Front Plant Sci. 2024 Aug 20;15:1396568. doi: 10.3389/fpls.2024.1396568. eCollection 2024.

ABSTRACT

Precision weed management (PWM), driven by machine vision and deep learning (DL) advancements, not only enhances agricultural product quality and optimizes crop yield but also provides a sustainable alternative to herbicide use. However, existing DL-based algorithms on weed detection are mainly developed based on supervised learning approaches, typically demanding large-scale datasets with manual-labeled annotations, which can be time-consuming and labor-intensive. As such, label-efficient learning methods, especially semi-supervised learning, have gained increased attention in the broader domain of computer vision and have demonstrated promising performance. These methods aim to utilize a small number of labeled data samples along with a great number of unlabeled samples to develop high-performing models comparable to the supervised learning counterpart trained on a large amount of labeled data samples. In this study, we assess the effectiveness of a semi-supervised learning framework for multi-class weed detection, employing two well-known object detection frameworks, namely FCOS (Fully Convolutional One-Stage Object Detection) and Faster-RCNN (Faster Region-based Convolutional Networks). Specifically, we evaluate a generalized student-teacher framework with an improved pseudo-label generation module to produce reliable pseudo-labels for the unlabeled data. To enhance generalization, an ensemble student network is employed to facilitate the training process. Experimental results show that the proposed approach is able to achieve approximately 76% and 96% detection accuracy as the supervised methods with only 10% of labeled data in CottonWeedDet3 and CottonWeedDet12, respectively. We offer access to the source code (https://github.com/JiajiaLi04/SemiWeeds), contributing a valuable resource for ongoing semi-supervised learning research in weed detection and beyond.

PMID:39228840 | PMC:PMC11369944 | DOI:10.3389/fpls.2024.1396568

Front Aging Neurosci. 2024 Aug 20;16:1425095. doi: 10.3389/fnagi.2024.1425095. eCollection 2024.

ABSTRACT

PURPOSE: Susceptibility map weighted imaging (SMWI), based on quantitative susceptibility mapping (QSM), allows accurate nigrosome-1 (N1) evaluation and has been used to develop Parkinson's disease (PD) deep learning (DL) classification algorithms. Neuromelanin-sensitive (NMS) MRI could improve automated quantitative N1 analysis by revealing neuromelanin content. This study aimed to compare classification performance of four approaches to PD diagnosis: (1) N1 quantitative "QSM-NMS" composite marker, (2) DL model for N1 morphological abnormality using SMWI ("Heuron IPD"), (3) DL model for N1 volume using SMWI ("Heuron NI"), and (4) N1 SMWI neuroradiological evaluation.

METHOD: PD patients (n = 82; aged 65 ± 9 years; 68% male) and healthy-controls (n = 107; 66 ± 7 years; 48% male) underwent 3 T midbrain MRI with T2*-SWI multi-echo-GRE (for QSM and SMWI), and NMS-MRI. AUC was used to compare diagnostic performance. We tested for correlation of each imaging measure with clinical parameters (severity, duration and levodopa dosing) by Spearman-Rho or Kendall-Tao-Beta correlation.

RESULTS: Classification performance was excellent for the QSM-NMS composite marker (AUC = 0.94), N1 SMWI abnormality (AUC = 0.92), N1 SMWI volume (AUC = 0.90), and neuroradiologist (AUC = 0.98). Reasons for misclassification were right-left asymmetry, through-plane re-slicing, pulsation artefacts, and thin N1. In the two DL models, all 18/189 (9.5%) cases misclassified by Heuron IPD were controls with normal N1 volumes. We found significant correlation of the SN QSM-NMS composite measure with levodopa dosing (rho = -0.303, p = 0.006).

CONCLUSION: Our data demonstrate excellent performance of a quantitative QSM-NMS marker and automated DL PD classification algorithms based on midbrain MRI, while suggesting potential further improvements. Clinical utility is supported but requires validation in earlier stage PD cohorts.

PMID:39228827 | PMC:PMC11369979 | DOI:10.3389/fnagi.2024.1425095

J Sports Sci Med. 2024 Sep 1;23(1):515-525. doi: 10.52082/jssm.2024.515. eCollection 2024 Sep.

ABSTRACT

OpenPose-based motion analysis (OpenPose-MA), utilizing deep learning methods, has emerged as a compelling technique for estimating human motion. It addresses the drawbacks associated with conventional three-dimensional motion analysis (3D-MA) and human visual detection-based motion analysis (Human-MA), including costly equipment, time-consuming analysis, and restricted experimental settings. This study aims to assess the precision of OpenPose-MA in comparison to Human-MA, using 3D-MA as the reference standard. The study involved a cohort of 21 young and healthy adults. OpenPose-MA employed the OpenPose algorithm, a deep learning-based open-source two-dimensional (2D) pose estimation method. Human-MA was conducted by a skilled physiotherapist. The knee valgus angle during a drop vertical jump task was computed by OpenPose-MA and Human-MA using the same frontal-plane video image, with 3D-MA serving as the reference standard. Various metrics were utilized to assess the reproducibility, accuracy and similarity of the knee valgus angle between the different methods, including the intraclass correlation coefficient (ICC) (1, 3), mean absolute error (MAE), coefficient of multiple correlation (CMC) for waveform pattern similarity, and Pearson's correlation coefficients (OpenPose-MA vs. 3D-MA, Human-MA vs. 3D-MA). Unpaired t-tests were conducted to compare MAEs and CMCs between OpenPose-MA and Human-MA. The ICCs (1,3) for OpenPose-MA, Human-MA, and 3D-MA demonstrated excellent reproducibility in the DVJ trial. No significant difference between OpenPose-MA and Human-MA was observed in terms of the MAEs (OpenPose: 2.4° [95%CI: 1.9-3.0°], Human: 3.2° [95%CI: 2.1-4.4°]) or CMCs (OpenPose: 0.83 [range: 0.99-0.53], Human: 0.87 [range: 0.24-0.98]) of knee valgus angles. The Pearson's correlation coefficients of OpenPose-MA and Human-MA relative to that of 3D-MA were 0.97 and 0.98, respectively. This study demonstrated that OpenPose-MA achieved satisfactory reproducibility, accuracy and exhibited waveform similarity comparable to 3D-MA, similar to Human-MA. Both OpenPose-MA and Human-MA showed a strong correlation with 3D-MA in terms of knee valgus angle excursion.

PMID:39228769 | PMC:PMC11366844 | DOI:10.52082/jssm.2024.515

Int J Part Ther. 2024 Aug 5;13:100624. doi: 10.1016/j.ijpt.2024.100624. eCollection 2024 Sep.

ABSTRACT

PURPOSE: Radiation-induced lymphopenia is a common immune toxicity that adversely impacts treatment outcomes. We report here our approach to translate a deep-learning (DL) model developed to predict severe lymphopenia risk among esophageal cancer into a strategy for incorporating the immune system as an organ-at-risk (iOAR) to mitigate the risk.

MATERIALS AND METHODS: We conducted "virtual clinical trials" utilizing retrospective data for 10 intensity-modulated radiation therapy (IMRT) and 10 passively-scattered proton therapy (PSPT) esophageal cancer patients. For each patient, additional treatment plans of the modality other than the original were created employing standard-of-care (SOC) dose constraints. Predicted values of absolute lymphocyte count (ALC) nadir for all plans were estimated using a previously-developed DL model. The model also yielded the relative magnitudes of contributions of iOARs dosimetric factors to ALC nadir, which were used to compute iOARs dose-volume constraints, which were incorporated into optimization criteria to produce "IMRT-enhanced" and "intensity-modulated proton therapy (IMPT)-enhanced" plans.

RESULTS: Model-predicted ALC nadir for the original IMRT (IMRT-SOC) and PSPT plans agreed well with actual values. IMPT-SOC showed greater immune sparing vs IMRT and PSPT. The average mean body doses were 13.10 Gy vs 7.62 Gy for IMRT-SOC vs IMPT-SOC for patients treated with IMRT-SOC; and 8.08 Gy vs 6.68 Gy for PSPT vs IMPT-SOC for patients treated with PSPT. For IMRT patients, the average predicted ALC nadir of IMRT-SOC, IMRT-enhanced, IMPT-SOC, and IMPT-enhanced was 281, 327, 351, and 392 cells/µL, respectively. For PSPT patients, the average predicted ALC nadir of PSPT, IMPT-SOC, and IMPT-enhanced was 258, 316, and 350 cells/µL, respectively. Enhanced plans achieved higher predicted ALC nadir, with an average improvement of 40.8 cells/µL (20.6%).

CONCLUSION: The proposed DL model-guided strategy to incorporate the immune system as iOAR in IMRT and IMPT optimization has the potential for radiation-induced lymphopenia mitigation. A prospective clinical trial is planned.

PMID:39228692 | PMC:PMC11369390 | DOI:10.1016/j.ijpt.2024.100624

Sci Rep. 2024 Sep 3;14(1):20484. doi: 10.1038/s41598-024-71530-z.

ABSTRACT

High-quality standard views in two-dimensional echocardiography are essential for accurate cardiovascular disease diagnosis and treatment decisions. However, the quality of echocardiographic images is highly dependent on the practitioner's experience. Ensuring timely quality control of echocardiographic images in the clinical setting remains a significant challenge. In this study, we aimed to propose new quality assessment criteria and develop a multi-task deep learning model for real-time multi-view classification and image quality assessment (six standard views and "others"). A total of 170,311 echocardiographic images collected between 2015 and 2022 were utilized to develop and evaluate the model. On the test set, the model achieved an overall classification accuracy of 97.8% (95%CI 97.7-98.0) and a mean absolute error of 6.54 (95%CI 6.43-6.66). A single-frame inference time of 2.8 ms was achieved, meeting real-time requirements. We also analyzed pre-stored images from three distinct groups of echocardiographers (junior, senior, and expert) to evaluate the clinical feasibility of the model. Our multi-task model can provide objective, reproducible, and clinically significant view quality assessment results for echocardiographic images, potentially optimizing the clinical image acquisition process and improving AI-assisted diagnosis accuracy.

PMID:39227373 | DOI:10.1038/s41598-024-71530-z

Best Pract Res Clin Endocrinol Metab. 2024 Aug 23:101923. doi: 10.1016/j.beem.2024.101923. Online ahead of print.

ABSTRACT

The topic of the diagnosis of phaeochromocytomas remains highly relevant because of advances in laboratory diagnostics, genetics, and therapeutic options and also the development of imaging methods. Computed tomography still represents an essential tool in clinical practice, especially in incidentally discovered adrenal masses; it allows morphological evaluation, including size, shape, necrosis, and unenhanced attenuation. More advanced post-processing tools to analyse digital images, such as texture analysis and radiomics, are currently being studied. Radiomic features utilise digital image pixels to calculate parameters and relations undetectable by the human eye. On the other hand, the amount of radiomic data requires massive computer capacity. Radiomics, together with machine learning and artificial intelligence in general, has the potential to improve not only the differential diagnosis but also the prediction of complications and therapy outcomes of phaeochromocytomas in the future. Currently, the potential of radiomics and machine learning does not match expectations and awaits its fulfilment.

PMID:39227277 | DOI:10.1016/j.beem.2024.101923

Cardiovasc Diabetol. 2024 Sep 3;23(1):328. doi: 10.1186/s12933-024-02411-y.

ABSTRACT

BACKGROUND: The aim of this study (EPIDIAB) was to assess the relationship between epicardial adipose tissue (EAT) and the micro and macrovascular complications (MVC) of type 2 diabetes (T2D).

METHODS: EPIDIAB is a post hoc analysis from the AngioSafe T2D study, which is a multicentric study aimed at determining the safety of antihyperglycemic drugs on retina and including patients with T2D screened for diabetic retinopathy (DR) (n = 7200) and deeply phenotyped for MVC. Patients included who had undergone cardiac CT for CAC (Coronary Artery Calcium) scoring after inclusion (n = 1253) were tested with a validated deep learning segmentation pipeline for EAT volume quantification.

RESULTS: Median age of the study population was 61 [54;67], with a majority of men (57%) a median duration of the disease 11 years [5;18] and a mean HbA1c of7.8 ± 1.4%. EAT was significantly associated with all traditional CV risk factors. EAT volume significantly increased with chronic kidney disease (CKD vs no CKD: 87.8 [63.5;118.6] vs 82.7 mL [58.8;110.8], p = 0.008), coronary artery disease (CAD vs no CAD: 112.2 [82.7;133.3] vs 83.8 mL [59.4;112.1], p = 0.0004, peripheral arterial disease (PAD vs no PAD: 107 [76.2;141] vs 84.6 mL[59.2; 114], p = 0.0005 and elevated CAC score (> 100 vs < 100 AU: 96.8 mL [69.1;130] vs 77.9 mL [53.8;107.7], p < 0.0001). By contrast, EAT volume was neither associated with DR, nor with peripheral neuropathy. We further evidenced a subgroup of patients with high EAT volume and a null CAC score. Interestingly, this group were more likely to be composed of young women with a high BMI, a lower duration of T2D, a lower prevalence of microvascular complications, and a higher inflammatory profile.

CONCLUSIONS: Fully-automated EAT volume quantification could provide useful information about the risk of both renal and macrovascular complications in T2D patients.

PMID:39227844 | DOI:10.1186/s12933-024-02411-y

BMC Oral Health. 2024 Sep 3;24(1):1034. doi: 10.1186/s12903-024-04786-6.

ABSTRACT

BACKGROUND: This study aims to evaluate the performance of a deep learning system for the evaluation of tooth development stages on images obtained from panoramic radiographs from child patients.

METHODS: The study collected a total of 1500 images obtained from panoramic radiographs from child patients between the ages of 5 and 14 years. YOLOv5, a convolutional neural network (CNN)-based object detection model, was used to automatically detect the calcification states of teeth. Images obtained from panoramic radiographs from child patients were trained and tested in the YOLOv5 algorithm. True-positive (TP), false-positive (FP), and false-negative (FN) ratios were calculated. A confusion matrix was used to evaluate the performance of the model.

RESULTS: Among the 146 test group images with 1022 labels, there were 828 TPs, 308 FPs, and 1 FN. The sensitivity, precision, and F1-score values of the detection model of the tooth stage development model were 0.99, 0.72, and 0.84, respectively.

CONCLUSIONS: In conclusion, utilizing a deep learning-based approach for the detection of dental development on pediatric panoramic radiographs may facilitate a precise evaluation of the chronological correlation between tooth development stages and age. This can help clinicians make treatment decisions and aid dentists in finding more accurate treatment options.

PMID:39227802 | DOI:10.1186/s12903-024-04786-6

BMC Genomics. 2024 Sep 3;25(Suppl 3):830. doi: 10.1186/s12864-024-10667-7.

ABSTRACT

BACKGROUND: Alternative splicing is a pivotal mechanism of post-transcriptional modification that contributes to the transcriptome plasticity and proteome diversity in metazoan cells. Although many splicing regulations around the exon/intron regions are known, the relationship between promoter-bound transcription factors and the downstream alternative splicing largely remains unexplored.

RESULTS: In this study, we present computational approaches to unravel the regulatory relationship between promoter-bound transcription factor binding sites (TFBSs) and the splicing patterns. We curated a fine dataset that includes DNase I hypersensitive site sequencing and transcriptomes across fifteen human tissues from ENCODE. Specifically, we proposed different representations of TF binding context and splicing patterns to examine the associations between the promoter and downstream splicing events. While machine learning models demonstrated potential in predicting splicing patterns based on TFBS occupancies, the limitations in the generalization of predicting the splicing forms of singleton genes across diverse tissues was observed with carefully examination using different cross-validation methods. We further investigated the association between alterations in individual TFBS at promoters and shifts in exon splicing efficiency. Our results demonstrate that the convolutional neural network (CNN) models, trained on TF binding changes in the promoters, can predict the changes in splicing patterns. Furthermore, a systemic in silico substitutions analysis on the CNN models highlighted several potential splicing regulators. Notably, using empirical validation using K562 CTCFL shRNA knock-down data, we showed the significant role of CTCFL in splicing regulation.

CONCLUSION: In conclusion, our finding highlights the potential role of promoter-bound TFBSs in influencing the regulation of downstream splicing patterns and provides insights for discovering alternative splicing regulations.

PMID:39227799 | DOI:10.1186/s12864-024-10667-7

Sci Rep. 2024 Sep 4;14(1):20531. doi: 10.1038/s41598-024-71496-y.

ABSTRACT

With the approval of the first two substances for the treatment of geographic atrophy (GA) secondary to age-related macular degeneration (AMD), a standardized monitoring of patients treated with complement inhibitors in clinical practice is needed. Optical coherence tomography (OCT) provides high-resolution access to the retinal pigment epithelium (RPE) and neurosensory layers, such as the ellipsoid zone (EZ), which further enhances the understanding of disease progression and therapeutic effects in GA compared to conventional fundus autofluorescence (FAF). In addition, artificial intelligence-based methodology allows the identification and quantification of GA-related pathology on OCT in an objective and standardized manner. The purpose of this study was to comprehensively evaluate automated OCT monitoring for GA compared to reading center-based manual FAF measurements in the largest successful phase 3 clinical trial data of complement inhibitor therapy to date. Automated OCT analysis of RPE loss showed a high and consistent correlation to manual GA measurements on conventional FAF. EZ loss on OCT was generally larger than areas of RPE loss, supporting the hypothesis that EZ loss exceeds underlying RPE loss as a fundamental pathophysiology in GA progression. Automated OCT analysis is well suited to monitor disease progression in GA patients treated in clinical practice and clinical trials.

PMID:39227682 | DOI:10.1038/s41598-024-71496-y

Sci Rep. 2024 Sep 3;14(1):20434. doi: 10.1038/s41598-024-71302-9.

ABSTRACT

Cancer seems to have a vast number of deaths due to its heterogeneity, aggressiveness, and significant propensity for metastasis. The predominant categories of cancer that may affect males and females and occur worldwide are colon and lung cancer. A precise and on-time analysis of this cancer can increase the survival rate and improve the appropriate treatment characteristics. An efficient and effective method for the speedy and accurate recognition of tumours in the colon and lung areas is provided as an alternative to cancer recognition methods. Earlier diagnosis of the disease on the front drastically reduces the chance of death. Machine learning (ML) and deep learning (DL) approaches can accelerate this cancer diagnosis, facilitating researcher workers to study a vast majority of patients in a limited period and at a low cost. This research presents Histopathological Imaging for the Early Detection of Lung and Colon Cancer via Ensemble DL (HIELCC-EDL) model. The HIELCC-EDL technique utilizes histopathological images to identify lung and colon cancer (LCC). To achieve this, the HIELCC-EDL technique uses the Wiener filtering (WF) method for noise elimination. In addition, the HIELCC-EDL model uses the channel attention Residual Network (CA-ResNet50) model for learning complex feature patterns. Moreover, the hyperparameter selection of the CA-ResNet50 model is performed using the tuna swarm optimization (TSO) technique. Finally, the detection of LCC is achieved by using the ensemble of three classifiers such as extreme learning machine (ELM), competitive neural networks (CNNs), and long short-term memory (LSTM). To illustrate the promising performance of the HIELCC-EDL model, a complete set of experimentations was performed on a benchmark dataset. The experimental validation of the HIELCC-EDL model portrayed a superior accuracy value of 99.60% over recent approaches.

PMID:39227664 | DOI:10.1038/s41598-024-71302-9

NPJ Digit Med. 2024 Sep 3;7(1):231. doi: 10.1038/s41746-024-01225-2.

ABSTRACT

Deep learning for computer vision can be leveraged for interpreting surgical scenes and providing surgeons with real-time guidance to avoid complications. However, neither generalizability nor scalability of computer-vision-based surgical guidance systems have been demonstrated, especially to geographic locations that lack hardware and infrastructure necessary for real-time inference. We propose a new equipment-agnostic framework for real-time use in operating suites. Using laparoscopic cholecystectomy and semantic segmentation models for predicting safe/dangerous ("Go"/"No-Go") zones of dissection as an example use case, this study aimed to develop and test the performance of a novel data pipeline linked to a web-platform that enables real-time deployment from any edge device. To test this infrastructure and demonstrate its scalability and generalizability, lightweight U-Net and SegFormer models were trained on annotated frames from a large and diverse multicenter dataset from 136 institutions, and then tested on a separate prospectively collected dataset. A web-platform was created to enable real-time inference on any surgical video stream, and performance was tested on and optimized for a range of network speeds. The U-Net and SegFormer models respectively achieved mean Dice scores of 57% and 60%, precision 45% and 53%, and recall 82% and 75% for predicting the Go zone, and mean Dice scores of 76% and 76%, precision 68% and 68%, and recall 92% and 92% for predicting the No-Go zone. After optimization of the client-server interaction over the network, we deliver a prediction stream of at least 60 fps and with a maximum round-trip delay of 70 ms for speeds above 8 Mbps. Clinical deployment of machine learning models for surgical guidance is feasible and cost-effective using a generalizable, scalable and equipment-agnostic framework that lacks dependency on hardware with high computing performance or ultra-fast internet connection speed.

PMID:39227660 | DOI:10.1038/s41746-024-01225-2

Sci Data. 2024 Sep 3;11(1):957. doi: 10.1038/s41597-024-03766-3.

ABSTRACT

Understanding and preserving the deep sea ecosystems is paramount for marine conservation efforts. Automated object (deep-sea biota) classification can enable the creation of detailed habitat maps that not only aid in biodiversity assessments but also provide essential data to evaluate ecosystem health and resilience. Having a significant source of labelled data helps prevent overfitting and enables training deep learning models with numerous parameters. In this paper, we contribute to the establishment of a significant deep-sea remotely operated vehicle (ROV) image classification dataset with 3994 images featuring deep-sea biota belonging to 33 classes. We manually label the images through rigorous quality control with human-in-the-loop image labelling. Leveraging data from ROV equipped with advanced imaging systems, our study provides results using novel deep-learning models for image classification. We use deep learning models including ResNet, DenseNet, Inception, and Inception-ResNet to benchmark the dataset that features class imbalance with many classes. Our results show that the Inception-ResNet model provides a mean classification accuracy of 65%, with AUC scores exceeding 0.8 for each class.

PMID:39227607 | DOI:10.1038/s41597-024-03766-3

J Imaging Inform Med. 2024 Sep 3. doi: 10.1007/s10278-024-01192-w. Online ahead of print.

ABSTRACT

Liver cancer, a leading cause of cancer mortality, is often diagnosed by analyzing the grayscale variations in liver tissue across different computed tomography (CT) images. However, the intensity similarity can be strong, making it difficult for radiologists to visually identify hepatocellular carcinoma (HCC) and metastases. It is crucial for the management and prevention strategies to accurately differentiate between these two liver cancers. This study proposes an automated system using a convolutional neural network (CNN) to enhance diagnostic accuracy to detect HCC, metastasis, and healthy liver tissue. This system incorporates automatic segmentation and classification. The liver lesions segmentation model is implemented using residual attention U-Net. A 9-layer CNN classifier implements the lesions classification model. Its input is the combination of the results of the segmentation model with original images. The dataset included 300 patients, with 223 used to develop the segmentation model and 77 to test it. These 77 patients also served as inputs for the classification model, consisting of 20 HCC cases, 27 with metastasis, and 30 healthy. The system achieved a mean Dice score of 87.65 % in segmentation and a mean accuracy of 93.97 % in classification, both in the test phase. The proposed method is a preliminary study with great potential in helping radiologists diagnose liver cancers.

PMID:39227538 | DOI:10.1007/s10278-024-01192-w

Acta Neuropathol. 2024 Sep 3;148(1):37. doi: 10.1007/s00401-024-02789-9.

ABSTRACT

The medial temporal lobe (MTL) is a hotspot for neuropathology, and measurements of MTL atrophy are often used as a biomarker for cognitive decline associated with neurodegenerative disease. Due to the aggregation of multiple proteinopathies in this region, the specific relationship of MTL atrophy to distinct neuropathologies is not well understood. Here, we develop two quantitative algorithms using deep learning to measure phosphorylated tau (p-tau) and TDP-43 (pTDP-43) pathology, which are both known to accumulate in the MTL and are associated with MTL neurodegeneration. We focus on these pathologies in the context of Alzheimer's disease (AD) and limbic predominant age-related TDP-43 encephalopathy (LATE) and apply our deep learning algorithms to distinct histology sections, on which MTL subregions were digitally annotated. We demonstrate that both quantitative pathology measures show high agreement with expert visual ratings of pathology and discriminate well between pathology stages. In 140 cases with antemortem MR imaging, we compare the association of semi-quantitative and quantitative postmortem measures of these pathologies in the hippocampus with in vivo structural measures of the MTL and its subregions. We find widespread associations of p-tau pathology with MTL subregional structural measures, whereas pTDP-43 pathology had more limited associations with the hippocampus and entorhinal cortex. Quantitative measurements of p-tau pathology resulted in a significantly better model of antemortem structural measures than semi-quantitative ratings and showed strong associations with cortical thickness and volume. By providing a more granular measure of pathology, the quantitative p-tau measures also showed a significant negative association with structure in a severe AD subgroup where semi-quantitative ratings displayed a ceiling effect. Our findings demonstrate the advantages of using quantitative neuropathology to understand the relationship of pathology to structure, particularly for p-tau, and motivate the use of quantitative pathology measurements in future studies.

PMID:39227502 | DOI:10.1007/s00401-024-02789-9

Clin Oral Investig. 2024 Sep 4;28(9):512. doi: 10.1007/s00784-024-05895-w.

ABSTRACT

OBJECTIVES: In orthognatic surgery, one of the primary determinants for reliable three-dimensional virtual surgery planning (3D VSP) and an accurate transfer of 3D VSP to the patient in the operation room is the condylar seating. Incorrectly seated condyles would primarily affect the accuracy of maxillary-first bimaxillary osteotomies as the maxillary repositioning is dependent on the positioning of the mandible in the cone-beam computed tomography (CBCT) scan. This study aimed to develop and validate a novel tool by utilizing a deep learning algorithm that automatically evaluates the condylar seating based on CBCT images as a proof of concept.

MATERIALS AND METHODS: As a reference, 60 CBCT scans (120 condyles) were labeled. The automatic assessment of condylar seating included three main parts: segmentation module, ray-casting, and feed-forward neural network (FFNN). The AI-based algorithm was trained and tested using fivefold cross validation. The method's performance was evaluated by comparing the labeled ground truth with the model predictions on the validation dataset.

RESULTS: The model achieved an accuracy of 0.80, positive predictive value of 0.61, negative predictive value of 0.9 and F1-score of 0.71. The sensitivity and specificity of the model was 0.86 and 0.78, respectively. The mean AUC over all folds was 0.87.

CONCLUSION: The innovative integration of multi-step segmentation, ray-casting and a FFNN demonstrated to be a viable approach for automating condylar seating assessment and have obtained encouraging results.

CLINICAL RELEVANCE: Automated condylar seating assessment using deep learning may improve orthognathic surgery, preventing errors and enhancing patient outcomes in maxillary-first bimaxillary osteotomies.

PMID:39227487 | DOI:10.1007/s00784-024-05895-w

Proc Natl Acad Sci U S A. 2024 Sep 10;121(37):e2316256121. doi: 10.1073/pnas.2316256121. Epub 2024 Sep 3.

ABSTRACT

Trajectory inference methods are essential for analyzing the developmental paths of cells in single-cell sequencing datasets. It provides insights into cellular differentiation, transitions, and lineage hierarchies, helping unravel the dynamic processes underlying development and disease progression. However, many existing tools lack a coherent statistical model and reliable uncertainty quantification, limiting their utility and robustness. In this paper, we introduce VITAE (Variational Inference for Trajectory by AutoEncoder), a statistical approach that integrates a latent hierarchical mixture model with variational autoencoders to infer trajectories. The statistical hierarchical model enhances the interpretability of our framework, while the posterior approximations generated by our variational autoencoder ensure computational efficiency and provide uncertainty quantification of cell projections along trajectories. Specifically, VITAE enables simultaneous trajectory inference and data integration, improving the accuracy of learning a joint trajectory structure in the presence of biological and technical heterogeneity across datasets. We show that VITAE outperforms other state-of-the-art trajectory inference methods on both real and synthetic data under various trajectory topologies. Furthermore, we apply VITAE to jointly analyze three distinct single-cell RNA sequencing datasets of the mouse neocortex, unveiling comprehensive developmental lineages of projection neurons. VITAE effectively reduces batch effects within and across datasets and uncovers finer structures that might be overlooked in individual datasets. Additionally, we showcase VITAE's efficacy in integrative analyses of multiomic datasets with continuous cell population structures.

PMID:39226366 | DOI:10.1073/pnas.2316256121

Proc Natl Acad Sci U S A. 2024 Sep 10;121(37):e2400002121. doi: 10.1073/pnas.2400002121. Epub 2024 Sep 3.

ABSTRACT

Single-cell RNA sequencing (scRNA-seq) data, susceptible to noise arising from biological variability and technical errors, can distort gene expression analysis and impact cell similarity assessments, particularly in heterogeneous populations. Current methods, including deep learning approaches, often struggle to accurately characterize cell relationships due to this inherent noise. To address these challenges, we introduce scAMF (Single-cell Analysis via Manifold Fitting), a framework designed to enhance clustering accuracy and data visualization in scRNA-seq studies. At the heart of scAMF lies the manifold fitting module, which effectively denoises scRNA-seq data by unfolding their distribution in the ambient space. This unfolding aligns the gene expression vector of each cell more closely with its underlying structure, bringing it spatially closer to other cells of the same cell type. To comprehensively assess the impact of scAMF, we compile a collection of 25 publicly available scRNA-seq datasets spanning various sequencing platforms, species, and organ types, forming an extensive RNA data bank. In our comparative studies, benchmarking scAMF against existing scRNA-seq analysis algorithms in this data bank, we consistently observe that scAMF outperforms in terms of clustering efficiency and data visualization clarity. Further experimental analysis reveals that this enhanced performance stems from scAMF's ability to improve the spatial distribution of the data and capture class-consistent neighborhoods. These findings underscore the promising application potential of manifold fitting as a tool in scRNA-seq analysis, signaling a significant enhancement in the precision and reliability of data interpretation in this critical field of study.

PMID:39226348 | DOI:10.1073/pnas.2400002121

PLoS Comput Biol. 2024 Sep 3;20(9):e1012340. doi: 10.1371/journal.pcbi.1012340. Online ahead of print.

ABSTRACT

The off-target activities within the CRISPR-Cas9 system remains a formidable barrier to its broader application and development. Recent advancements have highlighted the potential of deep learning models in predicting these off-target effects, yet they encounter significant hurdles including imbalances within datasets and the intricacies associated with encoding schemes and model architectures. To surmount these challenges, our study innovatively introduces an Efficiency and Specificity-Based (ESB) class rebalancing strategy, specifically devised for datasets featuring mismatches-only off-target instances, marking a pioneering approach in this realm. Furthermore, through a meticulous evaluation of various One-hot encoding schemes alongside numerous hybrid neural network models, we discern that encoding and models of moderate complexity ideally balance performance and efficiency. On this foundation, we advance a novel hybrid model, the CRISPR-MCA, which capitalizes on multi-feature extraction to enhance predictive accuracy. The empirical results affirm that the ESB class rebalancing strategy surpasses five conventional methods in addressing extreme dataset imbalances, demonstrating superior efficacy and broader applicability across diverse models. Notably, the CRISPR-MCA model excels in off-target effect prediction across four distinct mismatches-only datasets and significantly outperforms contemporary state-of-the-art models in datasets comprising both mismatches and indels. In summation, the CRISPR-MCA model, coupled with the ESB rebalancing strategy, offers profound insights and a robust framework for future explorations in this field.

PMID:39226304 | DOI:10.1371/journal.pcbi.1012340

PLoS One. 2024 Sep 3;19(9):e0305268. doi: 10.1371/journal.pone.0305268. eCollection 2024.

ABSTRACT

MOTIVATION: There exists an unexplained diverse variation within the predefined colon cancer stages using only features from either genomics or histopathological whole slide images as prognostic factors. Unraveling this variation will bring about improved staging and treatment outcomes. Hence, motivated by the advancement of Deep Neural Network (DNN) libraries and complementary factors within some genomics datasets, we aggregate atypia patterns in histopathological images with diverse carcinogenic expression from mRNA, miRNA and DNA methylation as an integrative input source into a deep neural network for colon cancer stages classification, and samples stratification into low or high-risk survival groups.

RESULTS: The genomics-only and integrated input features return Area Under Curve-Receiver Operating Characteristic curve (AUC-ROC) of 0.97 compared with AUC-ROC of 0.78 obtained when only image features are used for the stage's classification. A further analysis of prediction accuracy using the confusion matrix shows that the integrated features have a weakly improved accuracy of 0.08% more than the accuracy obtained with genomics features. Also, the extracted features were used to split the patients into low or high-risk survival groups. Among the 2,700 fused features, 1,836 (68%) features showed statistically significant survival probability differences in aggregating samples into either low or high between the two risk survival groups. Availability and Implementation: https://github.com/Ogundipe-L/EDCNN.

PMID:39226289 | DOI:10.1371/journal.pone.0305268