Sci Rep. 2024 Nov 20;14(1):28742. doi: 10.1038/s41598-024-78774-9.

ABSTRACT

The protection and restoration of existing buildings requires accurate acquisition of the characteristics of the building facade. The complex, diverse, and irregular distribution characteristics of the building facade components of ethnic minorities have led to a huge workload of field research, surveying, mapping, and calculation, and it is more difficult to extract its facade characteristics accurately. This study proposes a visual model based on the Swin Transformer and applies it to the graphic recognition of ethnic building elevations. The model combines the advantages of the migration learning method and deep neural network technology and is further enriched by layer normalization to improve the stability and extraction ability of model training. In the field survey of ethnic minority buildings in Kangba, Sichuan, 1100 images of local buildings were collected, including 8 different types of ethnic minority buildings. The experimental results show that compared with other mainstream deep neural network models, the Swin Transformer visual model shows excellent predictive performance to prove the effectiveness of the proposed method. This study also uses the t-sne dimension reduction method to verify the feature extraction ability of the Swin Transformer, which contributes to the protection and restoration of ethnic minority buildings, active exploration of energy conservation, digital archiving, and more. Provide theoretical and practical reference in the fields of architectural style and cultural research.

PMID:39567608 | DOI:10.1038/s41598-024-78774-9

Sci Rep. 2024 Nov 20;14(1):28717. doi: 10.1038/s41598-024-79132-5.

ABSTRACT

Tapping line detection and rubber tapping pose estimation are challenging tasks in rubber plantation environments for rubber tapping robots. This study proposed a method for tapping line detection and rubber tapping pose estimation based on improved YOLOv8 and RGB-D information fusion. Firstly, YOLOv8n was improved by introducing the CFB module into the backbone, adding an output layer into the neck, fusing the EMA attention mechanism into the neck, and modifying the loss function as NWD to realize multi-object detection and segmentation. Secondly, the trunk skeleton line was extracted by combining level set and ellipse fitting. Then, the new tapping line was located by combining edge detection and geometric analysis. Finally, the rubber tapping pose was estimated based on the trunk skeleton line and the new tapping line. The detection results from 597 test images showed the improved YOLOv8n's detection mAP0.5, segmentation mAP0.5, and model size were 81.9%, 72.9%, and 6.06 MB, respectively. The improved YOLOv8n's effect and efficiency were superior compared to other networks, and it could better detect and segment natural rubber tree image targets in different scenes. The pose estimation results from 300 new tapping lines showed the average success rate and average time consumed for rubber tapping pose estimation were 96% and 0.2818 s, respectively. The positioning errors in x, y, and z directions were 0.69 ± 0.51 mm, 0.73 ± 0.4 mm, and 1.07 ± 0.56 mm, respectively. The error angles in a, o, and n directions were 1.65° ± 0.68°, 2.53° ± 0.88°, and 2.26° ± 0.89°, respectively. Therefore, this method offers an effective solution for rubber tapping pose estimation and provides theoretical support for the development of rubber tapping robots.

PMID:39567603 | DOI:10.1038/s41598-024-79132-5

Sci Data. 2024 Nov 20;11(1):1256. doi: 10.1038/s41597-024-04090-6.

ABSTRACT

This dataset is from an EEG brain-computer interface (BCI) study investigating the use of deep learning (DL) for online continuous pursuit (CP) BCI. In this task, subjects use Motor Imagery (MI) to control a cursor to follow a randomly moving target, instead of a single stationary target used in other traditional BCI tasks. DL methods have recently achieved promising performance in traditional BCI tasks, but most studies investigate offline data analysis using DL algorithms. This dataset consists of ~168 hours of EEG recordings from complex CP BCI experiments, collected from 28 unique human subjects over multiple sessions each, with an online DL-based decoder. The large amount of subject specific data from multiple sessions may be useful for developing new BCI decoders, especially DL methods that require large amounts of training data. By providing this dataset to the public, we hope to help facilitate the development of new or improved BCI decoding algorithms for the complex CP paradigm for continuous object control, bringing EEG-based BCIs closer to real-world applications.

PMID:39567538 | DOI:10.1038/s41597-024-04090-6

Nat Commun. 2024 Nov 20;15(1):10025. doi: 10.1038/s41467-024-54153-w.

ABSTRACT

We use seismic waves that pass through the hypocentral region of the 2016 M6.5 Norcia earthquake together with Deep Learning (DL) to distinguish between foreshocks, aftershocks and time-to-failure (TTF). Binary and N-class models defined by TTF correctly identify seismograms in test with > 90% accuracy. We use raw seismic records as input to a 7 layer CNN model to perform the classification. Here we show that DL models successfully distinguish seismic waves pre/post mainshock in accord with lab and theoretical expectations of progressive changes in crack density prior to abrupt change at failure and gradual postseismic recovery. Performance is lower for band-pass filtered seismograms (below 10 Hz) suggesting that DL models learn from the evolution of subtle changes in elastic wave attenuation. Tests to verify that our results indeed provide a proxy for fault properties included DL models trained with the wrong mainshock time and those using seismic waves far from the Norcia mainshock; both show degraded performance. Our results demonstrate that DL models have the potential to track the evolution of fault zone properties during the seismic cycle. If this result is generalizable it could improve earthquake early warning and seismic hazard analysis.

PMID:39567514 | DOI:10.1038/s41467-024-54153-w

Nat Commun. 2024 Nov 20;15(1):10031. doi: 10.1038/s41467-024-53340-z.

ABSTRACT

Recent technological advancements in single-cell genomics have enabled joint profiling of gene expression and alternative modalities at unprecedented scale. Consequently, the complexity of multi-omics data sets is increasing massively. Existing models for multi-modal data are typically limited in functionality or scalability, making data integration and downstream analysis cumbersome. We present multiDGD, a scalable deep generative model providing a probabilistic framework to learn shared representations of transcriptome and chromatin accessibility. It shows outstanding performance on data reconstruction without feature selection. We demonstrate on several data sets from human and mouse that multiDGD learns well-clustered joint representations. We further find that probabilistic modeling of sample covariates enables post-hoc data integration without the need for fine-tuning. Additionally, we show that multiDGD can detect statistical associations between genes and regulatory regions conditioned on the learned representations. multiDGD is available as an scverse-compatible package on GitHub.

PMID:39567490 | DOI:10.1038/s41467-024-53340-z

Clin Oral Investig. 2024 Nov 20;28(12):648. doi: 10.1007/s00784-024-05967-x.

ABSTRACT

OBJECTIVES: During mandibular third molar (MTM) extraction surgery, preoperative analysis to quantify the proximity of the MTM to the surrounding inferior alveolar nerve (IAN) is essential to minimize the risk of IAN injury. This study aims to propose an automated tool to quantitatively measure the proximity of IAN and MTM in cone-beam computed tomography (CBCT) images.

MATERIALS AND METHODS: Using the dataset including 302 CBCT scans with 546 MTMs, a deep-learning-based network was developed to support the automatic detection of the IAN, MTM, and intersection region IR. To ensure accurate proximity detection, a distance detection algorithm and a volume measurement algorithm were also developed.

RESULTS: The deep learning-based model showed encouraging segmentation accuracy of the target structures (Dice similarity coefficient: 0.9531 ± 0.0145, IAN; 0.9832 ± 0.0055, MTM; 0.8336 ± 0.0746, IR). In addition, with the application of the developed algorithms, the distance between the IAN and MTM and the volume of the IR could be equivalently detected (90% confidence interval (CI): - 0.0345-0.0014 mm, distance; - 0.0155-0.0759 mm3, volume). The total time for the IAN, MTM, and IR segmentation was 2.96 ± 0.11 s, while the accurate manual segmentation required 39.01 ± 5.89 min.

CONCLUSIONS: This study presented a novel, fast, and accurate model for the detection and proximity quantification of the IAN and MTM on CBCT.

CLINICAL RELEVANCE: This model illustrates that a deep learning network may assist surgeons in evaluating the risk of MTM extraction surgery by detecting the proximity of the IAN and MTM at a quantitative level that was previously unparalleled.

PMID:39567447 | DOI:10.1007/s00784-024-05967-x

Eur Radiol. 2024 Nov 20. doi: 10.1007/s00330-024-11206-4. Online ahead of print.

ABSTRACT

OBJECTIVES: To assess the correlation between the use of artificial intelligence (AI) software and burnout in the radiology departments of hospitals in China.

METHODS: This study employed a cross-sectional research design. From February to July 2024, an online survey was conducted among radiologists and technicians at 68 public hospitals in China. The survey utilized general information questionnaires, the Maslach Burnout Inventory-Human Services Survey (MBI-HSS) scale, and a custom-designed AI usage questionnaire. This study analyzed the correlation between AI software usage and occupational burnout, and general information was included as a control variable in a multiple linear regression analysis.

RESULTS: The analysis of survey data from 522 radiology staff revealed that 389 (74.5%) had used AI and that 252 (48.3%) had used it for more than 12 months. Only 133 (25.5%) had not yet adopted AI. Among the respondents, radiologists had a higher AI usage rate (82.0%) than technicians (only 59.9%). Furthermore, 344 (65.9%) of the respondents exhibited signs of burnout. The duration of AI software usage was significantly negatively correlated with overall burnout, yielding a Pearson correlation coefficient of -0.112 (p < 0.05). Multiple stepwise regression analysis revealed that salary satisfaction, night shifts, duration of AI usage, weekly working hours, having children, and professional rank were the main factors influencing occupational burnout (all p < 0.05).

CONCLUSION: AI has the potential to significantly help mitigate occupational burnout among radiology staff. This study reveals the key role that AI plays in assisting radiology staff in their work.

KEY POINTS: Questions Although we are aware that radiology staff burnout is intensifying, there is no quantitative research assessing whether artificial intelligence software can mitigate this occupational burnout. Findings The longer staff use deep learning-based artificial intelligence imaging software, the less severe their occupational burnout tends to be. This result is particularly evident among radiologists. Clinical relevance In China, radiologists and technicians experience high burnout rates. Even if there is an artificial intelligence usage controversy, encouraging the use of artificial intelligence software in radiology helps prevent and alleviate this occupational burnout.

PMID:39567429 | DOI:10.1007/s00330-024-11206-4

Mol Biol Evol. 2024 Nov 20:msae242. doi: 10.1093/molbev/msae242. Online ahead of print.

ABSTRACT

In recent years, advances in image processing and machine learning have fueled a paradigm shift in detecting genomic regions under natural selection. Early machine learning techniques employed population-genetic summary statistics as features, which focus on specific genomic patterns expected by adaptive and neutral processes. Though such engineered features are important when training data is limited, the ease at which simulated data can now be generated has led to the recent development of approaches that take in image representations of haplotype alignments and automatically extract important features using convolutional neural networks. Digital image processing methods termed α-molecules are a class of techniques for multi-scale representation of objects that can extract a diverse set of features from images. One such α-molecule method, termed wavelet decomposition, lends greater control over high-frequency components of images. Another α-molecule method, termed curvelet decomposition, is an extension of the wavelet concept that considers events occurring along curves within images. We show that application of these α-molecule techniques to extract features from image representations of haplotype alignments yield high true positive rate and accuracy to detect hard and soft selective sweep signatures from genomic data with both linear and nonlinear machine learning classifiers. Moreover, we find that such models are easy to visualize and interpret, with performance rivaling those of contemporary deep learning approaches for detecting sweeps.

PMID:39565932 | DOI:10.1093/molbev/msae242

Rheumatology (Oxford). 2024 Nov 20:keae523. doi: 10.1093/rheumatology/keae523. Online ahead of print.

ABSTRACT

OBJECTIVES: To evaluate whether the application of deep learning (DL) could achieve high diagnostic accuracy in differentiating between green colour coding, indicative of tophi, and clumpy artifacts observed in dual-energy computed tomography (DECT) scans.

METHODS: A comprehensive analysis of 18 704 regions of interest (ROIs) extracted from green foci in DECT scans obtained from 47 patients with gout and 27 gout-free controls was performed. The ROIs were categorized into three size groups: small, medium, and large. Convolutional neural network (CNN) analysis on a per-lesion basis and support vector machine (SVM) analysis on a per-patient basis were performed. The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value of the models were compared.

RESULTS: For small ROIs, the sensitivity and specificity of the CNN model were 81.5% and 96.1%, respectively; for medium ROIs, 82.7% and 96.1%, respectively; for large ROIs, 91.8% and 86.9%, respectively. Additionally, the DL algorithm exhibited accuracies of 88.5%, 88.6%, and 91.0% for small, medium, and large ROIs, respectively. In the per-patient analysis, the SVM approach demonstrated a sensitivity of 87.2%, a specificity of 100%, and an accuracy of 91.8% in distinguishing between patients with gout and gout-free controls.

CONCLUSION: Our study demonstrates the effectiveness of the DL algorithm in differentiating between green colour coding indicative of crystal deposition and clumpy artifacts in DECT scans. With high sensitivity, specificity, and accuracy, the utilization of DL in DECT for diagnosing gout enables precise lesion classification, facilitating early-stage diagnosis and promoting timely intervention approaches.

PMID:39565918 | DOI:10.1093/rheumatology/keae523

Annu Rev Anim Biosci. 2024 Nov 20. doi: 10.1146/annurev-animal-111523-102217. Online ahead of print.

ABSTRACT

Transcriptional regulation in response to diverse physiological cues involves complicated biological processes. Recent initiatives that leverage whole genome sequencing and annotation of regulatory elements significantly contribute to our understanding of transcriptional gene regulation. Advances in the data sets available for comparative genomics and epigenomics can identify evolutionarily constrained regulatory variants and shed light on noncoding elements that influence transcription in different tissues and developmental stages across species. Most epigenomic data, however, are generated from healthy subjects at specific developmental stages. To bridge the genotype-phenotype gap, future research should focus on generating multidimensional epigenomic data under diverse physiological conditions. Farm animal species offer advantages in terms of feasibility, cost, and experimental design for such integrative analyses in comparison to humans. Deep learning modeling and cutting-edge technologies in sequencing and functional screening and validation also provide great promise for better understanding transcriptional regulation in this dynamic field.

PMID:39565835 | DOI:10.1146/annurev-animal-111523-102217

JMIR Med Inform. 2024 Nov 20;12:e45289. doi: 10.2196/45289.

ABSTRACT

BACKGROUND: Social networking services (SNS) closely reflect the lives of individuals in modern society and generate large amounts of data. Previous studies have extracted drug information using relevant SNS data. In particular, it is important to detect adverse drug reactions (ADRs) early using drug surveillance systems. To this end, various deep learning methods have been used to analyze data in multiple languages in addition to English.

OBJECTIVE: A cautionary drug that can cause ADRs in older patients was selected, and Korean SNS data containing this drug information were collected. Based on this information, we aimed to develop a deep learning model that classifies drug ADR posts based on a recurrent neural network.

METHODS: In previous studies, ketoprofen, which has a high prescription frequency and, thus, was referred to the most in posts secured from SNS data, was selected as the target drug. Blog posts, café posts, and NAVER Q&A posts from 2005 to 2020 were collected from NAVER, a portal site containing drug-related information, and natural language processing techniques were applied to analyze data written in Korean. Posts containing highly relevant drug names and ADR word pairs were filtered through association analysis, and training data were generated through manual labeling tasks. Using the training data, an embedded layer of word2vec was formed, and a Bidirectional Long Short-Term Memory (Bi-LSTM) classification model was generated. Then, we evaluated the area under the curve with other machine learning models. In addition, the entire process was further verified using the nonsteroidal anti-inflammatory drug aceclofenac.

RESULTS: Among the nonsteroidal anti-inflammatory drugs, Korean SNS posts containing information on ketoprofen and aceclofenac were secured, and the generic name lexicon, ADR lexicon, and Korean stop word lexicon were generated. In addition, to improve the accuracy of the classification model, an embedding layer was created considering the association between the drug name and the ADR word. In the ADR post classification test, ketoprofen and aceclofenac achieved 85% and 80% accuracy, respectively.

CONCLUSIONS: Here, we propose a process for developing a model for classifying ADR posts using SNS data. After analyzing drug name-ADR patterns, we filtered high-quality data by extracting posts, including known ADR words based on the analysis. Based on these data, we developed a model that classifies ADR posts. This confirmed that a model that can leverage social data to monitor ADRs automatically is feasible.

PMID:39565685 | DOI:10.2196/45289

Eur Radiol Exp. 2024 Nov 20;8(1):132. doi: 10.1186/s41747-024-00518-1.

ABSTRACT

BACKGROUND: To retrospectively assess the added value of an artificial intelligence (AI) algorithm for detecting pulmonary nodules on ultra-low-dose computed tomography (ULDCT) performed at the emergency department (ED).

METHODS: In the OPTIMACT trial, 870 patients with suspected nontraumatic pulmonary disease underwent ULDCT. The ED radiologist prospectively read the examinations and reported incidental pulmonary nodules requiring follow-up. All ULDCTs were processed post hoc using an AI deep learning software marking pulmonary nodules ≥ 6 mm. Three chest radiologists independently reviewed the subset of ULDCTs with either prospectively detected incidental nodules in 35/870 patients or AI marks in 458/870 patients; findings scored as nodules by at least two chest radiologists were used as true positive reference standard. Proportions of true and false positives were compared.

RESULTS: During the OPTIMACT study, 59 incidental pulmonary nodules requiring follow-up were prospectively reported. In the current analysis, 18/59 (30.5%) nodules were scored as true positive while 104/1,862 (5.6%) AI marks in 84/870 patients (9.7%) were scored as true positive. Overall, 5.8 times more (104 versus 18) true positive pulmonary nodules were detected with the use of AI, at the expense of 42.9 times more (1,758 versus 41) false positives. There was a median number of 1 (IQR: 0-2) AI mark per ULDCT.

CONCLUSION: The use of AI on ULDCT in patients suspected of pulmonary disease in an emergency setting results in the detection of many more incidental pulmonary nodules requiring follow-up (5.8×) with a high trade-off in terms of false positives (42.9×).

RELEVANCE STATEMENT: AI aids in the detection of incidental pulmonary nodules that require follow-up at chest-CT, aiding early pulmonary cancer detection but also results in an increase of false positive results that are mainly clustered in patients with major abnormalities.

TRIAL REGISTRATION: The OPTIMACT trial was registered on 6 December 2016 in the National Trial Register (number NTR6163) (onderzoekmetmensen.nl).

KEY POINTS: An AI deep learning algorithm was tested on 870 ULDCT examinations acquired in the ED. AI detected 5.8 times more pulmonary nodules requiring follow-up (true positives). AI resulted in the detection of 42.9 times more false positive results, clustered in patients with major abnormalities. AI in the ED setting may aid in early pulmonary cancer detection with a high trade-off in terms of false positives.

PMID:39565453 | DOI:10.1186/s41747-024-00518-1

Environ Sci Technol. 2024 Nov 20. doi: 10.1021/acs.est.4c07341. Online ahead of print.

ABSTRACT

Accurate estimation of atmospheric chemical concentrations from multiple observations is crucial for assessing the health effects of air pollution. However, existing methods are limited by imbalanced samples from observations. Here, we introduce a novel deep-learning model-measurement fusion method (DeepMMF) constrained by physical laws inferred from a chemical transport model (CTM) to estimate NO2 concentrations over the Continental United States (CONUS). By pretraining with spatiotemporally complete CTM simulations, fine-tuning with satellite and ground measurements, and employing a novel optimization strategy for selecting proper prior emission, DeepMMF delivers improved NO2 estimates, showing greater consistency and daily variation alignment with observations (with NMB reduced from -0.3 to -0.1 compared to original CTM simulations). More importantly, DeepMMF effectively addressed the sample imbalance issue that causes overestimation (by over 100%) of downwind or rural concentrations in other methods. It achieves a higher R2 of 0.98 and a lower RMSE of 1.45 ppb compared to surface NO2 observations, overperforming other approaches, which show R2 values of 0.4-0.7 and RMSEs of 3-6 ppb. The method also offers a synergistic advantage by adjusting corresponding emissions, in agreement with changes (-10% to -20%) reported in the NEI between 2019 and 2020. Our results demonstrate the great potential of DeepMMF in data fusion to better support air pollution exposure estimation and forecasting.

PMID:39565242 | DOI:10.1021/acs.est.4c07341

Radiol Artif Intell. 2024 Nov 20:e240206. doi: 10.1148/ryai.240206. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate and compare performance of different artificial intelligence (AI) models in differentiating between benign and malignant breast tumors on diffusion-weighted imaging (DWI), including comparison with radiologist assessments. Materials and Methods In this retrospective study, patients with breast lesions underwent 3T breast MRI from May 2019 to March 2022. In addition to T1-weighted imaging, T2-weighted imaging, and contrast-enhanced imaging, DWI was acquired five b-values (0, 200, 800, 1000, and 1500 s/mm2). DWI data split into training and tuning and test sets were used for the development and assessment of AI models, including a small 2D convolutional neural network (CNN), ResNet18, EfficientNet-B0, and a 3D CNN. Performance of the DWI-based models in differentiating between benign and malignant breast tumors was compared with that of radiologists assessing standard breast MRI, with diagnostic performance assessed using receiver operating characteristic analysis. The study also examined data augmentation effects (A: random elastic deformation, B: random affine transformation/random noise, and C: mixup) on model performance. Results A total of 334 breast lesions in 293 patients (mean age [SD], 56.5 [15.1] years; all female) were analyzed. 2D CNN models outperformed the 3D CNN on the test dataset (area under the receiver operating characteristic curve [AUC] with different data augmentation methods: 0.83-0.88 versus 0.75-0.76). There was no evidence of a difference in performance between the small 2D CNN with augmentations A and B (AUC 0.88) and the radiologists (AUC 0.86) on the test dataset (P = .64). When comparing the small 2D CNN to radiologists, there was no evidence of a difference in specificity (81.4% versus 72.1%; P = .64) or sensitivity (85.9% versus 98.8%; P = .64). Conclusion AI models, particularly a small 2D CNN, showed good performance in differentiating between malignant and benign breast tumors using DWI, without needing manual segmentation. ©RSNA, 2024.

PMID:39565222 | DOI:10.1148/ryai.240206

J Acoust Soc Am. 2024 Nov 1;156(5):3502-3513. doi: 10.1121/10.0034445.

ABSTRACT

Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their need to fine-tune threshold parameters for different datasets and limited generalization restrict their utility in real-world applications. To address these challenges, this study proposes a supervised voicing detection model that leverages recorded laryngograph data. The model, adapted from a recently developed CrossNet architecture, is trained using reference voicing decisions derived from laryngograph datasets. Pretraining is also investigated to improve the generalization ability of the model. The proposed model produces robust voicing detection results, outperforming other strong baseline methods, and generalizes well to unseen datasets. The source code of the proposed model with pretraining is provided along with the list of used laryngograph datasets to facilitate further research in this area.

PMID:39565144 | DOI:10.1121/10.0034445

mSystems. 2024 Nov 20:e0139524. doi: 10.1128/msystems.01395-24. Online ahead of print.

ABSTRACT

The tumor microbiome, a complex community of microbes found in tumors, has been found to be linked to cancer development, progression, and treatment outcome. However, it remains a bottleneck in distangling the relationship between the tumor microbiome and host gene expressions in tumor microenvironment, as well as their concert effects on patient survival. In this study, we aimed to decode this complex relationship by developing ASD-cancer (autoencoder-based subtypes detector for cancer), a semi-supervised deep learning framework that could extract survival-related features from tumor microbiome and transcriptome data, and identify patients' survival subtypes. By using tissue samples from The Cancer Genome Atlas database, we identified two statistically distinct survival subtypes across all 20 types of cancer Our framework provided improved risk stratification (e.g., for liver hepatocellular carcinoma, [LIHC], log-rank test, P = 8.12E-6) compared to PCA (e.g., for LIHC, log-rank test, P = 0.87), predicted survival subtypes accurately, and identified biomarkers for survival subtypes. Additionally, we identified potential interactions between microbes and host genes that may play roles in survival. For instance, in LIHC, Arcobacter, Methylocella, and Isoptericola may regulate host survival through interactions with host genes enriched in the HIF-1 signaling pathway, indicating these species as potential therapy targets. Further experiments on validation data sets have also supported these patterns. Collectively, ASD-cancer has enabled accurate survival subtyping and biomarker discovery, which could facilitate personalized treatment for broad-spectrum types of cancers.IMPORTANCEUnraveling the intricate relationship between the tumor microbiome, host gene expressions, and their collective impact on cancer outcomes is paramount for advancing personalized treatment strategies. Our study introduces ASD-cancer, a cutting-edge autoencoder-based subtype detector. ASD-cancer decodes the complexities within the tumor microenvironment, successfully identifying distinct survival subtypes across 20 cancer types. Its superior risk stratification, demonstrated by significant improvements over traditional methods like principal component analysis, holds promise for refining patient prognosis. Accurate survival subtype predictions, biomarker discovery, and insights into microbe-host gene interactions elevate ASD-cancer as a powerful tool for advancing precision medicine. These findings not only contribute to a deeper understanding of the tumor microenvironment but also open avenues for personalized interventions across diverse cancer types, underscoring the transformative potential of ASD-cancer in shaping the future of cancer care.

PMID:39565103 | DOI:10.1128/msystems.01395-24

Hum Brain Mapp. 2024 Dec 1;45(17):e70071. doi: 10.1002/hbm.70071.

ABSTRACT

The retinogeniculate visual pathway (RGVP) is responsible for carrying visual information from the retina to the lateral geniculate nucleus. Identification and visualization of the RGVP are important in studying the anatomy of the visual system and can inform the treatment of related brain diseases. Diffusion MRI (dMRI) tractography is an advanced imaging method that uniquely enables in vivo mapping of the 3D trajectory of the RGVP. Currently, identification of the RGVP from tractography data relies on expert (manual) selection of tractography streamlines, which is time-consuming, has high clinical and expert labor costs, and is affected by inter-observer variability. In this paper, we present a novel deep learning framework, DeepRGVP, to enable fast and accurate identification of the RGVP from dMRI tractography data. We design a novel microstructure-informed supervised contrastive learning method that leverages both streamline label and tissue microstructure information to determine positive and negative pairs. We propose a new streamline-level data augmentation method to address highly imbalanced training data, where the number of RGVP streamlines is much lower than that of non-RGVP streamlines. In the experiments, we perform comparisons with several state-of-the-art deep learning methods that were designed for tractography parcellation. Furthermore, to assess the generalizability of the proposed RGVP method, we apply our method to dMRI tractography data from neurosurgical patients with pituitary tumors. In comparison with the state-of-the-art methods, we show superior RGVP identification results using DeepRGVP with significantly higher accuracy and F1 scores. In the patient data experiment, we show DeepRGVP can successfully identify RGVPs despite the effect of lesions affecting the RGVPs. Overall, our study shows the high potential of using deep learning to automatically identify the RGVP.

PMID:39564727 | DOI:10.1002/hbm.70071

ACS Appl Mater Interfaces. 2024 Nov 20. doi: 10.1021/acsami.4c15835. Online ahead of print.

ABSTRACT

It is challenging to build a deep learning predictive model using traditional data mining methods due to the scarcity of available data, and the model's internal decision-making process is often nonintuitive and difficult to explain. In this work, a directed message passing neural network model with transfer learning (TL) and chemprop interpreter is proposed to improve energy levels prediction and visualization for organic photovoltaic materials. The established model shows the best performance, with coefficient of determination reaching 0.787 for HOMO and 0.822 for LUMO in a small testing set after TL, compared to the other four models. Then, the chemprop interpreter analyzes local and global effects of 12 molecular structures on the energy levels for organic materials. After a comprehensive analysis of the energy level effects of nonfullerene Y-series, IT-series, and other organic materials, 12 new IT-series derivatives are designed. 1,1-dicyano-methylene-3-indanone (IC) end group halogenation can reduce HOMO and LUMO energy levels to varying degrees, while IC end group modified by electron-withdrawing aromatic groups can increase HOMO and LUMO energy levels and obtain relatively smaller electrostatic potential (ESP) to reducing intermolecular interactions. The influence of side-chain modification on energy levels is limited. It is worth mentioning that the predicted results of IT-series derivatives match density functional theory calculations. The model also shows good generalization and transferability for predicting the energy levels of other organic electronic materials. This work not only provides a cost-effective model for predicting the energy levels of organic photovoltaic materials but also explains the potential bridge between molecular structure and electronic properties.

PMID:39564708 | DOI:10.1021/acsami.4c15835

IEEE Open J Eng Med Biol. 2024 Sep 2;6:20-27. doi: 10.1109/OJEMB.2024.3453060. eCollection 2025.

ABSTRACT

Goal: To accurately detect infections in Diabetic Foot Ulcers (DFUs) using photographs taken at the Point of Care (POC). Achieving high performance is critical for preventing complications and amputations, as well as minimizing unnecessary emergency department visits and referrals. Methods: This paper proposes the Guided Conditional Diffusion Classifier (ConDiff). This novel deep-learning framework combines guided image synthesis with a denoising diffusion model and distance-based classification. The process involves (1) generating guided conditional synthetic images by injecting Gaussian noise to a guide (input) image, followed by denoising the noise-perturbed image through a reverse diffusion process, conditioned on infection status and (2) classifying infections based on the minimum Euclidean distance between synthesized images and the original guide image in embedding space. Results: ConDiff demonstrated superior performance with an average accuracy of 81% that outperformed state-of-the-art (SOTA) models by at least 3%. It also achieved the highest sensitivity of 85.4%, which is crucial in clinical domains while significantly improving specificity to 74.4%, surpassing the best SOTA model. Conclusions: ConDiff not only improves the diagnosis of DFU infections but also pioneers the use of generative discriminative models for detailed medical image analysis, offering a promising approach for improving patient outcomes.

PMID:39564561 | PMC:PMC11573405 | DOI:10.1109/OJEMB.2024.3453060

IEEE Open J Eng Med Biol. 2024 Sep 9;6:41-53. doi: 10.1109/OJEMB.2024.3455801. eCollection 2025.

ABSTRACT

Infectious diseases are a major global public health concern. Precise modeling and prediction methods are essential to develop effective strategies for disease control. However, data imbalance and the presence of noise and intensity inhomogeneity make disease detection more challenging. Goal: In this article, a novel infectious disease pattern prediction system is proposed by integrating deterministic and stochastic model benefits with the benefits of the deep learning model. Results: The combined benefits yield improvement in the performance of solution prediction. Moreover, the objective is also to investigate the influence of time delay on infection rates and rates associated with vaccination. Conclusions: In this proposed framework, at first, the global stability at disease free equilibrium is effectively analysed using Routh-Haurwitz criteria and Lyapunov method, and the endemic equilibrium is analysed using non-linear Volterra integral equations in the infectious disease model. Unlike the existing model, emphasis is given to suggesting a model that is capable of investigating stability while considering the effect of vaccination and migration rate. Next, the influence of vaccination on the rate of infection is effectively predicted using an efficient deep learning model by employing the long-term dependencies in sequential data. Thus making the prediction more accurate.

PMID:39564557 | PMC:PMC11573407 | DOI:10.1109/OJEMB.2024.3455801