Doojin Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Doojin Kim has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Doo-Ho Lee
Gachon University Gil Medical Center, Gachon University College of Medicine
8 shared publications - Yeon Ho Park
Department of Surgery, Gachon University Gil Medical Center, Gachon University College of Medicine, Incheon, Korea
5 shared publications - Sang Tae Choi
Department of Surgery, Gachon University Gil Medical Center, Gachon University College of Medicine, Incheon, Korea
4 shared publications Yeon Ho Park
Department of Surgery, Gachon University Gil Medical Center, Gachon University School of Medicine, Incheon, Korea
4 shared publications- Jaehun Yang
Department of Surgery, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
3 shared publications Joo Seop Kim
Department of Surgery, Kangdong Sungsim Hospital, Hallym University School of Medicine, Seoul, South Korea
3 shared publications
Latest Publications
- Open Access
- 8 November 2025
- Published by MDPI AG in Diagnostics
- Vol. 15  (22) , 2834
Deep Learning Model for Volume Measurement of the Remnant Pancreas After Pancreaticoduodenectomy and Distal Pancreatectomy
Background/Objectives: Accurate volumetry of the remnant pancreas after pancreatectomy is crucial for assessing postoperative endocrine and exocrine function but remains challenging due to anatomical variability and complex postoperative morphology. This study aimed to develop and validate a deep learning (DL)-based model for automatic segmentation and volumetry of the remnant pancreas using abdominal CT images. Methods: A total of 1067 CT scans from 341 patients who underwent pancreaticoduodenectomy and 512 scans from 184 patients who underwent distal pancreatectomy were analyzed. Ground truth masks were manually delineated and verified through multi-expert consensus. Six 3D segmentation models were trained and compared, including four convolution-based U-Net variants (basic, dense, residual, and residual dense) and two transformer-based models (Trans U-Net and Swin U-Net). Model performance was evaluated using five-fold cross-validation with sensitivity, specificity, precision, accuracy, and Dice similarity coefficient. Results: The Residual Dense U-Net achieved the best performance among convolutional models, with dice similarity coefficient (DSC) values of 0.7655 ± 0.0052 for pancreaticoduodenectomy and 0.8086 ± 0.0091 for distal pancreatectomy. Transformer-based models showed slightly higher DSCs (Swin U-Net: 0.7787 ± 0.0062 and 0.8132 ± 0.0101), with statistically significant but numerically small improvements (p < 0.01). Conclusions: The proposed DL-based approach enables accurate and reproducible postoperative pancreas segmentation and volumetry. Automated volumetric assessment may support objective evaluation of remnant pancreatic function and provide a foundation for predictive modeling in long-term clinical management after pancreatectomy.
- 8 November 2025
- Published by MDPI AG in Diagnostics
- Vol. 15  (22) , 2834
Open AccessDeep Learning Model for Volume Measurement of the Remnant Pancreas After Pancreaticoduodenectomy and Distal Pancreatectomy
Background/Objectives: Accurate volumetry of the remnant pancreas after pancreatectomy is crucial for assessing postoperative endocrine and exocrine function but remains challenging due to anatomical variability and complex postoperative morphology. This study aimed to develop and validate a deep learning (DL)-based model for automatic segmentation and volumetry of the remnant pancreas using abdominal CT images. Methods: A total of 1067 CT scans from 341 patients who underwent pancreaticoduodenectomy and 512 scans from 184 patients who underwent distal pancreatectomy were analyzed. Ground truth masks were manually delineated and verified through multi-expert consensus. Six 3D segmentation models were trained and compared, including four convolution-based U-Net variants (basic, dense, residual, and residual dense) and two transformer-based models (Trans U-Net and Swin U-Net). Model performance was evaluated using five-fold cross-validation with sensitivity, specificity, precision, accuracy, and Dice similarity coefficient. Results: The Residual Dense U-Net achieved the best performance among convolutional models, with dice similarity coefficient (DSC) values of 0.7655 ± 0.0052 for pancreaticoduodenectomy and 0.8086 ± 0.0091 for distal pancreatectomy. Transformer-based models showed slightly higher DSCs (Swin U-Net: 0.7787 ± 0.0062 and 0.8132 ± 0.0101), with statistically significant but numerically small improvements (p < 0.01). Conclusions: The proposed DL-based approach enables accurate and reproducible postoperative pancreas segmentation and volumetry. Automated volumetric assessment may support objective evaluation of remnant pancreatic function and provide a foundation for predictive modeling in long-term clinical management after pancreatectomy.
- Open Access
- 30 October 2025
- Published by Bentham Science Publishers Ltd. in Current Medical Imaging
- Vol. 21, 1-9
Artificial Intelligence-based Liver Volume Measurement using Preoperative and Postoperative CT Images
Introduction: Accurate liver volumetry is crucial for hepatectomy. In this study, we developed and validated a deep learning system for automated liver volumetry in patients undergoing hepatectomy, both preoperatively and at 7 days and 3 months postoperatively. Methods: A 3D U-Net model was trained on CT images from three time points using a five-fold cross-validation approach. Model performance was assessed with standard metrics and comparatively evaluated across the time points. Results: The model achieved a mean Dice Similarity Coefficient (DSC) of 94.31% (preoperative: 94.91%; 7-day post-operative: 93.45%; 3-month postoperative: 94.57%) and a mean recall of 96.04%. The volumetric difference between predicted and actual volumes was 1.01 ± 0.06% preoperatively, compared to 1.04 ± 0.03% at other time points (p < 0.05). Discussion: This study demonstrates a novel capability to automatically track post-hepatectomy regeneration using AI, offering significant potential to enhance surgical planning and patient monitoring. A key limitation, however, was that the direct correlation with clinical outcomes was not assessed due to constraints of the current dataset. Therefore, future studies using larger, multi-center datasets are essential to validate the model's clinical and prognostic utility. Conclusion: The developed artificial intelligence model successfully and accurately measured liver volumes across three critical post-hepatectomy time points. These findings support the use of this automated technology as a precise and reliable tool to assist in surgical decision-making and postoperative assessment, providing a strong foundation for enhancing patient care.
- 30 October 2025
- Published by Bentham Science Publishers Ltd. in Current Medical Imaging
- Vol. 21, 1-9
Open AccessArtificial Intelligence-based Liver Volume Measurement using Preoperative and Postoperative CT Images
Introduction: Accurate liver volumetry is crucial for hepatectomy. In this study, we developed and validated a deep learning system for automated liver volumetry in patients undergoing hepatectomy, both preoperatively and at 7 days and 3 months postoperatively. Methods: A 3D U-Net model was trained on CT images from three time points using a five-fold cross-validation approach. Model performance was assessed with standard metrics and comparatively evaluated across the time points. Results: The model achieved a mean Dice Similarity Coefficient (DSC) of 94.31% (preoperative: 94.91%; 7-day post-operative: 93.45%; 3-month postoperative: 94.57%) and a mean recall of 96.04%. The volumetric difference between predicted and actual volumes was 1.01 ± 0.06% preoperatively, compared to 1.04 ± 0.03% at other time points (p < 0.05). Discussion: This study demonstrates a novel capability to automatically track post-hepatectomy regeneration using AI, offering significant potential to enhance surgical planning and patient monitoring. A key limitation, however, was that the direct correlation with clinical outcomes was not assessed due to constraints of the current dataset. Therefore, future studies using larger, multi-center datasets are essential to validate the model's clinical and prognostic utility. Conclusion: The developed artificial intelligence model successfully and accurately measured liver volumes across three critical post-hepatectomy time points. These findings support the use of this automated technology as a precise and reliable tool to assist in surgical decision-making and postoperative assessment, providing a strong foundation for enhancing patient care.
- Open Access
- 31 March 2025
- Published by The Korean Society of Traumatology in Journal of Trauma and Injury
- Vol. 38  (1) , 14-21
Changes in the clinical features and demographics of donors after brain death, before and after the establishment of a regional trauma center: 20 years of experience at a single center in Korea
Purpose: Organ transplantation is considered the definitive treatment for end-stage organ disease. However, the scarcity of donor organs compared to the number of patients awaiting transplants is a major barrier. This study aimed to assess the impact of a regional trauma center on organ procurement and to provide a basis for future collaboration between regional trauma centers and transplant centers.Methods: This retrospective study analyzed organ donors after brain death over a 20-year period from January 1, 2003, to December 31, 2022. It compared patients before and after the establishment of the regional trauma center, as well as trauma and nontrauma patients. The study investigated general patient characteristics and the number and types of donated organs.Results: The average age of patients significantly increased from 37.75 years before the trauma center was established to 46.72 years after (t=–4.32, P<0.001). The organ acquisition rate significantly increased from 3.03 before to 3.47 after (t=–2.96, P=0.003). Suicide (t=6.52, P=0.011) and cardiopulmonary resuscitation cases were more common among nontrauma patients than among trauma patients (t=8.34, P=0.004). However, the organ acquisition rate was significantly higher among trauma patients than among nontrauma patients (3.53 vs. 3.21; t=2.04, P=0.004).Conclusions: This study identified changes in the characteristics and donor organs of patients diagnosed with brain death after the establishment of a regional trauma center. Given the increase in the proportion of trauma patients and the rate of organ acquisition per capita post-establishment, efforts should be made to encourage organ donation from patients diagnosed with brain death through close collaboration between regional trauma centers and organ transplant centers.
- 31 March 2025
- Published by The Korean Society of Traumatology in Journal of Trauma and Injury
- Vol. 38  (1) , 14-21
Open AccessChanges in the clinical features and demographics of donors after brain death, before and after the establishment of a regional trauma center: 20 years of experience at a single center in Korea
Purpose: Organ transplantation is considered the definitive treatment for end-stage organ disease. However, the scarcity of donor organs compared to the number of patients awaiting transplants is a major barrier. This study aimed to assess the impact of a regional trauma center on organ procurement and to provide a basis for future collaboration between regional trauma centers and transplant centers.Methods: This retrospective study analyzed organ donors after brain death over a 20-year period from January 1, 2003, to December 31, 2022. It compared patients before and after the establishment of the regional trauma center, as well as trauma and nontrauma patients. The study investigated general patient characteristics and the number and types of donated organs.Results: The average age of patients significantly increased from 37.75 years before the trauma center was established to 46.72 years after (t=–4.32, P<0.001). The organ acquisition rate significantly increased from 3.03 before to 3.47 after (t=–2.96, P=0.003). Suicide (t=6.52, P=0.011) and cardiopulmonary resuscitation cases were more common among nontrauma patients than among trauma patients (t=8.34, P=0.004). However, the organ acquisition rate was significantly higher among trauma patients than among nontrauma patients (3.53 vs. 3.21; t=2.04, P=0.004).Conclusions: This study identified changes in the characteristics and donor organs of patients diagnosed with brain death after the establishment of a regional trauma center. Given the increase in the proportion of trauma patients and the rate of organ acquisition per capita post-establishment, efforts should be made to encourage organ donation from patients diagnosed with brain death through close collaboration between regional trauma centers and organ transplant centers.
- Open Access
- 9 May 2024
- Published by The Korean Association of Hepato-Biliary-Pancreatic Surgery in Annals of Hepato-Biliary-Pancreatic Surgery
- Vol. 28  (2) , 134-143
Surgical outcome and risk scoring to predict survival after hepatic resection for hepatocellular carcinoma with portal vein tumor thrombosis
Tae-Seok Kim, Kwangho Yang, Gi Hong Choi, Hye Yeon Yang, Dong-Sik Kim, Hye-Sung Jo, Gyu-Seong Choi, Kwan Woo Kim, Young Chul Yoon, Jaryung Han, Doo Jin Kim, Shin Hwang, Koo Jeong Kang. Ann Hepatobiliary Pancreat Surg 2024;28:134-43. https://doi.org/10.14701/ahbps.24-048
- 9 May 2024
- Published by The Korean Association of Hepato-Biliary-Pancreatic Surgery in Annals of Hepato-Biliary-Pancreatic Surgery
- Vol. 28  (2) , 134-143
Open AccessSurgical outcome and risk scoring to predict survival after hepatic resection for hepatocellular carcinoma with portal vein tumor thrombosis
Tae-Seok Kim, Kwangho Yang, Gi Hong Choi, Hye Yeon Yang, Dong-Sik Kim, Hye-Sung Jo, Gyu-Seong Choi, Kwan Woo Kim, Young Chul Yoon, Jaryung Han, Doo Jin Kim, Shin Hwang, Koo Jeong Kang. Ann Hepatobiliary Pancreat Surg 2024;28:134-43. https://doi.org/10.14701/ahbps.24-048
- Open Access
- 23 April 2024
- Published by The Korean Association of Hepato-Biliary-Pancreatic Surgery in Annals of Hepato-Biliary-Pancreatic Surgery
- Vol. 28  (3) , 364-370
Pancreatic volume and endocrine function changes following pancreaticoduodenectomy for peri-ampullary neoplasms: A retrospective single-center study utilizing pancreas volumetry
Jaehun Yang, Yeon Ho Park, Doojin Kim, Doo-Ho Lee. Ann Hepatobiliary Pancreat Surg 2024;28:364-70. https://doi.org/10.14701/ahbps.24-004
- 23 April 2024
- Published by The Korean Association of Hepato-Biliary-Pancreatic Surgery in Annals of Hepato-Biliary-Pancreatic Surgery
- Vol. 28  (3) , 364-370
Open AccessPancreatic volume and endocrine function changes following pancreaticoduodenectomy for peri-ampullary neoplasms: A retrospective single-center study utilizing pancreas volumetry
Jaehun Yang, Yeon Ho Park, Doojin Kim, Doo-Ho Lee. Ann Hepatobiliary Pancreat Surg 2024;28:364-70. https://doi.org/10.14701/ahbps.24-004
- Open Access
- 8 June 2023
- Published by The Korean Association of Hepato-Biliary-Pancreatic Surgery in Annals of Hepato-Biliary-Pancreatic Surgery
- Vol. 27  (1) , S322
The impact of the multiple bile ducts on postoperative biliary complications in patient underwent living donor liver transplantation
Doo-Ho LEE, Doojin KIM*, Yeon Ho PARK. Ann Hepatobiliary Pancreat Surg 2023;27:S322. https://doi.org/10.14701/ahbps.2023S1.EP-55
- 8 June 2023
- Published by The Korean Association of Hepato-Biliary-Pancreatic Surgery in Annals of Hepato-Biliary-Pancreatic Surgery
- Vol. 27  (1) , S322
Open AccessThe impact of the multiple bile ducts on postoperative biliary complications in patient underwent living donor liver transplantation
Doo-Ho LEE, Doojin KIM*, Yeon Ho PARK. Ann Hepatobiliary Pancreat Surg 2023;27:S322. https://doi.org/10.14701/ahbps.2023S1.EP-55
- Open Access
- 1 May 2022
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 23  (9) , 5035
Plasma Aldo-Keto Reductase Family 1 Member B10 as a Biomarker Performs Well in the Diagnosis of Nonalcoholic Steatohepatitis and Fibrosis
We found several blood biomarkers through computational secretome analyses, including aldo-keto reductase family 1 member B10 (AKR1B10), which reflected the progression of nonalcoholic fatty liver disease (NAFLD). After confirming that hepatic AKR1B10 reflected the progression of NAFLD in a subgroup with NAFLD, we evaluated the diagnostic accuracy of plasma AKR1B10 and other biomarkers for the diagnosis of nonalcoholic steatohepatitis (NASH) and fibrosis in replication cohort. We enrolled healthy control subjects and patients with biopsy-proven NAFLD (n = 102) and evaluated the performance of various diagnostic markers. Plasma AKR1B10 performed well in the diagnosis of NASH with an area under the receiver operating characteristic (AUROC) curve of 0.834 and a cutoff value of 1078.2 pg/mL, as well as advanced fibrosis (AUROC curve value of 0.914 and cutoff level 1078.2 pg/mL), with further improvement in combination with C3. When we monitored a subgroup of obese patients who underwent bariatric surgery (n = 35), plasma AKR1B10 decreased dramatically, and 40.0% of patients with NASH at baseline showed a decrease in plasma AKR1B10 levels to below the cutoff level after the surgery. In an independent validation study, we proved that plasma AKR1B10 was a specific biomarker of NAFLD progression across varying degrees of renal dysfunction. Despite perfect correlation between plasma and serum levels of AKR1B10 in paired sample analysis, its serum level was 1.4-fold higher than that in plasma. Plasma AKR1B10 alone and in combination with C3 could be a useful noninvasive biomarker for the diagnosis of NASH and hepatic fibrosis.
- 1 May 2022
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 23  (9) , 5035
Open AccessPlasma Aldo-Keto Reductase Family 1 Member B10 as a Biomarker Performs Well in the Diagnosis of Nonalcoholic Steatohepatitis and Fibrosis
We found several blood biomarkers through computational secretome analyses, including aldo-keto reductase family 1 member B10 (AKR1B10), which reflected the progression of nonalcoholic fatty liver disease (NAFLD). After confirming that hepatic AKR1B10 reflected the progression of NAFLD in a subgroup with NAFLD, we evaluated the diagnostic accuracy of plasma AKR1B10 and other biomarkers for the diagnosis of nonalcoholic steatohepatitis (NASH) and fibrosis in replication cohort. We enrolled healthy control subjects and patients with biopsy-proven NAFLD (n = 102) and evaluated the performance of various diagnostic markers. Plasma AKR1B10 performed well in the diagnosis of NASH with an area under the receiver operating characteristic (AUROC) curve of 0.834 and a cutoff value of 1078.2 pg/mL, as well as advanced fibrosis (AUROC curve value of 0.914 and cutoff level 1078.2 pg/mL), with further improvement in combination with C3. When we monitored a subgroup of obese patients who underwent bariatric surgery (n = 35), plasma AKR1B10 decreased dramatically, and 40.0% of patients with NASH at baseline showed a decrease in plasma AKR1B10 levels to below the cutoff level after the surgery. In an independent validation study, we proved that plasma AKR1B10 was a specific biomarker of NAFLD progression across varying degrees of renal dysfunction. Despite perfect correlation between plasma and serum levels of AKR1B10 in paired sample analysis, its serum level was 1.4-fold higher than that in plasma. Plasma AKR1B10 alone and in combination with C3 could be a useful noninvasive biomarker for the diagnosis of NASH and hepatic fibrosis.
- Open Access
- 7 October 2021
- Published by The Korean Society for Transplantation in Korean Journal of Transplantation
- Vol. 35  (1) , S132
The impact of the multiple bile ducts on postoperative biliary complications in living donor liver transplantation: a single center experience
Doojin Kim, Doo-Hoo Lee, Sang-Tae Choi, Yeon Ho Park. Korean J Transplant 2021;35:132. https://doi.org/10.4285/ATW2021.PO-1279
- 7 October 2021
- Published by The Korean Society for Transplantation in Korean Journal of Transplantation
- Vol. 35  (1) , S132
Open AccessThe impact of the multiple bile ducts on postoperative biliary complications in living donor liver transplantation: a single center experience
Doojin Kim, Doo-Hoo Lee, Sang-Tae Choi, Yeon Ho Park. Korean J Transplant 2021;35:132. https://doi.org/10.4285/ATW2021.PO-1279
- Open Access
- 27 August 2021
- Published by Elsevier in Asian Journal of Surgery
- Vol. 44  (10) , 1289-1290
Portal inflow reconstruction between distal collateral vessels after renoportal anastomosis in a liver transplant patient with extensive portomesenteric venous thrombosis
- 27 August 2021
- Published by Elsevier in Asian Journal of Surgery
- Vol. 44  (10) , 1289-1290
Open AccessPortal inflow reconstruction between distal collateral vessels after renoportal anastomosis in a liver transplant patient with extensive portomesenteric venous thrombosis
- 26 March 2021
- Published by Springer Nature in Surgical Endoscopy
- Vol. 36  (2) , 1424-1432
Laparoscopic cholecystectomy in patients with previous upper midline abdominal surgery: comparison of laparoscopic cholecystectomy after gastric surgery and non-gastric surgery using propensity score matching
Background Previous upper midline abdominal surgery is a reported relative contraindication to laparoscopic cholecystectomy. We aimed to investigate the effects of previous upper abdominal surgery on the feasibility and safety of laparoscopic cholecystectomy; we evaluated the effects of the previous upper abdominal surgery type on laparoscopic cholecystectomy with respect to complications and conversion to open surgery. Methods We prospectively evaluated 1,258 patients who underwent laparoscopic cholecystectomy, including those who underwent upper midline abdominal surgery previously, at a single tertiary referral center. The perioperative and postoperative outcomes—open conversion rate, operation time, intraoperative and postoperative complications, and length of hospital stay—were evaluated. Patients were grouped according to the previous surgical method into the gastric (n = 77), non-gastric (n = 40), and control (n = 1141) groups. Patients in the gastric + non-gastric groups (n = 117) were 1:1 matched with those in the control group (n = 117) using propensity score matching (PSM). Results Before PSM, age, sex, open conversion rate, gallbladder status, port number, overall morbidity, and postoperative hospital stay duration did not significantly differ between the gastric and non-gastric groups; the body mass index (22.3 ± 3.4 versus 24.1 ± 3.8 kg/m2, p = 0.009) and operation time (129.9 ± 63.6 versus 97.9 ± 51.1 min, p = 0.004) significantly differed. After PSM, age, sex, body mass index, and American Society of Anesthesiology score did not significantly differ between gastric + non-gastric (n = 117) and conventional groups (n = 117; the operation time (118.9 ± 61.3 versus 75.8 ± 37.1 min, p < 0.001), open conversion rate (n = 6, 5.1% versus n = 0, 0.0%, p = 0.013), port number, overall morbidities (n = 26, 22.2% versus n = 10, 8.5%, p = 0.004), and postoperative hospital stay duration (6.7 ± 4.3 versus 5.5 ± 3.2 days, p = 0.031) significantly differed. Conclusion Previous upper midline abdominal surgery was not contraindicative to safe laparoscopic cholecystectomy. Patients with previous upper midline abdominal surgery undergoing laparoscopic cholecystectomy should be informed preoperatively of the probability of conversion to open surgery, lengthened duration, and associated morbidities.
- 26 March 2021
- Published by Springer Nature in Surgical Endoscopy
- Vol. 36  (2) , 1424-1432
Laparoscopic cholecystectomy in patients with previous upper midline abdominal surgery: comparison of laparoscopic cholecystectomy after gastric surgery and non-gastric surgery using propensity score matching
Background Previous upper midline abdominal surgery is a reported relative contraindication to laparoscopic cholecystectomy. We aimed to investigate the effects of previous upper abdominal surgery on the feasibility and safety of laparoscopic cholecystectomy; we evaluated the effects of the previous upper abdominal surgery type on laparoscopic cholecystectomy with respect to complications and conversion to open surgery. Methods We prospectively evaluated 1,258 patients who underwent laparoscopic cholecystectomy, including those who underwent upper midline abdominal surgery previously, at a single tertiary referral center. The perioperative and postoperative outcomes—open conversion rate, operation time, intraoperative and postoperative complications, and length of hospital stay—were evaluated. Patients were grouped according to the previous surgical method into the gastric (n = 77), non-gastric (n = 40), and control (n = 1141) groups. Patients in the gastric + non-gastric groups (n = 117) were 1:1 matched with those in the control group (n = 117) using propensity score matching (PSM). Results Before PSM, age, sex, open conversion rate, gallbladder status, port number, overall morbidity, and postoperative hospital stay duration did not significantly differ between the gastric and non-gastric groups; the body mass index (22.3 ± 3.4 versus 24.1 ± 3.8 kg/m2, p = 0.009) and operation time (129.9 ± 63.6 versus 97.9 ± 51.1 min, p = 0.004) significantly differed. After PSM, age, sex, body mass index, and American Society of Anesthesiology score did not significantly differ between gastric + non-gastric (n = 117) and conventional groups (n = 117; the operation time (118.9 ± 61.3 versus 75.8 ± 37.1 min, p < 0.001), open conversion rate (n = 6, 5.1% versus n = 0, 0.0%, p = 0.013), port number, overall morbidities (n = 26, 22.2% versus n = 10, 8.5%, p = 0.004), and postoperative hospital stay duration (6.7 ± 4.3 versus 5.5 ± 3.2 days, p = 0.031) significantly differed. Conclusion Previous upper midline abdominal surgery was not contraindicative to safe laparoscopic cholecystectomy. Patients with previous upper midline abdominal surgery undergoing laparoscopic cholecystectomy should be informed preoperatively of the probability of conversion to open surgery, lengthened duration, and associated morbidities.