Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310421807> ?p ?o ?g. }
- W4310421807 abstract "Cell segmentation algorithms are commonly used to analyze large histologic images as they facilitate interpretation, but on the other hand they complicate hypothesis-free spatial analysis. Therefore, many applications train convolutional neural networks (CNNs) on high-resolution images that resolve individual cells instead, but their practical application is severely limited by computational resources. In this work, we propose and investigate an alternative spatial data representation based on cell segmentation data for direct training of CNNs.We introduce and analyze the properties of Cell2Grid, an algorithm that generates compact images from cell segmentation data by placing individual cells into a low-resolution grid and resolves possible cell conflicts. For evaluation, we present a case study on colorectal cancer relapse prediction using fluorescent multiplex immunohistochemistry images.We could generate Cell2Grid images at 5-μm resolution that were 100 times smaller than the original ones. Cell features, such as phenotype counts and nearest-neighbor cell distances, remain similar to those of original cell segmentation tables ( p<0.0001 ). These images could be directly fed to a CNN for predicting colon cancer relapse. Our experiments showed that test set error rate was reduced by 25% compared with CNNs trained on images rescaled to 5μm with bilinear interpolation. Compared with images at 1-μm resolution (bilinear rescaling), our method reduced CNN training time by 85%.Cell2Grid is an efficient spatial data representation algorithm that enables the use of conventional CNNs on cell segmentation data. Its cell-based representation additionally opens a door for simplified model interpretation and synthetic image generation." @default.
- W4310421807 created "2022-12-10" @default.
- W4310421807 creator A5011985941 @default.
- W4310421807 creator A5012530512 @default.
- W4310421807 creator A5060480108 @default.
- W4310421807 creator A5070873799 @default.
- W4310421807 creator A5074264567 @default.
- W4310421807 creator A5086003470 @default.
- W4310421807 date "2022-11-30" @default.
- W4310421807 modified "2023-10-18" @default.
- W4310421807 title "Cell2Grid: an efficient, spatial, and convolutional neural network-ready representation of cell segmentation data" @default.
- W4310421807 cites W1437485837 @default.
- W4310421807 cites W1513879401 @default.
- W4310421807 cites W1818937361 @default.
- W4310421807 cites W1859257957 @default.
- W4310421807 cites W1915485278 @default.
- W4310421807 cites W1975675300 @default.
- W4310421807 cites W2079428324 @default.
- W4310421807 cites W2097117768 @default.
- W4310421807 cites W2108598243 @default.
- W4310421807 cites W211081217 @default.
- W4310421807 cites W2113275188 @default.
- W4310421807 cites W2117539524 @default.
- W4310421807 cites W2124833977 @default.
- W4310421807 cites W2126563020 @default.
- W4310421807 cites W2141461755 @default.
- W4310421807 cites W2163318198 @default.
- W4310421807 cites W2194775991 @default.
- W4310421807 cites W2222512263 @default.
- W4310421807 cites W2282915343 @default.
- W4310421807 cites W2301536592 @default.
- W4310421807 cites W2302302587 @default.
- W4310421807 cites W2580035316 @default.
- W4310421807 cites W2743344672 @default.
- W4310421807 cites W2761668583 @default.
- W4310421807 cites W2764024122 @default.
- W4310421807 cites W2802206159 @default.
- W4310421807 cites W2809376948 @default.
- W4310421807 cites W2811106513 @default.
- W4310421807 cites W2885650974 @default.
- W4310421807 cites W2889232360 @default.
- W4310421807 cites W2897118246 @default.
- W4310421807 cites W2898557814 @default.
- W4310421807 cites W2907564726 @default.
- W4310421807 cites W2914568698 @default.
- W4310421807 cites W2918927577 @default.
- W4310421807 cites W2922204263 @default.
- W4310421807 cites W2922268597 @default.
- W4310421807 cites W2922475342 @default.
- W4310421807 cites W2949648625 @default.
- W4310421807 cites W2961686530 @default.
- W4310421807 cites W2964282006 @default.
- W4310421807 cites W2970985632 @default.
- W4310421807 cites W2971714046 @default.
- W4310421807 cites W2972621596 @default.
- W4310421807 cites W2974825848 @default.
- W4310421807 cites W2988856610 @default.
- W4310421807 cites W2991497437 @default.
- W4310421807 cites W3008837427 @default.
- W4310421807 cites W3017374234 @default.
- W4310421807 cites W3046129945 @default.
- W4310421807 cites W3046154346 @default.
- W4310421807 cites W3047081808 @default.
- W4310421807 cites W3082098720 @default.
- W4310421807 cites W3083976124 @default.
- W4310421807 cites W3084379634 @default.
- W4310421807 cites W3133161980 @default.
- W4310421807 cites W3133839297 @default.
- W4310421807 cites W3135547872 @default.
- W4310421807 cites W3152893301 @default.
- W4310421807 cites W3156579229 @default.
- W4310421807 cites W3157112321 @default.
- W4310421807 cites W3160261825 @default.
- W4310421807 cites W3175191608 @default.
- W4310421807 cites W3179262290 @default.
- W4310421807 cites W3201612301 @default.
- W4310421807 cites W3203838058 @default.
- W4310421807 cites W3214596602 @default.
- W4310421807 cites W4205091810 @default.
- W4310421807 cites W4220748891 @default.
- W4310421807 cites W4223903727 @default.
- W4310421807 cites W621251951 @default.
- W4310421807 doi "https://doi.org/10.1117/1.jmi.9.6.067501" @default.
- W4310421807 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36466076" @default.
- W4310421807 hasPublicationYear "2022" @default.
- W4310421807 type Work @default.
- W4310421807 citedByCount "0" @default.
- W4310421807 crossrefType "journal-article" @default.
- W4310421807 hasAuthorship W4310421807A5011985941 @default.
- W4310421807 hasAuthorship W4310421807A5012530512 @default.
- W4310421807 hasAuthorship W4310421807A5060480108 @default.
- W4310421807 hasAuthorship W4310421807A5070873799 @default.
- W4310421807 hasAuthorship W4310421807A5074264567 @default.
- W4310421807 hasAuthorship W4310421807A5086003470 @default.
- W4310421807 hasBestOaLocation W43104218071 @default.
- W4310421807 hasConcept C124504099 @default.
- W4310421807 hasConcept C153180895 @default.
- W4310421807 hasConcept C154945302 @default.
- W4310421807 hasConcept C17744445 @default.
- W4310421807 hasConcept C199539241 @default.