JPJi-Hwan Pahk

Ji-Hwan Pahk

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ji-Hwan Pahk has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Modified Tibial Plateau Levelling Osteotomy in a Cat With a Cranial Cruciate Ligament Rupture and a Concurrent Medial Patellar Luxation

    by Ji‐Hwan Pahk, Kyu‐Won Kang, Byung‐Jae Kang

    Case Summary: A 12‐year‐old, castrated male Russian Blue cat presented with chronic right pelvic limb lameness that had markedly worsened over the previous week. Orthopaedic examination revealed cranial cruciate ligament rupture with concurrent Grade 3 medial patellar luxation (MPL) in the right stifle. Pain was elicited upon patellar reduction. Radiographs showed a tibial plateau angle (TPA) of 35° and medial deviation of the tibial tuberosity. A modified tibial plateau levelling osteotomy (mTPLO) was planned for the right pelvic limb to correct both cranial tibial thrust and MPL in a single procedure. The right stifle was explored by lateral arthrotomy, and adjunctive surgical techniques, including trochlear block recession, medial release and lateral imbrication, were performed to correct the MPL. The proximal tibial segment was rotated to achieve a post‐operative TPA of 5° and stabilized using an Arix‐vet 1.5/2.0 mTPLO plate with a 2‐mm offset. Post‐operative imaging confirmed correction of the TPA and lateral translation of the tibial tuberosity. The bone apposition ratio was 0.83. At 4 months post‐operatively, radiographic union was confirmed. Gait pattern and orthopaedic examination findings, including patellar stability and absence of cranial tibial thrust, were comparable to the pre‐deterioration clinical state. Relevance and Novel Information: To our knowledge, this is the first report of mTPLO in a feline patient. Given the difficulty of post‐operative exercise restriction in cats, the single‐cut design and maintenance of bone apposition of the mTPLO may offer enhanced stability. No significant alteration in the mechanical medial proximal tibial angle was observed, supporting the safety of a 2‐mm offset in this case.

  • Open Access

    Clinical Effects of a Prescription Joint Diet in Small-Breed Dogs with Osteoarthritis

    by Dohkyung Lee, Jaeyoung Jang, Changsu Jung, Namyul Kim, Ji-Hwan Pahk, Kyu-Won Kang, Chae-Lim Lee, Sungho Do, HooDeok Kim, Byung-Jae Kang

    Dohkyung Lee, Jaeyoung Jang, Changsu Jung, Namyul Kim, Ji-Hwan Pahk, Kyu-Won Kang, Chae-Lim Lee, Sungho Do, HooDeok Kim, Byung-Jae Kang. J Vet Clin 2026;43:94-101. https://doi.org/10.17555/jvc.2026.43.2.94

  • Open Access

    A deep learning–based markerless gait analysis model for dogs shows promising accuracy when validated with 2-dimensional marker–based data

    by Ji-Hwan Pahk, Sung-Jun Park, Ji-Hyun Seo, Hyun-Su Kim, Mi-Jin Son, Young-Seok Jin, Hyun-Jung Kim, Byung-Jae Kang

    Objective: To train a deep learning–based markerless gait analysis model from random initialization, tailored for canine gait analysis, in clinical settings and to validate against 2-D marker–based systems. Methods: This prospective observational study used 408 client-owned dogs of more than 30 breeds, ranging from small to large body types. Dogs walked or trotted a 3.3-m straight walkway and were recorded via a lateral single-camera setup using a smartphone camera (1080p resolution, 30 frames/s). Of these, 374 dogs contributed 20,000 markerless images for model training. For model validation and testing, 34 dogs (20 for the validation set and 14 for the test set) were recorded with physical markers that were directly attached to specific bony landmarks by a veterinarian to generate ground-truth data, and each subset included 10 breeds representing a range of sizes and morphologies. The ViTPose-L model was further trained from random initialization on the canine-specific dataset. Accuracy was evaluated using the Common Objects in Context (COCO)-style mean average precision, normalized keypoint error, and percentage of correct keypoints. Results: The markerless model achieved high accuracy, with a mean average precision of 96.6%, mean normalized keypoint error of 2.29 and percentage of correct keypoints at 0.05 of 92.62%. The model’s performance exceeded previously reported benchmarks on public datasets. Conclusions: A deep learning–based markerless gait analysis system shows promising but early-stage accuracy for canine landmark localization compared with 2-D marker–based data. Clinical Relevance: This system may offer clinical utility for canine gait assessment, but further validation across breeds and environments is needed before routine use.