FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295810146> ?p ?o ?g. }

• W4295810146 abstract "Over the past decades, histopathological cancer diagnostics has become more complex, and the increasing number of biopsies is a challenge for most pathology laboratories. Thus, development of automatic methods for evaluation of histopathological cancer sections would be of value. In this study, we used 624 whole slide images (WSIs) of breast cancer from a Norwegian cohort. We propose a cascaded convolutional neural network design, called H2G-Net, for segmentation of breast cancer region from gigapixel histopathological images. The design involves a detection stage using a patch-wise method, and a refinement stage using a convolutional autoencoder. To validate the design, we conducted an ablation study to assess the impact of selected components in the pipeline on tumor segmentation. Guiding segmentation, using hierarchical sampling and deep heatmap refinement, proved to be beneficial when segmenting the histopathological images. We found a significant improvement when using a refinement network for post-processing the generated tumor segmentation heatmaps. The overall best design achieved a Dice similarity coefficient of 0.933±0.069 on an independent test set of 90 WSIs. The design outperformed single-resolution approaches, such as cluster-guided, patch-wise high-resolution classification using MobileNetV2 (0.872±0.092) and a low-resolution U-Net (0.874±0.128). In addition, the design performed consistently on WSIs across all histological grades and segmentation on a representative × 400 WSI took ~ 58 s, using only the central processing unit. The findings demonstrate the potential of utilizing a refinement network to improve patch-wise predictions. The solution is efficient and does not require overlapping patch inference or ensembling. Furthermore, we showed that deep neural networks can be trained using a random sampling scheme that balances on multiple different labels simultaneously, without the need of storing patches on disk. Future work should involve more efficient patch generation and sampling, as well as improved clustering." @default.
• W4295810146 created "2022-09-15" @default.
• W4295810146 creator A5010423987 @default.
• W4295810146 creator A5023766551 @default.
• W4295810146 creator A5025496151 @default.
• W4295810146 creator A5030118242 @default.
• W4295810146 creator A5044809861 @default.
• W4295810146 creator A5051726150 @default.
• W4295810146 creator A5055622780 @default.
• W4295810146 creator A5070206724 @default.
• W4295810146 creator A5090654106 @default.
• W4295810146 date "2022-09-14" @default.
• W4295810146 modified "2023-09-27" @default.
• W4295810146 title "H2G-Net: A multi-resolution refinement approach for segmentation of breast cancer region in gigapixel histopathological images" @default.
• W4295810146 cites W1977653087 @default.
• W4295810146 cites W1998646002 @default.
• W4295810146 cites W2004426748 @default.
• W4295810146 cites W2010871781 @default.
• W4295810146 cites W2034269086 @default.
• W4295810146 cites W2108598243 @default.
• W4295810146 cites W2117692326 @default.
• W4295810146 cites W2132162500 @default.
• W4295810146 cites W2133059825 @default.
• W4295810146 cites W2183341477 @default.
• W4295810146 cites W2294798173 @default.
• W4295810146 cites W2301358467 @default.
• W4295810146 cites W2340897893 @default.
• W4295810146 cites W2752967760 @default.
• W4295810146 cites W2772723798 @default.
• W4295810146 cites W2774292910 @default.
• W4295810146 cites W2803416021 @default.
• W4295810146 cites W2885824038 @default.
• W4295810146 cites W2889232360 @default.
• W4295810146 cites W2921577390 @default.
• W4295810146 cites W2952481429 @default.
• W4295810146 cites W2953531386 @default.
• W4295810146 cites W2963129226 @default.
• W4295810146 cites W2963163009 @default.
• W4295810146 cites W2969278648 @default.
• W4295810146 cites W2973444803 @default.
• W4295810146 cites W2975180264 @default.
• W4295810146 cites W2990120196 @default.
• W4295810146 cites W2995682783 @default.
• W4295810146 cites W2997591727 @default.
• W4295810146 cites W3004053956 @default.
• W4295810146 cites W3011941780 @default.
• W4295810146 cites W3016045558 @default.
• W4295810146 cites W3043535018 @default.
• W4295810146 cites W3045345885 @default.
• W4295810146 cites W3081752372 @default.
• W4295810146 cites W3087188664 @default.
• W4295810146 cites W3089090082 @default.
• W4295810146 cites W3092103057 @default.
• W4295810146 cites W3106307315 @default.
• W4295810146 cites W3112701542 @default.
• W4295810146 cites W3129373370 @default.
• W4295810146 cites W3132455321 @default.
• W4295810146 cites W3135547872 @default.
• W4295810146 cites W3153193598 @default.
• W4295810146 cites W3167557177 @default.
• W4295810146 cites W3172375847 @default.
• W4295810146 cites W3175701034 @default.
• W4295810146 cites W3203225264 @default.
• W4295810146 cites W4225529913 @default.
• W4295810146 cites W4287325018 @default.
• W4295810146 doi "https://doi.org/10.3389/fmed.2022.971873" @default.
• W4295810146 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36186805" @default.
• W4295810146 hasPublicationYear "2022" @default.
• W4295810146 type Work @default.
• W4295810146 citedByCount "4" @default.
• W4295810146 countsByYear W42958101462022 @default.
• W4295810146 countsByYear W42958101462023 @default.
• W4295810146 crossrefType "journal-article" @default.
• W4295810146 hasAuthorship W4295810146A5010423987 @default.
• W4295810146 hasAuthorship W4295810146A5023766551 @default.
• W4295810146 hasAuthorship W4295810146A5025496151 @default.
• W4295810146 hasAuthorship W4295810146A5030118242 @default.
• W4295810146 hasAuthorship W4295810146A5044809861 @default.
• W4295810146 hasAuthorship W4295810146A5051726150 @default.
• W4295810146 hasAuthorship W4295810146A5055622780 @default.
• W4295810146 hasAuthorship W4295810146A5070206724 @default.
• W4295810146 hasAuthorship W4295810146A5090654106 @default.
• W4295810146 hasBestOaLocation W42958101461 @default.
• W4295810146 hasConcept C108583219 @default.
• W4295810146 hasConcept C121608353 @default.
• W4295810146 hasConcept C124504099 @default.
• W4295810146 hasConcept C126322002 @default.
• W4295810146 hasConcept C153180895 @default.
• W4295810146 hasConcept C154945302 @default.
• W4295810146 hasConcept C163892561 @default.
• W4295810146 hasConcept C199360897 @default.
• W4295810146 hasConcept C41008148 @default.
• W4295810146 hasConcept C43521106 @default.
• W4295810146 hasConcept C530470458 @default.
• W4295810146 hasConcept C71924100 @default.
• W4295810146 hasConcept C81363708 @default.
• W4295810146 hasConcept C89600930 @default.
• W4295810146 hasConceptScore W4295810146C108583219 @default.
• W4295810146 hasConceptScore W4295810146C121608353 @default.
• W4295810146 hasConceptScore W4295810146C124504099 @default.

• next