Sci Rep. 2024 Jun 14;14(1):13707. doi: 10.1038/s41598-024-61879-6.

ABSTRACT

Determining the fundamental characteristics that define a face as "feminine" or "masculine" has long fascinated anatomists and plastic surgeons, particularly those involved in aesthetic and gender-affirming surgery. Previous studies in this area have relied on manual measurements, comparative anatomy, and heuristic landmark-based feature extraction. In this study, we collected retrospectively at Cedars Sinai Medical Center (CSMC) a dataset of 98 skull samples, which is the first dataset of this kind of 3D medical imaging. We then evaluated the accuracy of multiple deep learning neural network architectures on sex classification with this dataset. Specifically, we evaluated methods representing three different 3D data modeling approaches: Resnet3D, PointNet++, and MeshNet. Despite the limited number of imaging samples, our testing results show that all three approaches achieve AUC scores above 0.9 after convergence. PointNet++ exhibits the highest accuracy, while MeshNet has the lowest. Our findings suggest that accuracy is not solely dependent on the sparsity of data representation but also on the architecture design, with MeshNet's lower accuracy likely due to the lack of a hierarchical structure for progressive data abstraction. Furthermore, we studied a problem related to sex determination, which is the analysis of the various morphological features that affect sex classification. We proposed and developed a new method based on morphological gradients to visualize features that influence model decision making. The method based on morphological gradients is an alternative to the standard saliency map, and the new method provides better visualization of feature importance. Our study is the first to develop and evaluate deep learning models for analyzing 3D facial skull images to identify imaging feature differences between individuals assigned male or female at birth. These findings may be useful for planning and evaluating craniofacial surgery, particularly gender-affirming procedures, such as facial feminization surgery.

PMID:38877045 | DOI:10.1038/s41598-024-61879-6

Eur J Radiol. 2024 Jun 9;177:111556. doi: 10.1016/j.ejrad.2024.111556. Online ahead of print.

ABSTRACT

PURPOSE: To conduct the fusion of radiomics and deep transfer learning features from the intratumoral and peritumoral areas in breast DCE-MRI images to differentiate between benign and malignant breast tumors, and to compare the diagnostic accuracy of this fusion model against the assessments made by experienced radiologists.

MATERIALS AND METHODS: This multi-center study conducted a retrospective analysis of DCE-MRI images from 330 women diagnosed with breast cancer, with 138 cases categorized as benign and 192 as malignant. The training and internal testing sets comprised 270 patients from center 1, while the external testing cohort consisted of 60 patients from center 2. A fusion feature set consisting of radiomics features and deep transfer learning features was constructed from both intratumoral (ITR) and peritumoral (PTR) areas. The Least absolute shrinkage and selection operator (LASSO) based support vector machine was chosen as the classifier by comparing its performance with five other machine learning models. The diagnostic performance and clinical usefulness of fusion model were verified and assessed through the area under the receiver operating characteristics (ROC) and decision curve analysis. Additionally, the performance of the fusion model was compared with the diagnostic assessments of two experienced radiologists to evaluate its relative accuracy. The study strictly adhered to CLEAR and METRICS guidelines for standardization to ensure rigorous and reproducible methods.

RESULTS: The findings show that the fusion model, utilizing radiomics and deep transfer learning features from the ITR and PTR, exhibited exceptional performance in classifying breast tumors, achieving AUCs of 0.950 in the internal testing set and 0.921 in the external testing set. This performance significantly surpasses that of models relying on singular regional radiomics or deep transfer learning features alone. Moreover, the fusion model demonstrated superior diagnostic accuracy compared to the evaluations conducted by two experienced radiologists, thereby highlighting its potential to support and enhance clinical decision-making in the differentiation of benign and malignant breast tumors.

CONCLUSION: The fusion model, combining multi-regional radiomics with deep transfer learning features, not only accurately differentiates between benign and malignant breast tumors but also outperforms the diagnostic assessments made by experienced radiologists. This underscores the model's potential as a valuable tool for improving the accuracy and reliability of breast tumor diagnosis.

PMID:38875748 | DOI:10.1016/j.ejrad.2024.111556

JMIR Biomed Eng. 2024 Feb 2;9:e48497. doi: 10.2196/48497.

ABSTRACT

BACKGROUND: Venovenous extracorporeal membrane oxygenation (VV-ECMO) is a therapy for patients with refractory respiratory failure. The decision to decannulate someone from extracorporeal membrane oxygenation (ECMO) often involves weaning trials and clinical intuition. To date, there are limited prognostication metrics to guide clinical decision-making to determine which patients will be successfully weaned and decannulated.

OBJECTIVE: This study aims to assist clinicians with the decision to decannulate a patient from ECMO, using Continuous Evaluation of VV-ECMO Outcomes (CEVVO), a deep learning-based model for predicting success of decannulation in patients supported on VV-ECMO. The running metric may be applied daily to categorize patients into high-risk and low-risk groups. Using these data, providers may consider initiating a weaning trial based on their expertise and CEVVO.

METHODS: Data were collected from 118 patients supported with VV-ECMO at the Columbia University Irving Medical Center. Using a long short-term memory-based network, CEVVO is the first model capable of integrating discrete clinical information with continuous data collected from an ECMO device. A total of 12 sets of 5-fold cross validations were conducted to assess the performance, which was measured using the area under the receiver operating characteristic curve (AUROC) and average precision (AP). To translate the predicted values into a clinically useful metric, the model results were calibrated and stratified into risk groups, ranging from 0 (high risk) to 3 (low risk). To further investigate the performance edge of CEVVO, 2 synthetic data sets were generated using Gaussian process regression. The first data set preserved the long-term dependency of the patient data set, whereas the second did not.

RESULTS: CEVVO demonstrated consistently superior classification performance compared with contemporary models (P<.001 and P=.04 compared with the next highest AUROC and AP). Although the model's patient-by-patient predictive power may be too low to be integrated into a clinical setting (AUROC 95% CI 0.6822-0.7055; AP 95% CI 0.8515-0.8682), the patient risk classification system displayed greater potential. When measured at 72 hours, the high-risk group had a successful decannulation rate of 58% (7/12), whereas the low-risk group had a successful decannulation rate of 92% (11/12; P=.04). When measured at 96 hours, the high- and low-risk groups had a successful decannulation rate of 54% (6/11) and 100% (9/9), respectively (P=.01). We hypothesized that the improved performance of CEVVO was owing to its ability to efficiently capture transient temporal patterns. Indeed, CEVVO exhibited improved performance on synthetic data with inherent temporal dependencies (P<.001) compared with logistic regression and a dense neural network.

CONCLUSIONS: The ability to interpret and integrate large data sets is paramount for creating accurate models capable of assisting clinicians in risk stratifying patients supported on VV-ECMO. Our framework may guide future incorporation of CEVVO into more comprehensive intensive care monitoring systems.

PMID:38875691 | DOI:10.2196/48497

JMIR Biomed Eng. 2024 Mar 21;9:e56245. doi: 10.2196/56245.

ABSTRACT

BACKGROUND: The digital era has witnessed an escalating dependence on digital platforms for news and information, coupled with the advent of "deepfake" technology. Deepfakes, leveraging deep learning models on extensive data sets of voice recordings and images, pose substantial threats to media authenticity, potentially leading to unethical misuse such as impersonation and the dissemination of false information.

OBJECTIVE: To counteract this challenge, this study aims to introduce the concept of innate biological processes to discern between authentic human voices and cloned voices. We propose that the presence or absence of certain perceptual features, such as pauses in speech, can effectively distinguish between cloned and authentic audio.

METHODS: A total of 49 adult participants representing diverse ethnic backgrounds and accents were recruited. Each participant contributed voice samples for the training of up to 3 distinct voice cloning text-to-speech models and 3 control paragraphs. Subsequently, the cloning models generated synthetic versions of the control paragraphs, resulting in a data set consisting of up to 9 cloned audio samples and 3 control samples per participant. We analyzed the speech pauses caused by biological actions such as respiration, swallowing, and cognitive processes. Five audio features corresponding to speech pause profiles were calculated. Differences between authentic and cloned audio for these features were assessed, and 5 classical machine learning algorithms were implemented using these features to create a prediction model. The generalization capability of the optimal model was evaluated through testing on unseen data, incorporating a model-naive generator, a model-naive paragraph, and model-naive participants.

RESULTS: Cloned audio exhibited significantly increased time between pauses (P<.001), decreased variation in speech segment length (P=.003), increased overall proportion of time speaking (P=.04), and decreased rates of micro- and macropauses in speech (both P=.01). Five machine learning models were implemented using these features, with the AdaBoost model demonstrating the highest performance, achieving a 5-fold cross-validation balanced accuracy of 0.81 (SD 0.05). Other models included support vector machine (balanced accuracy 0.79, SD 0.03), random forest (balanced accuracy 0.78, SD 0.04), logistic regression, and decision tree (balanced accuracies 0.76, SD 0.10 and 0.72, SD 0.06). When evaluating the optimal AdaBoost model, it achieved an overall test accuracy of 0.79 when predicting unseen data.

CONCLUSIONS: The incorporation of perceptual, biological features into machine learning models demonstrates promising results in distinguishing between authentic human voices and cloned audio.

PMID:38875685 | DOI:10.2196/56245

JMIR AI. 2024 May 31;3:e58342. doi: 10.2196/58342.

ABSTRACT

BACKGROUND: The integration of artificial intelligence (AI), particularly deep learning models, has transformed the landscape of medical technology, especially in the field of diagnosis using imaging and physiological data. In otolaryngology, AI has shown promise in image classification for middle ear diseases. However, existing models often lack patient-specific data and clinical context, limiting their universal applicability. The emergence of GPT-4 Vision (GPT-4V) has enabled a multimodal diagnostic approach, integrating language processing with image analysis.

OBJECTIVE: In this study, we investigated the effectiveness of GPT-4V in diagnosing middle ear diseases by integrating patient-specific data with otoscopic images of the tympanic membrane.

METHODS: The design of this study was divided into two phases: (1) establishing a model with appropriate prompts and (2) validating the ability of the optimal prompt model to classify images. In total, 305 otoscopic images of 4 middle ear diseases (acute otitis media, middle ear cholesteatoma, chronic otitis media, and otitis media with effusion) were obtained from patients who visited Shinshu University or Jichi Medical University between April 2010 and December 2023. The optimized GPT-4V settings were established using prompts and patients' data, and the model created with the optimal prompt was used to verify the diagnostic accuracy of GPT-4V on 190 images. To compare the diagnostic accuracy of GPT-4V with that of physicians, 30 clinicians completed a web-based questionnaire consisting of 190 images.

RESULTS: The multimodal AI approach achieved an accuracy of 82.1%, which is superior to that of certified pediatricians at 70.6%, but trailing behind that of otolaryngologists at more than 95%. The model's disease-specific accuracy rates were 89.2% for acute otitis media, 76.5% for chronic otitis media, 79.3% for middle ear cholesteatoma, and 85.7% for otitis media with effusion, which highlights the need for disease-specific optimization. Comparisons with physicians revealed promising results, suggesting the potential of GPT-4V to augment clinical decision-making.

CONCLUSIONS: Despite its advantages, challenges such as data privacy and ethical considerations must be addressed. Overall, this study underscores the potential of multimodal AI for enhancing diagnostic accuracy and improving patient care in otolaryngology. Further research is warranted to optimize and validate this approach in diverse clinical settings.

PMID:38875669 | DOI:10.2196/58342

JMIR AI. 2024 May 20;3:e47805. doi: 10.2196/47805.

ABSTRACT

BACKGROUND: Passive mobile sensing provides opportunities for measuring and monitoring health status in the wild and outside of clinics. However, longitudinal, multimodal mobile sensor data can be small, noisy, and incomplete. This makes processing, modeling, and prediction of these data challenging. The small size of the data set restricts it from being modeled using complex deep learning networks. The current state of the art (SOTA) tackles small sensor data sets following a singular modeling paradigm based on traditional machine learning (ML) algorithms. These opt for either a user-agnostic modeling approach, making the model susceptible to a larger degree of noise, or a personalized approach, where training on individual data alludes to a more limited data set, giving rise to overfitting, therefore, ultimately, having to seek a trade-off by choosing 1 of the 2 modeling approaches to reach predictions.

OBJECTIVE: The objective of this study was to filter, rank, and output the best predictions for small, multimodal, longitudinal sensor data using a framework that is designed to tackle data sets that are limited in size (particularly targeting health studies that use passive multimodal sensors) and that combines both user agnostic and personalized approaches, along with a combination of ranking strategies to filter predictions.

METHODS: In this paper, we introduced a novel ranking framework for longitudinal multimodal sensors (FLMS) to address challenges encountered in health studies involving passive multimodal sensors. Using the FLMS, we (1) built a tensor-based aggregation and ranking strategy for final interpretation, (2) processed various combinations of sensor fusions, and (3) balanced user-agnostic and personalized modeling approaches with appropriate cross-validation strategies. The performance of the FLMS was validated with the help of a real data set of adolescents diagnosed with major depressive disorder for the prediction of change in depression in the adolescent participants.

RESULTS: Predictions output by the proposed FLMS achieved a 7% increase in accuracy and a 13% increase in recall for the real data set. Experiments with existing SOTA ML algorithms showed an 11% increase in accuracy for the depression data set and how overfitting and sparsity were handled.

CONCLUSIONS: The FLMS aims to fill the gap that currently exists when modeling passive sensor data with a small number of data points. It achieves this through leveraging both user-agnostic and personalized modeling techniques in tandem with an effective ranking strategy to filter predictions.

PMID:38875667 | DOI:10.2196/47805

JMIR AI. 2024 May 10;3:e52171. doi: 10.2196/52171.

ABSTRACT

BACKGROUND: There are a wide range of potential adverse health effects, ranging from headaches to cardiovascular disease, associated with long-term negative emotions and chronic stress. Because many indicators of stress are imperceptible to observers, the early detection of stress remains a pressing medical need, as it can enable early intervention. Physiological signals offer a noninvasive method for monitoring affective states and are recorded by a growing number of commercially available wearables.

OBJECTIVE: We aim to study the differences between personalized and generalized machine learning models for 3-class emotion classification (neutral, stress, and amusement) using wearable biosignal data.

METHODS: We developed a neural network for the 3-class emotion classification problem using data from the Wearable Stress and Affect Detection (WESAD) data set, a multimodal data set with physiological signals from 15 participants. We compared the results between a participant-exclusive generalized, a participant-inclusive generalized, and a personalized deep learning model.

RESULTS: For the 3-class classification problem, our personalized model achieved an average accuracy of 95.06% and an F1-score of 91.71%; our participant-inclusive generalized model achieved an average accuracy of 66.95% and an F1-score of 42.50%; and our participant-exclusive generalized model achieved an average accuracy of 67.65% and an F1-score of 43.05%.

CONCLUSIONS: Our results emphasize the need for increased research in personalized emotion recognition models given that they outperform generalized models in certain contexts. We also demonstrate that personalized machine learning models for emotion classification are viable and can achieve high performance.

PMID:38875573 | DOI:10.2196/52171

JMIR AI. 2023 Jun 6;2:e44835. doi: 10.2196/44835.

ABSTRACT

BACKGROUND: With the growing volume and complexity of laboratory repositories, it has become tedious to parse unstructured data into structured and tabulated formats for secondary uses such as decision support, quality assurance, and outcome analysis. However, advances in natural language processing (NLP) approaches have enabled efficient and automated extraction of clinically meaningful medical concepts from unstructured reports.

OBJECTIVE: In this study, we aimed to determine the feasibility of using the NLP model for information extraction as an alternative approach to a time-consuming and operationally resource-intensive handcrafted rule-based tool. Therefore, we sought to develop and evaluate a deep learning-based NLP model to derive knowledge and extract information from text-based laboratory reports sourced from a provincial laboratory repository system.

METHODS: The NLP model, a hierarchical multilabel classifier, was trained on a corpus of laboratory reports covering testing for 14 different respiratory viruses and viral subtypes. The corpus includes 87,500 unique laboratory reports annotated by 8 subject matter experts (SMEs). The classification task involved assigning the laboratory reports to labels at 2 levels: 24 fine-grained labels in level 1 and 6 coarse-grained labels in level 2. A "label" also refers to the status of a specific virus or strain being tested or detected (eg, influenza A is detected). The model's performance stability and variation were analyzed across all labels in the classification task. Additionally, the model's generalizability was evaluated internally and externally on various test sets.

RESULTS: Overall, the NLP model performed well on internal, out-of-time (pre-COVID-19), and external (different laboratories) test sets with microaveraged F1-scores >94% across all classes. Higher precision and recall scores with less variability were observed for the internal and pre-COVID-19 test sets. As expected, the model's performance varied across categories and virus types due to the imbalanced nature of the corpus and sample sizes per class. There were intrinsically fewer classes of viruses being detected than those tested; therefore, the model's performance (lowest F1-score of 57%) was noticeably lower in the detected cases.

CONCLUSIONS: We demonstrated that deep learning-based NLP models are promising solutions for information extraction from text-based laboratory reports. These approaches enable scalable, timely, and practical access to high-quality and encoded laboratory data if integrated into laboratory information system repositories.

PMID:38875570 | DOI:10.2196/44835

JMIR AI. 2023 Sep 8;2:e44909. doi: 10.2196/44909.

ABSTRACT

BACKGROUND: Accurate projections of procedural case durations are complex but critical to the planning of perioperative staffing, operating room resources, and patient communication. Nonlinear prediction models using machine learning methods may provide opportunities for hospitals to improve upon current estimates of procedure duration.

OBJECTIVE: The aim of this study was to determine whether a machine learning algorithm scalable across multiple centers could make estimations of case duration within a tolerance limit because there are substantial resources required for operating room functioning that relate to case duration.

METHODS: Deep learning, gradient boosting, and ensemble machine learning models were generated using perioperative data available at 3 distinct time points: the time of scheduling, the time of patient arrival to the operating or procedure room (primary model), and the time of surgical incision or procedure start. The primary outcome was procedure duration, defined by the time between the arrival and the departure of the patient from the procedure room. Model performance was assessed by mean absolute error (MAE), the proportion of predictions falling within 20% of the actual duration, and other standard metrics. Performance was compared with a baseline method of historical means within a linear regression model. Model features driving predictions were assessed using Shapley additive explanations values and permutation feature importance.

RESULTS: A total of 1,177,893 procedures from 13 academic and private hospitals between 2016 and 2019 were used. Across all procedures, the median procedure duration was 94 (IQR 50-167) minutes. In estimating the procedure duration, the gradient boosting machine was the best-performing model, demonstrating an MAE of 34 (SD 47) minutes, with 46% of the predictions falling within 20% of the actual duration in the test data set. This represented a statistically and clinically significant improvement in predictions compared with a baseline linear regression model (MAE 43 min; P<.001; 39% of the predictions falling within 20% of the actual duration). The most important features in model training were historical procedure duration by surgeon, the word "free" within the procedure text, and the time of day.

CONCLUSIONS: Nonlinear models using machine learning techniques may be used to generate high-performing, automatable, explainable, and scalable prediction models for procedure duration.

PMID:38875567 | DOI:10.2196/44909

JMIR AI. 2023 Jun 1;2:e44537. doi: 10.2196/44537.

ABSTRACT

BACKGROUND: Ground-glass opacities (GGOs) appearing in computed tomography (CT) scans may indicate potential lung malignancy. Proper management of GGOs based on their features can prevent the development of lung cancer. Electronic health records are rich sources of information on GGO nodules and their granular features, but most of the valuable information is embedded in unstructured clinical notes.

OBJECTIVE: We aimed to develop, test, and validate a deep learning-based natural language processing (NLP) tool that automatically extracts GGO features to inform the longitudinal trajectory of GGO status from large-scale radiology notes.

METHODS: We developed a bidirectional long short-term memory with a conditional random field-based deep-learning NLP pipeline to extract GGO and granular features of GGO retrospectively from radiology notes of 13,216 lung cancer patients. We evaluated the pipeline with quality assessments and analyzed cohort characterization of the distribution of nodule features longitudinally to assess changes in size and solidity over time.

RESULTS: Our NLP pipeline built on the GGO ontology we developed achieved between 95% and 100% precision, 89% and 100% recall, and 92% and 100% F1-scores on different GGO features. We deployed this GGO NLP model to extract and structure comprehensive characteristics of GGOs from 29,496 radiology notes of 4521 lung cancer patients. Longitudinal analysis revealed that size increased in 16.8% (240/1424) of patients, decreased in 14.6% (208/1424), and remained unchanged in 68.5% (976/1424) in their last note compared to the first note. Among 1127 patients who had longitudinal radiology notes of GGO status, 815 (72.3%) were reported to have stable status, and 259 (23%) had increased/progressed status in the subsequent notes.

CONCLUSIONS: Our deep learning-based NLP pipeline can automatically extract granular GGO features at scale from electronic health records when this information is documented in radiology notes and help inform the natural history of GGO. This will open the way for a new paradigm in lung cancer prevention and early detection.

PMID:38875565 | DOI:10.2196/44537

JMIR AI. 2023 Dec 19;2:e45770. doi: 10.2196/45770.

ABSTRACT

BACKGROUND: The utilization of artificial intelligence (AI) technologies in the biomedical field has attracted increasing attention in recent decades. Studying how past AI technologies have found their way into medicine over time can help to predict which current (and future) AI technologies have the potential to be utilized in medicine in the coming years, thereby providing a helpful reference for future research directions.

OBJECTIVE: The aim of this study was to predict the future trend of AI technologies used in different biomedical domains based on past trends of related technologies and biomedical domains.

METHODS: We collected a large corpus of articles from the PubMed database pertaining to the intersection of AI and biomedicine. Initially, we attempted to use regression on the extracted keywords alone; however, we found that this approach did not provide sufficient information. Therefore, we propose a method called "background-enhanced prediction" to expand the knowledge utilized by the regression algorithm by incorporating both the keywords and their surrounding context. This method of data construction resulted in improved performance across the six regression models evaluated. Our findings were confirmed through experiments on recurrent prediction and forecasting.

RESULTS: In our analysis using background information for prediction, we found that a window size of 3 yielded the best results, outperforming the use of keywords alone. Furthermore, utilizing data only prior to 2017, our regression projections for the period of 2017-2021 exhibited a high coefficient of determination (R2), which reached up to 0.78, demonstrating the effectiveness of our method in predicting long-term trends. Based on the prediction, studies related to proteins and tumors will be pushed out of the top 20 and become replaced by early diagnostics, tomography, and other detection technologies. These are certain areas that are well-suited to incorporate AI technology. Deep learning, machine learning, and neural networks continue to be the dominant AI technologies in biomedical applications. Generative adversarial networks represent an emerging technology with a strong growth trend.

CONCLUSIONS: In this study, we explored AI trends in the biomedical field and developed a predictive model to forecast future trends. Our findings were confirmed through experiments on current trends.

PMID:38875563 | DOI:10.2196/45770

J Imaging Inform Med. 2024 Jun 14. doi: 10.1007/s10278-024-01154-2. Online ahead of print.

ABSTRACT

Retinal diseases stand as a primary cause of childhood blindness. Analyzing the progression of these diseases requires close attention to lesion morphology and spatial information. Standard image registration methods fail to accurately reconstruct pediatric fundus images containing significant distortion and blurring. To address this challenge, we proposed a robust deep learning-based image registration method (RDLR). The method consisted of two modules: registration module (RM) and panoramic view module (PVM). RM effectively integrated global and local feature information and learned prior information related to the orientation of images. PVM was capable of reconstructing spatial information in panoramic images. Furthermore, as the registration model was trained on over 280,000 pediatric fundus images, we introduced a registration annotation automatic generation process coupled with a quality control module to ensure the reliability of training data. We compared the performance of RDLR to the other methods, including conventional registration pipeline (CRP), voxel morph (WM), generalizable image matcher (GIM), and self-supervised techniques (SS). RDLR achieved significantly higher registration accuracy (average Dice score of 0.948) than the other methods (ranging from 0.491 to 0.802). The resulting panoramic retinal maps reconstructed by RDLR also demonstrated substantially higher fidelity (average Dice score of 0.960) compared to the other methods (ranging from 0.720 to 0.783). Overall, the proposed method addressed key challenges in pediatric retinal imaging, providing an effective solution to enhance disease diagnosis. Our source code is available at https://github.com/wuwusky/RobustDeepLeraningRegistration .

PMID:38874699 | DOI:10.1007/s10278-024-01154-2

J Chem Inf Model. 2024 Jun 14. doi: 10.1021/acs.jcim.4c00295. Online ahead of print.

ABSTRACT

Anticancer peptides (ACPs) play a vital role in selectively targeting and eliminating cancer cells. Evaluating and comparing predictions from various machine learning (ML) and deep learning (DL) techniques is challenging but crucial for anticancer drug research. We conducted a comprehensive analysis of 15 ML and 10 DL models, including the models released after 2022, and found that support vector machines (SVMs) with feature combination and selection significantly enhance overall performance. DL models, especially convolutional neural networks (CNNs) with light gradient boosting machine (LGBM) based feature selection approaches, demonstrate improved characterization. Assessment using a new test data set (ACP10) identifies ACPred, MLACP 2.0, AI4ACP, mACPred, and AntiCP2.0_AAC as successive optimal predictors, showcasing robust performance. Our review underscores current prediction tool limitations and advocates for an omnidirectional ACP prediction framework to propel ongoing research.

PMID:38874445 | DOI:10.1021/acs.jcim.4c00295

G3 (Bethesda). 2024 Jun 14:jkae124. doi: 10.1093/g3journal/jkae124. Online ahead of print.

ABSTRACT

Candida albicans is a major fungal pathogen of humans that can cause serious systemic infections in vulnerable immunocompromised populations. One of its virulence attributes is its capacity to transition between yeast and filamentous morphologies, but our understanding of this process remains incomplete. Here, we analyzed data from a functional genomic screen performed with the C. albicans Gene Replacement And Conditional Expression (GRACE) collection to identify genes crucial for morphogenesis in host-relevant conditions. Through manual scoring of microscopy images coupled with analysis of each image using a deep learning-based method termed Candescence, we identified 307 genes important for filamentation in tissue culture medium at 37 °C with 5% CO2. One such factor was orf19.5963, which is predicted to encode the prenyltransferase Nus1 based on sequence homology to Saccharomyces cerevisiae. We further showed that Nus1 and its predicted interacting partner Rer2 are important for filamentation in multiple liquid filament-inducing conditions as well as for wrinkly colony formation on solid agar. Finally, we highlight that Nus1 and Rer2 likely govern C. albicans morphogenesis due to their importance in intracellular trafficking, as well as maintaining lipid homeostasis. Overall, this work identifies Nus1 and Rer2 as important regulators of C. albicans filamentation and highlights the power of functional genomic screens in advancing our understanding of gene function in human fungal pathogens.

PMID:38874344 | DOI:10.1093/g3journal/jkae124

Med Phys. 2024 Jun 14. doi: 10.1002/mp.17254. Online ahead of print.

ABSTRACT

BACKGROUND: Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) stand as pivotal diagnostic tools for brain disorders, offering the potential for mutually enriching disease diagnostic perspectives. However, the costs associated with PET scans and the inherent radioactivity have limited the widespread application of PET. Furthermore, it is noteworthy to highlight the promising potential of high-field and ultra-high-field neuroimaging in cognitive neuroscience research and clinical practice. With the enhancement of MRI resolution, a related question arises: can high-resolution MRI improve the quality of PET images?

PURPOSE: This study aims to enhance the quality of synthesized PET images by leveraging the superior resolution capabilities provided by high-field and ultra-high-field MRI.

METHODS: From a statistical perspective, the joint probability distribution is considered the most direct and fundamental approach for representing the correlation between PET and MRI. In this study, we proposed a novel model, the joint diffusion attention model, namely, the joint diffusion attention model (JDAM), which primarily focuses on learning information about the joint probability distribution. JDAM consists of two primary processes: the diffusion process and the sampling process. During the diffusion process, PET gradually transforms into a Gaussian noise distribution by adding Gaussian noise, while MRI remains fixed. The central objective of the diffusion process is to learn the gradient of the logarithm of the joint probability distribution between MRI and noise PET. The sampling process operates as a predictor-corrector. The predictor initiates a reverse diffusion process, and the corrector applies Langevin dynamics.

RESULTS: Experimental results from the publicly available Alzheimer's Disease Neuroimaging Initiative dataset highlight the effectiveness of the proposed model compared to state-of-the-art (SOTA) models such as Pix2pix and CycleGAN. Significantly, synthetic PET images guided by ultra-high-field MRI exhibit marked improvements in signal-to-noise characteristics when contrasted with those generated from high-field MRI data. These results have been endorsed by medical experts, who consider the PET images synthesized through JDAM to possess scientific merit. This endorsement is based on their symmetrical features and precise representation of regions displaying hypometabolism, a hallmark of Alzheimer's disease.

CONCLUSIONS: This study establishes the feasibility of generating PET images from MRI. Synthesis of PET by JDAM significantly enhances image quality compared to SOTA models.

PMID:38874206 | DOI:10.1002/mp.17254

Curr Pharm Des. 2024 Jun 13. doi: 10.2174/0113816128308066240529121148. Online ahead of print.

ABSTRACT

Over the period of the preceding decade, artificial intelligence (AI) has proved an outstanding performance in entire dimensions of science including pharmaceutical sciences. AI uses the concept of machine learning (ML), deep learning (DL), and neural networks (NNs) approaches for novel algorithm and hypothesis development by training the machines in multiple ways. AI-based drug development from molecule identification to clinical approval tremendously reduces the cost of development and the time over conventional methods. The COVID-19 vaccine development and approval by regulatory agencies within 1-2 years is the finest example of drug development. Hence, AI is fast becoming a boon for scientific researchers to streamline their advanced discoveries. AI-based FDA-approved nanomedicines perform well as target selective, synergistic therapies, recolonize the theragnostic pharmaceutical stream, and significantly improve drug research outcomes. This comprehensive review delves into the fundamental aspects of AI along with its applications in the realm of pharmaceutical life sciences. It explores AI's role in crucial areas such as drug designing, drug discovery and development, traditional Chinese medicine, integration of multi-omics data, as well as investigations into drug repurposing and polypharmacology studies.

PMID:38874046 | DOI:10.2174/0113816128308066240529121148

Curr Med Imaging. 2024;20(1):e15734056309748. doi: 10.2174/0115734056309748240509072222.

ABSTRACT

INTRODUCTION: The aim of the study was to develop deep-learning neural networks to guide treatment decisions and for the accurate evaluation of tumor response to neoadjuvant chemoradiotherapy (nCRT) in rectal cancer using magnetic resonance (MR) images.

METHODS: Fifty-nine tumors with stage 2 or 3 rectal cancer that received nCRT were retrospectively evaluated. Pathological tumor regression grading was carried out using the Dworak (Dw-TRG) guidelines and served as the ground truth for response predictions. Imaging-based tumor regression grading was performed according to the MERCURY group guidelines from pre-treatment and post-treatment para-axial T2-weighted MR images (MR-TRG). Tumor signal intensity signatures were extracted by segmenting the tumors volumetrically on the images. Normalized histograms of the signatures were used as input to a deep neural network (DNN) housing long short-term memory (LSTM) units. The output of the network was the tumor regression grading prediction, DNN-TRG.

RESULTS: In predicting complete or good response, DNN-TRG demonstrated modest agreement with Dw-TRG (Cohen's kappa= 0.79) and achieved 84.6% sensitivity, 93.9% specificity, and 89.8% accuracy. MR-TRG revealed 46.2% sensitivity, 100% specificity, and 76.3% accuracy. In predicting a complete response, DNN-TRG showed slight agreement with Dw-TRG (Cohen's kappa= 0.75) with 71.4% sensitivity, 97.8% specificity, and 91.5% accuracy. MR-TRG provided 42.9% sensitivity, 100% specificity, and 86.4% accuracy. DNN-TRG benefited from higher sensitivity but lower specificity, leading to higher accuracy than MR-TRG in predicting tumor response.

CONCLUSION: The use of deep LSTM neural networks is a promising approach for evaluating the tumor response to nCRT in rectal cancer.</P>.

PMID:38874041 | DOI:10.2174/0115734056309748240509072222

Curr Med Imaging. 2024 Jun 13. doi: 10.2174/0115734056305633240603061644. Online ahead of print.

ABSTRACT

OBJECTIVE: The increasing longevity of the population has made Alzheimer's disease (AD) a significant public health concern. However, the challenge of accurately distinguishing different disease stages due to limited variability within the same stage and the potential for errors in manual classification highlights the need for more precise approaches to classifying AD stages. In the field of deep learning, the ResNet50V2 model stands as a testament to its exceptional capabilities in image classification tasks.

MATERIALS: The dataset employed in this study was sourced from Kaggle and consisted of 6400 MRI images that were meticulously collected and rigorously verified to assure their precision. The selection of images was conducted with great attention to detail, drawing from a diverse array of sources.

METHODS: This study focuses on harnessing the potential of this model for AD classification, a task that relies on extracting disease-specific features. Furthermore, to achieve this, a multi-class classification methodology is employed, using transfer learning and fine-tuning of layers to adapt the pre-trained ResNet50V2 model for AD classification. Notably, the impact of various input layer sizes on model performance is investigated, meticulously striking a balance between capacity and computational efficiency. The optimal fine-tuning strategy is determined by counting layers within convolution blocks and selectively unfreezing and training individual layers after a designated layer index, ensuring consistency and reproducibility. Custom classification layers, dynamic learning rate reduction, and extensive visualization techniques are incorporated.

RESULTS: The model's performance is evaluated using accuracy, AUC, precision, recall, F1-score, and ROC curves. The comprehensive analysis reveals the model's ability to discriminate between AD stages. Visualization through confusion matrices aided in understanding model behavior. The rounded predicted labels enhanced practical utility.

CONCLUSION: This approach combined empirical research and iterative refinement, resulting in enhanced accuracy and reliability in AD classification. Our model holds promise for real-world applications, achieving an accuracy of 96.18%, showcasing the potential of deep learning in addressing complex medical challenges.

PMID:38874032 | DOI:10.2174/0115734056305633240603061644

Curr Med Imaging. 2024 Jun 13. doi: 10.2174/0115734056305021240603114137. Online ahead of print.

ABSTRACT

INTRODUCTION: The second highest cause of death among males is Prostate Cancer (PCa) in America. Over the globe, it's the usual case in men, and the annual PCa ratio is very surprising. Identical to other prognosis and diagnostic medical systems, deep learning-based automated recognition and detection systems (i.e., Computer Aided Detection (CAD) systems) have gained enormous attention in PCA.

METHODS: These paradigms have attained promising results with a high segmentation, detection, and classification accuracy ratio. Numerous researchers claimed efficient results from deep learning-based approaches compared to other ordinary systems that utilized pathological samples.

RESULTS: This research is intended to perform prostate segmentation using transfer learning-based Mask R-CNN, which is consequently helpful in prostate cancer detection.

CONCLUSION: Lastly, limitations in current work, research findings, and prospects have been discussed.

PMID:38874030 | DOI:10.2174/0115734056305021240603114137

Front Public Health. 2024 May 30;12:1361901. doi: 10.3389/fpubh.2024.1361901. eCollection 2024.

ABSTRACT

With the acceleration of urbanization, the risk of urban population exposure to environmental pollutants is increasing. Protecting public health is the top priority in the construction of smart cities. The purpose of this study is to propose a method for identifying toxicological biological indicators of human exposure in smart cities based on public health data and deep learning to achieve accurate assessment and management of exposure risks. Initially, the study used a network of sensors within the smart city infrastructure to collect environmental monitoring data, including indicators such as air quality, water quality, and soil pollution. Using public health data, a database containing information on types and concentrations of environmental pollutants has been established. Convolutional neural network was used to recognize the pattern of environmental monitoring data, identify the relationship between different indicators, and build the correlation model between health indicators and environmental indicators. Identify biological indicators associated with environmental pollution exposure through training optimization. Experimental analysis showed that the prediction accuracy of the model reached 93.45%, which could provide decision support for the government and the health sector. In the recognition of the association pattern between respiratory diseases, cardiovascular diseases and environmental exposure factors such as PM2.5 and SO2, the fitting degree between the model and the simulation value reached more than 0.90. The research design model can play a positive role in public health and provide new decision-making ideas for protecting public health.

PMID:38873314 | PMC:PMC11171719 | DOI:10.3389/fpubh.2024.1361901