박창민 교수
Chang Min Park
서울대학교 · 의학
연구실 소개
박창민 교수의 연구실은 의료 영상 분석 분야에서 인공지능 기반 진단 보조 시스템 개발에 주력하고 있습니다. 특히 흉부 X선 및 CT 영상에서 폐암, 결핵, 기도 종양 등의 질환을 정밀하게 탐지하는 딥러닝 기반 알고리즘의 성능 향상에 초점을 맞추고 있으며, 임상 현장에서의 적용 가능성을 높이기 위해 정확성과 일관성을 확보하는 데 중점을 두고 있습니다. 또한 영상 유전자(라이믹스) 분석을 통해 영상 소견과 생물학적 특성 간의 연관성을 규명하는 연구도 진행 중입니다.
연구 현황
연구 성과 추이
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
주요 논문
15The algorithm consistently outperformed physicians, including thoracic radiologists, in the discrimination of chest radiographs with major thoracic diseases, demonstrating its potential to improve the quality and efficiency of clinical practice.
The popularization of computed tomography (CT) in clinical practice and the introduction of mass screening for early lung cancer with the use of CT have increased the frequency of findings of subtle nodules or nodular ground-glass opacity. Nodular ground-glass opacity may be observed in malignancies such as bronchioloalveolar carcinoma and adenocarcinoma, as well as in their putative precursors, such as atypical adenomatous hyperplasia. Nodular ground-glass opacity also may be seen in the presen
Our DLAD demonstrated excellent and consistent performance in the detection of active pulmonary tuberculosis on CR, outperforming physicians, including thoracic radiologists.
The incidence of hemodynamically significant celiac axis stenosis in this asymptomatic Korean population was 7.3% and the most important etiology was extrinsic compression by the median arcuate ligament of the diaphragm. Atherosclerosis was only a minor cause of the condition.
A variety of tumors, including primary malignant tumors, secondary malignant tumors, and benign tumors, can occur in the tracheobronchial tree. Primary malignant tumors commonly originate from the surface epithelium or the salivary glands, whereas most benign tumors arise from the mesenchymal tissue. At computed tomography (CT), primary malignant tumors manifest as a polypoid lesion, a focal sessile lesion, eccentric narrowing of the airway lumen, or circumferential wall thickening. At fluorine
Most of the radiomic features were significantly affected by the reconstruction algorithms. Inter-reconstruction algorithm variability was greater than inter-reader variability for entropy, homogeneity, and GLCM-based features.
Computed tomography texture features have the potential to be used as prognostic biomarkers in unresectable NSCLC patients undergoing definitive CCRT.
In 2011, the International Association for the Study of Lung Cancer, American Thoracic Society, and European Respiratory Society proposed a new classification for lung adenocarcinoma that included a number of changes to previous classifications. This classification now considers resection specimens, small biopsies, and cytology specimens. Two former histopathologic terms, bronchioloalveolar carcinoma and mixed subtype adenocarcinoma, are no longer to be used. For resection specimens, the new ter
Computed tomography texture features such as higher entropy and lower homogeneity were significant differentiating factors of IPAs presenting as PGGNs larger than 5 mm and have potentials to enhance the differentiating performance.
Atypical adenomatous hyperplasia is often associated with malignancy. This tumor is shown on CT as persistent well-defined oval or round nodular GGOs without solid components, and it does not change on the follow-up CT.
Variations in volume and attenuation measurements of persistent pure ground-glass nodules using commercial software were reasonably small, allowing the detection of clinically relevant growth.
Texture analysis of PSNs in addition to clinical and CT features analysis has the potential to improve the differentiation of transient from persistent PSNs.
대표 연구 분야
박창민 교수의 연구를 Nubint에서 더 깊이 살펴보세요
이 연구실의 논문을 앱에서 열어 AI와 함께 읽고, 핵심을 요약하고, 내 글에 인용하세요.