, and cardiac organoids. Complementing this, we developed a sophisticated deep learning approach to automatically segment the organoid tissues and their internal structures, such as hollows and chambers. Utilizing this advanced imaging and analysis platform, we quantitatively assessed critical parameters, including size, area, volume, and cardiac beating, offering a comprehensive live characterization and classification of the organoids. These findings provide profound insights into the differentiation and developmental processes of organoids, positioning quantitative OCT imaging as a potentially transformative tool for future organoid research.

PMID:38855657 | PMC:PMC11161340 | DOI:10.1364/BOE.515781

Front Psychiatry. 2024 May 24;15:1392158. doi: 10.3389/fpsyt.2024.1392158. eCollection 2024.

ABSTRACT

BACKGROUND: The current biomarker-supported diagnosis of Alzheimer's disease (AD) is hindered by invasiveness and cost issues. This study aimed to address these challenges by utilizing portable electroencephalography (EEG). We propose a novel, non-invasive, and cost-effective method for identifying AD, using a sample of patients with biomarker-verified AD, to facilitate early and accessible disease screening.

METHODS: This study included 35 patients with biomarker-verified AD, confirmed via cerebrospinal fluid sampling, and 35 age- and sex-balanced healthy volunteers (HVs). All participants underwent portable EEG recordings, focusing on 2-minute resting-state EEG epochs with closed eyes state. EEG recordings were transformed into scalogram images, which were analyzed using "vision Transformer(ViT)," a cutting-edge deep learning model, to differentiate patients from HVs.

RESULTS: The application of ViT to the scalogram images derived from portable EEG data demonstrated a significant capability to distinguish between patients with biomarker-verified AD and HVs. The method achieved an accuracy of 73%, with an area under the receiver operating characteristic curve of 0.80, indicating robust performance in identifying AD pathology using neurophysiological measures.

CONCLUSIONS: Our findings highlight the potential of portable EEG combined with advanced deep learning techniques as a transformative tool for screening of biomarker-verified AD. This study not only contributes to the neurophysiological understanding of AD but also opens new avenues for the development of accessible and non-invasive diagnostic methods. The proposed approach paves the way for future clinical applications, offering a promising solution to the limitations of advanced diagnostic practices for dementia.

PMID:38855641 | PMC:PMC11157607 | DOI:10.3389/fpsyt.2024.1392158

ArXiv [Preprint]. 2024 May 28:arXiv:2405.18327v1.

ABSTRACT

Predictive biomarkers of treatment response are lacking for metastatic clear cell renal cell carcinoma (ccRCC), a tumor type that is treated with angiogenesis inhibitors, immune checkpoint inhibitors, mTOR inhibitors and a HIF2 inhibitor. The Angioscore, an RNA-based quantification of angiogenesis, is arguably the best candidate to predict anti-angiogenic (AA) response. However, the clinical adoption of transcriptomic assays faces several challenges including standardization, time delay, and high cost. Further, ccRCC tumors are highly heterogenous, and sampling multiple areas for sequencing is impractical. Here we present a novel deep learning (DL) approach to predict the Angioscore from ubiquitous histopathology slides. To overcome the lack of interpretability, one of the biggest limitations of typical DL models, our model produces a visual vascular network which is the basis of the model's prediction. To test its reliability, we applied this model to multiple cohorts including a clinical trial dataset. Our model accurately predicts the RNA-based Angioscore on multiple independent cohorts (spearman correlations of 0.77 and 0.73). Further, the predictions help unravel meaningful biology such as association of angiogenesis with grade, stage, and driver mutation status. Finally, we find our model can predict response to AA therapy, in both a real-world cohort and the IMmotion150 clinical trial. The predictive power of our model vastly exceeds that of CD31, a marker of vasculature, and nearly rivals the performance (c-index 0.66 vs 0.67) of the ground truth RNA-based Angioscore at a fraction of the cost. By providing a robust yet interpretable prediction of the Angioscore from histopathology slides alone, our approach offers insights into angiogenesis biology and AA treatment response.

PMID:38855551 | PMC:PMC11160863

ArXiv [Preprint]. 2024 May 29:arXiv:2405.18676v1.

ABSTRACT

Image-guided mouse irradiation is essential to understand interventions involving radiation prior to human studies. Our objective is to employ Swin UNEt Transformers (Swin UNETR) to segment native micro-CT and contrast-enhanced micro-CT scans and benchmark the results against 3D no-new-Net (nnU-Net). Swin UNETR reformulates mouse organ segmentation as a sequence-to-sequence prediction task, using a hierarchical Swin Transformer encoder to extract features at 5 resolution levels, and connects to a Fully Convolutional Neural Network (FCNN)-based decoder via skip connections. The models were trained and evaluated on open datasets, with data separation based on individual mice. Further evaluation on an external mouse dataset acquired on a different micro-CT with lower kVp and higher imaging noise was also employed to assess model robustness and generalizability. Results indicate that Swin UNETR consistently outperforms nnU-Net and AIMOS in terms of average dice similarity coefficient (DSC) and Hausdorff distance (HD95p), except in two mice of intestine contouring. This superior performance is especially evident in the external dataset, confirming the model's robustness to variations in imaging conditions, including noise and quality, thereby positioning Swin UNETR as a highly generalizable and efficient tool for automated contouring in pre-clinical workflows.

PMID:38855547 | PMC:PMC11160888

Insights Imaging. 2024 Jun 9;15(1):139. doi: 10.1186/s13244-024-01686-9.

ABSTRACT

OBJECTIVES: To investigate whether reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) with deep learning reconstruction (DLR) can improve the accuracy of evaluating muscle invasion using VI-RADS.

METHODS: Eighty-six bladder cancer participants who were evaluated by conventional full field-of-view (fFOV) DWI, standard rFOV (rFOVSTA) DWI, and fast rFOV with DLR (rFOVDLR) DWI were included in this prospective study. Tumors were categorized according to the vesical imaging reporting and data system (VI-RADS). Qualitative image quality scoring, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and ADC value were evaluated. Friedman test with post hoc test revealed the difference across the three DWIs. Receiver operating characteristic analysis was performed to calculate the areas under the curve (AUCs).

RESULTS: The AUC of the rFOVSTA DWI and rFOVDLR DWI were higher than that of fFOV DWI. rFOVDLR DWI reduced the acquisition time from 5:02 min to 3:25 min, and showed higher scores in overall image quality with higher CNR and SNR, compared to rFOVSTA DWI (p < 0.05). The mean ADC of all cases of rFOVSTA DWI and rFOVDLR DWI was significantly lower than that of fFOV DWI (all p < 0.05). There was no difference in mean ADC value and the AUC for evaluating muscle invasion between rFOVSTA DWI and rFOVDLR DWI (p > 0.05).

CONCLUSIONS: rFOV DWI with DLR can improve the diagnostic accuracy of fFOV DWI for evaluating muscle invasion. Applying DLR to rFOV DWI reduced the acquisition time and improved overall image quality while maintaining ADC value and diagnostic accuracy.

CRITICAL RELEVANCE STATEMENT: The diagnostic performance and image quality of full field-of-view DWI, reduced field-of-view (rFOV) DWI with and without DLR were compared. DLR would benefit the wide clinical application of rFOV DWI by reducing the acquisition time and improving the image quality.

KEY POINTS: Deep learning reconstruction (DLR) can reduce scan time and improve image quality. Reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) with DLR showed better diagnostic performances than full field-of-view DWI. There was no difference of diagnostic accuracy between rFOV DWI with DLR and standard rFOV DWI.

PMID:38853219 | DOI:10.1186/s13244-024-01686-9

Insights Imaging. 2024 Jun 9;15(1):141. doi: 10.1186/s13244-024-01690-z.

ABSTRACT

BACKGROUND: The efficacy of levodopa, the most crucial metric for Parkinson's disease diagnosis and treatment, is traditionally gauged through the levodopa challenge test, which lacks a predictive model. This study aims to probe the predictive power of T1-weighted MRI, the most accessible modality for levodopa response.

METHODS: This retrospective study used two datasets: from the Parkinson's Progression Markers Initiative (219 records) and the external clinical dataset from Ruijin Hospital (217 records). A novel feature extraction method using MedicalNet, a pre-trained deep learning network, along with three previous approaches was applied. Three machine learning models were trained and tested on the PPMI dataset and included clinical features, imaging features, and their union set, using the area under the curve (AUC) as the metric. The most significant brain regions were visualized. The external clinical dataset was further evaluated using trained models. A paired one-tailed t-test was performed between the two sets; statistical significance was set at p < 0.001.

RESULTS: For 46 test set records (mean age, 62 ± 9 years, 28 men), MedicalNet-extracted features demonstrated a consistent improvement in all three machine learning models (SVM 0.83 ± 0.01 versus 0.73 ± 0.01, XgBoost 0.80 ± 0.04 versus 0.74 ± 0.02, MLP 0.80 ± 0.03 versus 0.70 ± 0.07, p < 0.001). Both feature sets were validated on the clinical dataset using SVM, where MedicalNet features alone achieved an AUC of 0.64 ± 0.03. Key responsible brain regions were visualized.

CONCLUSION: The T1-weighed MRI features were more robust and generalizable than the clinical features in prediction; their combination provided the best results. T1-weighed MRI provided insights on specific regions responsible for levodopa response prediction.

CRITICAL RELEVANCE STATEMENT: This study demonstrated that T1w MRI features extracted by a deep learning model have the potential to predict the levodopa response of PD patients and are more robust than widely used clinical information, which might help in determining treatment strategy.

KEY POINTS: This study investigated the predictive value of T1w features for levodopa response. MedicalNet extractor outperformed all other previously published methods with key region visualization. T1w features are more effective than clinical information in levodopa response prediction.

PMID:38853208 | DOI:10.1186/s13244-024-01690-z

Sci Rep. 2024 Jun 9;14(1):13232. doi: 10.1038/s41598-024-63531-9.

ABSTRACT

Hepatocellular carcinoma (HCC) is a common malignancy with poor survival and requires long-term follow-up. Hence, we collected information on patients with Primary Hepatocellular Carcinoma in the United States from the Surveillance, Epidemiology, and EndResults (SEER) database. We used this information to establish a deep learning with a multilayer neural network (the NMTLR model) for predicting the survival rate of patients with Primary Hepatocellular Carcinoma. HCC patients pathologically diagnosed between January 2011 and December 2015 in the SEER (Surveillance, Epidemiology, and End Results) database of the National Cancer Institute of the United States were selected as study subjects. We utilized two deep learning-based algorithms (DeepSurv and Neural Multi-Task Logistic Regression [NMTLR]) and a machine learning-based algorithm (Random Survival Forest [RSF]) for model training. A multivariable Cox Proportional Hazards (CoxPH) model was also constructed for comparison. The dataset was randomly divided into a training set and a test set in a 7:3 ratio. The training dataset underwent hyperparameter tuning through 1000 iterations of random search and fivefold cross-validation. Model performance was assessed using the concordance index (C-index), Brier score, and Integrated Brier Score (IBS). The accuracy of predicting 1-year, 3-year, and 5-year survival rates was evaluated using Receiver Operating Characteristic (ROC) curves, calibration plots, and Area Under the Curve (AUC). The primary outcomes were the 1-year, 3-year, and 5-year overall survival rates. Models were developed using DeepSurv, NMTLR, RSF, and Cox Proportional Hazards regression. Model differentiation was evaluated using the C-index, calibration with concordance plots, and risk stratification capability with the log-rank test. The study included 2197 HCC patients, randomly divided into a training cohort (70%, n = 1537) and a testing cohort (30%, n = 660). Clinical characteristics between the two cohorts showed no significant statistical difference (p > 0.05). The deep learning models outperformed both RSF and CoxPH models, with C-indices of 0.735 (NMTLR) and 0.731 (DeepSurv) in the test dataset. The NMTLR model demonstrated enhanced accuracy and well-calibrated survival estimates, achieving an Area Under the Curve (AUC) of 0.824 for 1-year survival predictions, 0.813 for 3-year, and 0.803 for 5-year survival rates. This model's superior calibration and discriminative ability enhance its utility for clinical prognostication in Primary Hepatocellular Carcinoma. We deployed the NMTLR model as a web application for clinical practice. The NMTLR model have potential advantages over traditional linear models in prognostic assessment and treatment recommendations. This novel analytical approach may provide reliable information on individual survival and treatment recommendations for patients with primary liver cancer.

PMID:38853169 | DOI:10.1038/s41598-024-63531-9

Sci Rep. 2024 Jun 9;14(1):13241. doi: 10.1038/s41598-024-63675-8.

ABSTRACT

Cochlear implants (CIs) do not offer the same level of effectiveness in noisy environments as in quiet settings. Current single-microphone noise reduction algorithms in hearing aids and CIs only remove predictable, stationary noise, and are ineffective against realistic, non-stationary noise such as multi-talker interference. Recent developments in deep neural network (DNN) algorithms have achieved noteworthy performance in speech enhancement and separation, especially in removing speech noise. However, more work is needed to investigate the potential of DNN algorithms in removing speech noise when tested with listeners fitted with CIs. Here, we implemented two DNN algorithms that are well suited for applications in speech audio processing: (1) recurrent neural network (RNN) and (2) SepFormer. The algorithms were trained with a customized dataset ( ∼ 30 h), and then tested with thirteen CI listeners. Both RNN and SepFormer algorithms significantly improved CI listener's speech intelligibility in noise without compromising the perceived quality of speech overall. These algorithms not only increased the intelligibility in stationary non-speech noise, but also introduced a substantial improvement in non-stationary noise, where conventional signal processing strategies fall short with little benefits. These results show the promise of using DNN algorithms as a solution for listening challenges in multi-talker noise interference.

PMID:38853168 | DOI:10.1038/s41598-024-63675-8

Sci Rep. 2024 Jun 9;14(1):13244. doi: 10.1038/s41598-024-63818-x.

ABSTRACT

Aiming at the problem of image classification with insignificant morphological structural features, strong target correlation, and low signal-to-noise ratio, combined with prior feature knowledge embedding, a deep learning method based on ResNet and Radial Basis Probabilistic Neural Network (RBPNN) is proposed model. Taking ResNet50 as a visual modeling network, it uses feature pyramid and self-attention mechanism to extract appearance and semantic features of images at multiple scales, and associate and enhance local and global features. Taking into account the diversity of category features, channel cosine similarity attention and dynamic C-means clustering algorithms are used to select representative sample features in different category of sample subsets to implicitly express prior category feature knowledge, and use them as the kernel centers of radial basis probability neurons (RBPN) to realize the embedding of diverse prior feature knowledge. In the RBPNN pattern aggregation layer, the outputs of RBPN are selectively summed according to the category of the kernel center, that is, the subcategory features are combined into category features, and finally the image classification is implemented based on Softmax. The functional module of the proposed method is designed specifically for image characteristics, which can highlight the significance of local and structural features of the image, form a non-convex decision-making area, and reduce the requirements for the completeness of the sample set. Applying the proposed method to medical image classification, experiments were conducted based on the brain tumor MRI image classification public dataset and the actual cardiac ultrasound image dataset, and the accuracy rate reached 85.82% and 83.92% respectively. Compared with the three mainstream image classification models, the performance indicators of this method have been significantly improved.

PMID:38853158 | DOI:10.1038/s41598-024-63818-x

Dig Liver Dis. 2024 Jun 8:S1590-8658(24)00791-6. doi: 10.1016/j.dld.2024.05.033. Online ahead of print.

ABSTRACT

BACKGROUND: Inflammatory bowel disease (IBD) includes Crohn's Disease (CD) and Ulcerative Colitis (UC). Correct diagnosis requires the identification of precise morphological features such basal plasmacytosis. However, histopathological interpretation can be challenging, and it is subject to high variability.

AIM: The IBD-Artificial Intelligence (AI) project aims at the development of an AI-based evaluation system to support the diagnosis of IBD, semi-automatically quantifying basal plasmacytosis.

METHODS: A deep learning model was trained to detect and quantify plasma cells on a public dataset of 4981 annotated images. The model was then tested on an external validation cohort of 356 intestinal biopsies of CD, UC and healthy controls. AI diagnostic performance was calculated compared to human gold standard.

RESULTS: The system correctly found that CD and UC samples had a greater prevalence of basal plasma cells with mean number of PCs within ROIs of 38.22 (95 % CI: 31.73, 49.04) for CD, 55.16 (46.57, 65.93) for UC, and 17.25 (CI: 12.17, 27.05) for controls. Overall, OR=4.968 (CI: 1.835, 14.638) was found for IBD compared to normal mucosa (CD: +59 %; UC: +129 %). Additionally, as expected, UC samples were found to have more plasma cells in colon than CD cases.

CONCLUSION: Our model accurately replicated human assessment of basal plasmacytosis, underscoring the value of AI models as a potential aid IBD diagnosis.

PMID:38853093 | DOI:10.1016/j.dld.2024.05.033

J Nucl Cardiol. 2024 Jun 7:101889. doi: 10.1016/j.nuclcard.2024.101889. Online ahead of print.

ABSTRACT

BACKGROUND: We developed an explainable deep learning-based classifier to identify flow-limiting coronary artery disease (CAD) by O-15 H2O perfusion PET/CT and coronary CT angiography (CTA) imaging. The classifier uses polar map images with numerical data and visualizes data findings.

METHODS: A deep learning (DL) model was implemented and evaluated on 138 subjects, consisting of a combined image- and data-based classifier considering 35 clinical, CTA and PET variables. Data from invasive coronary angiography was used as reference. Performance was evaluated with clinical classification using accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE), precision (PRE), net benefit and Cohen's Kappa. Statistical testing was conducted using McNemar's test.

RESULTS: The DL model had a median ACC 0.8478, AUC 0.8481, F1S 0.8293, SEN 0.8500, SPE 0.8846 and PRE 0.8500. Improved detection of TP and FN cases, increased net benefit in thresholds up to 34 %, and comparable Cohen's kappa was seen, reaching similar performance to clinical reading. Statistical testing revealed no significant differences between DL model and clinical reading.

CONCLUSIONS: The combined DL model is a feasible and an effective method in detection of CAD, allowing to highlight important data findings individually in interpretable manner.

PMID:38852900 | DOI:10.1016/j.nuclcard.2024.101889

Environ Pollut. 2024 Jun 7:124345. doi: 10.1016/j.envpol.2024.124345. Online ahead of print.

ABSTRACT

This study aims to present a comprehensive study on the risks associated with the residual presence and transport of Escherichia coli (E. coli) in soil following the application of livestock manure in Chinese farmlands by integrating machine learning algorithms with mechanism-based models (Phydrus). We initially review 28 published papers to gather data on E. coli's die-off and attachment characteristics in soil. Machine learning models, including deep learning and gradient boosting machine, are employed to predict key parameters such as the die-off rate of E. coli and first-order attachment coefficient in soil. Then, Phydrus was used to simulate E. coli transport and survival in 23692 subregions in China. The model considered regional differences in E. coli residual risk and transport, influenced by soil properties, soil depths, precipitation, seasonal variations, and regional disparities. The findings indicate higher residual risks in regions such as the Northeast China, Eastern Qinghai-Tibet Plateau, and pronounced transport risks in the fringe of the Sichuan Basin fringe, the Loess Plateau, the North China Plain, the Northeast Plain, the Shigatse Basin, and the Shangri-La region. The study also demonstrates a significant reduction in both residual and transport risks one month after manure application, highlighting the importance of timing manure application and implementing region-specific standards. This research contributes to the broader understanding of pathogen behavior in agricultural soils and offers practical guidelines for managing the risks associated with manure use. This study's comprehensive method offers a potentially valuable tool for evaluating microbial contaminants in agricultural soils across the globe.

PMID:38852664 | DOI:10.1016/j.envpol.2024.124345

J Fish Biol. 2024 Jun 9. doi: 10.1111/jfb.15793. Online ahead of print.

ABSTRACT

With the continuous development of green and high-quality aquaculture technology, the process of industrialized aquaculture has been promoted. Automation, intelligence, and precision have become the future development trend of the aquaculture industry. Fish individual recognition can further distinguish fish individuals based on the determination of fish categories, providing basic support for fish disease analysis, bait feeding, and precision aquaculture. However, the high similarity of fish individuals and the complexity of the underwater environment presents great challenges to fish individual recognition. To address these problems, we propose a novel fish individual recognition method for precision farming that rethinks the knowledge distillation strategy and the chunking method in the vision transformer. The method uses the traditional convolutional neural network model as the teacher model, introducing the teacher token to guide the student model to learn the fish texture features. We propose stride patch embedding to expand the range of the receptive field, thus enhancing the local continuity of the image, and self-attention-pruning to discard unimportant tokens and reduce the model computation. The experimental results on the DlouFish dataset show that the proposed method in this paper improves accuracy by 3.25% compared to ECA Resnet152, with an accuracy of 93.19%, and also outperforms other vision transformer models.

PMID:38852608 | DOI:10.1111/jfb.15793

Biochem Biophys Res Commun. 2024 Jun 4;724:150225. doi: 10.1016/j.bbrc.2024.150225. Online ahead of print.

ABSTRACT

Data acquisition for transcriptomic studies used to be the bottleneck in the transcriptomic analytical pipeline. However, recent developments in transcriptome profiling technologies have increased researchers' ability to obtain data, resulting in a shift in focus to data analysis. Incorporating machine learning to traditional analytical methods allows the possibility of handling larger volumes of complex data more efficiently. Many bioinformaticians, especially those unfamiliar with ML in the study of human transcriptomics and complex biological systems, face a significant barrier stemming from their limited awareness of the current landscape of ML utilisation in this field. To address this gap, this review endeavours to introduce those individuals to the general types of ML, followed by a comprehensive range of more specific techniques, demonstrated through examples of their incorporation into analytical pipelines for human transcriptome investigations. Important computational aspects such as data pre-processing, task formulation, results (performance of ML models), and validation methods are encompassed. In hope of better practical relevance, there is a strong focus on studies published within the last five years, almost exclusively examining human transcriptomes, with outcomes compared with standard non-ML tools.

PMID:38852503 | DOI:10.1016/j.bbrc.2024.150225