Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Radiology Radiology

Characteristics of perivascular space dilatation in normal aging.

In Human brain mapping

The increased incidence of dilated perivascular spaces (dPVSs) visible on MRI has been observed with advancing age, but the relevance of PVS dilatation to normal aging across the lifespan has yet to be fully clarified. In the current study, we sought to find out the age dependence of dPVSs by exploring changes in different characteristics of PVS dilatation across a wide range of age. For 1220 healthy subjects aged between 18 and 100 years, PVSs were automatically segmented and characteristics of PVS dilatation were assessed in terms of the burden, location, and morphology of PVSs in the white matter (WM) and basal ganglia (BG). A machine learning model using the random forests method was constructed to estimate the subjects' age by employing the PVS features. The constructed machine learning model was able to estimate the age of the subjects with an error of 9.53 years on average (correlation = 0.875). The importance of the PVS features indicated the primary contribution of the burden of PVSs in the BG and the additional contribution of locational and morphological changes of PVSs, specifically peripheral extension and reduced linearity, in the WM to age estimation. Indeed, adding the PVS location or morphology features to the PVS burden features provided an improvement to the performance of age estimation. The age dependence of dPVSs in terms of such various characteristics of PVS dilatation in healthy subjects could provide a more comprehensive reference for detecting brain disease-related PVS dilatation.

Park Chang-Hyun, Shin Na-Young, Nam Yoonho, Yoon Uicheul, Ahn Kookjin, Lee Seung-Koo

2023-Mar-17

age estimation, machine learning, normal aging, perivascular space

Radiology Radiology

Overcoming the challenges to implementation of artificial intelligence in pathology.

In Journal of the National Cancer Institute

Pathologists worldwide are facing remarkable challenges with the increasing workloads and the lack of time to provide consistently high-quality patient care. The application of artificial intelligence (AI) to digital whole slide images has the potential of democratizing the access to expert pathology and affordable biomarkers, by supporting pathologists in the provision of timely and accurate diagnosis as well as supporting oncologists by extracting prognostic and predictive biomarkers directly from tissue slides. The long-awaited adoption of AI in pathology, however, has not materialized, and the transformation of pathology is happening at a pace that is much slower than that observed in other fields (eg,, radiology). Here, we provide a critical summary of the developments in digital and computational pathology in the last ten years, outline key hurdles and ways to overcome them, and provide a perspective for AI-supported precision oncology in the future.

Reis-Filho Jorge S, Kather Jakob Nikolas

2023-Mar-17

Artificial intelligence, deep learning, machine learning, oncology, pathology

General General

scMCs: a framework for single cell multi-omics data integration and multiple clusterings.

In Bioinformatics (Oxford, England)

MOTIVATION : The integration of single-cell multi-omics data can uncover the underlying regulatory basis of diverse cell types and states. However, contemporary methods disregard the omics individuality, and the high noise, sparsity, and heterogeneity of single-cell data also impact the fusion effect. Furthermore, available single-cell clustering methods only focus on the cell type clustering, which can not mine the alternative clustering to comprehensively analyze cells.

RESULTS : We propose a single-cell data fusion based multiple clustering (scMCs) approach that can jointly model single-cell transcriptomics and epigenetic data, and explore multiple different clusterings. scMCs first mines the omics-specific and cross-omics consistent representations, then fuses them into a co-embedding representation, which can dissect cellular heterogeneity and impute data. To discover the potential alternative clustering embedded in multi-omics, scMCs projects the co-embedding representation into different salient subspaces. Meanwhile, it reduces the redundancy between subspaces to enhance the diversity of alternative clusterings and optimizes the cluster centers in each subspace to boost the quality of corresponding clustering. Unlike single clustering, these alternative clusterings provide additional perspectives for understanding complex genetic information such as cell types and states. Experimental results show that scMCs can effectively identify subcellular types, impute dropout events, and uncover diverse cell characteristics by giving different but meaningful clusterings.

AVAILABILITY : The code is available at www.sdu-idea.cn/codes.php?name=scMCs.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Ren Liangrui, Wang Jun, Li Zhao, Li Qingzhong, Yu Guoxian

2023-Mar-17

General General

DeepOM: Single-molecule optical genome mapping via deep learning.

In Bioinformatics (Oxford, England)

MOTIVATION : Efficient tapping into genomic information from a single microscopic image of an intact DNA molecule is an outstanding challenge and its solution will open new frontiers in molecular diagnostics. Here, a new computational method for optical genome mapping utilizing Deep Learning is presented, termed DeepOM. Utilization of a Convolutional Neural Network (CNN), trained on simulated images of labeled DNA molecules, improves the success rate in alignment of DNA images to genomic references.

RESULTS : The method is evaluated on acquired images of human DNA molecules stretched in nano-channels. The accuracy of the method is benchmarked against state-of-the-art commercial software Bionano Solve. The results show a significant advantage in alignment success rate for molecules shorter than 50 kb. DeepOM improves yield, sensitivity and throughput of optical genome mapping experiments in applications of human genomics and microbiology.

AVAILABILITY AND IMPLEMENTATION : The source code for the presented method is publicly available at https://github.com/yevgenin/DeepOM.

SUPPLEMENTARY INFORMATION : Supplementary information is available at Bioinformatics online.

Nogin Yevgeni, Detinis Zur Tahir, Margalit Sapir, Barzilai Ilana, Alalouf Onit, Ebenstein Yuval, Shechtman Yoav

2023-Mar-17

Radiology Radiology

Direct Estimation of Regional Lung Volume Change from Paired and Single CT Images using Residual Regression Neural Network.

In Medical physics ; h5-index 59.0

BACKGROUND : Chest computed tomography (CT) enables characterization of pulmonary diseases by producing high-resolution and high-contrast images of the intricate lung structures. Deformable image registration is used to align chest CT scans at different lung volumes, yielding estimates of local tissue expansion and contraction.

PURPOSE : We investigated the utility of deep generative models for directly predicting local tissue volume change from lung CT images, bypassing computationally expensive iterative image registration and providing a method that can be utilized in scenarios where either one or two CT scans are available.

METHODS : A residual regression convolutional neural network, called Reg3DNet+, is proposed for directly regressing high-resolution images of local tissue volume change (i.e., Jacobian) from CT images. Image registration was performed between lung volumes at total lung capacity (TLC) and functional residual capacity (FRC) using a tissue mass- and structure-preserving registration algorithm. The Jacobian image was calculated from the registration-derived displacement field and used as the ground truth for local tissue volume change. Four separate Reg3DNet+ models were trained to predict Jacobian images using a multifactorial study design to compare the effects of network input (i.e., single image vs. paired images) and output space (i.e., FRC vs. TLC). The models were trained and evaluated on image datasets from the COPDGene study. Models were evaluated against the registration-derived Jacobian images using local, regional, and global evaluation metrics.

RESULTS : Statistical analysis revealed that both factors - network input and output space - were significant determinants for change in evaluation metrics. Paired-input models performed better than single-input models, and model performance was better in the output space of FRC rather than TLC. Mean structural similarity index for paired-input models was 0.959 and 0.956 for FRC and TLC output spaces, respectively, and for single-input models was 0.951 and 0.937. Global evaluation metrics demonstrated correlation between registration-derived Jacobian mean and predicted Jacobian mean: coefficient of determination (r2 ) for paired-input models was 0.974 and 0.938 for FRC and TLC output spaces, respectively, and for single-input models was 0.598 and 0.346. After correcting for effort, registration-derived lobar volume change was strongly correlated with the predicted lobar volume change: for paired-input models r2 was 0.899 for both FRC and TLC output spaces, and for single-input models r2 was 0.803 and 0.862, respectively.

CONCLUSIONS : Convolutional neural networks can be used to directly predict local tissue mechanics, eliminating the need for computationally expensive image registration. Networks that use paired CT images acquired at TLC and FRC allow for more accurate prediction of local tissue expansion compared to networks that use a single image. Networks that only require a single input image still show promising results, particularly after correcting for effort, and allow for local tissue expansion estimation in cases where multiple CT scans are not available. For single-input networks, the FRC image is more predictive of local tissue volume change compared to the TLC image.

Gerard Sarah E, Chaudhary Muhammad Fa, Herrmann Jacob, Christensen Gary E, Estépar Raúl San José, Reinhardt Joseph M, Hoffman Eric A

2023-Mar-17

computed tomography, deep learning, pulmonary

Surgery Surgery

SERS spectroscopy with machine learning to analyze human plasma derived sEVs for coronary artery disease diagnosis and prognosis.

In Bioengineering & translational medicine

Coronary artery disease (CAD) is one of the major cardiovascular diseases and represents the leading causes of global mortality. Developing new diagnostic and therapeutic approaches for CAD treatment are critically needed, especially for an early accurate CAD detection and further timely intervention. In this study, we successfully isolated human plasma small extracellular vesicles (sEVs) from four stages of CAD patients, that is, healthy control, stable plaque, non-ST-elevation myocardial infarction, and ST-elevation myocardial infarction. Surface-enhanced Raman scattering (SERS) measurement in conjunction with five machine learning approaches, including Quadratic Discriminant Analysis, Support Vector Machine (SVM), K-Nearest Neighbor, Artificial Neural network, were then applied for the classification and prediction of the sEV samples. Among these five approaches, the overall accuracy of SVM shows the best predication results on both early CAD detection (86.4%) and overall prediction (92.3%). SVM also possesses the highest sensitivity (97.69%) and specificity (95.7%). Thus, our study demonstrates a promising strategy for noninvasive, safe, and high accurate diagnosis for CAD early detection.

Huang Xi, Liu Bo, Guo Shenghan, Guo Weihong, Liao Ke, Hu Guoku, Shi Wen, Kuss Mitchell, Duryee Michael J, Anderson Daniel R, Lu Yongfeng, Duan Bin

2023-Mar

coronary artery disease, diagnostics, machine learning, small extracellular vesicles, spectrogram