Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey
Convolutional Neural Networks (CNNs) intrinsically requires large-scale data whereas Chest X-Ray (CXR) images tend to be data/annotation-scarce, leading to over-fitting. Therefore, based on our development experience and related work, this paper thoroughly introduces tricks to improve generalization...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2021-06 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Han, Changhee Okamoto, Takayuki Takeuchi, Koichi Katsios, Dimitris Grushnikov, Andrey Kobayashi, Masaaki Choppin, Antoine Kurashina, Yutaka Shimahara, Yuki |
| description | Convolutional Neural Networks (CNNs) intrinsically requires large-scale data whereas Chest X-Ray (CXR) images tend to be data/annotation-scarce, leading to over-fitting. Therefore, based on our development experience and related work, this paper thoroughly introduces tricks to improve generalization in the CXR diagnosis: how to (i) leverage additional data, (ii) augment/distillate data, (iii) regularize training, and (iv) conduct efficient segmentation. As a development example based on such optimization techniques, we also feature LPIXEL's CNN-based CXR solution, EIRL Chest Nodule, which improved radiologists/non-radiologists' nodule detection sensitivity by 0.100/0.131, respectively, while maintaining specificity. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2536671342</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2536671342</sourcerecordid><originalsourceid>FETCH-proquest_journals_25366713423</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwCcksKFZIzEtRCCnKTM4uVijJV_DMLSjKL0tVcPbz001KLE5NUXDOSC0uUYjQLUqsVHDJTEzPyy_OLLZScFQILi0qS63kYWBNS8wpTuWF0twMym6uIc4eukBzCkuBWuOz8kuL8oBS8UamxmZm5obGJkbGxKkCAGlxONw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2536671342</pqid></control><display><type>article</type><title>Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey</title><source>Freely Accessible Journals</source><creator>Han, Changhee ; Okamoto, Takayuki ; Takeuchi, Koichi ; Katsios, Dimitris ; Grushnikov, Andrey ; Kobayashi, Masaaki ; Choppin, Antoine ; Kurashina, Yutaka ; Shimahara, Yuki</creator><creatorcontrib>Han, Changhee ; Okamoto, Takayuki ; Takeuchi, Koichi ; Katsios, Dimitris ; Grushnikov, Andrey ; Kobayashi, Masaaki ; Choppin, Antoine ; Kurashina, Yutaka ; Shimahara, Yuki</creatorcontrib><description>Convolutional Neural Networks (CNNs) intrinsically requires large-scale data whereas Chest X-Ray (CXR) images tend to be data/annotation-scarce, leading to over-fitting. Therefore, based on our development experience and related work, this paper thoroughly introduces tricks to improve generalization in the CXR diagnosis: how to (i) leverage additional data, (ii) augment/distillate data, (iii) regularize training, and (iv) conduct efficient segmentation. As a development example based on such optimization techniques, we also feature LPIXEL's CNN-based CXR solution, EIRL Chest Nodule, which improved radiologists/non-radiologists' nodule detection sensitivity by 0.100/0.131, respectively, while maintaining specificity.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Annotations ; Artificial neural networks ; Chest ; Diagnosis ; Image segmentation ; Optimization ; Optimization techniques</subject><ispartof>arXiv.org, 2021-06</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Han, Changhee</creatorcontrib><creatorcontrib>Okamoto, Takayuki</creatorcontrib><creatorcontrib>Takeuchi, Koichi</creatorcontrib><creatorcontrib>Katsios, Dimitris</creatorcontrib><creatorcontrib>Grushnikov, Andrey</creatorcontrib><creatorcontrib>Kobayashi, Masaaki</creatorcontrib><creatorcontrib>Choppin, Antoine</creatorcontrib><creatorcontrib>Kurashina, Yutaka</creatorcontrib><creatorcontrib>Shimahara, Yuki</creatorcontrib><title>Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey</title><title>arXiv.org</title><description>Convolutional Neural Networks (CNNs) intrinsically requires large-scale data whereas Chest X-Ray (CXR) images tend to be data/annotation-scarce, leading to over-fitting. Therefore, based on our development experience and related work, this paper thoroughly introduces tricks to improve generalization in the CXR diagnosis: how to (i) leverage additional data, (ii) augment/distillate data, (iii) regularize training, and (iv) conduct efficient segmentation. As a development example based on such optimization techniques, we also feature LPIXEL's CNN-based CXR solution, EIRL Chest Nodule, which improved radiologists/non-radiologists' nodule detection sensitivity by 0.100/0.131, respectively, while maintaining specificity.</description><subject>Annotations</subject><subject>Artificial neural networks</subject><subject>Chest</subject><subject>Diagnosis</subject><subject>Image segmentation</subject><subject>Optimization</subject><subject>Optimization techniques</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwCcksKFZIzEtRCCnKTM4uVijJV_DMLSjKL0tVcPbz001KLE5NUXDOSC0uUYjQLUqsVHDJTEzPyy_OLLZScFQILi0qS63kYWBNS8wpTuWF0twMym6uIc4eukBzCkuBWuOz8kuL8oBS8UamxmZm5obGJkbGxKkCAGlxONw</recordid><startdate>20210602</startdate><enddate>20210602</enddate><creator>Han, Changhee</creator><creator>Okamoto, Takayuki</creator><creator>Takeuchi, Koichi</creator><creator>Katsios, Dimitris</creator><creator>Grushnikov, Andrey</creator><creator>Kobayashi, Masaaki</creator><creator>Choppin, Antoine</creator><creator>Kurashina, Yutaka</creator><creator>Shimahara, Yuki</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210602</creationdate><title>Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey</title><author>Han, Changhee ; Okamoto, Takayuki ; Takeuchi, Koichi ; Katsios, Dimitris ; Grushnikov, Andrey ; Kobayashi, Masaaki ; Choppin, Antoine ; Kurashina, Yutaka ; Shimahara, Yuki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25366713423</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Annotations</topic><topic>Artificial neural networks</topic><topic>Chest</topic><topic>Diagnosis</topic><topic>Image segmentation</topic><topic>Optimization</topic><topic>Optimization techniques</topic><toplevel>online_resources</toplevel><creatorcontrib>Han, Changhee</creatorcontrib><creatorcontrib>Okamoto, Takayuki</creatorcontrib><creatorcontrib>Takeuchi, Koichi</creatorcontrib><creatorcontrib>Katsios, Dimitris</creatorcontrib><creatorcontrib>Grushnikov, Andrey</creatorcontrib><creatorcontrib>Kobayashi, Masaaki</creatorcontrib><creatorcontrib>Choppin, Antoine</creatorcontrib><creatorcontrib>Kurashina, Yutaka</creatorcontrib><creatorcontrib>Shimahara, Yuki</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Han, Changhee</au><au>Okamoto, Takayuki</au><au>Takeuchi, Koichi</au><au>Katsios, Dimitris</au><au>Grushnikov, Andrey</au><au>Kobayashi, Masaaki</au><au>Choppin, Antoine</au><au>Kurashina, Yutaka</au><au>Shimahara, Yuki</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey</atitle><jtitle>arXiv.org</jtitle><date>2021-06-02</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>Convolutional Neural Networks (CNNs) intrinsically requires large-scale data whereas Chest X-Ray (CXR) images tend to be data/annotation-scarce, leading to over-fitting. Therefore, based on our development experience and related work, this paper thoroughly introduces tricks to improve generalization in the CXR diagnosis: how to (i) leverage additional data, (ii) augment/distillate data, (iii) regularize training, and (iv) conduct efficient segmentation. As a development example based on such optimization techniques, we also feature LPIXEL's CNN-based CXR solution, EIRL Chest Nodule, which improved radiologists/non-radiologists' nodule detection sensitivity by 0.100/0.131, respectively, while maintaining specificity.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2021-06 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2536671342 |
| source | Freely Accessible Journals |
| subjects | Annotations Artificial neural networks Chest Diagnosis Image segmentation Optimization Optimization techniques |
| title | Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T07%3A40%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Tips%20and%20Tricks%20to%20Improve%20CNN-based%20Chest%20X-ray%20Diagnosis:%20A%20Survey&rft.jtitle=arXiv.org&rft.au=Han,%20Changhee&rft.date=2021-06-02&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2536671342%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2536671342&rft_id=info:pmid/&rfr_iscdi=true |