Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220896502> ?p ?o ?g. }
- W4220896502 endingPage "2262" @default.
- W4220896502 startingPage "2252" @default.
- W4220896502 abstract "Histopathological tissue classification is a simpler way to achieve semantic segmentation for the whole slide images, which can alleviate the requirement of pixel-level dense annotations. Existing works mostly leverage the popular CNN classification backbones in computer vision to achieve histopathological tissue classification. In this paper, we propose a super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), for any well-trained classification backbone to improve the classification performance without a re-training burden. For each patch, we construct a multi-resolution image pyramid to obtain the pyramidal contextual information. For each level in the pyramid, we extract the multi-scale deep-broad features by our proposed Deep-Broad block (DB-block). We equip PDBL in three popular classification backbones, ShuffLeNetV2, EfficientNetb0, and ResNet50 to evaluate the effectiveness and efficiency of our proposed module on two datasets (Kather Multiclass Dataset and the LC25000 Dataset). Experimental results demonstrate the proposed PDBL can steadily improve the tissue-level classification performance for any CNN backbones, especially for the lightweight models when given a small among of training samples (less than 10%). It greatly saves the computational resources and annotation efforts. The source code is available at: https://github.com/linjiatai/PDBL." @default.
- W4220896502 created "2022-04-03" @default.
- W4220896502 creator A5001198279 @default.
- W4220896502 creator A5003926160 @default.
- W4220896502 creator A5004657494 @default.
- W4220896502 creator A5007122542 @default.
- W4220896502 creator A5007767807 @default.
- W4220896502 creator A5016655901 @default.
- W4220896502 creator A5018863416 @default.
- W4220896502 creator A5020316684 @default.
- W4220896502 creator A5028311940 @default.
- W4220896502 creator A5035896421 @default.
- W4220896502 creator A5046771717 @default.
- W4220896502 creator A5065451819 @default.
- W4220896502 creator A5074481485 @default.
- W4220896502 creator A5081917774 @default.
- W4220896502 creator A5088302108 @default.
- W4220896502 date "2022-09-01" @default.
- W4220896502 modified "2023-10-16" @default.
- W4220896502 title "PDBL: Improving Histopathological Tissue Classification With Plug-and-Play Pyramidal Deep-Broad Learning" @default.
- W4220896502 cites W2108598243 @default.
- W4220896502 cites W2194775991 @default.
- W4220896502 cites W2302302587 @default.
- W4220896502 cites W2566365295 @default.
- W4220896502 cites W2618999197 @default.
- W4220896502 cites W2716665989 @default.
- W4220896502 cites W2738226240 @default.
- W4220896502 cites W2760946358 @default.
- W4220896502 cites W2883567318 @default.
- W4220896502 cites W2883780447 @default.
- W4220896502 cites W2887576641 @default.
- W4220896502 cites W2888109343 @default.
- W4220896502 cites W2890126432 @default.
- W4220896502 cites W2890706287 @default.
- W4220896502 cites W2914568698 @default.
- W4220896502 cites W2916845318 @default.
- W4220896502 cites W2948930564 @default.
- W4220896502 cites W2956228567 @default.
- W4220896502 cites W2963125010 @default.
- W4220896502 cites W2964350391 @default.
- W4220896502 cites W2971045153 @default.
- W4220896502 cites W2978575375 @default.
- W4220896502 cites W2998401461 @default.
- W4220896502 cites W3007943565 @default.
- W4220896502 cites W3027869849 @default.
- W4220896502 cites W3043835773 @default.
- W4220896502 cites W3089090082 @default.
- W4220896502 cites W3090043060 @default.
- W4220896502 cites W3092124539 @default.
- W4220896502 cites W3094977690 @default.
- W4220896502 cites W3126827997 @default.
- W4220896502 cites W3135345798 @default.
- W4220896502 cites W3142507299 @default.
- W4220896502 cites W3152926200 @default.
- W4220896502 cites W3159302505 @default.
- W4220896502 cites W3182999054 @default.
- W4220896502 cites W2979835189 @default.
- W4220896502 doi "https://doi.org/10.1109/tmi.2022.3161787" @default.
- W4220896502 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35320093" @default.
- W4220896502 hasPublicationYear "2022" @default.
- W4220896502 type Work @default.
- W4220896502 citedByCount "13" @default.
- W4220896502 countsByYear W42208965022022 @default.
- W4220896502 countsByYear W42208965022023 @default.
- W4220896502 crossrefType "journal-article" @default.
- W4220896502 hasAuthorship W4220896502A5001198279 @default.
- W4220896502 hasAuthorship W4220896502A5003926160 @default.
- W4220896502 hasAuthorship W4220896502A5004657494 @default.
- W4220896502 hasAuthorship W4220896502A5007122542 @default.
- W4220896502 hasAuthorship W4220896502A5007767807 @default.
- W4220896502 hasAuthorship W4220896502A5016655901 @default.
- W4220896502 hasAuthorship W4220896502A5018863416 @default.
- W4220896502 hasAuthorship W4220896502A5020316684 @default.
- W4220896502 hasAuthorship W4220896502A5028311940 @default.
- W4220896502 hasAuthorship W4220896502A5035896421 @default.
- W4220896502 hasAuthorship W4220896502A5046771717 @default.
- W4220896502 hasAuthorship W4220896502A5065451819 @default.
- W4220896502 hasAuthorship W4220896502A5074481485 @default.
- W4220896502 hasAuthorship W4220896502A5081917774 @default.
- W4220896502 hasAuthorship W4220896502A5088302108 @default.
- W4220896502 hasBestOaLocation W42208965021 @default.
- W4220896502 hasConcept C108583219 @default.
- W4220896502 hasConcept C111919701 @default.
- W4220896502 hasConcept C115961682 @default.
- W4220896502 hasConcept C120665830 @default.
- W4220896502 hasConcept C121332964 @default.
- W4220896502 hasConcept C12267149 @default.
- W4220896502 hasConcept C123860398 @default.
- W4220896502 hasConcept C142575187 @default.
- W4220896502 hasConcept C153083717 @default.
- W4220896502 hasConcept C153180895 @default.
- W4220896502 hasConcept C154945302 @default.
- W4220896502 hasConcept C160633673 @default.
- W4220896502 hasConcept C2524010 @default.
- W4220896502 hasConcept C2776321320 @default.
- W4220896502 hasConcept C2777210771 @default.
- W4220896502 hasConcept C33923547 @default.
- W4220896502 hasConcept C41008148 @default.