FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290973154> ?p ?o ?g. }

• W4290973154 endingPage "e0271106" @default.
• W4290973154 startingPage "e0271106" @default.
• W4290973154 abstract "Deep learning techniques have achieved remarkable success in lesion segmentation and classification between benign and malignant tumors in breast ultrasound images. However, existing studies are predominantly focused on devising efficient neural network-based learning structures to tackle specific tasks individually. By contrast, in clinical practice, sonographers perform segmentation and classification as a whole; they investigate the border contours of the tissue while detecting abnormal masses and performing diagnostic analysis. Performing multiple cognitive tasks simultaneously in this manner facilitates exploitation of the commonalities and differences between tasks. Inspired by this unified recognition process, this study proposes a novel learning scheme, called the cross-task guided network (CTG-Net), for efficient ultrasound breast image understanding. CTG-Net integrates the two most significant tasks in computerized breast lesion pattern investigation: lesion segmentation and tumor classification. Further, it enables the learning of efficient feature representations across tasks from ultrasound images and the task-specific discriminative features that can greatly facilitate lesion detection. This is achieved using task-specific attention models to share the prediction results between tasks. Then, following the guidance of task-specific attention soft masks, the joint feature responses are efficiently calibrated through iterative model training. Finally, a simple feature fusion scheme is used to aggregate the attention-guided features for efficient ultrasound pattern analysis. We performed extensive experimental comparisons on multiple ultrasound datasets. Compared to state-of-the-art multi-task learning approaches, the proposed approach can improve the Dice’s coefficient, true-positive rate of segmentation, AUC, and sensitivity of classification by 11%, 17%, 2%, and 6%, respectively. The results demonstrate that the proposed cross-task guided feature learning framework can effectively fuse the complementary information of ultrasound image segmentation and classification tasks to achieve accurate tumor localization. Thus, it can aid sonographers to detect and diagnose breast cancer." @default.
• W4290973154 created "2022-08-13" @default.
• W4290973154 creator A5027102173 @default.
• W4290973154 creator A5042295379 @default.
• W4290973154 creator A5049352132 @default.
• W4290973154 creator A5055002737 @default.
• W4290973154 creator A5060905149 @default.
• W4290973154 creator A5080335228 @default.
• W4290973154 date "2022-08-11" @default.
• W4290973154 modified "2023-09-26" @default.
• W4290973154 title "CTG-Net: Cross-task guided network for breast ultrasound diagnosis" @default.
• W4290973154 cites W1901129140 @default.
• W4290973154 cites W1903029394 @default.
• W4290973154 cites W2009950565 @default.
• W4290973154 cites W2046887523 @default.
• W4290973154 cites W2054010632 @default.
• W4290973154 cites W2059900648 @default.
• W4290973154 cites W2121879722 @default.
• W4290973154 cites W2194775991 @default.
• W4290973154 cites W2290687990 @default.
• W4290973154 cites W2571079985 @default.
• W4290973154 cites W2744692634 @default.
• W4290973154 cites W2796827612 @default.
• W4290973154 cites W2805550523 @default.
• W4290973154 cites W2809348156 @default.
• W4290973154 cites W2884436604 @default.
• W4290973154 cites W2888358068 @default.
• W4290973154 cites W2906785117 @default.
• W4290973154 cites W2922358453 @default.
• W4290973154 cites W2928133111 @default.
• W4290973154 cites W2932464288 @default.
• W4290973154 cites W2945528352 @default.
• W4290973154 cites W2955058313 @default.
• W4290973154 cites W2962858109 @default.
• W4290973154 cites W2962914239 @default.
• W4290973154 cites W2963104294 @default.
• W4290973154 cites W2963430933 @default.
• W4290973154 cites W2963446712 @default.
• W4290973154 cites W2963881378 @default.
• W4290973154 cites W2964150021 @default.
• W4290973154 cites W2964309882 @default.
• W4290973154 cites W2969326038 @default.
• W4290973154 cites W2969908837 @default.
• W4290973154 cites W2991372685 @default.
• W4290973154 cites W2996341812 @default.
• W4290973154 cites W2997709384 @default.
• W4290973154 cites W3014269107 @default.
• W4290973154 cites W3027739765 @default.
• W4290973154 cites W3034210623 @default.
• W4290973154 cites W3082402367 @default.
• W4290973154 cites W3086072045 @default.
• W4290973154 cites W3095777298 @default.
• W4290973154 cites W3096117505 @default.
• W4290973154 cites W3100227965 @default.
• W4290973154 cites W3103010481 @default.
• W4290973154 cites W3106904274 @default.
• W4290973154 cites W3110722024 @default.
• W4290973154 cites W3128528820 @default.
• W4290973154 cites W3131251465 @default.
• W4290973154 cites W3133858468 @default.
• W4290973154 cites W3156044584 @default.
• W4290973154 cites W3164872277 @default.
• W4290973154 cites W3174295900 @default.
• W4290973154 cites W3175198793 @default.
• W4290973154 cites W3182850645 @default.
• W4290973154 cites W3205636410 @default.
• W4290973154 cites W3212106213 @default.
• W4290973154 doi "https://doi.org/10.1371/journal.pone.0271106" @default.
• W4290973154 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35951606" @default.
• W4290973154 hasPublicationYear "2022" @default.
• W4290973154 type Work @default.
• W4290973154 citedByCount "5" @default.
• W4290973154 countsByYear W42909731542022 @default.
• W4290973154 countsByYear W42909731542023 @default.
• W4290973154 crossrefType "journal-article" @default.
• W4290973154 hasAuthorship W4290973154A5027102173 @default.
• W4290973154 hasAuthorship W4290973154A5042295379 @default.
• W4290973154 hasAuthorship W4290973154A5049352132 @default.
• W4290973154 hasAuthorship W4290973154A5055002737 @default.
• W4290973154 hasAuthorship W4290973154A5060905149 @default.
• W4290973154 hasAuthorship W4290973154A5080335228 @default.
• W4290973154 hasBestOaLocation W42909731541 @default.
• W4290973154 hasConcept C108583219 @default.
• W4290973154 hasConcept C119857082 @default.
• W4290973154 hasConcept C121608353 @default.
• W4290973154 hasConcept C126322002 @default.
• W4290973154 hasConcept C138885662 @default.
• W4290973154 hasConcept C153180895 @default.
• W4290973154 hasConcept C154945302 @default.
• W4290973154 hasConcept C162324750 @default.
• W4290973154 hasConcept C187736073 @default.
• W4290973154 hasConcept C2776401178 @default.
• W4290973154 hasConcept C2777423100 @default.
• W4290973154 hasConcept C2780451532 @default.
• W4290973154 hasConcept C2780472235 @default.
• W4290973154 hasConcept C28006648 @default.
• W4290973154 hasConcept C41008148 @default.
• W4290973154 hasConcept C41895202 @default.

• next