J Biomed Phys Eng. 2024 Dec 1;14(6):579-592. doi: 10.31661/jbpe.v0i0.2207-1521. eCollection 2024 Dec.

ABSTRACT

BACKGROUND: The P300 signal, an endogenous component of event-related potentials, is extracted from an electroencephalography signal and employed in Brain-computer Interface (BCI) devices.

OBJECTIVE: The current study aimed to address challenges in extracting useful features from P300 components and detecting P300 through a hybrid unsupervised manner based on Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM).

MATERIAL AND METHODS: In this cross-sectional study, CNN as a useful method for the P300 classification task emphasizes spatial characteristics of data. However, CNN and LSTM networks are combined to modify the classification system by extracting both spatial and temporal features. Then, the CNN-LSTM network was trained in an unsupervised learning method based on an autoencoder to improve Signal-to-noise Ratio (SNR) by extracting main components from latent space. To deal with imbalanced data, an Adaptive Synthetic Sampling Approach (ADASYN) is used and augmented without any duplication.

RESULTS: The trained model, tested on the BCI competition III dataset, including two normal subjects, with an accuracy of 95% and 94% for subjects A and B in P300 detection, respectively.

CONCLUSION: CNN-LSTM, was embedded into an autoencoder and introduced to simultaneously extract spatial and temporal features and manage the computational complexity of the method. Further, ADASYN as an augmentation method was proposed to deal with the imbalanced nature of data, which not only maintained feature space as before but also preserved anatomical features of P300. High-quality results highlight the suitable efficiency of the proposed method.

PMID:39726882 | PMC:PMC11668936 | DOI:10.31661/jbpe.v0i0.2207-1521

Digit Discov. 2024 Dec 16. doi: 10.1039/d4dd00311j. Online ahead of print.

ABSTRACT

Deep learning has significantly accelerated drug discovery, with 'chemical language' processing (CLP) emerging as a prominent approach. CLP approaches learn from molecular string representations (e.g., Simplified Molecular Input Line Entry Systems [SMILES] and Self-Referencing Embedded Strings [SELFIES]) with methods akin to natural language processing. Despite their growing importance, training predictive CLP models is far from trivial, as it involves many 'bells and whistles'. Here, we analyze the key elements of CLP and provide guidelines for newcomers and experts. Our study spans three neural network architectures, two string representations, three embedding strategies, across ten bioactivity datasets, for both classification and regression purposes. This 'hitchhiker's guide' not only underscores the importance of certain methodological decisions, but it also equips researchers with practical recommendations on ideal choices, e.g., in terms of neural network architectures, molecular representations, and hyperparameter optimization.

PMID:39726698 | PMC:PMC11667676 | DOI:10.1039/d4dd00311j

Front Med (Lausanne). 2024 Dec 12;11:1520878. doi: 10.3389/fmed.2024.1520878. eCollection 2024.

ABSTRACT

OBJECTIVES: To implement state-of-the-art deep learning architectures such as Deep-Residual-U-Net and DeepLabV3+ for precise segmentation of hippocampus and ventricles, in functional magnetic resonance imaging (fMRI). Integrate VGG-16 with Random Forest (VGG-16-RF) and VGG-16 with Support Vector Machine (VGG-16-SVM) to enhance the binary classification accuracy of Alzheimer's disease, comparing their performance against traditional classifiers.

METHOD: OpenNeuro and Harvard's Data verse provides Alzheimer's coronal functional MRI data. Ventricles and hippocampus are segmented using a Deep-Residual-UNet and Deep labV3+ system. The functional features were extracted from each segmented component and classified using SVM, Adaboost, Logistic regression, and VGG 16, DenseNet-169, VGG-16-RF, and VGG-16-SVM classifier.

RESULTS: This research proposes a precise and efficient deep-learning architecture like DeepLab V3+ and Deep Residual U-NET for hippocampus and ventricle segmentation in detection of AD. DeepLab V3+ has produced a good segmentation accuracy of 94.62% with Jaccard co-efficient of 85.5% and dice co-efficient of 84.75%. Among the three ML classifiers used, SVM has provided a good accuracy of 93%. Among some DL techniques, VGG-16-RF classifier has given better accuracy of 96.87%.

CONCLUSION: The novelty of this work lies in the seamless integration of advanced segmentation techniques with hybrid classifiers, offering a robust and scalable framework for early AD detection. The proposed study demonstrates a significant advancement in the early detection of Alzheimer's disease by integrating state-of-the-art deep learning models and comprehensive functional connectivity analysis. This early detection capability is crucial for timely intervention and better management of the disease in neurodegenerative disorder diagnostics.

PMID:39726682 | PMC:PMC11669652 | DOI:10.3389/fmed.2024.1520878

Interspeech. 2024 Sep;2024:927-931. doi: 10.21437/interspeech.2024-2236.

ABSTRACT

Magnetic Resonance Imaging (MRI) allows analyzing speech production by capturing high-resolution images of the dynamic processes in the vocal tract. In clinical applications, combining MRI with synchronized speech recordings leads to improved patient outcomes, especially if a phonological-based approach is used for assessment. However, when audio signals are unavailable, the recognition accuracy of sounds is decreased when using only MRI data. We propose a contrastive learning approach to improve the detection of phonological classes from MRI data when acoustic signals are not available at inference time. We demonstrate that frame-wise recognition of phonological classes improves from an f1 of 0.74 to 0.85 when the contrastive loss approach is implemented. Furthermore, we show the utility of our approach in the clinical application of using such phonological classes to assess speech disorders in patients with tongue cancer, yielding promising results in the recognition task.

PMID:39726638 | PMC:PMC11671147 | DOI:10.21437/interspeech.2024-2236

BMC Bioinformatics. 2024 Dec 26;25(1):391. doi: 10.1186/s12859-024-06016-w.

ABSTRACT

As a heterogeneous disease, prostate cancer (PCa) exhibits diverse clinical and biological features, which pose significant challenges for early diagnosis and treatment. Metabolomics offers promising new approaches for early diagnosis, treatment, and prognosis of PCa. However, metabolomics data are characterized by high dimensionality, noise, variability, and small sample sizes, presenting substantial challenges for classification. Despite the wide range of applications of deep learning methods, the use of deep learning in metabolomics research has not been extensively explored. In this study, we propose a hybrid model, TransConvNet, which combines transformer and convolutional neural networks for the classification of prostate cancer metabolomics data. We introduce a 1D convolution layer for the inputs to the dot-product attention mechanism, enabling the interaction of both local and global information. Additionally, a gating mechanism is incorporated to dynamically adjust the attention weights. The features extracted by multi-head attention are further refined through 1D convolution, and a residual network is introduced to alleviate the gradient vanishing problem in the convolutional layers. We conducted comparative experiments with seven other machine learning algorithms. Through five-fold cross-validation, TransConvNet achieved an accuracy of 81.03% and an AUC of 0.89, significantly outperforming the other algorithms. Additionally, we validated TransConvNet's generalization ability through experiments on the lung cancer dataset, with the results demonstrating its robustness and adaptability to different metabolomics datasets. We also proposed the MI-RF (Mutual Information-based random forest) model, which effectively identified key biomarkers associated with prostate cancer by leveraging comprehensive feature weight coefficients. In contrast, traditional methods identified only a limited number of biomarkers. In summary, these results highlight the potential of TransConvNet and MI-RF in both classification tasks and biomarker discovery, providing valuable insights for the clinical application of prostate cancer diagnosis.

PMID:39725937 | DOI:10.1186/s12859-024-06016-w

Nan Fang Yi Ke Da Xue Xue Bao. 2024 Dec 20;44(12):2412-2420. doi: 10.12122/j.issn.1673-4254.2024.12.18.

ABSTRACT

METHODS: We retrospectively collected CT scan data from 276 patients with pathologically confirmed primary bone tumors from 4 medical centers in Guangdong Province between January, 2010 and August, 2021. A convolutional neural network (CNN) was employed as the deep learning architecture. The optimal baseline deep learning model (R-Net) was determined through transfer learning, and an optimized model (S-Net) was obtained through algorithmic improvements. Multivariate logistic regression analysis was used to screen the clinical features such as sex, age, mineralization location, and pathological fractures, which were then connected with the imaging features to construct the deep learning fusion model (SC-Net). The diagnostic performance of the SC-Net model and machine learning models were compared with radiologists' diagnoses, and their classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) and F1 score.

RESULTS: In the external test set, the fusion model (SC-Net) achieved the best performance with an AUC of 0.901 (95% CI: 0.803-1.00), an accuracy of 83.7% (95% CI: 69.3%-93.2%) and an F1 score of 0.857, and outperformed the S-Net model with an AUC of 0.818 (95% CI: 0.694-0.942), an accuracy of 76.7% (95% CI: 61.4%-88.2%), and an F1 score of 0.828. The overall classification performance of the fusion model (SC-Net) exceeded that of radiologists' diagnoses.

CONCLUSIONS: The deep learning fusion model based on multi-center CT images and clinical features is capable of accurate classification of osseous and chondroid matrix mineralization and may potentially improve the accuracy of clinical diagnoses of osteogenic versus chondrogenic primary bone tumors.

PMID:39725631 | DOI:10.12122/j.issn.1673-4254.2024.12.18

Oral Surg Oral Med Oral Pathol Oral Radiol. 2024 Nov 12:S2212-4403(24)00794-6. doi: 10.1016/j.oooo.2024.11.002. Online ahead of print.

ABSTRACT

OBJECTIVE: This study aimed to develop 3 models based on computed tomography (CT) images of patients with craniofacial fibrous dysplasia (CFD): a radiomics model (Model Rad), a deep learning (DL) model (Model DL), and a hybrid radiomics and DL model (Model Rad+DL), and evaluate the ability of these models to distinguish between adolescents with active lesion progression and adults with stable lesion progression.

METHODS: We retrospectively analyzed preoperative CT scans from 148 CFD patients treated at Shanghai Ninth People's Hospital. The images were processed using 3D-Slicer software to segment and extract regions of interest for radiomics and DL analysis. Feature selection was performed using t-tests, mutual information, correlation tests, and the least absolute shrinkage and selection operator algorithm to develop the 3 models. Model accuracy was evaluated using measurements including the area under the curve (AUC) derived from receiver operating characteristic analysis, sensitivity, specificity, and F1 score. Decision curve analysis (DCA) was conducted to evaluate clinical benefits.

RESULTS: In total, 1,130 radiomics features and 512 DL features were successfully extracted. Model Rad+DL demonstrated superior AUC values compared to Model Rad and Model DL in the training and validation sets. DCA revealed that Model Rad+DL offered excellent clinical benefits when the threshold probability exceeded 20%.

CONCLUSIONS: Model Rad+DL exhibits superior potential in evaluating CFD progression, determining the optimal surgical timing for adult CFD patients.

PMID:39725588 | DOI:10.1016/j.oooo.2024.11.002

Arthroscopy. 2024 Dec 24:S0749-8063(24)01088-0. doi: 10.1016/j.arthro.2024.12.024. Online ahead of print.

ABSTRACT

PURPOSE: Improve the accuracy of one-stage object detection by modifying the YOLOv7 with Convolutional Block Attention Module (CBAM), known as YOLOv7-CBAM, which can automatically identify torn or intact rotator cuff tendon to assist physicians in diagnosing rotator cuff lesions through ultrasound.

METHODS: Between 2020 and 2021, patients who experienced shoulder pain for over 3 months and had both ultrasound and MRI examinations were categorized into torn and intact group. To ensure balanced training, we included the same number of patients on both groups. Transfer learning was conducted using a pre-trained model of Yolov7 and an improved model with CBAM. The mean average precision (mAP), sensitivity and F1-score were calculated to evaluate the models. Gradient-weighted Class Activation Mapping (Grad-CAM) method was employed to visualize important regions using a heatmap. Simulation dataset was recruited to evaluate the diagnostic performance of clinical physicians using our AI-assisted model.

RESULTS: A total of 280 patients were included in this study, with 80% of 840 ultrasound images randomly allocated for model training. The accuracy for test set was 0.96 for Yolov7 and 0.98 for Yolov7-CBAM, the precision and sensitivity were 0.94 and 0.98 for Yolov7, 0.98 and 0.98 for Yolov7-CBAM. F1-score and mAP@0.5 were higher for Yolov7-CBAM (0.980 and 0.993) than Yolov7 (0.961 and 0.965). Furthermore, the Grad-CAM method elucidated that the deep learning model primarily emphasized hypoechoic anechoic defect within the tendon. Following adopting an AI-assisted model (YOLOv7-CBAM model), diagnostic accuracy improved from 80.86% to 88.86% (p=0.01) and interobserver reliability improved from 0.49 to 0.71 among physicians.

CONCLUSION: The YOLOv7-CBAM model demonstrate high accuracy in detecting torn or intact rotator cuff tendon from ultrasound images. Integrating this model into the diagnostic process can assist physicians in improving diagnostic accuracy and interobserver reliability across different physicians.

CLINICAL RELEVANCE: The attentional deep learning model aids physicians in improving the accuracy and consistency of ultrasound diagnosis of torn or intact rotator cuff tendons.

PMID:39725049 | DOI:10.1016/j.arthro.2024.12.024

J Neuropathol Exp Neurol. 2024 Dec 26:nlae120. doi: 10.1093/jnen/nlae120. Online ahead of print.

ABSTRACT

Microinfarcts and microhemorrhages are characteristic lesions of cerebrovascular disease. Although multiple studies have been published, there is no one universal standard criteria for the neuropathological assessment of cerebrovascular disease. In this study, we propose a novel application of machine learning in the automated screening of microinfarcts and microhemorrhages. Utilizing whole slide images (WSIs) from postmortem human brain samples, we adapted a patch-based pipeline with convolutional neural networks. Our cohort consisted of 22 cases from the University of California Davis Alzheimer's Disease Research Center brain bank with hematoxylin and eosin-stained formalin-fixed, paraffin-embedded sections across 3 anatomical areas: frontal, parietal, and occipital lobes (40 WSIs with microinfarcts and/or microhemorrhages, 26 without). We propose a multiple field-of-view prediction step to mitigate false positives. We report screening performance (ie, the ability to distinguish microinfarct/microhemorrhage-positive from microinfarct/microhemorrhage-negative WSIs), and detection performance (ie, the ability to localize the affected regions within a WSI). Our proposed approach improved detection precision and screening accuracy by reducing false positives thereby achieving 100% screening accuracy. Although this sample size is small, this pipeline provides a proof-of-concept for high efficacy in screening for characteristic brain changes of cerebrovascular disease to aid in screening of microinfarcts/microhemorrhages at the WSI level.

PMID:39724914 | DOI:10.1093/jnen/nlae120

Georgian Med News. 2024 Oct;(355):184-187.

ABSTRACT

The corona virus disease-19 (COVID-19) epidemic, the whole globe is suffering from a medical condition catastrophe that is unprecedented in scale. As the coronavirus spreads, scientists are worried about offering or helping in the supply of remedies to preserve lives and end the epidemic. Artificial intelligence (AI), for example, has occurred altered to deal with the difficulties raised by pandemics. We provide an in-depth learning approach for locating and extracting attributes of COVID-19 from Chest X-rays. Hierarchical multilevel ResNet50 (HMResNet50) was adjusted to better COVID-19 data, which was collected to build this dataset with images of a typical chest X-ray from numerous public sources. We employed information enhancement methods such as randomized rotations with a ten-ten-degree slant, random noise, and horizontal flips to generate numerous images of chest X-ray. Outcome of the research is encouraging: the suggested models correctly identified COVID-19 chest X-rays or standard with an accuracy of 99.10 % for Resnet50 and 97.20 % for hierarchal Multilevel Resnet50. The findings suggest that the proposed is effective, with high performance and simple COVID-19 recognition methods.

PMID:39724901

Digestion. 2024 Dec 26:1-13. doi: 10.1159/000543345. Online ahead of print.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) has significantly impacted medical imaging, particularly in gastrointestinal endoscopy. Computer-aided detection and diagnosis systems (CADe and CADx) are thought to enhance the quality of colonoscopy procedures.

SUMMARY: Colonoscopy is essential for colorectal cancer screening, but often misses a significant percentage of adenomas. AI-assisted systems employing deep learning offer improved detection and differentiation of colorectal polyps, potentially increasing adenoma detection rates by 8%-10%. The main benefit of CADe is in detecting small adenomas, whereas it has a limited impact on advanced neoplasm detection. Recent advancements include real-time CADe systems and CADx for histopathological predictions, aiding in the differentiation of neoplastic and non-neoplastic lesions. Biases such as the Hawthorne effect and potential overdiagnosis necessitate large-scale clinical trials to validate the long-term benefits of AI. Additionally, novel concepts such as computer-aided quality improvement systems are emerging to address limitations facing current CADe systems.

KEY MESSAGES: Despite the potential of AI for enhancing colonoscopy outcomes, its effectiveness in reducing colorectal cancer incidence and mortality remains unproven. Further prospective studies are essential to establish the overall utility and clinical benefits of AI in colonoscopy.

PMID:39724867 | DOI:10.1159/000543345

Phys Med. 2024 Dec 25;129:104881. doi: 10.1016/j.ejmp.2024.104881. Online ahead of print.

ABSTRACT

PURPOSE: We investigate the feasibility of using a biophysically guided approach for delineating the Clinical Target Volume (CTV) in Glioblastoma Multiforme (GBM) by evaluating its impact on the treatment outcomes, specifically Overall Survival (OS) time.

METHODS: An established reaction-diffusion model was employed to simulate the spatiotemporal evolution of cancerous regions in T1-MRI images of GBM patients. The effects of the parameters of this model on the simulated tumor borders were quantified and the optimal values were used to estimate the distribution of infiltrative cells (CTVmodel). Radiomics and deep learning models were examined to predict the OS time by analyzing the GTV, clinical CTV, and CTVmodel.

RESULTS: The study involves 126 subjects for model development and 62 independent subjects for testing. Evaluation of the proposed approach demonstrates comparable predictive power for OS time that is achieved with the clinically defined CTV. Specifically, for the binary survival prediction, short vs. long time, the proposed CTVmodelresulted in improvements of prognostic power, in terms of AUROC, both for the validation (0.77 from 0.75) and the testing (0.73 from 0.71) set. Quantitative comparisons for three-class prediction and survival regression models exhibited a similar trend of comparable performance.

CONCLUSION: The findings highlight the potential of biophysical modeling for estimating and incorporating the spread of infiltrating cells into CTV delineation. Further clinical investigations are required to validate the clinical efficacy.

PMID:39724784 | DOI:10.1016/j.ejmp.2024.104881

Invest Radiol. 2024 Oct 9. doi: 10.1097/RLI.0000000000001126. Online ahead of print.

ABSTRACT

PURPOSE: Accurate detection of central venous catheter (CVC) misplacement is crucial for patient safety and effective treatment. Existing artificial intelligence (AI) often grapple with the limitations of label inaccuracies and output interpretations that lack clinician-friendly comprehensibility. This study aims to introduce an approach that employs segmentation of support material and anatomy to enhance the precision and comprehensibility of CVC misplacement detection.

MATERIALS AND METHODS: The study utilized 2 datasets: the publicly accessible RANZCR CLiP dataset and a bespoke in-house dataset of 1006 annotated supine chest x-rays. Three deep learning models were trained: a classification network, a segmentation network, and a combination of both. These models were evaluated using receiver operating characteristic analysis, area under the curve, DICE similarity coefficient, and Hausdorff distance.

RESULTS: The combined model demonstrated superior performance with an area under the curve of 0.99 for correctly positioned CVCs and 0.95 for misplacements. The model maintained high efficacy even with reduced training data from the local dataset. Sensitivity and specificity rates were high, and the model effectively managed the segmentation and classification tasks, even in images with multiple CVCs and other support materials.

CONCLUSIONS: This study illustrates the potential of AI-based models in accurately and reliably determining CVC placement in chest x-rays. The proposed method shows high accuracy and offers improved interpretability, important for clinical decision-making. The findings also highlight the importance of dataset quality and diversity in training AI models for medical image analysis.

PMID:39724590 | DOI:10.1097/RLI.0000000000001126

Int J Surg. 2024 Oct 1. doi: 10.1097/JS9.0000000000002105. Online ahead of print.

ABSTRACT

OBJECTIVE: To develop a model for accurate prediction of axillary lymph node (LN) status after neoadjuvant chemotherapy (NAC) in breast cancer patients with nodal involvement.

METHODS: Between October 2018 and February 2024, 671 breast cancer patients with biopsy-proven LN metastasis who received NAC followed by axillary LN dissection were enrolled in this prospective, multicenter study. Preoperative ultrasound (US) images, including B-mode ultrasound (BUS) and shear wave elastography (SWE), were obtained. The included patients were randomly divided at a ratio of 8:2 into a training set and an independent test set, with five-fold cross-validation applied to training set. We first identified clinicopathological characteristics and conventional US features significantly associated with the axillary LN response and developed corresponding prediction models. We then constructed deep learning radiomics (DLR) models based on BUS and SWE data. Models performances were compared, and a combination model was developed using significant clinicopathological data and interpreted US features with the SWE-based DLR model. Discrimination, calibration and clinical utility of this model were analyzed using receiver operating characteristic curve, calibration curve and decision curve, respectively.

RESULTS: Axillary pathologic complete response (pCR) was achieved in 52.41% of patients. In the test cohort, the clinicopathologic model had an accuracy of 71.30%, while radiologists' diagnoses ranged from 64.26% to 71.11%, indicating limited to moderate predictive ability for the axillary response to NAC. The SWE-based DLR model, with an accuracy of 80.81%, significantly outperformed the BUS-based DLR model, which scored 59.57%. The combination DLR model boasted an accuracy of 88.70% and a false-negative rate of 8.82%. It demonstrated strong discriminatory ability (AUC, 0.95), precise calibration (p value obtained by Hosmer-Lemeshow goodness-of-fit test, 0.68), and practical clinical utility (probability threshold, 2.5-97.5%).

CONCLUSIONS: The combination SWE-based DLR model can predict the axillary status after NAC in patients with node-positive breast cancer, and thus, may inform clinical decision-making to help avoid unnecessary axillary LN dissection.

PMID:39724577 | DOI:10.1097/JS9.0000000000002105

J Chem Inf Model. 2024 Dec 26. doi: 10.1021/acs.jcim.4c01096. Online ahead of print.

ABSTRACT

In recent years, the deep learning (DL) technique has rapidly developed and shown great success in scoring the protein-ligand binding affinities. The protein-ligand conformation optimization based on DL-derived scoring functions holds broad application prospects, for instance, drug design and enzyme engineering. In this study, we evaluated the robustness of a DL-based ligand conformation optimization protocol (DeepRMSD+Vina) for optimizing structures with input perturbations by examining the predicted ligand binding poses and scoring. Our results clearly indicated that compared to traditional optimization algorithms (such as Prime MM-GBSA and Vina optimization), DeepRMSD+Vina exhibits higher performance when treating diverse protein-ligand cases. The DeepRMSD+Vina is robust and can always generate the correct binding structures even if perturbations (up to 3 Å) are introduced to the input structure. The success rate is 62% for perturbation with a RMSD within 2-3 Å. However, the success rate dramatically drops to 11% for large perturbations, with RMSD extending to 3-4 Å. Furthermore, compared to the widely used optimization protocol of AutoDock Vina, the DL-generated conformation shows a balanced performance for all of the systems under examination. Overall, the DL-based DeepRMSD+Vina is unarguably more reliable than the traditional methods, which is attributed to the physically inspired design of the neural networks in DeepRMSD+Vina where the distance-transformed features describing the atomic interactions between the protein and the ligand have been explicitly considered and modeled. The outstanding robustness of the DL-based ligand conformational optimization algorithm further validates its superiority in the field of conformational optimization.

PMID:39724561 | DOI:10.1021/acs.jcim.4c01096

Hum Reprod. 2024 Dec 26:deae267. doi: 10.1093/humrep/deae267. Online ahead of print.

ABSTRACT

STUDY QUESTION: How can we best achieve tissue segmentation and cell counting of multichannel-stained endometriosis sections to understand tissue composition?

SUMMARY ANSWER: A combination of a machine learning-based tissue analysis software for tissue segmentation and a deep learning-based algorithm for segmentation-independent cell identification shows strong performance on the automated histological analysis of endometriosis sections.

WHAT IS KNOWN ALREADY: Endometriosis is characterized by the complex interplay of various cell types and exhibits great variation between patients and endometriosis subtypes.

STUDY DESIGN, SIZE, DURATION: Endometriosis tissue samples of eight patients of different subtypes were obtained during surgery.

PARTICIPANTS/MATERIALS, SETTING, METHODS: Endometriosis tissue was formalin-fixed and paraffin-embedded before sectioning and staining by (multiplex) immunohistochemistry. A 6-plex immunofluorescence panel in combination with a nuclear stain was established following a standardized protocol. This panel enabled the distinction of different tissue structures and dividing cells. Artificial intelligence-based tissue and cell phenotyping were employed to automatically segment the various tissue structures and extract quantitative features.

MAIN RESULTS AND THE ROLE OF CHANCE: An endometriosis-specific multiplex panel comprised of PanCK, CD10, α-SMA, calretinin, CD45, Ki67, and DAPI enabled the distinction of tissue structures in endometriosis. Whereas a machine learning approach enabled a reliable segmentation of tissue substructure, for cell identification, the segmentation-free deep learning-based algorithm was superior.

LIMITATIONS, REASONS FOR CAUTION: The present analysis was conducted on a limited number of samples for method establishment. For further refinement, quantification of collagen-rich cell-free areas should be included which could further enhance the assessment of the extent of fibrotic changes. Moreover, the method should be applied to a larger number of samples to delineate subtype-specific differences.

WIDER IMPLICATIONS OF THE FINDINGS: We demonstrate the great potential of combining multiplex staining and cell phenotyping for endometriosis research. The optimization procedure of the multiplex panel was transferred from a cancer-related project, demonstrating the robustness of the procedure beyond the cancer context. This panel can be employed for larger batch analyses. Furthermore, we demonstrate that the deep learning-based approach is capable of performing cell phenotyping on tissue types that were not part of the training set underlining the potential of the method for heterogenous endometriosis samples.

STUDY FUNDING/COMPETING INTEREST(S): All funding was provided through departmental funds. The authors declare no competing interests.

TRIAL REGISTRATION NUMBER: N/A.

PMID:39724530 | DOI:10.1093/humrep/deae267

Environ Monit Assess. 2024 Dec 26;197(1):103. doi: 10.1007/s10661-024-13595-x.

ABSTRACT

Waste sorting is a key part of sustainable development. To maximize the recovery of resources and reduce labor costs, a waste management and classification system is established. In the system, we use Internet of Things (IoT) and edge computing to implement waste sorting and the systematic long-distance information transmission and monitoring. A dataset of recyclable waste images with realistic backgrounds was collected, where the images contained multiple waste categories in a single image. An improved deep learning model based on YOLOv7-tiny is proposed to adapt to the realistic complex background of waste images. In the model, adding partial convolution (PConv) to Efficient Layer Aggregation Network (ELAN) module reduces parameters and floating point of operations (FLOPs). Coordinate attention (CA) is added to spatial pyramid pooling (Sppcspc) module and ELAN module, respectively. SIoU loss function is used, which improves the recognition accuracy of the model. The improved model shows a higher accuracy on the basis of lighter weight and is more suitable for deployment on edge devices. The proposed model and the original model were trained using our dataset, and their performance was compared. According to the experimental results, mAP@.5, mAP@.5:.95 of the improved YOLOv7-tiny are increased by 1.7% and 1.4%, and the parameter and FLOPs are decreased by 4.8% and 5%, respectively. The improved model has an average inference time of 110 ms and an FPS of 9 on the Jetson Nano. Hence, we believe that the developed system can better meet the needs of current garbage collection system.

PMID:39724392 | DOI:10.1007/s10661-024-13595-x

Genomics Proteomics Bioinformatics. 2024 Dec 26:qzae091. doi: 10.1093/gpbjnl/qzae091. Online ahead of print.

ABSTRACT

Chromatin compartmentalization and epigenomic modification are crucial in cell differentiation and diseases development. However, precise mapping of chromatin compartmental patterns requires Hi-C or Micro-C data at high sequencing depth. Exploring the systematic relationship between epigenomic modifications and compartmental patterns remains challenging. To address these issues, we present COCOA, a deep neural network framework using convolution and attention mechanisms to infer fine-scale chromatin compartment patterns from six histone modification signals. COCOA extracts 1-D track features through bi-directional feature reconstruction after resolution-specific binning epigenomic signals. These track features are then cross-fused with contact features using an attention mechanism and transformed into chromatin compartment patterns through residual feature reduction. COCOA demonstrates accurate inference of chromatin compartmentalization at a fine-scale resolution and exhibits stable performance on test sets. Additionally, we explored the impact of histone modifications on chromatin compartmentalization prediction through in silico epigenomic perturbation experiments. Unlike obscure compartments observed with 1 kb resolution high-depth experimental data, COCOA generates clear and detailed compartmental patterns, highlighting its superior performance. Finally, we demonstrated that COCOA enables cell-type-specific prediction of unrevealed chromatin compartment patterns in various biological processes, making it an effective tool for gaining chromatin compartmentalization insights from epigenomics in diverse biological scenarios. The COCOA python code is publicly available at https://github.com/onlybugs/COCOA.

PMID:39724385 | DOI:10.1093/gpbjnl/qzae091

J Comput Aided Mol Des. 2024 Dec 26;39(1):4. doi: 10.1007/s10822-024-00582-0.

ABSTRACT

Conotoxins, being small disulfide-rich and bioactive peptides, manifest notable pharmacological potential and find extensive applications. However, the exploration of conotoxins' vast molecular space using traditional methods is severely limited, necessitating the urgent need of developing novel approaches. Recently, deep learning (DL)-based methods have advanced to the molecular generation of proteins and peptides. Nevertheless, the limited data and the intricate structure of conotoxins constrain the application of deep learning models in the generation of conotoxins. We propose ConoDL, a framework for the generation and prediction of conotoxins, comprising the end-to-end conotoxin generation model (ConoGen) and the conotoxin prediction model (ConoPred). ConoGen employs transfer learning and a large language model (LLM) to tackle the challenges in conotoxin generation. Meanwhile, ConoPred filters artificial conotoxins generated by ConoGen, narrowing down the scope for subsequent research. A comprehensive evaluation of the peptide properties at both sequence and structure levels indicates that the artificial conotoxins generated by ConoDL exhibit a certain degree of similarity to natural conotoxins. Furthermore, ConoDL has generated artificial conotoxins with novel cysteine scaffolds. Therefore, ConoDL may uncover new cysteine scaffolds and conotoxin molecules, facilitating further exploration of the molecular space of conotoxins and the discovery of pharmacologically active variants.

PMID:39724258 | DOI:10.1007/s10822-024-00582-0

JAMA Oncol. 2024 Dec 26. doi: 10.1001/jamaoncol.2024.5356. Online ahead of print.

ABSTRACT

IMPORTANCE: Only a small fraction of patients with advanced non-small cell lung cancer (NSCLC) respond to immune checkpoint inhibitor (ICI) treatment. For optimal personalized NSCLC care, it is imperative to identify patients who are most likely to benefit from immunotherapy.

OBJECTIVE: To develop a supervised deep learning-based ICI response prediction method; evaluate its performance alongside other known predictive biomarkers; and assess its association with clinical outcomes in patients with advanced NSCLC.

DESIGN, SETTING, AND PARTICIPANTS: This multicenter cohort study developed and independently validated a deep learning-based response stratification model for predicting ICI treatment outcome in patients with advanced NSCLC from whole slide hematoxylin and eosin-stained images. Images for model development and validation were obtained from 1 participating center in the US and 3 in the European Union (EU) from August 2014 to December 2022. Data analyses were performed from September 2022 to May 2024.

EXPOSURE: Monotherapy with ICIs.

MAIN OUTCOMES AND MEASURES: Model performance measured by clinical end points and objective response rate (ORR) differentiation power vs other predictive biomarkers, ie, programmed death-ligand 1 (PD-L1), tumor mutational burden (TMB), and tumor-infiltrating lymphocytes (TILs).

RESULTS: A total of 295 581 image tiles from 958 patients (mean [SD] age, 66.0 [10.6] years; 456 [48%] females and 502 [52%] males) treated with ICI for NSCLC were included in the analysis. The US-based development cohort consisted of 614 patients with median (IQR) follow-up time of 54.5 (38.2-68.1) months, and the EU-based validation cohort, 344 patients with 43.3 (27.4-53.9) months of follow-up. The ORR to ICI was 26% in the developmental cohort and 28% in the validation cohort. The deep learning model's area under the receiver operating characteristic curve (AUC) for ORR was 0.75 (95% CI, 0.64-0.85) in the internal test set and 0.66 (95% CI, 0.60-0.72) in the validation cohort. In a multivariable analysis, the deep learning model's score was an independent predictor of ICI response in the validation cohort for both progression-free (hazard ratio, 0.56; 95% CI, 0.42-0.76; P < .001) and overall survival (hazard ratio, 0.53; 95% CI, 0.39-0.73; P < .001). The tuned deep learning model achieved a higher AUC than TMB, TILs, and PD-L1 in the internal set; in the validation cohort, it was superior to TILs and comparable with PD-L1 (AUC, 0.67; 95% CI, 0.60-0.74), with a 10-percentage point improvement in specificity. In the validation cohort, combining the deep learning model with PD-L1 scores achieved an AUC of 0.70 (95% CI, 0.63-0.76), outperforming either marker alone, with a response rate of 51% compared to 41% for PD-L1 (≥50%) alone.

CONCLUSIONS AND RELEVANCE: The findings of this cohort study demonstrate a strong and independent deep learning-based feature associated with ICI response in patients with NSCLC across various cohorts. Clinical use of this deep learning model could refine treatment precision and better identify patients who are likely to benefit from ICI for treatment of advanced NSCLC.

PMID:39724105 | DOI:10.1001/jamaoncol.2024.5356