GFGregory B. Furman

Gregory B. Furman

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Gregory B. Furman has a total of 98 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Anisotropy of dipolar order relaxation rate in phospholipid bilayers

    by Gregory Furman, Theodore Aptekarev, Vladimir Sokolovsky

  • Open Access

    Transformer Architectures for Respiratory Sound Analysis and Multimodal Diagnosis

    by Theodore Aptekarev, Vladimir Sokolovsky, Gregory Furman, Evgeny Furman

    Breath sound analysis is one of the diagnostic approaches for various lung diseases. However, traditional auscultation is subjective and dependent on the physician’s experience. Recent studies have demonstrated that computer-assisted methods analyzing these sounds can significantly improve the accuracy of diagnosis of the patient’s condition. However, the absence of a common basis for fair comparison, limited use of patient metadata, and lack of interpretability make these approaches difficult to adopt in clinical practice. In the paper, we propose to utilize the benefits of the recent state-of-the-art sound classification models and a multimodal approach for respiratory disease screening and diagnostics. To achieve this goal, we use the Audio Spectrogram Transformer (AST) model and a vision-language model (VLM) Moondream2. We compare them with our previous work on the DenseNet201 Convolutional Neural Network (CNN). The proposed methodology allows a fair comparison of different computer-assisted methods for respiratory disease screening and diagnostics. The training and evaluation of the models have been conducted using the same dataset containing respiratory sound recordings and patient information. The obtained results demonstrate that these transformer-based models can serve as a basis for the development of computer-assisted methods for asthma diagnosis, as well as for continuous and remote monitoring of patient condition. In addition, our approach enables interpretability of the model performance. The achieved performance is much better than the best results of the physician’s auscultation.

  • Open Access

    Structural anisotropy in celery stalks by microscopic MRI and polarized light microscopy

    by Sarah Salem, Farid Badar, Amanveer Singh, Vladimir Sokolovsky, Gregory Furman, Yang Xia

    Structural anisotropy of celery stalks was studied using T2 anisotropy in microscopic MRI (μMRI) and supplemented by quantitative polarized light microscopy (PLM) at optical resolutions. Parenchyma, which is the ground tissue in celery and has a diameter in the range of 50–90 μm, was found to have isotropic T2; in contrast, collenchyma, which is the structural part of the ground tissue in celery and has a diameter in the range of 8–12 μm, was found to have strong anisotropic T2. Substantial size variations within each porous structure and substantial co-existences of more than one type of structural tissues within a single μMRI voxel were noticed in the optical images, which can contribute to the less clear anisotropies in the smaller vascular structures (e.g., phloem (approximately 2–6 μm in diameter) and xylem (approximately 5–15 μm in diameter)). Celery could be used as a simple plant model to study the relationships between tissue microstructures and nuclear spin relaxation in fibrous and porous specimens.

  • Open Access

    Analysis of Multi‐Component Echo Decay in Achilles Tendon by NMR Spectroscopy

    by Theodore Aptekarev, Gregory Furman, Vladimir Sokolovsky, Yang Xia

    Fibrous tissues are characterized by angular anisotropy of relaxation times at the nuclear magnetic resonance (NMR) testing. The anisotropy is associated with the water distribution inside such tissues, and its determination requires multiple experiments with the sample rotation relative to the magnetic field. In this paper a quantitative link between a single NMR echo decay and the structure and fluctuations of the water‐filled nanocavity in tendon is established, without orientation‐dependent relaxation measurements. Echo decays were acquired from Achilles tendon using the Carr‐Purcell‐Meiboom‐Gill and spin‐locking sequences. To determine the relationship between the NMR relaxation and the structure and fluctuations of water‐filled nanocavities, a physical model was used based on the representation of the tendon as a set of nanocavities and the averaged Hamiltonian of the dipole–dipole spin interaction. Two distinct nanocavity types were identified, which differ in the parameters of the nanocavity structure and their fluctuations. Non‐invasive quantitative assessment of the nanocavity structural characteristics opens a way to develop biomarkers for detecting pathological changes in a tendon.

  • Open Access

    Transformer Architectures for Respiratory Sound Analysis and Multimodal Diagnosis

    by Theodore Aptekarev, Vladimir Sokolovsky, Gregory Furman

    Respiratory sound analysis is a crucial tool for screening asthma and other pulmonary pathologies, yet traditional auscultation remains subjective and experience-dependent. Our prior research established a CNN baseline using DenseNet201, which demonstrated high sensitivity in classifying respiratory sounds. In this work, we (i) adapt the Audio Spectrogram Transformer (AST) for respiratory sound analysis and (ii) evaluate a multimodal Vision-Language Model (VLM) that integrates spectrograms with structured patient metadata. AST is initialized from publicly available weights and fine-tuned on a medical dataset containing hundreds of recordings per diagnosis. The VLM experiment uses a compact Moondream-type model that processes spectrogram images alongside a structured text prompt (sex, age, recording site) to output a JSON-formatted diagnosis. Results indicate that AST achieves approximately 97% accuracy with an F1-score around 97% and ROC AUC of 0.98 for asthma detection, significantly outperforming both the internal CNN baseline and typical external benchmarks. The VLM reaches 86-87% accuracy, performing comparably to the CNN baseline while demonstrating the capability to integrate clinical context into the inference process. These results confirm the effectiveness of self-attention for acoustic screening and highlight the potential of multimodal architectures for holistic diagnostic tools.

  • Open Access

    Depth-dependent characterization of cartilage nanostructures using MRI signal decays

    by Theodore Aptekarev, Gregory Furman, Vladimir Sokolovsky, Farid Badar, Yang Xia


  • Open Access

    Nonlocality of three-qubit states of a nuclear spin-7/2

    by Gregory Furman, Vladimir Sokolovsky

    Advances in quantum information processing can open a way for numerous applications of the processing in various fields of science and technology: communication, precision measurement, computing, nano-scale detectors, and sensors. Classical and various quantum correlations have been studied in real spin 1/2 systems. The nonlocality measures provide a novel classification scheme for bipartite states, highlighting that nonlocality is a quantum resource distinct from other types of quantum correlations. We first studied the temperature and field dependencies of nonlocality measure in the three fictitious spin 1/2 system, which represents a nuclear spin-7/2 placed in magnetic and inhomogeneous electric fields. The relationship between nonlocality and other quantum correlations (entanglement and geometric discord) was studied. The Hamiltonian and spin operators for a spin 7/2 are represented in the basis formed by the Kronecker products of the Pauli matrices. This transformation allows us to represent a spin 7/2 as a system of three coupled fictitious spins 1/2 and, from the quantum information point of view, as an equivalent system of three coupling qubits. Well-developed methods were used to calculate measures of quantum correlations. For example, we consider 59Co (spin 7/2) in the compounds [Co(NH3)5Cl]Cl2 and Ca3Co2O6. The interaction between the fictitious spins of 59Co nuclei depends on the magnitude and direction of the external magnetic field. Other potential cases of quantum correlations can be realized based on nuclear spins 7/2 in solid-state systems, for instance, such as 51V, 165Ho, or 123Sb.


  • Study of the collagen tissue nanostructure by analyzing the echo decay obtained using the MRI technique

    by Theodore Aptekarev, Gregory Furman, Farid Badar, Vladimir Sokolovsky, Yang Xia

    The multicomponent relaxation observed in nuclear magnetic resonance experiments in biological tissues makes it difficult to establish a correlation between specific relaxation times and tissue structural parameters.