SRStefano E. Romero

Stefano E. Romero

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

Stefano E. Romero has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Optimizing harmonic shear wave elastography over three distinct frequency regimes

    by Gilmer Alberto Flores Barrera, Stefano Romero, Kevin J Parker

    Objective To investigate how excitation frequency and source configuration influence shear wave propagation in bounded soft tissues, and to establish practical guidelines for optimizing shear wave elastography across different operating regimes. Approach We analyze shear wave propagation using theoretical modeling, numerical simulations, and experimental observations across a wide range of frequencies and source configurations. The study identifies distinct propagation regimes based on the relationship between wavelength, attenuation, and geometry, and evaluates their impact on shear wave behavior. Main results We demonstrate that shear wave fields exhibit three distinct regimes—quasistatic, modal, and free-space—each associated with different propagation characteristics and limitations for inverse reconstruction. We further show that optimized source configurations can significantly enhance shear wave dominance while minimizing compressional components, leading to order-of-magnitude improvements in signal-to-noise ratio and spatial resolution at higher frequencies. Significance These findings provide a unified framework for understanding frequency-dependent wave behavior in elastography and highlight that frequency selection is a critical determinant of both wave physics and reconstruction validity. The proposed guidelines offer practical insight for translating experimental optimization strategies into clinically relevant settings.

  • Morphology-enhanced CAM-guided SAM for weakly supervised breast lesion segmentation

    by Xin Yue, Qing Zhao, Xiaoling Liu, Jianqiang Li, Jing Bai, Changwei Song, Suqin Liu, Rodrigo Moreno, Zhikai Yang, Stefano E. Romero, et al.


  • Comparison of interpolation techniques for 3D freehand ultrasound: A phantom experiment

    by Danitza Bermejo, Piero G. Latorre-Quevedo, Carlos Zegarra, Ana Paula Alejos G, Stefano E. Romero, Benjamin Castaneda

    Limited access to advanced medical imaging in rural areas of developing countries due to cost and personnel challenges is addressed through teleultrasound imaging. However, systems like Volume Sweep Imaging (VSI) exhibit spatial limitations, encompassing partially focused regions and poor image quality. This study investigates the potential of 3D freehand reconstruction algorithms using rural teleultrasound equipment. We analyze the integration of 3D reconstruction algorithms and batches to optimize the utility of teleultrasound imaging. Overall, we observe a diversity of behaviors across the interpolation techniques. For instance, the positioning system and time calibration in achieving accurate reconstructions. The results show that the Spherical Kernel interpolation is identified as a high-precision method, much more than VNN. We demonstrate the potential for batches to address the challenges posed by limited resources, paving the way for future work on image-guided surgery.

  • Comparison between U-Net and DeepLabV3 for Crawling Waves Sonoelastography approach

    by Alexys Caytano, Sebastian Merino, Hans Trujillo, Benjamin Castaneda, Stefano E. Romero

    Crawling Wave Sonoelastography is an elastography ultrasound-based approach that provides tissue stiffness information. Two mechanical sources generate an interference pattern on a tissue to obtaining a shear wave speed (SWS) map. Many estimators have been developed with important limitations such as the presence of artifacts, border effects or high computational cost. In this study, semantic segmentation approaches based on convolutional neuronal network (CNN) were performed to enhance the crawling waves differentiation. Training and validation were realized with 220 simulated frames in a range from 200 Hz to 480 Hz. Testing was made with real data acquired from experiments on a gelatin phantom with a circular inclusion vibrating on a range between 200 Hz and 360 Hz with steps of 20 Hz. It is found that comparable SWS map were generated using both architectures and model within a certain region of interest in the inclusion and in the background. Finally, CNNs presented lowest coefficient of variation and the highest contrast-to-noise ratio for most frequencies, which allows better discrimination between regions.

  • Modified Continuous Wavelet Transform Estimator for Crawling Waves Sonoelastography Using Normal Propagation

    by Hans Trujillo, Sebastian Merino, Alexys Caytano, Benjamin Castaneda, Stefano E. Romero

    Crawling Waves Sonoelastography (CWS) is a quantitative ultrasound elastography technique that uses an interference pattern to estimate the Shear Wave Speed (SWS) which is related to tissue stiffness. This technique requires vibration sources to generate a mechanical reaction in soft tissue and depends on the location of the mechanical sources, elastography approach is obtained. There are a set of different methods to estimate the SWS values. However, many of them are designed for a parallel propagation which is difficult to generate the tissue movement in clinical practice. In this regard, an alternative normal propagation have been previously proposed for it evaluation and it can be more applicable approach to in vivo analysis due the location of the vibration sources placed on the top of the surface. A previous estimator based on Phase Derivative (PD) has been modified to apply it with a normal setup, however, results in phantom studies suggest the presence of artifacts in the SWS map that generate bad discrimination of the regions. In this study, an estimator based on Continuous Wavelet Transform (CWT) is modified for normal propagation and the performance is evaluated with heterogeneous phantom studies and compared with results obtained with PD estimator. SWS values were obtained for the two estimator within a region of interest for the background (At 300 Hz, TOF: 3.45 m/s, CWT: 3.49 ± 0.37 m/s, PD: 3.95 ± 0.24 m/s) and in the inclusion (At 300 Hz, TOF: 5.1 m/s CWT: 4.89 ± 0.13 m/s, PD: 4.37 ± 0.39 m/s). To evaluate the capability of the estimators to discriminate between regions two metrics were taken into consideration: contrast-to-noise ratio and contrast ratio. The results show that the modified CWT estimator presents higher accuracy and the differentiation of regions will be better with this estimator. Clinical relevance — This study presents a modified continuous wavelet transform estimator for Crawling Wave Sonoelastography. This algorithm can be useful to provide tissue stiffness information for diagnosis or monitoring of tissue pathologies.

  • Characterisation of the soft tissue viscous and elastic properties using ultrasound elastography and rheological models: validation and applications in plantar soft tissue assessment

    by Aldo Tecse, Stefano E Romero, Roozbeh Naemi, Benjamin Castaneda

    Objective . The mechanical behaviour of soft tissue is influenced by its elastic and viscous characteristics. Therefore, the aim of this study was to develop a validated method to characterise the viscoelastic properties of soft tissues based on ultrasound elastography data. Approach . Plantar soft tissue was chosen as the tissue of interest, and gelatine-phantoms replicating its mechanical properties were manufactured for validation of the protocol. Both plantar soft tissue and the phantom were scanned using Reverberant shear wave ultrasound (US) elastography at 400–600 Hz. Shear wave speed was estimated using the US particle velocity data. The viscoelastic parameters were extracted by fitting the Young’s modulus as a function of frequency derived from the constitutive equations of the eight rheological models (four classic and their fractional-derivative versions) to the shear wave dispersion data. Furthermore, stress-time functions derived from the eight rheological models were fitted to the phantom stress-relaxation data. Main results . The viscoelastic parameters estimated using elastography data based on the fractional-derivative (FD) models, compared to the classic models, were closer to those quantified using the mechanical test. In addition, the FD-Maxwell and FD-Kelvin–Voigt models showed to more effectively replicate the viscoelastic behaviour of the plantar soft tissue with minimum number of model parameters ( R 2 = 0.72 for both models) . Hence the FD-KV and FD-Maxwell models can more effectively quantify the viscoelastic characteristics of the soft tissue compared to other models. Significance . In this study, a method for mechanical characterisation of the viscoelastic properties of soft tissue in ultrasound elastography was developed and fully validated. An investigation into the most valid rheological model and its applications in plantar soft tissue assessment were also presented. This proposed approach for the characterisation of viscous and elastic mechanical properties of soft tissue has implications in assessing the soft tissue function where those can be used as markers for diagnosis or prognosis of tissue status.


  • Open Access

    No sonographer, no radiologist: Assessing accuracy of artificial intelligence on breast ultrasound volume sweep imaging scans

    by Thomas J Marini, Benjamin Castaneda, Kevin Parker, Timothy M Baran, Stefano Romero, Radha Iyer, Yu T Zhao, Zaegyoo Hah, Moon Ho Park, Galen Brennan, et al.

    Breast ultrasound provides a first-line evaluation for breast masses, but the majority of the world lacks access to any form of diagnostic imaging. In this pilot study, we assessed the combination of artificial intelligence (Samsung S-Detect for Breast) with volume sweep imaging (VSI) ultrasound scans to evaluate the possibility of inexpensive, fully automated breast ultrasound acquisition and preliminary interpretation without an experienced sonographer or radiologist. This study was conducted using examinations from a curated data set from a previously published clinical study of breast VSI. Examinations in this data set were obtained by medical students without prior ultrasound experience who performed VSI using a portable Butterfly iQ ultrasound probe. Standard of care ultrasound exams were performed concurrently by an experienced sonographer using a high-end ultrasound machine. Expert-selected VSI images and standard of care images were input into S-Detect which output mass features and classification as “possibly benign” and “possibly malignant.” Subsequent comparison of the S-Detect VSI report was made between 1) the standard of care ultrasound report by an expert radiologist, 2) the standard of care ultrasound S-Detect report, 3) the VSI report by an expert radiologist, and 4) the pathological diagnosis. There were 115 masses analyzed by S-Detect from the curated data set. There was substantial agreement of the S-Detect interpretation of VSI among cancers, cysts, fibroadenomas, and lipomas to the expert standard of care ultrasound report (Cohen’s κ = 0.73 (0.57–0.9 95% CI), p<0.0001), the standard of care ultrasound S-Detect interpretation (Cohen’s κ = 0.79 (0.65–0.94 95% CI), p<0.0001), the expert VSI ultrasound report (Cohen’s κ = 0.73 (0.57–0.9 95% CI), p<0.0001), and the pathological diagnosis (Cohen’s κ = 0.80 (0.64–0.95 95% CI), p<0.0001). All pathologically proven cancers (n = 20) were designated as “possibly malignant” by S-Detect with a sensitivity of 100% and specificity of 86%. Integration of artificial intelligence and VSI could allow both acquisition and interpretation of ultrasound images without a sonographer and radiologist. This approach holds potential for increasing access to ultrasound imaging and therefore improving outcomes related to breast cancer in low- and middle- income countries.


  • Plantar Soft Tissue Characterization Using Reverberant Shear Wave Elastography: A Proof-of-Concept Study

    by Stefano E. Romero, Roozbeh Naemi, Gilmer Flores, David Allan, Juvenal Ormachea, Evelyn Gutierrez, Fanny L. Casado, Benjamin Castaneda


  • Validation of high-frequency ultrasound crawling waves sonoelastography

    by Aldo Tecse, Stefano E. Romero, Ana C. Saavedra, Benjamin Castaneda

    Skin diseases cause changes in the elasticity of the skin. Recently, a new ultrasound method which combines crawling waves elastography with a high-frequency ultrasound (HF-US) system was reported for the estimation of skin elasticity. This study applies crawling waves method with an HF-US system in homogeneous and heterogeneous phantoms with similar shear wave speeds found in the literature to validate this technique. In addition, estimation performance was compared between the Phase Derivative (PD) estimator and the Regularized Wave- length Average Velocity Estimator (R-WAVE). Results corroborate the feasibility of this method. Additionally, it suggests that R-WAVE estimator can provide better measurements than PD with a lower coefficient of variation and fewer artifacts.


  • A regularized quantitative ultrasound method for simultaneous calculation of backscatter and attenuation coefficients

    by Stefano E. Romero, Andres Coila, Roberto J. Lavarello

    Quantitative ultrasound has shown potential of improving medical diagnosis. In this work, a regularized power law (RPL) for the joint estimation of backscatter coefficient (BSC) and attenuation coefficient (AC) parameters was derived and tested with simulated phantoms and in vivo. For the RPL method, a total variation regularization term regarding the BSC and AC parameters were used. The results were compared with ground truth simulated values. An improvement of precision can be appreciated without compromising the accuracy by factor of 80% and 54% according to bias and coefficient of variation, respectively. The in vivo experiments showed comparable results of the algorithm with the literature (i.e. fibroadenoma:1.90 ± 0.31dB.cm−1 .MHz−1 , normal tissue: 0.62 ± 0.20dB.cm−1 .MHz−1 ). The results suggest the RPL method has the potential to accurately and precisely estimating BSCs and ACs.