FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3182257448> ?p ?o ?g. }

• W3182257448 endingPage "181" @default.
• W3182257448 startingPage "181" @default.
• W3182257448 abstract "Abstract Background:Breast cancer (BC) is the second most common cancer among women. BC screening is usually based on mammography interpreted by radiologists. Recently, some researchers have used deep learning to automatically diagnose BC in mammography and so assist radiologists. The progress of BC detection algorithms can be measured by their performance on public datasets. The CBIS-DDSM is a widely used public dataset composed of scanned mammographies, equally divided into malignant and non-malignant (benign) images. Each image is accompanied by the segmentation of the lesion. Shen et al. (Nature Sci. Rep., 2019) presented a BC detection algorithm using an “end-to-end” approach to train deep neural networks. In this algorithm, a patch classifier is first trained to classify local image patches. The patch classifier's weights are then used to initialize the whole image classifier, that is refined using datasets with the cancer status of the whole image. They achieved an AUC of 0.87 [0.84, 0.90] in classifying CBIS-DDSM images, using their best single-model, single-view breast classifier. They used ResNet (He et al., CVPR 2016) as the basis of their algorithm. Our hypothesis was that replacing the old ResNet with the modern EfficientNet (Tan et al., arXiv 2019) and MobileNetV2 (Sandler et al.,CVPR 2018) would result in greater accuracy. Methods:We tested many different models, to conclude that the best model is obtained using EfficientNet-B4 as the base model, with a MobileNetV2 block at the top, followed by a dense layer with two output categories. We trained the patch classifier using 52,528 patches with 224x224 pixels extracted from CBIS-DDSM. From each image, we extracted 20 patches: 10 patches containing the lesion and 10 from the background (without lesion). The patch classifier weights were then used to initialize the whole image classifier, that was trained using the end-to-end approach with CBIS-DDSM images resized to 1152x896 pixels, with data augmentation. The training was performed using a step learning rate of 1e-4 for the first 20 epochs then 1e-5 for the remaining 10 and batch size of 4, using 10-fold cross-validation. We used 81% of the dataset for training, 9% for validation and 10% for testing. Results:We obtained an AUC of 0.8963±0.06, using a single-model, single-view classifier and without test-time data augmentation. Conclusions:Using EfficientNet and MobileNetV2 as the basis of the BC detection algorithm (instead of ResNet), we obtained an improvement in classifying CBIS-DDSM images into malignant/non-malignant: AUC has increased from 0.87 to 0.896. Our AUC is also larger than other recent papers in the literature, such as Shu et al. (IEEE Trans Med. Image, 2020) that achieved an AUC of 0.838 in the same CBIS-DDSM dataset. Citation Format: Daniel G. Petrini, Carlos Shimizu, Gabriel V. Valente, Guilherme Folgueira, Guilherme A. Novaes, Maria L. Katayama, Pedro Serio, Rosimeire A. Roela, Tatiana C. Tucunduva, Maria Aparecida A. Folgueira, Hae Y. Kim. High-accuracy breast cancer detection in mammography using EfficientNet and end-to-end training [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 181." @default.
• W3182257448 created "2021-07-19" @default.
• W3182257448 creator A5012552798 @default.
• W3182257448 creator A5016720580 @default.
• W3182257448 creator A5019450152 @default.
• W3182257448 creator A5019545518 @default.
• W3182257448 creator A5024344534 @default.
• W3182257448 creator A5026107119 @default.
• W3182257448 creator A5032433006 @default.
• W3182257448 creator A5042726894 @default.
• W3182257448 creator A5045582462 @default.
• W3182257448 creator A5067399777 @default.
• W3182257448 creator A5073754238 @default.
• W3182257448 date "2021-07-01" @default.
• W3182257448 modified "2023-09-27" @default.
• W3182257448 title "Abstract 181: High-accuracy breast cancer detection in mammography using EfficientNet and end-to-end training" @default.
• W3182257448 doi "https://doi.org/10.1158/1538-7445.am2021-181" @default.
• W3182257448 hasPublicationYear "2021" @default.
• W3182257448 type Work @default.
• W3182257448 sameAs 3182257448 @default.
• W3182257448 citedByCount "0" @default.
• W3182257448 crossrefType "journal-article" @default.
• W3182257448 hasAuthorship W3182257448A5012552798 @default.
• W3182257448 hasAuthorship W3182257448A5016720580 @default.
• W3182257448 hasAuthorship W3182257448A5019450152 @default.
• W3182257448 hasAuthorship W3182257448A5019545518 @default.
• W3182257448 hasAuthorship W3182257448A5024344534 @default.
• W3182257448 hasAuthorship W3182257448A5026107119 @default.
• W3182257448 hasAuthorship W3182257448A5032433006 @default.
• W3182257448 hasAuthorship W3182257448A5042726894 @default.
• W3182257448 hasAuthorship W3182257448A5045582462 @default.
• W3182257448 hasAuthorship W3182257448A5067399777 @default.
• W3182257448 hasAuthorship W3182257448A5073754238 @default.
• W3182257448 hasConcept C108583219 @default.
• W3182257448 hasConcept C119857082 @default.
• W3182257448 hasConcept C121608353 @default.
• W3182257448 hasConcept C126322002 @default.
• W3182257448 hasConcept C153180895 @default.
• W3182257448 hasConcept C154945302 @default.
• W3182257448 hasConcept C2780472235 @default.
• W3182257448 hasConcept C2944601119 @default.
• W3182257448 hasConcept C41008148 @default.
• W3182257448 hasConcept C530470458 @default.
• W3182257448 hasConcept C58471807 @default.
• W3182257448 hasConcept C71924100 @default.
• W3182257448 hasConcept C89600930 @default.
• W3182257448 hasConcept C95623464 @default.
• W3182257448 hasConceptScore W3182257448C108583219 @default.
• W3182257448 hasConceptScore W3182257448C119857082 @default.
• W3182257448 hasConceptScore W3182257448C121608353 @default.
• W3182257448 hasConceptScore W3182257448C126322002 @default.
• W3182257448 hasConceptScore W3182257448C153180895 @default.
• W3182257448 hasConceptScore W3182257448C154945302 @default.
• W3182257448 hasConceptScore W3182257448C2780472235 @default.
• W3182257448 hasConceptScore W3182257448C2944601119 @default.
• W3182257448 hasConceptScore W3182257448C41008148 @default.
• W3182257448 hasConceptScore W3182257448C530470458 @default.
• W3182257448 hasConceptScore W3182257448C58471807 @default.
• W3182257448 hasConceptScore W3182257448C71924100 @default.
• W3182257448 hasConceptScore W3182257448C89600930 @default.
• W3182257448 hasConceptScore W3182257448C95623464 @default.
• W3182257448 hasIssue "13_Supplement" @default.
• W3182257448 hasLocation W31822574481 @default.
• W3182257448 hasOpenAccess W3182257448 @default.
• W3182257448 hasPrimaryLocation W31822574481 @default.
• W3182257448 hasRelatedWork W2563096758 @default.
• W3182257448 hasRelatedWork W2790662084 @default.
• W3182257448 hasRelatedWork W2954384599 @default.
• W3182257448 hasRelatedWork W2960184797 @default.
• W3182257448 hasRelatedWork W3104734424 @default.
• W3182257448 hasRelatedWork W3209779739 @default.
• W3182257448 hasRelatedWork W4226289457 @default.
• W3182257448 hasRelatedWork W4285827401 @default.
• W3182257448 hasRelatedWork W4386053843 @default.
• W3182257448 hasRelatedWork W3158004940 @default.
• W3182257448 hasVolume "81" @default.
• W3182257448 isParatext "false" @default.
• W3182257448 isRetracted "false" @default.
• W3182257448 magId "3182257448" @default.
• W3182257448 workType "article" @default.