Heliyon. 2024 Aug 23;10(17):e36743. doi: 10.1016/j.heliyon.2024.e36743. eCollection 2024 Sep 15.

ABSTRACT

This review article offers a comprehensive analysis of current developments in the application of machine learning for cancer diagnostic systems. The effectiveness of machine learning approaches has become evident in improving the accuracy and speed of cancer detection, addressing the complexities of large and intricate medical datasets. This review aims to evaluate modern machine learning techniques employed in cancer diagnostics, covering various algorithms, including supervised and unsupervised learning, as well as deep learning and federated learning methodologies. Data acquisition and preprocessing methods for different types of data, such as imaging, genomics, and clinical records, are discussed. The paper also examines feature extraction and selection techniques specific to cancer diagnosis. Model training, evaluation metrics, and performance comparison methods are explored. Additionally, the review provides insights into the applications of machine learning in various cancer types and discusses challenges related to dataset limitations, model interpretability, multi-omics integration, and ethical considerations. The emerging field of explainable artificial intelligence (XAI) in cancer diagnosis is highlighted, emphasizing specific XAI techniques proposed to improve cancer diagnostics. These techniques include interactive visualization of model decisions and feature importance analysis tailored for enhanced clinical interpretation, aiming to enhance both diagnostic accuracy and transparency in medical decision-making. The paper concludes by outlining future directions, including personalized medicine, federated learning, deep learning advancements, and ethical considerations. This review aims to guide researchers, clinicians, and policymakers in the development of efficient and interpretable machine learning-based cancer diagnostic systems.

PMID:39263113 | PMC:PMC11387343 | DOI:10.1016/j.heliyon.2024.e36743

Heliyon. 2024 Aug 25;10(17):e36823. doi: 10.1016/j.heliyon.2024.e36823. eCollection 2024 Sep 15.

ABSTRACT

Human Pose Estimation (HPE) is a crucial step towards understanding people in images and videos. HPE provides geometric and motion information of the human body, which has been applied to a wide range of applications (e.g., human-computer interaction, motion analysis, augmented reality, virtual reality, healthcare, etc.). An extremely useful task of this kind is the 2D pose estimation of bedridden patients from infrared (IR) images. Here, the IR imaging modality is preferred due to privacy concerns and the need for monitoring both uncovered and covered patients at different levels of illumination. The major drawback of this research problem is the unavailability of covered examples, which are very costly to collect and time-consuming to label. In this work, a deep learning-based framework was developed for human sleeping pose estimation on covered images using only the uncovered training images. In the training scheme, two different image augmentation techniques, a statistical approach as well as a GAN-based approach, were explored for domain adaptation, where the statistical approach performed better. The accuracy of the model trained on the statistically augmented dataset was improved by 124 % as compared with the model trained on non-augmented images. To handle the scarcity of training infrared images, a transfer learning strategy was used by pre-training the model on an RGB pose estimation dataset, resulting in a further increment in accuracy of 4 %. Semi-supervised learning techniques, with a novel pose discriminator model in the loop, were adopted to utilize the unannotated training data, resulting in a further 3 % increase in accuracy. Thus, significant improvement has been shown in the case of 2D pose estimation from infrared images, with a comparatively small amount of annotated data and a large amount of unannotated data by using the proposed training pipeline powered by heavy augmentation.

PMID:39263111 | PMC:PMC11388740 | DOI:10.1016/j.heliyon.2024.e36823

Heliyon. 2024 Aug 23;10(17):e36652. doi: 10.1016/j.heliyon.2024.e36652. eCollection 2024 Sep 15.

ABSTRACT

The rapid dissemination of misinformation on the internet complicates the decision-making process for individuals seeking reliable information, particularly parents researching child development topics. This misinformation can lead to adverse consequences, such as inappropriate treatment of children based on myths. While previous research has utilized text-mining techniques to predict child abuse cases, there has been a gap in the analysis of child development myths and facts. This study addresses this gap by applying text mining techniques and classification models to distinguish between myths and facts about child development, leveraging newly gathered data from publicly available websites. The research methodology involved several stages. First, text mining techniques were employed to pre-process the data, ensuring enhanced accuracy. Subsequently, the structured data was analysed using six robust Machine Learning (ML) classifiers and one Deep Learning (DL) model, with two feature extraction techniques applied to assess their performance across three different training-testing splits. To ensure the reliability of the results, cross-validation was performed using both k-fold and leave-one-out methods. Among the classification models tested, Logistic Regression (LR) demonstrated the highest accuracy, achieving a 90 % accuracy with the Bag-of-Words (BoW) feature extraction technique. LR stands out for its exceptional speed and efficiency, maintaining low testing time per statement (0.97 μs). These findings suggest that LR, when combined with BoW, is effective in accurately classifying child development information, thus providing a valuable tool for combating misinformation and assisting parents in making informed decisions.

PMID:39263104 | PMC:PMC11388728 | DOI:10.1016/j.heliyon.2024.e36652

Transl Lung Cancer Res. 2024 Aug 31;13(8):1816-1827. doi: 10.21037/tlcr-24-258. Epub 2024 Aug 26.

ABSTRACT

BACKGROUND: Early-stage invasive lung adenocarcinoma (ADC) characterized by a predominant micropapillary or solid pattern exhibit an elevated risk of recurrence following sub-lobar resection, thus determining histological subtype of early-stage invasive ADC prior surgery is important for formulating lobectomy or sub-lobar resection. This study aims to develop a deep learning algorithm and assess its clinical capability in distinguishing high-risk or low-risk histologic patterns in early-stage invasive ADC based on preoperative computed tomography (CT) scans.

METHODS: Two retrospective cohorts were included: development cohort 1 and external test cohort 2, comprising patients diagnosed with T1 stage invasive ADC. Electronic medical records and CT scans of all patients were documented. Patients were stratified into two risk groups. High-risk group: comprising cases with a micropapillary component ≥5% or a predominant solid pattern. Low-risk group: encompassing cases with a micropapillary component <5% and an absence of a predominant solid pattern. The overall segmentation model was modified based on Mask Region-based Convolutional Neural Network (Mask-RCNN), and Residual Network 50 (ResNet50)_3D was employed for image classification.

RESULTS: A total of 432 patients participated in this study, with 385 cases in cohort 1 and 47 cases in cohort 2. The fine-outline results produced by the auto-segmentation model exhibited a high level of agreement with manual segmentation by human experts, yielding a mean dice coefficient of 0.86 [95% confidence interval (CI): 0.85-0.87] in cohort 1 and 0.84 (95% CI: 0.82-0.85) in cohort 2. Furthermore, the deep learning model effectively differentiated the high-risk group from the low-risk group, achieving an area under the curve (AUC) of 0.89 (95% CI: 0.88-0.90) in cohort 1. In the external validation conducted in cohort 2, the deep learning model displayed an AUC of 0.87 (95% CI: 0.84-0.88) in distinguishing the high-risk group from the low-risk group. The average diagnostic time was 16.00±3.2 seconds, with an accuracy of 0.82 (95% CI: 0.81-0.83).

CONCLUSIONS: We have developed a deep learning algorithm, LungPath, for the automated segmentation of pulmonary nodules and prediction of high-risk histological patterns in early-stage lung ADC based on CT scans.

PMID:39263012 | PMC:PMC11384487 | DOI:10.21037/tlcr-24-258

Eur J Med Res. 2024 Sep 11;29(1):455. doi: 10.1186/s40001-024-02044-7.

ABSTRACT

BACKGROUND: The incidence and mortality rates of cardiovascular disease worldwide are a major concern in the healthcare industry. Precise prediction of cardiovascular disease is essential, and the use of machine learning and deep learning can aid in decision-making and enhance predictive abilities.

OBJECTIVE: The goal of this paper is to introduce a model for precise cardiovascular disease prediction by combining machine learning and deep learning.

METHOD: Two public heart disease classification datasets with 70,000 and 1190 records besides a locally collected dataset with 600 records were used in our experiments. Then, a model which makes use of both machine learning and deep learning was proposed in this paper. The proposed model employed CNN and LSTM, as the representatives of deep learning models, besides KNN and XGB, as the representatives of machine learning models. As each classifier defined the output classes, majority voting was then used as an ensemble learner to predict the final output class.

RESULT: The proposed model obtained the highest classification performance based on all evaluation metrics on all datasets, demonstrating its suitability and reliability in forecasting the probability of cardiovascular disease.

PMID:39261891 | DOI:10.1186/s40001-024-02044-7

BMC Med Imaging. 2024 Sep 11;24(1):238. doi: 10.1186/s12880-024-01417-y.

ABSTRACT

This systematic review aimed to evaluate the potential of deep learning algorithms for converting low-dose Positron Emission Tomography (PET) images to full-dose PET images in different body regions. A total of 55 articles published between 2017 and 2023 by searching PubMed, Web of Science, Scopus and IEEE databases were included in this review, which utilized various deep learning models, such as generative adversarial networks and UNET, to synthesize high-quality PET images. The studies involved different datasets, image preprocessing techniques, input data types, and loss functions. The evaluation of the generated PET images was conducted using both quantitative and qualitative methods, including physician evaluations and various denoising techniques. The findings of this review suggest that deep learning algorithms have promising potential in generating high-quality PET images from low-dose PET images, which can be useful in clinical practice.

PMID:39261796 | DOI:10.1186/s12880-024-01417-y

BMC Oral Health. 2024 Sep 11;24(1):1064. doi: 10.1186/s12903-024-04779-5.

ABSTRACT

OBJECTIVE: This study aimed to develop a deep learning model to predict skeletal malocclusions with an acceptable level of accuracy using airway and cephalometric landmark values obtained from analyzing different CBCT images.

BACKGROUND: In orthodontics, multitudinous studies have reported the correlation between orthodontic treatment and changes in the anatomy as well as the functioning of the airway. Typically, the values obtained from various measurements of cephalometric landmarks are used to determine skeletal class based on the interpretation an orthodontist experiences, which sometimes may not be accurate.

METHODS: Samples of skeletal anatomical data were retrospectively obtained and recorded in Digital Imaging and Communications in Medicine (DICOM) file format. The DICOM files were used to reconstruct 3D models using 3DSlicer (slicer.org) by thresholding airway regions to build up 3D polygon models of airway regions for each sample. The 3D models were measured for different landmarks that included measurements across the nasopharynx, the oropharynx, and the hypopharynx. Male and female subjects were combined as one data set to develop supervised learning models. These measurements were utilized to build 7 artificial intelligence-based supervised learning models.

RESULTS: The supervised learning model with the best accuracy was Random Forest, with a value of 0.74. All the other models were lower in terms of their accuracy. The recall scores for Class I, II, and III malocclusions were 0.71, 0.69, and 0.77, respectively, which represented the total number of actual positive cases predicted correctly, making the sensitivity of the model high.

CONCLUSION: In this study, it is observed that the Random Forest model was the most accurate model for predicting the skeletal malocclusion based on various airway and cephalometric landmarks.

PMID:39261793 | DOI:10.1186/s12903-024-04779-5

Nature. 2024 Sep 11. doi: 10.1038/s41586-024-07939-3. Online ahead of print.

ABSTRACT

We can now measure the connectivity of every neuron in a neural circuit1-9, but we cannot measure other biological details, including the dynamical characteristics of each neuron. The degree to which measurements of connectivity alone can inform the understanding of neural computation is an open question10. Here we show that with experimental measurements of only the connectivity of a biological neural network, we can predict the neural activity underlying a specified neural computation. We constructed a model neural network with the experimentally determined connectivity for 64 cell types in the motion pathways of the fruit fly optic lobe1-5 but with unknown parameters for the single-neuron and single-synapse properties. We then optimized the values of these unknown parameters using techniques from deep learning11, to allow the model network to detect visual motion12. Our mechanistic model makes detailed, experimentally testable predictions for each neuron in the connectome. We found that model predictions agreed with experimental measurements of neural activity across 26 studies. Our work demonstrates a strategy for generating detailed hypotheses about the mechanisms of neural circuit function from connectivity measurements. We show that this strategy is more likely to be successful when neurons are sparsely connected-a universally observed feature of biological neural networks across species and brain regions.

PMID:39261740 | DOI:10.1038/s41586-024-07939-3

Nat Methods. 2024 Sep 11. doi: 10.1038/s41592-024-02400-9. Online ahead of print.

ABSTRACT

Every collected photon is precious in live-cell super-resolution (SR) microscopy. Here, we describe a data-efficient, deep learning-based denoising solution to improve diverse SR imaging modalities. The method, SN2N, is a Self-inspired Noise2Noise module with self-supervised data generation and self-constrained learning process. SN2N is fully competitive with supervised learning methods and circumvents the need for large training set and clean ground truth, requiring only a single noisy frame for training. We show that SN2N improves photon efficiency by one-to-two orders of magnitude and is compatible with multiple imaging modalities for volumetric, multicolor, time-lapse SR microscopy. We further integrated SN2N into different SR reconstruction algorithms to effectively mitigate image artifacts. We anticipate SN2N will enable improved live-SR imaging and inspire further advances.

PMID:39261639 | DOI:10.1038/s41592-024-02400-9

Sci Rep. 2024 Sep 11;14(1):21279. doi: 10.1038/s41598-024-71640-8.

ABSTRACT

Accelerated material development for refractory ceramics triggers possibilities in context to enhanced energy efficiency for industrial processes. Here, the gathering of comprehensive material data is essential. High temperature-confocal laser scanning microscopy (HT-CLSM) displays a highly suitable in-situ method to study the underlying dissolution kinetics in the slag over time. A major drawback concerns the efficient and accurate processing of the collected image data. Here, we introduce an attention encoder-decoder convolutional neural network enabling the fully automated evaluation of the particle dissolution rate with a precision of 99.1%. The presented approach provides accurate and efficient analysis capabilities with high statistical gain and is highly resilient to image quality changes. The prediction model allows an automated diameter evaluation of the MgO particles' dissolution in the silicate slag for different temperature settings and various HT-CLSM data sets. Moreover, it is not limited to HT-CLSM image data and can be applied to various domains.

PMID:39261562 | DOI:10.1038/s41598-024-71640-8

Sci Rep. 2024 Sep 11;14(1):21278. doi: 10.1038/s41598-024-72155-y.

ABSTRACT

Pedestrian two-stage crossings are common at large, busy signalized intersections with long crosswalks and high traffic volumes. This design aims to address pedestrian operation and safety by allowing navigation in two stages, negotiating each traffic direction separately. Understanding crosswalk behavior, especially during bidirectional interactions, is essential. This paper presents a two-stage pedestrian crossing model based on Physics-Informed Neural Networks (PINNs), incorporating fluid dynamics equations to determine characteristics such as speed, density, acceleration, and Reynolds number during crossings. The study shows that PINNs outperform traditional deep learning methods in calculating and predicting pedestrian fluid properties, achieving a mean squared error as low as 10-8. The model effectively captures dynamic pedestrian flow characteristics and provides insights into pedestrian behavior impacts. The results are significant for designing pedestrian facilities to ensure comfort and optimizing signal timing to enhance mobility and safety. Additionally, these findings can aid autonomous vehicles in better understanding pedestrian intentions in intelligent transportation systems.

PMID:39261548 | DOI:10.1038/s41598-024-72155-y

Sci Rep. 2024 Sep 11;14(1):21208. doi: 10.1038/s41598-024-71284-8.

ABSTRACT

The variational autoencoder (VAE) architecture has significant advantages in predictive image generation. This study proposes a novel RFCNN-βVAE model, which combines residual-connected fully connected neural networks with VAE to handle multi-heat source arrangements. By integrating analytical solutions, polynomial fitting, and temperature field superposition, we accurately simulated the temperature rise distribution of a single heat source. We further explored the use of multiple equivalent heat sources to replace adiabatic boundary conditions. This enables the analytical method to effectively solve the two-dimensional conjugate convective heat transfer problem, providing a reliable alternative to traditional numerical solutions. Our results show that the model achieved high predictive accuracy. By adjusting the β parameter, we balanced reconstruction accuracy and latent space generalization. During the stable phase of the multi-heat source optimization iteration, 73.4% of the results outperformed the dense dataset benchmark, indicating that the model successfully optimized heat source coordinates and minimized peak temperature rise. This validates the feasibility and effectiveness of deep learning in thermal management system design. This research lays the groundwork for optimizing complex thermal environments and contributes valuable perspectives on the effective design of systems with multiple thermal sources or for applications like multi-beam lighting equalization.

PMID:39261507 | DOI:10.1038/s41598-024-71284-8

Nat Commun. 2024 Sep 11;15(1):7946. doi: 10.1038/s41467-024-52060-8.

ABSTRACT

Generative deep learning models enable data-driven de novo design of molecules with tailored features. Chemical language models (CLM) trained on string representations of molecules such as SMILES have been successfully employed to design new chemical entities with experimentally confirmed activity on intended targets. Here, we probe the application of CLM to generate multi-target ligands for designed polypharmacology. We capitalize on the ability of CLM to learn from small fine-tuning sets of molecules and successfully bias the model towards designing drug-like molecules with similarity to known ligands of target pairs of interest. Designs obtained from CLM after pooled fine-tuning are predicted active on both proteins of interest and comprise pharmacophore elements of ligands for both targets in one molecule. Synthesis and testing of twelve computationally favored CLM designs for six target pairs reveals modulation of at least one intended protein by all selected designs with up to double-digit nanomolar potency and confirms seven compounds as designed dual ligands. These results corroborate CLM for multi-target de novo design as source of innovation in drug discovery.

PMID:39261471 | DOI:10.1038/s41467-024-52060-8

J Imaging Inform Med. 2024 Sep 11. doi: 10.1007/s10278-024-01245-0. Online ahead of print.

ABSTRACT

We aimed to evaluate the ability of deep learning (DL) models to identify patients from a paired chest radiograph (CXR) and compare their performance with that of human experts. In this retrospective study, patient identification DL models were developed using 240,004 CXRs. The models were validated using multiple datasets, namely, internal validation, CheXpert, and Chest ImaGenome (CIG), which include different populations. Model performance was analyzed in terms of disease change status. The performance of the models to identify patients from paired CXRs was compared with three junior radiology residents (group I), two senior radiology residents (group II), and two board-certified expert radiologists (group III). For the reader study, 240 patients (age, 56.617 ± 13.690 years, 113 females, 160 same pairs) were evaluated. A one-sided non-inferiority test was performed with a one-sided margin of 0.05. SimChest, our similarity-based DL model, demonstrated the best patient identification performance across multiple datasets, regardless of disease change status (internal validation [area under the receiver operating characteristic curve range: 0.992-0.999], CheXpert [0.933-0.948], and CIG [0.949-0.951]). The radiologists identified patients from the paired CXRs with a mean accuracy of 0.900 (95% confidence interval: 0.852-0.948), with performance increasing with experience (mean accuracy:group I [0.874], group II [0.904], group III [0.935], and SimChest [0.904]). SimChest achieved non-inferior performance compared to the radiologists (P for non-inferiority: 0.015). The findings of this diagnostic study indicate that DL models can screen for patient misidentification using a pair of CXRs non-inferiorly to human experts.

PMID:39261374 | DOI:10.1007/s10278-024-01245-0

Comput Med Imaging Graph. 2024 Sep 5;117:102430. doi: 10.1016/j.compmedimag.2024.102430. Online ahead of print.

ABSTRACT

Spontaneous intracerebral hemorrhage (ICH) is a type of stroke less prevalent than ischemic stroke but associated with high mortality rates. Hematoma expansion (HE) is an increase in the bleeding that affects 30%-38% of hemorrhagic stroke patients. It is observed within 24 h of onset and associated with patient worsening. Clinically it is relevant to detect the patients that will develop HE from their initial computed tomography (CT) scans which could improve patient management and treatment decisions. However, this is a significant challenge due to the predictive nature of the task and its low prevalence, which hinders the availability of large datasets with the required longitudinal information. In this work, we present an end-to-end deep learning framework capable of predicting which cases will exhibit HE using only the initial basal image. We introduce a deep learning framework based on the 2D EfficientNet B0 model to predict the occurrence of HE using initial non-contrasted CT scans and their corresponding lesion annotation as priors. We used an in-house acquired dataset of 122 ICH patients, including 35 HE cases, containing longitudinal CT scans with manual lesion annotations in both basal and follow-up (obtained within 24 h after the basal scan). Experiments were conducted using a 5-fold cross-validation strategy. We addressed the limited data problem by incorporating synthetic images into the training process. To the best of our knowledge, our approach is novel in the field of HE prediction, being the first to use image synthesis to enhance results. We studied different scenarios such as training only with the original scans, using standard image augmentation techniques, and using synthetic image generation. The best performance was achieved by adding five generated versions of each image, along with standard data augmentation, during the training process. This significantly improved (p=0.0003) the performance obtained with our baseline model using directly the original CT scans from an Accuracy of 0.56 to 0.84, F1-Score of 0.53 to 0.82, Sensitivity of 0.51 to 0.77, and Specificity of 0.60 to 0.91, respectively. The proposed approach shows promising results in predicting HE, especially with the inclusion of synthetically generated images. The obtained results highlight the significance of this research direction, which has the potential to improve the clinical management of patients with hemorrhagic stroke. The code is available at: https://github.com/NIC-VICOROB/HE-prediction-SynthCT.

PMID:39260113 | DOI:10.1016/j.compmedimag.2024.102430

Med Image Anal. 2024 Sep 5;99:103342. doi: 10.1016/j.media.2024.103342. Online ahead of print.

ABSTRACT

Ovarian cancer, predominantly epithelial ovarian cancer (EOC), is a global health concern due to its high mortality rate. Despite the progress made during the last two decades in the surgery and chemotherapy of ovarian cancer, more than 70% of advanced patients are with recurrent cancer and disease. Bevacizumab is a humanized monoclonal antibody, which blocks VEGF signaling in cancer, inhibits angiogenesis and causes tumor shrinkage, and has been recently approved by the FDA as a monotherapy for advanced ovarian cancer in combination with chemotherapy. Unfortunately, Bevacizumab may also induce harmful adverse effects, such as hypertension, bleeding, arterial thromboembolism, poor wound healing and gastrointestinal perforation. Given the expensive cost and unwanted toxicities, there is an urgent need for predictive methods to identify who could benefit from bevacizumab. Of the 18 (approved) requests from 5 countries, 6 teams using 284 whole section WSIs for training to develop fully automated systems submitted their predictions on a test set of 180 tissue core images, with the corresponding ground truth labels kept private. This paper summarizes the 5 qualified methods successfully submitted to the international challenge of automated prediction of treatment effectiveness in ovarian cancer using the histopathologic images (ATEC23) held at the 26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) in 2023 and evaluates the methods in comparison with 5 state of the art deep learning approaches. This study further assesses the effectiveness of the presented prediction models as indicators for patient selection utilizing both Cox proportional hazards analysis and Kaplan-Meier survival analysis. A robust and cost-effective deep learning pipeline for digital histopathology tasks has become a necessity within the context of the medical community. This challenge highlights the limitations of current MIL methods, particularly within the context of prognosis-based classification tasks, and the importance of DCNNs like inception that has nonlinear convolutional modules at various resolutions to facilitate processing the data in multiple resolutions, which is a key feature required for pathology related prediction tasks. This further suggests the use of feature reuse at various scales to improve models for future research directions. In particular, this paper releases the labels of the testing set and provides applications for future research directions in precision oncology to predict ovarian cancer treatment effectiveness and facilitate patient selection via histopathological images.

PMID:39260034 | DOI:10.1016/j.media.2024.103342

Med Image Anal. 2024 Aug 30;99:103330. doi: 10.1016/j.media.2024.103330. Online ahead of print.

ABSTRACT

Twin-to-Twin Transfusion Syndrome (TTTS) is a rare condition that affects about 15% of monochorionic pregnancies, in which identical twins share a single placenta. Fetoscopic laser photocoagulation (FLP) is the standard treatment for TTTS, which significantly improves the survival of fetuses. The aim of FLP is to identify abnormal connections between blood vessels and to laser ablate them in order to equalize blood supply to both fetuses. However, performing fetoscopic surgery is challenging due to limited visibility, a narrow field of view, and significant variability among patients and domains. In order to enhance the visualization of placental vessels during surgery, we propose TTTSNet, a network architecture designed for real-time and accurate placental vessel segmentation. Our network architecture incorporates a novel channel attention module and multi-scale feature fusion module to precisely segment tiny placental vessels. To address the challenges posed by FLP-specific fiberscope and amniotic sac-based artifacts, we employed novel data augmentation techniques. These techniques simulate various artifacts, including laser pointer, amniotic sac particles, and structural and optical fiber artifacts. By incorporating these simulated artifacts during training, our network architecture demonstrated robust generalizability. We trained TTTSNet on a publicly available dataset of 2060 video frames from 18 independent fetoscopic procedures and evaluated it on a multi-center external dataset of 24 in-vivo procedures with a total of 2348 video frames. Our method achieved significant performance improvements compared to state-of-the-art methods, with a mean Intersection over Union of 78.26% for all placental vessels and 73.35% for a subset of tiny placental vessels. Moreover, our method achieved 172 and 152 frames per second on an A100 GPU, and Clara AGX, respectively. This potentially opens the door to real-time application during surgical procedures. The code is publicly available at https://github.com/SanoScience/TTTSNet.

PMID:39260033 | DOI:10.1016/j.media.2024.103330

J Clin Oncol. 2024 Sep 11:JCO2401271. doi: 10.1200/JCO-24-01271. Online ahead of print.

NO ABSTRACT

PMID:39259925 | DOI:10.1200/JCO-24-01271

Sci Adv. 2024 Sep 13;10(37):eadp8681. doi: 10.1126/sciadv.adp8681. Epub 2024 Sep 11.

ABSTRACT

The limitations and complexity of traditional noncontact sensors in terms of sensitivity and threshold settings pose great challenges to extend the traditional five human senses. Here, we propose tele-perception to enhance human perception and cognition beyond these conventional noncontact sensors. Our bionic multi-receptor skin employs structured doping of inorganic nanoparticles to enhance the local electric field, coupled with advanced deep learning algorithms, achieving a ΔV/Δd sensitivity of 14.2, surpassing benchmarks. This enables precise remote control of surveillance systems and robotic manipulators. Our long short-term memory-based adaptive pulse identification achieves 99.56% accuracy in material identification with accelerated processing speeds. In addition, we demonstrate the feasibility of using a two-dimensional (2D) sensor matrix to integrate real object scan data into a convolutional neural network to accurately discriminate the shape and material of 3D objects. This promises transformative advances in human-computer interaction and neuromorphic computing.

PMID:39259789 | DOI:10.1126/sciadv.adp8681

Curr Opin Ophthalmol. 2024 Aug 29. doi: 10.1097/ICU.0000000000001088. Online ahead of print.

ABSTRACT

PURPOSE OF REVIEW: The purpose of this review was to provide a summary of currently available retinal imaging and visual function testing methods for assessing inherited retinal degenerations (IRDs), with the emphasis on the application of deep learning (DL) approaches to assist the determination of structural biomarkers for IRDs.

RECENT FINDINGS: (clinical trials for IRDs; discover effective biomarkers as endpoints; DL applications in processing retinal images to detect disease-related structural changes).

SUMMARY: Assessing photoreceptor loss is a direct way to evaluate IRDs. Outer retinal layer structures, including outer nuclear layer, ellipsoid zone, photoreceptor outer segment, RPE, are potential structural biomarkers for IRDs. More work may be needed on structure and function relationship.

PMID:39259656 | DOI:10.1097/ICU.0000000000001088