FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2572512422> ?p ?o ?g. }

• W2572512422 endingPage "1027" @default.
• W2572512422 startingPage "1017" @default.
• W2572512422 abstract "Purpose It is estimated that 7% of women in the western world will develop palpable breast cysts in their lifetime. Even though cysts have been correlated with risk of developing breast cancer, many of them are benign and do not require follow‐up. We develop a method to discriminate benign solitary cysts from malignant masses in digital mammography. We think a system like this can have merit in the clinic as a decision aid or complementary to specialized modalities. Methods We employ a deep convolutional neural network (CNN) to classify cyst and mass patches. Deep CNNs have been shown to be powerful classifiers, but need a large amount of training data for which medical problems are often difficult to come by. The key contribution of this paper is that we show good performance can be obtained on a small dataset by pretraining the network on a large dataset of a related task. We subsequently investigate the following: (a) when a mammographic exam is performed, two different views of the same breast are recorded. We investigate the merit of combining the output of the classifier from these two views. (b) We evaluate the importance of the resolution of the patches fed to the network. (c) A method dubbed tissue augmentation is subsequently employed, where we extract normal tissue from normal patches and superimpose this onto the actual samples aiming for a classifier invariant to occluding tissue. (d) We combine the representation extracted using the deep CNN with our previously developed features. Results We show that using the proposed deep learning method, an area under the ROC curve (AUC) value of 0.80 can be obtained on a set of benign solitary cysts and malignant mass findings recalled in screening. We find that it works significantly better than our previously developed approach by comparing the AUC of the ROC using bootstrapping. By combining views, the results can be further improved, though this difference was not found to be significant. We find no significant difference between using a resolution of 100 versus 200 micron. The proposed tissue augmentations give a small improvement in performance, but this improvement was also not found to be significant. The final system obtained an AUC of 0.80 with 95% confidence interval [0.78, 0.83], calculated using bootstrapping. The system works best for lesions larger than 27 mm where it obtains an AUC value of 0.87. Conclusion We have presented a computer‐aided diagnosis (CADx) method to discriminate cysts from solid lesion in mammography using features from a deep CNN trained on a large set of mass candidates, obtaining an AUC of 0.80 on a set of diagnostic exams recalled from screening. We believe the system shows great potential and comes close to the performance of recently developed spectral mammography. We think the system can be further improved when more data and computational power becomes available." @default.
• W2572512422 created "2017-01-26" @default.
• W2572512422 creator A5033914440 @default.
• W2572512422 creator A5042982766 @default.
• W2572512422 creator A5069883501 @default.
• W2572512422 creator A5085370896 @default.
• W2572512422 date "2017-03-01" @default.
• W2572512422 modified "2023-10-06" @default.
• W2572512422 title "Discriminating solitary cysts from soft tissue lesions in mammography using a pretrained deep convolutional neural network" @default.
• W2572512422 cites W1677182931 @default.
• W2572512422 cites W1678356000 @default.
• W2572512422 cites W1901129140 @default.
• W2572512422 cites W1901943601 @default.
• W2572512422 cites W1903029394 @default.
• W2572512422 cites W1917647701 @default.
• W2572512422 cites W1923404803 @default.
• W2572512422 cites W1982896147 @default.
• W2572512422 cites W1997199085 @default.
• W2572512422 cites W2004557351 @default.
• W2572512422 cites W2007693625 @default.
• W2572512422 cites W2043765507 @default.
• W2572512422 cites W2072072671 @default.
• W2572512422 cites W2076063813 @default.
• W2572512422 cites W2095972041 @default.
• W2572512422 cites W2112467442 @default.
• W2572512422 cites W2117897510 @default.
• W2572512422 cites W2141619730 @default.
• W2572512422 cites W2145339207 @default.
• W2572512422 cites W2159318977 @default.
• W2572512422 cites W2163905093 @default.
• W2572512422 cites W2167896953 @default.
• W2572512422 cites W22040386 @default.
• W2572512422 cites W2253429366 @default.
• W2572512422 cites W2257979135 @default.
• W2572512422 cites W2314628605 @default.
• W2572512422 cites W2346062110 @default.
• W2572512422 cites W2492863677 @default.
• W2572512422 cites W2493683088 @default.
• W2572512422 cites W2919115771 @default.
• W2572512422 cites W2963305465 @default.
• W2572512422 cites W399473641 @default.
• W2572512422 doi "https://doi.org/10.1002/mp.12110" @default.
• W2572512422 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28094850" @default.
• W2572512422 hasPublicationYear "2017" @default.
• W2572512422 type Work @default.
• W2572512422 sameAs 2572512422 @default.
• W2572512422 citedByCount "90" @default.
• W2572512422 countsByYear W25725124222017 @default.
• W2572512422 countsByYear W25725124222018 @default.
• W2572512422 countsByYear W25725124222019 @default.
• W2572512422 countsByYear W25725124222020 @default.
• W2572512422 countsByYear W25725124222021 @default.
• W2572512422 countsByYear W25725124222022 @default.
• W2572512422 countsByYear W25725124222023 @default.
• W2572512422 crossrefType "journal-article" @default.
• W2572512422 hasAuthorship W2572512422A5033914440 @default.
• W2572512422 hasAuthorship W2572512422A5042982766 @default.
• W2572512422 hasAuthorship W2572512422A5069883501 @default.
• W2572512422 hasAuthorship W2572512422A5085370896 @default.
• W2572512422 hasBestOaLocation W25725124221 @default.
• W2572512422 hasConcept C108583219 @default.
• W2572512422 hasConcept C121608353 @default.
• W2572512422 hasConcept C126322002 @default.
• W2572512422 hasConcept C126838900 @default.
• W2572512422 hasConcept C153180895 @default.
• W2572512422 hasConcept C154945302 @default.
• W2572512422 hasConcept C2777423100 @default.
• W2572512422 hasConcept C2780472235 @default.
• W2572512422 hasConcept C2781281974 @default.
• W2572512422 hasConcept C31601959 @default.
• W2572512422 hasConcept C41008148 @default.
• W2572512422 hasConcept C50644808 @default.
• W2572512422 hasConcept C530470458 @default.
• W2572512422 hasConcept C71924100 @default.
• W2572512422 hasConcept C81363708 @default.
• W2572512422 hasConcept C95623464 @default.
• W2572512422 hasConceptScore W2572512422C108583219 @default.
• W2572512422 hasConceptScore W2572512422C121608353 @default.
• W2572512422 hasConceptScore W2572512422C126322002 @default.
• W2572512422 hasConceptScore W2572512422C126838900 @default.
• W2572512422 hasConceptScore W2572512422C153180895 @default.
• W2572512422 hasConceptScore W2572512422C154945302 @default.
• W2572512422 hasConceptScore W2572512422C2777423100 @default.
• W2572512422 hasConceptScore W2572512422C2780472235 @default.
• W2572512422 hasConceptScore W2572512422C2781281974 @default.
• W2572512422 hasConceptScore W2572512422C31601959 @default.
• W2572512422 hasConceptScore W2572512422C41008148 @default.
• W2572512422 hasConceptScore W2572512422C50644808 @default.
• W2572512422 hasConceptScore W2572512422C530470458 @default.
• W2572512422 hasConceptScore W2572512422C71924100 @default.
• W2572512422 hasConceptScore W2572512422C81363708 @default.
• W2572512422 hasConceptScore W2572512422C95623464 @default.
• W2572512422 hasFunder F4320322777 @default.
• W2572512422 hasIssue "3" @default.
• W2572512422 hasLocation W25725124221 @default.
• W2572512422 hasLocation W25725124222 @default.
• W2572512422 hasLocation W25725124223 @default.
• W2572512422 hasOpenAccess W2572512422 @default.

• next