IEEE Trans Pattern Anal Mach Intell. 2024 Jul 1;PP. doi: 10.1109/TPAMI.2024.3421300. Online ahead of print.

ABSTRACT

Training with more data has always been the most stable and effective way of improving performance in the deep learning era. The Open Images dataset, the largest object detection dataset, presents significant opportunities and challenges for general and sophisticated scenarios. However, its semi-automatic collection and labeling process, designed to manage the huge data scale, leads to label-related problems, including explicit or implicit multiple labels per object and highly imbalanced label distribution. In this work, we quantitatively analyze the major problems in large-scale object detection and provide a detailed yet comprehensive demonstration of our solutions. First, we design a concurrent softmax to handle the multi-label problems in object detection and propose a soft-balance sampling method with a hybrid training scheduler to address the label imbalance. This approach yields a notable improvement of 3.34 points, achieving the best single-model performance with a mAP of 60.90% on the public object detection test set of Open Images. Then, we introduce a well-designed ensemble mechanism that substantially enhances the performance of the single model, achieving an overall mAP of 67.17%, which is 4.29 points higher than the best result from the Open Images public test 2018. Our result is published on https://www.kaggle.com/c/open-images-2019-object-detection/leaderboard.

PMID:38949947 | DOI:10.1109/TPAMI.2024.3421300

IEEE Trans Med Imaging. 2024 Jul 1;PP. doi: 10.1109/TMI.2024.3421644. Online ahead of print.

ABSTRACT

Deep learning approaches for multi-label Chest X-ray (CXR) images classification usually require large-scale datasets. However, acquiring such datasets with full annotations is costly, time-consuming, and prone to noisy labels. Therefore, we introduce a weakly supervised learning problem called Single Positive Multi-label Learning (SPML) into CXR images classification (abbreviated as SPML-CXR), in which only one positive label is annotated per image. A simple solution to SPML-CXR problem is to assume that all the unannotated pathological labels are negative, however, it might introduce false negative labels and decrease the model performance. To this end, we present a Multi-level Pseudo-label Consistency (MPC) framework for SPML-CXR. First, inspired by the pseudo-labeling and consistency regularization in semi-supervised learning, we construct a weak-to-strong consistency framework, where the model prediction on weakly-augmented image is treated as the pseudo label for supervising the model prediction on a strongly-augmented version of the same image, and define an Image-level Perturbation-based Consistency (IPC) regularization to recover the potential mislabeled positive labels. Besides, we incorporate Random Elastic Deformation (RED) as an additional strong augmentation to enhance the perturbation. Second, aiming to expand the perturbation space, we design a perturbation stream to the consistency framework at the feature-level and introduce a Feature-level Perturbation-based Consistency (FPC) regularization as a supplement. Third, we design a Transformer-based encoder module to explore the sample relationship within each mini-batch by a Batch-level Transformer-based Correlation (BTC) regularization. Extensive experiments on the CheXpert and MIMIC-CXR datasets have shown the effectiveness of our MPC framework for solving the SPML-CXR problem.

PMID:38949934 | DOI:10.1109/TMI.2024.3421644

IEEE Trans Neural Syst Rehabil Eng. 2024 Jul 1;PP. doi: 10.1109/TNSRE.2024.3421551. Online ahead of print.

ABSTRACT

Brain-computer interfaces (BCIs) provide a communication interface between the brain and external devices and have the potential to restore communication and control in patients with neurological injury or disease. For the invasive BCIs, most studies recruited participants from hospitals requiring invasive device implantation. Three widely used clinical invasive devices that have the potential for BCIs applications include surface electrodes used in electrocorticography (ECoG) and depth electrodes used in Stereo-electroencephalography (SEEG) and deep brain stimulation (DBS). This review focused on BCIs research using surface (ECoG) and depth electrodes (including SEEG, and DBS electrodes) for movement decoding on human subjects. Unlike previous reviews, the findings presented here are from the perspective of the decoding target or task. In detail, five tasks will be considered, consisting of the kinematic decoding, kinetic decoding, identification of body parts, dexterous hand decoding, and motion intention decoding. The typical studies are surveyed and analyzed. The reviewed literature demonstrated a distributed motor-related network that spanned multiple brain regions. Comparison between surface and depth studies demonstrated that richer information can be obtained using surface electrodes. With regard to the decoding algorithms, deep learning exhibited superior performance using raw signals than traditional machine learning algorithms. Despite the promising achievement made by the open-loop BCIs, closed-loop BCIs with sensory feedback are still in their early stage, and the chronic implantation of both ECoG surface and depth electrodes has not been thoroughly evaluated.

PMID:38949928 | DOI:10.1109/TNSRE.2024.3421551

IEEE Trans Neural Syst Rehabil Eng. 2024 Jul 1;PP. doi: 10.1109/TNSRE.2024.3420960. Online ahead of print.

ABSTRACT

Machine learning and deep learning advancements have boosted Brain-Computer Interface (BCI) performance, but their wide-scale applicability is limited due to factors like individual health, hardware variations, and cultural differences affecting neural data. Studies often focus on uniform single-site experiments in uniform settings, leading to high performance that may not translate well to real-world diversity. Deep learning models aim to enhance BCI classification accuracy, and transfer learning has been suggested to adapt models to individual neural patterns using a base model trained on others' data. This approach promises better generalizability and reduced overfitting, yet challenges remain in handling diverse and imbalanced datasets from different equipment, subjects, multiple centres in different countries, and both healthy and patient populations for effective model transfer and tuning. In a setting characterized by maximal heterogeneity, we proposed P300 wave detection in BCIs employing a convolutional neural network fitted with adaptive transfer learning based on Poison Sampling Disk (PDS) called Active Sampling (AS), which flexibly adjusts the transition from source data to the target domain. Our results reported for subject adaptive with 40% of adaptive fine-tuning that the averaged classification accuracy improved by 5.36% and standard deviation reduced by 12.22% using two distinct, internationally replicated datasets. These results outperformed in classification accuracy, computational time, and training efficiency, mainly due to the proposed Active Sampling (AS) method for transfer learning.

PMID:38949927 | DOI:10.1109/TNSRE.2024.3420960

Med Phys. 2024 Jul 1. doi: 10.1002/mp.17283. Online ahead of print.

ABSTRACT

BACKGROUND: Lung cancer is the most common type of cancer. Detection of lung cancer at an early stage can reduce mortality rates. Pulmonary nodules may represent early cancer and can be identified through computed tomography (CT) scans. Malignant risk can be estimated based on attributes like size, shape, location, and density.

PURPOSE: Deep learning algorithms have achieved remarkable advancements in this domain compared to traditional machine learning methods. Nevertheless, many existing anchor-based deep learning algorithms exhibit sensitivity to predefined anchor-box configurations, necessitating manual adjustments to obtain optimal outcomes. Conversely, current anchor-free deep learning-based nodule detection methods normally adopt fixed-size nodule models like cubes or spheres.

METHODS: To address these technical challenges, we propose a multiscale 3D anchor-free deep learning network (M3N) for pulmonary nodule detection, leveraging adjustable nodule modeling (ANM). Within this framework, ANM empowers the representation of target objects in an anisotropic manner, with a novel point selection strategy (PSS) devised to accelerate the learning process of anisotropic representation. We further incorporate a composite loss function that combines the conventional L2 loss and cosine similarity loss, facilitating M3N to learn nodules' intensity distribution in three dimensions.

RESULTS: Experiment results show that the M3N achieves 90.6% competitive performance metrics (CPM) with seven predefined false positives per scan on the LUNA 16 dataset. This performance appears to exceed that of other state-of-the-art deep learning-based networks reported in their respective publications. Individual test results also demonstrate that M3N excels in providing more accurate, adaptive bounding boxes surrounding the contours of target nodules.

CONCLUSIONS: The newly developed nodule detection system reduces reliance on prior knowledge, such as the general size of objects in the dataset, thus it should enhance overall robustness and versatility. Distinct from traditional nodule modeling techniques, the ANM approach aligns more closely with the morphological characteristics of nodules. Time consumption and detection results demonstrate promising efficiency and accuracy which should be validated in clinical settings.

PMID:38949577 | DOI:10.1002/mp.17283

J Acoust Soc Am. 2024 Jul 1;156(1):65-80. doi: 10.1121/10.0026437.

ABSTRACT

Environment estimation is a challenging task in reverberant settings such as the underwater and indoor acoustic domains. The locations of reflective boundaries, for example, can be estimated using acoustic echoes and leveraged for subsequent, more accurate localization and mapping. Current boundary estimation methods are constrained to high signal-to-noise ratios or are customized to specific environments. Existing methods also often require a correct assignment of echoes to boundaries, which is difficult if spurious echoes are detected. To evade these limitations, a convolutional neural network (NN) method is developed for robust two-dimensional boundary estimation, given known emitter and receiver locations. A Hough transform-inspired algorithm is leveraged to transform echo times of arrival into images, which are amenable to multi-resolution regression by NNs. The same architecture is trained on transform images of different resolutions to obtain diverse NNs, deployed sequentially for increasingly refined boundary estimation. A correct echo labeling solution is not required, and the method is robust to reverberation. The proposed method is tested in simulation and for real data from a water tank, where it outperforms state-of-the-art alternatives. These results are encouraging for the future development of data-driven three-dimensional environment estimation with high practical value in underwater acoustic detection and tracking.

PMID:38949286 | DOI:10.1121/10.0026437

J Med Primatol. 2024 Aug;53(4):e12722. doi: 10.1111/jmp.12722.

ABSTRACT

BACKGROUND: Tuberculosis (TB) kills approximately 1.6 million people yearly despite the fact anti-TB drugs are generally curative. Therefore, TB-case detection and monitoring of therapy, need a comprehensive approach. Automated radiological analysis, combined with clinical, microbiological, and immunological data, by machine learning (ML), can help achieve it.

METHODS: Six rhesus macaques were experimentally inoculated with pathogenic Mycobacterium tuberculosis in the lung. Data, including Computed Tomography (CT), were collected at 0, 2, 4, 8, 12, 16, and 20 weeks.

RESULTS: Our ML-based CT analysis (TB-Net) efficiently and accurately analyzed disease progression, performing better than standard deep learning model (LLM OpenAI's CLIP Vi4). TB-Net based results were more consistent than, and confirmed independently by, blinded manual disease scoring by two radiologists and exhibited strong correlations with blood biomarkers, TB-lesion volumes, and disease-signs during disease pathogenesis.

CONCLUSION: The proposed approach is valuable in early disease detection, monitoring efficacy of therapy, and clinical decision making.

PMID:38949157 | DOI:10.1111/jmp.12722

bioRxiv [Preprint]. 2024 Jun 22:2024.06.18.599625. doi: 10.1101/2024.06.18.599625.

ABSTRACT

Kidney disease is highly heritable; however, the causal genetic variants, the cell types in which these variants function, and the molecular mechanisms underlying kidney disease remain largely unknown. To identify genetic loci affecting kidney function, we performed a GWAS using multiple kidney function biomarkers and identified 462 loci. To begin to investigate how these loci affect kidney function, we generated single-cell chromatin accessibility (scATAC-seq) maps of the human kidney and identified candidate cis -regulatory elements (cCREs) for kidney podocytes, tubule epithelial cells, and kidney endothelial, stromal, and immune cells. Kidney tubule epithelial cCREs explained 58% of kidney function SNP-heritability and kidney podocyte cCREs explained an additional 6.5% of SNP-heritability. In contrast, little kidney function heritability was explained by kidney endothelial, stromal, or immune cell-specific cCREs. Through functionally informed fine-mapping, we identified putative causal kidney function variants and their corresponding cCREs. Using kidney scATAC-seq data, we created a deep learning model (which we named ChromKid) to predict kidney cell type-specific chromatin accessibility from sequence. ChromKid and allele specific kidney scATAC-seq revealed that many fine-mapped kidney function variants locally change chromatin accessibility in tubule epithelial cells. Enhancer assays confirmed that fine-mapped kidney function variants alter tubule epithelial regulatory element function. To map the genes which these regulatory elements control, we used CRISPR interference (CRISPRi) to target these regulatory elements in tubule epithelial cells and assessed changes in gene expression. CRISPRi of enhancers harboring kidney function variants regulated NDRG1 and RBPMS expression. Thus, inherited differences in tubule epithelial NDRG1 and RBPMS expression may predispose to kidney disease in humans. We conclude that genetic variants affecting tubule epithelial regulatory element function account for most SNP-heritability of human kidney function. This work provides an experimental approach to identify the variants, regulatory elements, and genes involved in polygenic disease.

PMID:38948875 | PMC:PMC11212968 | DOI:10.1101/2024.06.18.599625

bioRxiv [Preprint]. 2024 Jun 21:2024.06.19.599799. doi: 10.1101/2024.06.19.599799.

ABSTRACT

Oligodendrocytes are the myelinating cells within the central nervous system. Many oligodendrocyte genes have been associated with brain disorders. However, how transcription factors (TFs) cooperate for gene regulation in oligodendrocytes remains largely uncharacterized. To address this, we integrated scRNA-seq and scATAC-seq data to identify the cooperative TFs that co-regulate the target gene (TG) expression in oligodendrocytes. First, we identified co- binding TF pairs whose binding sites overlapped in oligodendrocyte-specific regulatory regions. Second, we trained a deep learning model to predict the expression level of each TG using the expression levels of co-binding TFs. Third, using the trained models, we computed the TF importance and TF-TF interaction scores for predicting TG expression by the Shapley interaction scores. We found that the co-binding TF pairs involving known important TF pairs for oligodendrocyte differentiation, such as SOX10-TCF12, SOX10-MYRF, and SOX10-OLIG2, exhibited significantly higher Shapley scores than others (t-test, p-value < 1e-4). Furthermore, we identified 153 oligodendrocyte-associated eQTLs that reside in oligodendrocyte-specific enhancers or promoters where their eGenes (TGs) are regulated by cooperative TFs, suggesting potential novel regulatory roles from genetic variants. We also experimentally validated some identified TF pairs such as SOX10-OLIG2 and SOX10-NKX2.2 by co-enrichment analysis, using ChIP-seq data from rat peripheral nerve.

PMID:38948852 | PMC:PMC11213031 | DOI:10.1101/2024.06.19.599799

bioRxiv [Preprint]. 2024 Jun 17:2024.06.14.599097. doi: 10.1101/2024.06.14.599097.

ABSTRACT

BACKGROUND: Transmission electron microscopy (TEM) images can visualize kidney glomerular filtration barrier ultrastructure, including the glomerular basement membrane (GBM) and podocyte foot processes (PFP). Podocytopathy is associated with glomerular filtration barrier morphological changes observed experimentally and clinically by measuring GBM or PFP width. However, these measurements are currently performed manually. This limits research on podocytopathy disease mechanisms and therapeutics due to labor intensiveness and inter-operator variability.

METHODS: We developed a deep learning-based digital pathology computational method to measure GBM and PFP width in TEM images from the kidneys of Integrin-Linked Kinase (ILK) podocyte-specific conditional knockout (cKO) mouse, an animal model of podocytopathy, compared to wild-type (WT) control mouse. We obtained TEM images from WT and ILK cKO littermate mice at 4 weeks old. Our automated method was composed of two stages: a U-Net model for GBM segmentation, followed by an image processing algorithm for GBM and PFP width measurement. We evaluated its performance with a 4-fold cross-validation study on WT and ILK cKO mouse kidney pairs.

RESULTS: Mean (95% confidence interval) GBM segmentation accuracy, calculated as Jaccard index, was 0.54 (0.52-0.56) for WT and 0.61 (0.56-0.66) for ILK cKO TEM images. Automated and corresponding manual measured PFP widths differed significantly for both WT (p<0.05) and ILK cKO (p<0.05), while automated and manual GBM widths differed only for ILK cKO (p<0.05) but not WT (p=0.49) specimens. WT and ILK cKO specimens were morphologically distinguishable by manual GBM (p<0.05) and PFP (p<0.05) width measurements. This phenotypic difference was reflected in the automated GBM (p=0.06) more than PFP (p=0.20) widths.

CONCLUSIONS: These results suggest that certain automated measurements enabled via deep learning-based digital pathology tools could distinguish healthy kidneys from those with podocytopathy. Our proposed method provides high-throughput, objective morphological analysis and could facilitate podocytopathy research and translate into clinical diagnosis.

KEY POINTS: We leveraged U-Net architecture in an algorithm to measure the widths of glomerular basement membrane and podocyte foot processes.Deep learning-based automated measurement of glomerular filtration barrier morphology has promise in podocytopathy research and diagnosis.

PMID:38948787 | PMC:PMC11212870 | DOI:10.1101/2024.06.14.599097

bioRxiv [Preprint]. 2024 Jun 20:2024.06.20.599815. doi: 10.1101/2024.06.20.599815.

ABSTRACT

In this paper, we introduce a new, open-source software developed in Python for analyzing Auditory Brainstem Response (ABR) waveforms. ABRs are a far-field recording of synchronous neural activity generated by the auditory fibers in the ear in response to sound, and used to study acoustic neural information traveling along the ascending auditory pathway. Common ABR data analysis practices are subject to human interpretation and are labor-intensive, requiring manual annotations and visual estimation of hearing thresholds. The proposed new Auditory Brainstem Response Analyzer (ABRA) software is designed to facilitate the analysis of ABRs by supporting batch data import/export, waveform visualization, and statistical analysis. Techniques implemented in this software include algorithmic peak finding, threshold estimation, latency estimation, time warping for curve alignment, and 3D plotting of ABR waveforms over stimulus frequencies and decibels. The excellent performance on a large dataset of ABR collected from three labs in the field of hearing research that use different experimental recording settings illustrates the efficacy, flexibility, and wide utility of ABRA.

PMID:38948763 | PMC:PMC11213013 | DOI:10.1101/2024.06.20.599815

bioRxiv [Preprint]. 2024 Jun 17:2024.06.17.599381. doi: 10.1101/2024.06.17.599381.

ABSTRACT

Cochlear hair cell stereocilia bundles are key organelles required for normal hearing. Often, deafness mutations cause aberrant stereocilia heights or morphology that are visually apparent but challenging to quantify. Actin-based structures, stereocilia are easily and most often labeled with phalloidin then imaged with 3D confocal microscopy. Unfortunately, phalloidin non-specifically labels all the actin in the tissue and cells and therefore results in a challenging segmentation task wherein the stereocilia phalloidin signal must be separated from the rest of the tissue. This can require many hours of manual human effort for each 3D confocal image stack. Currently, there are no existing software pipelines that provide an end-to-end automated solution for 3D stereocilia bundle instance segmentation. Here we introduce VASCilia, a Napari plugin designed to automatically generate 3D instance segmentation and analysis of 3D confocal images of cochlear hair cell stereocilia bundles stained with phalloidin. This plugin combines user-friendly manual controls with advanced deep learning-based features to streamline analyses. With VASCilia, users can begin their analysis by loading image stacks. The software automatically preprocesses these samples and displays them in Napari. At this stage, users can select their desired range of z-slices, adjust their orientation, and initiate 3D instance segmentation. After segmentation, users can remove any undesired regions and obtain measurements including volume, centroids, and surface area. VASCilia introduces unique features that measures bundle heights, determines their orientation with respect to planar polarity axis, and quantifies the fluorescence intensity within each bundle. The plugin is also equipped with trained deep learning models that differentiate between inner hair cells and outer hair cells and predicts their tonotopic position within the cochlea spiral. Additionally, the plugin includes a training section that allows other laboratories to fine-tune our model with their own data, provides responsive mechanisms for manual corrections through event-handlers that check user actions, and allows users to share their analyses by uploading a pickle file containing all intermediate results. We believe this software will become a valuable resource for the cochlea research community, which has traditionally lacked specialized deep learning-based tools for obtaining high-throughput image quantitation. Furthermore, we plan to release our code along with a manually annotated dataset that includes approximately 55 3D stacks featuring instance segmentation. This dataset comprises a total of 1,870 instances of hair cells, distributed between 410 inner hair cells and 1,460 outer hair cells, all annotated in 3D. As the first open-source dataset of its kind, we aim to establish a foundational resource for constructing a comprehensive atlas of cochlea hair cell images. Together, this open-source tool will greatly accelerate the analysis of stereocilia bundles and demonstrates the power of deep learning-based algorithms for challenging segmentation tasks in biological imaging research. Ultimately, this initiative will support the development of foundational models adaptable to various species, markers, and imaging scales to advance and accelerate research within the cochlea research community.

PMID:38948743 | PMC:PMC11212889 | DOI:10.1101/2024.06.17.599381

BJR Open. 2024 Jun 3;6(1):tzae014. doi: 10.1093/bjro/tzae014. eCollection 2024 Jan.

ABSTRACT

OBJECTIVES: Toxicity-driven adaptive radiotherapy (RT) is enhanced by the superior soft tissue contrast of magnetic resonance (MR) imaging compared with conventional computed tomography (CT). However, in an MR-only RT pathway synthetic CTs (sCT) are required for dose calculation. This study evaluates 3 sCT approaches for accurate rectal toxicity prediction in prostate RT.

METHODS: Thirty-six patients had MR (T2-weighted acquisition optimized for anatomical delineation, and T1-Dixon) with same day standard-of-care planning CT for prostate RT. Multiple sCT were created per patient using bulk density (BD), tissue stratification (TS, from T1-Dixon) and deep-learning (DL) artificial intelligence (AI) (from T2-weighted) approaches for dose distribution calculation and creation of rectal dose volume histograms (DVH) and dose surface maps (DSM) to assess grade-2 (G2) rectal bleeding risk.

RESULTS: Maximum absolute errors using sCT for DVH-based G2 rectal bleeding risk (risk range 1.6% to 6.1%) were 0.6% (BD), 0.3% (TS) and 0.1% (DL). DSM-derived risk prediction errors followed a similar pattern. DL sCT has voxel-wise density generated from T2-weighted MR and improved accuracy for both risk-prediction methods.

CONCLUSIONS: DL improves dosimetric and predicted risk calculation accuracy. Both TS and DL methods are clinically suitable for sCT generation in toxicity-guided RT, however, DL offers increased accuracy and offers efficiencies by removing the need for T1-Dixon MR.

ADVANCES IN KNOWLEDGE: This study demonstrates novel insights regarding the effect of sCT on predictive toxicity metrics, demonstrating clear accuracy improvement with increased sCT resolution. Accuracy of toxicity calculation in MR-only RT should be assessed for all treatment sites where dose to critical structures will guide adaptive-RT strategies.

CLINICAL TRIAL REGISTRATION NUMBER: Patient data were taken from an ethically approved (UK Health Research Authority) clinical trial run at Guy's and St Thomas' NHS Foundation Trust. Study Name: MR-simulation in Radiotherapy for Prostate Cancer. ClinicalTrials.gov Identifier: NCT03238170.

PMID:38948455 | PMC:PMC11213647 | DOI:10.1093/bjro/tzae014

Front Genet. 2024 Jun 14;15:1401544. doi: 10.3389/fgene.2024.1401544. eCollection 2024.

ABSTRACT

Introduction: Synergistic medication, a crucial therapeutic strategy in cancer treatment, involves combining multiple drugs to enhance therapeutic effectiveness and mitigate side effects. Current research predominantly employs deep learning models for extracting features from cell line and cancer drug structure data. However, these methods often overlook the intricate nonlinear relationships within the data, neglecting the distribution characteristics and weighted probability densities of gene expression data in multi-dimensional space. It also fails to fully exploit the structural information of cancer drugs and the potential interactions between drug molecules. Methods: To overcome these challenges, we introduce an innovative end-to-end learning model specifically tailored for cancer drugs, named Dual Kernel Density and Positional Encoding (DKPE) for Graph Synergy Representation Network (DKPEGraphSYN). This model is engineered to refine the prediction of drug combination synergy effects in cancer. DKPE-GraphSYN utilizes Dual Kernel Density Estimation and Positional Encoding techniques to effectively capture the weighted probability density and spatial distribution information of gene expression, while exploring the interactions and potential relationships between cancer drug molecules via a graph neural network. Results: Experimental results show that our prediction model achieves significant performance enhancements in forecasting drug synergy effects on a comprehensive cancer drug and cell line synergy dataset, achieving an AUPR of 0.969 and an AUC of 0.976. Discussion: These results confirm our model's superior accuracy in predicting cancer drug combinations, providing a supportive method for clinical medication strategy in cancer.

PMID:38948360 | PMC:PMC11211516 | DOI:10.3389/fgene.2024.1401544

Reprod Med Biol. 2024 Jun 28;23(1):e12590. doi: 10.1002/rmb2.12590. eCollection 2024 Jan-Dec.

ABSTRACT

BACKGROUND: The third AI boom, which began in 2010, has been characterized by the rapid evolution and diversification of AI and marked by the development of key technologies such as machine learning and deep learning. AI is revolutionizing the medical field, enhancing diagnostic accuracy, surgical outcomes, and drug production.

METHODS: This review includes explanations of digital transformation (DX), the history of AI, the difference between machine learning and deep learning, recent AI topics, medical AI, and AI research in male infertility.

MAIN FINDINGS RESULTS: In research on male infertility, I established an AI-based prediction model for Johnsen scores and an AI predictive model for sperm retrieval in non-obstructive azoospermia, both by no-code AI.

CONCLUSIONS: AI is making constant progress. It would be ideal for physicians to acquire a knowledge of AI and even create AI models. No-code AI tools have revolutionized model creation, allowing individuals to independently handle data preparation and model development. Previously a team effort, this shift empowers users to craft customized AI models solo, offering greater flexibility and control in the model creation process.

PMID:38948339 | PMC:PMC11211808 | DOI:10.1002/rmb2.12590

Cancer Innov. 2024 May 12;3(4):e110. doi: 10.1002/cai2.110. eCollection 2024 Aug.

ABSTRACT

BACKGROUND: The rate at which the anticancer drug paclitaxel is cleared from the body markedly impacts its dosage and chemotherapy effectiveness. Importantly, paclitaxel clearance varies among individuals, primarily because of genetic polymorphisms. This metabolic variability arises from a nonlinear process that is influenced by multiple single nucleotide polymorphisms (SNPs). Conventional bioinformatics methods struggle to accurately analyze this complex process and, currently, there is no established efficient algorithm for investigating SNP interactions.

METHODS: We developed a novel machine-learning approach called GEP-CSIs data mining algorithm. This algorithm, an advanced version of GEP, uses linear algebra computations to handle discrete variables. The GEP-CSI algorithm calculates a fitness function score based on paclitaxel clearance data and genetic polymorphisms in patients with nonsmall cell lung cancer. The data were divided into a primary set and a validation set for the analysis.

RESULTS: We identified and validated 1184 three-SNP combinations that had the highest fitness function values. Notably, SERPINA1, ATF3 and EGF were found to indirectly influence paclitaxel clearance by coordinating the activity of genes previously reported to be significant in paclitaxel clearance. Particularly intriguing was the discovery of a combination of three SNPs in genes FLT1, EGF and MUC16. These SNPs-related proteins were confirmed to interact with each other in the protein-protein interaction network, which formed the basis for further exploration of their functional roles and mechanisms.

CONCLUSION: We successfully developed an effective deep-learning algorithm tailored for the nuanced mining of SNP interactions, leveraging data on paclitaxel clearance and individual genetic polymorphisms.

PMID:38948246 | PMC:PMC11212318 | DOI:10.1002/cai2.110

Npj Imaging. 2024;2(1):17. doi: 10.1038/s44303-024-00021-7. Epub 2024 Jun 28.

ABSTRACT

Label-free autofluorescence lifetime is a unique feature of the inherent fluorescence signals emitted by natural fluorophores in biological samples. Fluorescence lifetime imaging microscopy (FLIM) can capture these signals enabling comprehensive analyses of biological samples. Despite the fundamental importance and wide application of FLIM in biomedical and clinical sciences, existing methods for analysing FLIM images often struggle to provide rapid and precise interpretations without reliable references, such as histology images, which are usually unavailable alongside FLIM images. To address this issue, we propose a deep learning (DL)-based approach for generating virtual Hematoxylin and Eosin (H&E) staining. By combining an advanced DL model with a contemporary image quality metric, we can generate clinical-grade virtual H&E-stained images from label-free FLIM images acquired on unstained tissue samples. Our experiments also show that the inclusion of lifetime information, an extra dimension beyond intensity, results in more accurate reconstructions of virtual staining when compared to using intensity-only images. This advancement allows for the instant and accurate interpretation of FLIM images at the cellular level without the complexities associated with co-registering FLIM and histology images. Consequently, we are able to identify distinct lifetime signatures of seven different cell types commonly found in the tumour microenvironment, opening up new opportunities towards biomarker-free tissue histology using FLIM across multiple cancer types.

PMID:38948152 | PMC:PMC11213708 | DOI:10.1038/s44303-024-00021-7

Risk Anal. 2024 Jun 30. doi: 10.1111/risa.14353. Online ahead of print.

ABSTRACT

This article presents a risk analysis of large language models (LLMs), a type of "generative" artificial intelligence (AI) system that produces text, commonly in response to textual inputs from human users. The article is specifically focused on the risk of LLMs causing an extreme catastrophe in which they do something akin to taking over the world and killing everyone. The possibility of LLM takeover catastrophe has been a major point of public discussion since the recent release of remarkably capable LLMs such as ChatGPT and GPT-4. This arguably marks the first time when actual AI systems (and not hypothetical future systems) have sparked concern about takeover catastrophe. The article's analysis compares (A) characteristics of AI systems that may be needed for takeover, as identified in prior theoretical literature on AI takeover risk, with (B) characteristics observed in current LLMs. This comparison reveals that the capabilities of current LLMs appear to fall well short of what may be needed for takeover catastrophe. Future LLMs may be similarly incapable due to fundamental limitations of deep learning algorithms. However, divided expert opinion on deep learning and surprise capabilities found in current LLMs suggests some risk of takeover catastrophe from future LLMs. LLM governance should monitor for changes in takeover characteristics and be prepared to proceed more aggressively if warning signs emerge. Unless and until such signs emerge, more aggressive governance measures may be unwarranted.

PMID:38945529 | DOI:10.1111/risa.14353

Sci Total Environ. 2024 Jun 28:174357. doi: 10.1016/j.scitotenv.2024.174357. Online ahead of print.

ABSTRACT

River water quality has been significantly impacted by climate change and extreme weather events worldwide. Despite increasing studies on deep learning techniques for river water quality management, understanding which riverine water quality parameters can be well predicted by meteorologically-driven deep learning still requires further investigation. Here we explored the prediction performance of a traditional Recurrent Neural Network, a Long Short-Term Memory network (LSTM), and a Gated Recurrent Unit (GRU) using meteorological conditions as inputs in the Dahei River basin. We found that deep learning models (i.e., LSTM and GRU) demonstrated remarkable effectiveness in predicting multiple water quality parameters at daily scale, including water temperature, dissolved oxygen, electrical conductivity, chemical oxygen demand, ammonia nitrogen, total phosphorous, and total nitrogen, but not turbidity. The GRU model performed best with an average determination coefficient of 0.94. Compared to the daily-average prediction, the GRU model exhibited limited error increment of 10-40 % for most water quality parameters when predicting daily extreme values (i.e., the maximum and minimum). Moreover, deep learning showed superior performance in collective prediction for multiple water quality parameters than individual ones, enabling a more comprehensive understanding of the river water quality dynamics from meteorological data. This study holds the promise of applying meteorologically-driven deep learning techniques for water quality prediction to a broader range of watersheds, particularly in chemically ungauged areas.

PMID:38945234 | DOI:10.1016/j.scitotenv.2024.174357

Neural Netw. 2024 Jun 21;178:106482. doi: 10.1016/j.neunet.2024.106482. Online ahead of print.

ABSTRACT

In practical engineering, obtaining labeled high-quality fault samples poses challenges. Conventional fault diagnosis methods based on deep learning struggle to discern the underlying causes of mechanical faults from a fine-grained perspective, due to the scarcity of annotated data. To tackle those issue, we propose a novel semi-supervised Gaussian Mixed Variational Autoencoder method, SeGMVAE, aimed at acquiring unsupervised representations that can be transferred across fine-grained fault diagnostic tasks, enabling the identification of previously unseen faults using only the small number of labeled samples. Initially, Gaussian mixtures are introduced as a multimodal prior distribution for the Variational Autoencoder. This distribution is dynamically optimized for each task through an expectation-maximization (EM) algorithm, constructing a latent representation of the bridging task and unlabeled samples. Subsequently, a set variational posterior approach is presented to encode each task sample into the latent space, facilitating meta-learning. Finally, semi-supervised EM integrates the posterior of labeled data by acquiring task-specific parameters for diagnosing unseen faults. Results from two experiments demonstrate that SeGMVAE excels in identifying new fine-grained faults and exhibits outstanding performance in cross-domain fault diagnosis across different machines. Our code is available at https://github.com/zhiqan/SeGMVAE.

PMID:38945116 | DOI:10.1016/j.neunet.2024.106482