Jaeho Shim

Jaeho Shim


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2015 in Journal of Physical Therapy Science
Verified
Journal Article
Open access
PDF file
JLJung-Seok Lee
Jung-Seok Lee
TKTae-Ho Kim
Tae-Ho Kim
DKDa Yeon Kim
Da Yeon Kim
JSJaeho Shim
Jaeho Shim
JLJin-Yong Lim
Jin-Yong Lim
Japan's largest platform for academic e-journals: J-STAGE is a full text database for reviewed academic papers published by Japanese societies

4 May 2025 in Animals
Verified
Journal Article
Open access
PDF file
SPSanghyeon Park
Sanghyeon Park
SGSeokmin Go
Seokmin Go
SKSeonhyo Kim
Seonhyo Kim
JSJaeho Shim
Jaeho Shim
Cataracts are a prevalent cause of vision loss in dogs, and timely diagnosis is essential for effective treatment. This study aimed to develop and evaluate deep learning models to automatically classify canine cataracts from ocular ultrasound images. A dataset of 3155 ultrasound images (comprising 1329 No cataract, 614 Cortical, 1033 Mature, and 179 Hypermature cases) was used to train and validate four widely used deep learning models (AlexNet, EfficientNetB3, ResNet50, and DenseNet161). Data augmentation and normalization techniques were applied to address category imbalance. DenseNet161 demonstrated the best performance, achieving a test accuracy of 92.03% and an F1-score of 0.8744. The confusion matrix revealed that the model attained the highest accuracy for the No cataract category (99.0%), followed by Cortical (90.3%) and Mature (86.5%) cataracts, while Hypermature cataracts were classified with lower accuracy (78.6%). Receiver Operating Characteristic (ROC) curve analysis confirmed strong discriminative ability, with an area under the curve (AUC) of 0.99. Visual interpretation using Gradient-weighted Class Activation Mapping indicated that the model effectively focused on clinically relevant regions. This deep learning-based classification framework shows significant potential for assisting veterinarians in diagnosing cataracts, thereby improving clinical decision-making in veterinary ophthalmology.

1 January 2022 in Journal of Veterinary Science
Verified
Journal Article
Open access
PDF file
YKYoungsam Kim
Youngsam Kim
SKSeonmi Kang
Seonmi Kang
SKSunhyo Kim
Sunhyo Kim
JSJaeho Shim
Jaeho Shim
SGSeokmin Go
Seokmin Go
KSKangmoon Seo
Kangmoon Seo
Kim Y, et al. J Vet Sci. 2021 Oct;23(1):e10. https://doi.org/10.4142/jvs.21169

1 April 2018 in Journal of Biomechanics
Verified
Journal Article
Closed access
EOEdward Ofori
Edward Ofori
JSJaeho Shim
Jaeho Shim
Jacob SosnoffJacob Sosnoff
Jacob Sosnoff

29 April 2022 in Veterinary Record
Verified
Journal Article
Closed access
DJDajeong Jeong
Dajeong Jeong
SKSeonmi Kang
Seonmi Kang
JSJaeho Shim
Jaeho Shim
ELEunji Lee
Eunji Lee
YJYoungseok Jeong
Youngseok Jeong
KSKangmoon Seo
Kangmoon Seo

5 June 2020 in Veterinary Ophthalmology
Verified
Journal Article
Open access
JSJaeho Shim
Jaeho Shim
SKSeonmi Kang
Seonmi Kang
YPYoonji Park
Yoonji Park
SKSunhyo Kim
Sunhyo Kim
SGSeokmin Go
Seokmin Go
KSKangmoon Seo
Kangmoon Seo
Objective: To evaluate the clinical relevance of intraocular pressure (IOP) measured with three different rebound tonometers in an ex vivo analysis and clinical trials in dogs.Animals and procedures: Ex vivo analysis and clinical trials were performed separately. For the ex vivo analysis, eight enucleated eyes were obtained from four Beagle dogs. IOP values measured with TONOVET®(TV‐IOP), TONOVET‐Plus®(TVP‐IOP), and SW‐500®(SW‐IOP) were compared with manometric IOPs. For clinical trials, each tonometer was evaluated separately, depending on whether TVP‐IOP was higher or lower than 14 mm Hg. One‐way repeatedmeasures analysis of variance, simple linear regression analysis, and Bland‐Altman plots were used for statistical analyses.Results: In ex vivo analysis, TV‐IOP and TVP‐IOP were not significantly different from manometric IOP. However, SW‐IOP underestimated IOP compared to manometry. Higher discrepancy was observed in TV‐IOP and SW‐IOP with an increase in manometric IOP. In clinical trials, no significant difference was observed between TV‐IOP (9.73 ± 2.92) and TVP‐IOP (11.36 ± 2.23) when TVP‐IOP was lower than 14 mm Hg, but SW‐IOP (8.70 ± 3.03) was significantly lower than TVP‐IOP. TV‐IOP (15.96 ± 6.47) and SW‐IOP (13.09 ± 3.72) were significantly lower than TVP‐IOP (20.08 ± 6.60) when the IOP was higher than 14 mm Hg of TVP‐IOP.Conclusions: This study demonstrates that the TONOVET®and TONOVET‐Plus®provide a useful approach for ex vivo analysis. In clinical trials, results of TV‐IOP and SW‐IOP were significantly lower than of TVP‐IOP when IOP was higher than 14 mm Hg of TVP‐IOP. The characteristics of rebound tonometers should be considered in clinical settings.