Breast CancerNCT05021055
Multicentric Study for External Validation of a Deep Learning Model for Mammographic Breast Density Categorization
An observational study of Breast Cancer, run by Hospital Italiano de Buenos Aires.
Trial summary
The correct categorization of breast density is essential to adapt the diagnostic examination to the needs of each patient. Assessment of breast density is performed visually by radiologists. Some authors have detected that this method involves considerable intra and interobserver variability. Read more about this study
- Who is it for?
- Any ageHealthy volunteers can take part
- Conditions the study is for
- Breast Cancer
- How many people
- 277 participants
- Where
- No sites listed yet
- Study dates
- Sep 2021to Jul 2022
- Phase
- Observational
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages Any age
- All sexes
- Healthy volunteers accepted
- Child, Adult, Older adult
Study population: The unit of analysis will be the bilateral mammographic images with mediolateral oblique and craniocaudal views. The images selected for this study will be screening mammograms performed at Saint John's Cancer Institute. The institution will select the images according to the inclusion and exclusion criteria. The images will be extracted from the institutional database retrospectively and will be anonymized without any personal data, except for the age of the patient. These images will be stored in DICOM format, in a safe place with restricted access limited only to the investigation team.
Who may be able to join
- Mammograms included in the study should meet the following criteria:
- Female patients of 40 years of age or more.
- To have at least one screening mammography exam performed at Saint John's
- Cancer Institute during the study period. These exams will be included regardless of the brand of the mammography equipment.
- Mammograms should be performed with digital equipment.
Who cannot join
- Mammograms with the following criteria will be excluded from the study:
- Patients with gigantomastia, defined by the need for more than one image of each mammographic view (mediolateral oblique and craniocaudal) to evaluate the entire breast volume.
- Patients with breast implants.
- Patients with a history of breast surgery.
Trial locations and contacts
No sites are listed yet.
About this study
The correct categorization of breast density is essential to adapt the diagnostic examination to the needs of each patient. Assessment of breast density is performed visually by radiologists. Some authors have detected that this method involves considerable intra and interobserver variability. On the other hand, automated systems for measuring breast density are becoming more and more frequent. Machine learning is a domain of Artificial Intelligence, which comprises the process of developing systems with the ability to learn and make predictions using data. These systems are designed to aid healthcare professional decision making. In the present work, the multicenter study of external validation of a tool based on deep learning for the categorization of mammographic breast density is proposed.
Read the detailed description
The correct categorization of breast density is essential to adapt the diagnostic examination to the needs of each patient. Assessment of breast density is performed visually by radiologists. Some authors have detected that this method involves considerable intra and interobserver variability. On the other hand, automated systems for measuring breast density are becoming more and more frequent. Consequently, in clinical practice, breast density is reported from the assessment carried out by specialists with the support of these systems. But there are few studies about the use, concordance and perception of usefulness of professionals on these tools. A study carried out at the Hospital Italiano de Buenos Aires reported a moderate to almost perfect inter- and intra-observer agreement among radiologists and a moderate concordance between the categorization carried out by experts and that carried out by commercial software of a digital mammography machine. Machine learning is a domain of Artificial Intelligence, which comprises the process of developing systems with the ability to learn and make predictions using data. Once a system designed to aid healthcare professional decision making is developed, it must be validated. In 2019, an internal validation of a tool based on deep learning techniques was carried out for the automatic categorization of mammographic breast density. The tool reached a very good interobserver agreement, kappa = 0.64 (95% CI 0.58-0.69), when compared with the performance of the professionals. It reached a sensitivity of 83.2 (CI: 76.9-88.3) and a specificity of 88.4 (83.9-92.0.) In the present work, the multicenter study of external validation of a tool based on deep learning for the categorization of mammographic breast density is proposed. The evaluation of this tool will be carried out in two external institutions: Hospital Alemán and Fundación Científica del Sur.
- Conditions
- Breast Cancer
- Keywords
- Breast cancer, artificial intelligence, deep learning, breast density, multicentric
- Medical subject headings
- Breast Neoplasms
What is being measured
The primary outcome is the main question the study is designed to answer.
Agreement between the majority report and Artemisia´s categorization of dense breasts/non-dense breasts
The agreement between the CNN and the total of the professionals' categorizations will be calculated with the linear weighted kappa. To this end, the categories assigned by the professionals will be considered as only one observer in each one of the studies and they will be compared to those assigned by Artemisia for the same set of images.
Measured: 2 months
Agreement between the majority report and Artemisia in each one of the four breast density categories
For each one of the professionals involved in the study, the agreement with the CNN will be calculated with the linear weighted kappa coefficient. To this end, the categories assigned by the professionals will be considered as only one observer in each one of the studies and they will be compared to those assigned by Artemisia for the same set of images.
Measured: 2 months
Secondary outcomes (4)
Agreement between each observer and Artemisia´s categorization of dense breasts/non-dense breasts
To this end, the categories assigned by the professionals will be considered as only one observer in each one of the studies and they will be compared to those assigned by Artemisia for the same set of images.
Measured: 2 months
Agreement between each observer and Artemisia in each one of the four breast density categories
For each one of the professionals involved in the study, the agreement with the CNN will be calculated with the linear weighted kappa coefficient. To this end, the categories assigned by the professionals will be considered as only one observer in each one of the studies and they will be compared to those assigned by Artemisia for the same set of images.
Measured: 2 months
Agreement between each observer and the majority report in the categorization of dense breasts/non-dense breasts
For each one of the professionals involved in the study, the agreement with the majority report will be calculated with the linear weighted kappa coefficient. To this end, the categories assigned by the professionals will be considered as only one observer in each one of the studies and they will be compared to those assigned by the majority report for the same set of images.
Measured: 2 months
Agreement between each observer and the majority report in each one of the four breast density categories
For each one of the professionals involved in the study, the agreement with the majority report will be calculated with the linear weighted kappa coefficient. To this end, the categories assigned by the professionals will be considered as only one observer in each one of the studies and they will be compared to those assigned by the majority report for the same set of images.
Measured: 2 months
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted25 Aug 2021
- Study startSep 2021 (estimated)
- Primary completionApr 2022 (estimated)
- Study completionJul 2022 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (22)Papers the sponsor has linked to this study.
- Other trials for Breast CancerStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Other
- Time perspective
- Prospective
- Enrolment
- 277 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Hospital Italiano de Buenos Aires
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
- Investigators
- Daniel R Luna, MD, Principal investigator, Hospital Italiano de Buenos Aires
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT05021055
- Sponsor's protocol ID
- 6077
- Other IDs
- 4927
- Status last verified
- Jul 2021
- First submitted
- 19 Aug 2021
- Last updated
- 25 Aug 2021
- Results posted
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Publications
Winkler NS, Raza S, Mackesy M, Birdwell RL. Breast density: clinical implications and assessment methods. Radiographics. 2015 Mar-Apr;35(2):316-24. doi: 10.1148/rg.352140134.
PubMed 25763719Ciatto S, Visioli C, Paci E, Zappa M. Breast density as a determinant of interval cancer at mammographic screening. Br J Cancer. 2004 Jan 26;90(2):393-6. doi: 10.1038/sj.bjc.6601548.
PubMed 14735182Wanders JOP, Holland K, Karssemeijer N, Peeters PHM, Veldhuis WB, Mann RM, van Gils CH. The effect of volumetric breast density on the risk of screen-detected and interval breast cancers: a cohort study. Breast Cancer Res. 2017 Jun 5;19(1):67. doi: 10.1186/s13058-017-0859-9.
PubMed 28583146Strand F, Azavedo E, Hellgren R, Humphreys K, Eriksson M, Shepherd J, Hall P, Czene K. Localized mammographic density is associated with interval cancer and large breast cancer: a nested case-control study. Breast Cancer Res. 2019 Jan 22;21(1):8. doi: 10.1186/s13058-019-1099-y.
PubMed 30670066Boyd NF, Guo H, Martin LJ, Sun L, Stone J, Fishell E, Jong RA, Hislop G, Chiarelli A, Minkin S, Yaffe MJ. Mammographic density and the risk and detection of breast cancer. N Engl J Med. 2007 Jan 18;356(3):227-36. doi: 10.1056/NEJMoa062790.
PubMed 17229950Swann CA, Kopans DB, McCarthy KA, White G, Hall DA. Mammographic density and physical assessment of the breast. AJR Am J Roentgenol. 1987 Mar;148(3):525-6. doi: 10.2214/ajr.148.3.525.
PubMed 3492880A L Mousa DS, Ryan EA, Mello-Thoms C, Brennan PC. What effect does mammographic breast density have on lesion detection in digital mammography? Clin Radiol. 2014 Apr;69(4):333-41. doi: 10.1016/j.crad.2013.11.014. Epub 2014 Jan 11.
PubMed 24424328Carreira Gomez MC, Estrada Blan MC. What we need to know about dense breasts: implications for breast cancer screening. Radiologia. 2016 Nov-Dec;58(6):421-426. doi: 10.1016/j.rx.2016.08.002. Epub 2016 Oct 15. English, Spanish.
PubMed 27751504McCormack VA, dos Santos Silva I. Breast density and parenchymal patterns as markers of breast cancer risk: a meta-analysis. Cancer Epidemiol Biomarkers Prev. 2006 Jun;15(6):1159-69. doi: 10.1158/1055-9965.EPI-06-0034.
PubMed 16775176Sprague BL, Conant EF, Onega T, Garcia MP, Beaber EF, Herschorn SD, Lehman CD, Tosteson AN, Lacson R, Schnall MD, Kontos D, Haas JS, Weaver DL, Barlow WE; PROSPR Consortium. Variation in Mammographic Breast Density Assessments Among Radiologists in Clinical Practice: A Multicenter Observational Study. Ann Intern Med. 2016 Oct 4;165(7):457-464. doi: 10.7326/M15-2934. Epub 2016 Jul 19.
PubMed 27428568Eom HJ, Cha JH, Kang JW, Choi WJ, Kim HJ, Go E. Comparison of variability in breast density assessment by BI-RADS category according to the level of experience. Acta Radiol. 2018 May;59(5):527-532. doi: 10.1177/0284185117725369. Epub 2017 Aug 2.
PubMed 28766978Alikhassi A, Esmaili Gourabi H, Baikpour M. Comparison of inter- and intra-observer variability of breast density assessments using the fourth and fifth editions of Breast Imaging Reporting and Data System. Eur J Radiol Open. 2018 Apr 20;5:67-72. doi: 10.1016/j.ejro.2018.04.002. eCollection 2018.
PubMed 29707614Melnikow J, Fenton JJ, Whitlock EP, Miglioretti DL, Weyrich MS, Thompson JH, Shah K. Supplemental Screening for Breast Cancer in Women With Dense Breasts: A Systematic Review for the U.S. Preventive Services Task Force. Ann Intern Med. 2016 Feb 16;164(4):268-78. doi: 10.7326/M15-1789. Epub 2016 Jan 12.
PubMed 26757021Jeffers AM, Sieh W, Lipson JA, Rothstein JH, McGuire V, Whittemore AS, Rubin DL. Breast Cancer Risk and Mammographic Density Assessed with Semiautomated and Fully Automated Methods and BI-RADS. Radiology. 2017 Feb;282(2):348-355. doi: 10.1148/radiol.2016152062. Epub 2016 Sep 5.
PubMed 27598536Ciatto S, Bernardi D, Calabrese M, Durando M, Gentilini MA, Mariscotti G, Monetti F, Moriconi E, Pesce B, Roselli A, Stevanin C, Tapparelli M, Houssami N. A first evaluation of breast radiological density assessment by QUANTRA software as compared to visual classification. Breast. 2012 Aug;21(4):503-6. doi: 10.1016/j.breast.2012.01.005. Epub 2012 Jan 27.
PubMed 22285387
Study at a glance
From the registry record, last updated by the sponsor on 25 Aug 2021. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Multicentric Study for External Validation of a Deep Learning Model for Mammographic Breast Density Categorization
- ClinicalTrials.gov ID
- NCT05021055
- Acronym / sponsor ID
- 6077
- Conditions
- Breast Cancer
- Keywords
- Breast cancer, artificial intelligence, deep learning, breast density, multicentric
- Study type
- Observational
- Recruitment status
- Unknown status
- Enrolment
- 277 participants (estimated)
- Lead sponsor
- Hospital Italiano de Buenos AiresUniversity, hospital or other
- Study start
- Sep 2021 (estimated)
- Primary completion
- Apr 2022 (estimated)
- Study completion
- Jul 2022 (estimated)
- First posted
- 25 Aug 2021 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
The correct categorization of breast density is essential to adapt the diagnostic examination to the needs of each patient. Assessment of breast density is performed visually by radiologists. Some authors have detected that this method involves considerable intra and interobserver variability. On the other hand, automated systems for measuring breast density are becoming more and more frequent. Machine learning is a domain of Artificial Intelligence, which comprises the process of developing systems with the ability to learn and make predictions using data. These systems are designed to aid healthcare professional decision making. In the present work, the multicenter study of external validation of a tool based on deep learning for the categorization of mammographic breast density is proposed.
Detailed description
The correct categorization of breast density is essential to adapt the diagnostic examination to the needs of each patient. Assessment of breast density is performed visually by radiologists. Some authors have detected that this method involves considerable intra and interobserver variability. On the other hand, automated systems for measuring breast density are becoming more and more frequent. Consequently, in clinical practice, breast density is reported from the assessment carried out by specialists with the support of these systems. But there are few studies about the use, concordance and perception of usefulness of professionals on these tools. A study carried out at the Hospital Italiano de Buenos Aires reported a moderate to almost perfect inter- and intra-observer agreement among radiologists and a moderate concordance between the categorization carried out by experts and that carried out by commercial software of a digital mammography machine. Machine learning is a domain of Artificial Intelligence, which comprises the process of developing systems with the ability to learn and make predictions using data. Once a system designed to aid healthcare professional decision making is developed, it must be validated. In 2019, an internal validation of a tool based on deep learning techniques was carried out for the automatic categorization of mammographic breast density. The tool reached a very good interobserver agreement, kappa = 0.64 (95% CI 0.58-0.69), when compared with the performance of the professionals. It reached a sensitivity of 83.2 (CI: 76.9-88.3) and a specificity of 88.4 (83.9-92.0.) In the present work, the multicenter study of external validation of a tool based on deep learning for the categorization of mammographic breast density is proposed. The evaluation of this tool will be carried out in two external institutions: Hospital Alemán and Fundación Científica del Sur.
Study design
- Observational model
- Other
- Time perspective
- Prospective
Who may qualify
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Child, Adult, Older adult
- Study population
- The unit of analysis will be the bilateral mammographic images with mediolateral oblique and craniocaudal views. The images selected for this study will be screening mammograms performed at Saint John's Cancer Institute. The institution will select the images according to the inclusion and exclusion criteria. The images will be extracted from the institutional database retrospectively and will be anonymized without any personal data, except for the age of the patient. These images will be stored in DICOM format, in a safe place with restricted access limited only to the investigation team.
Key inclusion criteria (5 listed)
- Mammograms included in the study should meet the following criteria:
Key exclusion criteria (4 listed)
- Mammograms with the following criteria will be excluded from the study:
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Primary outcome
Agreement between the majority report and Artemisia´s categorization of dense breasts/non-dense breasts
Time frame: 2 months
The agreement between the CNN and the total of the professionals' categorizations will be calculated with the linear weighted kappa. To this end, the categories assigned by the professionals will be considered as only one observer in each one of the studies and they will be compared to those assigned by Artemisia for the same set of images.
Agreement between the majority report and Artemisia in each one of the four breast density categories
Time frame: 2 months
For each one of the professionals involved in the study, the agreement with the CNN will be calculated with the linear weighted kappa coefficient. To this end, the categories assigned by the professionals will be considered as only one observer in each one of the studies and they will be compared to those assigned by Artemisia for the same set of images.
4 secondary outcomes
Agreement between each observer and Artemisia´s categorization of dense breasts/non-dense breasts
Time frame: 2 months
Agreement between each observer and Artemisia in each one of the four breast density categories
Time frame: 2 months
Agreement between each observer and the majority report in the categorization of dense breasts/non-dense breasts
Time frame: 2 months
Agreement between each observer and the majority report in each one of the four breast density categories
Time frame: 2 months
Results and safety
Results are not available in the source record.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 25 Aug 2021.
- Background: PubMed 25763719Winkler NS, Raza S, Mackesy M, Birdwell RL. Breast density: clinical implications and assessment methods. Radiographics. 2015 Mar-Apr;35(2):316-24. doi: 10.1148/rg.352140134.
- Background: PubMed 14735182Ciatto S, Visioli C, Paci E, Zappa M. Breast density as a determinant of interval cancer at mammographic screening. Br J Cancer. 2004 Jan 26;90(2):393-6. doi: 10.1038/sj.bjc.6601548.
- Background: PubMed 28583146Wanders JOP, Holland K, Karssemeijer N, Peeters PHM, Veldhuis WB, Mann RM, van Gils CH. The effect of volumetric breast density on the risk of screen-detected and interval breast cancers: a cohort study. Breast Cancer Res. 2017 Jun 5;19(1):67. doi: 10.1186/s13058-017-0859-9.
- Background: PubMed 30670066Strand F, Azavedo E, Hellgren R, Humphreys K, Eriksson M, Shepherd J, Hall P, Czene K. Localized mammographic density is associated with interval cancer and large breast cancer: a nested case-control study. Breast Cancer Res. 2019 Jan 22;21(1):8. doi: 10.1186/s13058-019-1099-y.
- Background: PubMed 17229950Boyd NF, Guo H, Martin LJ, Sun L, Stone J, Fishell E, Jong RA, Hislop G, Chiarelli A, Minkin S, Yaffe MJ. Mammographic density and the risk and detection of breast cancer. N Engl J Med. 2007 Jan 18;356(3):227-36. doi: 10.1056/NEJMoa062790.
- Background: PubMed 3492880Swann CA, Kopans DB, McCarthy KA, White G, Hall DA. Mammographic density and physical assessment of the breast. AJR Am J Roentgenol. 1987 Mar;148(3):525-6. doi: 10.2214/ajr.148.3.525.
- Background: PubMed 24424328A L Mousa DS, Ryan EA, Mello-Thoms C, Brennan PC. What effect does mammographic breast density have on lesion detection in digital mammography? Clin Radiol. 2014 Apr;69(4):333-41. doi: 10.1016/j.crad.2013.11.014. Epub 2014 Jan 11.
- Background: PubMed 27751504Carreira Gomez MC, Estrada Blan MC. What we need to know about dense breasts: implications for breast cancer screening. Radiologia. 2016 Nov-Dec;58(6):421-426. doi: 10.1016/j.rx.2016.08.002. Epub 2016 Oct 15. English, Spanish.
- Background: PubMed 16775176McCormack VA, dos Santos Silva I. Breast density and parenchymal patterns as markers of breast cancer risk: a meta-analysis. Cancer Epidemiol Biomarkers Prev. 2006 Jun;15(6):1159-69. doi: 10.1158/1055-9965.EPI-06-0034.
- Background: PubMed 27428568Sprague BL, Conant EF, Onega T, Garcia MP, Beaber EF, Herschorn SD, Lehman CD, Tosteson AN, Lacson R, Schnall MD, Kontos D, Haas JS, Weaver DL, Barlow WE; PROSPR Consortium. Variation in Mammographic Breast Density Assessments Among Radiologists in Clinical Practice: A Multicenter Observational Study. Ann Intern Med. 2016 Oct 4;165(7):457-464. doi: 10.7326/M15-2934. Epub 2016 Jul 19.
- Background: PubMed 28766978Eom HJ, Cha JH, Kang JW, Choi WJ, Kim HJ, Go E. Comparison of variability in breast density assessment by BI-RADS category according to the level of experience. Acta Radiol. 2018 May;59(5):527-532. doi: 10.1177/0284185117725369. Epub 2017 Aug 2.
- Background: PubMed 29707614Alikhassi A, Esmaili Gourabi H, Baikpour M. Comparison of inter- and intra-observer variability of breast density assessments using the fourth and fifth editions of Breast Imaging Reporting and Data System. Eur J Radiol Open. 2018 Apr 20;5:67-72. doi: 10.1016/j.ejro.2018.04.002. eCollection 2018.
- Sickles EA, D'Orsi CJ, Bassett LW, Appleton CM, Berg WA, Burnside ES, et al. ACR BI-RADS® Atlas, Breast imaging reporting and data system. Reston, VA: American College of Radiology. 2013;39-48.Link provided by the sponsor.
- Individual participant dataSharing planned: No
Related trials for Breast Cancer
Active, not recruitingPhase 2
Tamoxifen Citrate or Z-Endoxifen Hydrochloride in Treating Patients With Locally Advanced or Metastatic, Estrogen Receptor-Positive, HER2-Negative Breast Cancer
Recurrent Breast Carcinoma, Stage III Breast Cancer AJCC v7
RecruitingPhase 1/2
A Study to Evaluate the Effect of GDC-4198 Alone and in Combination With Giredestrant Versus Abemaciclib and Giredestrant in Participants With Locally Advanced or Metastatic Estrogen Receptor-Positive (ER+), Human Epidermal Growth Factor Receptor-Negative (HER2-) Breast Cancer
Breast Cancer
Not yet recruiting
Podcast-Based Psychosocial Support for Women Newly Diagnosed With Breast Cancer
Breast Cancer
Recruiting
A Study of Skipping Radiation Therapy in People With Breast Cancer
HER2-positive Breast Cancer, Breast Cancer
Active, not recruiting
Dance Study for Post-surgical Pain in Breast Cancer Survivors
Breast Cancer, Survivorship
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
Daniel R Luna, MD principal investigator
Hospital Italiano de Buenos Aires
Questions about this trial
What is this clinical trial studying?
An observational study of Breast Cancer, run by Hospital Italiano de Buenos Aires.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 5 inclusion and 4 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: status not confirmed, as of the sponsor's last update on 25 Aug 2021. Status can change between updates, so confirm with the study contact before making plans.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
Results are not available in the source record.
How can a doctor refer a patient or contact the research team?
Contact Andrés Brandan (+5493816212804, andres.brandan@hospitalitaliano.org.ar), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Agreement between the majority report and Artemisia´s categorization of dense breasts/non-dense breasts (time frame: 2 months). The study lists 2 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT05021055, which also lists 22 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 25 Aug 2021.