Filters








5 Hits in 21.5 sec

Abnormality Detection in Mammography using Deep Convolutional Neural Networks [article]

Pengcheng Xi, Chang Shu, Rafik Goubran
2018 arXiv   pre-print
Our approach demonstrates that deep convolutional neural network classifiers have remarkable localization capabilities despite no supervision on the location of abnormalities is provided.  ...  To reduce the cost and workload of radiologists, we propose a computer aided detection approach for classifying and localizing calcifications and masses in mammogram images.  ...  [29] introduced ChestX-ray8, a hospital-scale chest X-ray database, and provided benchmarks on weakly-supervised classification and localization of common thorax diseases.  ... 
arXiv:1803.01906v1 fatcat:2465qphxajchzegpic57qe3cfu

Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy [article]

Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li, Philip Sellars, Samar M Alsaleh, Robby T Tan, Carola-Bibiane Schönlieb
2021 arXiv   pre-print
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge.  ...  We demonstrate that our technique reports state-of-the-art results for semi-supervised classification.  ...  Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classi- fication and localization of common thorax diseases.  ... 
arXiv:1906.08635v4 fatcat:hmfiiq3dbrapfiowpvfit22gna

Chest X-ray anomaly detection based on normal models of anatomical structures segmented by U-Net
U-Netで領域抽出した解剖構造の正常モデルに基づく胸部X線異常検知

Kenji KONDO, Jun OZAWA, Masaki KIYONO, Shinichi FUJIMOTO, Masato TANAKA, Toshiki ADACHI, Harumi ITO, Hirohiko KIMURA
2019
We report a chest X-ray anomaly detection method based on normal models of anatomical structures, and the corresponding evaluation results.  ...  The method consists of segmentation process for anatomical structures and anomaly detection process for the segmented regions.  ...  Summers, "ChestX-ray8: Hospital-scale ChestX-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases , CVPR2017 2017. [Youden 50] W. J.  ... 
doi:10.11517/pjsai.jsai2019.0_1h4j1301 fatcat:qpndigwvn5bl3k5gm2hf4wplsy

What is being transferred in transfer learning? [article]

Behnam Neyshabur and Hanie Sedghi and Chiyuan Zhang
2021 arXiv   pre-print
Through a series of analyses on transferring to block-shuffled images, we separate the effect of feature reuse from learning low-level statistics of data and show that some benefit of transfer learning  ...  One desired capability for machines is the ability to transfer their knowledge of one domain to another where data is (usually) scarce.  ...  Acknowledgements We would like to thank Samy Bengio and Maithra Raghu for valuable conversations. References  ... 
arXiv:2008.11687v2 fatcat:y47sffba55f77exczzo6c7cip4

20th ECP

2005 Virchows Archiv  
The authors made a preliminary assessement of possible correlations between the amount of fibrillary components and capillary network of intratumoral stroma and the degree of glandular formation in 20  ...  stromal components variations and the degree of tubule formation.  ...  On the chest X-ray paracardial consolidation of the left lung was found. Physical examination was unremarkable. Chest CT-scan revealed a picture suspicious of intralobar pulmonary sequestration.  ... 
doi:10.1007/s00428-005-1288-1 fatcat:25f45fdp5ffvdlo25zaqkddywm