Plant Methods. 2024 Aug 14;20(1):126. doi: 10.1186/s13007-024-01244-w.

ABSTRACT

PURPOSE: Wood comprises different cell types, such as fibers, tracheids and vessels, defining its properties. Studying cells' shape, size, and arrangement in microscopy images is crucial for understanding wood characteristics. Typically, this involves macerating (soaking) samples in a solution to separate cells, then spreading them on slides for imaging with a microscope that covers a wide area, capturing thousands of cells. However, these cells often cluster and overlap in images, making the segmentation difficult and time-consuming using standard image-processing methods.

RESULTS: In this work, we developed an automatic deep learning segmentation approach that utilizes the one-stage YOLOv8 model for fast and accurate segmentation and characterization of macerated fiber and vessel form aspen trees in microscopy images. The model can analyze 32,640 x 25,920 pixels images and demonstrate effective cell detection and segmentation, achieving a mAP 0.5 - 0.95 of 78 %. To assess the model's robustness, we examined fibers from a genetically modified tree line known for longer fibers. The outcomes were comparable to previous manual measurements. Additionally, we created a user-friendly web application for image analysis and provided the code for use on Google Colab.

CONCLUSION: By leveraging YOLOv8's advances, this work provides a deep learning solution to enable efficient quantification and analysis of wood cells suitable for practical applications.

PMID:39143615 | DOI:10.1186/s13007-024-01244-w

Radiol Phys Technol. 2024 Aug 14. doi: 10.1007/s12194-024-00832-8. Online ahead of print.

ABSTRACT

Urinary toxicities are one of the serious complications of radiotherapy for prostate cancer, and dose-volume histogram of prostatic urethra has been associated with such toxicities in previous reports. Previous research has focused on estimating the prostatic urethra, which is difficult to delineate in CT images; however, these studies, which are limited in number, mainly focused on cases undergoing brachytherapy uses low-dose-rate sources and do not involve external beam radiation therapy (EBRT). In this study, we aimed to develop a deep learning-based method of determining the position of the prostatic urethra in patients eligible for EBRT. We used contour data from 430 patients with localized prostate cancer. In all cases, a urethral catheter was placed when planning CT to identify the prostatic urethra. We used 2D and 3D U-Net segmentation models. The input images included the bladder and prostate, while the output images focused on the prostatic urethra. The 2D model determined the prostate's position based on results from both coronal and sagittal directions. Evaluation metrics included the average distance between centerlines. The average centerline distances for the 2D and 3D models were 2.07 ± 0.87 mm and 2.05 ± 0.92 mm, respectively. Increasing the number of cases while maintaining equivalent accuracy as we did in this study suggests the potential for high generalization performance and the feasibility of using deep learning technology for estimating the position of the prostatic urethra.

PMID:39143386 | DOI:10.1007/s12194-024-00832-8

Sci Rep. 2024 Aug 14;14(1):18900. doi: 10.1038/s41598-024-69725-5.

ABSTRACT

To investigate whether peritumoral edema (PE) could enhance deep learning radiomic (DLR) model in predicting axillary lymph node metastasis (ALNM) burden in breast cancer. Invasive breast cancer patients with preoperative MRI were retrospectively enrolled and categorized into low (< 2 lymph nodes involved (LNs+)) and high (≥ 2 LNs+) burden groups based on surgical pathology. PE was evaluated on T2WI, and intra- and peri-tumoral radiomic features were extracted from MRI-visible tumors in DCE-MRI. Deep learning models were developed for LN burden prediction in the training cohort and validated in an independent cohort. The incremental value of PE was evaluated through receiver operating characteristic (ROC) analysis, confirming the improvement in the area under the curve (AUC) using the Delong test. This was complemented by net reclassification improvement (NRI) and integrated discrimination improvement (IDI) metrics. The deep learning combined model, incorporating PE with selected radiomic features, demonstrated significantly higher AUC values compared to the MRI model and the DLR model in the training cohort (n = 177) (AUC: 0.953 vs. 0.849 and 0.867, p < 0.05) and the validation cohort (n = 111) (AUC: 0.963 vs. 0.883 and 0.882, p < 0.05). The complementary analysis demonstrated that PE significantly enhances the prediction performance of the DLR model (Categorical NRI: 0.551, p < 0.001; IDI = 0.343, p < 0.001). These findings were confirmed in the validation cohort (Categorical NRI: 0.539, p < 0.001; IDI = 0.387, p < 0.001). PE improved preoperative ALNM burden prediction of DLR model, facilitating personalized axillary management in breast cancer patients.

PMID:39143315 | DOI:10.1038/s41598-024-69725-5

Sci Rep. 2024 Aug 14;14(1):18922. doi: 10.1038/s41598-024-69568-0.

ABSTRACT

When a person listens to natural speech, the relation between features of the speech signal and the corresponding evoked electroencephalogram (EEG) is indicative of neural processing of the speech signal. Using linguistic representations of speech, we investigate the differences in neural processing between speech in a native and foreign language that is not understood. We conducted experiments using three stimuli: a comprehensible language, an incomprehensible language, and randomly shuffled words from a comprehensible language, while recording the EEG signal of native Dutch-speaking participants. We modeled the neural tracking of linguistic features of the speech signals using a deep-learning model in a match-mismatch task that relates EEG signals to speech, while accounting for lexical segmentation features reflecting acoustic processing. The deep learning model effectively classifies coherent versus nonsense languages. We also observed significant differences in tracking patterns between comprehensible and incomprehensible speech stimuli within the same language. It demonstrates the potential of deep learning frameworks in measuring speech understanding objectively.

PMID:39143297 | DOI:10.1038/s41598-024-69568-0

Sci Rep. 2024 Aug 14;14(1):18865. doi: 10.1038/s41598-024-69848-9.

ABSTRACT

This study investigated the usefulness of deep learning-based automatic detection of temporomandibular joint (TMJ) effusion using magnetic resonance imaging (MRI) in patients with temporomandibular disorder and whether the diagnostic accuracy of the model improved when patients' clinical information was provided in addition to MRI images. The sagittal MR images of 2948 TMJs were collected from 1017 women and 457 men (mean age 37.19 ± 18.64 years). The TMJ effusion diagnostic performances of three convolutional neural networks (scratch, fine-tuning, and freeze schemes) were compared with those of human experts based on areas under the curve (AUCs) and diagnosis accuracies. The fine-tuning model with proton density (PD) images showed acceptable prediction performance (AUC = 0.7895), and the from-scratch (0.6193) and freeze (0.6149) models showed lower performances (p < 0.05). The fine-tuning model had excellent specificity compared to the human experts (87.25% vs. 58.17%). However, the human experts were superior in sensitivity (80.00% vs. 57.43%) (all p < 0.001). In gradient-weighted class activation mapping (Grad-CAM) visualizations, the fine-tuning scheme focused more on effusion than on other structures of the TMJ, and the sparsity was higher than that of the from-scratch scheme (82.40% vs. 49.83%, p < 0.05). The Grad-CAM visualizations agreed with the model learned through important features in the TMJ area, particularly around the articular disc. Two fine-tuning models on PD and T2-weighted images showed that the diagnostic performance did not improve compared with using PD alone (p < 0.05). Diverse AUCs were observed across each group when the patients were divided according to age (0.7083-0.8375) and sex (male:0.7576, female:0.7083). The prediction accuracy of the ensemble model was higher than that of the human experts when all the data were used (74.21% vs. 67.71%, p < 0.05). A deep neural network (DNN) was developed to process multimodal data, including MRI and patient clinical data. Analysis of four age groups with the DNN model showed that the 41-60 age group had the best performance (AUC = 0.8258). The fine-tuning model and DNN were optimal for judging TMJ effusion and may be used to prevent true negative cases and aid in human diagnostic performance. Assistive automated diagnostic methods have the potential to increase clinicians' diagnostic accuracy.

PMID:39143180 | DOI:10.1038/s41598-024-69848-9

NPJ Syst Biol Appl. 2024 Aug 14;10(1):88. doi: 10.1038/s41540-024-00415-8.

ABSTRACT

We present a study where predictive mechanistic modeling is combined with deep learning methods to predict individual patient survival probabilities under immune checkpoint inhibitor (ICI) immunotherapy. This hybrid approach enables prediction based on both measures that are calculable from mechanistic models of key mechanisms underlying ICI therapy that may not be directly measurable in the clinic and easily measurable quantities or patient characteristics that are not always readily incorporated into predictive mechanistic models. A deep learning time-to-event predictive model trained on a hybrid mechanistic + clinical data set from 93 patients achieved higher per-patient predictive accuracy based on event-time concordance, Brier score, and negative binomial log-likelihood-based criteria than when trained on only mechanistic model-derived values or only clinical data. Feature importance analysis revealed that both clinical and model-derived parameters play prominent roles in increasing prediction accuracy, further supporting the advantage of our hybrid approach.

PMID:39143136 | DOI:10.1038/s41540-024-00415-8

Sci Rep. 2024 Aug 14;14(1):18895. doi: 10.1038/s41598-024-69529-7.

ABSTRACT

To develop a deep learning-based model capable of segmenting the left ventricular (LV) myocardium on native T1 maps from cardiac MRI in both long-axis and short-axis orientations. Models were trained on native myocardial T1 maps from 50 healthy volunteers and 75 patients using manual segmentation as the reference standard. Based on a U-Net architecture, we systematically optimized the model design using two different training metrics (Sørensen-Dice coefficient = DSC and Intersection-over-Union = IOU), two different activation functions (ReLU and LeakyReLU) and various numbers of training epochs. Training with DSC metric and a ReLU activation function over 35 epochs achieved the highest overall performance (mean error in T1 10.6 ± 17.9 ms, mean DSC 0.88 ± 0.07). Limits of agreement between model results and ground truth were from -35.5 to + 36.1 ms. This was superior to the agreement between two human raters (-34.7 to + 59.1 ms). Segmentation was as accurate for long-axis views (mean error T1: 6.77 ± 8.3 ms, mean DSC: 0.89 ± 0.03) as for short-axis images (mean error ΔT1: 11.6 ± 19.7 ms, mean DSC: 0.88 ± 0.08). Fully automated segmentation and quantitative analysis of native myocardial T1 maps is possible in both long-axis and short-axis orientations with very high accuracy.

PMID:39143126 | DOI:10.1038/s41598-024-69529-7

Sci Rep. 2024 Aug 14;14(1):18868. doi: 10.1038/s41598-024-69427-y.

ABSTRACT

Ovarian cysts pose significant health risks including torsion, infertility, and cancer, necessitating rapid and accurate diagnosis. Ultrasonography is commonly employed for screening, yet its effectiveness is hindered by challenges like weak contrast, speckle noise, and hazy boundaries in images. This study proposes an adaptive deep learning-based segmentation technique using a database of ovarian ultrasound cyst images. A Guided Trilateral Filter (GTF) is applied for noise reduction in pre-processing. Segmentation utilizes an Adaptive Convolutional Neural Network (AdaResU-net) for precise cyst size identification and benign/malignant classification, optimized via the Wild Horse Optimization (WHO) algorithm. Objective functions Dice Loss Coefficient and Weighted Cross-Entropy are optimized to enhance segmentation accuracy. Classification of cyst types is performed using a Pyramidal Dilated Convolutional (PDC) network. The method achieves a segmentation accuracy of 98.87%, surpassing existing techniques, thereby promising improved diagnostic accuracy and patient care outcomes.

PMID:39143122 | DOI:10.1038/s41598-024-69427-y

Sci Data. 2024 Aug 14;11(1):882. doi: 10.1038/s41597-024-03701-6.

ABSTRACT

Recent advances in computer vision and deep learning techniques have facilitated significant progress in video scene understanding, thus helping film and television practitioners achieve accurate video editing. However, so far, publicly available semantic segmentation datasets are mostly limited to indoor scenes, city streets, and natural images, often ignoring example objects in action movies, which is a research gap that needs to be urgently filled. In this paper, we introduce a large-scale, high-precision semantic segmentation dataset of props in Chinese martial arts movie clips, named ChineseMPD. Specifically, this dataset first establishes segmentation rules and general review criteria for audiovisual data, and then provides semantic segmentation annotations for six weapon props (Gun, Sword, Stick, Knife, Hook, and Arrow) with a summary of 32,992 objects.To the best of our knowledge, this dataset is the largest semantic segmentation dataset for movie props to date. ChineseMPD dataset not only significantly expands the application of traditional tasks of computer vision such as object detection and scene understanding, but also opens up new avenues for interdisciplinary research.

PMID:39143093 | DOI:10.1038/s41597-024-03701-6

Mol Imaging Biol. 2024 Aug 14. doi: 10.1007/s11307-024-01943-9. Online ahead of print.

ABSTRACT

PURPOSE: Develop a universal lesion recognition algorithm for PET/CT and PET/MRI, validate it, and explore factors affecting performance.

PROCEDURES: The 2022 AutoPet Challenge's 1014 PET/CT dataset was used to train the lesion detection model based on 2D and 3D fractional-residual (F-Res) models. To extend this to PET/MRI, a network for converting MR images to synthetic CT (sCT) was developed, using 41 sets of whole-body MR and corresponding CT data. 38 patients' PET/CT and PET/MRI data were used to verify the universal lesion recognition algorithm. Image quality was assessed using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Total lesion glycolysis (TLG), metabolic tumor volume (MTV), and lesion count were calculated from the resultant lesion masks. Experienced physicians reviewed and corrected the model's outputs, establishing the ground truth. The performance of the lesion detection deep-learning model on different PET images was assessed by detection accuracy, precision, recall, and dice coefficients. Data with a detection accuracy score (DAS) less than 1 was used for analysis of outliers.

RESULTS: Compared to PET/CT, PET/MRI scans had a significantly longer delay time (135 ± 45 min vs 61 ± 12 min) and lower SNR (6.17 ± 1.11 vs 9.27 ± 2.77). However, CNR values were similar (7.37 ± 5.40 vs 5.86 ± 6.69). PET/MRI detected more lesions (with a mean difference of -3.184). TLG and MTV showed no significant differences between PET/CT and PET/MRI (TLG: 119.18 ± 203.15 vs 123.57 ± 151.58, p = 0.41; MTV: 36.58 ± 57.00 vs 39.16 ± 48.34, p = 0.33). A total of 12 PET/CT and 14 PET/MRI datasets were included in the analysis of outliers. Outlier analysis revealed PET/CT anomalies in intestines, ureters, and muscles, while PET/MRI anomalies were in intestines, testicles, and low tracer uptake regions, with false positives in ureters (PET/CT) and intestines/testicles (PET/MRI).

CONCLUSION: The deep learning lesion detection model performs well with both PET/CT and PET/MRI. SNR, CNR and reconstruction parameters minimally impact recognition accuracy, but delay time post-injection is significant.

PMID:39141195 | DOI:10.1007/s11307-024-01943-9

Oral Radiol. 2024 Aug 14. doi: 10.1007/s11282-024-00770-6. Online ahead of print.

ABSTRACT

OBJECTIVES: This study aimed to train a 3D U-Net convolutional neural network (CNN) for mandible and lower dentition segmentation from cone-beam computed tomography (CBCT) scans.

METHODS: In an ambispective cross-sectional design, CBCT scans from two hospitals (2009-2019 and 2021-2022) constituted an internal dataset and external validation set, respectively. Manual segmentation informed CNN training, and evaluations employed Dice similarity coefficient (DSC) for volumetric accuracy. A blinded oral maxillofacial surgeon performed qualitative grading of CBCT scans and object meshes. Statistical analyses included independent t-tests and ANOVA tests to compare DSC across patient subgroups of gender, race, body mass index (BMI), test dataset used, age, and degree of metal artifact. Tests were powered for a minimum detectable difference in DSC of 0.025, with alpha of 0.05 and power level of 0.8.

RESULTS: 648 CBCT scans from 490 patients were included in the study. The CNN achieved high accuracy (average DSC: 0.945 internal, 0.940 external). No DSC differences were observed between test set used, gender, BMI, and race. Significant differences in DSC were identified based on age group and the degree of metal artifact. The majority (80%) of object meshes produced by both manual and automatic segmentation were rated as acceptable or higher quality.

CONCLUSION: We developed a model for automatic mandible and lower dentition segmentation from CBCT scans in a demographically diverse cohort including a high degree of metal artifacts. The model demonstrated good accuracy on internal and external test sets, with majority acceptable quality from a clinical grader.

PMID:39141154 | DOI:10.1007/s11282-024-00770-6

Radiol Artif Intell. 2024 Aug 14:e230391. doi: 10.1148/ryai.230391. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a deep learning algorithm that uses temporal information to improve the performance of a previously published framework of cancer lesion detection for digital breast tomosynthesis (DBT). Materials and Methods This retrospective study analyzed the current and the 1-year prior Hologic DBT screening examinations from 8 different institutions between 2016 to 2020. The dataset contained 973 cancer and 7123 noncancer cases. The front-end of this algorithm was an existing deep learning framework that performed singleview lesion detection followed by ipsilateral view matching. For this study, PriorNet was implemented as a cascaded deep learning module that used the additional growth information to refine the final probability of malignancy. Data from seven of the eight sites were used for training and validation, while the eighth site was reserved for external testing. Model performance was evaluated using localization receiver operating characteristic (ROC) curves. Results On the validation set, PriorNet showed an area under the ROC curve (AUC) of 0.931 (95% CI 0.930- 0.931), which outperformed both baseline models using single-view detection (AUC, 0.892 (95% CI 0.891-0.892), P < .001) and ipsilateral matching (AUC, 0.915 (95% CI 0.914-0.915), P < .001). On the external test set, PriorNet achieved an AUC of 0.896 (95% CI 0.885-0.896), outperforming both baselines (AUCs, 0.846 (95% CI 0.846-0.847, P < .001) and 0.865 (95% CI 0.865-0.866) P < .001, respectively). In the high sensitivity range of 0.9 to 1.0, the partial AUC of PriorNet was significantly higher (P < .001) relative to both baselines. Conclusion PriorNet using temporal information further improved the breast cancer detection performance of an existing DBT cancer detection framework. ©RSNA, 2024.

PMID:39140867 | DOI:10.1148/ryai.230391

Med Phys. 2024 Aug 14. doi: 10.1002/mp.17349. Online ahead of print.

ABSTRACT

BACKGROUND: Fluoroscopy guided interventions (FGIs) pose a risk of prolonged radiation exposure; personalized patient dosimetry is necessary to improve patient safety during these procedures. However, current FGIs systems do not capture the precise exposure regions of the patient, making it challenging to perform patient-procedure-specific dosimetry. Thus, there is a pressing need to develop approaches to extract and use this information to enable personalized radiation dosimetry for interventional procedures.

PURPOSE: To propose a deep learning (DL) approach for the automatic localization of 3D anatomical landmarks on randomly collimated and magnified 2D head fluoroscopy images.

MATERIALS AND METHODS: The model was developed with datasets comprising 800 000 pseudo 2D synthetic images (mixture of vessel-enhanced and non-enhancement), each with 55 annotated anatomical landmarks (two are landmarks for eye lenses), generated from 135 retrospectively collected head computed tomography (CT) volumetric data. Before training, dynamic random cropping was performed to mimic the varied field-size collimation in FGI procedures. Gaussian-distributed additive noise was applied to each individual image to enhance the robustness of the DL model in handling image degradation that may occur during clinical image acquisition in a clinical environment. The model was trained with 629 370 synthetic images for approximately 275 000 iterations and evaluated against a synthetic image test set and a clinical fluoroscopy test set.

RESULTS: The model shows good performance in estimating in- and out-of-image landmark positions and shows feasibility to instantiate the skull shape. The model successfully detected 96.4% and 92.5% 2D and 3D landmarks, respectively, within a 10 mm error on synthetic test images. It demonstrated an average of 3.6 ± 2.3 mm mean radial error and successfully detected 96.8% 2D landmarks within 10 mm error on clinical fluoroscopy images.

CONCLUSION: Our deep-learning model successfully localizes anatomical landmarks and estimates the gross shape of skull structures from collimated 2D projection views. This method may help identify the exposure region required for patient-specific organ dosimetry in FGIs procedures.

PMID:39140650 | DOI:10.1002/mp.17349

Acta Cir Bras. 2024 Aug 12;39:e394224. doi: 10.1590/acb394224. eCollection 2024.

ABSTRACT

PURPOSE: Amid rising health awareness, natural products which has milder effects than medical drugs are becoming popular. However, only few systems can quantitatively assess their impact on living organisms. Therefore, we developed a deep-learning system to automate the counting of cells in a gerbil model, aiming to assess a natural product's effectiveness against ischemia.

METHODS: The image acquired from paraffin blocks containing gerbil brains was analyzed by a deep-learning model (fine-tuned Detectron2).

RESULTS: The counting system achieved a 79%-positive predictive value and 85%-sensitivity when visual judgment by an expert was used as ground truth.

CONCLUSIONS: Our system evaluated hydrogen water's potential against ischemia and found it potentially useful, which is consistent with expert assessment. Due to natural product's milder effects, large data sets are needed for evaluation, making manual measurement labor-intensive. Hence, our system offers a promising new approach for evaluating natural products.

PMID:39140525 | DOI:10.1590/acb394224

Anal Methods. 2024 Aug 14. doi: 10.1039/d4ay00602j. Online ahead of print.

ABSTRACT

Raman spectroscopy is widely used for substance identification, providing molecular information from various components along with noise and instrument interference. Consequently, identifying components based on Raman spectra remains challenging. In this study, we collected Raman spectral data of 474 hazardous chemical substances using a portable Raman spectrometer, resulting in a dataset of 59 468 spectra. Our research employed a deep neural convolutional network based on the ResNet architecture, incorporating an attention mechanism called the SE module. By enhancing the weighting of certain spectral features, the performance of the model was significantly improved. We also investigated the classification predictive performance of the model under small-sample conditions, facilitating the addition of new hazardous chemical categories for future deployment on mobile devices. Additionally, we explored the features extracted by the convolutional neural network from Raman spectra, considering both Raman intensity and Raman shift aspects. We discovered that the neural network did not solely rely on intensity or shift for substance classification, but rather effectively combined both aspects. This research contributes to the advancement of Raman spectroscopy applications for hazardous chemical identification, particularly in scenarios with limited data availability. The findings shed light on the significance of spectral features in the model's decision-making process and have implications for broader applications of deep learning techniques in Raman spectroscopy-based substance identification.

PMID:39140306 | DOI:10.1039/d4ay00602j

Yi Chuan. 2024 Aug;46(8):661-669. doi: 10.16288/j.yczz.24-102.

ABSTRACT

The identification of enzyme functions plays a crucial role in understanding the mechanisms of biological activities and advancing the development of life sciences. However, existing enzyme EC number prediction methods did not fully utilize protein sequence information and still had shortcomings in identification accuracy. To address this issue, we proposed an EC number prediction network using hierarchical features and global features (ECPN-HFGF). This method first utilized residual networks to extract generic features from protein sequences, and then employed hierarchical feature extraction modules and global feature extraction modules to further extract hierarchical and global features of protein sequences. Subsequently, the prediction results of both feature types were combined, and a multitask learning framework was utilized to achieve accurate prediction of enzyme EC numbers. Experimental results indicated that the ECPN-HFGF method performed best in the task of predicting EC numbers for protein sequences, achieving macro F1 and micro F1 scores of 95.5% and 99.0%, respectively. The ECPN-HFGF method effectively combined hierarchical and global features of protein sequences, allowing for rapid and accurate EC number prediction. Compared to current commonly used methods, this method offers significantly higher prediction accuracy, providing an efficient approach for the advancement of enzymology research and enzyme engineering applications.

PMID:39140146 | DOI:10.16288/j.yczz.24-102

Perspect Clin Res. 2024 Jul-Sep;15(3):108-115. doi: 10.4103/picr.picr_196_23. Epub 2023 Dec 19.

ABSTRACT

Chat generative pretrained transformer (ChatGPT) is a conversational language model powered by artificial intelligence (AI). It is a sophisticated language model that employs deep learning methods to generate human-like text outputs to inputs in the natural language. This narrative review aims to shed light on ethical concerns about using AI models like ChatGPT in writing assistance in the health care and medical domains. Currently, all the AI models like ChatGPT are in the infancy stage; there is a risk of inaccuracy of the generated content, lack of contextual understanding, dynamic knowledge gaps, limited discernment, lack of responsibility and accountability, issues of privacy, data security, transparency, and bias, lack of nuance, and originality. Other issues such as authorship, unintentional plagiarism, falsified and fabricated content, and the threat of being red-flagged as AI-generated content highlight the need for regulatory compliance, transparency, and disclosure. If the legitimate issues are proactively considered and addressed, the potential applications of AI models as writing assistance could be rewarding.

PMID:39140014 | PMC:PMC11318783 | DOI:10.4103/picr.picr_196_23

J Infrastruct Preserv Resil. 2024;5(1):10. doi: 10.1186/s43065-024-00102-2. Epub 2024 Aug 11.

ABSTRACT

Structural elements undergo multiple levels of damage at various locations due to environments and critical loading conditions. The level of damage and its location can be predicted using acoustic emission (AE) waveforms that are captured from the generation of inherent microcracks. Existing AE methods are reliant on the feature selection of the captured waveforms and may be subjective in nature. To automate this process, this paper proposes a deep-learning model to predict the damage severity and its expected location using AE waveforms. The model is based on a densely connected convolutional neural network (CNN) that offers superior feature extraction and minimal training data requirements. Time-domain AE waveforms are used as inputs of the proposed model to automate the process of predicting the severity of damage and identifying the expected location of the damage in structural elements. The proposed approach is validated using AE data collected from a concrete beam and a wooden beam and plate. The results show the capability of the proposed method for predicting the level of damage with an accuracy range of 92-95% and identifying the approximate location of damage with 90-100% accuracy. Thus, the proposed method serves as a robust technique for damage severity prediction and localization in civil structures.

PMID:39140005 | PMC:PMC11317450 | DOI:10.1186/s43065-024-00102-2

Data Eng Med Imaging (2023). 2023 Oct;14314:91-101. doi: 10.1007/978-3-031-44992-5_9. Epub 2023 Oct 1.

ABSTRACT

Due to limited direct organ visualization, minimally invasive interventions rely extensively on medical imaging and image guidance to ensure accurate surgical instrument navigation and target tissue manipulation. In the context of laparoscopic liver interventions, intra-operative video imaging only provides a limited field-of-view of the liver surface, with no information of any internal liver lesions identified during diagnosis using pre-procedural imaging. Hence, to enhance intra-procedural visualization and navigation, the registration of pre-procedural, diagnostic images and anatomical models featuring target tissues to be accessed or manipulated during surgery entails a sufficient accurate registration of the pre-procedural data into the intra-operative setting. Prior work has demonstrated the feasibility of neural network-based solutions for nonrigid volume-to-surface liver registration. However, view occlusion, lack of meaningful feature landmarks, and liver deformation between the pre- and intra-operative settings all contribute to the difficulty of this registration task. In this work, we leverage some of the state-of-the-art deep learning frameworks to implement and test various network architecture modifications toward improving the accuracy and robustness of volume-to-surface liver registration. Specifically, we focus on the adaptation of a transformer-based segmentation network for the task of better predicting the optimal displacement field for nonrigid registration. Our results suggest that one particular transformer-based network architecture-UTNet-led to significant improvements over baseline performance, yielding a mean displacement error on the order of 4 mm across a variety of datasets.

PMID:39139984 | PMC:PMC11318296 | DOI:10.1007/978-3-031-44992-5_9

J Arrhythm. 2024 Jun 21;40(4):948-957. doi: 10.1002/joa3.13096. eCollection 2024 Aug.

ABSTRACT

BACKGROUND: Predicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application.

METHODS: The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician's careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research.

RESULTS: The evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician's assessment.

CONCLUSIONS: The feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.

PMID:39139876 | PMC:PMC11317653 | DOI:10.1002/joa3.13096