Assessment of the Breast Cosmesis Using Deep Neural Networks: an Exploratory Study (ABCD)

Breast Cancer Clinical Trial

— ABCD  

Official title:

Assessment of the Breast Cosmesis Using Deep Neural Networks: an Exploratory Study (ABCD)

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT05450016
• Other study ID #: 3734
• Status: Recruiting
• Start date: October 4, 2021
• Est. completion date: September 2026

Study information

• Verified date: July 2022
• Source: Tata Memorial Centre
• Contact: Tabassum Wadasadawala, MD
• Phone: 9324445303
• Email: twadasadwala[@]actrec.gov.in
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Surgery and radiotherapy in breast cancer patients can cause treatment changes and may affect the final breast appearance. In this study, we are trying to evaluate the post treatment breast photographs of the patients and subject these to Artificial Intelligence based program so as to classify into appropriate categories based upon changes from baseline. This automated solution will help in decreasing the time required to achieve this task by physicians in the clinic.

Description:

A new algorithm was introduced which is based on deep neural network (DNN) which receives an image as input and returns the coordinates of the breast key points as output. These key points are then given to a shortest-path algorithm that models images as graphs to refine breast key point localization. The algorithm learns, directly from the image, to compute features and to use those features in the analysis of the aesthetic result. This comprises of two main modules: regression and refinement of heatmaps, and regression of key points. To perform the heatmap regression, the U-Net model is used.

The goal of the first module is to generate an intermediate representation consisting on a fuzzy localization for the key points that are to be detected.

The second module receives and refines this fuzzy localization, and through complex calculations, outputting the x and y coordinates of the keypoints, and the data generated from which can be used for disease / image classification.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 720
• Est. completion date: September 2026
• Est. primary completion date: September 2024
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: Female
• Age group: 19 Years to 80 Years

Eligibility

Inclusion Criteria:

• Confirmed diagnosis of primary breast cancer (invasive or in situ)

• Patient undergone breast conservation / Whole breast reconstruction

• Patient received breast RT

• Already provided written informed consent on earlier projects

• Patient provided photographs of both breasts

• Non-metastatic disease or oligometastatic

• Age > 18 years

• Reconsent given

Exclusion Criteria:

• Mastectomy without whole breast reconstruction

• Bilateral breast cancer

• Partial breast irradiation

• Male patient

• Limited life expectancy due to co-morbidity

• Patients undergoing brachy boost

Related Conditions & MeSH terms

• Breast Cancer

Locations

Country	Name	City	State
India	Tata Memorial Centre	Mumbai	Maharashtra

Sponsors (1)

Lead Sponsor	Collaborator
Tata Memorial Centre

Country where clinical trial is conducted

India, 

References & Publications (21)

Budrukkar AN, Sarin R, Shrivastava SK, Deshpande DD, Dinshaw KA. Cosmesis, late sequelae and local control after breast-conserving therapy: influence of type of tumour bed boost and adjuvant chemotherapy. Clin Oncol (R Coll Radiol). 2007 Oct;19(8):596-603 — View Citation

Cardoso JS, Silva W, Cardoso MJ. Evolution, current challenges, and future possibilities in the objective assessment of aesthetic outcome of breast cancer locoregional treatment. Breast. 2020 Feb;49:123-130. doi: 10.1016/j.breast.2019.11.006. Epub 2019 No — View Citation

Cardoso MJ, Cardoso JS, Wild T, Krois W, Fitzal F. Comparing two objective methods for the aesthetic evaluation of breast cancer conservative treatment. Breast Cancer Res Treat. 2009 Jul;116(1):149-52. doi: 10.1007/s10549-008-0173-4. Epub 2008 Sep 7. — View Citation

Cohen M, Evanoff B, George LT, Brandt KE. A subjective rating scale for evaluating the appearance outcome of autologous breast reconstruction. Plast Reconstr Surg. 2005 Aug;116(2):440-9. — View Citation

Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017 Feb 2;542(7639):115-118. doi: 10.1038/nature21056. Epub 2017 Jan 25. Erratum in: Nature. 2017 Jun 2 — View Citation

Fitzal F, Krois W, Trischler H, Wutzel L, Riedl O, Kühbelböck U, Wintersteiner B, Cardoso MJ, Dubsky P, Gnant M, Jakesz R, Wild T. The use of a breast symmetry index for objective evaluation of breast cosmesis. Breast. 2007 Aug;16(4):429-35. Epub 2007 Mar — View Citation

Hamidinekoo A, Denton E, Rampun A, Honnor K, Zwiggelaar R. Deep learning in mammography and breast histology, an overview and future trends. Med Image Anal. 2018 Jul;47:45-67. doi: 10.1016/j.media.2018.03.006. Epub 2018 Mar 26. Review. — View Citation

Hill-Kayser CE, Vachani C, Hampshire MK, Di Lullo GA, Metz JM. Cosmetic outcomes and complications reported by patients having undergone breast-conserving treatment. Int J Radiat Oncol Biol Phys. 2012 Jul 1;83(3):839-44. doi: 10.1016/j.ijrobp.2011.08.013. — View Citation

Kim MS, Reece GP, Beahm EK, Miller MJ, Atkinson EN, Markey MK. Objective assessment of aesthetic outcomes of breast cancer treatment: measuring ptosis from clinical photographs. Comput Biol Med. 2007 Jan;37(1):49-59. Epub 2006 Jan 24. — View Citation

Le WT, Maleki F, Romero FP, Forghani R, Kadoury S. Overview of Machine Learning: Part 2: Deep Learning for Medical Image Analysis. Neuroimaging Clin N Am. 2020 Nov;30(4):417-431. doi: 10.1016/j.nic.2020.06.003. Epub 2020 Sep 18. Review. — View Citation

Lowery JC, Wilkins EG, Kuzon WM, Davis JA. Evaluations of aesthetic results in breast reconstruction: an analysis of reliability. Ann Plast Surg. 1996 Jun;36(6):601-6; discussion 607. — View Citation

Maier A, Syben C, Lasser T, Riess C. A gentle introduction to deep learning in medical image processing. Z Med Phys. 2019 May;29(2):86-101. doi: 10.1016/j.zemedi.2018.12.003. Epub 2019 Jan 25. Review. — View Citation

Pezner RD, Lipsett JA, Vora NL, Desai KR. Limited usefulness of observer-based cosmesis scales employed to evaluate patients treated conservatively for breast cancer. Int J Radiat Oncol Biol Phys. 1985 Jun;11(6):1117-9. — View Citation

Pezner RD, Patterson MP, Hill LR, Vora N, Desai KR, Archambeau JO, Lipsett JA. Breast retraction assessment: an objective evaluation of cosmetic results of patients treated conservatively for breast cancer. Int J Radiat Oncol Biol Phys. 1985 Mar;11(3):575 — View Citation

Sarin R, Dinshaw KA, Shrivastava SK, Sharma V, Deore SM. Therapeutic factors influencing the cosmetic outcome and late complications in the conservative management of early breast cancer. Int J Radiat Oncol Biol Phys. 1993 Sep 30;27(2):285-92. — View Citation

Shen D, Wu G, Suk HI. Deep Learning in Medical Image Analysis. Annu Rev Biomed Eng. 2017 Jun 21;19:221-248. doi: 10.1146/annurev-bioeng-071516-044442. Epub 2017 Mar 9. Review. — View Citation

START Trialists' Group, Bentzen SM, Agrawal RK, Aird EG, Barrett JM, Barrett-Lee PJ, Bentzen SM, Bliss JM, Brown J, Dewar JA, Dobbs HJ, Haviland JS, Hoskin PJ, Hopwood P, Lawton PA, Magee BJ, Mills J, Morgan DA, Owen JR, Simmons S, Sumo G, Sydenham MA, Ve — View Citation

START Trialists' Group, Bentzen SM, Agrawal RK, Aird EG, Barrett JM, Barrett-Lee PJ, Bliss JM, Brown J, Dewar JA, Dobbs HJ, Haviland JS, Hoskin PJ, Hopwood P, Lawton PA, Magee BJ, Mills J, Morgan DA, Owen JR, Simmons S, Sumo G, Sydenham MA, Venables K, Ya — View Citation

Vrieling C, Collette L, Bartelink E, Borger JH, Brenninkmeyer SJ, Horiot JC, Pierart M, Poortmans PM, Struikmans H, Van der Schueren E, Van Dongen JA, Van Limbergen E, Bartelink H. Validation of the methods of cosmetic assessment after breast-conserving t — View Citation

Wadasadawala T, Sinha S, Parmar V, Verma S, Gaikar M, Kannan S, Mondal M, Pathak R, Jain U, Sarin R. Comparison of subjective, objective and patient-reported cosmetic outcomes between accelerated partial breast irradiation and whole breast radiotherapy: a — View Citation

Wadasadawala T, Sinha S, Verma S, Parmar V, Kannan S, Pathak R, Sarin R, Gaikar M. A prospective comparison of subjective and objective assessments of cosmetic outcomes following breast brachytherapy. J Contemp Brachytherapy. 2019 Jun;11(3):207-214. doi: — View Citation

* Note: There are 21 references in all — Click here to view all references

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Proportion of patients with excellent/good cosmesis	The patient photographs will be processed for artificial intelligence based analysis of prediction of breast cosmesis	3 years
Secondary	Kappa statistic between different deep neural networks	Concordance of various deep neural networks in prediction of breast cosmesis	3 years

External Links

•   R-CNN, Fast R-CNN, Faster R-CNN, YOLO - Object Detection Algorithms.
•   YOLOv3: Real-Time Object Detection Algorithm (What's New?).