Computer methods and programs in biomedicine最新文献

Background and Objectives:

Artificial intelligence (AI) is revolutionizing Magnetic Resonance Imaging (MRI) along the acquisition and processing chain. Advanced AI frameworks have been applied in various successive tasks, such as image reconstruction, quantitative parameter map estimation, and image segmentation. However, existing frameworks are often designed to perform tasks independently of each other or are focused on specific models or single datasets, limiting generalization. This work introduces the Advanced Toolbox for Multitask Medical Imaging Consistency (ATOMMIC), a novel open-source toolbox that streamlines AI applications for accelerated MRI reconstruction and analysis. ATOMMIC implements several tasks using deep learning (DL) models and enables MultiTask Learning (MTL) to perform related tasks in an integrated manner, targeting generalization in the MRI domain.

Methods:

We conducted a comprehensive literature review and analyzed 12,479 GitHub repositories to assess the current landscape of AI frameworks for MRI. Subsequently, we demonstrate how ATOMMIC standardizes workflows and improves data interoperability, enabling effective benchmarking of various DL models across MRI tasks and datasets. To showcase ATOMMIC’s capabilities, we evaluated twenty-five DL models on eight publicly available datasets, focusing on accelerated MRI reconstruction, segmentation, quantitative parameter map estimation, and joint accelerated MRI reconstruction and segmentation using MTL.

Results:

ATOMMIC’s high-performance training and testing capabilities, utilizing multiple GPUs and mixed precision support, enable efficient benchmarking of multiple models across various tasks. The framework’s modular architecture implements each task through a collection of data loaders, models, loss functions, evaluation metrics, and pre-processing transformations, facilitating seamless integration of new tasks, datasets, and models. Our findings demonstrate that ATOMMIC supports MTL for multiple MRI tasks with harmonized complex-valued and real-valued data support while maintaining active development and documentation. Task-specific evaluations demonstrate that physics-based models outperform other approaches in reconstructing highly accelerated acquisitions. These high-quality reconstruction models also show superior accuracy in estimating quantitative parameter maps. Furthermore, when combining high-performing reconstruction models with robust segmentation networks through MTL, performance is improved in both tasks.

Conclusions:

ATOMMIC advances MRI reconstruction and analysis by leveraging MTL and ensuring consistency across tasks, models, and datasets. This comprehensive framework serves as a versatile platform for researchers to use existing AI methods and develop new approaches in medical imaging.

As the global incidence of cancer continues to rise rapidly, the need for swift and precise diagnoses has become increasingly pressing. Pathologists commonly rely on H&E-panCK stain pairs for various aspects of cancer diagnosis, including the detection of occult tumor cells and the evaluation of tumor budding. Nevertheless, conventional chemical staining methods suffer from notable drawbacks, such as time-intensive processes and irreversible staining outcomes. The virtual stain technique, leveraging generative adversarial network (GAN), has emerged as a promising alternative to chemical stains. This approach aims to transform biopsy scans (often H&E) into other stain types. Despite achieving notable progress in recent years, current state-of-the-art virtual staining models confront challenges that hinder their efficacy, particularly in achieving accurate staining outcomes under specific conditions. These limitations have impeded the practical integration of virtual staining into diagnostic practices. To address the goal of producing virtual panCK stains capable of replacing chemical panCK, we propose an innovative multi-model framework. Our approach involves employing a combination of Mask-RCNN (for cell segmentation) and GAN models to extract cytokeratin distribution from chemical H&E images. Additionally, we introduce a tailored dynamic GAN model to convert H&E images into virtual panCK stains, integrating the derived cytokeratin distribution. Our framework is motivated by the fact that the unique pattern of the panCK is derived from cytokeratin distribution. As a proof of concept, we employ our virtual panCK stains to evaluate tumor budding in 45 H&E whole-slide images taken from breast cancer-invaded lymph nodes . Through thorough validation by both pathologists and the QuPath software, our virtual panCK stains demonstrate a remarkable level of accuracy. In stark contrast, the accuracy of state-of-the-art single cycleGAN virtual panCK stains is negligible. To our best knowledge, this is the first instance of a multi-model virtual panCK framework and the utilization of virtual panCK for tumor budding assessment. Our framework excels in generating dependable virtual panCK stains with significantly improved efficiency, thereby considerably reducing turnaround times in diagnosis. Furthermore, its outcomes are easily comprehensible even to pathologists who may not be well-versed in computer technology. We firmly believe that our framework has the potential to advance the field of virtual stain, thereby making significant strides towards improved cancer diagnosis.

Background:

Material characterization of brain white matter (BWM) is difficult due to the anisotropy inherent to the three-dimensional microstructure and the various interactions between heterogeneous brain-tissue (axon, myelin, and glia). Developing full scale finite element models that accurately represent the relationship between the micro and macroscale BWM is however extremely challenging and computationally expensive. The anisotropic properties of the microstructure of BWM computed by building unit cells under frequency domain viscoelasticity comprises of 36 individual constants each, for the loss and storage moduli. Furthermore, the architecture of each unit cell is arbitrary in an infinite dataset.

Methods:

In this study, we extend our previous work on developing representative volume elements (RVE) of the microstructure of the BWM in the frequency domain to develop 3D deep learning algorithms that can predict the anisotropic composite properties. The deep 3D convolutional neural network (CNN) algorithms utilizes a voxelization method to obtain geometry information from 3D RVEs. The architecture information encoded in the voxelized location is employed as input data while cross-referencing the RVEs’ material properties (output data). We further develop methods by incorporating parallel pathways, Residual Neural Networks and inception modulus that improve the efficiency of deep learning algorithms.

Results:

This paper presents different CNN algorithms in predicting the anisotropic composite properties of BWM. A quantitative analysis of the individual algorithms is presented with the view of identifying optimal strategies to interpret the combined measurements of brain MRE and DTI.

Significance:

The proposed Multiscale 3D ResNet (M3DR) algorithm demonstrates high learning ability and performance over baseline CNN algorithms in predicting BWM tissue properties. The hybrid M3DR framework also overcomes the significant limitations encountered in modeling brain tissue using finite elements alone including those such as high computational cost, mesh and simulation failure. The proposed framework also provides an efficient and streamlined platform for implementing complex boundary conditions, modeling intrinsic material properties and imparting interfacial architecture information.

Background and Objective

Tinnitus is a neuropathological condition that results in mild buzzing or ringing of the ears without an external sound source. Current tinnitus diagnostic methods often rely on subjective assessment and require intricate medical examinations. This study aimed to propose an interpretable tinnitus diagnostic framework using auditory late response (ALR) and electroencephalogram (EEG), inspired by the gap-prepulse inhibition (GPI) paradigm.

Methods

We collected spontaneous EEG and ALR data from 44 patients with tinnitus and 47 hearing loss-matched controls using specialized hardware to capture responses to sound stimuli with embedded gaps. In this cohort study of tinnitus and control groups, we examined EEG spectral and ALR features of N-P complexes, comparing the responses to gap durations of 50 and 20 ms alongside no-gap conditions. To this end, we developed an interpretable tinnitus diagnostic model using ALR and EEG metrics, boosting machine learning architecture, and explainable feature attribution approaches.

Results

Our proposed model achieved 90 % accuracy in identifying tinnitus, with an area under the performance curve of 0.89. The explainable artificial intelligence approaches have revealed gap-embedded ALR features such as the GPI ratio of N1-P2 and EEG spectral ratio, which can serve as diagnostic metrics for tinnitus. Our method successfully provides personalized prediction explanations for tinnitus diagnosis using gap-embedded auditory and neurological features.

Conclusions

Deficits in GPI alongside activity in the EEG alpha-beta ratio offer a promising screening tool for assessing tinnitus risk, aligning with current clinical insights from hearing research.

Introduction:

We propose a novel approach for the non-invasive quantification of dynamic PET imaging data, focusing on the arterial input function (AIF) without the need for invasive arterial cannulation.

Methods:

Our method utilizes a combination of three-dimensional depth-wise separable convolutional layers and a physically informed deep neural network to incorporatea priori knowledge about the AIF’s functional form and shape, enabling precise predictions of the concentrations of [${}^{11}C$]PBR28 in whole blood and the free tracer in metabolite-corrected plasma.

Results:

We found a robust linear correlation between our model’s predicted AIF curves and those obtained through traditional, invasive measurements. We achieved an average cross-validated Pearson correlation of 0.86 for whole blood and 0.89 for parent plasma curves. Moreover, our method’s ability to estimate the volumes of distribution across several key brain regions – without significant differences between the use of predicted versus actual AIFs in a two-tissue compartmental model – successfully captures the intrinsic variability related to sex, the binding affinity of the translocator protein (18 kDa), and age.

Conclusions:

These results not only validate our method’s accuracy and reliability but also establish a foundation for a streamlined, non-invasive approach to dynamic PET data quantification. By offering a precise and less invasive alternative to traditional quantification methods, our technique holds significant promise for expanding the applicability of PET imaging across a wider range of tracers, thereby enhancing its utility in both clinical research and diagnostic settings.

Background and objectives:

In endoscopy, measurement of target size can assist medical diagnosis. However, limited operating space, low image quality, and irregular target shape pose great challenges to traditional vision-based measurement methods.

Methods:

In this paper, we propose a novel approach to measure irregular target size under monocular endoscope using image rendering. Firstly synthesize virtual poses on the same main optical axis as known camera poses, and use implicit neural representation module that considers brightness and target boundaries to render images corresponding to virtual poses. Then, Swin-Unet and rotating calipers are utilized to obtain maximum pixel length of the target in image pairs with the same main optical axis. Finally, the similarity triangle relationship of the endoscopic imaging model is used to measure the size of the target.

Results:

The evaluation is conducted using renal stone fragments of patients which are placed in the kidney model and the isolated porcine kidney. The mean error of measurement is 0.12 mm.

Conclusions:

The approached method can automatically measure object size within narrow body cavities in any visible direction. It improves the effectiveness and accuracy of measurement in limited endoscopic space.

Background and objective:

The incidence of facial fractures is on the rise globally, yet limited studies are addressing the diverse forms of facial fractures present in 3D images. In particular, due to the nature of the facial fracture, the direction in which the bone fractures vary, and there is no clear outline, it is difficult to determine the exact location of the fracture in 2D images. Thus, 3D image analysis is required to find the exact fracture area, but it needs heavy computational complexity and expensive pixel-wise labeling for supervised learning. In this study, we tackle the problem of reducing the computational burden and increasing the accuracy of fracture localization by using a weakly-supervised object localization without pixel-wise labeling in a 3D image space.

Methods:

We propose a Very Fast, High-Resolution Aggregation 3D Detection CAM (VFHA-CAM) model, which can detect various facial fractures. To better detect tiny fractures, our model uses high-resolution feature maps and employs Ablation CAM to find an exact fracture location without pixel-wise labeling, where we use a rough fracture image detected with 3D box-wise labeling. To this end, we extract important features and use only essential features to reduce the computational complexity in 3D image space.

Results:

Experimental findings demonstrate that VFHA-CAM surpasses state-of-the-art 2D detection methods by up to 20% in sensitivity/person and specificity/person, achieving sensitivity/person and specificity/person scores of 87% and 85%, respectively. In addition, Our VFHA-CAM reduces location analysis time to 76 s without performance degradation compared to a simple Ablation CAM method that takes more than 20 min.

Conclusion:

This study introduces a novel weakly-supervised object localization approach for bone fracture detection in 3D facial images. The proposed method employs a 3D detection model, which helps detect various forms of facial bone fractures accurately. The CAM algorithm adopted for fracture area segmentation within a 3D fracture detection box is key in quickly informing medical staff of the exact location of a facial bone fracture in a weakly-supervised object localization. In addition, we provide 3D visualization so that even non-experts unfamiliar with 3D CT images can identify the fracture status and location.

Background and objective

Alzheimer's disease (AD) is one of the leading causes of dementia, affecting the world's population at a growing rate. The preclinical stage of AD lasts over a decade, hence understanding AD-related early neuropathological effects on brain function at this stage facilitates early detection of the disease.

Methods

Resting-state functional magnetic resonance imaging (rs-fMRI) has been a powerful tool for understanding brain function, and it has been widely used in AD research. In this study, we apply Recurrence Quantification Analysis (RQA) on rs-fMRI images of 4-months (4 m) and 6-months-old (6 m) TgF344-AD rats and WT littermates to identify changes related to the AD phenotype and aging. RQA has been focused on areas of the default mode-like network (DMLN) and was performed based on Recurrence Plots (RP). RP is a mathematical representation of any dynamical system that evolves over time as a set of its state recurrences. In this paper, RPs were extracted in order to identify the affected regions of the DMLN at very early stages of AD.

Results

Using the RQA approach, we identified significant changes related to the AD phenotype at 4 m and/or 6 m in several areas of the rat DMLN including the BFB, Hippocampal fields CA1 and CA3, CG1, CG2, PrL, PtA, RSC, TeA, V1, V2. In addition, with age, brain activity of WT rats showed less predictability, while the AD rats presented reduced decline of predictability.

Conclusions

The results of this study demonstrate that RQA of rs-fMRI data is a potent approach that can detect subtle changes which might be missed by other methodologies due to the brain's non-linear dynamics. Moreover, this study provides helpful information about specific areas involved in AD pathology at very early stages of the disease in a very promising rat model of AD. Our results provide valuable information for the development of early detection methods and novel diagnosis tools for AD.

Background and Objective

We develop an efficient deep-learning based dual-domain reconstruction method for sparse-view CT reconstruction with small training parameters and comparable running time. We aim to investigate the model's capability and its clinical value by performing objective and subjective quality assessments using clinical CT projection data acquired on commercial scanners.

Methods

We designed two lightweight networks, namely Sino-Net and Img-Net, to restore the projection and image signal from the DD-Net reconstructed images in the projection and image domains, respectively. The proposed network has small training parameters and comparable running time among dual-domain based reconstruction networks and is easy to train (end-to-end). We prospectively collected clinical thoraco-abdominal CT projection data acquired on a Siemens Biograph 128 Edge CT scanner to train and validate the proposed network. Further, we quantitatively evaluated the CT Hounsfield unit (HU) values on 21 organs and anatomic structures, such as the liver, aorta, and ribcage. We also analyzed the noise properties and compared the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) of the reconstructed images. Besides, two radiologists conducted the subjective qualitative evaluation including the confidence and conspicuity of anatomic structures, and the overall image quality using a 1–5 likert scoring system.

Results

Objective and subjective evaluation showed that the proposed algorithm achieves competitive results in eliminating noise and artifacts, restoring fine structure details, and recovering edges and contours of anatomic structures using 384 views (1/6 sparse rate). The proposed method exhibited good computational cost performance on clinical projection data.

Conclusion

This work presents an efficient dual-domain learning network for sparse-view CT reconstruction on raw projection data from a commercial scanner. The study also provides insights for designing an organ-based image quality assessment pipeline for sparse-view reconstruction tasks, potentially benefiting organ-specific dose reduction by sparse-view imaging.

Background and Objective:

Ultrasound information entropy imaging is an emerging quantitative ultrasound technique for characterizing local tissue scatterer concentrations and arrangements. However, the commonly used ultrasound Shannon entropy imaging based on histogram-derived discrete probability estimation suffers from the drawbacks of histogram settings dependence and unknown estimator performance. In this paper, we introduced the information-theoretic cumulative residual entropy (CRE) defined in a continuous distribution of cumulative distribution functions as a new entropy measure of ultrasound backscatter envelope uncertainty or complexity, and proposed ultrasound CRE imaging for tissue characterization.

Methods:

We theoretically analyzed the CRE for Rayleigh and Nakagami distributions and proposed a normalized CRE for characterizing scatterer distribution patterns. We proposed a method based on an empirical cumulative distribution function estimator and a trapezoidal numerical integration for estimating the normalized CRE from ultrasound backscatter envelope signals. We presented an ultrasound normalized CRE imaging scheme based on the normalized CRE estimator and the parallel computation technique. We also conducted theoretical analysis of the differential entropy which is an extension of the Shannon entropy to a continuous distribution, and introduced a method for ultrasound differential entropy estimation and imaging. Monte-Carlo simulation experiments were performed to evaluate the estimation accuracy of the normalized CRE and differential entropy estimators. Phantom simulation and clinical experiments were conducted to evaluate the performance of the proposed normalized CRE imaging in characterizing scatterer concentrations and hepatic steatosis ($n$ = 204), respectively.

Results:

The theoretical normalized CRE for the Rayleigh distribution was $\sqrt{\pi }/4$, corresponding to the case where there were $\ge 10$ randomly distributed scatterers within the resolution cell of an ultrasound transducer. The theoretical normalized CRE for the Nakagami distribution decreased as the Nakagami parameter $m$ increased, corresponding to that the ultrasound backscattered statistics varied from pre-Rayleigh to Rayleigh and to post-Rayleigh distributions. Monte-Carlo simulation experiments showed that the proposed normalized CRE and differential entropy estimators can produce a satisfying estimation accuracy even when the size of the test samples is small. Phantom simulation experiments showed that the proposed normalized CRE and differential entropy imaging can characterize scatterer concentrations. Clinical experiments showed that the proposed ultrasound normalized CRE imaging is capabl