CWChen Wang

Chen Wang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chen Wang has a total of 121 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Deep-learning-aided sarcoma biopsy guidance using forward-view endoscopic optical coherence tomography

    by Haoyang Cui, Chen Wang, Kar-Ming Fung, Ajay Jain, Paul Calle, Ronghao Liu, Junyuan Liu, Yan Cui, Qinghao Zhang, Yuye Ling, et al.

    Sarcoma diagnosis remains challenging due to tumor heterogeneity and the risk of sampling errors during biopsy, as tissue misidentification can result in non-diagnostic outcomes and repeated procedures. This study specifically targets undifferentiated pleomorphic sarcoma (UPS) and myxofibrosarcoma, imaged in specimens from the human arms and legs. Optical coherence tomography (OCT) offers high-resolution, real-time microstructural imaging and has shown strong potential for image-guided oncology. In this study, we benchmarked five 2D deep learning models and one custom 3D convolutional neural network (CNN) for normal versus tumor tissues classification using endoscopic OCT. The 2D models were applied to cross-sectional 2D images while the 3D CNN operated on volumetric images, with both evaluated across the Intensity and polarization-sensitive OCT channels (PS-OCT). 3D CNN reached the highest accuracy of 92.67% on Intensity, while PS-OCT channels benefited more from modern 2D architectures and 3D volumetric modeling, with performance gains up to 9.63% for the optic axis. These results demonstrated the feasibility of endoscopic OCT as a real-time, label-free tissue characterization tool during biopsy of these sarcoma tissues. The integration of deep learning with forward-viewing endoscopic OCT offers a promising pathway toward more accurate needle guidance and reduced diagnostic failure rates and established a reproducible benchmarking framework for future OCT-based detection and analysis of sarcoma tissues.


  • Human donor liver viability evaluation with polarization-sensitive optical coherence tomography

    by Feng Yan, Qinghao Zhang, Bornface M. Mutembei, Ke Zhang, Yan Cui, Ronghao Liu, Junyuan Liu, Chen Wang, Zaid A. Alhajeri, Kaustubh Pandit, et al.

    Human liver transplantation is constrained by a critical shortage of viable donor livers. In response to this shortage, marginal livers from extended criteria donors are increasingly used to expand the donor pool. Donor liver viability assessment remains limited by invasive, biopsy-based pathological sampling, and there is a need for more comprehensive and noninvasive evaluation techniques to meet the increasing demand for liver transplants. In this study, we propose the use of polarization-sensitive optical coherence tomography (PS-OCT) to perform a multiparameter viability evaluation across the entire surface of donor livers. PS-OCT imaging was conducted on multiple regions of human donor livers, and the findings were cross-validated with histopathological evaluations. Machine learning and texture analysis were used to evaluate hepatic steatosis, fibrosis, inflammation, and necrosis from PS-OCT measurements in comparison with traditional pathological assessments, finding a correlation (>80%) between PS-OCT quantifications and pathology. PS-OCT imaging findings demonstrated strong correlations with donor liver functional performance during normothermic machine perfusion and with clinical liver transplant outcomes. PS-OCT offers a noninvasive assessment of liver viability by quantifying hepatic parameters across the entire donor liver, effectively complementing current pathological analysis. These results suggest that PS-OCT provides a robust approach to assessing donor liver viability, which could potentially decrease the discard rate of high-risk livers, thereby expanding the donor pool and reducing the inadvertent use of unsuitable livers for transplantation.

  • Deep learning fusion of multi-channel imaging from polarization-sensitive optical coherence tomography

    by Yunlong Liu, Chen Wang, Paul Calle, Justin Reynolds, Sinaro Ly, Haoyang Cui, Alberto J. de Armendi, Shashank S. Shettar, Kar-Ming Fung, Qi Li, et al.

    Multi-contrast polarization-sensitive optical coherence tomography (PS-OCT) provides complementary structural and polarization information that may improve epidural tissue classification. Here, we evaluated deep learning fusion of four PS-OCT channels, including intensity, phase retardation, degree of polarization uniformity (DOPU), and optic axis, using porcine (n = 6) and human (n = 5) spinal specimens. We benchmarked six multi-channel fusion strategies: Probability averaging, feature concatenation, trainable weighted output, shared-stage resnet, merged multi-channel input, and pooled data. Across subject-level nested cross-validation, multi-channel methods achieved modest but consistent accuracy improvements over the best single-channel baselines while reducing subject-to-subject variability. On porcine data, Probability Averaging increased mean validation accuracy by 3.46% (93.07% vs. 89.61% for the best single-channel baseline). On human data, fusion methods maintained the high single-channel baseline (approximately 97% to 98%) while modestly improving stability, with probability averaging achieving the highest mean validation accuracy (98.26%). In cross-testing, trainable weighted output achieved 92.32% versus 91.53% for the best porcine single-channel baseline, and probability averaging achieved 97.87% versus 97.75% for the best human single-channel baseline. On the human cohort, the gain in mean accuracy was small, but multi-channel fusion produced a statistically significant reduction in between-subject variance (Levene's p = 0.0108) and removed the need to know in advance which single channel would generalize best. Overall, multi-channel fusion improved classification performance and robustness, with probability averaging offering a favorable balance between accuracy and complexity because it requires no additional training beyond single-channel models.

  • Open Access

    Percutaneous nephrostomy guidance by a convolutional-neural-network-based optical coherence tomography endoscope

    by Chen Wang, Paul Calle, Feng Yan, Qinghao Zhang, Kar-Ming Fung, Zhongxin Yu, Sean G. Duguay, William B. Vanlandingham, Nathan A. Bradley, Sanjay G. Patel, et al.

    Percutaneous nephrostomy is widely used in kidney access surgeries. Despite its prevalence in urological interventions, it presents two operational challenges: 1) precise needle placement into the renal pelvis; and 2) avoiding hemorrhage from blood vessel rupture. In this study, we developed an endoscopic optical coherence tomography probe for needle navigation. We conducted experiments on thirty-one human kidneys for two aspects: 1) tissue recognition, and 2) blood vessel detection. Experimental results indicated that renal tissues including cortex, medulla, calyx, sinus fat, and pelvis could be effectively distinguished through structural optical coherence tomography imaging, and renal blood flow could be detected through the Doppler function. Deep learning methods were utilized to automate recognition procedures. For tissue classification, an Inception model was used, achieving a recognition accuracy of 99.6%. For blood vessel detection, an nnU-net model was applied, exhibiting an intersection over union value of 0.8917 for blood vessel and 0.9916 for background.


  • Label-free viability assessment of ex vivo mouse kidneys for transplant applications using dynamic optical coherence tomography

    by Ke Zhang, Qinghao Zhang, Trisha Valerio, Feng Yan, Yan Cui, Ronghao Liu, Xiaoyu Ma, Junyuan Liu, Tri Vu, Chen Wang, et al.

    Kidney transplantation remains the preferred treatment for patients with end-stage kidney disease. However, the ongoing shortage of donor organs continues to limit the availability of transplant treatments. Existing evaluation methods, such as the kidney donor profile index (KDPI) and pre-transplant donor biopsy (PTDB), have various limitations, including low discriminative power, invasiveness, and sampling errors, which reduce their effectiveness in organ quality assessment and contribute to the risk of unnecessary organ discard. In this study, we explored the dynamic optical coherence tomography (DOCT) as a label-free, non-invasive approach to monitor the viability of ex vivo mouse kidneys during static cold storage over 48 hours. The dynamic metrics logarithmic intensity variance (LIV), early OCT correlation decay speed (OCDS e ), and late OCT correlation decay speed (OCDS l ) were extracted from OCT signal fluctuations to quantify temporal and spatial tissue activity and deterioration. Our results demonstrate that DOCT provides complementary information relevant to tissue viability, in addition to the morphological assessment offered by conventional OCT imaging, showing potential to improve pre-transplant organ evaluation and clinic decision-making.


  • Evaluation of radio frequency ablation in human left atrial tissues for atrial fibrillation using optical coherence tomography

    by Ebenezer Raj Selvaraj Mercyshalinie, Dylan O. Patterson, Bornface M. Mutembei, Avery D. Ladymon, Feng Yan, Kaustubh Pandit, Hayden Peek, Kar-Ming A. Fung, Qinghao Zhang, Chen Wang, et al.

    Despite its widespread adoption, the success of radiofrequency (RF) ablation is often limited by challenges in achieving durable, transmural lesions while avoiding complications such as incomplete ablation or over-ablation. Optical coherence tomography (OCT) offers high-resolution visualization of cardiac tissue, enabling real-time assessment of lesion depth. Therefore, we investigated the impact of RF ablation on donated human left atrial tissue using an OCT imaging system to assess lesion formation in a controlled laboratory setting. RF ablation lesions were created at durations of 20, 40, 60, 80, and 100 seconds (s), and their effects were quantified by calculating the attenuation coefficient from OCT images. To identify tissue regions in the image, a U-Net model was employed for segmentation, achieving a mean intersection over union (IoU) of 0.9748 with an inference time of 82 milliseconds. Our results demonstrated clear differences in tissue response before and after ablation, with distinct lesion characteristics across the tested durations. One-way ANOVA analysis yielded a p-value of 1.09 × 10−8, confirming statistically significant differences among the ablation durations. These findings highlight the potential of SD-OCT for precise, real-time monitoring of ablation effects. Future work aims to integrate OCT with ablation catheters for clinical applications, enhancing the precision of catheter-based treatments for conditions like atrial fibrillation.

  • Evaluating the Efficacy of Mebendazole Repurposing for Ovarian Cancer Therapy Using Optical Coherence Tomography

    by Rajani Rai, Qinghao Zhang, Bornface M. Mutembei, Feng Yan, Kaustubh Pandit, Ke Zhang, Chen Wang, Ronghao Liu, Junyuan Liu, Ebenezer Raj Selvaraj Mercyshalinie, et al.

    Ovarian cancer (OvCa) remains the leading cause of gynecological cancer mortality, with most patients developing chemoresistance. Drug repurposing offers promising alternatives, with mebendazole (MBZ) showing anticancer activity. This study evaluates MBZ efficacy using Spectral Domain Optical Coherence Tomography (SD‐OCT). We conducted longitudinal imaging of 40 wild‐type (WT) and cisplatin‐resistant (CPR) OVCAR8 multicellular tumor spheroids over 11 days. Four analyses were performed: volume analysis, optical attenuation analysis, uniformity analysis, and texture feature analysis. Volume analysis showed MBZ reduced spheroid growth in both groups, with greater effects in CPR‐MCTs. Optical attenuation analysis revealed increased necrotic tissue ratios in treated spheroids. Uniformity analysis demonstrated MBZ targets heterogeneous tissues effectively. Texture analysis identified significant structural changes, with 866 altered features in CPR spheroids versus 124 in WT spheroids. Cell viability assays confirmed MBZ's effectiveness against standard and chemo‐resistant OVCAR8 tumors. This study demonstrates SD‐OCT's utility for noninvasive therapy monitoring in 3D cancer models.

  • Open Access

    Octascope: a lightweight pre-trained model for optical coherence tomography

    by Haoyang Cui, Chen Wang, Paul Calle, Yunlong Liu, Qinghao Zhang, Sinaro Ly, Justin Reynolds, Feng Yan, Ke Zhang, Ronghao Liu, et al.

    Optical coherence tomography (OCT) imaging enables high resolution visualization of sub-surface tissue microstructures. However, OCT image analysis using deep learning is hampered by limited diverse training data to meet performance requirements and high inference latency for real-time applications. To address these challenges, we developed Octascope, a lightweight domain-specific convolutional neural network (CNN) - based model designed for OCT image analysis. Octascope was pre-trained using a curriculum learning approach, which involves sequential training, first on natural images (ImageNet), then on OCT images from retinal, abdominal, and renal tissues, to progressively acquire transferable knowledge. This multi-domain pre-training enables Octascope to generalize across varied tissue types. In two downstream tasks, Octascope demonstrated notable improvements in predictive accuracy compared to alternative approaches. In the epidural tissue detection task, our method surpassed single-task learning with fine-tuning by 9.13% and OCT-specific transfer learning by 5.95% in accuracy. Octascope outperformed VGG16 and ResNet50 by 5.36% and 6.66% in a retinal diagnosis task, respectively. In comparison to a Transformer-based OCT foundation model - RETFound, Octascope delivered 2 to 4.4 times faster inference speed with slightly better predictive accuracies in both downstream tasks. Octascope represented a significant advancement for OCT image analysis by providing an effective balance between computational efficiency and diagnostic accuracy for real-time clinical applications.


  • Deep Learning for Autonomous Surgical Guidance Using 3‐Dimensional Images From Forward‐Viewing Endoscopic Optical Coherence Tomography

    by Sinaro Ly, Adrien Badré, Parker Brandt, Chen Wang, Paul Calle, Justin Reynolds, Qinghao Zhang, Kar‐Ming Fung, Haoyang Cui, Zhongxin Yu, et al.

    A three‐dimensional convolutional neural network (3D‐CNN) was developed for the analysis of volumetric optical coherence tomography (OCT) images to enhance endoscopic guidance during percutaneous nephrostomy. The model was performance‐benchmarked using a 10‐fold nested cross‐validation procedure and achieved an average test accuracy of 90.57% across a dataset of 10 porcine kidneys. This performance significantly exceeded that of 2D‐CNN models that attained average test accuracies ranging from 85.63% to 88.22% using 1, 10, or 100 radial sections extracted from the 3D OCT volumes. The 3D‐CNN (~12 million parameters) was benchmarked against three state‐of‐the‐art volumetric architectures: the 3D Vision Transformer (3D‐ViT, ~45 million parameters), 3D‐DenseNet121 (~12 million parameters), and the Multi‐plane and Multi‐slice Transformer (M3T, ~29 million parameters). While these models achieved comparable inferencing accuracy, the 3D‐CNN exhibited lower inference latency (33 ms) than 3D‐ViT (86 ms), 3D‐DenseNet121 (58 ms), and M3T (93 ms), representing a critical advantage for real‐time surgical guidance applications. These results demonstrate the 3D‐CNN's capability as a powerful and practical tool for computer‐aided diagnosis in OCT‐guided surgical interventions.


  • Open Access

    Automatic renal carcinoma biopsy guidance using forward-viewing endoscopic optical coherence tomography and deep learning

    by Chen Wang, Haoyang Cui, Qinghao Zhang, Paul Calle, Yuyang Yan, Feng Yan, Kar-Ming Fung, Sanjay G. Patel, Zhongxin Yu, Sean Duguay, et al.

    Percutaneous renal biopsy is commonly used for kidney cancer diagnosis. However, the biopsy procedure remains challenging in sampling accuracy. Here we introduce a forward-viewing optical coherence tomography probe for differentiating tumor and normal tissues, aiming at precise biopsy guidance. Totally, ten human kidney samples, nine of which had malignant renal carcinoma and one had benign oncocytoma, were used for system evaluation. Based on their distinct imaging features, carcinoma could be efficiently distinguished from normal renal tissues. Additionally, oncocytoma could be differentiated from carcinoma. We developed convolutional neural networks for tissue recognition. Compared to the conventional attenuation coefficient method, convolutional neural network models provided more accurate carcinoma predictions. These models reached a tissue recognition accuracy of 99.1% on a hold-out set of four kidney samples. Furthermore, they could efficiently distinguish oncocytoma from carcinoma. In conclusion, our convolutional neural network-aided endoscopic imaging platform could enhance carcinoma diagnosis during percutaneous renal biopsy procedures.