Hao-En Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hao-En Lu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Jing Wang
University of Pittsburgh, Department of Radiology, Pittsburgh, Pennsylvania, United States
3 shared publicationsTong Yu
University of Pittsburgh, Department of Radiology, Pittsburgh, Pennsylvania, United States
3 shared publications- Dinesh Kumbhare
University of Toronto
2 shared publications - Jiantao Pu
Department of Radiology, University of Pittsburgh, Pittsburgh, USA
2 shared publications Richard Wilson
The MetroHealth System
2 shared publicationsXin Meng
University of Pittsburgh
2 shared publications
Latest Publications
- 1 September 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (05) , 1-16
Promise and challenges of heart chamber segmentation from noncontrast CT scans using contrastive unpaired image translation: a feasibility study
PurposeTo evaluate the feasibility and challenges of heart chamber segmentation from noncontrast CT scans using contrastive unpaired image translation and deep learning-based segmentation.ApproachWe developed ChameleonNet, a framework utilizing the Contrastive Unpaired Translation (CUT) network with decoupled contrastive learning (DCL) loss to synthesize noncontrast CT from contrast CT scans. Using annotations of four heart chambers (left atrium (LA), left ventricle (LV), right atrium (RA), and right ventricle (RV)) from contrast scans, we trained a Hausdorff distance loss-enhanced nnU-Net on synthesized noncontrast images. The translation model was trained with 35,538 contrast-enhanced and 37,197 noncontrast CT slices. The segmentation model was trained with 292 synthesized noncontrast scans. Performance was evaluated using Dice similarity coefficient (DSC) and 95th Hausdorff distance (HD95) on 36 synthesized noncontrast scans, and volume agreement on 36 real noncontrast CT scans was assessed using Pearson correlation, mean absolute percentage error (MAPE), and mean percentage error (MPE).ResultsThe segmentation model achieved DSC of 0.94 (±0.01), 0.91 (±0.04), 0.92 (±0.03), 0.93 (±0.02), and HD95 of 3.63 (±1.49), 5.74 (±4.08), 5.18 (±1.77), and 5.51 (±3.21) mm on synthesized noncontrast images for LA, LV, RA, and RV, respectively. On real noncontrast CT scans, Pearson correlations were 0.93, 0.82, 0.87, and 0.89 (all p<0.001), with MAPE ranging from 9.22% to 20.79%, and MPE ranging from −12.52% to 4.67%.ConclusionsChameleonNet demonstrated feasibility for heart chamber segmentation from noncontrast CT without manual noncontrast annotations. However, volume errors, particularly for LV and RV, indicate that further refinement and validation are needed before clinical use.
- 1 September 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (05) , 1-16
Promise and challenges of heart chamber segmentation from noncontrast CT scans using contrastive unpaired image translation: a feasibility study
PurposeTo evaluate the feasibility and challenges of heart chamber segmentation from noncontrast CT scans using contrastive unpaired image translation and deep learning-based segmentation.ApproachWe developed ChameleonNet, a framework utilizing the Contrastive Unpaired Translation (CUT) network with decoupled contrastive learning (DCL) loss to synthesize noncontrast CT from contrast CT scans. Using annotations of four heart chambers (left atrium (LA), left ventricle (LV), right atrium (RA), and right ventricle (RV)) from contrast scans, we trained a Hausdorff distance loss-enhanced nnU-Net on synthesized noncontrast images. The translation model was trained with 35,538 contrast-enhanced and 37,197 noncontrast CT slices. The segmentation model was trained with 292 synthesized noncontrast scans. Performance was evaluated using Dice similarity coefficient (DSC) and 95th Hausdorff distance (HD95) on 36 synthesized noncontrast scans, and volume agreement on 36 real noncontrast CT scans was assessed using Pearson correlation, mean absolute percentage error (MAPE), and mean percentage error (MPE).ResultsThe segmentation model achieved DSC of 0.94 (±0.01), 0.91 (±0.04), 0.92 (±0.03), 0.93 (±0.02), and HD95 of 3.63 (±1.49), 5.74 (±4.08), 5.18 (±1.77), and 5.51 (±3.21) mm on synthesized noncontrast images for LA, LV, RA, and RV, respectively. On real noncontrast CT scans, Pearson correlations were 0.93, 0.82, 0.87, and 0.89 (all p<0.001), with MAPE ranging from 9.22% to 20.79%, and MPE ranging from −12.52% to 4.67%.ConclusionsChameleonNet demonstrated feasibility for heart chamber segmentation from noncontrast CT without manual noncontrast annotations. However, volume errors, particularly for LV and RV, indicate that further refinement and validation are needed before clinical use.
- Open Access
Data-efficient Self-Supervised Diffusion Learning for Detecting Myofascial Pain in Upper Trapezius Muscle with B-mode Ultrasound Videos
Deep learning has transformed medical image and video analysis, but it usually requires large, well annotated datasets. In many clinical domains, especially when testing novel mechanistic hypotheses, such retrospective datasets are hard to obtain since acquiring adequate cohorts is time intensive, costly, and operationally difficult. This creates a critical translational gap: scientifically compelling early stage ideas may remain untested due to lack of sufficient sample size to support conventional deep learning pipelines. Developing data-efficient strategies for evaluating new hypotheses within small prospective cohorts is therefore essential to de-risk innovation before large-scale validation. Myofascial Pain Syndrome (MPS) exemplifies this challenge, as quantitative ultrasound imaging biomarkers for MPS remain underexplored. We investigated whether MPS in the upper trapezius can be detected from full B-mode ultrasound videos in a small prospective cohort (11 controls, 13 patients). Videos were automatically preprocessed and resampled using a sliding window strategy to expand training samples (404 clips). A self-supervised Video Diffusion Encoder (VDE) is developed to learn spatiotemporal representations without relying on extensive labeled data, and compared it with transfer-learning-based ResNet, VideoMAE, and SimCLR. Using subject-level stratified four-fold cross-validation, the VDE outperformed transfer learning baselines and achieved performance comparable to SimCLR, with subject-level AUC of 0.79 and accuracy of 0.86, and no significant differences between latent-only and combined trigger point analyses. These results demonstrate that self-supervised diffusion learning can support robust, data-efficient deep learning in small prospective studies, enabling early feasibility testing of innovative ultrasound biomarkers before large-scale clinical trials.
Open AccessData-efficient Self-Supervised Diffusion Learning for Detecting Myofascial Pain in Upper Trapezius Muscle with B-mode Ultrasound Videos
Deep learning has transformed medical image and video analysis, but it usually requires large, well annotated datasets. In many clinical domains, especially when testing novel mechanistic hypotheses, such retrospective datasets are hard to obtain since acquiring adequate cohorts is time intensive, costly, and operationally difficult. This creates a critical translational gap: scientifically compelling early stage ideas may remain untested due to lack of sufficient sample size to support conventional deep learning pipelines. Developing data-efficient strategies for evaluating new hypotheses within small prospective cohorts is therefore essential to de-risk innovation before large-scale validation. Myofascial Pain Syndrome (MPS) exemplifies this challenge, as quantitative ultrasound imaging biomarkers for MPS remain underexplored. We investigated whether MPS in the upper trapezius can be detected from full B-mode ultrasound videos in a small prospective cohort (11 controls, 13 patients). Videos were automatically preprocessed and resampled using a sliding window strategy to expand training samples (404 clips). A self-supervised Video Diffusion Encoder (VDE) is developed to learn spatiotemporal representations without relying on extensive labeled data, and compared it with transfer-learning-based ResNet, VideoMAE, and SimCLR. Using subject-level stratified four-fold cross-validation, the VDE outperformed transfer learning baselines and achieved performance comparable to SimCLR, with subject-level AUC of 0.79 and accuracy of 0.86, and no significant differences between latent-only and combined trigger point analyses. These results demonstrate that self-supervised diffusion learning can support robust, data-efficient deep learning in small prospective studies, enabling early feasibility testing of innovative ultrasound biomarkers before large-scale clinical trials.