Matches in SemOpenAlex for { <https://semopenalex.org/work/W4207055912> ?p ?o ?g. }
- W4207055912 endingPage "105250" @default.
- W4207055912 startingPage "105250" @default.
- W4207055912 abstract "To investigate the ability of our convolutional neural network (CNN) to predict axillary lymph node metastasis using primary breast cancer ultrasound (US) images. In this IRB-approved study, 338 US images (two orthogonal images) from 169 patients from 1/2014–12/2016 were used. Suspicious lymph nodes were seen on US and patients subsequently underwent core-biopsy. 64 patients had metastatic lymph nodes. A custom CNN was utilized on 248 US images from 124 patients in the training dataset and tested on 90 US images from 45 patients. The CNN was implemented entirely of 3 × 3 convolutional kernels and linear layers. The 9 convolutional kernels consisted of 6 residual layers, totaling 12 convolutional layers. Feature maps were down-sampled using strided convolutions. Dropout with a 0.5 keep probability and L2 normalization was utilized. Training was implemented by using the Adam optimizer and a final SoftMax score threshold of 0.5 from the average of raw logits from each pixel was used for two class classification (metastasis or not). Our CNN achieved an AUC of 0.72 (SD ± 0.08) in predicting axillary lymph node metastasis from US images in the testing dataset. The model had an accuracy of 72.6% (SD ± 8.4) with a sensitivity and specificity of 65.5% (SD ± 28.6) and 78.9% (SD ± 15.1) respectively. Our algorithm is available to be shared for research use. (https://github.com/stmutasa/MetUS). It's feasible to predict axillary lymph node metastasis from US images using a deep learning technique. This can potentially aid nodal staging in patients with breast cancer." @default.
- W4207055912 created "2022-01-26" @default.
- W4207055912 creator A5012995283 @default.
- W4207055912 creator A5014796559 @default.
- W4207055912 creator A5019234233 @default.
- W4207055912 creator A5022667218 @default.
- W4207055912 creator A5024252699 @default.
- W4207055912 creator A5056417923 @default.
- W4207055912 creator A5060117211 @default.
- W4207055912 creator A5067878276 @default.
- W4207055912 creator A5074397580 @default.
- W4207055912 date "2022-04-01" @default.
- W4207055912 modified "2023-10-03" @default.
- W4207055912 title "Deep learning prediction of axillary lymph node status using ultrasound images" @default.
- W4207055912 cites W1992106518 @default.
- W4207055912 cites W2027748666 @default.
- W4207055912 cites W2030161963 @default.
- W4207055912 cites W2066706667 @default.
- W4207055912 cites W2090384234 @default.
- W4207055912 cites W2090548298 @default.
- W4207055912 cites W2099474055 @default.
- W4207055912 cites W2155090854 @default.
- W4207055912 cites W2160986504 @default.
- W4207055912 cites W2253618607 @default.
- W4207055912 cites W2596288071 @default.
- W4207055912 cites W2739692619 @default.
- W4207055912 cites W2802190884 @default.
- W4207055912 cites W2803760365 @default.
- W4207055912 cites W2808447393 @default.
- W4207055912 cites W2867962572 @default.
- W4207055912 cites W2891484462 @default.
- W4207055912 cites W2897434820 @default.
- W4207055912 cites W2914675314 @default.
- W4207055912 cites W2915829734 @default.
- W4207055912 cites W2922364031 @default.
- W4207055912 cites W2946878452 @default.
- W4207055912 cites W2964189045 @default.
- W4207055912 cites W2972885291 @default.
- W4207055912 cites W2986614196 @default.
- W4207055912 cites W2989693433 @default.
- W4207055912 cites W2992412398 @default.
- W4207055912 cites W3013389750 @default.
- W4207055912 cites W3016375157 @default.
- W4207055912 cites W3016608747 @default.
- W4207055912 cites W3033974041 @default.
- W4207055912 cites W4252714226 @default.
- W4207055912 doi "https://doi.org/10.1016/j.compbiomed.2022.105250" @default.
- W4207055912 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35114444" @default.
- W4207055912 hasPublicationYear "2022" @default.
- W4207055912 type Work @default.
- W4207055912 citedByCount "14" @default.
- W4207055912 countsByYear W42070559122022 @default.
- W4207055912 countsByYear W42070559122023 @default.
- W4207055912 crossrefType "journal-article" @default.
- W4207055912 hasAuthorship W4207055912A5012995283 @default.
- W4207055912 hasAuthorship W4207055912A5014796559 @default.
- W4207055912 hasAuthorship W4207055912A5019234233 @default.
- W4207055912 hasAuthorship W4207055912A5022667218 @default.
- W4207055912 hasAuthorship W4207055912A5024252699 @default.
- W4207055912 hasAuthorship W4207055912A5056417923 @default.
- W4207055912 hasAuthorship W4207055912A5060117211 @default.
- W4207055912 hasAuthorship W4207055912A5067878276 @default.
- W4207055912 hasAuthorship W4207055912A5074397580 @default.
- W4207055912 hasConcept C108583219 @default.
- W4207055912 hasConcept C121608353 @default.
- W4207055912 hasConcept C126322002 @default.
- W4207055912 hasConcept C126838900 @default.
- W4207055912 hasConcept C136886441 @default.
- W4207055912 hasConcept C142724271 @default.
- W4207055912 hasConcept C144024400 @default.
- W4207055912 hasConcept C153180895 @default.
- W4207055912 hasConcept C154945302 @default.
- W4207055912 hasConcept C160633673 @default.
- W4207055912 hasConcept C188441871 @default.
- W4207055912 hasConcept C19165224 @default.
- W4207055912 hasConcept C2777649267 @default.
- W4207055912 hasConcept C2779720271 @default.
- W4207055912 hasConcept C2780849966 @default.
- W4207055912 hasConcept C41008148 @default.
- W4207055912 hasConcept C530470458 @default.
- W4207055912 hasConcept C71924100 @default.
- W4207055912 hasConcept C81363708 @default.
- W4207055912 hasConceptScore W4207055912C108583219 @default.
- W4207055912 hasConceptScore W4207055912C121608353 @default.
- W4207055912 hasConceptScore W4207055912C126322002 @default.
- W4207055912 hasConceptScore W4207055912C126838900 @default.
- W4207055912 hasConceptScore W4207055912C136886441 @default.
- W4207055912 hasConceptScore W4207055912C142724271 @default.
- W4207055912 hasConceptScore W4207055912C144024400 @default.
- W4207055912 hasConceptScore W4207055912C153180895 @default.
- W4207055912 hasConceptScore W4207055912C154945302 @default.
- W4207055912 hasConceptScore W4207055912C160633673 @default.
- W4207055912 hasConceptScore W4207055912C188441871 @default.
- W4207055912 hasConceptScore W4207055912C19165224 @default.
- W4207055912 hasConceptScore W4207055912C2777649267 @default.
- W4207055912 hasConceptScore W4207055912C2779720271 @default.
- W4207055912 hasConceptScore W4207055912C2780849966 @default.
- W4207055912 hasConceptScore W4207055912C41008148 @default.