Internal connectivity of a standard LSTM cell.
<div><p>Among the most common cancers, colorectal cancer (CRC) has a high death rate. The best way to screen for colorectal cancer (CRC) is with a colonoscopy, which has been shown to lower the risk of the disease. As a result, Computer-aided polyp classification technique is applied to...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , |
| Published: |
2024
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852026002835767296 |
|---|---|
| author | Jun Tan (46388) |
| author2 | Jiamin Yuan (10353958) Xiaoyong Fu (482754) Yilin Bai (13929663) |
| author2_role | author author author |
| author_facet | Jun Tan (46388) Jiamin Yuan (10353958) Xiaoyong Fu (482754) Yilin Bai (13929663) |
| author_role | author |
| dc.creator.none.fl_str_mv | Jun Tan (46388) Jiamin Yuan (10353958) Xiaoyong Fu (482754) Yilin Bai (13929663) |
| dc.date.none.fl_str_mv | 2024-10-11T17:22:55Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0302800.g005 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Internal_connectivity_of_a_standard_LSTM_cell_/27212597 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Biotechnology Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> among high death rate experimental results demonstrate scattering wavelet transform polyp classification technique correct classification rates visually categorizing polyps effectively classify polyps class polyp classification class experiment reached two public datasets scattering wavelet filters identify colorectal cancer end models based different lighting conditions commonly used cnns art cnn models proposed eswcnn method class classification wavelet filters proposed method colorectal cancer validation experiment six end designed based learnable filters classification accuracy video sequences various scales serrated polyps provide guidance previous works network architecture negative ). input channel hyperplastic polyps future research fold cross eswcnn ), efficacy compared common cancers best way average sensitivity 4 %, |
| dc.title.none.fl_str_mv | Internal connectivity of a standard LSTM cell. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Among the most common cancers, colorectal cancer (CRC) has a high death rate. The best way to screen for colorectal cancer (CRC) is with a colonoscopy, which has been shown to lower the risk of the disease. As a result, Computer-aided polyp classification technique is applied to identify colorectal cancer. But visually categorizing polyps is difficult since different polyps have different lighting conditions. Different from previous works, this article presents Enhanced Scattering Wavelet Convolutional Neural Network (ESWCNN), a polyp classification technique that combines Convolutional Neural Network (CNN) and Scattering Wavelet Transform (SWT) to improve polyp classification performance. This method concatenates simultaneously learnable image filters and wavelet filters on each input channel. The scattering wavelet filters can extract common spectral features with various scales and orientations, while the learnable filters can capture image spatial features that wavelet filters may miss. A network architecture for ESWCNN is designed based on these principles and trained and tested using colonoscopy datasets (two public datasets and one private dataset). An n-fold cross-validation experiment was conducted for three classes (adenoma, hyperplastic, serrated) achieving a classification accuracy of 96.4%, and 94.8% accuracy in two-class polyp classification (positive and negative). In the three-class classification, correct classification rates of 96.2% for adenomas, 98.71% for hyperplastic polyps, and 97.9% for serrated polyps were achieved. The proposed method in the two-class experiment reached an average sensitivity of 96.7% with 93.1% specificity. Furthermore, we compare the performance of our model with the state-of-the-art general classification models and commonly used CNNs. Six end-to-end models based on CNNs were trained using 2 dataset of video sequences. The experimental results demonstrate that the proposed ESWCNN method can effectively classify polyps with higher accuracy and efficacy compared to the state-of-the-art CNN models. These findings can provide guidance for future research in polyp classification.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_1e8ee7d6d54a2b3fcef00a3a2b070989 |
| identifier_str_mv | 10.1371/journal.pone.0302800.g005 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/27212597 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Internal connectivity of a standard LSTM cell.Jun Tan (46388)Jiamin Yuan (10353958)Xiaoyong Fu (482754)Yilin Bai (13929663)BiotechnologyCancerSpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedxlink "> amonghigh death rateexperimental results demonstratescattering wavelet transformpolyp classification techniquecorrect classification ratesvisually categorizing polypseffectively classify polypsclass polyp classificationclass experiment reachedtwo public datasetsscattering wavelet filtersidentify colorectal cancerend models baseddifferent lighting conditionscommonly used cnnsart cnn modelsproposed eswcnn methodclass classificationwavelet filtersproposed methodcolorectal cancervalidation experimentsix enddesigned basedlearnable filtersclassification accuracyvideo sequencesvarious scalesserrated polypsprovide guidanceprevious worksnetwork architecturenegative ).input channelhyperplastic polypsfuture researchfold crosseswcnn ),efficacy comparedcommon cancersbest wayaverage sensitivity4 %,<div><p>Among the most common cancers, colorectal cancer (CRC) has a high death rate. The best way to screen for colorectal cancer (CRC) is with a colonoscopy, which has been shown to lower the risk of the disease. As a result, Computer-aided polyp classification technique is applied to identify colorectal cancer. But visually categorizing polyps is difficult since different polyps have different lighting conditions. Different from previous works, this article presents Enhanced Scattering Wavelet Convolutional Neural Network (ESWCNN), a polyp classification technique that combines Convolutional Neural Network (CNN) and Scattering Wavelet Transform (SWT) to improve polyp classification performance. This method concatenates simultaneously learnable image filters and wavelet filters on each input channel. The scattering wavelet filters can extract common spectral features with various scales and orientations, while the learnable filters can capture image spatial features that wavelet filters may miss. A network architecture for ESWCNN is designed based on these principles and trained and tested using colonoscopy datasets (two public datasets and one private dataset). An n-fold cross-validation experiment was conducted for three classes (adenoma, hyperplastic, serrated) achieving a classification accuracy of 96.4%, and 94.8% accuracy in two-class polyp classification (positive and negative). In the three-class classification, correct classification rates of 96.2% for adenomas, 98.71% for hyperplastic polyps, and 97.9% for serrated polyps were achieved. The proposed method in the two-class experiment reached an average sensitivity of 96.7% with 93.1% specificity. Furthermore, we compare the performance of our model with the state-of-the-art general classification models and commonly used CNNs. Six end-to-end models based on CNNs were trained using 2 dataset of video sequences. The experimental results demonstrate that the proposed ESWCNN method can effectively classify polyps with higher accuracy and efficacy compared to the state-of-the-art CNN models. These findings can provide guidance for future research in polyp classification.</p></div>2024-10-11T17:22:55ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0302800.g005https://figshare.com/articles/figure/Internal_connectivity_of_a_standard_LSTM_cell_/27212597CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/272125972024-10-11T17:22:55Z |
| spellingShingle | Internal connectivity of a standard LSTM cell. Jun Tan (46388) Biotechnology Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> among high death rate experimental results demonstrate scattering wavelet transform polyp classification technique correct classification rates visually categorizing polyps effectively classify polyps class polyp classification class experiment reached two public datasets scattering wavelet filters identify colorectal cancer end models based different lighting conditions commonly used cnns art cnn models proposed eswcnn method class classification wavelet filters proposed method colorectal cancer validation experiment six end designed based learnable filters classification accuracy video sequences various scales serrated polyps provide guidance previous works network architecture negative ). input channel hyperplastic polyps future research fold cross eswcnn ), efficacy compared common cancers best way average sensitivity 4 %, |
| status_str | publishedVersion |
| title | Internal connectivity of a standard LSTM cell. |
| title_full | Internal connectivity of a standard LSTM cell. |
| title_fullStr | Internal connectivity of a standard LSTM cell. |
| title_full_unstemmed | Internal connectivity of a standard LSTM cell. |
| title_short | Internal connectivity of a standard LSTM cell. |
| title_sort | Internal connectivity of a standard LSTM cell. |
| topic | Biotechnology Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> among high death rate experimental results demonstrate scattering wavelet transform polyp classification technique correct classification rates visually categorizing polyps effectively classify polyps class polyp classification class experiment reached two public datasets scattering wavelet filters identify colorectal cancer end models based different lighting conditions commonly used cnns art cnn models proposed eswcnn method class classification wavelet filters proposed method colorectal cancer validation experiment six end designed based learnable filters classification accuracy video sequences various scales serrated polyps provide guidance previous works network architecture negative ). input channel hyperplastic polyps future research fold cross eswcnn ), efficacy compared common cancers best way average sensitivity 4 %, |