Radiol Artif Intell. 2024 Jul;6(4):e240117. doi: 10.1148/ryai.240117.

NO ABSTRACT

PMID:38864744 | DOI:10.1148/ryai.240117

ACS Appl Mater Interfaces. 2024 Jun 12. doi: 10.1021/acsami.4c06122. Online ahead of print.

ABSTRACT

Enhancing the sensitivity of capacitive pressure sensors through microstructure design may compromise the reliability of the device and rely on intricate manufacturing processes. It is an effective way to solve this issue by balancing the intrinsic properties (elastic modulus and dielectric constant) of the dielectric layer materials. Here, we introduce a liquid metal (LM) hybrid elastomer prepared by a chain-extension-free polyurethane (PU) and LM. The synergistic strategies of extender-free and LM doping effectively reduce the elastic modulus (7.6 ± 0.2-2.1 ± 0.3 MPa) and enhance the dielectric constant (5.12-8.17 @1 kHz) of LM hybrid elastomers. Interestingly, the LM hybrid elastomer combines reprocessability, recyclability, and photothermal conversion. The obtained flexible pressure sensor can be used for detecting hand and throat muscle movements, and high-precision speech recognition of seven words has been using a convolutional neural network (CNN) in deep learning. This work provides an idea for designing and manufacturing wearable, recyclable, and intelligent control pressure sensors.

PMID:38864718 | DOI:10.1021/acsami.4c06122

Protein Sci. 2024 Jul;33(7):e5033. doi: 10.1002/pro.5033.

ABSTRACT

In silico validation of de novo designed proteins with deep learning (DL)-based structure prediction algorithms has become mainstream. However, formal evidence of the relationship between a high-quality predicted model and the chance of experimental success is lacking. We used experimentally characterized de novo water-soluble and transmembrane β-barrel designs to show that AlphaFold2 and ESMFold excel at different tasks. ESMFold can efficiently identify designs generated based on high-quality (designable) backbones. However, only AlphaFold2 can predict which sequences have the best chance of experimentally folding among similar designs. We show that ESMFold can generate high-quality structures from just a few predicted contacts and introduce a new approach based on incremental perturbation of the prediction ("in silico melting"), which can reveal differences in the presence of favorable contacts between designs. This study provides a new insight on DL-based structure prediction models explainability and on how they could be leveraged for the design of increasingly complex proteins; in particular membrane proteins which have historically lacked basic in silico validation tools.

PMID:38864690 | DOI:10.1002/pro.5033

Adv Sci (Weinh). 2024 Jun 12:e2307591. doi: 10.1002/advs.202307591. Online ahead of print.

ABSTRACT

Image-based cytometry faces challenges due to technical variations arising from different experimental batches and conditions, such as differences in instrument configurations or image acquisition protocols, impeding genuine biological interpretation of cell morphology. Existing solutions, often necessitating extensive pre-existing data knowledge or control samples across batches, have proved limited, especially with complex cell image data. To overcome this, "Cyto-Morphology Adversarial Distillation" (CytoMAD), a self-supervised multi-task learning strategy that distills biologically relevant cellular morphological information from batch variations, is introduced to enable integrated analysis across multiple data batches without complex data assumptions or extensive manual annotation. Unique to CytoMAD is its "morphology distillation", symbiotically paired with deep-learning image-contrast translation-offering additional interpretable insights into label-free cell morphology. The versatile efficacy of CytoMAD is demonstrated in augmenting the power of biophysical imaging cytometry. It allows integrated label-free classification of human lung cancer cell types and accurately recapitulates their progressive drug responses, even when trained without the drug concentration information. CytoMAD also allows joint analysis of tumor biophysical cellular heterogeneity, linked to epithelial-mesenchymal plasticity, that standard fluorescence markers overlook. CytoMAD can substantiate the wide adoption of biophysical cytometry for cost-effective diagnosis and screening.

PMID:38864546 | DOI:10.1002/advs.202307591

Health Informatics J. 2024 Apr-Jun;30(2):14604582241259328. doi: 10.1177/14604582241259328.

ABSTRACT

OBJECTIVES: In this article, we provide a database of nonproliferative diabetes retinopathy, which focuses on early diabetes retinopathy with hard exudation, and further explore its clinical application in disease recognition.

METHODS: We collect the photos of nonproliferative diabetes retinopathy taken by Optos Panoramic 200 laser scanning ophthalmoscope, filter out the pictures with poor quality, and label the hard exudative lesions in the images under the guidance of professional medical personnel. To validate the effectiveness of the datasets, five deep learning models are used to perform learning predictions on the datasets. Furthermore, we evaluate the performance of the model using evaluation metrics.

RESULTS: Nonproliferative diabetes retinopathy is smaller than proliferative retinopathy and more difficult to identify. The existing segmentation models have poor lesion segmentation performance, while the intersection over union (IOU) value for deep lesion segmentation of models targeting small lesions can reach 66.12%, which is higher than ordinary lesion segmentation models, but there is still a lot of room for improvement.

CONCLUSION: The segmentation of small hard exudative lesions is more challenging than that of large hard exudative lesions. More targeted datasets are needed for model training. Compared with the previous diabetes retina datasets, the NDRD dataset pays more attention to micro lesions.

PMID:38864242 | DOI:10.1177/14604582241259328

Cureus. 2024 May 12;16(5):e60145. doi: 10.7759/cureus.60145. eCollection 2024 May.

ABSTRACT

Chronic kidney disease (CKD) is a progressive condition characterized by gradual loss of kidney function, necessitating timely monitoring and interventions. This systematic review comprehensively evaluates the application of artificial intelligence (AI) and machine learning (ML) techniques for predicting CKD progression. A rigorous literature search identified 13 relevant studies employing diverse AI/ML algorithms, including logistic regression, support vector machines, random forests, neural networks, and deep learning approaches. These studies primarily aimed to predict CKD progression to end-stage renal disease (ESRD) or the need for renal replacement therapy, with some focusing on diabetic kidney disease progression, proteinuria, or estimated glomerular filtration rate (GFR) decline. The findings highlight the promising predictive performance of AI/ML models, with several achieving high accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve scores. Key factors contributing to enhanced prediction included incorporating longitudinal data, baseline characteristics, and specific biomarkers such as estimated GFR, proteinuria, serum albumin, and hemoglobin levels. Integration of these predictive models with electronic health records and clinical decision support systems offers opportunities for timely risk identification, early interventions, and personalized management strategies. While challenges related to data quality, bias, and ethical considerations exist, the reviewed studies underscore the potential of AI/ML techniques to facilitate early detection, risk stratification, and targeted interventions for CKD patients. Ongoing research, external validation, and careful implementation are crucial to leveraging these advanced analytical approaches in clinical practice, ultimately improving outcomes and reducing the burden of CKD.

PMID:38864072 | PMC:PMC11166249 | DOI:10.7759/cureus.60145

Front Neurosci. 2024 May 27;18:1351387. doi: 10.3389/fnins.2024.1351387. eCollection 2024.

ABSTRACT

INTRODUCTION: Multiple sclerosis (MS) and neuromyelitis optic spectrum disorder (NMOSD) are mimic autoimmune diseases of the central nervous system with a very high disability rate. Their clinical symptoms and imaging findings are similar, making it difficult to diagnose and differentiate. Existing research typically employs the T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) MRI imaging technique to focus on a single task in MS and NMOSD lesion segmentation or disease classification, while ignoring the collaboration between the tasks.

METHODS: To make full use of the correlation between lesion segmentation and disease classification tasks of MS and NMOSD, so as to improve the accuracy and speed of the recognition and diagnosis of MS and NMOSD, a joint model is proposed in this study. The joint model primarily comprises three components: an information-sharing subnetwork, a lesion segmentation subnetwork, and a disease classification subnetwork. Among them, the information-sharing subnetwork adopts a dualbranch structure composed of a convolution module and a Swin Transformer module to extract local and global features, respectively. These features are then input into the lesion segmentation subnetwork and disease classification subnetwork to obtain results for both tasks simultaneously. In addition, to further enhance the mutual guidance between the tasks, this study proposes two information interaction methods: a lesion guidance module and a crosstask loss function. Furthermore, the lesion location maps provide interpretability for the diagnosis process of the deep learning model.

RESULTS: The joint model achieved a Dice similarity coefficient (DSC) of 74.87% on the lesion segmentation task and accuracy (ACC) of 92.36% on the disease classification task, demonstrating its superior performance. By setting up ablation experiments, the effectiveness of information sharing and interaction between tasks is verified.

DISCUSSION: The results show that the joint model can effectively improve the performance of the two tasks.

PMID:38863883 | PMC:PMC11166028 | DOI:10.3389/fnins.2024.1351387

Front Immunol. 2024 May 28;15:1407470. doi: 10.3389/fimmu.2024.1407470. eCollection 2024.

ABSTRACT

INTRODUCTION: Somatic hypermutation (SHM) of immunoglobulin variable (V) regions by activation induced deaminase (AID) is essential for robust, long-term humoral immunity against pathogen and vaccine antigens. AID mutates cytosines preferentially within WRCH motifs (where W=A or T, R=A or G and H=A, C or T). However, it has been consistently observed that the mutability of WRCH motifs varies substantially, with large variations in mutation frequency even between multiple occurrences of the same motif within a single V region. This has led to the notion that the immediate sequence context of WRCH motifs contributes to mutability. Recent studies have highlighted the potential role of local DNA sequence features in promoting mutagenesis of AGCT, a commonly mutated WRCH motif. Intriguingly, AGCT motifs closer to 5' ends of V regions, within the framework 1 (FW1) sub-region1, mutate less frequently, suggesting an SHM-suppressing sequence context.

METHODS: Here, we systematically examined the basis of AGCT positional biases in human SHM datasets with DeepSHM, a machine-learning model designed to predict SHM patterns. This was combined with integrated gradients, an interpretability method, to interrogate the basis of DeepSHM predictions.

RESULTS: DeepSHM predicted the observed positional differences in mutation frequencies at AGCT motifs with high accuracy. For the conserved, lowly mutating AGCT motifs in FW1, integrated gradients predicted a large negative contribution of 5'C and 3'G flanking residues, suggesting that a CAGCTG context in this location was suppressive for SHM. CAGCTG is the recognition motif for E-box transcription factors, including E2A, which has been implicated in SHM. Indeed, we found a strong, inverse relationship between E-box motif fidelity and mutation frequency. Moreover, E2A was found to associate with the V region locale in two human B cell lines. Finally, analysis of human SHM datasets revealed that naturally occurring mutations in the 3'G flanking residues, which effectively ablate the E-box motif, were associated with a significantly increased rate of AGCT mutation.

DISCUSSION: Our results suggest an antagonistic relationship between mutation frequency and the binding of E-box factors like E2A at specific AGCT motif contexts and, therefore, highlight a new, suppressive mechanism regulating local SHM patterns in human V regions.

PMID:38863710 | PMC:PMC11165027 | DOI:10.3389/fimmu.2024.1407470

Front Plant Sci. 2024 May 28;15:1367738. doi: 10.3389/fpls.2024.1367738. eCollection 2024.

ABSTRACT

Currently, foliar diseases of chili have significantly impacted both yield and quality. Despite effective advancements in deep learning techniques for the classification of chili leaf diseases, most existing classification models still face challenges in terms of accuracy and practical application in disease identification. Therefore, in this study, an optimized and enhanced convolutional neural network model named MCCM (MCSAM-ConvNeXt-MSFFM) is proposed by introducing ConvNeXt. The model incorporates a Multi-Scale Feature Fusion Module (MSFFM) aimed at better capturing disease features of various sizes and positions within the images. Moreover, adjustments are made to the positioning, activation functions, and normalization operations of the MSFFM module to further optimize the overall model. Additionally, a proposed Mixed Channel Spatial Attention Mechanism (MCSAM) strengthens the correlation between non-local channels and spatial features, enhancing the model's extraction of fundamental characteristics of chili leaf diseases. During the training process, pre-trained weights are obtained from the Plant Village dataset using transfer learning to accelerate the model's convergence. Regarding model evaluation, the MCCM model is compared with existing CNN models (Vgg16, ResNet34, GoogLeNet, MobileNetV2, ShuffleNet, EfficientNetV2, ConvNeXt), and Swin-Transformer. The results demonstrate that the MCCM model achieves average improvements of 3.38%, 2.62%, 2.48%, and 2.53% in accuracy, precision, recall, and F1 score, respectively. Particularly noteworthy is that compared to the original ConvNeXt model, the MCCM model exhibits significant enhancements across all performance metrics. Furthermore, classification experiments conducted on rice and maize disease datasets showcase the MCCM model's strong generalization performance. Finally, in terms of application, a chili leaf disease classification website is successfully developed using the Flask framework. This website accurately identifies uploaded chili leaf disease images, demonstrating the practical utility of the model.

PMID:38863551 | PMC:PMC11165206 | DOI:10.3389/fpls.2024.1367738

Bioinformatics. 2024 Jun 11:btae355. doi: 10.1093/bioinformatics/btae355. Online ahead of print.

ABSTRACT

MOTIVATION: Protein-protein interactions (PPIs) provide the skeleton for signal transduction in the cell. Current PPI measurement techniques do not provide information on their directionality which is critical for elucidating signaling pathways. To date, there are hundreds of thousands of known PPIs in public databases, yet only a small fraction of them have an assigned direction. This information gap calls for computational approaches for inferring the directionality of PPIs, aka network orientation.

RESULTS: In this work we propose a novel deep learning approach for PPI network orientation. Our method first generates a set of proximity scores between a protein interaction and sets of cause and effect proteins using a network propagation procedure. Each of these score sets is fed, one at a time, to a deep set encoder whose outputs are used as features for predicting the interaction's orientation. On a comprehensive data set of oriented protein-protein interactions taken from five different sources, we achieve an area under the precision-recall curve of 0.89-0.92, outperforming previous methods. We further demonstrate the utility of the oriented network in prioritizing cancer driver genes and disease genes.

AVAILABILITY: D'or is implemented in Python and is publicly available at https://github.com/pirakd/DeepOrienter.

PMID:38862241 | DOI:10.1093/bioinformatics/btae355

J Biomed Inform. 2024 Jun 9:104673. doi: 10.1016/j.jbi.2024.104673. Online ahead of print.

ABSTRACT

OBJECTIVE: Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. Recently, artificial intelligence (AI), especially deep learning (DL), has been increasingly employed for automating the diagnostic process of pneumothorax. To address the opaqueness often associated with DL models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement.

METHOD: We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of thee explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template's boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods (Saliency Map, Grad-CAM, and Integrated Gradients) with and without our template guidance when explaining two DL models (VGG-19 and ResNet-50) in two real-world datasets (SIIM-ACR and ChestX-Det).

RESULTS: The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. We further visualized baseline and template-guided model explanations on radiographs to showcase the performance of our approach.

CONCLUSIONS: In the context of pneumothorax diagnoses, we proposed a template-guided approach for improving model explanations. Our approach not only aligns model explanations more closely with clinical insights but also exhibits extensibility to other thoracic diseases. We anticipate that our template guidance will forge a novel approach to elucidating AI models by integrating clinical domain expertise.

PMID:38862083 | DOI:10.1016/j.jbi.2024.104673

Comput Methods Programs Biomed. 2024 May 28;254:108253. doi: 10.1016/j.cmpb.2024.108253. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVES: Optical coherence tomography (OCT) has ushered in a transformative era in the domain of ophthalmology, offering non-invasive imaging with high resolution for ocular disease detection. OCT, which is frequently used in diagnosing fundamental ocular pathologies, such as glaucoma and age-related macular degeneration (AMD), plays an important role in the widespread adoption of this technology. Apart from glaucoma and AMD, we will also investigate pertinent pathologies, such as epiretinal membrane (ERM), macular hole (MH), macular dystrophy (MD), vitreomacular traction (VMT), diabetic maculopathy (DMP), cystoid macular edema (CME), central serous chorioretinopathy (CSC), diabetic macular edema (DME), diabetic retinopathy (DR), drusen, glaucomatous optic neuropathy (GON), neovascular AMD (nAMD), myopia macular degeneration (MMD) and choroidal neovascularization (CNV) diseases. This comprehensive review examines the role that OCT-derived images play in detecting, characterizing, and monitoring eye diseases.

METHOD: The 2020 PRISMA guideline was used to structure a systematic review of research on various eye conditions using machine learning (ML) or deep learning (DL) techniques. A thorough search across IEEE, PubMed, Web of Science, and Scopus databases yielded 1787 publications, of which 1136 remained after removing duplicates. Subsequent exclusion of conference papers, review papers, and non-open-access articles reduced the selection to 511 articles. Further scrutiny led to the exclusion of 435 more articles due to lower-quality indexing or irrelevance, resulting in 76 journal articles for the review.

RESULTS: During our investigation, we found that a major challenge for ML-based decision support is the abundance of features and the determination of their significance. In contrast, DL-based decision support is characterized by a plug-and-play nature rather than relying on a trial-and-error approach. Furthermore, we observed that pre-trained networks are practical and especially useful when working on complex images such as OCT. Consequently, pre-trained deep networks were frequently utilized for classification tasks. Currently, medical decision support aims to reduce the workload of ophthalmologists and retina specialists during routine tasks. In the future, it might be possible to create continuous learning systems that can predict ocular pathologies by identifying subtle changes in OCT images.

PMID:38861878 | DOI:10.1016/j.cmpb.2024.108253

Spectrochim Acta A Mol Biomol Spectrosc. 2024 Jun 4;320:124592. doi: 10.1016/j.saa.2024.124592. Online ahead of print.

ABSTRACT

Systemic lupus erythematosus (SLE) is an autoimmune disease with multiple symptoms, and its rapid screening is the research focus of surface-enhanced Raman scattering (SERS) technology. In this study, gold@silver-porous silicon (Au@Ag-PSi) composite substrates were synthesized by electrochemical etching and in-situ reduction methods, which showed excellent sensitivity and accuracy in the detection of rhodamine 6G (R6G) and serum from SLE patients. SERS technology was combined with deep learning algorithms to model serum features using selected CNN, AlexNet, and RF models. 92 % accuracy was achieved in classifying SLE patients by CNN models, and the reliability of these models in accurately identifying sera was verified by ROC curve analysis. This study highlights the great potential of Au@Ag-PSi substrate in SERS detection and introduces a novel deep learning approach for SERS for accurate screening of SLE. The proposed method and composite substrate provide significant value for rapid, accurate, and noninvasive SLE screening and provide insights into SERS-based diagnostic techniques.

PMID:38861826 | DOI:10.1016/j.saa.2024.124592

Genome Biol. 2024 Jun 11;25(1):152. doi: 10.1186/s13059-024-03291-x.

ABSTRACT

Protein folding has become a tractable problem with the significant advances in deep learning-driven protein structure prediction. Here we propose FoldPAthreader, a protein folding pathway prediction method that uses a novel folding force field model by exploring the intrinsic relationship between protein evolution and folding from the known protein universe. Further, the folding force field is used to guide Monte Carlo conformational sampling, driving the protein chain fold into its native state by exploring potential intermediates. On 30 example targets, FoldPAthreader successfully predicts 70% of the proteins whose folding pathway is consistent with biological experimental data.

PMID:38862984 | DOI:10.1186/s13059-024-03291-x

J Imaging Inform Med. 2024 Jun 11. doi: 10.1007/s10278-024-01144-4. Online ahead of print.

ABSTRACT

Distal radius fracture (DRF) is one of the most common types of wrist fractures. We aimed to construct a model for the automatic segmentation of wrist radiographs using a deep learning approach and further perform automatic identification and classification of DRF. A total of 2240 participants with anteroposterior wrist radiographs from one hospital between January 2015 and October 2021 were included. The outcomes were automatic segmentation of wrist radiographs, identification of DRF, and classification of DRF (type A, type B, type C). The Unet model and Fast-RCNN model were used for automatic segmentation. The DenseNet121 model and ResNet50 model were applied to DRF identification of DRF. The DenseNet121 model, ResNet50 model, VGG-19 model, and InceptionV3 model were used for DRF classification. The area under the curve (AUC) with 95% confidence interval (CI), accuracy, precision, and F1-score was utilized to assess the effectiveness of the identification and classification models. Of these 2240 participants, 1440 (64.3%) had DRF, of which 701 (48.7%) were type A, 278 (19.3%) were type B, and 461 (32.0%) were type C. Both the Unet model and the Fast-RCNN model showed good segmentation of wrist radiographs. For DRF identification, the AUCs of the DenseNet121 model and the ResNet50 model in the testing set were 0.941 (95%CI: 0.926-0.965) and 0.936 (95%CI: 0.913-0.955), respectively. The AUCs of the DenseNet121 model (testing set) for classification type A, type B, and type C were 0.96, 0.96, and 0.96, respectively. The DenseNet121 model may provide clinicians with a tool for interpreting wrist radiographs.

PMID:38862852 | DOI:10.1007/s10278-024-01144-4

Oral Radiol. 2024 Jun 11. doi: 10.1007/s11282-024-00759-1. Online ahead of print.

ABSTRACT

BACKGROUND: Previous deep learning-based studies were mainly conducted on detecting periapical lesions; limited information in classification, such as the periapical index (PAI) scoring system, is available. The study aimed to apply two deep learning models, Faster R-CNN and YOLOv4, in detecting and classifying periapical lesions using the PAI score from periapical radiographs (PR) in three different regions of the dental arch: anterior teeth, premolars, and molars.

METHODS: Out of 2658 PR selected for the study, 2122 PR were used for training, 268 PR were used for validation and 268 PR were used for testing. The diagnosis made by experienced dentists was used as the reference diagnosis.

RESULTS: The Faster R-CNN and YOLOv4 models obtained great sensitivity, specificity, accuracy, and precision for detecting periapical lesions. No clear difference in the performance of both models among these three regions was found. The true prediction of Faster R-CNN was 89%, 83.01% and 91.84% for PAI 3, PAI 4 and PAI 5 lesions, respectively. The corresponding values of YOLOv4 were 68.06%, 50.94%, and 65.31%.

CONCLUSIONS: Our study demonstrated the potential of YOLOv4 and Faster R-CNN models for detecting and classifying periapical lesions based on the PAI scoring system using periapical radiographs.

PMID:38862834 | DOI:10.1007/s11282-024-00759-1

Commun Chem. 2024 Jun 11;7(1):133. doi: 10.1038/s42004-024-01217-z.

ABSTRACT

Molecular representation is critical in chemical machine learning. It governs the complexity of model development and the fulfillment of training data to avoid either over- or under-fitting. As electronic structures and associated attributes are the root cause for molecular interactions and their manifested properties, we have sought to examine the local electron information on a molecular manifold to understand and predict molecular interactions. Our efforts led to the development of a lower-dimensional representation of a molecular manifold, Manifold Embedding of Molecular Surface (MEMS), to embody surface electronic quantities. By treating a molecular surface as a manifold and computing its embeddings, the embedded electronic attributes retain the chemical intuition of molecular interactions. MEMS can be further featurized as input for chemical learning. Our solubility prediction with MEMS demonstrated the feasibility of both shallow and deep learning by neural networks, suggesting that MEMS is expressive and robust against dimensionality reduction.

PMID:38862828 | DOI:10.1038/s42004-024-01217-z

Surg Endosc. 2024 Jun 11. doi: 10.1007/s00464-024-10980-y. Online ahead of print.

ABSTRACT

BACKGROUND: Deep learning models (DLMs) using preoperative computed tomography (CT) imaging have shown promise in predicting outcomes following abdominal wall reconstruction (AWR), including component separation, wound complications, and pulmonary failure. This study aimed to apply these methods in predicting hernia recurrence and to evaluate if incorporating additional clinical data would improve the DLM's predictive ability.

METHODS: Patients were identified from a prospectively maintained single-institution database. Those who underwent AWR with available preoperative CTs were included, and those with < 18 months of follow up were excluded. Patients were separated into a training (80%) set and a testing (20%) set. A DLM was trained on the images only, and another DLM was trained on demographics only: age, sex, BMI, diabetes, and history of tobacco use. A mixed-value DLM incorporated data from both. The DLMs were evaluated by the area under the curve (AUC) in predicting recurrence.

RESULTS: The models evaluated data from 190 AWR patients with a 14.7% recurrence rate after an average follow up of more than 7 years (mean ± SD: 86 ± 39 months; median [Q1, Q3]: 85.4 [56.1, 113.1]). Patients had a mean age of 57.5 ± 12.3 years and were majority (65.8%) female with a BMI of 34.2 ± 7.9 kg/m2. There were 28.9% with diabetes and 16.8% with a history of tobacco use. The AUCs for the imaging DLM, clinical DLM, and combined DLM were 0.500, 0.667, and 0.604, respectively.

CONCLUSIONS: The clinical-only DLM outperformed both the image-only DLM and the mixed-value DLM in predicting recurrence. While all three models were poorly predictive of recurrence, the clinical-only DLM was the most predictive. These findings may indicate that imaging characteristics are not as useful for predicting recurrence as they have been for other AWR outcomes. Further research should focus on understanding the imaging characteristics that are identified by these DLMs and expanding the demographic information incorporated in the clinical-only DLM to further enhance the predictive ability of this model.

PMID:38862826 | DOI:10.1007/s00464-024-10980-y

Int J Legal Med. 2024 Jun 12. doi: 10.1007/s00414-024-03268-2. Online ahead of print.

ABSTRACT

In the field of forensic anthropology, researchers aim to identify anonymous human remains and determine the cause and circumstances of death from skeletonized human remains. Sex determination is a fundamental step of this procedure because it influences the estimation of other traits, such as age and stature. Pelvic bones are especially dimorphic, and are thus the most useful bones for sex identification. Sex estimation methods are usually based on morphologic traits, measurements, or landmarks on the bones. However, these methods are time-consuming and can be subject to inter- or intra-observer bias. Sex determination can be done using dry bones or CT scans. Recently, artificial neural networks (ANN) have attracted attention in forensic anthropology. Here we tested a fully automated and data-driven machine learning method for sex estimation using CT-scan reconstructions of coxal bones. We studied 580 CT scans of living individuals. Sex was predicted by two networks trained on an independent sample: a disentangled variational auto-encoder (DVAE) alone, and the same DVAE associated with another classifier (Crecon). The DVAE alone exhibited an accuracy of 97.9%, and the DVAE + Crecon showed an accuracy of 99.8%. Sensibility and precision were also high for both sexes. These results are better than those reported from previous studies. These data-driven algorithms are easy to implement, since the pre-processing step is also entirely automatic. Fully automated methods save time, as it only takes a few minutes to pre-process the images and predict sex, and does not require strong experience in forensic anthropology.

PMID:38862820 | DOI:10.1007/s00414-024-03268-2

Nat Methods. 2024 Jun 11. doi: 10.1038/s41592-024-02304-8. Online ahead of print.

ABSTRACT

Macromolecular structure determination by electron cryo-microscopy (cryo-EM) is limited by the alignment of noisy images of individual particles. Because smaller particles have weaker signals, alignment errors impose size limitations on its applicability. Here, we explore how image alignment is improved by the application of deep learning to exploit prior knowledge about biological macromolecular structures that would otherwise be difficult to express mathematically. We train a denoising convolutional neural network on pairs of half-set reconstructions from the electron microscopy data bank (EMDB) and use this denoiser as an alternative to a commonly used smoothness prior. We demonstrate that this approach, which we call Blush regularization, yields better reconstructions than do existing algorithms, in particular for data with low signal-to-noise ratios. The reconstruction of a protein-nucleic acid complex with a molecular weight of 40 kDa, which was previously intractable, illustrates that denoising neural networks will expand the applicability of cryo-EM structure determination for a wide range of biological macromolecules.

PMID:38862790 | DOI:10.1038/s41592-024-02304-8