A Deep Learning Convolutional Neural Network Can Recognize Common Patterns of Injury in Gastric Pathology
Most deep learning (DL) studies have focused on neoplastic pathology, with the realm of inflammatory pathology remaining largely untouched. To investigate the use of DL for nonneoplastic gastric biopsies. Gold standard diagnoses were blindly established by 2 gastrointestinal pathologists. For phase...
Gespeichert in:
| Veröffentlicht in: | Archives of pathology & laboratory medicine (1976) 2020-03, Vol.144 (3), p.370-378 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 378 |
|---|---|
| container_issue | 3 |
| container_start_page | 370 |
| container_title | Archives of pathology & laboratory medicine (1976) |
| container_volume | 144 |
| creator | Martin, David R Hanson, Joshua A Gullapalli, Rama R Schultz, Fred A Sethi, Aisha Clark, Douglas P |
| description | Most deep learning (DL) studies have focused on neoplastic pathology, with the realm of inflammatory pathology remaining largely untouched.
To investigate the use of DL for nonneoplastic gastric biopsies.
Gold standard diagnoses were blindly established by 2 gastrointestinal pathologists. For phase 1, 300 classic cases (100 normal, 100
, 100 reactive gastropathy) that best displayed the desired pathology were scanned and annotated for DL analysis. A total of 70% of the cases for each group were selected for the training set, and 30% were included in the test set. The software assigned colored labels to the test biopsies, which corresponded to the area of the tissue assigned a diagnosis by the DL algorithm, termed area distribution (AD). For Phase 2, an additional 106 consecutive nonclassical gastric biopsies from our archives were tested in the same fashion.
For Phase 1, receiver operating curves showed near perfect agreement with the gold standard diagnoses at an AD percentage cutoff of 50% for normal (area under the curve [AUC] = 99.7%) and
(AUC = 100%), and 40% for reactive gastropathy (AUC = 99.9%). Sensitivity/specificity pairings were as follows: normal (96.7%, 86.7%),
(100%, 98.3%), and reactive gastropathy (96.7%, 96.7%). For phase 2, receiver operating curves were slightly less discriminatory, with optimal AD cutoffs reduced to 40% across diagnostic groups. The AUCs were 91.9% for normal, 100% for
, and 94.0% for reactive gastropathy. Sensitivity/specificity parings were as follows: normal (73.7%, 79.6%),
(95.7%, 100%), reactive gastropathy (100%, 62.5%).
A convolutional neural network can serve as an effective screening tool/diagnostic aid for
gastritis. |
| doi_str_mv | 10.5858/arpa.2019-0004-OA |
| format | Article |
| fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_miscellaneous_2248380875</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A619399313</galeid><sourcerecordid>A619399313</sourcerecordid><originalsourceid>FETCH-LOGICAL-c469t-ec6bd77e3cdf2bc44b9d8002ab18444f2a7565ef77352ca3cbb4159d6396e5e93</originalsourceid><addsrcrecordid>eNpdkU2P0zAQhi0EYsvCD-CCLCGhvWTxd-xjVNhlpYoiBGfLcSZtSmIXOwGVX09CCwdOI9vPO5rxg9BLSm6llvqtS0d3ywg1BSFEFNvqEVpRKXjBqJKP0Wq-5YUxWl6hZzkf5qNhjD5FV5wyoShlK9RV-B3AEW_ApdCFHV7H8CP209jF4Hr8Eab0p4w_Y_qG1y7gz-DjLnS_YEaHIQb8yY0jpJBxbPFDOEzphLuA710eU-eX133s4-70HD1pXZ_hxaVeo69377-sPxSb7f3DutoUXigzFuBV3ZQlcN-0rPZC1KbRhDBXUy2EaJkrpZLQliWXzDvu61pQaRrFjQIJhl-jm3PfY4rfJ8ijHbrsoe9dgDhly5jQXBNdyhl9_R96iFOa954pXpbKGKKXhm_O1M71YPfg-nGfL1-UbaWo4cZwymeQnkGfYs4JWntM3eDSyVJiF2F2EWYXYXYRZrfVnHl1GWGqB2j-Jf4a4r8Bha6RWw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2377699089</pqid></control><display><type>article</type><title>A Deep Learning Convolutional Neural Network Can Recognize Common Patterns of Injury in Gastric Pathology</title><source>Allen Press Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Martin, David R ; Hanson, Joshua A ; Gullapalli, Rama R ; Schultz, Fred A ; Sethi, Aisha ; Clark, Douglas P</creator><creatorcontrib>Martin, David R ; Hanson, Joshua A ; Gullapalli, Rama R ; Schultz, Fred A ; Sethi, Aisha ; Clark, Douglas P</creatorcontrib><description>Most deep learning (DL) studies have focused on neoplastic pathology, with the realm of inflammatory pathology remaining largely untouched.
To investigate the use of DL for nonneoplastic gastric biopsies.
Gold standard diagnoses were blindly established by 2 gastrointestinal pathologists. For phase 1, 300 classic cases (100 normal, 100
, 100 reactive gastropathy) that best displayed the desired pathology were scanned and annotated for DL analysis. A total of 70% of the cases for each group were selected for the training set, and 30% were included in the test set. The software assigned colored labels to the test biopsies, which corresponded to the area of the tissue assigned a diagnosis by the DL algorithm, termed area distribution (AD). For Phase 2, an additional 106 consecutive nonclassical gastric biopsies from our archives were tested in the same fashion.
For Phase 1, receiver operating curves showed near perfect agreement with the gold standard diagnoses at an AD percentage cutoff of 50% for normal (area under the curve [AUC] = 99.7%) and
(AUC = 100%), and 40% for reactive gastropathy (AUC = 99.9%). Sensitivity/specificity pairings were as follows: normal (96.7%, 86.7%),
(100%, 98.3%), and reactive gastropathy (96.7%, 96.7%). For phase 2, receiver operating curves were slightly less discriminatory, with optimal AD cutoffs reduced to 40% across diagnostic groups. The AUCs were 91.9% for normal, 100% for
, and 94.0% for reactive gastropathy. Sensitivity/specificity parings were as follows: normal (73.7%, 79.6%),
(95.7%, 100%), reactive gastropathy (100%, 62.5%).
A convolutional neural network can serve as an effective screening tool/diagnostic aid for
gastritis.</description><identifier>ISSN: 0003-9985</identifier><identifier>ISSN: 1543-2165</identifier><identifier>EISSN: 1543-2165</identifier><identifier>DOI: 10.5858/arpa.2019-0004-OA</identifier><identifier>PMID: 31246112</identifier><language>eng</language><publisher>United States: College of American Pathologists</publisher><subject>Algorithms ; Analysis ; Anti-inflammatory agents ; Artificial neural networks ; Bile ; Breast ; Cable television broadcasting industry ; Chronic infection ; Data processing ; Deep learning ; Drug abuse ; Edema ; Epidermal growth factor ; Epithelium ; ErbB-2 protein ; Estrogen receptors ; Ethanol ; Gastritis ; Germinal centers ; Helicobacter pylori ; Hyperplasia ; Inflammation ; International economic relations ; Lamina propria ; Leukocytes (neutrophilic) ; Lymph nodes ; Lymphatic system ; Medical research ; Metastases ; Metastasis ; Mitosis ; Mucin ; Mucosa ; Neoplasia ; Neural networks ; Nonsteroidal anti-inflammatory drugs ; Organisms ; Pathology ; Progesterone ; Regeneration ; Smooth muscle ; Software ; Training ; Ulcers</subject><ispartof>Archives of pathology & laboratory medicine (1976), 2020-03, Vol.144 (3), p.370-378</ispartof><rights>COPYRIGHT 2020 College of American Pathologists</rights><rights>Copyright College of American Pathologists Mar 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c469t-ec6bd77e3cdf2bc44b9d8002ab18444f2a7565ef77352ca3cbb4159d6396e5e93</citedby><cites>FETCH-LOGICAL-c469t-ec6bd77e3cdf2bc44b9d8002ab18444f2a7565ef77352ca3cbb4159d6396e5e93</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31246112$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Martin, David R</creatorcontrib><creatorcontrib>Hanson, Joshua A</creatorcontrib><creatorcontrib>Gullapalli, Rama R</creatorcontrib><creatorcontrib>Schultz, Fred A</creatorcontrib><creatorcontrib>Sethi, Aisha</creatorcontrib><creatorcontrib>Clark, Douglas P</creatorcontrib><title>A Deep Learning Convolutional Neural Network Can Recognize Common Patterns of Injury in Gastric Pathology</title><title>Archives of pathology & laboratory medicine (1976)</title><addtitle>Arch Pathol Lab Med</addtitle><description>Most deep learning (DL) studies have focused on neoplastic pathology, with the realm of inflammatory pathology remaining largely untouched.
To investigate the use of DL for nonneoplastic gastric biopsies.
Gold standard diagnoses were blindly established by 2 gastrointestinal pathologists. For phase 1, 300 classic cases (100 normal, 100
, 100 reactive gastropathy) that best displayed the desired pathology were scanned and annotated for DL analysis. A total of 70% of the cases for each group were selected for the training set, and 30% were included in the test set. The software assigned colored labels to the test biopsies, which corresponded to the area of the tissue assigned a diagnosis by the DL algorithm, termed area distribution (AD). For Phase 2, an additional 106 consecutive nonclassical gastric biopsies from our archives were tested in the same fashion.
For Phase 1, receiver operating curves showed near perfect agreement with the gold standard diagnoses at an AD percentage cutoff of 50% for normal (area under the curve [AUC] = 99.7%) and
(AUC = 100%), and 40% for reactive gastropathy (AUC = 99.9%). Sensitivity/specificity pairings were as follows: normal (96.7%, 86.7%),
(100%, 98.3%), and reactive gastropathy (96.7%, 96.7%). For phase 2, receiver operating curves were slightly less discriminatory, with optimal AD cutoffs reduced to 40% across diagnostic groups. The AUCs were 91.9% for normal, 100% for
, and 94.0% for reactive gastropathy. Sensitivity/specificity parings were as follows: normal (73.7%, 79.6%),
(95.7%, 100%), reactive gastropathy (100%, 62.5%).
A convolutional neural network can serve as an effective screening tool/diagnostic aid for
gastritis.</description><subject>Algorithms</subject><subject>Analysis</subject><subject>Anti-inflammatory agents</subject><subject>Artificial neural networks</subject><subject>Bile</subject><subject>Breast</subject><subject>Cable television broadcasting industry</subject><subject>Chronic infection</subject><subject>Data processing</subject><subject>Deep learning</subject><subject>Drug abuse</subject><subject>Edema</subject><subject>Epidermal growth factor</subject><subject>Epithelium</subject><subject>ErbB-2 protein</subject><subject>Estrogen receptors</subject><subject>Ethanol</subject><subject>Gastritis</subject><subject>Germinal centers</subject><subject>Helicobacter pylori</subject><subject>Hyperplasia</subject><subject>Inflammation</subject><subject>International economic relations</subject><subject>Lamina propria</subject><subject>Leukocytes (neutrophilic)</subject><subject>Lymph nodes</subject><subject>Lymphatic system</subject><subject>Medical research</subject><subject>Metastases</subject><subject>Metastasis</subject><subject>Mitosis</subject><subject>Mucin</subject><subject>Mucosa</subject><subject>Neoplasia</subject><subject>Neural networks</subject><subject>Nonsteroidal anti-inflammatory drugs</subject><subject>Organisms</subject><subject>Pathology</subject><subject>Progesterone</subject><subject>Regeneration</subject><subject>Smooth muscle</subject><subject>Software</subject><subject>Training</subject><subject>Ulcers</subject><issn>0003-9985</issn><issn>1543-2165</issn><issn>1543-2165</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpdkU2P0zAQhi0EYsvCD-CCLCGhvWTxd-xjVNhlpYoiBGfLcSZtSmIXOwGVX09CCwdOI9vPO5rxg9BLSm6llvqtS0d3ywg1BSFEFNvqEVpRKXjBqJKP0Wq-5YUxWl6hZzkf5qNhjD5FV5wyoShlK9RV-B3AEW_ApdCFHV7H8CP209jF4Hr8Eab0p4w_Y_qG1y7gz-DjLnS_YEaHIQb8yY0jpJBxbPFDOEzphLuA710eU-eX133s4-70HD1pXZ_hxaVeo69377-sPxSb7f3DutoUXigzFuBV3ZQlcN-0rPZC1KbRhDBXUy2EaJkrpZLQliWXzDvu61pQaRrFjQIJhl-jm3PfY4rfJ8ijHbrsoe9dgDhly5jQXBNdyhl9_R96iFOa954pXpbKGKKXhm_O1M71YPfg-nGfL1-UbaWo4cZwymeQnkGfYs4JWntM3eDSyVJiF2F2EWYXYXYRZrfVnHl1GWGqB2j-Jf4a4r8Bha6RWw</recordid><startdate>20200301</startdate><enddate>20200301</enddate><creator>Martin, David R</creator><creator>Hanson, Joshua A</creator><creator>Gullapalli, Rama R</creator><creator>Schultz, Fred A</creator><creator>Sethi, Aisha</creator><creator>Clark, Douglas P</creator><general>College of American Pathologists</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>4T-</scope><scope>4U-</scope><scope>7RV</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>88I</scope><scope>8AF</scope><scope>8AO</scope><scope>8C1</scope><scope>8FE</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>K9.</scope><scope>KB0</scope><scope>LK8</scope><scope>M0S</scope><scope>M1P</scope><scope>M2P</scope><scope>M7P</scope><scope>NAPCQ</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7X8</scope></search><sort><creationdate>20200301</creationdate><title>A Deep Learning Convolutional Neural Network Can Recognize Common Patterns of Injury in Gastric Pathology</title><author>Martin, David R ; Hanson, Joshua A ; Gullapalli, Rama R ; Schultz, Fred A ; Sethi, Aisha ; Clark, Douglas P</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c469t-ec6bd77e3cdf2bc44b9d8002ab18444f2a7565ef77352ca3cbb4159d6396e5e93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Analysis</topic><topic>Anti-inflammatory agents</topic><topic>Artificial neural networks</topic><topic>Bile</topic><topic>Breast</topic><topic>Cable television broadcasting industry</topic><topic>Chronic infection</topic><topic>Data processing</topic><topic>Deep learning</topic><topic>Drug abuse</topic><topic>Edema</topic><topic>Epidermal growth factor</topic><topic>Epithelium</topic><topic>ErbB-2 protein</topic><topic>Estrogen receptors</topic><topic>Ethanol</topic><topic>Gastritis</topic><topic>Germinal centers</topic><topic>Helicobacter pylori</topic><topic>Hyperplasia</topic><topic>Inflammation</topic><topic>International economic relations</topic><topic>Lamina propria</topic><topic>Leukocytes (neutrophilic)</topic><topic>Lymph nodes</topic><topic>Lymphatic system</topic><topic>Medical research</topic><topic>Metastases</topic><topic>Metastasis</topic><topic>Mitosis</topic><topic>Mucin</topic><topic>Mucosa</topic><topic>Neoplasia</topic><topic>Neural networks</topic><topic>Nonsteroidal anti-inflammatory drugs</topic><topic>Organisms</topic><topic>Pathology</topic><topic>Progesterone</topic><topic>Regeneration</topic><topic>Smooth muscle</topic><topic>Software</topic><topic>Training</topic><topic>Ulcers</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Martin, David R</creatorcontrib><creatorcontrib>Hanson, Joshua A</creatorcontrib><creatorcontrib>Gullapalli, Rama R</creatorcontrib><creatorcontrib>Schultz, Fred A</creatorcontrib><creatorcontrib>Sethi, Aisha</creatorcontrib><creatorcontrib>Clark, Douglas P</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Docstoc</collection><collection>University Readers</collection><collection>Nursing & Allied Health Database</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Science Database (Alumni Edition)</collection><collection>STEM Database</collection><collection>ProQuest Pharma Collection</collection><collection>Public Health Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>ProQuest Biological Science Collection</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Science Database</collection><collection>Biological Science Database</collection><collection>Nursing & Allied Health Premium</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>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><jtitle>Archives of pathology & laboratory medicine (1976)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Martin, David R</au><au>Hanson, Joshua A</au><au>Gullapalli, Rama R</au><au>Schultz, Fred A</au><au>Sethi, Aisha</au><au>Clark, Douglas P</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Deep Learning Convolutional Neural Network Can Recognize Common Patterns of Injury in Gastric Pathology</atitle><jtitle>Archives of pathology & laboratory medicine (1976)</jtitle><addtitle>Arch Pathol Lab Med</addtitle><date>2020-03-01</date><risdate>2020</risdate><volume>144</volume><issue>3</issue><spage>370</spage><epage>378</epage><pages>370-378</pages><issn>0003-9985</issn><issn>1543-2165</issn><eissn>1543-2165</eissn><abstract>Most deep learning (DL) studies have focused on neoplastic pathology, with the realm of inflammatory pathology remaining largely untouched.
To investigate the use of DL for nonneoplastic gastric biopsies.
Gold standard diagnoses were blindly established by 2 gastrointestinal pathologists. For phase 1, 300 classic cases (100 normal, 100
, 100 reactive gastropathy) that best displayed the desired pathology were scanned and annotated for DL analysis. A total of 70% of the cases for each group were selected for the training set, and 30% were included in the test set. The software assigned colored labels to the test biopsies, which corresponded to the area of the tissue assigned a diagnosis by the DL algorithm, termed area distribution (AD). For Phase 2, an additional 106 consecutive nonclassical gastric biopsies from our archives were tested in the same fashion.
For Phase 1, receiver operating curves showed near perfect agreement with the gold standard diagnoses at an AD percentage cutoff of 50% for normal (area under the curve [AUC] = 99.7%) and
(AUC = 100%), and 40% for reactive gastropathy (AUC = 99.9%). Sensitivity/specificity pairings were as follows: normal (96.7%, 86.7%),
(100%, 98.3%), and reactive gastropathy (96.7%, 96.7%). For phase 2, receiver operating curves were slightly less discriminatory, with optimal AD cutoffs reduced to 40% across diagnostic groups. The AUCs were 91.9% for normal, 100% for
, and 94.0% for reactive gastropathy. Sensitivity/specificity parings were as follows: normal (73.7%, 79.6%),
(95.7%, 100%), reactive gastropathy (100%, 62.5%).
A convolutional neural network can serve as an effective screening tool/diagnostic aid for
gastritis.</abstract><cop>United States</cop><pub>College of American Pathologists</pub><pmid>31246112</pmid><doi>10.5858/arpa.2019-0004-OA</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0003-9985 |
| ispartof | Archives of pathology & laboratory medicine (1976), 2020-03, Vol.144 (3), p.370-378 |
| issn | 0003-9985 1543-2165 1543-2165 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2248380875 |
| source | Allen Press Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Algorithms Analysis Anti-inflammatory agents Artificial neural networks Bile Breast Cable television broadcasting industry Chronic infection Data processing Deep learning Drug abuse Edema Epidermal growth factor Epithelium ErbB-2 protein Estrogen receptors Ethanol Gastritis Germinal centers Helicobacter pylori Hyperplasia Inflammation International economic relations Lamina propria Leukocytes (neutrophilic) Lymph nodes Lymphatic system Medical research Metastases Metastasis Mitosis Mucin Mucosa Neoplasia Neural networks Nonsteroidal anti-inflammatory drugs Organisms Pathology Progesterone Regeneration Smooth muscle Software Training Ulcers |
| title | A Deep Learning Convolutional Neural Network Can Recognize Common Patterns of Injury in Gastric Pathology |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T20%3A54%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Deep%20Learning%20Convolutional%20Neural%20Network%20Can%20Recognize%20Common%20Patterns%20of%20Injury%20in%20Gastric%20Pathology&rft.jtitle=Archives%20of%20pathology%20&%20laboratory%20medicine%20(1976)&rft.au=Martin,%20David%20R&rft.date=2020-03-01&rft.volume=144&rft.issue=3&rft.spage=370&rft.epage=378&rft.pages=370-378&rft.issn=0003-9985&rft.eissn=1543-2165&rft_id=info:doi/10.5858/arpa.2019-0004-OA&rft_dat=%3Cgale_proqu%3EA619399313%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2377699089&rft_id=info:pmid/31246112&rft_galeid=A619399313&rfr_iscdi=true |