Opt Lett. 2024 Jun 1;49(11):2926-2929. doi: 10.1364/OL.527429.

ABSTRACT

Adaptive optics (AO) technology is an effective means to compensate for atmospheric turbulence, but the inherent delay error of an AO system will cause the compensation phase of the deformable mirror (DM) to lag behind the actual distortion, which limits the correction performance of the AO technology. Therefore, the feed-forward prediction of atmospheric turbulence has important research value and application significance to offset the inherent time delay and improve the correction bandwidth of the AO system. However, most prediction algorithms are limited to an open-loop system, and the deployment and the application in the actual AO system are rarely reported, so its correction performance improvement has not been verified in practice. We report, to our knowledge, the first successful test of a deep learning-based spatiotemporal prediction model in an actual 3 km laser atmospheric transport AO system and compare it with the traditional closed-loop control methods, demonstrating that the AO system with the prediction model has higher correction performance.

PMID:38824294 | DOI:10.1364/OL.527429

Opt Lett. 2024 Jun 1;49(11):2894-2897. doi: 10.1364/OL.523832.

ABSTRACT

Coded aperture snapshot spectral imaging (CASSI) can capture hyperspectral images (HSIs) in one shot, but it suffers from optical aberrations that degrade the reconstruction quality. Existing deep learning methods for CASSI reconstruction lose some performance on real data due to aberrations. We propose a method to restore high-resolution HSIs from a low-resolution CASSI measurement. We first generate realistic training data that mimics the optical aberrations of CASSI using a spectral imaging simulation technique. A generative network is then trained on this data to recover HSIs from a blurred and distorted CASSI measurement. Our method adapts to the optical system degradation model and thus improves the reconstruction robustness. Experiments on both simulated and real data indicate that our method significantly enhances the image quality of reconstruction outcomes and can be applied to different CASSI systems.

PMID:38824286 | DOI:10.1364/OL.523832

Opt Lett. 2024 Jun 1;49(11):2886-2889. doi: 10.1364/OL.522701.

ABSTRACT

Light field (LF) imaging has gained significant attention in the field of computational imaging due to its unique capability to capture both spatial and angular information of a scene. In recent years, super-resolution (SR) techniques based on deep learning have shown considerable advantages in enhancing LF image resolution. However, the inherent challenges of obtaining rich structural information and reconstructing complex texture details persist, particularly in scenarios where spatial and angular information are intricately interwoven. This Letter introduces a novel, to the best of our knowledge, approach for Disentangling LF Image SR Network (DLISN) by leveraging the synergy of dual learning and Fourier channel attention (FCA) mechanisms. Dual learning strategies are employed to enhance reconstruction results, addressing limitations in model generalization caused by the difficulty in acquiring paired datasets in real-world LF scenarios. The integration of FCA facilitates the extraction of high-frequency information associated with different structures, contributing to improved spatial resolution. Experimental results consistently demonstrate superior performance in enhancing the resolution of LF images.

PMID:38824284 | DOI:10.1364/OL.522701

Comput Biol Med. 2024 May 25;177:108659. doi: 10.1016/j.compbiomed.2024.108659. Online ahead of print.

ABSTRACT

Automatic abdominal organ segmentation is an essential prerequisite for accurate volumetric analysis, disease diagnosis, and tracking by medical practitioners. However, the deformable shapes, variable locations, overlapping with nearby organs, and similar contrast make the segmentation challenging. Moreover, the requirement of a large manually labeled dataset makes it harder. Hence, a semi-supervised contrastive learning approach is utilized to perform the automatic abdominal organ segmentation. Existing 3D deep learning models based on contrastive learning are not able to capture the 3D context of medical volumetric data along three planes/views: axial, sagittal, and coronal views. In this work, a semi-supervised view-adaptive unified model (VAU-model) is proposed to make the 3D deep learning model as view-adaptive to learn 3D context along each view in a unified manner. This method utilizes the novel optimization function that assists the 3D model to learn the 3D context of volumetric medical data along each view in a single model. The effectiveness of the proposed approach is validated on the three types of datasets: BTCV, NIH, and MSD quantitatively and qualitatively. The results demonstrate that the VAU model achieves an average Dice score of 81.61% which is a 3.89% improvement compared to the previous best results for pancreas segmentation in multi-organ dataset BTCV. It also achieves an average Dice score of 77.76% and 76.76% for the pancreas under the single organ non-pathological NIH dataset, and pathological MSD dataset.

PMID:38823366 | DOI:10.1016/j.compbiomed.2024.108659

Comput Biol Med. 2024 May 21;177:108625. doi: 10.1016/j.compbiomed.2024.108625. Online ahead of print.

ABSTRACT

Liver segmentation is a fundamental prerequisite for the diagnosis and surgical planning of hepatocellular carcinoma. Traditionally, the liver contour is drawn manually by radiologists using a slice-by-slice method. However, this process is time-consuming and error-prone, depending on the radiologist's experience. In this paper, we propose a new end-to-end automatic liver segmentation framework, named ResTransUNet, which exploits the transformer's ability to capture global context for remote interactions and spatial relationships, as well as the excellent performance of the original U-Net architecture. The main contribution of this paper lies in proposing a novel fusion network that combines Unet and Transformer architectures. In the encoding structure, a dual-path approach is utilized, where features are extracted separately using both convolutional neural networks (CNNs) and Transformer networks. Additionally, an effective feature enhancement unit is designed to transfer the global features extracted by the Transformer network to the CNN for feature enhancement. This model aims to address the drawbacks of traditional Unet-based methods, such as feature loss during encoding and poor capture of global features. Moreover, it avoids the disadvantages of pure Transformer models, which suffer from large parameter sizes and high computational complexity. The experimental results on the LiTS2017 dataset demonstrate remarkable performance for our proposed model, with Dice coefficients, volumetric overlap error (VOE), and relative volume difference (RVD) values for liver segmentation reaching 0.9535, 0.0804, and -0.0007, respectively. Furthermore, to further validate the model's generalization capability, we conducted tests on the 3Dircadb, Chaos, and Sliver07 datasets. The experimental results demonstrate that the proposed method outperforms other closely related models with higher liver segmentation accuracy. In addition, significant improvements can be achieved by applying our method when handling liver segmentation with small and discontinuous liver regions, as well as blurred liver boundaries. The code is available at the website: https://github.com/Jouiry/ResTransUNet.

PMID:38823365 | DOI:10.1016/j.compbiomed.2024.108625

Animal. 2024 May 3;18(6):101178. doi: 10.1016/j.animal.2024.101178. Online ahead of print.

ABSTRACT

Measuring feed intake accurately is crucial to determine feed efficiency and for genetic selection. A system using three-dimensional (3D) cameras and deep learning algorithms can measure the volume of feed intake in dairy cows, but for now, the system has not been validated for feed intake expressed as weight of feed. The aim of this study was to validate the weight of feed intake predicted from the 3D cameras with the actual measured weight. It was hypothesised that diet-specific coefficients are necessary for predicting changes in weight, that the relationship between weight and volume is curvilinear throughout the day, and that manually pushing the feed affects this relationship. Twenty-four lactating Danish Holstein cows were used in a cross-over design with four dietary treatments, 2 × 2 factorial arranged with either grass-clover silage or maize silage as silage factor, and barley or dried beet pulp as concentrate factor. Cows were adapted to the diets for 11 d, and for 3 d to tie-stall housing before camera measurements. Six cameras were used for recording, each mounted over an individual feeding platform equipped with a weight scale. When building the predictive models, four cameras were used for training, and the remaining two for testing the prediction of the models. The most accurate predictions were found for the average feed intake over a period when using the starting density of the feed pile, which resulted in the lowest errors, 6% when expressed as RMSE and 5% expressed as mean absolute error. A model including curvilinear effects of feed volume and the impact of manual feed pushing was used on a dataset including daily time points. When cross-validating, the inclusion of a curvilinear effect and a feed push effect did not improve the accuracy of the model for neither the feed pile nor the feed removed by the cow between consecutive time points. In conclusion, measuring daily feed intake from this 3D camera system in the present experimental setup could be accomplished with an acceptable error (below 8%), but the system should be improved for individual meal intake measurements if these measures were to be implemented.

PMID:38823283 | DOI:10.1016/j.animal.2024.101178

Sci Rep. 2024 Jun 1;14(1):12598. doi: 10.1038/s41598-024-63280-9.

ABSTRACT

To tackle the difficulty of extracting features from one-dimensional spectral signals using traditional spectral analysis, a metabolomics analysis method is proposed to locate two-dimensional correlated spectral feature bands and combine it with deep learning classification for wine origin traceability. Metabolomics analysis was performed on 180 wine samples from 6 different wine regions using UPLC-Q-TOF-MS. Indole, Sulfacetamide, and caffeine were selected as the main differential components. By analyzing the molecular structure of these components and referring to the main functional groups on the infrared spectrum, characteristic band regions with wavelengths in the range of 1000-1400 nm and 1500-1800 nm were selected. Draw two-dimensional correlation spectra (2D-COS) separately, generate synchronous correlation spectra and asynchronous correlation spectra, establish convolutional neural network (CNN) classification models, and achieve the purpose of wine origin traceability. The experimental results demonstrate that combining two segments of two-dimensional characteristic spectra determined by metabolomics screening with convolutional neural networks yields optimal classification results. This validates the effectiveness of using metabolomics screening to determine spectral feature regions in tracing wine origin. This approach effectively removes irrelevant variables while retaining crucial chemical information, enhancing spectral resolution. This integrated approach strengthens the classification model's understanding of samples, significantly increasing accuracy.

PMID:38824219 | DOI:10.1038/s41598-024-63280-9

Sci Rep. 2024 Jun 1;14(1):12615. doi: 10.1038/s41598-024-63108-6.

ABSTRACT

Standard clinical practice to assess fetal well-being during labour utilises monitoring of the fetal heart rate (FHR) using cardiotocography. However, visual evaluation of FHR signals can result in subjective interpretations leading to inter and intra-observer disagreement. Therefore, recent studies have proposed deep-learning-based methods to interpret FHR signals and detect fetal compromise. These methods have typically focused on evaluating fixed-length FHR segments at the conclusion of labour, leaving little time for clinicians to intervene. In this study, we propose a novel FHR evaluation method using an input length invariant deep learning model (FHR-LINet) to progressively evaluate FHR as labour progresses and achieve rapid detection of fetal compromise. Using our FHR-LINet model, we obtained approximately 25% reduction in the time taken to detect fetal compromise compared to the state-of-the-art multimodal convolutional neural network while achieving 27.5%, 45.0%, 56.5% and 65.0% mean true positive rate at 5%, 10%, 15% and 20% false positive rate respectively. A diagnostic system based on our approach could potentially enable earlier intervention for fetal compromise and improve clinical outcomes.

PMID:38824217 | DOI:10.1038/s41598-024-63108-6

Sci Rep. 2024 Jun 2;14(1):12630. doi: 10.1038/s41598-024-63319-x.

ABSTRACT

In this study, we present the development of a fine structural human phantom designed specifically for applications in dentistry. This research focused on assessing the viability of applying medical computer vision techniques to the task of segmenting individual teeth within a phantom. Using a virtual cone-beam computed tomography (CBCT) system, we generated over 170,000 training datasets. These datasets were produced by varying the elemental densities and tooth sizes within the human phantom, as well as varying the X-ray spectrum, noise intensity, and projection cutoff intensity in the virtual CBCT system. The deep-learning (DL) based tooth segmentation model was trained using the generated datasets. The results demonstrate an agreement with manual contouring when applied to clinical CBCT data. Specifically, the Dice similarity coefficient exceeded 0.87, indicating the robust performance of the developed segmentation model even when virtual imaging was used. The present results show the practical utility of virtual imaging techniques in dentistry and highlight the potential of medical computer vision for enhancing precision and efficiency in dental imaging processes.

PMID:38824210 | DOI:10.1038/s41598-024-63319-x

Sci Rep. 2024 Jun 1;14(1):12623. doi: 10.1038/s41598-024-63310-6.

ABSTRACT

Crowd flow prediction has been studied for a variety of purposes, ranging from the private sector such as location selection of stores according to the characteristics of commercial districts and customer-tailored marketing to the public sector for social infrastructure design such as transportation networks. Its importance is even greater in light of the spread of contagious diseases such as COVID-19. In many cases, crowd flow can be divided into subgroups by common characteristics such as gender, age, location type, etc. If we use such hierarchical structure of the data effectively, we can improve prediction accuracy of crowd flow for subgroups. But the existing prediction models do not consider such hierarchical structure of the data. In this study, we propose a deep learning model based on global-local structure of the crowd flow data, which utilizes the overall(global) and subdivided by the types of sites(local) crowd flow data simultaneously to predict the crowd flow of each subgroup. The experiment result shows that the proposed model improves the prediction accuracy of each sub-divided subgroup by 5.2% (Table 5 Cat #9)-45.95% (Table 11 Cat #5), depending on the data set. This result comes from the comparison with the related works under the same condition that use target category data to predict each subgroup. In addition, when we refine the global data composition by considering the correlation between subgroups and excluding low correlated subgroups, the prediction accuracy is further improved by 5.6-48.65%.

PMID:38824208 | DOI:10.1038/s41598-024-63310-6

Sci Rep. 2024 Jun 1;14(1):12606. doi: 10.1038/s41598-024-63422-z.

ABSTRACT

Most artificial intelligence (AI) studies have attempted to identify dental implant systems (DISs) while excluding low-quality and distorted dental radiographs, limiting their actual clinical use. This study aimed to evaluate the effectiveness of an AI model, trained on a large and multi-center dataset, in identifying different types of DIS in low-quality and distorted dental radiographs. Based on the fine-tuned pre-trained ResNet-50 algorithm, 156,965 panoramic and periapical radiological images were used as training and validation datasets, and 530 low-quality and distorted images of four types (including those not perpendicular to the axis of the fixture, radiation overexposure, cut off the apex of the fixture, and containing foreign bodies) were used as test datasets. Moreover, the accuracy performance of low-quality and distorted DIS classification was compared using AI and five periodontists. Based on a test dataset, the performance evaluation of the AI model achieved accuracy, precision, recall, and F1 score metrics of 95.05%, 95.91%, 92.49%, and 94.17%, respectively. However, five periodontists performed the classification of nine types of DISs based on four different types of low-quality and distorted radiographs, achieving a mean overall accuracy of 37.2 ± 29.0%. Within the limitations of this study, AI demonstrated superior accuracy in identifying DIS from low-quality or distorted radiographs, outperforming dental professionals in classification tasks. However, for actual clinical application of AI, extensive standardization research on low-quality and distorted radiographic images is essential.

PMID:38824187 | DOI:10.1038/s41598-024-63422-z

NPJ Digit Med. 2024 Jun 1;7(1):144. doi: 10.1038/s41746-024-01139-z.

ABSTRACT

Apnea and hypopnea are common sleep disorders characterized by the obstruction of the airways. Polysomnography (PSG) is a sleep study typically used to compute the Apnea-Hypopnea Index (AHI), the number of times a person has apnea or certain types of hypopnea per hour of sleep, and diagnose the severity of the sleep disorder. Early detection and treatment of apnea can significantly reduce morbidity and mortality. However, long-term PSG monitoring is unfeasible as it is costly and uncomfortable for patients. To address these issues, we propose a method, named DRIVEN, to estimate AHI at home from wearable devices and detect when apnea, hypopnea, and periods of wakefulness occur throughout the night. The method can therefore assist physicians in diagnosing the severity of apneas. Patients can wear a single sensor or a combination of sensors that can be easily measured at home: abdominal movement, thoracic movement, or pulse oximetry. For example, using only two sensors, DRIVEN correctly classifies 72.4% of all test patients into one of the four AHI classes, with 99.3% either correctly classified or placed one class away from the true one. This is a reasonable trade-off between the model's performance and the patient's comfort. We use publicly available data from three large sleep studies with a total of 14,370 recordings. DRIVEN consists of a combination of deep convolutional neural networks and a light-gradient-boost machine for classification. It can be implemented for automatic estimation of AHI in unsupervised long-term home monitoring systems, reducing costs to healthcare systems and improving patient care.

PMID:38824175 | DOI:10.1038/s41746-024-01139-z

Sci Rep. 2024 Jun 1;14(1):12611. doi: 10.1038/s41598-024-63047-2.

ABSTRACT

Wildfires are uncontrolled fires fuelled by dry conditions, high winds, and flammable materials that profoundly impact vegetation, leading to significant consequences including noteworthy changes to ecosystems. In this study, we provide a novel methodology to understand and evaluate post-fire effects on vegetation. In regions affected by wildfires, earth-observation data from various satellite sources can be vital in monitoring vegetation and assessing its impact. These effects can be understood by detecting vegetation change over the years using a novel unsupervised method termed Deep Embedded Clustering (DEC), which enables us to classify regions based on whether there has been a change in vegetation after the fire. Our model achieves an impressive accuracy of 96.17%. Appropriate vegetation indices can be used to evaluate the evolution of vegetation patterns over the years; for this study, we utilized Enhanced Vegetation Index (EVI) based trend analysis showing the greening fraction, which ranges from 0.1 to 22.4 km2 while the browning fraction ranges from 0.1 to 18.1 km2 over the years. Vegetation recovery maps can be created to assess re-vegetation in regions affected by the fire, which is performed via a deep learning-based unsupervised method, Adaptive Generative Adversarial Neural Network Model (AdaptiGAN) on post-fire data collected from various regions affected by wildfire with a training error of 0.075 proving its capability. Based on the results obtained from the study, our approach tends to have notable merits when compared to pre-existing works.

PMID:38824170 | DOI:10.1038/s41598-024-63047-2

Sci Rep. 2024 Jun 1;14(1):12601. doi: 10.1038/s41598-024-63292-5.

ABSTRACT

Data categorization is a top concern in medical data to predict and detect illnesses; thus, it is applied in modern healthcare informatics. In modern informatics, machine learning and deep learning models have enjoyed great attention for categorizing medical data and improving illness detection. However, the existing techniques, such as features with high dimensionality, computational complexity, and long-term execution duration, raise fundamental problems. This study presents a novel classification model employing metaheuristic methods to maximize efficient positives on Chronic Kidney Disease diagnosis. The medical data is initially massively pre-processed, where the data is purified with various mechanisms, including missing values resolution, data transformation, and the employment of normalization procedures. The focus of such processes is to leverage the handling of the missing values and prepare the data for deep analysis. We adopt the Binary Grey Wolf Optimization method, a reliable subset selection feature using metaheuristics. This operation is aimed at improving illness prediction accuracy. In the classification step, the model adopts the Extreme Learning Machine with hidden nodes through data optimization to predict the presence of CKD. The complete classifier evaluation employs established measures, including recall, specificity, kappa, F-score, and accuracy, in addition to the feature selection. Data related to the study show that the proposed approach records high levels of accuracy, which is better than the existing models.

PMID:38824162 | DOI:10.1038/s41598-024-63292-5

Nat Commun. 2024 Jun 1;15(1):4677. doi: 10.1038/s41467-024-49125-z.

ABSTRACT

Electron microscopy (EM) revolutionized the way to visualize cellular ultrastructure. Volume EM (vEM) has further broadened its three-dimensional nanoscale imaging capacity. However, intrinsic trade-offs between imaging speed and quality of EM restrict the attainable imaging area and volume. Isotropic imaging with vEM for large biological volumes remains unachievable. Here, we developed EMDiffuse, a suite of algorithms designed to enhance EM and vEM capabilities, leveraging the cutting-edge image generation diffusion model. EMDiffuse generates realistic predictions with high resolution ultrastructural details and exhibits robust transferability by taking only one pair of images of 3 megapixels to fine-tune in denoising and super-resolution tasks. EMDiffuse also demonstrated proficiency in the isotropic vEM reconstruction task, generating isotropic volume even in the absence of isotropic training data. We demonstrated the robustness of EMDiffuse by generating isotropic volumes from seven public datasets obtained from different vEM techniques and instruments. The generated isotropic volume enables accurate three-dimensional nanoscale ultrastructure analysis. EMDiffuse also features self-assessment functionalities on predictions' reliability. We envision EMDiffuse to pave the way for investigations of the intricate subcellular nanoscale ultrastructure within large volumes of biological systems.

PMID:38824146 | DOI:10.1038/s41467-024-49125-z

Nat Commun. 2024 Jun 1;15(1):4690. doi: 10.1038/s41467-024-49153-9.

ABSTRACT

Accurate identification of genetic alterations in tumors, such as Fibroblast Growth Factor Receptor, is crucial for treating with targeted therapies; however, molecular testing can delay patient care due to the time and tissue required. Successful development, validation, and deployment of an AI-based, biomarker-detection algorithm could reduce screening cost and accelerate patient recruitment. Here, we develop a deep-learning algorithm using >3000 H&E-stained whole slide images from patients with advanced urothelial cancers, optimized for high sensitivity to avoid ruling out trial-eligible patients. The algorithm is validated on a dataset of 350 patients, achieving an area under the curve of 0.75, specificity of 31.8% at 88.7% sensitivity, and projected 28.7% reduction in molecular testing. We successfully deploy the system in a non-interventional study comprising 89 global study clinical sites and demonstrate its potential to prioritize/deprioritize molecular testing resources and provide substantial cost savings in the drug development and clinical settings.

PMID:38824132 | DOI:10.1038/s41467-024-49153-9

Anal Chem. 2024 Jun 1. doi: 10.1021/acs.analchem.4c01211. Online ahead of print.

ABSTRACT

The emerging field of nanoscale infrared (nano-IR) offers label-free molecular contrast, yet its imaging speed is limited by point-by-point traverse acquisition of a three-dimensional (3D) data cube. Here, we develop a spatial-spectral network (SS-Net), a miniaturized deep-learning model, together with compressive sampling to accelerate the nano-IR imaging. The compressive sampling is performed in both the spatial and spectral domains to accelerate the imaging process. The SS-Net is trained to learn the mapping from small nano-IR image patches to the corresponding spectra. With this elaborated mapping strategy, the training can be finished quickly within several minutes using the subsampled data, eliminating the need for a large-labeled dataset of common deep learning methods. We also designed an efficient loss function, which incorporates the image and spectral similarity to enhance the training. We first validate the SS-Net on an open stimulated Raman-scattering dataset; the results exhibit the potential of 10-fold imaging speed improvement with state-of-the-art performance. We then demonstrate the versatility of this approach on atomic force microscopy infrared (AFM-IR) microscopy with 7-fold imaging speed improvement, even on nanoscale Fourier transform infrared (nano-FTIR) microscopy with up to 261.6 folds faster imaging speed. We further showcase the generalization of this method on AFM-force volume-based multiparametric nanoimaging. This method establishes a paradigm for rapid nano-IR imaging, opening new possibilities for cutting-edge research in materials, photonics, and beyond.

PMID:38822784 | DOI:10.1021/acs.analchem.4c01211

Otolaryngol Head Neck Surg. 2024 Jun 1. doi: 10.1002/ohn.840. Online ahead of print.

ABSTRACT

OBJECTIVE: Recognition of auditory brainstem response (ABR) waveforms may be challenging, particularly for older individuals or those with hearing loss. This study aimed to investigate deep learning frameworks to improve the automatic recognition of ABR waveforms in participants with varying ages and hearing levels.

STUDY DESIGN: The research used a descriptive study design to collect and analyze pure tone audiometry and ABR data from 100 participants.

SETTING: The research was conducted at a tertiary academic medical center, specifically at the Clinical Audiology Center of Tsinghua Chang Gung Hospital (Beijing, China).

METHODS: Data from 100 participants were collected and categorized into four groups based on age and hearing level. Features from both time-domain and frequency-domain ABR signals were extracted and combined with demographic factors, such as age, sex, pure-tone thresholds, stimulus intensity, and original signal sequences to generate feature vectors. An enhanced Wide&Deep model was utilized, incorporating the Light-multi-layer perceptron (MLP) model to train the recognition of ABR waveforms. The recognition accuracy (ACC) of each model was calculated for the overall data set and each group.

RESULTS: The ACC rates of the Light-MLP model were 97.8%, 97.2%, 93.8%, and 92.0% for Groups 1 to 4, respectively, with a weighted average ACC rate of 95.4%. For the Wide&Deep model, the ACC rates were 93.4%, 90.8%, 92.0%, and 88.3% for Groups 1 to 4, respectively, with a weighted average ACC rate of 91.0%.

CONCLUSION: Both the Light-MLP model and the Wide&Deep model demonstrated excellent ACC in automatic recognition of ABR waveforms across participants with diverse ages and hearing levels. While the Wide&Deep model's performance was slightly poorer than that of the Light-MLP model, particularly due to the limited sample size, it is anticipated that with an expanded data set, the performance of Wide&Deep model may be further improved.

PMID:38822760 | DOI:10.1002/ohn.840

Cytopathology. 2024 Jun 1. doi: 10.1111/cyt.13396. Online ahead of print.

ABSTRACT

The transformative role of artificial intelligence (AI) and multiomics could enhance the diagnostic and prognostic capabilities of liquid biopsy (LB) for lung cancer (LC). Despite advances, the transition from tissue biopsies to more sophisticated, non-invasive methods like LB has been impeded by challenges such as the heterogeneity of biomarkers and the low concentration of tumour-related analytes. The advent of multiomics - enabled by deep learning algorithms - offers a solution by allowing the simultaneous analysis of various analytes across multiple biological fluids, presenting a paradigm shift in cancer diagnostics. Through multi-marker, multi-analyte and multi-source approaches, this review showcases how AI and multiomics are identifying clinically valuable biomarker combinations that correlate with patients' health statuses. However, the path towards clinical implementation is fraught with challenges, including study reproducibility and lack of methodological standardization, thus necessitating urgent solutions to solve these common issues.

PMID:38822635 | DOI:10.1111/cyt.13396

NMR Biomed. 2024 Jun 1:e5197. doi: 10.1002/nbm.5197. Online ahead of print.

ABSTRACT

The accurate segmentation of individual muscles is essential for quantitative MRI analysis of thigh images. Deep learning methods have achieved state-of-the-art results in segmentation, but they require large numbers of labeled data to perform well. However, labeling individual thigh muscles slice by slice for numerous volumes is a laborious and time-consuming task, which limits the availability of annotated datasets. To address this challenge, self-supervised learning (SSL) emerges as a promising technique to enhance model performance by pretraining the model on unlabeled data. A recent approach, called positional contrastive learning, exploits the information given by the axial position of the slices to learn features transferable on the segmentation task. The aim of this work was to propose positional contrastive SSL for the segmentation of individual thigh muscles from MRI acquisitions in a population of elderly healthy subjects and to evaluate it on different levels of limited annotated data. An unlabeled dataset of 72 T1w MRI thigh acquisitions was available for SSL pretraining, while a labeled dataset of 52 volumes was employed for the final segmentation task, split into training and test sets. The effectiveness of SSL pretraining to fine-tune a U-Net architecture for thigh muscle segmentation was compared with that of a randomly initialized model (RND), considering an increasing number of annotated volumes (S = 1, 2, 5, 10, 20, 30, 40). Our results demonstrated that SSL yields substantial improvements in Dice similarity coefficient (DSC) when using a very limited number of labeled volumes (e.g., for S $$ S $$ = 1, DSC 0.631 versus 0.530 for SSL and RND, respectively). Moreover, enhancements are achievable even when utilizing the full number of labeled subjects, with DSC = 0.927 for SSL and 0.924 for RND. In conclusion, positional contrastive SSL was effective in obtaining more accurate thigh muscle segmentation, even with a very low number of labeled data, with a potential impact of speeding up the annotation process in clinics.

PMID:38822595 | DOI:10.1002/nbm.5197