CLChin-Hsin Liu

Chin-Hsin Liu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chin-Hsin Liu has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A multi-task masked autoencoder with GAN-based augmentation for PD-L1 prediction from chest CT images

    by Ying-Zhen Ye, Pei-Yu Chou, De-Xiang Ou, Wei-Hsuan Tai, Chong-Jen Yu, Shu-Yung Lin, Yen-Fu Chen, Cheng-Yi Wang, Chin-Hsin Liu, Chi-En Lee, et al.

    Targeted and immune-based therapies, such as PD-1/PD-L1 inhibitors, have become standard treatments for advanced non-small cell lung cancer (NSCLC). However, accurately identifying patients who benefit from these therapies remains challenging due to tumor heterogeneity and variability in PD-L1 staining. To address this issue, we propose a non-invasive, model-driven computer-aided diagnosis framework that predicts PD-L1 expression directly from CT images under limited labeled data conditions. This study included 188 NSCLC patients from two university hospitals, of whom 49 had PD-L1 expression ≥ 50% and 139 had < 50%. We introduce a Multi-task Masked Autoencoder (MTMAE) with three key components: (1) a self-supervised masked image modeling strategy to leverage unlabeled data and improve data efficiency, (2) an integrated segmentation task to enhance tumor-focused feature learning, and (3) a Gabor-based generative adversarial network for data augmentation to improve generalization. The proposed model achieved an AUC of 0.735 and an accuracy of 0.724, outperforming traditional supervised pretraining (AUC 0.695) and single-task MAE (AUC 0.712). These results demonstrate that combining self-supervised learning, multi-task learning, and GAN-based augmentation enables a reproducible and standardized model-based prediction of clinically reported PD-L1 status from CT images, providing a non-invasive complementary tool for treatment decision-making.

  • Open Access

    The Diagnostic Value of Pulsar Perimetry, Optical Coherence Tomography, and Optical Coherence Tomography Angiography in Pre-Perimetric and Perimetric Glaucoma

    by Hung-Chih Chen, Michael Chia-Yen Chou, Ming-Tsung Lee, Chia-Yi Lee, Che-Ning Yang, Chin-Hsin Liu, Shih-Chun Chao

    The purpose of this article is to investigate the diagnostic value of Pulsar perimetry (PP), optical coherence tomography (OCT), and optical coherence tomography angiography (OCTA) in pre-perimetric glaucoma (PPG) and perimetric glaucoma (PG). This retrospective cross-sectional study included 202 eyes (145 eyes in the control group, 40 eyes in the PPG group, and 17 eyes in the PG group) from 105 subjects. The results were analyzed by paired t-tests and Wilcoxon signed-rank test. The area under the curve (AUC), sensitivity, and specificity were used to evaluate the diagnostic accuracy. Pearson correlation was used to investigate the relationships of each parameter. The most sensitive parameters for differentiating the control group from the PPG group by using Pulsar, OCT, and OCTA were square loss variance of PP (AUC = 0.673, p < 0.001), superior ganglion cell complex thickness (AUC = 0.860, p < 0.001), and superior-hemi retina thickness (AUC = 0.817, p < 0.001). In the PG group, the most sensitive parameters were mean defect of PP (AUC = 0.885, p < 0.001), whole image of ganglion cell complex thickness (AUC = 0.847, p < 0.001), and perifoveal retina thickness (AUC = 0.833, p < 0.001). The mean defect of PP was significantly correlated with vascular parameters (radial peripapillary capillary (RPC), p = 0.008; vessel density of macular superficial vascular complex (VDms), p = 0.001; vessel density of macular deep vascular complex (VDmd), p = 0.002). In conclusion, structural measurements using OCT were more sensitive than vascular measurements of OCTA and functional measurements of PP for PPG, while PP was more sensitive than the structural and vascular measurements for PG. The mean defect of PP was also shown to be highly correlated with the reduction of vessel density.


  • Open Access

    Early Macular Angiography among Patients with Glaucoma, Ocular Hypertension, and Normal Subjects

    by Shih-Chun Chao, Shang-Jung Yang, Hung-Chi Chen, Chi-Chin Sun, Chin-Hsin Liu, Chia-Yi Lee

    Purpose. To evaluate early macular circulation in open-angle glaucoma (OAG), normal-tension glaucoma (NTG), ocular hypertension (OHT), and healthy subjects via optical coherence tomography angiography (OCTA). Methods. A retrospective cross-sectional study was conducted. Medical records were reviewed, and the patients who received OCTA examinations were divided into the OAG, NTG, OHT, and normal groups. The ophthalmic data including best-corrected visual acuity, spherical equivalent, intraocular pressure, central corneal thickness, central foveal thickness, visual field deviation, retinal nerve fiber layers thickness, and ganglion cell complex thickness were obtained from medical documents. For the macular area, the superficial vessel density (VD), deep VD, foveal avascular zone (FAZ), flow area of the outer retina, and flow area of the choriocapillaris were measured via OCTA and analyzed using the default vascular density analysis program in the same OCTA device. Results. A total of 70 eyes from 70 patients were analyzed in the current study. Significant differences in the intraocular pressure, central corneal thickness, visual field deviation, retinal fiber layer thickness, and ganglion cell complex thickness were observed in the patients in the glaucoma group at their last visits. The OAG and NTG groups evinced a lower superficial VD than did the control group, while the NTG group had a lower deep VD than the control group. The NTG group also had a larger FAZ than did the OHT group. The flow area of the outer retina in the OAG group was low relative to those of the OHT and control groups. No difference in choriocapillaris perfusion was observed among the groups. Conclusion. The OAG and NTG patients demonstrated impaired vasculature before significant disease development could be observed. Furthermore, the differences in macular circulation may be associated with differences in the courses of disease between the glaucoma and OHT patients.