Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313591539> ?p ?o ?g. }
- W4313591539 endingPage "1476" @default.
- W4313591539 startingPage "1467" @default.
- W4313591539 abstract "Breast cancer was the most commonly diagnosed cancer among women worldwide in 2020. Recently, several deep learning-based classification approaches have been proposed to screen breast cancer in mammograms. However, most of these approaches require additional detection or segmentation annotations. Meanwhile, some other image-level label-based methods often pay insufficient attention to lesion areas, which are critical for diagnosis. This study designs a novel deep-learning method for automatically diagnosing breast cancer in mammography, which focuses on the local lesion areas and only utilizes image-level classification labels. In this study, we propose to select discriminative feature descriptors from feature maps instead of identifying lesion areas using precise annotations. And we design a novel adaptive convolutional feature descriptor selection (AFDS) structure based on the distribution of the deep activation map. Specifically, we adopt the triangle threshold strategy to calculate a specific threshold for guiding the activation map to determine which feature descriptors (local areas) are discriminative. Ablation experiments and visualization analysis indicate that the AFDS structure makes the model easier to learn the difference between malignant and benign/normal lesions. Furthermore, since the AFDS structure can be regarded as a highly efficient pooling structure, it can be easily plugged into most existing convolutional neural networks with negligible effort and time consumption. Experimental results on two publicly available INbreast and CBIS-DDSM datasets indicate that the proposed method performs satisfactorily compared with state-of-the-art methods." @default.
- W4313591539 created "2023-01-06" @default.
- W4313591539 creator A5006247366 @default.
- W4313591539 creator A5037608200 @default.
- W4313591539 creator A5048069849 @default.
- W4313591539 creator A5070032905 @default.
- W4313591539 date "2023-03-01" @default.
- W4313591539 modified "2023-09-30" @default.
- W4313591539 title "Convolutional Feature Descriptor Selection for Mammogram Classification" @default.
- W4313591539 cites W1547714734 @default.
- W4313591539 cites W1861891407 @default.
- W4313591539 cites W1917647701 @default.
- W4313591539 cites W1971967553 @default.
- W4313591539 cites W2040620478 @default.
- W4313591539 cites W2086543716 @default.
- W4313591539 cites W2101668496 @default.
- W4313591539 cites W2101771332 @default.
- W4313591539 cites W2102150307 @default.
- W4313591539 cites W2129882004 @default.
- W4313591539 cites W2170249894 @default.
- W4313591539 cites W2216351247 @default.
- W4313591539 cites W2290344319 @default.
- W4313591539 cites W2295107390 @default.
- W4313591539 cites W2527654160 @default.
- W4313591539 cites W2617855130 @default.
- W4313591539 cites W2727347885 @default.
- W4313591539 cites W2736374171 @default.
- W4313591539 cites W2763070548 @default.
- W4313591539 cites W2903065295 @default.
- W4313591539 cites W2950557962 @default.
- W4313591539 cites W2962858109 @default.
- W4313591539 cites W2963090248 @default.
- W4313591539 cites W2963351448 @default.
- W4313591539 cites W2963446712 @default.
- W4313591539 cites W2964275459 @default.
- W4313591539 cites W2980030301 @default.
- W4313591539 cites W3001021123 @default.
- W4313591539 cites W3017004682 @default.
- W4313591539 cites W304373761 @default.
- W4313591539 cites W3087457015 @default.
- W4313591539 cites W3094286186 @default.
- W4313591539 cites W3112635222 @default.
- W4313591539 cites W3128646645 @default.
- W4313591539 cites W4205943891 @default.
- W4313591539 cites W4225597912 @default.
- W4313591539 cites W4285082580 @default.
- W4313591539 cites W4285097858 @default.
- W4313591539 doi "https://doi.org/10.1109/jbhi.2022.3233535" @default.
- W4313591539 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37018253" @default.
- W4313591539 hasPublicationYear "2023" @default.
- W4313591539 type Work @default.
- W4313591539 citedByCount "1" @default.
- W4313591539 countsByYear W43135915392023 @default.
- W4313591539 crossrefType "journal-article" @default.
- W4313591539 hasAuthorship W4313591539A5006247366 @default.
- W4313591539 hasAuthorship W4313591539A5037608200 @default.
- W4313591539 hasAuthorship W4313591539A5048069849 @default.
- W4313591539 hasAuthorship W4313591539A5070032905 @default.
- W4313591539 hasConcept C108583219 @default.
- W4313591539 hasConcept C119857082 @default.
- W4313591539 hasConcept C121608353 @default.
- W4313591539 hasConcept C126322002 @default.
- W4313591539 hasConcept C138885662 @default.
- W4313591539 hasConcept C148483581 @default.
- W4313591539 hasConcept C153180895 @default.
- W4313591539 hasConcept C154945302 @default.
- W4313591539 hasConcept C2776401178 @default.
- W4313591539 hasConcept C2780472235 @default.
- W4313591539 hasConcept C41008148 @default.
- W4313591539 hasConcept C41895202 @default.
- W4313591539 hasConcept C52622490 @default.
- W4313591539 hasConcept C530470458 @default.
- W4313591539 hasConcept C70437156 @default.
- W4313591539 hasConcept C71924100 @default.
- W4313591539 hasConcept C81363708 @default.
- W4313591539 hasConcept C89600930 @default.
- W4313591539 hasConcept C97931131 @default.
- W4313591539 hasConceptScore W4313591539C108583219 @default.
- W4313591539 hasConceptScore W4313591539C119857082 @default.
- W4313591539 hasConceptScore W4313591539C121608353 @default.
- W4313591539 hasConceptScore W4313591539C126322002 @default.
- W4313591539 hasConceptScore W4313591539C138885662 @default.
- W4313591539 hasConceptScore W4313591539C148483581 @default.
- W4313591539 hasConceptScore W4313591539C153180895 @default.
- W4313591539 hasConceptScore W4313591539C154945302 @default.
- W4313591539 hasConceptScore W4313591539C2776401178 @default.
- W4313591539 hasConceptScore W4313591539C2780472235 @default.
- W4313591539 hasConceptScore W4313591539C41008148 @default.
- W4313591539 hasConceptScore W4313591539C41895202 @default.
- W4313591539 hasConceptScore W4313591539C52622490 @default.
- W4313591539 hasConceptScore W4313591539C530470458 @default.
- W4313591539 hasConceptScore W4313591539C70437156 @default.
- W4313591539 hasConceptScore W4313591539C71924100 @default.
- W4313591539 hasConceptScore W4313591539C81363708 @default.
- W4313591539 hasConceptScore W4313591539C89600930 @default.
- W4313591539 hasConceptScore W4313591539C97931131 @default.
- W4313591539 hasIssue "3" @default.
- W4313591539 hasLocation W43135915391 @default.