Sci Adv. 2024 May 24;10(21):eadj4452. doi: 10.1126/sciadv.adj4452. Epub 2024 May 23.

ABSTRACT

Most genetic variants associated with psychiatric disorders are located in noncoding regions of the genome. To investigate their functional implications, we integrate epigenetic data from the PsychENCODE Consortium and other published sources to construct a comprehensive atlas of candidate brain cis-regulatory elements. Using deep learning, we model these elements' sequence syntax and predict how binding sites for lineage-specific transcription factors contribute to cell type-specific gene regulation in various types of glia and neurons. The elements' evolutionary history suggests that new regulatory information in the brain emerges primarily via smaller sequence mutations within conserved mammalian elements rather than entirely new human- or primate-specific sequences. However, primate-specific candidate elements, particularly those active during fetal brain development and in excitatory neurons and astrocytes, are implicated in the heritability of brain-related human traits. Additionally, we introduce PsychSCREEN, a web-based platform offering interactive visualization of PsychENCODE-generated genetic and epigenetic data from diverse brain cell types in individuals with psychiatric disorders and healthy controls.

PMID:38781344 | DOI:10.1126/sciadv.adj4452

PLoS One. 2024 May 23;19(5):e0302294. doi: 10.1371/journal.pone.0302294. eCollection 2024.

ABSTRACT

Due to the recent advances in the Internet and communication technologies, network systems and data have evolved rapidly. The emergence of new attacks jeopardizes network security and make it really challenging to detect intrusions. Multiple network attacks by an intruder are unavoidable. Our research targets the critical issue of class imbalance in intrusion detection, a reflection of the real-world scenario where legitimate network activities significantly out number malicious ones. This imbalance can adversely affect the learning process of predictive models, often resulting in high false-negative rates, a major concern in Intrusion Detection Systems (IDS). By focusing on datasets with this imbalance, we aim to develop and refine advanced algorithms and techniques, such as anomaly detection, cost-sensitive learning, and oversampling methods, to effectively handle such disparities. The primary goal is to create models that are highly sensitive to intrusions while minimizing false alarms, an essential aspect of effective IDS. This approach is not only practical for real-world applications but also enhances the theoretical understanding of managing class imbalance in machine learning. Our research, by addressing these significant challenges, is positioned to make substantial contributions to cybersecurity, providing valuable insights and applicable solutions in the fight against digital threats and ensuring robustness and relevance in IDS development. An intrusion detection system (IDS) checks network traffic for security, availability, and being non-shared. Despite the efforts of many researchers, contemporary IDSs still need to further improve detection accuracy, reduce false alarms, and detect new intrusions. The mean convolutional layer (MCL), feature-weighted attention (FWA) learning, a bidirectional long short-term memory (BILSTM) network, and the random forest algorithm are all parts of our unique hybrid model called MCL-FWA-BILSTM. The CNN-MCL layer for feature extraction receives data after preprocessing. After convolution, pooling, and flattening phases, feature vectors are obtained. The BI-LSTM and self-attention feature weights are used in the suggested method to mitigate the effects of class imbalance. The attention layer and the BI-LSTM features are concatenated to create mapped features before feeding them to the random forest algorithm for classification. Our methodology and model performance were validated using NSL-KDD and UNSW-NB-15, two widely available IDS datasets. The suggested model's accuracies on binary and multi-class classification tasks using the NSL-KDD dataset are 99.67% and 99.88%, respectively. The model's binary and multi-class classification accuracies on the UNSW-NB15 dataset are 99.56% and 99.45%, respectively. Further, we compared the suggested approach with other previous machine learning and deep learning models and found it to outperform them in detection rate, FPR, and F-score. For both binary and multiclass classifications, the proposed method reduces false positives while increasing the number of true positives. The model proficiently identifies diverse network intrusions on computer networks and accomplishes its intended purpose. The suggested model will be helpful in a variety of network security research fields and applications.

PMID:38781186 | DOI:10.1371/journal.pone.0302294

PLoS One. 2024 May 23;19(5):e0297989. doi: 10.1371/journal.pone.0297989. eCollection 2024.

ABSTRACT

In light of the exponential growth in information volume, the significance of graph data has intensified. Graph clustering plays a pivotal role in graph data processing by jointly modeling the graph structure and node attributes. Notably, the practical significance of multi-view graph clustering is heightened due to the presence of diverse relationships within real-world graph data. Nonetheless, prevailing graph clustering techniques, predominantly grounded in deep learning neural networks, face challenges in effectively handling multi-view graph data. These challenges include the incapability to concurrently explore the relationships between multiple view structures and node attributes, as well as difficulties in processing multi-view graph data with varying features. To tackle these issues, this research proposes a straightforward yet effective multi-view graph clustering approach known as SLMGC. This approach uses graph filtering to filter noise, reduces computational complexity by extracting samples based on node importance, enhances clustering representations through graph contrastive regularization, and achieves the final clustering outcomes using a self-training clustering algorithm. Notably, unlike neural network algorithms, this approach avoids the need for intricate parameter settings. Comprehensive experiments validate the supremacy of the SLMGC approach in multi-view graph clustering endeavors when contrasted with prevailing deep neural network techniques.

PMID:38781184 | DOI:10.1371/journal.pone.0297989

PLoS One. 2024 May 23;19(5):e0301087. doi: 10.1371/journal.pone.0301087. eCollection 2024.

ABSTRACT

Tibetan Buddhism, as an indigenous religion, has a significant and far-reaching influence in the Tibetan areas of China. This study, focusing on Lhasa, explores the integration of Tibetan Buddhist spiritual perceptions within urban spaces. Employing a novel approach that combines street view data and deep learning technology, the research aims to identify and map the spatial distribution of Tibetan Buddhist spiritual sites against the backdrop of the urban landscape. Our analysis reveals a notable concentration of these spiritual places near urban architectural and cultural heritage areas, highlighting the profound connection between residents' cultural life and spiritual practices. Despite challenges posed by modern urbanisation, these spiritual sites demonstrate resilience and adaptability, continuing to serve as cultural and spiritual pillars of the Tibetan Buddhist community. This study contributes to the fields of urban planning, religious studies, and digital humanities by demonstrating the potential of technology in examining the impact of urban development on cultural and religious landscapes. The research underscores the importance of protecting and integrating spaces of spiritual perception in urban development planning. It shows that safeguarding these spaces is crucial not only for cultural heritage preservation but also for achieving sustainable urban development and social harmony. This study opens new avenues for interdisciplinary research, advocating for a deeper understanding of the dynamic relationship between urban development and spiritual spaces from psychological, sociological, and environmental science perspectives. As urban landscapes evolve, the study emphasises the need to maintain a balance between material sustainability and cultural and spiritual richness in urban planning.

PMID:38781137 | DOI:10.1371/journal.pone.0301087

IEEE J Biomed Health Inform. 2024 May 23;PP. doi: 10.1109/JBHI.2024.3404664. Online ahead of print.

ABSTRACT

Depression is a prevalent mental disorder that affects a significant portion of the global population. Despite recent advancements in EEG-based depression recognition models rooted in machine learning and deep learning approaches, many lack comprehensive consideration of depression's pathogenesis, leading to limited neuroscientific interpretability. To address these issues, we propose a hemisphere asymmetry network (HEMAsNet) inspired by the brain for depression recognition from EEG signals. HEMAsNet employs a combination of multi-scale Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) blocks to extract temporal features from both hemispheres of the brain. Moreover, the model introduces a unique 'Callosum- like' block, inspired by the corpus callosum's pivotal role in facilitating inter-hemispheric information transfer within the brain. This block enhances information exchange between hemispheres, potentially improving depression recognition accuracy. To validate the performance of HEMAsNet, we first confirmed the asymmetric features of frontal lobe EEG in the MODMA dataset. Subsequently, our method achieved a depression recognition accuracy of 0.8067, indicating its effectiveness in increasing classification performance. Furthermore, we conducted a comprehensive investigation from spatial and frequency perspectives, demonstrating HEMAsNet's innovation in explaining model decisions. The advantages of HEMAsNet lie in its ability to achieve more accurate and interpretable recognition of depression through the simulation of physiological processes, integration of spatial information, and incorporation of the Callosum- like block.

PMID:38781058 | DOI:10.1109/JBHI.2024.3404664

IEEE Trans Ultrason Ferroelectr Freq Control. 2024 May 23;PP. doi: 10.1109/TUFFC.2024.3404622. Online ahead of print.

ABSTRACT

Deep learning (DL) models have emerged as alternative methods to conventional ultrasound (US) signal processing, offering the potential to mimic signal processing chains, reduce inference time, and enable the portability of processing chains across hardware. This paper proposes a DL model that replicates the fine-tuned BMode signal processing chain of a high-end US system and explores the potential of using it with a different probe and a lower-end system. A deep neural network was trained in a supervised manner to map raw beamformed in-phase and quadrature component data into processed images. The dataset consisted of 30,000 cardiac image frames acquired using the GE HealthCare Vivid E95 system with the 4Vc-D matrix array probe. The signal processing chain includes depth-dependent bandpass filtering, elevation compounding, frequency compounding, and image compression and filtering. The results indicate that a lightweight DL model can accurately replicate the signal processing chain of a commercial scanner for a given application. Evaluation on a 15 patient test dataset of about three thousand image frames gave a structural similarity index measure of 98.56 ± 0.49. Applying the DL model to data from another probe showed equivalent or improved image quality. This indicates that a single DL model may be used for a set of probes on a given system that targets the same application, which could be a cost-effective tuning and implementation strategy for vendors. Further, the DL model enhanced image quality on a Verasonics dataset, suggesting the potential to port features from high-end US systems to lower-end counterparts.

PMID:38781056 | DOI:10.1109/TUFFC.2024.3404622

Transl Vis Sci Technol. 2024 May 1;13(5):20. doi: 10.1167/tvst.13.5.20.

ABSTRACT

PURPOSE: We sough to develop an automatic method of quantifying optic disc pallor in fundus photographs and determine associations with peripapillary retinal nerve fiber layer (pRNFL) thickness.

METHODS: We used deep learning to segment the optic disc, fovea, and vessels in fundus photographs, and measured pallor. We assessed the relationship between pallor and pRNFL thickness derived from optical coherence tomography scans in 118 participants. Separately, we used images diagnosed by clinical inspection as pale (n = 45) and assessed how measurements compared with healthy controls (n = 46). We also developed automatic rejection thresholds and tested the software for robustness to camera type, image format, and resolution.

RESULTS: We developed software that automatically quantified disc pallor across several zones in fundus photographs. Pallor was associated with pRNFL thickness globally (β = -9.81; standard error [SE] = 3.16; P < 0.05), in the temporal inferior zone (β = -29.78; SE = 8.32; P < 0.01), with the nasal/temporal ratio (β = 0.88; SE = 0.34; P < 0.05), and in the whole disc (β = -8.22; SE = 2.92; P < 0.05). Furthermore, pallor was significantly higher in the patient group. Last, we demonstrate the analysis to be robust to camera type, image format, and resolution.

CONCLUSIONS: We developed software that automatically locates and quantifies disc pallor in fundus photographs and found associations between pallor measurements and pRNFL thickness.

TRANSLATIONAL RELEVANCE: We think our method will be useful for the identification, monitoring, and progression of diseases characterized by disc pallor and optic atrophy, including glaucoma, compression, and potentially in neurodegenerative disorders.

PMID:38780955 | DOI:10.1167/tvst.13.5.20

J Med Syst. 2024 May 23;48(1):55. doi: 10.1007/s10916-024-02066-y.

ABSTRACT

Designing implants for large and complex cranial defects is a challenging task, even for professional designers. Current efforts on automating the design process focused mainly on convolutional neural networks (CNN), which have produced state-of-the-art results on reconstructing synthetic defects. However, existing CNN-based methods have been difficult to translate to clinical practice in cranioplasty, as their performance on large and complex cranial defects remains unsatisfactory. In this paper, we present a statistical shape model (SSM) built directly on the segmentation masks of the skulls represented as binary voxel occupancy grids and evaluate it on several cranial implant design datasets. Results show that, while CNN-based approaches outperform the SSM on synthetic defects, they are inferior to SSM when it comes to large, complex and real-world defects. Experienced neurosurgeons evaluate the implants generated by the SSM to be feasible for clinical use after minor manual corrections. Datasets and the SSM model are publicly available at https://github.com/Jianningli/ssm .

PMID:38780820 | DOI:10.1007/s10916-024-02066-y

Eur Radiol. 2024 May 23. doi: 10.1007/s00330-024-10776-7. Online ahead of print.

ABSTRACT

OBJECTIVES: To establish and evaluate an ultra-fast MRI screening protocol for prostate cancer (PCa) in comparison to the standard multiparametric (mp) protocol, reducing scan time and maintaining adequate diagnostic performance.

MATERIALS AND METHODS: This prospective single-center study included consecutive biopsy-naïve patients with suspected PCa between December 2022 and March 2023. A PI-RADSv2.1 conform mpMRI protocol was acquired in a 3 T scanner (scan time: 25 min 45 sec). In addition, two deep-learning (DL) accelerated sequences (T2- and diffusion-weighted) were acquired, serving as a screening protocol (scan time: 3 min 28 sec). Two readers evaluated image quality and the probability of PCa regarding PI-RADSv2.1 scores in two sessions. The diagnostic performance of the screening protocol with mpMRI serving as the reference standard was derived. Inter- and intra-reader agreements were evaluated using weighted kappa statistics.

RESULTS: We included 77 patients with 97 lesions (mean age: 66 years; SD: 7.7). Diagnostic performance of the screening protocol was excellent with a sensitivity and specificity of 100%/100% and 89%/98% (cut-off ≥ PI-RADS 4) for reader 1 (R1) and reader 2 (R2), respectively. Mean image quality was 3.96 (R1) and 4.35 (R2) for the standard protocol vs. 4.74 and 4.57 for the screening protocol (p < 0.05). Inter-reader agreement was moderate (κ: 0.55) for the screening protocol and substantial (κ: 0.61) for the multiparametric protocol.

CONCLUSION: The ultra-fast screening protocol showed similar diagnostic performance and better imaging quality compared to the mpMRI in under 15% of scan time, improving efficacy and enabling the implementation of screening protocols in clinical routine.

CLINICAL RELEVANCE STATEMENT: The ultra-fast protocol enables examinations without contrast administration, drastically reducing scan time to 3.5 min with similar diagnostic performance and better imaging quality. This facilitates patient-friendly, efficient examinations and addresses the conflict of increasing demand for examinations at currently exhausted capacities.

KEY POINTS: Time-consuming MRI protocols are in conflict with an expected increase in examinations required for prostate cancer screening. An ultra-fast MRI protocol shows similar performance and better image quality compared to the standard protocol. Deep-learning acceleration facilitates efficient and patient-friendly examinations, thus improving prostate cancer screening capacity.

PMID:38780766 | DOI:10.1007/s00330-024-10776-7

Anal Chem. 2024 May 23. doi: 10.1021/acs.analchem.4c01092. Online ahead of print.

ABSTRACT

We describe micro- and nanoelectrode array analysis with an automated version of the array microcell method (AMCM). Characterization of hundreds of electrodes, with diameters ranging from 100 nm to 2 μm, was carried out by using AMCM voltammetry and chronoamperometry. The influence of solvent evaporation on mass transport in the AMCM pipette and the resultant electrochemical response were investigated, with experimental results supported by finite element method simulations. We also describe the application of AMCM to high-throughput single-entity electrochemistry in measurements of stochastic nanoparticle impacts. Collision experiments recorded 3270 single-particle events from 671 electrodes. Data collection parameters were optimized to enable these experiments to be completed in a few hours, and the collision transient sizes were analyzed with a U-Net deep learning model. Elucidation of collision transient sizes by histograms from these experiments was enhanced due to the large sample size possible with AMCM.

PMID:38780285 | DOI:10.1021/acs.analchem.4c01092

ACS Appl Mater Interfaces. 2024 May 23. doi: 10.1021/acsami.3c18773. Online ahead of print.

ABSTRACT

Perovskite oxides are gaining significant attention for use in next-generation magnetic and ferroelectric devices due to their exceptional charge transport properties and the opportunity to tune the charge, spin, lattice, and orbital degrees of freedom. Interfaces between perovskite oxides, exemplified by La1-xSrxCoO3-δ/La1-xSrxMnO3-δ (LSCO/LSMO) bilayers, exhibit unconventional magnetic exchange switching behavior, offering a pathway for innovative designs in perovskite oxide-based devices. However, the precise atomic-level stoichiometric compositions and chemophysical properties of these interfaces remain elusive, hindering the establishment of surrogate design principles. We leverage first-principles simulations, evolutionary algorithms, and neural network searches with on-the-fly uncertainty quantification to design deep learning model ensembles to investigate over 50,000 LSCO/LSMO bilayer structures as a function of oxygen deficiency (δ) and strontium concentration (x). Structural analysis of the low-energy interface structures reveals that preferential segregation of oxygen vacancies toward the interfacial La0.7Sr0.3CoO3-δ layers causes distortion of the CoOx polyhedra and the emergence of magnetically active Co2+ ions. At the same time, an increase in the Sr concentration and a decrease in oxygen vacancies in the La0.7Sr0.3MnO3-δ layers tend to retain MnO6 octahedra and promote the formation of Mn4+ ions. Electronic structure analysis reveals that the nonuniform distributions of Sr ions and oxygen vacancies on both sides of the interface can alter the local magnetization at the interface, showing a transition from ferromagnetic (FM) to local antiferromagnetic (AFM) or ferrimagnetic regions. Therefore, the exotic properties of La1-xSrxCoO3-δ/La1-xSrxMnO3-δ are strongly coupled to the presence of hard/soft magnetic layers, as well as the FM to AFM transition at the interface, and can be tuned by changing the Sr concentration and oxygen partial pressure during growth. These insights provide valuable guidance for the precise design of perovskite oxide multilayers, enabling tailoring of their functional properties to meet specific requirements for various device applications.

PMID:38780088 | DOI:10.1021/acsami.3c18773

Health Informatics J. 2024 Apr-Jun;30(2):14604582241255818. doi: 10.1177/14604582241255818.

ABSTRACT

Mycoplasma pneumonia may lead to hospitalizations and pose life-threatening risks in children. The automated identification of mycoplasma pneumonia from electronic medical records holds significant potential for improving the efficiency of hospital resource allocation. In this study, we proposed a novel method for identifying mycoplasma pneumonia by integrating multi-modal features derived from both free-text descriptions and structured test data in electronic medical records. Our approach begins with the extraction of free-text and structured data from clinical records through a systematic preprocessing pipeline. Subsequently, we employ a pre-trained transformer language model to extract features from the free-text, while multiple additive regression trees are used to transform features from the structured data. An attention-based fusion mechanism is then applied to integrate these multi-modal features for effective classification. We validated our method using clinic records of 7157 patients, retrospectively collected for training and testing purposes. The experimental results demonstrate that our proposed multi-modal fusion approach achieves significant improvements over other methods across four key performance metrics.

PMID:38779978 | DOI:10.1177/14604582241255818

Arterioscler Thromb Vasc Biol. 2024 May 23. doi: 10.1161/ATVBAHA.124.320672. Online ahead of print.

ABSTRACT

BACKGROUND: Analysis of vascular networks is an essential step to unravel the mechanisms regulating the physiological and pathological organization of blood vessels. So far, most of the analyses are performed using 2-dimensional projections of 3-dimensional (3D) networks, a strategy that has several obvious shortcomings. For instance, it does not capture the true geometry of the vasculature and generates artifacts on vessel connectivity. These limitations are accepted in the field because manual analysis of 3D vascular networks is a laborious and complex process that is often prohibitive for large volumes.

METHODS: To overcome these issues, we developed 3DVascNet, a deep learning-based software for automated segmentation and quantification of 3D retinal vascular networks. 3DVascNet performs segmentation based on a deep learning model, and it quantifies vascular morphometric parameters such as vessel density, branch length, vessel radius, and branching point density. We tested the performance of 3DVascNet using a large data set of 3D microscopy images of mouse retinal blood vessels.

RESULTS: We demonstrated that 3DVascNet efficiently segments vascular networks in 3D and that vascular morphometric parameters capture phenotypes detected by using manual segmentation and quantification in 2 dimension. In addition, we showed that, despite being trained on retinal images, 3DVascNet has high generalization capability and successfully segments images originating from other data sets and organs.

CONCLUSIONS: Overall, we present 3DVascNet, a freely available software that includes a user-friendly graphical interface for researchers with no programming experience, which will greatly facilitate the ability to study vascular networks in 3D in health and disease. Moreover, the source code of 3DVascNet is publicly available, thus it can be easily extended for the analysis of other 3D vascular networks by other users.

PMID:38779855 | DOI:10.1161/ATVBAHA.124.320672

Clin Transl Radiat Oncol. 2024 May 9;47:100792. doi: 10.1016/j.ctro.2024.100792. eCollection 2024 Jul.

ABSTRACT

Radiation therapy (RT) nowadays is a main treatment modality of cancer. To ensure the therapeutic efficacy of patients, accurate dose distribution is often required, which is a time-consuming and labor-intensive process. In addition, due to the differences in knowledge and experience among participants and diverse institutions, the predicted dose are often inconsistent. In last several decades, artificial intelligence (AI) has been applied in various aspects of RT, several products have been implemented in clinical practice and confirmed superiority. In this paper, we will review the research of AI in dose prediction, focusing on the progress in deep learning (DL).

PMID:38779524 | PMC:PMC11109740 | DOI:10.1016/j.ctro.2024.100792

Curr Res Food Sci. 2024 May 13;8:100758. doi: 10.1016/j.crfs.2024.100758. eCollection 2024.

ABSTRACT

Today, environmental sustainability is one of the most critical issue. Hence, the food service industry is actively seeking ways to minimize its ecological footprint. One solution to address this issue is the adoption of reusable foodware in the food service industry. This approach requires a careful process for the collection and thorough cleaning of the foodware, ensuring it can be safely reused. However, reusable foodware might be damaged during the collection process, which can pose food safety hazards for customers. Additionally, there are cases where the cleaning process might not effectively remove all contaminants and therefore cannot be reused after the washing process. To ensure consumer safety, a manual inspection is typically conducted after the cleaning process. However, this step is labor-intensive and prone to human error, particularly as workers' attention may decrease over extended periods. Consequently, the adoption of precise and automated methods for detecting defects and contaminants is becoming crucial, not only to ensure safety but also to achieve scalability and enhance cost-efficiency in the pursuit of environmental sustainability. In our research, we explore various data augmentation strategies and the application of knowledge transfer from various samples of reusable food containers. This method only requires few images from a clean sample to teach the network about normal patterns, and to detect defects by identifying irregular details that do not exist in normal samples. This allows us to rapidly deploy the detection system even with a limited number of collected samples. Experimental results demonstrate the effectiveness of our approach in detecting both contamination and cracks on food containers.

PMID:38779346 | PMC:PMC11109354 | DOI:10.1016/j.crfs.2024.100758

Cureus. 2024 Apr 22;16(4):e58744. doi: 10.7759/cureus.58744. eCollection 2024 Apr.

ABSTRACT

BACKGROUND: As oral cancer remains a major worldwide health concern, sophisticated diagnostic tools are needed to aid in early diagnosis. Non-invasive methods like exfoliative cytology, albeit with the help of artificial intelligence (AI), have drawn additional interest.

AIM: The study aimed to harness the power of machine learning algorithms for the automated analysis of nuclear parameters in oral exfoliative cytology. Further, the analysis of two different AI systems, namely convoluted neural networks (CNN) and support vector machine (SVM), were compared for accuracy.

METHODS: A comparative diagnostic study was performed in two groups of patients (n=60). The control group without evidence of lesions (n=30) and the other group with clinically suspicious oral malignancy (n=30) were evaluated. All patients underwent cytological smears using an exfoliative cytology brush, followed by routine Hematoxylin and Eosin staining. Image preprocessing, data splitting, machine learning, model development, feature extraction, and model evaluation were done. An independent t-test was run on each nuclear characteristic, and Pearson's correlation coefficient test was performed with Statistical Package for the Social Sciences (SPSS) software (IBM SPSS Statistics for Windows, Version 28.0. IBM Corp, Armonk, NY, USA).

RESULTS: The study found substantial variations between the study and control groups in nuclear size (p<0.05), nuclear shape (p<0.01), and chromatin distribution (p<0.001). The Pearson correlation coefficient of SVM was 0.6472, and CNN was 0.7790, showing that SVM had more accuracy.

CONCLUSION: The availability of multidimensional datasets, combined with breakthroughs in high-performance computers and new deep-learning architectures, has resulted in an explosion of AI use in numerous areas of oncology research. The discerned diagnostic accuracy exhibited by the SVM and CNN models suggests prospective improvements in early detection rates, potentially improving patient outcomes and enhancing healthcare practices.

PMID:38779230 | PMC:PMC11110917 | DOI:10.7759/cureus.58744

Front Oncol. 2024 May 8;14:1362737. doi: 10.3389/fonc.2024.1362737. eCollection 2024.

ABSTRACT

Liver tumors, whether primary or metastatic, have emerged as a growing concern with substantial global health implications. Timely identification and characterization of liver tumors are pivotal factors in order to provide optimum treatment. Imaging is a crucial part of the detection of liver tumors; however, conventional imaging has shortcomings in the proper characterization of these tumors which leads to the need for tissue biopsy. Artificial intelligence (AI) and radiomics have recently emerged as investigational opportunities with the potential to enhance the detection and characterization of liver lesions. These advancements offer opportunities for better diagnostic accuracy, prognostication, and thereby improving patient care. In particular, these techniques have the potential to predict the histopathology, genotype, and immunophenotype of tumors based on imaging data, hence providing guidance for personalized treatment of such tumors. In this review, we outline the progression and potential of AI in the field of liver oncology imaging, specifically emphasizing manual radiomic techniques and deep learning-based representations. We discuss how these tools can aid in clinical decision-making challenges. These challenges encompass a broad range of tasks, from prognosticating patient outcomes, differentiating benign treatment-related factors and actual disease progression, recognizing uncommon response patterns, and even predicting the genetic and molecular characteristics of the tumors. Lastly, we discuss the pitfalls, technical limitations and future direction of these AI-based techniques.

PMID:38779098 | PMC:PMC11109422 | DOI:10.3389/fonc.2024.1362737

Wellcome Open Res. 2023 Oct 12;8:452. doi: 10.12688/wellcomeopenres.20000.1. eCollection 2023.

ABSTRACT

Background Using reports of randomised trials of smoking cessation interventions as a test case, this study aimed to develop and evaluate machine learning (ML) algorithms for extracting information from study reports and predicting outcomes as part of the Human Behaviour-Change Project. It is the first of two linked papers, with the second paper reporting on further development of a prediction system. Methods Researchers manually annotated 70 items of information ('entities') in 512 reports of randomised trials of smoking cessation interventions covering intervention content and delivery, population, setting, outcome and study methodology using the Behaviour Change Intervention Ontology. These entities were used to train ML algorithms to extract the information automatically. The information extraction ML algorithm involved a named-entity recognition system using the 'FLAIR' framework. The manually annotated intervention, population, setting and study entities were used to develop a deep-learning algorithm using multiple layers of long-short-term-memory (LSTM) components to predict smoking cessation outcomes. Results The F1 evaluation score, derived from the false positive and false negative rates (range 0-1), for the information extraction algorithm averaged 0.42 across different types of entity (SD=0.22, range 0.05-0.88) compared with an average human annotator's score of 0.75 (SD=0.15, range 0.38-1.00). The algorithm for assigning entities to study arms ( e.g., intervention or control) was not successful. This initial ML outcome prediction algorithm did not outperform prediction based just on the mean outcome value or a linear regression model. Conclusions While some success was achieved in using ML to extract information from reports of randomised trials of smoking cessation interventions, we identified major challenges that could be addressed by greater standardisation in the way that studies are reported. Outcome prediction from smoking cessation studies may benefit from development of novel algorithms, e.g., using ontological information to inform ML (as reported in the linked paper 3).

PMID:38779058 | PMC:PMC11109593 | DOI:10.12688/wellcomeopenres.20000.1

Heliyon. 2024 May 10;10(10):e30779. doi: 10.1016/j.heliyon.2024.e30779. eCollection 2024 May 30.

ABSTRACT

BACKGROUND AND OBJECTIVE: Spatial interaction between tumor-infiltrating lymphocytes (TILs) and tumor cells is valuable in predicting the effectiveness of immune response and prognosis amongst patients with lung adenocarcinoma (LUAD). Recent evidence suggests that the spatial distance between tumor cells and lymphocytes also influences the immune responses, but the distance analysis based on Hematoxylin and Eosin (H&E) -stained whole-slide images (WSIs) remains insufficient. To address this issue, we aim to explore the relationship between distance and prognosis prediction of patients with LUAD in this study.

METHODS: We recruited patients with resectable LUAD from three independent cohorts in this multi-center study. We proposed a simple but effective deep learning-driven workflow to automatically segment different cell types in the tumor region using the HoVer-Net model, and quantified the spatial distance (DIST) between tumor cells and lymphocytes based on H&E-stained WSIs. The association of DIST with disease-free survival (DFS) was explored in the discovery set (D1, n = 276) and the two validation sets (V1, n = 139; V2, n = 115).

RESULTS: In multivariable analysis, the low DIST group was associated with significantly better DFS in the discovery set (D1, HR, 0.61; 95 % CI, 0.40-0.94; p = 0.027) and the two validation sets (V1, HR, 0.54; 95 % CI, 0.32-0.91; p = 0.022; V2, HR, 0.44; 95 % CI, 0.24-0.81; p = 0.009). By integrating the DIST with clinicopathological factors, the integrated model (full model) had better discrimination for DFS in the discovery set (C-index, D1, 0.745 vs. 0.723) and the two validation sets (V1, 0.621 vs. 0.596; V2, 0.671 vs. 0.650). Furthermore, the computerized DIST was associated with immune phenotypes such as immune-desert and inflamed phenotypes.

CONCLUSIONS: The integration of DIST with clinicopathological factors could improve the stratification performance of patients with resectable LUAD, was beneficial for the prognosis prediction of LUAD patients, and was also expected to assist physicians in individualized treatment.

PMID:38779006 | PMC:PMC11109847 | DOI:10.1016/j.heliyon.2024.e30779

Digit Health. 2024 May 21;10:20552076241255471. doi: 10.1177/20552076241255471. eCollection 2024 Jan-Dec.

ABSTRACT

OBJECTIVE: The mitotic activity index is an important prognostic factor in the diagnosis of cancer. The task of mitosis detection is difficult as the nuclei are microscopic in size and partially labeled, and there are many more non-mitotic nuclei compared to mitotic ones. In this paper, we highlight the challenges of current mitosis detection pipelines and propose a method to tackle these challenges.

METHODS: Our proposed methodology is inspired from recent research on deep learning and an extensive analysis on the dataset and training pipeline. We first used the MiDoG'22 dataset for training, validation, and testing. We then tested the methodology without fine-tuning on the TUPAC'16 dataset and on a real-time case from Shaukat Khanum Memorial Cancer Hospital and Research Centre.

RESULTS: Our methodology has shown promising results both quantitatively and qualitatively. Quantitatively, our methodology achieved an F1-score of 0.87 on the MiDoG'22 dataset and an F1-score of 0.83 on the TUPAC dataset. Qualitatively, our methodology is generalizable and interpretable across various datasets and clinical settings.

CONCLUSION: In this paper, we highlight the challenges of current mitosis detection pipelines and propose a method that can accurately predict mitotic nuclei. We illustrate the accuracy, generalizability, and interpretability of our approach across various datasets and clinical settings. Our methodology can speed up the adoption of computer-aided digital pathology in clinical settings.

PMID:38778869 | PMC:PMC11110526 | DOI:10.1177/20552076241255471