Odontology. 2024 Jul 17. doi: 10.1007/s10266-024-00980-8. Online ahead of print.

ABSTRACT

The aim of this study was to develop an optimal, simple, and lightweight deep learning convolutional neural network (CNN) model to detect the presence of mesiodens on panoramic radiographs. A total of 628 panoramic radiographs with and without mesiodens were used as training, validation, and test data. The training, validation, and test dataset were consisted of 218, 51, and 40 images with mesiodens and 203, 55, and 61 without mesiodens, respectively. Unclear panoramic radiographs for which the diagnosis could not be accurately determined and other modalities were required for the final diagnosis were retrospectively identified and employed as the training dataset. Four CNN models provided within software supporting the creation of neural network models for deep learning were modified and developed. The diagnostic performance of the CNNs was evaluated according to accuracy, precision, recall and F1 scores, receiver operating characteristics (ROC) curves, and area under the ROC curve (AUC). In addition, we used SHapley Additive exPlanations (SHAP) to attempt to visualize the image features that were important in the classifications of the model that exhibited the best diagnostic performance. A binary_connect_mnist_LeNet model exhibited the best performance of the four deep learning models. Our results suggest that a simple lightweight model is able to detect mesiodens. It is worth referring to AI-based diagnosis before an additional radiological examination when diagnosis of mesiodens cannot be made on unclear images. However, further revaluation by the specialist would be also necessary for careful consideration because children are more radiosensitive than adults.

PMID:39017730 | DOI:10.1007/s10266-024-00980-8

Anal Bioanal Chem. 2024 Jul 17. doi: 10.1007/s00216-024-05445-z. Online ahead of print.

ABSTRACT

As a lung cancer biomarker, exosomes were utilized for in vitro diagnosis to overcome the lack of sensitivity of conventional imaging and the potential harm caused by tissue biopsy. However, given the inherent heterogeneity of exosomes, the challenge of accurately and reliably recognizing subtle differences in the composition of exosomes from clinical samples remains significant. Herein, we report an artificial intelligence-assisted surface-enhanced Raman spectroscopy (SERS) strategy for label-free profiling of plasma exosomes for accurate diagnosis of early-stage lung cancer. Specifically, we build a deep learning model using exosome spectral data from lung cancer cell lines and normal cell lines. Then, we extracted the features of cellular exosomes by training a convolutional neural network (CNN) model on the spectral data of cellular exosomes and used them as inputs to a support vector machine (SVM) model. Eventually, the spectral features of plasma exosomes were combined to effectively distinguish adenocarcinoma in situ (AIS) from healthy controls (HC). Notably, the approach demonstrated significant performance in distinguishing AIS from HC samples, with an area under the curve (AUC) of 0.84, sensitivity of 83.3%, and specificity of 83.3%. Together, the results demonstrate the utility of exosomes as a biomarker for the early diagnosis of lung cancer and provide a new approach to prescreening techniques for lung cancer.

PMID:39017700 | DOI:10.1007/s00216-024-05445-z

Pediatr Radiol. 2024 Jul 17. doi: 10.1007/s00247-024-05978-6. Online ahead of print.

ABSTRACT

BACKGROUND: Ventricular volumetry using a short-axis stack of two-dimensional (D) cine balanced steady-state free precession (bSSFP) sequences is crucial in any cardiac magnetic resonance imaging (MRI) examination. This task becomes particularly challenging in children due to multiple breath-holds.

OBJECTIVE: To assess the diagnostic performance of accelerated 3-RR cine MRI sequences using deep learning reconstruction compared with standard 2-D cine bSSFP sequences.

MATERIAL AND METHODS: Twenty-nine consecutive patients (mean age 11 ± 5, median 12, range 1-17 years) undergoing cardiac MRI were scanned with a conventional segmented 2-D cine and a deep learning accelerated cine (three heartbeats) acquisition on a 1.5-tesla scanner. Short-axis volumetrics were performed (semi-)automatically in both datasets retrospectively by two experienced readers who visually assessed image quality employing a 4-point grading scale. Scan times and image quality were compared using the Wilcoxon rank-sum test. Volumetrics were assessed with linear regression and Bland-Altman analyses, and measurement agreement with intraclass correlation coefficient (ICC).

RESULTS: Mean acquisition time was significantly reduced with the 3-RR deep learning cine compared to the standard cine sequence (45.5 ± 13.8 s vs. 218.3 ± 44.8 s; P < 0.001). No significant differences in biventricular volumetrics were found. Left ventricular (LV) mass was increased in the deep learning cine compared with the standard cine sequence (71.4 ± 33.1 g vs. 69.9 ± 32.5 g; P < 0.05). All volumetric measurements had an excellent agreement with ICC > 0.9 except for ejection fraction (EF) (LVEF 0.81, RVEF 0.73). The image quality of deep learning cine images was decreased for end-diastolic and end-systolic contours, papillary muscles, and valve depiction (2.9 ± 0.5 vs. 3.5 ± 0.4; P < 0.05).

CONCLUSION: Deep learning cine volumetrics did not differ significantly from standard cine results except for LV mass, which was slightly overestimated with deep learning cine. Deep learning cine sequences result in a significant reduction in scan time with only slightly lower image quality.

PMID:39017676 | DOI:10.1007/s00247-024-05978-6

Radiol Artif Intell. 2024 Jul 17:e230502. doi: 10.1148/ryai.230502. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop and evaluate a publicly available deep learning model for segmenting and classifying cardiac implantable electronic devices (CIEDs) on Digital Imaging and Communications in Medicine (DICOM) and smartphone-based chest radiograph (CXR) images. Materials and Methods This institutional review board-approved retrospective study included patients with implantable pacemakers, cardioverter defibrillators, cardiac resynchronization therapy devices, and cardiac monitors who underwent chest radiography between January 2012 and January 2022. A U-Net model with a ResNet-50 backbone was created to classify CIEDs on DICOM and smartphone images. Using 2,321 CXRs from 897 patients (median age, 76 years (range 18-96 years); 625 male, 272 female), CIEDs were categorized into four manufacturers, 27 models, and one 'other' category. Five smartphones were used to acquire 11,072 images. Performance was reported using the Dice coefficient on the validation set for segmentation or balanced accuracy on the test set for manufacturer and model classification, respectively. Results The segmentation tool achieved a mean Dice coefficient of 0.936 (IQR: 0.890-0.958). The model had an accuracy of 94.36% (95% CI: 90.93%-96.84%; n = 251/266) for CIED manufacturer classification and 84.21% (95% CI: 79.31%-88.30%; n = 224/266) for CIED model classification. Conclusion The proposed deep learning model, trained on both traditional DICOM and smartphone images, showed high accuracy for segmentation and classification of CIEDs on CXRs. ©RSNA, 2024.

PMID:39017033 | DOI:10.1148/ryai.230502

Front Comput Neurosci. 2024 Jul 2;18:1397819. doi: 10.3389/fncom.2024.1397819. eCollection 2024.

ABSTRACT

Many studies have shown that the human visual system has two major functionally distinct cortical visual pathways: a ventral pathway, thought to be important for object recognition, and a dorsal pathway, thought to be important for spatial cognition. According to our and others previous studies, artificial neural networks with two segregated pathways can determine objects' identities and locations more accurately and efficiently than one-pathway artificial neural networks. In addition, we showed that these two segregated artificial cortical visual pathways can each process identity and spatial information of visual objects independently and differently. However, when using such networks to process multiple objects' identities and locations, a binding problem arises because the networks may not associate each object's identity with its location correctly. In a previous study, we constrained the binding problem by training the artificial identity pathway to retain relative location information of objects. This design uses a location map to constrain the binding problem. One limitation of that study was that we only considered two attributes of our objects (identity and location) and only one possible map (location) for binding. However, typically the brain needs to process and bind many attributes of an object, and any of these attributes could be used to constrain the binding problem. In our current study, using visual objects with multiple attributes (identity, luminance, orientation, and location) that need to be recognized, we tried to find the best map (among an identity map, a luminance map, an orientation map, or a location map) to constrain the binding problem. We found that in our experimental simulations, when visual attributes are independent of each other, a location map is always a better choice than the other kinds of maps examined for constraining the binding problem. Our findings agree with previous neurophysiological findings that show that the organization or map in many visual cortical areas is primarily retinotopic or spatial.

PMID:39015744 | PMC:PMC11250423 | DOI:10.3389/fncom.2024.1397819

Front Toxicol. 2024 Jul 2;6:1440229. doi: 10.3389/ftox.2024.1440229. eCollection 2024.

NO ABSTRACT

PMID:39015653 | PMC:PMC11249549 | DOI:10.3389/ftox.2024.1440229

Front Oncol. 2024 Jul 2;14:1444543. doi: 10.3389/fonc.2024.1444543. eCollection 2024.

NO ABSTRACT

PMID:39015491 | PMC:PMC11250536 | DOI:10.3389/fonc.2024.1444543

J Phys Chem C Nanomater Interfaces. 2024 Jun 29;128(27):11183-11189. doi: 10.1021/acs.jpcc.4c01630. eCollection 2024 Jul 11.

ABSTRACT

High-entropy alloys (HEAs), characterized as compositionally complex solid solutions with five or more metal elements, have emerged as a novel class of catalytic materials with unique attributes. Because of the remarkable diversity of multielement sites or site ensembles stabilized by configurational entropy, human exploration of the multidimensional design space of HEAs presents a formidable challenge, necessitating an efficient, computational and data-driven strategy over traditional trial-and-error experimentation or physics-based modeling. Leveraging deep learning interatomic potentials for large-scale molecular simulations and pretrained machine learning models of surface reactivity, our approach effectively rationalizes the enhanced activity of a previously synthesized PdCuPtNiCo HEA nanoparticle system for electrochemical oxygen reduction, as corroborated by experimental observations. We contend that this framework deepens our fundamental understanding of the surface reactivity of high-entropy materials and fosters the accelerated development and synthesis of monodisperse HEA nanoparticles as a versatile material platform for catalyzing sustainable chemical and energy transformations.

PMID:39015415 | PMC:PMC11247481 | DOI:10.1021/acs.jpcc.4c01630

Front Neurosci. 2024 Jul 2;18:1387196. doi: 10.3389/fnins.2024.1387196. eCollection 2024.

ABSTRACT

Abnormal β-amyloid (Aβ) accumulation in the brain is an early indicator of Alzheimer's disease (AD) and is typically assessed through invasive procedures such as PET (positron emission tomography) or CSF (cerebrospinal fluid) assays. As new anti-Alzheimer's treatments can now successfully target amyloid pathology, there is a growing interest in predicting Aβ positivity (Aβ+) from less invasive, more widely available types of brain scans, such as T1-weighted (T1w) MRI. Here we compare multiple approaches to infer Aβ + from standard anatomical MRI: (1) classical machine learning algorithms, including logistic regression, XGBoost, and shallow artificial neural networks, (2) deep learning models based on 2D and 3D convolutional neural networks (CNNs), (3) a hybrid ANN-CNN, combining the strengths of shallow and deep neural networks, (4) transfer learning models based on CNNs, and (5) 3D Vision Transformers. All models were trained on paired MRI/PET data from 1,847 elderly participants (mean age: 75.1 yrs. ± 7.6SD; 863 females/984 males; 661 healthy controls, 889 with mild cognitive impairment (MCI), and 297 with Dementia), scanned as part of the Alzheimer's Disease Neuroimaging Initiative. We evaluated each model's balanced accuracy and F1 scores. While further tests on more diverse data are warranted, deep learning models trained on standard MRI showed promise for estimating Aβ + status, at least in people with MCI. This may offer a potential screening option before resorting to more invasive procedures.

PMID:39015378 | PMC:PMC11250587 | DOI:10.3389/fnins.2024.1387196

Front Artif Intell. 2024 Jul 2;7:1408845. doi: 10.3389/frai.2024.1408845. eCollection 2024.

ABSTRACT

Sentiment analysis also referred to as opinion mining, plays a significant role in automating the identification of negative, positive, or neutral sentiments expressed in textual data. The proliferation of social networks, review sites, and blogs has rendered these platforms valuable resources for mining opinions. Sentiment analysis finds applications in various domains and languages, including English and Arabic. However, Arabic presents unique challenges due to its complex morphology characterized by inflectional and derivation patterns. To effectively analyze sentiment in Arabic text, sentiment analysis techniques must account for this intricacy. This paper proposes a model designed using the transformer model and deep learning (DL) techniques. The word embedding is represented by Transformer-based Model for Arabic Language Understanding (ArabBert), and then passed to the AraBERT model. The output of AraBERT is subsequently fed into a Long Short-Term Memory (LSTM) model, followed by feedforward neural networks and an output layer. AraBERT is used to capture rich contextual information and LSTM to enhance sequence modeling and retain long-term dependencies within the text data. We compared the proposed model with machine learning (ML) algorithms and DL algorithms, as well as different vectorization techniques: term frequency-inverse document frequency (TF-IDF), ArabBert, Continuous Bag-of-Words (CBOW), and skipGrams using four Arabic benchmark datasets. Through extensive experimentation and evaluation of Arabic sentiment analysis datasets, we showcase the effectiveness of our approach. The results underscore significant improvements in sentiment analysis accuracy, highlighting the potential of leveraging transformer models for Arabic Sentiment Analysis. The outcomes of this research contribute to advancing Arabic sentiment analysis, enabling more accurate and reliable sentiment analysis in Arabic text. The findings reveal that the proposed framework exhibits exceptional performance in sentiment classification, achieving an impressive accuracy rate of over 97%.

PMID:39015364 | PMC:PMC11250580 | DOI:10.3389/frai.2024.1408845

Imaging Neurosci (Camb). 2024 Jun 25;2:1-33. doi: 10.1162/imag_a_00197. eCollection 2024 Jun 25.

ABSTRACT

Affine image registration is a cornerstone of medical-image analysis. While classical algorithms can achieve excellent accuracy, they solve a time-consuming optimization for every image pair. Deep-learning (DL) methods learn a function that maps an image pair to an output transform. Evaluating the function is fast, but capturing large transforms can be challenging, and networks tend to struggle if a test-image characteristic shifts from the training domain, such as the resolution. Most affine methods are agnostic to the anatomy the user wishes to align, meaning the registration will be inaccurate if algorithms consider all structures in the image. We address these shortcomings with SynthMorph, a fast, symmetric, diffeomorphic, and easy-to-use DL tool for joint affine-deformable registration of any brain image without preprocessing. First, we leverage a strategy that trains networks with widely varying images synthesized from label maps, yielding robust performance across acquisition specifics unseen at training. Second, we optimize the spatial overlap of select anatomical labels. This enables networks to distinguish anatomy of interest from irrelevant structures, removing the need for preprocessing that excludes content which would impinge on anatomy-specific registration. Third, we combine the affine model with a deformable hypernetwork that lets users choose the optimal deformation-field regularity for their specific data, at registration time, in a fraction of the time required by classical methods. This framework is applicable to learning anatomy-aware, acquisition-agnostic registration of any anatomy with any architecture, as long as label maps are available for training. We analyze how competing architectures learn affine transforms and compare state-of-the-art registration tools across an extremely diverse set of neuroimaging data, aiming to truly capture the behavior of methods in the real world. SynthMorph demonstrates high accuracy and is available at https://w3id.org/synthmorph, as a single complete end-to-end solution for registration of brain magnetic resonance imaging (MRI) data.

PMID:39015335 | PMC:PMC11247402 | DOI:10.1162/imag_a_00197

Front Plant Sci. 2024 Jul 2;15:1425131. doi: 10.3389/fpls.2024.1425131. eCollection 2024.

ABSTRACT

Accurate wheat ear counting is one of the key indicators for wheat phenotyping. Convolutional neural network (CNN) algorithms for counting wheat have evolved into sophisticated tools, however because of the limitations of sensory fields, CNN is unable to simulate global context information, which has an impact on counting performance. In this study, we present a hybrid attention network (CTHNet) for wheat ear counting from RGB images that combines local features and global context information. On the one hand, to extract multi-scale local features, a convolutional neural network is built using the Cross Stage Partial framework. On the other hand, to acquire better global context information, tokenized image patches from convolutional neural network feature maps are encoded as input sequences using Pyramid Pooling Transformer. Then, the feature fusion module merges the local features with the global context information to significantly enhance the feature representation. The Global Wheat Head Detection Dataset and Wheat Ear Detection Dataset are used to assess the proposed model. There were 3.40 and 5.21 average absolute errors, respectively. The performance of the proposed model was significantly better than previous studies.

PMID:39015290 | PMC:PMC11250278 | DOI:10.3389/fpls.2024.1425131

Research (Wash D C). 2024 Jul 16;7:0399. doi: 10.34133/research.0399. eCollection 2024.

ABSTRACT

With the development of artificial intelligence and breakthroughs in deep learning, large-scale foundation models (FMs), such as generative pre-trained transformer (GPT), Sora, etc., have achieved remarkable results in many fields including natural language processing and computer vision. The application of FMs in autonomous driving holds considerable promise. For example, they can contribute to enhancing scene understanding and reasoning. By pre-training on rich linguistic and visual data, FMs can understand and interpret various elements in a driving scene, and provide cognitive reasoning to give linguistic and action instructions for driving decisions and planning. Furthermore, FMs can augment data based on the understanding of driving scenarios to provide feasible scenes of those rare occurrences in the long tail distribution that are unlikely to be encountered during routine driving and data collection. The enhancement can subsequently lead to improvement in the accuracy and reliability of autonomous driving systems. Another testament to the potential of FMs' applications lies in world models, exemplified by the DREAMER series, which showcases the ability to comprehend physical laws and dynamics. Learning from massive data under the paradigm of self-supervised learning, world models can generate unseen yet plausible driving environments, facilitating the enhancement in the prediction of road users' behaviors and the off-line training of driving strategies. In this paper, we synthesize the applications and future trends of FMs in autonomous driving. By utilizing the powerful capabilities of FMs, we strive to tackle the potential issues stemming from the long-tail distribution in autonomous driving, consequently advancing overall safety in this domain.

PMID:39015204 | PMC:PMC11249913 | DOI:10.34133/research.0399

Front Neurorobot. 2024 Jul 2;18:1423738. doi: 10.3389/fnbot.2024.1423738. eCollection 2024.

ABSTRACT

INTRODUCTION: Road cracks significantly shorten the service life of roads. Manual detection methods are inefficient and costly. The YOLOv5 model has made some progress in road crack detection. However, issues arise when deployed on edge computing devices. The main problem is that edge computing devices are directly connected to sensors. This results in the collection of noisy, poor-quality data. This problem adds computational burden to the model, potentially impacting its accuracy. To address these issues, this paper proposes a novel road crack detection algorithm named EMG-YOLO.

METHODS: First, an Efficient Decoupled Header is introduced in YOLOv5 to optimize the head structure. This approach separates the classification task from the localization task. Each task can then focus on learning its most relevant features. This significantly reduces the model's computational resources and time. It also achieves faster convergence rates. Second, the IOU loss function in the model is upgraded to the MPDIOU loss function. This function works by minimizing the top-left and bottom-right point distances between the predicted bounding box and the actual labeled bounding box. The MPDIOU loss function addresses the complex computation and high computational burden of the current YOLOv5 model. Finally, the GCC3 module replaces the traditional convolution. It performs global context modeling with the input feature map to obtain global context information. This enhances the model's detection capabilities on edge computing devices.

RESULTS: Experimental results show that the improved model has better performance in all parameter indicators compared to current mainstream algorithms. The EMG-YOLO model improves the accuracy of the YOLOv5 model by 2.7%. The mAP (0.5) and mAP (0.9) are improved by 2.9% and 0.9%, respectively. The new algorithm also outperforms the YOLOv5 model in complex environments on edge computing devices.

DISCUSSION: The EMG-YOLO algorithm proposed in this paper effectively addresses the issues of poor data quality and high computational burden on edge computing devices. This is achieved through optimizing the model head structure, upgrading the loss function, and introducing global context modeling. Experimental results demonstrate significant improvements in both accuracy and efficiency, especially in complex environments. Future research can further optimize this algorithm and explore more lightweight and efficient object detection models for edge computing devices.

PMID:39015151 | PMC:PMC11250488 | DOI:10.3389/fnbot.2024.1423738

Sci Rep. 2024 Jul 16;14(1):16389. doi: 10.1038/s41598-024-64855-2.

ABSTRACT

Fluorescence polarization (Fpol) imaging of methylene blue (MB) is a promising quantitative approach to thyroid cancer detection. Clinical translation of MB Fpol technology requires reduction of the data analysis time that can be achieved via deep learning-based automated cell segmentation with a 2D U-Net convolutional neural network. The model was trained and tested using images of pathologically diverse human thyroid cells and evaluated by comparing the number of cells selected, segmented areas, and Fpol values obtained using automated (AU) and manual (MA) data processing methods. Overall, the model segmented 15.8% more cells than the human operator. Differences in AU and MA segmented cell areas varied between - 55.2 and + 31.0%, whereas differences in Fpol values varied from - 20.7 and + 10.7%. No statistically significant differences between AU and MA derived Fpol data were observed. The largest differences in Fpol values correlated with greatest discrepancies in AU versus MA segmented cell areas. Time required for auto-processing was reduced to 10 s versus one hour required for MA data processing. Implementation of the automated cell analysis makes quantitative fluorescence polarization-based diagnosis clinically feasible.

PMID:39013980 | DOI:10.1038/s41598-024-64855-2

Sci Rep. 2024 Jul 16;14(1):16401. doi: 10.1038/s41598-024-62151-7.

ABSTRACT

Lameness affects animal mobility, causing pain and discomfort. Lameness in early stages often goes undetected due to a lack of observation, precision, and reliability. Automated and non-invasive systems offer precision and detection ease and may improve animal welfare. This study was conducted to create a repository of images and videos of sows with different locomotion scores. Our goal is to develop a computer vision model for automatically identifying specific points on the sow's body. The automatic identification and ability to track specific body areas, will allow us to conduct kinematic studies with the aim of facilitating the detection of lameness using deep learning. The video database was collected on a pig farm with a scenario built to allow filming of sows in locomotion with different lameness scores. Two stereo cameras were used to record 2D videos images. Thirteen locomotion experts assessed the videos using the Locomotion Score System developed by Zinpro Corporation. From this annotated repository, computational models were trained and tested using the open-source deep learning-based animal pose tracking framework SLEAP (Social LEAP Estimates Animal Poses). The top-performing models were constructed using the LEAP architecture to accurately track 6 (lateral view) and 10 (dorsal view) skeleton keypoints. The architecture achieved average precisions values of 0.90 and 0.72, average distances of 6.83 and 11.37 in pixel, and similarities of 0.94 and 0.86 for the lateral and dorsal views, respectively. These computational models are proposed as a Precision Livestock Farming tool and method for identifying and estimating postures in pigs automatically and objectively. The 2D video image repository with different pig locomotion scores can be used as a tool for teaching and research. Based on our skeleton keypoint classification results, an automatic system could be developed. This could contribute to the objective assessment of locomotion scores in sows, improving their welfare.

PMID:39013897 | DOI:10.1038/s41598-024-62151-7

Nat Commun. 2024 Jul 17;15(1):5997. doi: 10.1038/s41467-024-50426-6.

ABSTRACT

Cancer is rarely the straightforward consequence of an abnormality in a single gene, but rather reflects a complex interplay of many genes, represented as gene modules. Here, we leverage the recent advances of model-agnostic interpretation approach and develop CGMega, an explainable and graph attention-based deep learning framework to perform cancer gene module dissection. CGMega outperforms current approaches in cancer gene prediction, and it provides a promising approach to integrate multi-omics information. We apply CGMega to breast cancer cell line and acute myeloid leukemia (AML) patients, and we uncover the high-order gene module formed by ErbB family and tumor factors NRG1, PPM1A and DLG2. We identify 396 candidate AML genes, and observe the enrichment of either known AML genes or candidate AML genes in a single gene module. We also identify patient-specific AML genes and associated gene modules. Together, these results indicate that CGMega can be used to dissect cancer gene modules, and provide high-order mechanistic insights into cancer development and heterogeneity.

PMID:39013885 | DOI:10.1038/s41467-024-50426-6

Nat Commun. 2024 Jul 16;15(1):5989. doi: 10.1038/s41467-024-50150-1.

ABSTRACT

Single-cell sequencing is a crucial tool for dissecting the cellular intricacies of complex diseases. Its prohibitive cost, however, hampers its application in expansive biomedical studies. Traditional cellular deconvolution approaches can infer cell type proportions from more affordable bulk sequencing data, yet they fall short in providing the detailed resolution required for single-cell-level analyses. To overcome this challenge, we introduce "scSemiProfiler", an innovative computational framework that marries deep generative models with active learning strategies. This method adeptly infers single-cell profiles across large cohorts by fusing bulk sequencing data with targeted single-cell sequencing from a few rigorously chosen representatives. Extensive validation across heterogeneous datasets verifies the precision of our semi-profiling approach, aligning closely with true single-cell profiling data and empowering refined cellular analyses. Originally developed for extensive disease cohorts, "scSemiProfiler" is adaptable for broad applications. It provides a scalable, cost-effective solution for single-cell profiling, facilitating in-depth cellular investigation in various biological domains.

PMID:39013867 | DOI:10.1038/s41467-024-50150-1

Semin Nucl Med. 2024 Jul 15:S0001-2998(24)00056-4. doi: 10.1053/j.semnuclmed.2024.06.003. Online ahead of print.

ABSTRACT

Radioligand therapy is an emerging and effective treatment option for various types of malignancies, but may be intricately linked to hematological side effects such as anemia, lymphopenia or thrombocytopenia. The safety and efficacy of novel theranostic agents, targeting increasingly complex targets, can be well served by comprehensive dosimetry. However, optimization in patient management and patient selection based on risk-factors predicting adverse events and built upon reliable dose-response relations is still an open demand. In this context, artificial intelligence methods, especially machine learning and deep learning algorithms, may play a crucial role. This review provides an overview of upcoming opportunities for integrating artificial intelligence methods into the field of dosimetry in nuclear medicine by improving bone marrow and blood dosimetry accuracy, enabling early identification of potential hematological risk-factors, and allowing for adaptive treatment planning. It will further exemplify inspirational success stories from neighboring disciplines that may be translated to nuclear medicine practices, and will provide conceptual suggestions for future directions. In the future, we expect artificial intelligence-assisted (predictive) dosimetry combined with clinical parameters to pave the way towards truly personalized theranostics in radioligand therapy.

PMID:39013673 | DOI:10.1053/j.semnuclmed.2024.06.003

AJNR Am J Neuroradiol. 2024 Jul 16:ajnr.A8418. doi: 10.3174/ajnr.A8418. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: To date, only a few small studies have attempted deep learning-based automatic segmentation of white matter hyperintensity (WMH) lesions in patients with cerebral infarction, which is complicated because stroke-related lesions can obscure WMH borders. We developed and validated deep learning algorithms to segment WMH lesions accurately in patients with cerebral infarction, using multisite datasets involving 8,421 patients with acute ischemic stroke.

MATERIALS AND METHODS: We included 8,421 stroke patients from 9 centers in Korea. 2D UNet and SE-Unet models were trained using 2,408 FLAIR MRI from 3 hospitals and validated using 6,013 FLAIR MRIs from 6 hospitals. WMH segmentation performance was assessed by calculating DSC, correlation coefficient, and concordance correlation coefficient compared to a human-segmented gold standard. In addition, we obtained an uncertainty index that represents overall ambiguity in the voxel classification for WMH segmentation in each patient based on the Kullback-Leibler divergence.

RESULTS: In the training dataset, the mean age was 67.4±13.0 years and 60.4% were men. The mean (95% CI) DSCs for Unet in internal testing and external validation were respectively 0.659 (0.649-0.669) and 0.710 (0.707-0.714), which were slightly lower than the reliability between humans (DSC=0.744; 95% CI=0.738-0.751; P=.031). Compared with the Unet, the SE-Unet demonstrated better performance, achieving a mean DSC of 0.675 (0.666-0.685; P<.001) in the internal testing and 0.722 (0.719-0.726; P<.001) in the external validation; moreover, it achieved high DSC values (ranging from 0.672 to 0.744) across multiple validation datasets. We observed a significant correlation between WMH volumes that were segmented automatically and manually for the Unet (r=0.917, P<.0001) and even stronger for the SE-Unet (r=0.933, P<.0001). The SE-Unet also attained a high concordance correlation coefficient (ranging from 0.841 to 0.956) in external test datasets. In addition, the uncertainty indices in the majority of patients (86%) in the external datasets were below 0.35, with an average DSC of 0.744 in these patients.

CONCLUSIONS: We developed and validated deep learning algorithms to segment WMH in patients with acute cerebral infarction using the largest-ever MRI datasets. In addition, we showed that the uncertainty index can be used to identify cases where automatic WMH segmentation is less accurate and requires human review.

ABBREVIATIONS: WMH = white matter hyperintensity; CNN = convolutional neural networks; SE = squeeze-and-excitation; KL = Kullback-Leibler; ReLU = rectified linear unit; LKW = last known well; mRS = modified Rankin Scale; NIHSS = National Institute of Health Stroke Scale; LAA = large artery atherosclerosis; SVO = small vessel occlusion; CE = cardioembolism.

PMID:39013565 | DOI:10.3174/ajnr.A8418