Search

Over the past few decades, convolutional neural networks (CNNs) have been at the forefront of the detection and tracking of various retinal diseases (RD). Despite their success, the emergence of vision transformers (ViT) in the 2020s has shifted the trajectory of RD model development. The leading-edge performance of ViT-based models in RD can be largely credited to their scalability-their ability to improve as more parameters are added. As a result, ViT-based models tend to outshine traditional CNNs in RD applications, albeit at the cost of increased data and computational demands. ViTs also differ from CNNs in their approach to processing images, working with patches rather than local regions, which can complicate the precise localization of small, variably presented lesions in RD. In our study, we revisited and updated the architecture of a CNN model, specifically MobileNet, to enhance its utility in RD diagnostics. We found that an optimized MobileNet, through selective modifications, can surpass ViT-based models in various RD benchmarks, including diabetic retinopathy grading, detection of multiple fundus diseases, and classification of diabetic macular edema. The code is available at https://github.com/Retinal-Research/NN-MOBILENET, Comment: Accepted as a conference paper to 2024 CVPRW

Background: Beta-amyloid (A$\beta$) plaques and tau protein tangles in the brain are the defining 'A' and 'T' hallmarks of Alzheimer's disease (AD), and together with structural atrophy detectable on brain magnetic resonance imaging (MRI) scans as one of the neurodegenerative ('N') biomarkers comprise the ''ATN framework'' of AD. Current methods to detect A$\beta$/tau pathology include cerebrospinal fluid (CSF; invasive), positron emission tomography (PET; costly and not widely available), and blood-based biomarkers (BBBM; promising but mainly still in development). Objective: To develop a non-invasive and widely available structural MRI-based framework to quantitatively predict the amyloid and tau measurements. Methods: With MRI-based hippocampal multivariate morphometry statistics (MMS) features, we apply our Patch Analysis-based Surface Correntropy-induced Sparse coding and max-pooling (PASCS-MP) method combined with the ridge regression model to individual amyloid/tau measure prediction. Results: We evaluate our framework on amyloid PET/MRI and tau PET/MRI datasets from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Each subject has one pair consisting of a PET image and MRI scan, collected at about the same time. Experimental results suggest that amyloid/tau measurements predicted with our PASCP-MP representations are closer to the real values than the measures derived from other approaches, such as hippocampal surface area, volume, and shape morphometry features based on spherical harmonics (SPHARM). Conclusion: The MMS-based PASCP-MP is an efficient tool that can bridge hippocampal atrophy with amyloid and tau pathology and thus help assess disease burden, progression, and treatment effects., Comment: 34 pages, 5 figures, 1 table, accepted by the Journal of Alzheimer's Disease

Lesion appearance is a crucial clue for medical providers to distinguish referable diabetic retinopathy (rDR) from non-referable DR. Most existing large-scale DR datasets contain only image-level labels rather than pixel-based annotations. This motivates us to develop algorithms to classify rDR and segment lesions via image-level labels. This paper leverages self-supervised equivariant learning and attention-based multi-instance learning (MIL) to tackle this problem. MIL is an effective strategy to differentiate positive and negative instances, helping us discard background regions (negative instances) while localizing lesion regions (positive ones). However, MIL only provides coarse lesion localization and cannot distinguish lesions located across adjacent patches. Conversely, a self-supervised equivariant attention mechanism (SEAM) generates a segmentation-level class activation map (CAM) that can guide patch extraction of lesions more accurately. Our work aims at integrating both methods to improve rDR classification accuracy. We conduct extensive validation experiments on the Eyepacs dataset, achieving an area under the receiver operating characteristic curve (AU ROC) of 0.958, outperforming current state-of-the-art algorithms., Comment: 7 pages, 2 tables, 3 figures. 18th International Symposium on Medical Information Processing and Analysis

Biomarker-assisted diagnosis and intervention in Alzheimer's disease (AD) may be the key to prevention breakthroughs. One of the hallmarks of AD is the accumulation of tau plaques in the human brain. However, current methods to detect tau pathology are either invasive (lumbar puncture) or quite costly and not widely available (Tau PET). In our previous work, structural MRI-based hippocampal multivariate morphometry statistics (MMS) showed superior performance as an effective neurodegenerative biomarker for preclinical AD and Patch Analysis-based Surface Correntropy-induced Sparse coding and max-pooling (PASCS-MP) has excellent ability to generate low-dimensional representations with strong statistical power for brain amyloid prediction. In this work, we apply this framework together with ridge regression models to predict Tau deposition in Braak12 and Braak34 brain regions separately. We evaluate our framework on 925 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Each subject has one pair consisting of a PET image and MRI scan which were collected at about the same times. Experimental results suggest that the representations from our MMS and PASCS-MP have stronger predictive power and their predicted Braak12 and Braak34 are closer to the real values compared to the measures derived from other approaches such as hippocampal surface area and volume, and shape morphometry features based on spherical harmonics (SPHARM)., Comment: 10 pages, 5 figures, 17th International Symposium on Medical Information Processing and Analysis

We relate transitions in galaxy structure and gas content to refueling, here defined to include both the external gas accretion and the internal gas processing needed to renew reservoirs for star formation. We analyze two z=0 data sets: a high-quality ~200-galaxy sample (the Nearby Field Galaxy Survey, data release herein) and a volume-limited ~3000-galaxy sample with reprocessed archival data. Both reach down to baryonic masses ~10^9Msun and span void-to-cluster environments. Two mass-dependent transitions are evident: (i) below the "gas-richness threshold" scale (V~125km/s), gas-dominated quasi-bulgeless Sd--Im galaxies become numerically dominant, while (ii) above the "bimodality" scale (V~200km/s), gas-starved E/S0s become the norm. Notwithstanding these transitions, galaxy mass (or V as its proxy) is a poor predictor of gas-to-stellar mass ratio M_gas/M_*. Instead, M_gas/M_* correlates well with the ratio of a galaxy's stellar mass formed in the last Gyr to its preexisting stellar mass, such that the two ratios have numerically similar values. This striking correspondence between past-averaged star formation and current gas richness implies routine refueling of star-forming galaxies on Gyr timescales. We argue that this refueling underlies the tight M_gas/M_* vs. color correlations often used to measure "photometric gas fractions." Furthermore, the threshold and bimodality scale transitions reflect mass-dependent demographic shifts between three refueling regimes --- accretion dominated, processing dominated, and quenched. In this picture, gas-dominated dwarfs are explained not by inefficient star formation but by overwhelming gas accretion, which fuels stellar mass doubling in <~1Gyr. Moreover, moderately gas-rich bulged disks such as the Milky Way are transitional, becoming abundant only in the narrow range between the threshold and bimodality scales., Comment: ApJ, accepted, 28 pages including 12 figures and Table 2; data for Table 1 available at http://www.physics.unc.edu/~sheila/k13_table1.csv

The plane-wave decomposition method (PWDM), a widely used means of numerically finding eigenstates of the Helmholtz equation in billiard systems is described as a variant of the mathematically well-established boundary integral method (BIM). A new unified framework encompassing the two methods is discussed. Furthermore, a third numerical method, which we call the Gauge Freedom Method (GFM) is derived from the BIM equations. This opens the way to further improvements in eigenstate search techniques., Comment: 24 pages, 9 figures, textual improvements