논문 리뷰46 Zhang et al., 2019, An investigation of CNN models for differentiating malignant from benign lesions using small pathologically proven datasets # 세줄 요약 # Cancer has been one of the most threatening diseases, so our major goal is to identify malignant from benign lesions at radiology or CT imaging in the early stages, But it is difficult to collect such a large volume of images with pathological information. This paper explores two CNN models by focusing extensively on the expansion of training samples from two small pathologically prove.. 2021. 9. 27. Medina et al., 2020. Deep learning method for segmentation of rotator cuff muscles on MR images # 세줄 요약 # To develop and validate a deep convolutional neural network (CNN) method capable of (1) selecting a specific shoulder sagittal MR image (Y-view) and (2) automatically segmenting rotator cuff (RC) muscles on a Y-view. For model A, we manually selected shoulder sagittal T1 Y-view from 258 cases as ground truth to train a classification, For model B, we manually segmented subscapularis, s.. 2021. 9. 19. Cohen & Blakeslee & Ryzhov, 1998, The Ages and Abundances of a Large Sample of M87 Globular Clusters # 세줄 요약 # Combining the new (20 GCs; this paper) and existing data (150 GCs; Cohen & Ryzhov, 1997) for the galactic GCs (Globular clusters) and comparing the (U-R) colors and the line indices gave qualitative indications for the ages and abundances of M87 GC system. We find that the M87 GCs span a wide range in metallicity, from very metal-poor to somewhat above solar metallicity. The behavior o.. 2021. 8. 28. Pota et al., 2015, A SLUGGS and Gemini/GMOS combined study of the elliptical galaxyM60: wide-field photometry and kinematics of the globular cluster system # 세줄 요약 # We present new wide-field photometry and spectroscopy of the globular clusters (GCs) around NGC 4649 (M60), the third brightest galaxy in the Virgo cluster. We confirm significant GC colour bimodality and find that the red GCs are more centrally concentrated, while the blue GCs are more spatially extended. We find that formation via a major merger between two gas-poor galaxies, followe.. 2021. 8. 23. Kim et al., 2020, Active learning for accuracy enhancement of semantic segmentation with CNN-corrected label curations: Evaluation on kidney segmentation in abdominal CT # 세줄 요약 # Recent advances in fully convolutional networks have enabled automatic segmentation, however, high labeling efforts and difficulty in acquiring sufficient and high-quality training data is still a challenge. In this study, a cascaded 3D U-Net with active learning to 3 stages: first, training small dataset with manual labeling ground truth, second, training previous dataset and newly ad.. 2021. 8. 16. Shim et al., 2020, Automated rotator cuff tear classification using 3D convolutional neural network # 세줄 요약 # Rotator cuff tear (RCT) is one of the most common shoulder injuries. When diagnosing RCT, skilled orthopedists visually interpret magnetic resonance imaging (MRI) scan data. MRI data from 2,124 patients were used to train and test the VRN-based 3D CNN to classify RCT into five classes (None, Partial, Small, Medium, Large-to-Massive). The VRN-based 3D CNN outperformed orthopedists speci.. 2021. 8. 8. Kanavati et al., 2021, A deep learning model for the classification of indeterminate lung carcinoma in biopsy whole slide images # 세줄 요약 # The differentiation between major histological types of lung cancer, such as adenocarcinoma (ADC), squamous cell carcinoma (SCC), and small-cell lung cancer (SCLS) is of crucial importance for determining optimum cancer treatment. Hematoxylin and Eosin (H&E)-stained slides of small transbronchial lung biopsy (TBLB) are one of the primary sources for making a diagnosis, but if this diag.. 2021. 7. 18. Lee & Park, 2019, Application of Artificial Intelligence in Lung Cancer Sreening # 세줄요약 # 저선량 CT를 이용한 폐암검진은 그 폐암 사망률 감소 효과가 입증되었기에, 효과적인 폐암검진을 위해서는 저선량 CT에 대한 정확한 판독이 필요하다. 인공지능 기술을 활용한 저선량 CT 판독 보조시스템 개발은 영상의학 전문가들의 판독에 대한 피로도를 줄일 수 있고, 딥러닝(deep learning) 기술의 적용으로 우수한 진단성능을 보이기에 학계 및 산업계에서 큰 관심을 보이고 있다. 폐암검진에서 딥러닝 기술(인공지능 기술)을 적용할 수 있는 분야는 컴퓨터 보조 병변 검출, 판독문 생성, 폐결절의 악성도 평가, 환자의 예후 예측 등이 있다. # 상세리뷰 # 1. 저선량 CT를 이용한 폐암검진은 그 폐암 사망률 감소 효과가 입증되었기에, 효과적인 폐암검진을 위해서는 저선량 CT에 대한 정확한.. 2021. 3. 15. [GoogLeNet] Szegedy et al., 2015, Going Deeper with Convolutions # 세줄요약 # 'Inception'이라고 불리는 새로운 모듈로 구성한 Deep CNN(Convolutional Neural Network), 일명 'GoogLeNet' 을 처음으로 소개한 논문으로, GoogleNet은 ILSVRC14(ImageNet Large-Scale Visual Recoginition Challenge 2014)에서 Classification과 Detection 모두에서 최고의 성능을 보였다. Inception 모듈은 multi-scale processing과 Hebbian principle에서 영감을 얻어 이전 층의 특성지도(feature map)를 다양한 크기의 필터(1x1, 3x3, 5x5, pooling)로 병렬처리한 이후 다시 하나의 출력으로 합치는 구조를 가지고 있다. .. 2020. 12. 16. [VGG] Simonyan & Zisserman, 2015, Very Deep Convolutional Networks For Large-Scale Image Recognition # 세줄 요약 # 저자들은 대량의 영상 인식 과제에서 합성곱 신경망(Convolutional Neural Network)의 깊이(depth; 여기선 신경망의 층을 늘리는 것을 의미함)에 따른 정확도의 변화를 연구하였다. 이 논문에서 소개된 신경망 모델은 매우 작은 크기(3X3)의 합성곱 필터(Convolutional filter)로 구성하여 신경망의 깊이를 증가시켰으며, 이 모델은 선행 신경망 모델들과 비교하여 신경망의 깊이는 16~19층까지 늘려서 유의미한 성능 향상 결과를 보여주었다. 이 논문의 저자들인 VGG그룹은 2014년 이미지넷 영상 인식 대회(ImageNet Large-Scale Visual Recoginition Challenge; ILSVRC)에서 localization 부문에서 1등, .. 2020. 12. 9. 이전 1 2 3 4 5 다음
