arXiv subjects

Serge Vasylechko

Publications and source records attributed to Serge Vasylechko.

5 recordsLinked to original sources

arXiv2026

WristMIR: Coarse-to-Fine Region-Aware Retrieval of Pediatric Wrist Radiographs with Radiology Report-Driven Learning

Retrieving wrist radiographs with analogous fracture patterns is challenging because clinically important cues are subtle, highly localized and often obscured by overlapping anatomy or variable imaging views. Progress is further limited by the scarcity of large, well-annotated datasets for case-based medical image retrieval. We introduce WristMIR, a region-aware pediatric wrist radiograph retrieval framework that leverages dense radiology reports and bone-specific localization to learn fine-grained, clinically meaningful image representations without any manual image-level annotations. Using MedGemma-based structured report mining to generate both global and region-level captions, together with pre-processed wrist images and bone-specific crops of the distal radius, distal ulna, and ulnar styloid, WristMIR jointly trains global and local contrastive encoders and performs a two-stage retrieval process: (1) coarse global matching to identify candidate exams, followed by (2) region-conditioned reranking aligned to a predefined anatomical bone region. WristMIR improves retrieval performance over strong vision-language baselines, raising image-to-text Recall@5 from 0.82% to 9.35%. Its embeddings also yield stronger fracture classification (AUROC 0.949, AUPRC 0.953). In region-aware evaluation, the two-stage design markedly improves retrieval-based fracture diagnosis, increasing mean $F_1$ from 0.568 to 0.753, and radiologists rate its retrieved cases as more clinically relevant, with mean scores rising from 3.36 to 4.35. These findings highlight the potential of anatomically guided retrieval to enhance diagnostic reasoning and support clinical decision-making in pediatric musculoskeletal imaging. The source code is publicly available at https://github.com/quin-med-harvard-edu/WristMIR.

cs.CV↗

arXiv2025

MRI Super-Resolution with Deep Learning: A Comprehensive Survey

High-resolution (HR) magnetic resonance imaging (MRI) is crucial for many clinical and research applications. However, achieving it remains costly and constrained by technical trade-offs and experimental limitations. Super-resolution (SR) presents a promising computational approach to overcome these challenges by generating HR images from more affordable low-resolution (LR) scans, potentially improving diagnostic accuracy and efficiency without requiring additional hardware. This survey reviews recent advances in MRI SR techniques, with a focus on deep learning (DL) approaches. It examines DL-based MRI SR methods from the perspectives of computer vision, computational imaging, inverse problems, and MR physics, covering theoretical foundations, architectural designs, learning strategies, benchmark datasets, and performance metrics. We propose a systematic taxonomy to categorize these methods and present an in-depth study of both established and emerging SR techniques applicable to MRI, considering unique challenges in clinical and research contexts. We also highlight open challenges and directions that the community needs to address. Additionally, we provide a collection of essential open-access resources, tools, and tutorials, available on our GitHub: https://github.com/mkhateri/Awesome-MRI-Super-Resolution. IEEE keywords: MRI, Super-Resolution, Deep Learning, Computational Imaging, Inverse Problem, Survey.

eess.IV↗

arXiv2024

Rapid, High-resolution and Distortion-free $R_{2}^{*}$ Mapping of Fetal Brain using Multi-echo Radial FLASH and Model-based Reconstruction

Purpose: To develop a rapid, high-resolution and distortion-free technique for simultaneous water-fat separation, $R_{2}^{*}$ and $B_{0}$ mapping of the fetal brain at 3T. Methods: A 2D multi-echo radial FLASH sequence with blip gradients is adapted for data acquisition during maternal free breathing. A calibrationless model-based reconstruction with sparsity constraints is developed to jointly estimate water, fat, $R_{2}^{*}$ and $B_{0}$ field maps directly from k-space. This approach was validated and compared to reference methods using numerical and NIST phantoms and data from nine fetuses between 26 and 36 weeks of gestation age. Results: Both numerical and experimental phantom studies confirm good accuracy and precision. In fetal studies, model-based reconstruction yields quantitative $R_{2}^{*}$ values in close agreement with those from a parallel imaging compressed sensing (PICS) technique using Graph Cut (intra-class correlation coefficient [ICC] = 0.9601), while providing enhanced image detail. Repeated scans confirm good reproducibility (ICC = 0.9213). Compared to multi-echo EPI, the proposed radial technique produces higher-resolution (1.1 $\times$ 1.1 $\times$ 3 mm$^{3}$ vs. 2-3 $\times$ 2-3 $\times$ 3 mm$^{3}$) $R_{2}^{*}$ maps with reduced distortion. Despite of differences in motion, resolution and distortion, $R_{2}^{*}$ values are comparable between the two acquisition strategies (ICC = 0.8049). Additionally, the proposed approach enables synthesis of high-resolution and distortion-free $R_{2}^{*}$-weighted images. Conclusion: This study demonstrates the feasibility of using multi-echo radial FLASH combined with calibrationless model-based reconstruction for motion-robust, distortion-free $R_{2}^{*}$ mapping of the fetal brain at 3T, achieving a nominal resolution of $1.1 \times 1.1 \times 3$ mm$^{3}$ within 2 seconds per slice.

physics.med-ph↗

arXiv2024

An Optimized Binning and Probabilistic Slice Sharing Algorithm for Motion Correction in Abdominal DW-MRI

Diffusion-weighted magnetic resonance imaging (DW-MRI) is a powerful, non-invasive tool for detecting and characterizing abdominal lesions to facilitate early diagnosis, but respiratory motion during a scan reduces image quality and accuracy of quantitative biomarkers. Respiratory binning, which groups image slices into motion phase bins based on a navigator signal, can help mitigate motion artifacts. However, in DW-MRI, the standard binning technique often generates volumes with missing slices along the superior-inferior axis. Thus, longer scans are required to obtain volumes without gaps. In this study, we proposed a new binning technique to minimize missing slices without increasing scan time. We first designed an algorithm using dynamic programming and prefix sum approaches to optimize the initial binning of MR images. Then, we developed a probabilistic refinement phase, selecting some slices to belong in two neighboring bins to further reduce missing slices. We tested our two-phase technique on free-breathing abdominal DW-MRI scans from eight subjects, including one with tumors. The proposed technique significantly reduced missing slices compared to standard binning (p<1.0*10-15), yielding an average reduction of 81.74+/-7.58%. Our technique also reduced motion artifacts, improving the conspicuity of malignant lesions. Apparent Diffusion Coefficient (ADC) maps generated from free-breathing scans corrected using the proposed technique had lower intra-subject variability compared to ADC maps from uncorrected free-breathing and shallow-breathing scans (p<0.001). Additionally, ADC maps from shallow-breathing scans were more consistent with corrected free-breathing maps rather than uncorrected free-breathing maps (p<0.01). The proposed technique corrects for motion while simultaneously reducing missing slices, allowing for shorter acquisition times compared to standard binning.

eess.IV↗

arXiv2022

Convolution-Free Medical Image Segmentation using Transformers

Like other applications in computer vision, medical image segmentation has been most successfully addressed using deep learning models that rely on the convolution operation as their main building block. Convolutions enjoy important properties such as sparse interactions, weight sharing, and translation equivariance. These properties give convolutional neural networks (CNNs) a strong and useful inductive bias for vision tasks. In this work we show that a different method, based entirely on self-attention between neighboring image patches and without any convolution operations, can achieve competitive or better results. Given a 3D image block, our network divides it into $n^3$ 3D patches, where $n=3 \text{ or } 5$ and computes a 1D embedding for each patch. The network predicts the segmentation map for the center patch of the block based on the self-attention between these patch embeddings. We show that the proposed model can achieve segmentation accuracies that are better than the state of the art CNNs on three datasets. We also propose methods for pre-training this model on large corpora of unlabeled images. Our experiments show that with pre-training the advantage of our proposed network over CNNs can be significant when labeled training data is small.

eess.IV↗