Yike Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yike Guo has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Kai Ding
Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD 21287, USA
5 shared publications - Yi Luo
Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA
5 shared publications - Hamed Hooshangnejad
Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
4 shared publications - Quan Chen
Department of Radiation Oncology, Mayo Clinic Arizona, Phoenix, AZ 85054, USA
4 shared publications - Rui Zhang
Division of Computational Health Sciences, Department of Surgery, University of Minnesota, Minneapolis, USA
4 shared publications - Xue Feng
Department of Biomedical Engineering University of Virginia Charlottesville Virginia USA
4 shared publications
Latest Publications
- Open Access
- 8 May 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (10) , 1441
Hybrid Curriculum Learning for Data-Efficient Lung Nodule Detection with YOLOv11
Background/Objectives: Accurate detection of pulmonary nodules on chest CT is critical for lung cancer screening, yet training robust detectors remains challenging due to the high cost of reliable annotations. In this work, we present a systematic study of curriculum learning for CT-based lung nodule detection on the enhanced LUNA25 benchmark and propose a hybrid curriculum learning framework for data-efficient optimization. Methods: Our approach estimates sample difficulty by fusing clinically interpretable handcrafted factors such as nodule size and count with model-driven signals such as prediction confidence from a teacher model, and constructs a three-stage progressive training curriculum from easy to hard samples. Using YOLOv11s as a strong baseline, the proposed hybrid curriculum is compared against conventional training without curriculum learning and against single-source curricula. Results: On the held-out LUNA25 test set, hybrid curriculum learning increases from 0.672 to 0.696, from 0.369 to 0.385, recall from 0.588 to 0.634, and precision from 0.725 to 0.764. Extensive data-efficiency experiments with proportional reductions (1/2, 1/5, 1/10) and fixed training samples (5000–40,000 slices) further confirm consistent gains across limited-data regimes. Conclusions: These results demonstrate that jointly leveraging intrinsic image complexity and optimization-aware feedback provides effective sample scheduling for robust and data-efficient lung nodule detection.- 8 May 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (10) , 1441
Open AccessHybrid Curriculum Learning for Data-Efficient Lung Nodule Detection with YOLOv11
Background/Objectives: Accurate detection of pulmonary nodules on chest CT is critical for lung cancer screening, yet training robust detectors remains challenging due to the high cost of reliable annotations. In this work, we present a systematic study of curriculum learning for CT-based lung nodule detection on the enhanced LUNA25 benchmark and propose a hybrid curriculum learning framework for data-efficient optimization. Methods: Our approach estimates sample difficulty by fusing clinically interpretable handcrafted factors such as nodule size and count with model-driven signals such as prediction confidence from a teacher model, and constructs a three-stage progressive training curriculum from easy to hard samples. Using YOLOv11s as a strong baseline, the proposed hybrid curriculum is compared against conventional training without curriculum learning and against single-source curricula. Results: On the held-out LUNA25 test set, hybrid curriculum learning increases from 0.672 to 0.696, from 0.369 to 0.385, recall from 0.588 to 0.634, and precision from 0.725 to 0.764. Extensive data-efficiency experiments with proportional reductions (1/2, 1/5, 1/10) and fixed training samples (5000–40,000 slices) further confirm consistent gains across limited-data regimes. Conclusions: These results demonstrate that jointly leveraging intrinsic image complexity and optimization-aware feedback provides effective sample scheduling for robust and data-efficient lung nodule detection. - Open Access
Impact of Hydrogel Spacer Insertion on Radiation Dose to Erectile Structures and Longitudinal Sexual Function in Prostate Cancer Patients
Background: Erectile dysfunction is a common late effect of prostate radiotherapy. Hydrogel spacers aim to reduce radiation exposure to nearby structures by increasing the distance between the prostate and surrounding tissues, potentially preserving sexual function. Methods: In this retrospective cohort study of 117 prostate cancer patients who received hydrogel spacers, we compared pre- and post-insertion radiation dose and anatomical positioning of erectile structures using paired t-tests. Longitudinal sexual function, assessed via EPIC scores, was modeled using linear mixed-effects regression with natural splines (df = 3), incorporating random intercepts and slopes to account for within-subject variability. Results: Spacer insertion significantly reduced radiation dose to the left and right neurovascular bundles (mean reductions: 1.66 Gy, 95% CI: 1.32–2.00; and 1.64 Gy, 95% CI: 1.28–2.01, respectively; p < 0.01) and the right perineal artery (1.33 Gy, 95% CI: 0.57–2.09; p < 0.01). No significant dose changes were observed for the penile bulb or left perineal artery, nor in anatomical distances. However, spatial displacement was confirmed by significant overlap and integrated volume changes. Longitudinal modeling showed a significant decline in sexual function between 12 and ≥36 months post-treatment (Spline 2: β = –12.72, 95% CI: −18.52–−6.92 and Spline 3: β = –6.68, 95% CI: −10.96–−2.40; p < 0.01). Conclusions: Hydrogel spacer insertion was associated with significant reductions in radiation dose to erectile structures, most notably the neurovascular bundles and the right perineal artery. However, longitudinal analyses revealed no corresponding preservation of sexual function. These findings suggest that while hydrogel spacers effectively reduce radiation exposure to key anatomical structures, their clinical benefit for maintaining erectile function remains uncertain.
Open AccessImpact of Hydrogel Spacer Insertion on Radiation Dose to Erectile Structures and Longitudinal Sexual Function in Prostate Cancer Patients
Background: Erectile dysfunction is a common late effect of prostate radiotherapy. Hydrogel spacers aim to reduce radiation exposure to nearby structures by increasing the distance between the prostate and surrounding tissues, potentially preserving sexual function. Methods: In this retrospective cohort study of 117 prostate cancer patients who received hydrogel spacers, we compared pre- and post-insertion radiation dose and anatomical positioning of erectile structures using paired t-tests. Longitudinal sexual function, assessed via EPIC scores, was modeled using linear mixed-effects regression with natural splines (df = 3), incorporating random intercepts and slopes to account for within-subject variability. Results: Spacer insertion significantly reduced radiation dose to the left and right neurovascular bundles (mean reductions: 1.66 Gy, 95% CI: 1.32–2.00; and 1.64 Gy, 95% CI: 1.28–2.01, respectively; p < 0.01) and the right perineal artery (1.33 Gy, 95% CI: 0.57–2.09; p < 0.01). No significant dose changes were observed for the penile bulb or left perineal artery, nor in anatomical distances. However, spatial displacement was confirmed by significant overlap and integrated volume changes. Longitudinal modeling showed a significant decline in sexual function between 12 and ≥36 months post-treatment (Spline 2: β = –12.72, 95% CI: −18.52–−6.92 and Spline 3: β = –6.68, 95% CI: −10.96–−2.40; p < 0.01). Conclusions: Hydrogel spacer insertion was associated with significant reductions in radiation dose to erectile structures, most notably the neurovascular bundles and the right perineal artery. However, longitudinal analyses revealed no corresponding preservation of sexual function. These findings suggest that while hydrogel spacers effectively reduce radiation exposure to key anatomical structures, their clinical benefit for maintaining erectile function remains uncertain.
- Open Access
Multiscale Segmentation-Guided Diffusion Model for CBCT-to-CT Synthesis
To improve synthetic CT (sCT) generation from cone-beam CT (CBCT) in radiotherapy, we propose a multiscale segmentation-guided diffusion framework. The proposed model integrates anatomical priors across multiple spatial resolutions through a segmentation mask pyramid and introduces a scale-specific loss function to guide learning at each level. When evaluated on the SynthRAD2023 brain dataset, our model achieves a mean absolute error (MAE) of 61.82 HU, a peak signal-to-noise ratio (PSNR) of 32.05 dB, and a structural similarity index (SSIM) of 0.90, outperforming baseline models. These results suggest that multiscale anatomical guidance can improve the fidelity and anatomical consistency of sCT images, thus facilitating high-quality CBCT-to-CT translation in radiotherapy applications.
Open AccessMultiscale Segmentation-Guided Diffusion Model for CBCT-to-CT Synthesis
To improve synthetic CT (sCT) generation from cone-beam CT (CBCT) in radiotherapy, we propose a multiscale segmentation-guided diffusion framework. The proposed model integrates anatomical priors across multiple spatial resolutions through a segmentation mask pyramid and introduces a scale-specific loss function to guide learning at each level. When evaluated on the SynthRAD2023 brain dataset, our model achieves a mean absolute error (MAE) of 61.82 HU, a peak signal-to-noise ratio (PSNR) of 32.05 dB, and a structural similarity index (SSIM) of 0.90, outperforming baseline models. These results suggest that multiscale anatomical guidance can improve the fidelity and anatomical consistency of sCT images, thus facilitating high-quality CBCT-to-CT translation in radiotherapy applications.
- Open Access
- 25 November 2025
- Published by MDPI AG in Bioengineering
- Vol. 12 (12) , 1297
Deep Learning for CT Synthesis in Radiotherapy
With the rapid development of artificial intelligence (AI), various deep learning (DL) methods have been introduced into radiation oncology. Among them, the generation of synthetic Computed Tomography (sCT) images has attracted increasing attention, as it supports different clinical scenarios, from image-guided adaptive radiotherapy (IGART) to the simulation-free workflow. This review provides a comprehensive overview of recent studies on DL-based sCT synthesis in radiotherapy from multiple imaging modalities, including Cone-Beam CT (CBCT), Magnetic Resonance Imaging (MRI), and diagnostic CT, and discusses their clinical applications in CBCT-based online adaptive radiotherapy, MRI-guided radiotherapy, and simulation-free workflows. We also examine the architectures of representative DL models such as convolutional neural networks (CNNs) and generative adversarial networks (GANs) and summarize emerging training strategies. Finally, we discuss current challenges of clinical translation of DL algorithms into clinical practice and suggest potential directions for future research. Overall, this paper highlights the potential of AI-driven sCT generation to advance treatment planning by reducing imaging burden, improving dose accuracy, and accelerating workflow efficiency, thus ultimately improving the treatment outcome of patient care.
- 25 November 2025
- Published by MDPI AG in Bioengineering
- Vol. 12 (12) , 1297
Open AccessDeep Learning for CT Synthesis in Radiotherapy
With the rapid development of artificial intelligence (AI), various deep learning (DL) methods have been introduced into radiation oncology. Among them, the generation of synthetic Computed Tomography (sCT) images has attracted increasing attention, as it supports different clinical scenarios, from image-guided adaptive radiotherapy (IGART) to the simulation-free workflow. This review provides a comprehensive overview of recent studies on DL-based sCT synthesis in radiotherapy from multiple imaging modalities, including Cone-Beam CT (CBCT), Magnetic Resonance Imaging (MRI), and diagnostic CT, and discusses their clinical applications in CBCT-based online adaptive radiotherapy, MRI-guided radiotherapy, and simulation-free workflows. We also examine the architectures of representative DL models such as convolutional neural networks (CNNs) and generative adversarial networks (GANs) and summarize emerging training strategies. Finally, we discuss current challenges of clinical translation of DL algorithms into clinical practice and suggest potential directions for future research. Overall, this paper highlights the potential of AI-driven sCT generation to advance treatment planning by reducing imaging burden, improving dose accuracy, and accelerating workflow efficiency, thus ultimately improving the treatment outcome of patient care.
- Open Access
Multimodal Slice Interaction Network Enhanced by Transfer Learning for Precise Segmentation of Internal Gross Tumor Volume in Lung Cancer PET/CT Imaging
Lung cancer remains the leading cause of cancerrelated deaths globally. Accurate delineation of internal gross tumor volume (IGTV) in PET/CT imaging is pivotal for optimal radiation therapy in mobile tumors such as lung cancer to account for tumor motion, yet is hindered by the limited availability of annotated IGTV datasets and attenuated PET signal intensity at tumor boundaries. In this study, we present a transfer learningbased methodology utilizing a multimodal interactive perception network with MAMBA, pre-trained on extensive gross tumor volume (GTV) datasets and subsequently fine-tuned on a private IGTV cohort. This cohort constitutes the PET/CT subset of the Lung-cancer Unified Cross-modal Imaging Dataset (LUCID). To further address the challenge of weak PET intensities in IGTV peripheral slices, we introduce a slice interaction module (SIM) within a 2.5D segmentation framework to effectively model inter-slice relationships. Our proposed module integrates channel and spatial attention branches with depthwise convolutions, enabling more robust learning of slice-to-slice dependencies and thereby improving overall segmentation performance. A comprehensive experimental evaluation demonstrates that our approach achieves a Dice of 0.609 on the private IGTV dataset, substantially surpassing the conventional baseline score of 0.385. This work highlights the potential of transfer learning, coupled with advanced multimodal techniques and a SIM to enhance the reliability and clinical relevance of IGTV segmentation for lung cancer radiation therapy planning.
Open AccessMultimodal Slice Interaction Network Enhanced by Transfer Learning for Precise Segmentation of Internal Gross Tumor Volume in Lung Cancer PET/CT Imaging
Lung cancer remains the leading cause of cancerrelated deaths globally. Accurate delineation of internal gross tumor volume (IGTV) in PET/CT imaging is pivotal for optimal radiation therapy in mobile tumors such as lung cancer to account for tumor motion, yet is hindered by the limited availability of annotated IGTV datasets and attenuated PET signal intensity at tumor boundaries. In this study, we present a transfer learningbased methodology utilizing a multimodal interactive perception network with MAMBA, pre-trained on extensive gross tumor volume (GTV) datasets and subsequently fine-tuned on a private IGTV cohort. This cohort constitutes the PET/CT subset of the Lung-cancer Unified Cross-modal Imaging Dataset (LUCID). To further address the challenge of weak PET intensities in IGTV peripheral slices, we introduce a slice interaction module (SIM) within a 2.5D segmentation framework to effectively model inter-slice relationships. Our proposed module integrates channel and spatial attention branches with depthwise convolutions, enabling more robust learning of slice-to-slice dependencies and thereby improving overall segmentation performance. A comprehensive experimental evaluation demonstrates that our approach achieves a Dice of 0.609 on the private IGTV dataset, substantially surpassing the conventional baseline score of 0.385. This work highlights the potential of transfer learning, coupled with advanced multimodal techniques and a SIM to enhance the reliability and clinical relevance of IGTV segmentation for lung cancer radiation therapy planning.