A5069469573- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Bladder and Urothelial Cancer Treatments
- Cancer Immunotherapy and Biomarkers
- Colorectal Cancer Screening and Detection
- Cancer Genomics and Diagnostics
- Ovarian cancer diagnosis and treatment
- Metastasis and carcinoma case studies
- Pancreatic and Hepatic Oncology Research
- Gastric Cancer Management and Outcomes
- Cancer-related molecular mechanisms research
- Lymphoma Diagnosis and Treatment
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Viral-associated cancers and disorders
- Genetic factors in colorectal cancer
- Cervical Cancer and HPV Research
- Gastrointestinal disorders and treatments
- Colorectal Cancer Surgical Treatments
- Breast Lesions and Carcinomas
- Soft tissue tumor case studies
- Urinary and Genital Oncology Studies
- Colorectal and Anal Carcinomas
- Vascular Tumors and Angiosarcomas
- MicroRNA in disease regulation
- Neuroendocrine Tumor Research Advances
Catholic University of Korea
2012-2025
Uijeongbu St. Mary's Hospital
2017-2025
Stanford Blood Center
2024
Seoul St. Mary's Hospital
2011-2022
Artificial intelligence (AI) is increasingly being applied in pathology and cytology, showing promising results. We collected a large dataset of whole slide images (WSIs) thyroid fine-needle aspiration cytology (FNA), incorporating z-stacking, from institutions across the nation to develop an AI model.
Objective: To determine the diagnostic performance of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and DCE ultrasound (DCE-US) for predicting response to neoadjuvant chemotherapy (NAC) in breast cancer patients.Materials Methods: This Institutional Review Board-approved prospective study was performed between 2014 2016.Thirty-nine women with underwent DCE-US DCE-MRI before NAC, follow-up after first cycle second NAC.DCE-MRI parameters (transfer constant [Ktrans], reverse...
A Pleural effusion cytology is vital for treating metastatic breast cancer; however, concerns have arisen regarding the low accuracy and inter-observer variability in cytologic diagnosis. Although artificial intelligence-based image analysis has shown promise cytopathology research, its application diagnosing cancer pleural fluid remains unexplored. To overcome these limitations, we evaluate diagnostic of an model using a large collection cytopathological slides, to detect malignant...
The prognosis of patients with lung adenocarcinoma (LUAD), especially early-stage LUAD, is dependent on clinicopathological features. However, its predictive utility limited. In this study, we developed and trained a DeepRePath model based deep convolutional neural network (CNN) using multi-scale pathology images to predict the LUAD. was pre-trained 1067 hematoxylin eosin-stained whole-slide LUAD from Cancer Genome Atlas. further validated two separate CNNs 393 resected cancer specimens...
AIMTo evaluate a novel grading system to predict lymph node metastasis (LNM) in patients with submucosal invasive colorectal carcinoma (SICRC). METHODSWe analyzed the associations between LNM and various clinicopathological features 252 SICRC who had undergone radical surgery at Seoul Saint Mary's hospital 2000 2015. RESULTSLNM was observed 31 (12.3%).The depth width of invasion, lymphatic tumor budding, presence poorly differentiated clusters (PDCs) were significantly 5936August 28,...
Ascites cytology is a cost-effective test for metastatic colorectal cancer (CRC) in the abdominal cavity. However, carcinoma of peritoneum difficult to diagnose based on biopsy findings, and ascitic aspiration has low sensitivity specificity high inter-observer variability. The aim present study was apply artificial intelligence (AI) classify benign malignant cells ascites patch images CRC using deep convolutional neural network. Datasets were collected from OPEN AI Dataset Project,...
Inflammatory myofibroblastic tumor (IMT) is an uncommon mesenchymal solid commonly documented in children and young adults. Here, we report a case of IMT colon confirmed pathologically after laparoscopic anterior resection. A 35-year-old man presented with anal bleeding defecation for 2 weeks. Colonoscopy demonstrated mass shallow ulceration the central area irregular margin accompanied by intact mucosa descending colon. Computer tomography showed well-demarcated homogenous solitary We...
CD8+ tumor-infiltrating lymphocytes (TILs) play a major role in antitumor immunity. High endothelial venules (HEVs) are related to diverse immune cells solid tumors. We analyzed and Foxp3+ TILs combination with HEVs determine their prognostic advanced gastric cancer (AGC). enrolled 157 patients AGC this study. The densities of were calculated using immunohistochemical staining. evaluated by MECA-79 expression. identified 60 (38.2%) cases was significantly associated an increased number (p =...
The tumor-associated neutrophils (TANs) value and tumor—stroma ratio (TSR) are promising prognostic parameters in the tumor microenvironment. We aimed to evaluate role relationship of TANs TSR gastric cancer. Our study comprised 157 patients who underwent gastrectomy for advanced were assessed by immunohistochemical staining (CD15 CD66b) analyzed with an image analyzer. have been known different functional subpopulations N1 (anti-tumor) N2 (pro-tumor). developed “calculated pro-tumor...
Background: Cytological diagnosis of pleural effusion plays an important role in the early detection and lung cancers. Recently, attempts have been made to overcome low diagnostic accuracy interobserver variability using artificial intelligence-based image analysis. However, such analysis is primarily performed at image-patch level not whole-slide (WSI) level. This study aims develop a WSI-level classification malignant effusions metastatic cancer based on fluid cytology quality-controlled,...
Gastric lipomatosis is a rare condition in which multiple lipomas develop the stomach. We herein describe 52-year-old woman diagnosed with gastric without any symptoms. The patient was incidentally on endoscopy and computed tomography four years previously. Recent examination revealed that located prepyloric antrum had increased size extent. Distal gastrectomy Billroth-II reconstruction were performed pathologically confirmed diagnosis of lipomatosis. has not experienced recurrence two...
Abstract Introduction: Gastric cancer (GC) has high mortality and limited treatment options, with histomorphological features predicting outcomes response. Stricter criteria for undifferentiated GC in Japanese guidelines underscore its poor prognosis. This study developed a deep learning (DL) model to classify as differentiated or undifferentiated, reducing diagnostic variability. The revealed genetic differences aligned distinct from pathologist classifications, providing precise spatial...
Abstract Introduction: Advanced gastric cancer (GC) is one of the most challenging malignancies, with high mortality rates and a lack effective treatment strategies. Histomorphological features, termed ‘morphologic phenotypes’, predict therapeutic response, lymphoepithelial carcinoma showing immunotherapy responsiveness while diffuse-type GC exhibits resistance to targeted therapies such as HER2 CLDN18 inhibitors. Despite these associations, comprehensive molecular understanding based on...