J Biophotonics. 2024 Jul 2:e202400200. doi: 10.1002/jbio.202400200. Online ahead of print.

ABSTRACT

Ovarian cancer is among the most common gynecological cancers and the eighth leading cause of cancer-related deaths among women worldwide. Surgery is among the most important options for cancer treatment. During surgery, a biopsy is generally required to screen for lesions; however, traditional case examinations are time consuming and laborious and require extensive experience and knowledge from pathologists. Therefore, this study proposes a simple, fast, and label-free ovarian cancer diagnosis method that combines second harmonic generation (SHG) imaging and deep learning. Unstained fresh human ovarian tissues were subjected to SHG imaging and accurately characterized using the Pyramid Vision Transformer V2 (PVTv2) model. The results showed that the SHG imaged collagen fibers could quantify ovarian cancer. In addition, the PVTv2 model could accurately differentiate the 3240 SHG images obtained from our imaging collection into benign, normal, and malignant images, with a final accuracy of 98.4%. These results demonstrate the great potential of SHG imaging techniques combined with deep learning models for diagnosing the diseased ovarian tissues.

PMID:38955356 | DOI:10.1002/jbio.202400200

Phys Med Biol. 2024 Jul 2. doi: 10.1088/1361-6560/ad5e59. Online ahead of print.

ABSTRACT

OBJECTIVE: Sparse-view dual-energy spectral computed tomography (DECT) imaging
is a challenging inverse problem. Due to the incompleteness of the collected data,
the presence of streak artifacts can result in the degradation of reconstructed spectral
images. The subsequent material decomposition task in DECT can further lead to
the amplification of artifacts and noise.

APPROACH: To address this problem, we
propose a novel one-step inverse generation network (OIGN) for sparse-view dual-
energy CT imaging, which can achieve simultaneous imaging of spectral images and
materials. The entire OIGN consists of five sub-networks that form four modules,
including the pre-reconstruction module, the pre-decomposition module, and the
following residual filtering module and residual decomposition module. The residual
feedback mechanism is introduced to synchronize the optimization of spectral CT
images and materials.

MAIN RESULTS: Numerical simulation experiments show that the
OIGN has better performance on both reconstruction and material decomposition than
other state-of-the-art spectral CT imaging algorithms. OIGN also demonstrates high
imaging efficiency by completing two high-quality imaging tasks in just 50 seconds.
Additionally, anti-noise testing is conducted to evaluate the robustness of OIGN.
Significance. These findings have great potential in high-quality multi-task spectral
CT imaging in clinical diagnosis.

PMID:38955333 | DOI:10.1088/1361-6560/ad5e59

Phys Med Biol. 2024 Jul 2. doi: 10.1088/1361-6560/ad5e31. Online ahead of print.

ABSTRACT


The trend in the medical field is towards intelligent detection-based medical diagnostic systems. However, these methods are often seen as "black boxes" due to their lack of interpretability. This situation presents challenges in identifying reasons for misdiagnoses and improving accuracy, which leads to potential risks of misdiagnosis and delayed treatment. Therefore, how to enhance the interpretability of diagnostic models is crucial for improving patient outcomes and reducing treatment delays. So far, only limited researches exist on deep learning-based prediction of spontaneous pneumothorax, a pulmonary disease that affects lung ventilation and venous return. 

Approach. 
This study develops an integrated medical image analysis system using explainable deep learning model for image recognition and visualization to achieve an interpretable automatic diagnosis process.

Main results.
The system achieves an impressive 95.56% accuracy in pneumothorax classification, which emphasizes the significance of the blood vessel penetration defect in clinical judgment.

Significance.
This would lead to improve model trustworthiness, reduce uncertainty, and accurate diagnosis of various lung diseases, which results in better medical outcomes for patients and better utilization of medical resources. Future research can focus on implementing new deep learning models to detect and diagnose other lung diseases that can enhance the generalizability of this system.&#xD.

PMID:38955331 | DOI:10.1088/1361-6560/ad5e31

Brain Res. 2024 Jun 30:149103. doi: 10.1016/j.brainres.2024.149103. Online ahead of print.

ABSTRACT

Amyloid PET scans help in identifying the beta-amyloid deposition in different brain regions. The purpose of this study is to develop a deep learning model that can automate the task of finding amyloid deposition in different regions of the brain only by using PET scan and without the corresponding MRI scan. 2647 18F-Florbetapir PET scans are collected from Alzheimer's Disease Neuroimaging Initiative (ADNI) from multiple centres taken over a period. A deep learning model based on multi-instance learning and attention is proposed which is trained and validated using 80% of the scans and the remaining 20% of the scans are used for testing the model. The performance of the model is validated using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The proposed model is further tested upon an external dataset consisting of 1413 18F-Florbetapir PET scans from the Anti-Amyloid Treatment in Asymptomatic Alzheimer's (A4) study. The proposed model achieves MAE of 0.0243 and RMSE of 0.0320 for summary Standardized Uptake Value Ratio (SUVR) based on composite reference region for ADNI test set. When tested on the A4-study dataset, the proposed model achieves MAE of 0.038 and RMSE of 0.0495 for summary SUVR based on the composite region The results show that the proposed model provides less MAE and RMSE when compared with existing models. A graphical user interface is developed based on the proposed model where the predictions are made by selecting the files of 18F-Florbetapir PET scans.

PMID:38955250 | DOI:10.1016/j.brainres.2024.149103

Cell Genom. 2024 Jun 25:100603. doi: 10.1016/j.xgen.2024.100603. Online ahead of print.

ABSTRACT

The uncovering of protein-RNA interactions enables a deeper understanding of RNA processing. Recent multiplexed crosslinking and immunoprecipitation (CLIP) technologies such as antibody-barcoded eCLIP (ABC) dramatically increase the throughput of mapping RNA binding protein (RBP) binding sites. However, multiplex CLIP datasets are multivariate, and each RBP suffers non-uniform signal-to-noise ratio. To address this, we developed Mudskipper, a versatile computational suite comprising two components: a Dirichlet multinomial mixture model to account for the multivariate nature of ABC datasets and a softmasking approach that identifies and removes non-specific protein-RNA interactions in RBPs with low signal-to-noise ratio. Mudskipper demonstrates superior precision and recall over existing tools on multiplex datasets and supports analysis of repetitive elements and small non-coding RNAs. Our findings unravel splicing outcomes and variant-associated disruptions, enabling higher-throughput investigations into diseases and regulation mediated by RBPs.

PMID:38955188 | DOI:10.1016/j.xgen.2024.100603

Biomed Phys Eng Express. 2024 Jul 2. doi: 10.1088/2057-1976/ad5db2. Online ahead of print.

ABSTRACT

The prevalence of vision impairment is increasing at an alarming rate. The goal of the study was to create an automated method that uses optical coherence tomography (OCT) to classify retinal disorders into four categories: choroidal neovascularization, diabetic macular edema, drusen, and normal cases. This study proposed a new framework that combines machine learning and deep learning-based techniques. The utilized classifiers were support vector machine (SVM), K-nearest neighbor (K-NN), decision tree (DT), and ensemble model (EM). A feature extractor, the InceptionV3 convolutional neural network, was also employed. The performance of the models was evaluated against nine criteria using a dataset of 18000 OCT images. For the SVM, K-NN, DT, and EM classifiers, the analysis exhibited state-of-the-art performance, with classification accuracies of 99.43%, 99.54%, 97.98%, and 99.31%, respectively. A promising methodology has been introduced for the automatic identification and classification of retinal disorders, leading to reduced human error and saved time.&#xD.

PMID:38955139 | DOI:10.1088/2057-1976/ad5db2

Comput Biol Med. 2024 Jul 1;179:108729. doi: 10.1016/j.compbiomed.2024.108729. Online ahead of print.

ABSTRACT

Recent studies have illuminated the critical role of the human microbiome in maintaining health and influencing the pharmacological responses of drugs. Clinical trials, encompassing approximately 150 drugs, have unveiled interactions with the gastrointestinal microbiome, resulting in the conversion of these drugs into inactive metabolites. It is imperative to explore the field of pharmacomicrobiomics during the early stages of drug discovery, prior to clinical trials. To achieve this, the utilization of machine learning and deep learning models is highly desirable. In this study, we have proposed graph-based neural network models, namely GCN, GAT, and GINCOV models, utilizing the SMILES dataset of drug microbiome. Our primary objective was to classify the susceptibility of drugs to depletion by gut microbiota. Our results indicate that the GINCOV surpassed the other models, achieving impressive performance metrics, with an accuracy of 93% on the test dataset. This proposed Graph Neural Network (GNN) model offers a rapid and efficient method for screening drugs susceptible to gut microbiota depletion and also encourages the improvement of patient-specific dosage responses and formulations.

PMID:38955124 | DOI:10.1016/j.compbiomed.2024.108729

Accid Anal Prev. 2024 Jul 1;205:107693. doi: 10.1016/j.aap.2024.107693. Online ahead of print.

ABSTRACT

Examining the relationship between streetscape features and road traffic accidents is pivotal for enhancing roadway safety. While previous studies have primarily focused on the influence of street design characteristics, sociodemographic features, and land use features on crash occurrence, the impact of streetscape features on pedestrian crashes has not been thoroughly investigated. Furthermore, while machine learning models demonstrate high accuracy in prediction and are increasingly utilized in traffic safety research, understanding the prediction results poses challenges. To address these gaps, this study extracts streetscape environment characteristics from street view images (SVIs) using a combination of semantic segmentation and object detection deep learning networks. These characteristics are then incorporated into the eXtreme Gradient Boosting (XGBoost) algorithm, along with a set of control variables, to model the occurrence of pedestrian crashes at intersections. Subsequently, the SHapley Additive exPlanations (SHAP) method is integrated with XGBoost to establish an interpretable framework for exploring the association between pedestrian crash occurrence and the surrounding streetscape built environment. The results are interpreted from global, local, and regional perspectives. The findings indicate that, from a global perspective, traffic volume and commercial land use are significant contributors to pedestrian-vehicle collisions at intersections, while road, person, and vehicle elements extracted from SVIs are associated with higher risks of pedestrian crash onset. At a local level, the XGBoost-SHAP framework enables quantification of features' local contributions for individual intersections, revealing spatial heterogeneity in factors influencing pedestrian crashes. From a regional perspective, similar intersections can be grouped to define geographical regions, facilitating the formulation of spatially responsive strategies for distinct regions to reduce traffic accidents. This approach can potentially enhance the quality and accuracy of local policy making. These findings underscore the underlying relationship between streetscape-level environmental characteristics and vehicle-pedestrian crashes. The integration of SVIs and deep learning techniques offers a visually descriptive portrayal of the streetscape environment at locations where traffic crashes occur at eye level. The proposed framework not only achieves excellent prediction performance but also enhances understanding of traffic crash occurrences, offering guidance for optimizing traffic accident prevention and treatment programs.

PMID:38955107 | DOI:10.1016/j.aap.2024.107693

Comput Methods Programs Biomed. 2024 Jun 25;254:108304. doi: 10.1016/j.cmpb.2024.108304. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVES: In ultrasound guided high-intensity focused ultrasound (HIFU) surgery, it is necessary to transmit sound waves at different frequencies simultaneously using two transducers: one for the HIFU therapy and another for the ultrasound imaging guidance. In this specific setting, real-time monitoring of non-invasive surgery is challenging due to severe contamination of the ultrasound guiding images by strong acoustic interference from the HIFU sonication.

METHODS: This paper proposed the use of a deep learning (DL) solution, specifically a diffusion implicit model, to suppress the HIFU interference. We considered the images contaminated with HIFU interference as low-resolution images, and those free from interference as high-resolution. While suppressing HIFU interference using the diffusion implicit (HIFU-Diff) model, the task was transformed into generating a high-resolution image through a series of forward diffusion steps and reverse sampling. A series of ex-vivo and in-vivo experiments, conducted under various parameters, were designed to validate the performance of the proposed network.

RESULTS: Quantitative evaluation and statistical analysis demonstrated that the HIFU-Diff network achieved superior performance in reconstructing interference-free images under a variety of ex-vivo and in-vivo conditions, compared to the most commonly used notch filtering and the recent 1D FUS-Net deep learning network. The HIFU-Diff maintains high performance with 'unseen' datasets from separate experiments, and its superiority is more pronounced under strong HIFU interferences and in complex in-vivo situations. Furthermore, the reconstructed interference-free images can also be used for quantitative attenuation imaging, indicating that the network preserves acoustic characteristics of the ultrasound images.

CONCLUSIONS: With the proposed technique, HIFU therapy and the ultrasound imaging can be conducted simultaneously, allowing for real-time monitoring of the treatment process. This capability could significantly enhance the safety and efficacy of the non-invasive treatment across various clinical applications. To the best of our knowledge, this is the first diffusion-based model developed for HIFU interference suppression.

PMID:38954917 | DOI:10.1016/j.cmpb.2024.108304

Comput Biol Chem. 2024 Jun 15;112:108130. doi: 10.1016/j.compbiolchem.2024.108130. Online ahead of print.

ABSTRACT

Retrosynthesis is vital in synthesizing target products, guiding reaction pathway design crucial for drug and material discovery. Current models often neglect multi-scale feature extraction, limiting efficacy in leveraging molecular descriptors. Our proposed SB-Net model, a deep-learning architecture tailored for retrosynthesis prediction, addresses this gap. SB-Net combines CNN and Bi-LSTM architectures, excelling in capturing multi-scale molecular features. It integrates parallel branches for processing one-hot encoded descriptors and ECFP, merging through dense layers. Experimental results demonstrate SB-Net's superiority, achieving 73.6 % top-1 and 94.6 % top-10 accuracy on USPTO-50k data. Versatility is validated on MetaNetX, with rates of 52.8 % top-1, 74.3 % top-3, 79.8 % top-5, and 83.5 % top-10. SB-Net's success in bioretrosynthesis prediction tasks indicates its efficacy. This research advances computational chemistry, offering a robust deep-learning model for retrosynthesis prediction. With implications for drug discovery and synthesis planning, SB-Net promises innovative and efficient pathways.

PMID:38954849 | DOI:10.1016/j.compbiolchem.2024.108130

Br J Radiol. 2024 Jul 2:tqae120. doi: 10.1093/bjr/tqae120. Online ahead of print.

NO ABSTRACT

PMID:38954833 | DOI:10.1093/bjr/tqae120

J Am Soc Mass Spectrom. 2024 Jul 2. doi: 10.1021/jasms.4c00144. Online ahead of print.

ABSTRACT

We have recently developed a charge inversion ion/ion reaction to selectively derivatize phosphatidylserine lipids via gas-phase Schiff base formation. This tandem mass spectrometry (MS/MS) workflow enables the separation and detection of isobaric lipids in imaging mass spectrometry, but the images acquired using this workflow are limited to relatively poor spatial resolutions due to the current time and limit of detection requirements for these ion/ion reaction imaging mass spectrometry experiments. This trade-off between chemical specificity and spatial resolution can be overcome by using computational image fusion, which combines complementary information from multiple images. Herein, we demonstrate a proof-of-concept workflow that fuses a low spatial resolution (i.e., 125 μm) ion/ion reaction product ion image with higher spatial resolution (i.e., 25 μm) ion images from a full scan experiment performed using the same tissue section, which results in a predicted ion/ion reaction product ion image with a 5-fold improvement in spatial resolution. Linear regression, random forest regression, and two-dimensional convolutional neural network (2-D CNN) predictive models were tested for this workflow. Linear regression and 2D CNN models proved optimal for predicted ion/ion images of PS 40:6 and SHexCer d38:1, respectively.

PMID:38954826 | DOI:10.1021/jasms.4c00144

PLoS One. 2024 Jul 2;19(7):e0306090. doi: 10.1371/journal.pone.0306090. eCollection 2024.

ABSTRACT

Diabetes is a chronic disease, which is characterized by abnormally high blood sugar levels. It may affect various organs and tissues, and even lead to life-threatening complications. Accurate prediction of diabetes can significantly reduce its incidence. However, the current prediction methods struggle to accurately capture the essential characteristics of nonlinear data, and the black-box nature of these methods hampers its clinical application. To address these challenges, we propose KCCAM_DNN, a diabetes prediction method that integrates Kendall's correlation coefficient and an attention mechanism within a deep neural network. In the KCCAM_DNN, Kendall's correlation coefficient is initially employed for feature selection, which effectively filters out key features influencing diabetes prediction. For missing values in the data, polynomial regression is utilized for imputation, ensuring data completeness. Subsequently, we construct a deep neural network (KCCAM_DNN) based on the self-attention mechanism, which assigns greater weight to crucial features affecting diabetes and enhances the model's predictive performance. Finally, we employ the SHAP model to analyze the impact of each feature on diabetes prediction, augmenting the model's interpretability. Experimental results show that KCCAM_DNN exhibits superior performance on both PIMA Indian and LMCH diabetes datasets, achieving test accuracies of 99.090% and 99.333%, respectively, approximately 2% higher than the best existing method. These results suggest that KCCAM_DNN is proficient in diabetes prediction, providing a foundation for informed decision-making in the diagnosis and prevention of diabetes.

PMID:38954714 | DOI:10.1371/journal.pone.0306090

IEEE Trans Pattern Anal Mach Intell. 2024 Jul 2;PP. doi: 10.1109/TPAMI.2024.3421359. Online ahead of print.

ABSTRACT

Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant challenges to effective and efficient processing. Existing deep point cloud sequence modeling approaches imitate the mature 2D video learning mechanisms by developing complex spatio-temporal point neighbor grouping and feature aggregation schemes, often resulting in methods lacking effectiveness, efficiency, and expressive power. In this paper, we propose a novel generic representation called Structured Point Cloud Videos (SPCVs). Intuitively, by leveraging the fact that 3D geometric shapes are essentially 2D manifolds, SPCV re-organizes a point cloud sequence as a 2D video with spatial smoothness and temporal consistency, where the pixel values correspond to the 3D coordinates of points. The structured nature of our SPCV representation allows for the seamless adaptation of well-established 2D image/video techniques, enabling efficient and effective processing and analysis of 3D point cloud sequences. To achieve such re-organization, we design a self-supervised learning pipeline that is geometrically regularized and driven by self-reconstructive and deformation field learning objectives. Additionally, we construct SPCV-based frameworks for both low-level and high-level 3D point cloud sequence processing and analysis tasks, including action recognition, temporal interpolation, and compression. Extensive experiments demonstrate the versatility and superiority of the proposed SPCV, which has the potential to offer new possibilities for deep learning on unstructured 3D point cloud sequences. Code will be released at https://github.com/ZENGYIMING-EAMON/SPCV.

PMID:38954587 | DOI:10.1109/TPAMI.2024.3421359

IEEE Trans Med Imaging. 2024 Jul 2;PP. doi: 10.1109/TMI.2024.3422102. Online ahead of print.

ABSTRACT

A large-scale labeled dataset is a key factor for the success of supervised deep learning in most ophthalmic image analysis scenarios. However, limited annotated data is very common in ophthalmic image analysis, since manual annotation is time-consuming and labor-intensive. Self-supervised learning (SSL) methods bring huge opportunities for better utilizing unlabeled data, as they do not require massive annotations. To utilize as many unlabeled ophthalmic images as possible, it is necessary to break the dimension barrier, simultaneously making use of both 2D and 3D images as well as alleviating the issue of catastrophic forgetting. In this paper, we propose a universal self-supervised Transformer framework named Uni4Eye++ to discover the intrinsic image characteristic and capture domain-specific feature embedding in ophthalmic images. Uni4Eye++ can serve as a global feature extractor, which builds its basis on a Masked Image Modeling task with a Vision Transformer architecture. On the basis of our previous work Uni4Eye, we further employ an image entropy guided masking strategy to reconstruct more-informative patches and a dynamic head generator module to alleviate modality confusion. We evaluate the performance of our pre-trained Uni4Eye++ encoder by fine-tuning it on multiple downstream ophthalmic image classification and segmentation tasks. The superiority of Uni4Eye++ is successfully established through comparisons to other state-of-the-art SSL pre-training methods. Our code is available at Github1.

PMID:38954581 | DOI:10.1109/TMI.2024.3422102

IEEE Trans Neural Netw Learn Syst. 2024 Jul 2;PP. doi: 10.1109/TNNLS.2024.3416701. Online ahead of print.

ABSTRACT

Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations or to translate signals from one domain to another (as in image captioning or text-to-image generation). However, current approaches mainly rely on brute-force supervised training over large multimodal datasets. In contrast, humans (and other animals) can learn useful multimodal representations from only sparse experience with matched cross-modal data. Here, we evaluate the capabilities of a neural network architecture inspired by the cognitive notion of a "global workspace" (GW): a shared representation for two (or more) input modalities. Each modality is processed by a specialized system (pretrained on unimodal data and subsequently frozen). The corresponding latent representations are then encoded to and decoded from a single shared workspace. Importantly, this architecture is amenable to self-supervised training via cycle-consistency: encoding-decoding sequences should approximate the identity function. For various pairings of vision-language modalities and across two datasets of varying complexity, we show that such an architecture can be trained to align and translate between two modalities with very little need for matched data (from four to seven times less than a fully supervised approach). The GW representation can be used advantageously for downstream classification and cross-modal retrieval tasks and for robust transfer learning. Ablation studies reveal that both the shared workspace and the self-supervised cycle-consistency training are critical to the system's performance.

PMID:38954575 | DOI:10.1109/TNNLS.2024.3416701

IEEE J Biomed Health Inform. 2024 Jul 2;PP. doi: 10.1109/JBHI.2024.3422180. Online ahead of print.

ABSTRACT

In recent years, data-driven remote medical management has received much attention, especially in application of survival time forecasting. By monitoring the physical characteristics indexes of patients, intelligent algorithms can be deployed to implement efficient healthcare management. However, such pure medical data-driven scenes generally lack multimedia information, which brings challenge to analysis tasks. To deal with this issue, this paper introduces the idea of ensemble deep learning to enhance feature representation ability, thus enhancing knowledge discovery in remote healthcare management. Therefore, a multiview deep learning-based efficient medical data management framework for survival time forecasting is proposed in this paper, which is named as "MDL-MDM" for short. Firstly, basic monitoring data for body indexes of patients is encoded, which serves as the data foundation for forecasting tasks. Then, three different neural network models, convolution neural network, graph attention network, and graph convolution network, are selected to build a hybrid computing framework. Their combination can bring a multiview feature learning framework to realize an efficient medical data management framework. In addition, experiments are conducted on a realistic medical dataset about cancer patients in the US. Results show that the proposal can predict survival time with 1% to 2% reduction in prediction error.

PMID:38954570 | DOI:10.1109/JBHI.2024.3422180

IEEE J Biomed Health Inform. 2024 Jul 2;PP. doi: 10.1109/JBHI.2024.3421550. Online ahead of print.

ABSTRACT

Accurate segmentation of colorectal polyps in colonoscopy images is crucial for effective diagnosis and management of colorectal cancer (CRC). However, current deep learning-based methods primarily rely on fusing RGB information across multiple scales, leading to limitations in accurately identifying polyps due to restricted RGB domain information and challenges in feature misalignment during multi-scale aggregation. To address these limitations, we propose the Polyp Segmentation Network with Shunted Transformer (PSTNet), a novel approach that integrates both RGB and frequency domain cues present in the images. PSTNet comprises three key modules: the Frequency Characterization Attention Module (FCAM) for extracting frequency cues and capturing polyp characteristics, the Feature Supplementary Alignment Module (FSAM) for aligning semantic information and reducing misalignment noise, and the Cross Perception localization Module (CPM) for synergizing frequency cues with high-level semantics to achieve efficient polyp segmentation. Extensive experiments on challenging datasets demonstrate PSTNet's significant improvement in polyp segmentation accuracy across various metrics, consistently outperforming state-of-the-art methods. The integration of frequency domain cues and the novel architectural design of PSTNet contribute to advancing computer-assisted polyp segmentation, facilitating more accurate diagnosis and management of CRC. Our source code is available for reference at https://github.com/clearxu/PSTNet.

PMID:38954569 | DOI:10.1109/JBHI.2024.3421550

IEEE J Biomed Health Inform. 2024 Jul 2;PP. doi: 10.1109/JBHI.2024.3422177. Online ahead of print.

ABSTRACT

Deep learning methods have recently achieved remarkable performance in vessel segmentation applications, yet require numerous labor-intensive labeled data. To alleviate the requirement of manual annotation, transfer learning methods can potentially be used to acquire the related knowledge of tubular structures from public large-scale labeled vessel datasets for target vessel segmentation in other anatomic sites of the human body. However, the cross-anatomy domain shift is a challenging task due to the formidable discrepancy among various vessel structures in different anatomies, resulting in the limited performance of transfer learning. Therefore, we propose a cross-anatomy transfer learning framework for 3D vessel segmentation, which first generates a pre-trained model on a public hepatic vessel dataset and then adaptively fine-tunes our target segmentation network initialized from the model for segmentation of other anatomic vessels. In the framework, the adaptive fine-tuning strategy is presented to dynamically decide on the frozen or fine-tuned filters of the target network for each input sample with a proxy network. Moreover, we develop a Gaussian-based signed distance map that explicitly encodes vessel-specific shape context. The prediction of the map is added as an auxiliary task in the segmentation network to capture geometry-aware knowledge in the fine-tuning. We demonstrate the effectiveness of our method through extensive experiments on two small-scale datasets of coronary artery and brain vessel. The results indicate the proposed method effectively overcomes the discrepancy of cross-anatomy domain shift to achieve accurate vessel segmentation for these two datasets.

PMID:38954568 | DOI:10.1109/JBHI.2024.3422177

Curr Allergy Asthma Rep. 2024 Jul 2. doi: 10.1007/s11882-024-01152-y. Online ahead of print.

ABSTRACT

PURPOSE OF REVIEW: Artificial intelligence (AI), be it neuronal networks, machine learning or deep learning, has numerous beneficial effects on healthcare systems; however, its potential applications and diagnostic capabilities for immunologic diseases have yet to be explored. Understanding AI systems can help healthcare workers better assimilate artificial intelligence into their practice and unravel its potential in diagnostics, clinical research, and disease management.

RECENT FINDINGS: We reviewed recent advancements in AI systems and their integration in healthcare systems, along with their potential benefits in the diagnosis and management of diseases. We explored machine learning as employed in allergy diagnosis and its learning patterns from patient datasets, as well as the possible advantages of using AI in the field of research related to allergic reactions and even remote monitoring. Considering the ethical challenges and privacy concerns raised by clinicians and patients with regard to integrating AI in healthcare, we explored the new guidelines adapted by regulatory bodies. Despite these challenges, AI appears to have been successfully incorporated into various healthcare systems and is providing patient-centered solutions while simultaneously assisting healthcare workers. Artificial intelligence offers new hope in the field of immunologic disease diagnosis, monitoring, and management and thus has the potential to revolutionize healthcare systems.

PMID:38954325 | DOI:10.1007/s11882-024-01152-y