View in EDS HTML Full Text PDF Full Text

Deep learning for detection of iso-dense, obscure masses in mammographically dense breasts.

Saved in:
Bibliographic Details
Title: Deep learning for detection of iso-dense, obscure masses in mammographically dense breasts.
Authors: Rangarajan, Krithika1,2 (AUTHOR) krithikarangarajan86@gmail.com, Aggarwal, Pranjal2 (AUTHOR), Gupta, Dhruv Kumar2 (AUTHOR), Dhanakshirur, Rohan2 (AUTHOR), Baby, Akhil1 (AUTHOR), Pal, Chandan1 (AUTHOR), Gupta, Arun Kumar1 (AUTHOR), Hari, Smriti1 (AUTHOR), Banerjee, Subhashis2 (AUTHOR), Arora, Chetan2 (AUTHOR)
Source: European Radiology. Nov2023, Vol. 33 Issue 11, p8112-8121. 10p.
Subjects: Deep learning, Medical screening, Patient selection, Early detection of cancer, Mammograms, Cancer education
Abstract: Objectives: To analyze the performance of deep learning in isodense/obscure masses in dense breasts. To build and validate a deep learning (DL) model using core radiology principles and analyze its performance in isodense/obscure masses. To show performance on screening mammography as well as diagnostic mammography distribution. Methods: This was a retrospective, single-institution, multi-centre study with external validation. For model building, we took a 3-pronged approach. First, we explicitly taught the network to learn features other than density differences: such as spiculations and architectural distortion. Second, we used the opposite breast to enable the detection of asymmetries. Third, we systematically enhanced each image by piece-wise-linear transformation. We tested the network on a diagnostic mammography dataset (2569 images with 243 cancers, January to June 2018) and a screening mammography dataset (2146 images with 59 cancers, patient recruitment from January to April 2021) from a different centre (external validation). Results: When trained with our proposed technique (and compared with baseline network), sensitivity for malignancy increased from 82.7 to 84.7% at 0.2 False positives per image (FPI) in the diagnostic mammography dataset, 67.9 to 73.8% in the subset of patients with dense breasts, 74.6 to 85.3 in the subset of patients with isodense/obscure cancers and 84.9 to 88.7 in an external validation test set with a screening mammography distribution. We showed that our sensitivity exceeded currently reported values (0.90 at 0.2 FPI) on a public benchmark dataset (INBreast). Conclusion: Modelling traditional mammographic teaching into a DL framework can help improve cancer detection accuracy in dense breasts. Clinical relevance statement: Incorporating medical knowledge into neural network design can help us overcome some limitations associated with specific modalities. In this paper, we show how one such deep neural network can help improve performance on mammographically dense breasts. Key Points: • Although state-of-the-art deep learning networks achieve good results in cancer detection in mammography in general, isodense, obscure masses and mammographically dense breasts posed a challenge to deep learning networks. • Collaborative network design and incorporation of traditional radiology teaching into the deep learning approach helped mitigate the problem. • The accuracy of deep learning networks may be translatable to different patient distributions. We showed the results of our network on screening as well as diagnostic mammography datasets. [ABSTRACT FROM AUTHOR]
Copyright of European Radiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 173151708
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Deep learning for detection of iso-dense, obscure masses in mammographically dense breasts.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Rangarajan%2C+Krithika%22">Rangarajan, Krithika</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> krithikarangarajan86@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Aggarwal%2C+Pranjal%22">Aggarwal, Pranjal</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gupta%2C+Dhruv+Kumar%22">Gupta, Dhruv Kumar</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dhanakshirur%2C+Rohan%22">Dhanakshirur, Rohan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Baby%2C+Akhil%22">Baby, Akhil</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Pal%2C+Chandan%22">Pal, Chandan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gupta%2C+Arun+Kumar%22">Gupta, Arun Kumar</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hari%2C+Smriti%22">Hari, Smriti</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Banerjee%2C+Subhashis%22">Banerjee, Subhashis</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Arora%2C+Chetan%22">Arora, Chetan</searchLink><relatesTo>2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22European+Radiology%22">European Radiology</searchLink>. Nov2023, Vol. 33 Issue 11, p8112-8121. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+screening%22">Medical screening</searchLink><br /><searchLink fieldCode="DE" term="%22Patient+selection%22">Patient selection</searchLink><br /><searchLink fieldCode="DE" term="%22Early+detection+of+cancer%22">Early detection of cancer</searchLink><br /><searchLink fieldCode="DE" term="%22Mammograms%22">Mammograms</searchLink><br /><searchLink fieldCode="DE" term="%22Cancer+education%22">Cancer education</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Objectives: To analyze the performance of deep learning in isodense/obscure masses in dense breasts. To build and validate a deep learning (DL) model using core radiology principles and analyze its performance in isodense/obscure masses. To show performance on screening mammography as well as diagnostic mammography distribution. Methods: This was a retrospective, single-institution, multi-centre study with external validation. For model building, we took a 3-pronged approach. First, we explicitly taught the network to learn features other than density differences: such as spiculations and architectural distortion. Second, we used the opposite breast to enable the detection of asymmetries. Third, we systematically enhanced each image by piece-wise-linear transformation. We tested the network on a diagnostic mammography dataset (2569 images with 243 cancers, January to June 2018) and a screening mammography dataset (2146 images with 59 cancers, patient recruitment from January to April 2021) from a different centre (external validation). Results: When trained with our proposed technique (and compared with baseline network), sensitivity for malignancy increased from 82.7 to 84.7% at 0.2 False positives per image (FPI) in the diagnostic mammography dataset, 67.9 to 73.8% in the subset of patients with dense breasts, 74.6 to 85.3 in the subset of patients with isodense/obscure cancers and 84.9 to 88.7 in an external validation test set with a screening mammography distribution. We showed that our sensitivity exceeded currently reported values (0.90 at 0.2 FPI) on a public benchmark dataset (INBreast). Conclusion: Modelling traditional mammographic teaching into a DL framework can help improve cancer detection accuracy in dense breasts. Clinical relevance statement: Incorporating medical knowledge into neural network design can help us overcome some limitations associated with specific modalities. In this paper, we show how one such deep neural network can help improve performance on mammographically dense breasts. Key Points: • Although state-of-the-art deep learning networks achieve good results in cancer detection in mammography in general, isodense, obscure masses and mammographically dense breasts posed a challenge to deep learning networks. • Collaborative network design and incorporation of traditional radiology teaching into the deep learning approach helped mitigate the problem. • The accuracy of deep learning networks may be translatable to different patient distributions. We showed the results of our network on screening as well as diagnostic mammography datasets. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of European Radiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=173151708
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00330-023-09717-7
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 8112
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Medical screening
        Type: general
      – SubjectFull: Patient selection
        Type: general
      – SubjectFull: Early detection of cancer
        Type: general
      – SubjectFull: Mammograms
        Type: general
      – SubjectFull: Cancer education
        Type: general
    Titles:
      – TitleFull: Deep learning for detection of iso-dense, obscure masses in mammographically dense breasts.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Rangarajan, Krithika
      – PersonEntity:
          Name:
            NameFull: Aggarwal, Pranjal
      – PersonEntity:
          Name:
            NameFull: Gupta, Dhruv Kumar
      – PersonEntity:
          Name:
            NameFull: Dhanakshirur, Rohan
      – PersonEntity:
          Name:
            NameFull: Baby, Akhil
      – PersonEntity:
          Name:
            NameFull: Pal, Chandan
      – PersonEntity:
          Name:
            NameFull: Gupta, Arun Kumar
      – PersonEntity:
          Name:
            NameFull: Hari, Smriti
      – PersonEntity:
          Name:
            NameFull: Banerjee, Subhashis
      – PersonEntity:
          Name:
            NameFull: Arora, Chetan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 11
              Text: Nov2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 09387994
          Numbering:
            – Type: volume
              Value: 33
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: European Radiology
              Type: main
ResultId 1