Deep Learning Model Based on Multisequence MRI Images for Assessing Adverse Pregnancy Outcome in Placenta Accreta
Background Preoperative assessment of adverse outcomes risk in placenta accreta spectrum (PAS) disorders is of high clinical relevance for perioperative management and prognosis. Purpose To investigate the association of preoperative MRI multisequence images and adverse pregnancy outcomes by establi...
Gespeichert in:
| Veröffentlicht in: | Journal of magnetic resonance imaging 2024-02, Vol.59 (2), p.510-521 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 521 |
|---|---|
| container_issue | 2 |
| container_start_page | 510 |
| container_title | Journal of magnetic resonance imaging |
| container_volume | 59 |
| creator | Zong, Ming Pei, Xinlong Yan, Kun Luo, Deng Zhao, Yangyu Wang, Ping Chen, Lian |
| description | Background
Preoperative assessment of adverse outcomes risk in placenta accreta spectrum (PAS) disorders is of high clinical relevance for perioperative management and prognosis.
Purpose
To investigate the association of preoperative MRI multisequence images and adverse pregnancy outcomes by establishing a deep learning model in patients with PAS.
Study Type
Retrospective.
Population
323 pregnant women (age from 20 to 46, the median age is 33), suspected of PAS, underwent MRI to assess the PAS, divided into the training (N = 227) and validation datasets (N = 96).
Field Strength/Sequence
1.5T scanner/fast imaging employing steady‐state acquisition sequence and single shot fast spin echo sequence.
Assessment
Different deep learning models (i.e., with single MRI input sequence/two sequences/multisequence) were compared to assess the risk of adverse pregnancy outcomes, which defined as intraoperative bleeding ≥1500 mL and/or hysterectomy. Net reclassification improvement (NRI) was used for quantitative comparison of assessing adverse pregnancy outcome between different models.
Statistical Tests
The AUC, sensitivity, specificity, and accuracy were used for evaluation. The Shapiro–Wilk test and t‐test were used. A P value of |
| doi_str_mv | 10.1002/jmri.29023 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2879407880</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2879407880</sourcerecordid><originalsourceid>FETCH-LOGICAL-c4113-4485bdaec43102f2453fb0ff0967a5c4aeb5fc7ac368ef042426065162323c3b3</originalsourceid><addsrcrecordid>eNp9kctu2zAQRYmiRfPc9AMKAt0UAZQMXxK1dF6NCxsJimZNUNTQkCFRDik18N9HrtMssuhqZnHmYGYuIV8YnDMAfrHuYnPOS-DiAzlkivOMK51_nHpQImMaigNylNIaAMpSqs_kQBRaMaXZIXm6RtzQBdoYmrCiy77Gll7ahDXtA12O7dAkfBoxOKTLX3M67-wKE_V9pLOUMKXd1Kz-gzEhfYi4Cja4Lb0fB9d3SJtAH1rrMAyWzpyLONgT8snbNuHpaz0mj7c3v6_ussX9j_nVbJE5yZjIpNSqqi06KRhwz6USvgLvocwLq5y0WCnvCutErtGD5JLnkCuWc8GFE5U4Jt_33k3spwPSYLomOWxbG7Afk-G6KCUUWsOEfnuHrvsxhmk7w0umQBdMFRN1tqdc7FOK6M0mNp2NW8PA7IIwuyDM3yAm-Ourcqw6rN_Qf5-fALYHnpsWt_9RmZ_T3_fSFz8SkfE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2915087157</pqid></control><display><type>article</type><title>Deep Learning Model Based on Multisequence MRI Images for Assessing Adverse Pregnancy Outcome in Placenta Accreta</title><source>Wiley Online Library Journals Frontfile Complete</source><creator>Zong, Ming ; Pei, Xinlong ; Yan, Kun ; Luo, Deng ; Zhao, Yangyu ; Wang, Ping ; Chen, Lian</creator><creatorcontrib>Zong, Ming ; Pei, Xinlong ; Yan, Kun ; Luo, Deng ; Zhao, Yangyu ; Wang, Ping ; Chen, Lian</creatorcontrib><description>Background
Preoperative assessment of adverse outcomes risk in placenta accreta spectrum (PAS) disorders is of high clinical relevance for perioperative management and prognosis.
Purpose
To investigate the association of preoperative MRI multisequence images and adverse pregnancy outcomes by establishing a deep learning model in patients with PAS.
Study Type
Retrospective.
Population
323 pregnant women (age from 20 to 46, the median age is 33), suspected of PAS, underwent MRI to assess the PAS, divided into the training (N = 227) and validation datasets (N = 96).
Field Strength/Sequence
1.5T scanner/fast imaging employing steady‐state acquisition sequence and single shot fast spin echo sequence.
Assessment
Different deep learning models (i.e., with single MRI input sequence/two sequences/multisequence) were compared to assess the risk of adverse pregnancy outcomes, which defined as intraoperative bleeding ≥1500 mL and/or hysterectomy. Net reclassification improvement (NRI) was used for quantitative comparison of assessing adverse pregnancy outcome between different models.
Statistical Tests
The AUC, sensitivity, specificity, and accuracy were used for evaluation. The Shapiro–Wilk test and t‐test were used. A P value of <0.05 was considered statistically significant.
Results
215 cases were invasive placenta accreta (67.44% of them with adverse outcomes) and 108 cases were non‐invasive placenta accreta (9.25% of them with adverse outcomes). The model with four sequences assessed adverse pregnancy outcomes with AUC of 0.8792 (95% CI, 0.8645–0.8939), with ACC of 85.93% (95%, 84.43%–87.43%), with SEN of 86.24% (95% CI, 82.46%–90.02%), and with SPC of 85.62% (95%, 82.00%–89.23%) on the test cohort. The performance of model with four sequences improved above 0.10 comparing with that of model with two sequences and above 0.20 comparing with that of model with single sequence in terms of NRI.
Data Conclusion
The proposed model showed good diagnostic performance for assessing adverse pregnancy outcomes.
Level of Evidence
3
Technical Efficacy
Stage 2</description><identifier>ISSN: 1053-1807</identifier><identifier>ISSN: 1522-2586</identifier><identifier>EISSN: 1522-2586</identifier><identifier>DOI: 10.1002/jmri.29023</identifier><identifier>PMID: 37851581</identifier><language>eng</language><publisher>Hoboken, USA: John Wiley & Sons, Inc</publisher><subject>adverse outcomes ; Deep learning ; Field strength ; Hysterectomy ; Magnetic resonance imaging ; Mathematical models ; Medical imaging ; multisequence MRI ; PAS ; Placenta ; Population studies ; Pregnancy ; Reclassification ; Risk assessment ; ROI ; Statistical analysis ; Statistical tests</subject><ispartof>Journal of magnetic resonance imaging, 2024-02, Vol.59 (2), p.510-521</ispartof><rights>2023 International Society for Magnetic Resonance in Medicine.</rights><rights>2024 International Society for Magnetic Resonance in Medicine</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c4113-4485bdaec43102f2453fb0ff0967a5c4aeb5fc7ac368ef042426065162323c3b3</citedby><cites>FETCH-LOGICAL-c4113-4485bdaec43102f2453fb0ff0967a5c4aeb5fc7ac368ef042426065162323c3b3</cites><orcidid>0000-0001-5425-6667</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Fjmri.29023$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fjmri.29023$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,777,781,1412,27905,27906,45555,45556</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37851581$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zong, Ming</creatorcontrib><creatorcontrib>Pei, Xinlong</creatorcontrib><creatorcontrib>Yan, Kun</creatorcontrib><creatorcontrib>Luo, Deng</creatorcontrib><creatorcontrib>Zhao, Yangyu</creatorcontrib><creatorcontrib>Wang, Ping</creatorcontrib><creatorcontrib>Chen, Lian</creatorcontrib><title>Deep Learning Model Based on Multisequence MRI Images for Assessing Adverse Pregnancy Outcome in Placenta Accreta</title><title>Journal of magnetic resonance imaging</title><addtitle>J Magn Reson Imaging</addtitle><description>Background
Preoperative assessment of adverse outcomes risk in placenta accreta spectrum (PAS) disorders is of high clinical relevance for perioperative management and prognosis.
Purpose
To investigate the association of preoperative MRI multisequence images and adverse pregnancy outcomes by establishing a deep learning model in patients with PAS.
Study Type
Retrospective.
Population
323 pregnant women (age from 20 to 46, the median age is 33), suspected of PAS, underwent MRI to assess the PAS, divided into the training (N = 227) and validation datasets (N = 96).
Field Strength/Sequence
1.5T scanner/fast imaging employing steady‐state acquisition sequence and single shot fast spin echo sequence.
Assessment
Different deep learning models (i.e., with single MRI input sequence/two sequences/multisequence) were compared to assess the risk of adverse pregnancy outcomes, which defined as intraoperative bleeding ≥1500 mL and/or hysterectomy. Net reclassification improvement (NRI) was used for quantitative comparison of assessing adverse pregnancy outcome between different models.
Statistical Tests
The AUC, sensitivity, specificity, and accuracy were used for evaluation. The Shapiro–Wilk test and t‐test were used. A P value of <0.05 was considered statistically significant.
Results
215 cases were invasive placenta accreta (67.44% of them with adverse outcomes) and 108 cases were non‐invasive placenta accreta (9.25% of them with adverse outcomes). The model with four sequences assessed adverse pregnancy outcomes with AUC of 0.8792 (95% CI, 0.8645–0.8939), with ACC of 85.93% (95%, 84.43%–87.43%), with SEN of 86.24% (95% CI, 82.46%–90.02%), and with SPC of 85.62% (95%, 82.00%–89.23%) on the test cohort. The performance of model with four sequences improved above 0.10 comparing with that of model with two sequences and above 0.20 comparing with that of model with single sequence in terms of NRI.
Data Conclusion
The proposed model showed good diagnostic performance for assessing adverse pregnancy outcomes.
Level of Evidence
3
Technical Efficacy
Stage 2</description><subject>adverse outcomes</subject><subject>Deep learning</subject><subject>Field strength</subject><subject>Hysterectomy</subject><subject>Magnetic resonance imaging</subject><subject>Mathematical models</subject><subject>Medical imaging</subject><subject>multisequence MRI</subject><subject>PAS</subject><subject>Placenta</subject><subject>Population studies</subject><subject>Pregnancy</subject><subject>Reclassification</subject><subject>Risk assessment</subject><subject>ROI</subject><subject>Statistical analysis</subject><subject>Statistical tests</subject><issn>1053-1807</issn><issn>1522-2586</issn><issn>1522-2586</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kctu2zAQRYmiRfPc9AMKAt0UAZQMXxK1dF6NCxsJimZNUNTQkCFRDik18N9HrtMssuhqZnHmYGYuIV8YnDMAfrHuYnPOS-DiAzlkivOMK51_nHpQImMaigNylNIaAMpSqs_kQBRaMaXZIXm6RtzQBdoYmrCiy77Gll7ahDXtA12O7dAkfBoxOKTLX3M67-wKE_V9pLOUMKXd1Kz-gzEhfYi4Cja4Lb0fB9d3SJtAH1rrMAyWzpyLONgT8snbNuHpaz0mj7c3v6_ussX9j_nVbJE5yZjIpNSqqi06KRhwz6USvgLvocwLq5y0WCnvCutErtGD5JLnkCuWc8GFE5U4Jt_33k3spwPSYLomOWxbG7Afk-G6KCUUWsOEfnuHrvsxhmk7w0umQBdMFRN1tqdc7FOK6M0mNp2NW8PA7IIwuyDM3yAm-Ourcqw6rN_Qf5-fALYHnpsWt_9RmZ_T3_fSFz8SkfE</recordid><startdate>202402</startdate><enddate>202402</enddate><creator>Zong, Ming</creator><creator>Pei, Xinlong</creator><creator>Yan, Kun</creator><creator>Luo, Deng</creator><creator>Zhao, Yangyu</creator><creator>Wang, Ping</creator><creator>Chen, Lian</creator><general>John Wiley & Sons, Inc</general><general>Wiley Subscription Services, Inc</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QO</scope><scope>7TK</scope><scope>8FD</scope><scope>FR3</scope><scope>K9.</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-5425-6667</orcidid></search><sort><creationdate>202402</creationdate><title>Deep Learning Model Based on Multisequence MRI Images for Assessing Adverse Pregnancy Outcome in Placenta Accreta</title><author>Zong, Ming ; Pei, Xinlong ; Yan, Kun ; Luo, Deng ; Zhao, Yangyu ; Wang, Ping ; Chen, Lian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c4113-4485bdaec43102f2453fb0ff0967a5c4aeb5fc7ac368ef042426065162323c3b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>adverse outcomes</topic><topic>Deep learning</topic><topic>Field strength</topic><topic>Hysterectomy</topic><topic>Magnetic resonance imaging</topic><topic>Mathematical models</topic><topic>Medical imaging</topic><topic>multisequence MRI</topic><topic>PAS</topic><topic>Placenta</topic><topic>Population studies</topic><topic>Pregnancy</topic><topic>Reclassification</topic><topic>Risk assessment</topic><topic>ROI</topic><topic>Statistical analysis</topic><topic>Statistical tests</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zong, Ming</creatorcontrib><creatorcontrib>Pei, Xinlong</creatorcontrib><creatorcontrib>Yan, Kun</creatorcontrib><creatorcontrib>Luo, Deng</creatorcontrib><creatorcontrib>Zhao, Yangyu</creatorcontrib><creatorcontrib>Wang, Ping</creatorcontrib><creatorcontrib>Chen, Lian</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Journal of magnetic resonance imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zong, Ming</au><au>Pei, Xinlong</au><au>Yan, Kun</au><au>Luo, Deng</au><au>Zhao, Yangyu</au><au>Wang, Ping</au><au>Chen, Lian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Learning Model Based on Multisequence MRI Images for Assessing Adverse Pregnancy Outcome in Placenta Accreta</atitle><jtitle>Journal of magnetic resonance imaging</jtitle><addtitle>J Magn Reson Imaging</addtitle><date>2024-02</date><risdate>2024</risdate><volume>59</volume><issue>2</issue><spage>510</spage><epage>521</epage><pages>510-521</pages><issn>1053-1807</issn><issn>1522-2586</issn><eissn>1522-2586</eissn><abstract>Background
Preoperative assessment of adverse outcomes risk in placenta accreta spectrum (PAS) disorders is of high clinical relevance for perioperative management and prognosis.
Purpose
To investigate the association of preoperative MRI multisequence images and adverse pregnancy outcomes by establishing a deep learning model in patients with PAS.
Study Type
Retrospective.
Population
323 pregnant women (age from 20 to 46, the median age is 33), suspected of PAS, underwent MRI to assess the PAS, divided into the training (N = 227) and validation datasets (N = 96).
Field Strength/Sequence
1.5T scanner/fast imaging employing steady‐state acquisition sequence and single shot fast spin echo sequence.
Assessment
Different deep learning models (i.e., with single MRI input sequence/two sequences/multisequence) were compared to assess the risk of adverse pregnancy outcomes, which defined as intraoperative bleeding ≥1500 mL and/or hysterectomy. Net reclassification improvement (NRI) was used for quantitative comparison of assessing adverse pregnancy outcome between different models.
Statistical Tests
The AUC, sensitivity, specificity, and accuracy were used for evaluation. The Shapiro–Wilk test and t‐test were used. A P value of <0.05 was considered statistically significant.
Results
215 cases were invasive placenta accreta (67.44% of them with adverse outcomes) and 108 cases were non‐invasive placenta accreta (9.25% of them with adverse outcomes). The model with four sequences assessed adverse pregnancy outcomes with AUC of 0.8792 (95% CI, 0.8645–0.8939), with ACC of 85.93% (95%, 84.43%–87.43%), with SEN of 86.24% (95% CI, 82.46%–90.02%), and with SPC of 85.62% (95%, 82.00%–89.23%) on the test cohort. The performance of model with four sequences improved above 0.10 comparing with that of model with two sequences and above 0.20 comparing with that of model with single sequence in terms of NRI.
Data Conclusion
The proposed model showed good diagnostic performance for assessing adverse pregnancy outcomes.
Level of Evidence
3
Technical Efficacy
Stage 2</abstract><cop>Hoboken, USA</cop><pub>John Wiley & Sons, Inc</pub><pmid>37851581</pmid><doi>10.1002/jmri.29023</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0001-5425-6667</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1053-1807 |
| ispartof | Journal of magnetic resonance imaging, 2024-02, Vol.59 (2), p.510-521 |
| issn | 1053-1807 1522-2586 1522-2586 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2879407880 |
| source | Wiley Online Library Journals Frontfile Complete |
| subjects | adverse outcomes Deep learning Field strength Hysterectomy Magnetic resonance imaging Mathematical models Medical imaging multisequence MRI PAS Placenta Population studies Pregnancy Reclassification Risk assessment ROI Statistical analysis Statistical tests |
| title | Deep Learning Model Based on Multisequence MRI Images for Assessing Adverse Pregnancy Outcome in Placenta Accreta |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T19%3A51%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20Learning%20Model%20Based%20on%20Multisequence%20MRI%20Images%20for%20Assessing%20Adverse%20Pregnancy%20Outcome%20in%20Placenta%20Accreta&rft.jtitle=Journal%20of%20magnetic%20resonance%20imaging&rft.au=Zong,%20Ming&rft.date=2024-02&rft.volume=59&rft.issue=2&rft.spage=510&rft.epage=521&rft.pages=510-521&rft.issn=1053-1807&rft.eissn=1522-2586&rft_id=info:doi/10.1002/jmri.29023&rft_dat=%3Cproquest_cross%3E2879407880%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2915087157&rft_id=info:pmid/37851581&rfr_iscdi=true |