Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yangmo Yoo has a total of 52 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A new single-sagittal-plane deep learning approach for continuous bladder volume monitoring: a feasibility study

    byĀ Junhwan Kwon, Ilseob Song, Sangeun Park, Jongsoo Lee, Yangmo Yoo

    Conventional ultrasound-based bladder volumetry multiplies three orthogonal diameters and applies a heuristic shape coefficient. This approach requires near-simultaneous transverse and sagittal imaging and is vulnerable to interplane misregistration and coefficient-dependent bias. This study evaluated whether a single sagittal B-mode image can provide accurate, patient-specific bladder volume estimation by leveraging sagittal morphology, perivesical echotexture, and latent image features associated with overall bladder geometry. In this Institutional Review Board-approved, single-center study, participants were scanned in the supine position, and bladder volume was referenced to immediate Foley catheter drainage. Segmentation masks were independently annotated by two sonographers and adjudicated by a urologist. Maximum sagittal length was extracted using OpenCV and included as an auxiliary scalar input. A single-stage deep learning model was developed that receives one sagittal B-mode image and its expert-annotated segmentation mask as input. The model used a lightweight convolutional neural network backbone with integrated self-attention to capture global echotextural cues. Performance on a held-out test set (n=53) was assessed using linear regression, Bland-Altman analysis, mean absolute error, and mean absolute percentage error. The model demonstrated a strong correlation with catheter-derived volumes (R²=0.87). Bland-Altman analysis showed a mean bias of -3.96±48.44 mL, with limits of agreement from -98.90 to +90.98 mL. Stratified error analysis showed a mean absolute error of 14.15 mL for volumes of 0-100 mL and a mean absolute percentage error of 16.64% for volumes ≄100 mL. Attention maps emphasized the bladder wall and perivesical soft tissues, suggesting reliance on contextual echotexture. A deep learning framework using a single sagittal plane estimated bladder volume with accuracy approaching that of two-plane techniques while simplifying image acquisition and eliminating reliance on fixed shape coefficients.

  • Open Access

    Intravascular ultrasound imaging with directional synthetic aperture focusing and coherence factor weighting

    byĀ Hyunwoo Cho, Jaebin Lee, Daehyun Park, Jin Ho Chang, Jihun Jang, Yangmo Yoo

    Purpose: Intravascular ultrasound (IVUS) is widely used to visualize vascular structures and assess atherosclerotic plaques, particularly for evaluating the risk of rupture. Although increasing the center frequency of the transducer can enhance spatial resolution, it also increases attenuation, which substantially degrades image quality at greater depths. To mitigate this trade-off, synthetic aperture focusing (SAF) techniques have been studied; however, when applied to single-element rotational IVUS systems, they have yielded only minimal improvements and introduced undesirable artifacts.Methods: In this work, a directional SAF (dSAF) method is proposed to address these limitations. The convex nature of the point spread function in rotational IVUS scanning is analyzed to track the true direction of echo signals, enabling the selective exclusion of off-axis signals. By focusing only on valid signals during synthesis, resolution degradation and artifact formation are prevented, and the fidelity of the reconstructed image is preserved.Results: Validation through simulations and phantom experiments indicates that the dSAF method achieves an average 37.3% improvement in lateral resolution and an 8.6% increase in contrast-to-noise ratio, without degrading penetration depth.Conclusion: These findings suggest that directional echo screening effectively mitigates the limitations encountered with conventional SAF in IVUS imaging, offering a robust pathway to improved image quality. Additionally, the proposed approach can be integrated into existing IVUS workflows, potentially expediting clinical adoption and advancing intravascular diagnostic capabilities.

  • Open Access

    Fully Automated Bladder Volume Measurement System Using a T-Shaped Ultrasound Probe and Free-Hand Motion-Based 3D Reconstruction

    byĀ Daehyun Park, Hyunwoo Cho, Ilseob Song, Jihun Jang, Yangmo Yoo

    Accurate measurement of bladder volume is critical for the effective management of urinary diseases. Among the available modalities, ultrasound imaging is favored due to its cost-effectiveness, non-ionizing nature, and capability to provide real-time bladder volume measurements. To enhance convenience in clinical practice, ultrasound bladder scanners have been developed and adopted in various settings. However, wobbling probe devices present significant limitations, including their inability to provide real-time images, the requirement for pre-scan alignment to ensure precise probe positioning, and the necessity for multiple volume estimations to achieve measurement accuracy. Additionally, conventional image-based estimations utilizing standard ultrasound machines or recently developed bladder scanners face challenges related to the use of shape coefficients. These methods typically rely on two image planes, which fail to fully capture the bladder’s shape, resulting in considerable errors in volume estimation when compensating for shape with coefficients. To overcome these limitations, this study proposes a novel automated bladder volume measurement technique that employs a T-shaped cross-array ultrasound probe in conjunction with free-hand motion-based 3D reconstruction. The T-shaped cross-array enables the simultaneous acquisition of sagittal and transverse view images of the bladder. By moving the probe at the suprapubic region, continuously acquired sagittal images can be combined into a 3D volume, with motion compensation achieved via the transverse images. Consequently, the proposed method can accurately reconstruct the entire bladder and measure its volume without the need for shape correction coefficients, while also reducing errors associated with ultrasound probe positioning. The proposed methodology was validated through phantom experiments simulating both spherical and irregular bladder shapes. The results demonstrated an error rate ranging from -8.8% to +5.6% when compared to the ground truth, indicating the method’s high accuracy. These results indicate that the proposed method, in conjunction with the developed array and system, has the potential to reduce the necessity for catheterization in clinical settings and enhance clinical decision-making.


  • Open Access

    Deep Coherence Learning: An Unsupervised Deep Beamformer for High Quality Single Plane Wave Imaging in Medical Ultrasound

    byĀ Hyunwoo Cho, Seongjun Park, Jinbum Kang, Yangmo Yoo

    Plane wave imaging (PWI) in medical ultrasound is becoming an important reconstruction method with high frame rates and new clinical applications. Recently, single PWI based on deep learning (DL) has been studied to overcome lowered frame rates of traditional PWI with multiple PW transmissions. However, due to the lack of appropriate ground truth images, DL-based PWI still remains challenging for performance improvements. To address this issue, in this paper, we propose a new unsupervised learning approach, i.e., deep coherence learning (DCL)-based DL beamformer (DL-DCL), for high-quality single PWI. In DL-DCL, the DL network is trained to predict highly correlated signals with a unique loss function from a set of PW data, and the trained DL model encourages high-quality PWI from low-quality single PW data. In addition, the DL-DCL framework based on complex baseband signals enables a universal beamformer. To assess the performance of DL-DCL, simulation, phantom and in vivo studies were conducted with public datasets, and it was compared with traditional beamformers (i.e., DAS with 75-PWs and DMAS with 1-PW) and other DL-based methods (i.e., supervised learning approach with 1-PW and generative adversarial network (GAN) with 1-PW). From the experiments, the proposed DL-DCL showed comparable results with DMAS with 1-PW and DAS with 75-PWs in spatial resolution, and it outperformed all comparison methods in contrast resolution. These results demonstrated that the proposed unsupervised learning approach can address the inherent limitations of traditional PWIs based on DL, and it also showed great potential in clinical settings with minimal artifacts.

  • Open Access

    Machine Learning Predicts Pathologic Complete Response to Neoadjuvant Chemotherapy for ER+HER2- Breast Cancer: Integrating Tumoral and Peritumoral MRI Radiomic Features

    byĀ Jiwoo Park, Min Jung Kim, Jong-Hyun Yoon, Kyunghwa Han, Eun-Kyung Kim, Joo Hyuk Sohn, Young Han Lee, Yangmo Yoo

    Background: This study aimed to predict pathologic complete response (pCR) in neoadjuvant chemotherapy for ER+HER2- locally advanced breast cancer (LABC), a subtype with limited treatment response. Methods: We included 265 ER+HER2- LABC patients (2010–2020) with pre-treatment MRI, neoadjuvant chemotherapy, and confirmed pathology. Using data from January 2016, we divided them into training and validation cohorts. Volumes of interest (VOI) for the tumoral and peritumoral regions were segmented on preoperative MRI from three sequences: T1-weighted early and delayed contrast-enhanced sequences and T2-weighted fat-suppressed sequence (T2FS). We constructed seven machine learning models using tumoral, peritumoral, and combined texture features within and across the sequences, and evaluated their pCR prediction performance using AUC values. Results: The best single sequence model was SVM using a 1 mm tumor-to-peritumor VOI in the early contrast-enhanced phase (AUC = 0.9447). Among the combinations, the top-performing model was K-Nearest Neighbor, using 1 mm tumor-to-peritumor VOI in the early contrast-enhanced phase and 3 mm peritumoral VOI in T2FS (AUC = 0.9631). Conclusions: We suggest that a combined machine learning model that integrates tumoral and peritumoral radiomic features across different MRI sequences can provide a more accurate pretreatment pCR prediction for neoadjuvant chemotherapy in ER+HER2- LABC.


  • Open Access

    A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study

    byĀ Hyunwoo Cho, Ilseob Song, Jihun Jang, Yangmo Yoo

    Bladder volume assessments are crucial for managing urinary disorders. Ultrasound imaging (US) is a preferred noninvasive, cost-effective imaging modality for bladder observation and volume measurements. However, the high operator dependency of US is a major challenge due to the difficulty in evaluating ultrasound images without professional expertise. To address this issue, image-based automatic bladder volume estimation methods have been introduced, but most conventional methods require high-complexity computing resources that are not available in point-of-care (POC) settings. Therefore, in this study, a deep learning-based bladder volume measurement system was developed for POC settings using a lightweight convolutional neural network (CNN)-based segmentation model, which was optimized on a low-resource system-on-chip (SoC) to detect and segment the bladder region in ultrasound images in real time. The proposed model achieved high accuracy and robustness and can be executed on the low-resource SoC at 7.93 frames per second, which is 13.44 times faster than the frame rate of a conventional network with negligible accuracy drawbacks (0.004 of the Dice coefficient). The feasibility of the developed lightweight deep learning network was demonstrated using tissue-mimicking phantoms.


  • Open Access

    A New Fast Logarithm Algorithm Using Advanced Exponent Bit Extraction for Software-Based Ultrasound Imaging Systems

    byĀ Seongjun Park, Yangmo Yoo

    Ultrasound B-mode imaging provides anatomical images of the body with a high resolution and frame rate. Recently, to improve its flexibility, most ultrasound signal and image processing modules in modern ultrasound B-mode imaging systems have been implemented in software. In a software-based B-mode imaging system, an efficient processing technique for calculating a logarithm instruction is required to support its high computational burden. In this paper, we present a new method to efficiently implement a logarithm operation based on exponent bit extraction. In the proposed method, the exponent bit field is first extracted and then some algebraic operations are applied to improve its precision. To evaluate the performance of the proposed method, the peak signal-to-noise ratio (PSNR) and the execution time were measured. The proposed efficient logarithm operation method substantially reduced the execution time, i.e., eight times, compared to direct computation while providing a PSNR of over 50 dB. These results indicate that the proposed efficient logarithm computation method can be used for lowering the computational burden in software-based ultrasound B-mode ultrasound imaging systems while improving or maintaining the image quality.