Search

Your search keyword '"O, Joo Hyun"' showing total 257 results
Start Over Author "O, Joo Hyun"
257 results on '"O, Joo Hyun"'

3. Semi-supervised learning towards automated segmentation of PET images with limited annotations: Application to lymphoma patients

Author

Yousefirizi, Fereshteh, Shiri, Isaac, O, Joo Hyun, Bloise, Ingrid, Martineau, Patrick, Wilson, Don, Bénard, François, Sehn, Laurie H., Savage, Kerry J., Zaidi, Habib, Uribe, Carlos F., and Rahmim, Arman

Subjects
Physics - Medical Physics, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

The time-consuming task of manual segmentation challenges routine systematic quantification of disease burden. Convolutional neural networks (CNNs) hold significant promise to reliably identify locations and boundaries of tumors from PET scans. We aimed to leverage the need for annotated data via semi-supervised approaches, with application to PET images of diffuse large B-cell lymphoma (DLBCL) and primary mediastinal large B-cell lymphoma (PMBCL). We analyzed 18F-FDG PET images of 292 patients with PMBCL (n=104) and DLBCL (n=188) (n=232 for training and validation, and n=60 for external testing). We employed FCM and MS losses for training a 3D U-Net with different levels of supervision: i) fully supervised methods with labeled FCM (LFCM) as well as Unified focal and Dice loss functions, ii) unsupervised methods with Robust FCM (RFCM) and Mumford-Shah (MS) loss functions, and iii) Semi-supervised methods based on FCM (RFCM+LFCM), as well as MS loss in combination with supervised Dice loss (MS+Dice). Unified loss function yielded higher Dice score (mean +/- standard deviation (SD)) (0.73 +/- 0.03; 95% CI, 0.67-0.8) compared to Dice loss (p-value<0.01). Semi-supervised (RFCM+alpha*LFCM) with alpha=0.3 showed the best performance, with a Dice score of 0.69 +/- 0.03 (95% CI, 0.45-0.77) outperforming (MS+alpha*Dice) for any supervision level (any alpha) (p<0.01). The best performer among (MS+alpha*Dice) semi-supervised approaches with alpha=0.2 showed a Dice score of 0.60 +/- 0.08 (95% CI, 0.44-0.76) compared to another supervision level in this semi-supervised approach (p<0.01). Semi-supervised learning via FCM loss (RFCM+alpha*LFCM) showed improved performance compared to supervised approaches. Considering the time-consuming nature of expert manual delineations and intra-observer variabilities, semi-supervised approaches have significant potential for automated segmentation workflows.

Published
2022

4. Convolutional neural network with a hybrid loss function for fully automated segmentation of lymphoma lesions in FDG PET images

Author

Yousefirizi, Fereshteh, Dubljevic, Natalia, Ahamed, Shadab, Bloise, Ingrid, Gowdy, Claire, O, Joo Hyun, Farag, Youssef, de Schaetzen, Rodrigue, Martineau, Patrick, Wilson, Don, Uribe, Carlos F., and Rahmim, Arman

Subjects
Physics - Medical Physics
Abstract

Segmentation of lymphoma lesions is challenging due to their varied sizes and locations in whole-body PET scans. This work presents a fully-automated segmentation technique using a multi-center dataset of diffuse large B-cell lymphoma (DLBCL) with heterogeneous characteristics. We utilized a dataset of [18F]FDG-PET scans (n=194) from two different imaging centers, including cases with primary mediastinal large B-cell lymphoma (PMBCL) (n=104). Automated brain and bladder removal approaches were utilized as preprocessing steps to tackle false positives caused by normal hypermetabolic uptake in these organs. Our segmentation model is a convolutional neural network (CNN) based on a 3D U-Net architecture that includes squeeze and excitation (SE) modules. Hybrid distribution, region, and boundary-based losses (Unified Focal and Mumford-Shah (MS)) were utilized that showed the best performance compared to other combinations (p<0.05). Cross-validation between different centers, DLBCL and PMBCL cases, and three random splits were applied on train/validation data. The ensemble of these six models achieved a Dice similarity coefficient (DSC) of 0.77 +- 0.08 and Hausdorff distance (HD) of 16.5 +-12.5. Our 3D U-net model with SE modules for segmentation with hybrid loss performed significantly better (p<0.05) as compared to the 3D U-Net (without SE modules) using the same loss function (Unified Focal and MS loss) (DSC= 0.64 +-0.21 and HD= 26.3 +- 18.7). Our model can facilitate a fully automated quantification pipeline in a multi-center context that opens the possibility for routine reporting of total metabolic tumor volume (TMTV) and other metrics shown useful for the management of lymphoma.

Published
2022

5. Nuclear Imaging of the Thyroid Gland

Author

O, Joo Hyun, Ha, Seunggyun, Kakudo, Kennichi, editor, Liu, Zhiyan, editor, Jung, Chan Kwon, editor, Hirokawa, Mitsuyoshi, editor, Bychkov, Andrey, editor, and Lai, Chiung-Ru, editor

Published
2023
Full Text
View/download PDF

13. Long-Term Clinical Outcomes of Optimizing Combination Therapy for Primary Pulmonary Mucosa-Associated Lymphoid Tissue Lymphoma: A Retrospective Study.

Author

Min, Gi-June, Rhee, Chin Kook, Kim, Tong Yoon, Jeon, Young-Woo, O, Joo Hyun, Choi, Byung-Ock, Park, Gyeongsin, and Cho, Seok-Goo

Subjects
MUCOSA-associated lymphoid tissue lymphoma, CANCER chemotherapy, OVERALL survival, PROGRESSION-free survival, LUNG cancer
Abstract

Introduction: Pulmonary mucosa-associated lymphoid tissue (MALT) lymphoma progresses with advancing disease stage. However, no standard treatment approach has been established. This single-center retrospective study evaluated clinical and radiological characteristics, treatment modalities, and long-term prognosis of pulmonary MALT lymphoma. Methods: The study included 42 patients diagnosed with pulmonary MALT lymphoma between October 2004 and July 2019. Primary therapeutic modalities were determined using modified Ann Arbor staging. Therapeutic response was evaluated via computed tomography and laboratory analyses every 6 months for 5 years. Radiological findings were categorized based on the Lugano classification as complete response (CR), partial response, stable disease (SD), or progressive disease. Results: Initial treatment included observation (n = 2), surgical resection (n = 6), or systemic chemotherapy (n = 34). Patients treated surgically had localized disease and achieved initial and long-term CR. Of the 34 patients who underwent chemotherapy, 30 achieved CR, 2 achieved SD, and 2 died. Overall and progression-free survival (PFS) rates were 93.9% and 54.3%, respectively. Multivariate analysis indicated that PFS was lower in patients with modified Ann Arbor stage III-IV lymphoma and those who did not achieve CR. Conclusions: Optimized treatment based on anatomical location, pulmonary function, and disease stage can improve long-term survival in patients with pulmonary MALT lymphoma. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

27. A Single Dose of Novel PSMA-Targeting Radiopharmaceutical Agent [177Lu]Ludotadipep for Patients with Metastatic Castration-Resistant Prostate Cancer: Phase I Clinical Trial

Author

Shin, Dongho, primary, Ha, Seunggyun, additional, O, Joo Hyun, additional, Rhew, Seung ah, additional, Yoon, Chang Eil, additional, Kwon, Hyeok Jae, additional, Moon, Hyong Woo, additional, Park, Yong Hyun, additional, Park, Sonya Youngju, additional, Park, Chansoo, additional, Chi, Dae Yoon, additional, Yoo, Ie Ryung, additional, and Lee, Ji Youl, additional

Published
2022
Full Text
View/download PDF

34. Comparison of FDG PET/CT and Bone Marrow Biopsy Results in Patients with Diffuse Large B Cell Lymphoma with Subgroup Analysis of PET Radiomics

Author

Han, Eun Ji, primary, O, Joo Hyun, additional, Yoon, Hyukjin, additional, Ha, Seunggyun, additional, Yoo, Ie Ryung, additional, Min, Jae Won, additional, Choi, Joon-Il, additional, Choi, Byung-Ock, additional, Park, Gyeongsin, additional, Lee, Han Hee, additional, Jeon, Young-Woo, additional, Min, Gi-June, additional, and Cho, Seok-Goo, additional

Published
2022
Full Text
View/download PDF

35. Bone Scan in Gastric Cancer Patients: A Retrospective Review

Author

Bandar Ali, O. Joo Hyun, and Khuloud Omar Bukhari

Subjects
medicine.medical_specialty, medicine.diagnostic_test, biology, Anemia, business.industry, Bone metastasis, Cancer, medicine.disease, medicine.anatomical_structure, Carcinoembryonic antigen, Bone scintigraphy, medicine, biology.protein, Radiology, medicine.symptom, Bone pain, Stomach cancer, business, Lymph node
Abstract

Background: Bone scan has a very highly sensitive role in detection bone metastases. Bone metastasis from stomach cancer occurs only rarely and it is known to have a very poor prognosis. Bone metastases in Gastric cancer are mainly osteolytic, and disruption of bone integrity and resulting in bone pain and pathological fracture. In this study, we aimed to review the incidence, clinical characteristics, and related risk factors for bone metastases in patients with a primarily diagnosis of gastric cancer. Methods: We retrospectively evaluated all patients who diagnosed with primary gastric cancer and underwent initially as staging working up with bone scintigraphy between 2010 and 2014 at Seoul St. Mary’s hospital, The Catholic University of Korea. Total numbers of primary diagnosis of gastric cancer patients were 1589/1721 (92.33%) patients received bone scan as initial staging work up. We further analyzed the patients according to eligibility criteria we created and the incidence of and the risk factors for bone metastases were investigated. Results: Out of 1589 patients analyzed, bone metastases were clearly confirmed only in 15 patients (0.8%). The mean age was 59.0 ± 8.6 years (range 24–90) and a majority of patients were male (60%). Dominant histological type either poorly differentiated type or signet ring cancer type and Bormann’s classification type 3 was the majority. In the distribution of the gastric tumor in correlation to the upper, middle and lower third was not clinically variant. The mean tumor size among this group was 3.6 ± 2.3 cm (range 0.6–20 cm). All patients were advanced gastric cancer type clinically and the median follow-up period was 9 months. The incidence of bone metastases was (20%). In (80%) of patients had bone metastases and another site of metastases. Among these, most of the time associated regional lymph node metastases was found. Most patients had multiple bone metastases instead of a single bone lesion. The whole patients of bone metastases were advanced gastric cancers, and the most common metastatic site was the whole skeleton, followed by combined vertebra, rib and scapula. Bone scintigraphy and PET-CT were mostly used together for diagnosing bone metastasis. The serum alkaline phosphatase at the time of diagnosis had increased in only 5 cases (35.71%) and there were clinical symptoms of bone pain in 8 cases (53.0%). Other variables also were not significantly valued like anemia, tumor markers like carcinoembryonic antigen (CEA) and cancer antigen 19-9 (CA19-9).Treatment was given to 14 cases (93.3%) and it was mostly chemo or concomitant chemoradiotherapy. Conclusions: The preoperative bone scan was positive in 0.8% for bone metastasis in patients with gastric cancer. Suggesting that whole-body bone scan should not be performed routinely in patients with gastric cancer. For bone scan to be as cost-effective tool, may be needed for selected group of patients i.e. advanced stages of gastric cancer or clinically symptomatic patients. Serum ALK has poor correlation with early bone metastasis detection.

Published
2021

37. A Single Dose of Novel PSMA-Targeting Radiopharmaceutical Agent [ 177 Lu]Ludotadipep for Patients with Metastatic Castration-Resistant Prostate Cancer: Phase I Clinical Trial.

Author

Shin, Dongho, Ha, Seunggyun, O, Joo Hyun, Rhew, Seung ah, Yoon, Chang Eil, Kwon, Hyeok Jae, Moon, Hyong Woo, Park, Yong Hyun, Park, Sonya Youngju, Park, Chansoo, Chi, Dae Yoon, Yoo, Ie Ryung, and Lee, Ji Youl

Subjects
DISEASE progression, DRUG efficacy, CLINICAL trials, METASTASIS, TREATMENT effectiveness, RADIOPHARMACEUTICALS, INTRAVENOUS injections, MOLECULAR structure, PROSTATE-specific membrane antigen, EVALUATION
Abstract

Simple Summary: Prostate specific membrane antigen (PSMA) is a transmembrane protein that is highly expressed in prostate cancer cells. For patients with metastatic castration-resistant prostate cancer (mCRPC) who do not respond to conventional treatment, PSMA targeting radiopharmaceutical therapy (RPT) has recently been in the spotlight. [177Lu]Ludotadipep is a novel PSMA-targeting therapeutic agent designed with an albumin motif in order to increase the circulation time and uptake in the tumors. The safety and efficacy of [177Lu]Ludotadipep were evaluated through a phase I trial. [177Lu]Ludotadipep, which enables targeted delivery of beta-particle radiation to prostate tumor cells, had been suggested as a promising therapeutic option for mCRPC. From November 2020 to March 2022, a total of 30 patients were enrolled for single dose of [177Lu]Ludotadipep RPT, 6 subjects in each of the 5 different activity groups of 1.9 GBq, 2.8 GBq, 3.7 GBq, 4.6 GBq, and 5.6 GBq. [177Lu]Ludotadipep was administered via venous injection, and patients were hospitalized for three days to monitor for any adverse effects. Serum PSA levels were followed up at weeks 1, 2, 3, 4, 6, 8, and 12, and PSMA PET/CT with [18F]Florastamin was obtained at baseline and again at weeks 4 and 8. The subjects required positive PSMA PET/CT prior to [177Lu]Ludotadipep administration. Among the 29 subjects who received [177Lu]Ludotadipep, 36 treatment emergent adverse events (TEAEs) occurred in 17 subjects (58.6%) and 4 adverse drug reactions (ADRs) in 3 subjects (10.3%). Of the total 24 subjects who had full 12-week follow-up data, 16 (66.7%) showed decrease in PSA of any magnitude, and 9 (37.5%) showed a decrease in PSA by 50% or greater. A total of 5 of the 24 patients (20.8%) showed disease progression (PSA increase of 25% or higher from the baseline) at the 12th week following single dose of [177Lu]Ludotadipep. These data thus far suggest that [177Lu]Ludotadipep could be a promising RPT agent with low toxicity in mCRPC patients who have not been responsive to conventional treatments. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results