PLoS One. 2024 Mar 11;19(3):e0299545. doi: 10.1371/journal.pone.0299545. eCollection 2024.

ABSTRACT

Musculoskeletal conditions affect an estimated 1.7 billion people worldwide, causing intense pain and disability. These conditions lead to 30 million emergency room visits yearly, and the numbers are only increasing. However, diagnosing musculoskeletal issues can be challenging, especially in emergencies where quick decisions are necessary. Deep learning (DL) has shown promise in various medical applications. However, previous methods had poor performance and a lack of transparency in detecting shoulder abnormalities on X-ray images due to a lack of training data and better representation of features. This often resulted in overfitting, poor generalisation, and potential bias in decision-making. To address these issues, a new trustworthy DL framework has been proposed to detect shoulder abnormalities (such as fractures, deformities, and arthritis) using X-ray images. The framework consists of two parts: same-domain transfer learning (TL) to mitigate imageNet mismatch and feature fusion to reduce error rates and improve trust in the final result. Same-domain TL involves training pre-trained models on a large number of labelled X-ray images from various body parts and fine-tuning them on the target dataset of shoulder X-ray images. Feature fusion combines the extracted features with seven DL models to train several ML classifiers. The proposed framework achieved an excellent accuracy rate of 99.2%, F1Score of 99.2%, and Cohen's kappa of 98.5%. Furthermore, the accuracy of the results was validated using three visualisation tools, including gradient-based class activation heat map (Grad CAM), activation visualisation, and locally interpretable model-independent explanations (LIME). The proposed framework outperformed previous DL methods and three orthopaedic surgeons invited to classify the test set, who obtained an average accuracy of 79.1%. The proposed framework has proven effective and robust, improving generalisation and increasing trust in the final results.

PMID:38466693 | DOI:10.1371/journal.pone.0299545

IEEE Trans Neural Syst Rehabil Eng. 2024 Mar 11;PP. doi: 10.1109/TNSRE.2024.3375320. Online ahead of print.

ABSTRACT

Computational biomechanical analysis plays a pivotal role in understanding and improving human movements and physical functions. Although physics-based modeling methods can interpret the dynamic interaction between the neural drive to muscle dynamics and joint kinematics, they suffer from high computational latency. In recent years, data-driven methods have emerged as a promising alternative due to their fast execution speed, but label information is still required during training, which is not easy to acquire in practice. To tackle these issues, this paper presents a novel physics-informed deep learning method to predict muscle forces without any label information during model training. In addition, the proposed method could also identify personalized muscle-tendon parameters. To achieve this, the Hill muscle model-based forward dynamics is embedded into the deep neural network as the additional loss to further regulate the behavior of the deep neural network. Experimental validations on the wrist joint from six healthy subjects are performed, and a fully connected neural network (FNN) is selected to implement the proposed method. The predicted results of muscle forces show comparable or even lower root mean square error (RMSE) and higher coefficient of determination compared with baseline methods, which have to use the labeled surface electromyography (sEMG) signals, and it can also identify muscle-tendon parameters accurately, demonstrating the effectiveness of the proposed physics-informed deep learning method.

PMID:38466606 | DOI:10.1109/TNSRE.2024.3375320

IEEE Trans Neural Netw Learn Syst. 2024 Mar 11;PP. doi: 10.1109/TNNLS.2024.3370918. Online ahead of print.

ABSTRACT

The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network (GNN) models and suggests aggregations beyond the one-hop neighborhood. In this article, we develop a new way to implement multiscale extraction via constructing Haar-type graph framelets with desired properties of permutation equivariance, efficiency, and sparsity, for deep learning tasks on graphs. We further design a graph framelet neural network model permutation equivariant graph framelet augmented network (PEGFAN) based on our constructed graph framelets. The experiments are conducted on a synthetic dataset and nine benchmark datasets to compare the performance with other state-of-the-art models. The result shows that our model can achieve the best performance on certain datasets of heterophilous graphs (including the majority of heterophilous datasets with relatively larger sizes and denser connections) and competitive performance on the remaining.

PMID:38466605 | DOI:10.1109/TNNLS.2024.3370918

IEEE Trans Neural Netw Learn Syst. 2024 Mar 11;PP. doi: 10.1109/TNNLS.2024.3371025. Online ahead of print.

ABSTRACT

The great success of deep learning poses an urgent challenge to establish the theoretical basis for its working mechanism. Recently, research on the convergence of deep neural networks (DNNs) has made great progress. However, the existing studies are based on the assumption that the samples are independent, which is too strong to be applied to many real-world scenarios. In this brief, we establish a fast learning rate for the empirical risk minimization (ERM) on DNN regression with dependent samples, and the dependence is expressed in terms of geometrically strongly mixing sequence. To the best of our knowledge, this is the first convergence result of DNN methods based on mixing sequences. This result is a natural generalization of the independent sample case.

PMID:38466602 | DOI:10.1109/TNNLS.2024.3371025

IEEE J Biomed Health Inform. 2024 Mar 11;PP. doi: 10.1109/JBHI.2024.3375621. Online ahead of print.

ABSTRACT

Exploring protein-protein interaction (PPI) is of paramount importance for elucidating the intrinsic mechanism of various biological processes. Nevertheless, experimental determination of PPI can be both time-consuming and expensive, motivating the exploration of data-driven deep learning technologies as a viable, efficient, and accurate alternative. Nonetheless, most current deep learning-based methods regarded a pair of proteins to be predicted for possible interaction as two separate entities when extracting PPI features, thus neglecting the knowledge sharing among the collaborative protein and the target protein. Aiming at the above issue, a collaborative learning framework CollaPPI was proposed in this study, where two kinds of collaboration, i.e., protein-level collaboration and task-level collaboration, were incorporated to achieve not only the knowledge-sharing between a pair of proteins, but also the complementation of such shared knowledge between biological domains closely related to PPI (i.e., protein function, and subcellular location). Evaluation results demonstrated that CollaPPI obtained superior performance compared to state-of-the-art methods on two PPI benchmarks. Besides, evaluation results of CollaPPI on the additional PPI type prediction task further proved its excellent generalization ability.

PMID:38466584 | DOI:10.1109/JBHI.2024.3375621

J Urban Health. 2024 Mar 11. doi: 10.1007/s11524-024-00830-6. Online ahead of print.

ABSTRACT

Understanding how outdoor environments affect mental health outcomes is vital in today's fast-paced and urbanized society. Recently, advancements in data-gathering technologies and deep learning have facilitated the study of the relationship between the outdoor environment and human perception. In a systematic review, we investigate how deep learning techniques can shed light on a better understanding of the influence of outdoor environments on human perceptions and emotions, with an emphasis on mental health outcomes. We have systematically reviewed 40 articles published in SCOPUS and the Web of Science databases which were the published papers between 2016 and 2023. The study presents and utilizes a novel topic modeling method to identify coherent keywords. By extracting the top words of each research topic, and identifying the current topics, we indicate that current studies are classified into three areas. The first topic was "Urban Perception and Environmental Factors" where the studies aimed to evaluate perceptions and mental health outcomes. Within this topic, the studies were divided based on human emotions, mood, stress, and urban features impacts. The second topic was titled "Data Analysis and Urban Imagery in Modeling" which focused on refining deep learning techniques, data collection methods, and participants' variability to understand human perceptions more accurately. The last topic was named "Greenery and visual exposure in urban spaces" which focused on the impact of the amount and the exposure of green features on mental health and perceptions. Upon reviewing the papers, this study provides a guide for subsequent research to enhance the view of using deep learning techniques to understand how urban environments influence mental health. It also provides various suggestions that should be taken into account when planning outdoor spaces.

PMID:38466494 | DOI:10.1007/s11524-024-00830-6

Eur Radiol. 2024 Mar 11. doi: 10.1007/s00330-024-10676-w. Online ahead of print.

ABSTRACT

OBJECTIVES: To evaluate an artificial intelligence (AI)-assisted double reading system for detecting clinically relevant missed findings on routinely reported chest radiographs.

METHODS: A retrospective study was performed in two institutions, a secondary care hospital and tertiary referral oncology centre. Commercially available AI software performed a comparative analysis of chest radiographs and radiologists' authorised reports using a deep learning and natural language processing algorithm, respectively. The AI-detected discrepant findings between images and reports were assessed for clinical relevance by an external radiologist, as part of the commercial service provided by the AI vendor. The selected missed findings were subsequently returned to the institution's radiologist for final review.

RESULTS: In total, 25,104 chest radiographs of 21,039 patients (mean age 61.1 years ± 16.2 [SD]; 10,436 men) were included. The AI software detected discrepancies between imaging and reports in 21.1% (5289 of 25,104). After review by the external radiologist, 0.9% (47 of 5289) of cases were deemed to contain clinically relevant missed findings. The institution's radiologists confirmed 35 of 47 missed findings (74.5%) as clinically relevant (0.1% of all cases). Missed findings consisted of lung nodules (71.4%, 25 of 35), pneumothoraces (17.1%, 6 of 35) and consolidations (11.4%, 4 of 35).

CONCLUSION: The AI-assisted double reading system was able to identify missed findings on chest radiographs after report authorisation. The approach required an external radiologist to review the AI-detected discrepancies. The number of clinically relevant missed findings by radiologists was very low.

CLINICAL RELEVANCE STATEMENT: The AI-assisted double reader workflow was shown to detect diagnostic errors and could be applied as a quality assurance tool. Although clinically relevant missed findings were rare, there is potential impact given the common use of chest radiography.

KEY POINTS: • A commercially available double reading system supported by artificial intelligence was evaluated to detect reporting errors in chest radiographs (n=25,104) from two institutions. • Clinically relevant missed findings were found in 0.1% of chest radiographs and consisted of unreported lung nodules, pneumothoraces and consolidations. • Applying AI software as a secondary reader after report authorisation can assist in reducing diagnostic errors without interrupting the radiologist's reading workflow. However, the number of AI-detected discrepancies was considerable and required review by a radiologist to assess their relevance.

PMID:38466390 | DOI:10.1007/s00330-024-10676-w

Technol Cancer Res Treat. 2024 Jan-Dec;23:15330338241235769. doi: 10.1177/15330338241235769.

ABSTRACT

Objectives: The purpose of this research is to summarize the structure of radiomics-based knowledge and to explore potential trends and priorities by using bibliometric analysis. Methods: Select radiomics-related publications from 2012 to October 2022 from the Science Core Collection Web site. Use VOSviewer (version 1.6.18), CiteSpace (version 6.1.3), Tableau (version 2022), Microsoft Excel and Rstudio's free online platforms (http://bibliometric.com) for co-writing, co-citing, and co-occurrence analysis of countries, institutions, authors, references, and keywords in the field. The visual analysis is also carried out on it. Results: The study included 6428 articles. Since 2012, there has been an increase in research papers based on radiomics. Judging by publications, China has made the largest contribution in this area. We identify the most productive institutions and authors as Fudan University and Tianjie. The top three magazines with the most publications are《FRONTIERS IN ONCOLOGY》, 《EUROPEAN RADIOLOGY》, and 《CANCERS》. According to the results of reference and keyword analysis, "deep learning, nomogram, ultrasound, f-18-fdg, machine learning, covid-19, radiogenomics" has been determined as the main research direction in the future. Conclusion: Radiomics is in a phase of vigorous development with broad prospects. Cross-border cooperation between countries and institutions should be strengthened in the future. It can be predicted that the development of deep learning-based models and multimodal fusion models will be the focus of future research. Advances in knowledge: This study explores the current state of research and hot spots in the field of radiomics from multiple perspectives, comprehensively, and objectively reflecting the evolving trends in imaging-related research and providing a reference for future research.

PMID:38465611 | DOI:10.1177/15330338241235769

Toxicol Pathol. 2024 Mar 11:1926233241234059. doi: 10.1177/01926233241234059. Online ahead of print.

ABSTRACT

The indirect assessment of adverse effects on fertility in cynomolgus monkeys requires that tissue sections of the testis be microscopically evaluated with awareness of the stage of spermatogenesis that a particular cross-section of a seminiferous tubule is in. This difficult and subjective task could very much benefit from automation. Using digital whole slide images (WSIs) from tissue sections of testis, we have developed a deep learning model that can annotate the stage of each tubule with high sensitivity, precision, and accuracy. The model was validated on six WSI using a six-stage spermatogenic classification system. Whole slide images contained an average number of 4938 seminiferous tubule cross-sections. On average, 78% of these tubules were staged with 29% in stage I-IV, 12% in stage V-VI, 4% in stage VII, 19% in stage VIII-IX, 18% in stage X-XI, and 17% in stage XII. The deep learning model supports pathologists in conducting a stage-aware evaluation of the testis. It also allows derivation of a stage-frequency map. The diagnostic value of this stage-frequency map is still unclear, as further data on its variability and relevance need to be generated for testes with spermatogenic disturbances.

PMID:38465599 | DOI:10.1177/01926233241234059

Hypertension. 2024 Mar 11. doi: 10.1161/HYPERTENSIONAHA.123.22176. Online ahead of print.

ABSTRACT

BACKGROUND: Gray matter (GM) and white matter (WM) impairments are both associated with raised blood pressure (BP), although whether elevated BP is differentially associated with the GM and WM aging process remains inadequately examined.

METHODS: We included 37 327 participants with diffusion-weighted imaging (DWI) and 39 630 participants with T1-weighted scans from UK Biobank. BP was classified into 4 categories: normal BP, high-normal BP, grade 1, and grade 2 hypertension. Brain age gaps (BAGs) for GM (BAGGM) and WM (BAGWM) were derived from diffusion-weighted imaging and T1 scans separately using 3-dimensional-convolutional neural network deep learning techniques.

RESULTS: There was an increase in both BAGGM and BAGWM with raised BP (P<0.05). BAGWM was significantly larger than BAGGM at high-normal BP (0.195 years older; P=0.006), grade 1 hypertension (0.174 years older; P=0.004), and grade 2 hypertension (0.510 years older; P<0.001), but not for normal BP. Mediation analysis revealed that the association between hypertension and cognitive decline was primarily mediated by WM impairment. Mendelian randomization analysis suggested a causal relationship between hypertension and WM aging acceleration (unstandardized B, 1.780; P=0.016) but not for GM (P>0.05). Sliding-window analysis indicated the association between hypertension and brain aging acceleration was moderated by chronological age, showing stronger correlations in midlife but weaker associations in the older age.

CONCLUSIONS: Compared with GM, WM was more vulnerable to raised BP. Our study provided compelling evidence that concerted efforts should be directed towards WM damage in individuals with hypertension in clinical practice.

PMID:38465593 | DOI:10.1161/HYPERTENSIONAHA.123.22176

Mach Learn Sci Technol. 2024 Mar 1;5(1):015042. doi: 10.1088/2632-2153/ad2e15. Epub 2024 Mar 8.

ABSTRACT

Limited access to breast cancer diagnosis globally leads to delayed treatment. Ultrasound, an effective yet underutilized method, requires specialized training for sonographers, which hinders its widespread use. Volume sweep imaging (VSI) is an innovative approach that enables untrained operators to capture high-quality ultrasound images. Combined with deep learning, like convolutional neural networks, it can potentially transform breast cancer diagnosis, enhancing accuracy, saving time and costs, and improving patient outcomes. The widely used UNet architecture, known for medical image segmentation, has limitations, such as vanishing gradients and a lack of multi-scale feature extraction and selective region attention. In this study, we present a novel segmentation model known as Wavelet_Attention_UNet (WATUNet). In this model, we incorporate wavelet gates and attention gates between the encoder and decoder instead of a simple connection to overcome the limitations mentioned, thereby improving model performance. Two datasets are utilized for the analysis: the public 'Breast Ultrasound Images' dataset of 780 images and a private VSI dataset of 3818 images, captured at the University of Rochester by the authors. Both datasets contained segmented lesions categorized into three types: no mass, benign mass, and malignant mass. Our segmentation results show superior performance compared to other deep networks. The proposed algorithm attained a Dice coefficient of 0.94 and an F1 score of 0.94 on the VSI dataset and scored 0.93 and 0.94 on the public dataset, respectively. Moreover, our model significantly outperformed other models in McNemar's test with false discovery rate correction on a 381-image VSI set. The experimental findings demonstrate that the proposed WATUNet model achieves precise segmentation of breast lesions in both standard-of-care and VSI images, surpassing state-of-the-art models. Hence, the model holds considerable promise for assisting in lesion identification, an essential step in the clinical diagnosis of breast lesions.

PMID:38464559 | PMC:PMC10921088 | DOI:10.1088/2632-2153/ad2e15

World J Orthop. 2024 Feb 18;15(2):105-109. doi: 10.5312/wjo.v15.i2.105. eCollection 2024 Feb 18.

ABSTRACT

Artificial intelligence (AI) and deep learning are becoming increasingly powerful tools in diagnostic and radiographic medicine. Deep learning has already been utilized for automated detection of pneumonia from chest radiographs, diabetic retinopathy, breast cancer, skin carcinoma classification, and metastatic lymphadenopathy detection, with diagnostic reliability akin to medical experts. In the World Journal of Orthopedics article, the authors apply an automated and AI-assisted technique to determine the hallux valgus angle (HVA) for assessing HV foot deformity. With the U-net neural network, the authors constructed an algorithm for pattern recognition of HV foot deformity from anteroposterior high-resolution radiographs. The performance of the deep learning algorithm was compared to expert clinician manual performance and assessed alongside clinician-clinician variability. The authors found that the AI tool was sufficient in assessing HVA and proposed the system as an instrument to augment clinical efficiency. Though further sophistication is needed to establish automated algorithms for more complicated foot pathologies, this work adds to the growing evidence supporting AI as a powerful diagnostic tool.

PMID:38464350 | PMC:PMC10921175 | DOI:10.5312/wjo.v15.i2.105

bioRxiv [Preprint]. 2024 Feb 27:2024.02.24.581671. doi: 10.1101/2024.02.24.581671.

ABSTRACT

Prediction of RNA structure from sequence remains an unsolved problem, and progress has been slowed by a paucity of experimental data. Here, we present Ribonanza, a dataset of chemical mapping measurements on two million diverse RNA sequences collected through Eterna and other crowdsourced initiatives. Ribonanza measurements enabled solicitation, training, and prospective evaluation of diverse deep neural networks through a Kaggle challenge, followed by distillation into a single, self-contained model called RibonanzaNet. When fine tuned on auxiliary datasets, RibonanzaNet achieves state-of-the-art performance in modeling experimental sequence dropout, RNA hydrolytic degradation, and RNA secondary structure, with implications for modeling RNA tertiary structure.

PMID:38464325 | PMC:PMC10925082 | DOI:10.1101/2024.02.24.581671

CPT Pharmacometrics Syst Pharmacol. 2024 Mar 11. doi: 10.1002/psp4.13124. Online ahead of print.

ABSTRACT

Noncompartmental analysis (NCA) is a model-independent approach for assessing pharmacokinetics (PKs). Although the existing NCA algorithms are very well-established and widely utilized, they suffer from low accuracies in the setting of sparse PK samples. In response, we developed Deep-NCA, a deep learning (DL) model to improve the prediction of key noncompartmental PK parameters. Our methodology utilizes synthetic PK data for model training and uses an innovative patient-specific normalization method for data preprocessing. Deep-NCA demonstrated adequate performance across six previously unseen simulated drugs under multiple dosing, showcasing effective generalization. Compared to traditional NCA, Deep-NCA exhibited superior performance for sparse PK data. This study advances the application of DL to PK studies and introduces an effective method for handling sparse PK data. With further validation and refinement, Deep-NCA could significantly enhance the efficiency of drug development by providing more accurate NCA estimates while requiring fewer PK samples.

PMID:38465417 | DOI:10.1002/psp4.13124

Imaging Neurosci (Camb). 2024 Mar;2. doi: 10.1162/imag_a_00090. Epub 2024 Feb 13.

ABSTRACT

Whole-head segmentation from Magnetic Resonance Images (MRI) establishes the foundation for individualized computational models using finite element method (FEM). This foundation paves the path for computer-aided solutions in fields, particularly in non-invasive brain stimulation. Most current automatic head segmentation tools are developed using healthy young adults. Thus, they may neglect the older population that is more prone to age-related structural decline such as brain atrophy. In this work, we present a new deep learning method called GRACE, which stands for General, Rapid, And Comprehensive whole-hEad tissue segmentation. GRACE is trained and validated on a novel dataset that consists of 177 manually corrected MR-derived reference segmentations that have undergone meticulous manual review. Each T1-weighted MRI volume is segmented into 11 tissue types, including white matter, grey matter, eyes, cerebrospinal fluid, air, blood vessel, cancellous bone, cortical bone, skin, fat, and muscle. To the best of our knowledge, this work contains the largest manually corrected dataset to date in terms of number of MRIs and segmented tissues. GRACE outperforms five freely available software tools and a traditional 3D U-Net on a five-tissue segmentation task. On this task, GRACE achieves an average Hausdorff Distance of 0.21, which exceeds the runner-up at an average Hausdorff Distance of 0.36. GRACE can segment a whole-head MRI in about 3 seconds, while the fastest software tool takes about 3 minutes. In summary, GRACE segments a spectrum of tissue types from older adults T1-MRI scans at favorable accuracy and speed. The trained GRACE model is optimized on older adult heads to enable high-precision modeling in age-related brain disorders. To support open science, the GRACE code and trained weights are made available online and open to the research community at https://github.com/lab-smile/GRACE.

PMID:38465203 | PMC:PMC10922731 | DOI:10.1162/imag_a_00090

Front Endocrinol (Lausanne). 2024 Feb 23;15:1327325. doi: 10.3389/fendo.2024.1327325. eCollection 2024.

ABSTRACT

OBJECTIVE: To investigate changes in the choroidal vasculature and their correlations with visual acuity in diabetic retinopathy (DR).

METHODS: The cohort was composed of 225 eyes from 225 subjects, including 60 eyes from 60 subjects with healthy control, 55 eyes from 55 subjects without DR, 46 eyes from 46 subjects with nonproliferative diabetic retinopathy (NPDR), 21 eyes from 21 subjects with proliferative diabetic retinopathy (PDR), and 43 eyes from 43 subjects with clinically significant macular edema (CSME). Swept-source optical coherence tomography (SS-OCT) was used to image the eyes with a 12-mm radial line scan protocol. The parameters for 6-mm diameters of region centered on the macular fovea were analyzed. Initially, a custom deep learning algorithm based on a modified residual U-Net architecture was utilized for choroidal boundary segmentation. Subsequently, the SS-OCT image was binarized and the Niblack-based automatic local threshold algorithm was employed to calibrate subfoveal choroidal thickness (SFCT), luminal area (LA), and stromal area (SA) by determining the distance between the two boundaries. Finally, the ratio of LA and total choroidal area (SA + LA) was defined as the choroidal vascularity index (CVI). The choroidal parameters in five groups were compared, and correlations of the choroidal parameters with age, gender, duration of diabetes mellitus (DM), glycated hemoglobin (HbA1c), fasting blood sugar, SFCT and best-corrected visual acuity (BCVA) were analyzed.

RESULTS: The CVI, SFCT, LA, and SA values of patients with DR were found to be significantly lower compared to both healthy patients and patients without DR (P < 0.05). The SFCT was significantly higher in NPDR group compared to the No DR group (P < 0.001). Additionally, the SFCT was lower in the PDR group compared to the NPDR group (P = 0.014). Furthermore, there was a gradual decrease in CVI with progression of diabetic retinopathy, reaching its lowest value in the PDR group. However, the CVI of the CSME group exhibited a marginally closer proximity to that of the NPDR group. The multivariate regression analysis revealed a positive correlation between CVI and the duration of DM as well as LA (P < 0.05). The results of both univariate and multivariate regression analyses demonstrated a significant positive correlation between CVI and BCVA (P = 0.003).

CONCLUSION: Choroidal vascular alterations, especially decreased CVI, occurred in patients with DR. The CVI decreased with duration of DM and was correlated with visual impairment, indicating that the CVI might be a reliable imaging biomarker to monitor the progression of DR.

PMID:38464970 | PMC:PMC10920230 | DOI:10.3389/fendo.2024.1327325

Neurooncol Adv. 2024 Feb 19;6(1):vdae015. doi: 10.1093/noajnl/vdae015. eCollection 2024 Jan-Dec.

ABSTRACT

BACKGROUND: Evaluation of treatment response for brain metastases (BMs) following stereotactic radiosurgery (SRS) becomes complex as the number of treated BMs increases. This study uses artificial intelligence (AI) to track BMs after SRS and validates its output compared with manual measurements.

METHODS: Patients with BMs who received at least one course of SRS and followed up with MRI scans were retrospectively identified. A tool for automated detection, segmentation, and tracking of intracranial metastases on longitudinal imaging, MEtastasis Tracking with Repeated Observations (METRO), was applied to the dataset. The longest three-dimensional (3D) diameter identified with METRO was compared with manual measurements of maximum axial BM diameter, and their correlation was analyzed. Change in size of the measured BM identified with METRO after SRS treatment was used to classify BMs as responding, or not responding, to treatment, and its accuracy was determined relative to manual measurements.

RESULTS: From 71 patients, 176 BMs were identified and measured with METRO and manual methods. Based on a one-to-one correlation analysis, the correlation coefficient was R2 = 0.76 (P = .0001). Using modified BM response classifications of BM change in size, the longest 3D diameter data identified with METRO had a sensitivity of 0.72 and a specificity of 0.95 in identifying lesions that responded to SRS, when using manual axial diameter measurements as the ground truth.

CONCLUSIONS: Using AI to automatically measure and track BM volumes following SRS treatment, this study showed a strong correlation between AI-driven measurements and the current clinically used method: manual axial diameter measurements.

PMID:38464949 | PMC:PMC10924534 | DOI:10.1093/noajnl/vdae015

JMIR AI. 2023 Jan-Dec;2(1):e40167. doi: 10.2196/40167. Epub 2023 Feb 23.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) applications based on advanced deep learning methods in image recognition tasks can increase efficiency in the monitoring of medication adherence through automation. AI has sparsely been evaluated for the monitoring of medication adherence in clinical settings. However, AI has the potential to transform the way health care is delivered even in limited-resource settings such as Africa.

OBJECTIVE: We aimed to pilot the development of a deep learning model for simple binary classification and confirmation of proper medication adherence to enhance efficiency in the use of video monitoring of patients in tuberculosis treatment.

METHODS: We used a secondary data set of 861 video images of medication intake that were collected from consenting adult patients with tuberculosis in an institutional review board-approved study evaluating video-observed therapy in Uganda. The video images were processed through a series of steps to prepare them for use in a training model. First, we annotated videos using a specific protocol to eliminate those with poor quality. After the initial annotation step, 497 videos had sufficient quality for training the models. Among them, 405 were positive samples, whereas 92 were negative samples. With some preprocessing techniques, we obtained 160 frames with a size of 224 × 224 in each video. We used a deep learning framework that leveraged 4 convolutional neural networks models to extract visual features from the video frames and automatically perform binary classification of adherence or nonadherence. We evaluated the diagnostic properties of the different models using sensitivity, specificity, F1-score, and precision. The area under the curve (AUC) was used to assess the discriminative performance and the speed per video review as a metric for model efficiency. We conducted a 5-fold internal cross-validation to determine the diagnostic and discriminative performance of the models. We did not conduct external validation due to a lack of publicly available data sets with specific medication intake video frames.

RESULTS: Diagnostic properties and discriminative performance from internal cross-validation were moderate to high in the binary classification tasks with 4 selected automated deep learning models. The sensitivity ranged from 92.8 to 95.8%, specificity from 43.5 to 55.4%, F1-score from 0.91 to 0.92, precision from 88% to 90.1%, and AUC from 0.78 to 0.85. The 3D ResNet model had the highest precision, AUC, and speed.

CONCLUSIONS: All 4 deep learning models showed comparable diagnostic properties and discriminative performance. The findings serve as a reasonable proof of concept to support the potential application of AI in the binary classification of video frames to predict medication adherence.

PMID:38464947 | PMC:PMC10923555 | DOI:10.2196/40167

Proc IEEE Int Symp Biomed Imaging. 2021 Apr;2021:1777-1780. doi: 10.1109/isbi48211.2021.9433956. Epub 2021 May 25.

ABSTRACT

We propose a Multi-scale, domain knowledge-Guided Attention model (MGA-Net) for a weakly supervised problem - disease diagnosis with only coarse scan-level labels. The use of guided attention models encourages the deep learning-based diagnosis model to focus on the area of interests (in our case, lung parenchyma), at different resolutions, in an end-to-end manner. The research interest is to diagnose subjects with idiopathic pulmonary fibrosis (IPF) among subjects with interstitial lung disease (ILD) using an axial chest high resolution computed tomography (HRCT) scan. Our dataset contains 279 IPF patients and 423 non-IPF ILD patients. The network's performance was evaluated by the area under the receiver operating characteristic curve (AUC) with standard errors (SE) using stratified five-fold cross validation. We observe that without attention modules, the IPF diagnosis model performs unsatisfactorily (AUC±SE =0.690 ± 0.194); by including unguided attention module, the IPF diagnosis model reaches satisfactory performance (AUC±SE =0.956±0.040), but lack explainability; when including only guided high- or medium- resolution attention, the learned attention maps highlight the lung areas but the AUC decreases; when including both high- and medium- resolution attention, the model reaches the highest AUC among all experiments (AUC± SE =0.971 ±0.021) and the estimated attention maps concentrate on the regions of interests for this task. Our results suggest that, for a weakly supervised task, MGA-Net can utilize the population-level domain knowledge to guide the training of the network in an end-to-end manner, which increases both model accuracy and explainability.

PMID:38464881 | PMC:PMC10924672 | DOI:10.1109/isbi48211.2021.9433956

World J Psychiatry. 2024 Feb 19;14(2):225-233. doi: 10.5498/wjp.v14.i2.225. eCollection 2024 Feb 19.

ABSTRACT

Depression is a common mental health disorder. With current depression detection methods, specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression assessment. Non-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively utilized. Specialized physicians usually require extensive training and experience to capture changes in these features. Advancements in deep learning technology have provided technical support for capturing non-biological markers. Several researchers have proposed automatic depression estimation (ADE) systems based on sounds and videos to assist physicians in capturing these features and conducting depression screening. This article summarizes commonly used public datasets and recent research on audio- and video-based ADE based on three perspectives: Datasets, deficiencies in existing research, and future development directions.

PMID:38464777 | PMC:PMC10921287 | DOI:10.5498/wjp.v14.i2.225