Searcharxiv⌕ Search

arXiv subjects

A. Amini

Publications and source records attributed to A. Amini.

5 recordsLinked to original sources

Domain-Adversarial Adaptation from MURA to In-House Radiographs for Improved Adult Elbow Fracture Classification

We studied domain shift in adult elbow fracture classification from radiographs when training on a large public dataset and deploying on a small, institution-specific dataset (UofL). We implemented a domain-adversarial neural network (DANN) to align feature distributions across source (MURA) and target (UofL) domains while optimizing fracture classification. A pretrained convolutional backbone was adapted to grayscale inputs; the task head predicts fracture presence, and a gradient-reversal-based domain head encourages domain-invariant features via adversarial learning. We compared four settings: (1) Source-only, (2) Target-only (limited labels), (3) Naive merge (pooled training), and (4) DANN (MURA to UofL). Evaluation on UofL test data uses AUC-ROC, and accuracy. DANN outperformed Source-only and Naive merge baselines by reducing domain bias without overfitting to the small target set. Ablations showed that progressive adversarial weight, dataset-size-aware domain loss, and domain-balanced sampling improved stability and target performance. Results demonstrated that domain alignment is a practical path to robust clinical generalization from public to local data.

cs.CV↗

LoRA-fine-tuned Large Vision Models for Automated Assessment of Post-SBRT Lung Injury

This study investigates the efficacy of Low-Rank Adaptation (LoRA) for fine-tuning large Vision Models, DinoV2 and SwinV2, to diagnose Radiation-Induced Lung Injury (RILI) from X-ray CT scans following Stereotactic Body Radiation Therapy (SBRT). To evaluate the robustness and efficiency of this approach, we compare LoRA with traditional full fine-tuning and inference-only (no fine-tuning) methods. Cropped images of two sizes (50 mm3 and 75 mm3), centered at the treatment isocenter, in addition to different adaptation techniques for adapting the 2D LVMs for 3D data were used to determine the sensitivity of the models to spatial context. Experimental results show that LoRA achieves comparable or superior performance to traditional fine-tuning while significantly reducing computational costs and training times by requiring fewer trainable parameters.

cs.CV↗

On pure subrings of sp-groups

Let $G$ be a sp-group such that for every prime $p$, $G_p$ is elementary. %$\oplus \End_{\zz}(G_p) \leq \End_{\zz}(G) \leq \prod \End_{\zz}(G_p)$. Suppose that $\frac{G}{\oplus_{p\in \mathbb{P}} G_p}$ is torsion-free divisible. %In this article we characterize pure subrings of $\prod_{p\in \mathbb{P}} \End(G_p)$. We show that $\End_{\zz}(G)$ is a sp-group and every subring $R$ of $\prod \End_{\zz}(G_p)$, containing $\oplus \End_{\zz}(G_p)$ is pure if and only if $R=\mathbb{M}_T=\{x\in \prod_{p\in \mathbb{P}}\End(G_p) \;|\; \exists k\in \nn \;\mbox{\rm{such that}} \;\; kx \in T \},$ where $T$ is a subring of $\prod_{p\in \mathbb{P}}\End(G_p)$. We observe that $\frac{\mathbb{M}_T}{\oplus_{p\in \mathbb{P}}\End(G_p)}$ is (ring) isomorphic with $T\otimes_{\zz} \qq$. Moreover, we conclude that a significant number of the examples around the topic can be easily obtained and described by choosing an appropriate subring $T$.

math.GR↗

Finding quadruply imaged quasars with machine learning. I. Methods

Strongly lensed quadruply imaged quasars (quads) are extraordinary objects. They are very rare in the sky -- only a few tens are known to date -- and yet they provide unique information about a wide range of topics, including the expansion history and the composition of the Universe, the distribution of stars and dark matter in galaxies, the host galaxies of quasars, and the stellar initial mass function. Finding them in astronomical images is a classic "needle in a haystack" problem, as they are outnumbered by other (contaminant) sources by many orders of magnitude. To solve this problem, we develop state-of-the-art deep learning methods and train them on realistic simulated quads based on real images of galaxies taken from the Dark Energy Survey, with realistic source and deflector models, including the chromatic effects of microlensing. The performance of the best methods on a mixture of simulated and real objects is excellent, yielding area under the receiver operating curve in the range 0.86 to 0.89. Recall is close to 100% down to total magnitude i~21 indicating high completeness, while precision declines from 85% to 70% in the range i~17-21. The methods are extremely fast: training on 2 million samples takes 20 hours on a GPU machine, and 10^8 multi-band cutouts can be evaluated per GPU-hour. The speed and performance of the method pave the way to apply it to large samples of astronomical sources, bypassing the need for photometric pre-selection that is likely to be a major cause of incompleteness in current samples of known quads.

astro-ph.CO↗

A Unified Approach to Sparse Signal Processing

A unified view of sparse signal processing is presented in tutorial form by bringing together various fields. For each of these fields, various algorithms and techniques, which have been developed to leverage sparsity, are described succinctly. The common benefits of significant reduction in sampling rate and processing manipulations are revealed. The key applications of sparse signal processing are sampling, coding, spectral estimation, array processing, component analysis, and multipath channel estimation. In terms of reconstruction algorithms, linkages are made with random sampling, compressed sensing and rate of innovation. The redundancy introduced by channel coding in finite/real Galois fields is then related to sampling with similar reconstruction algorithms. The methods of Prony, Pisarenko, and MUSIC are next discussed for sparse frequency domain representations. Specifically, the relations of the approach of Prony to an annihilating filter and Error Locator Polynomials in coding are emphasized; the Pisarenko and MUSIC methods are further improvements of the Prony method. Such spectral estimation methods is then related to multi-source location and DOA estimation in array processing. The notions of sparse array beamforming and sparse sensor networks are also introduced. Sparsity in unobservable source signals is also shown to facilitate source separation in SCA; the algorithms developed in this area are also widely used in compressed sensing. Finally, the multipath channel estimation problem is shown to have a sparse formulation; algorithms similar to sampling and coding are used to estimate OFDM channels.

cs.IT↗