AI Model for Classifying Breast Cancer From Histopathology Images

NCT06717984 | Recruiting

• 1 other identifier: NICRH/IRB/2024/134
• Study Type: observational
• Target: 500
• Locations: 1 country
• Sites: 1

Brief Summary

Breast cancer, a prevalent and potentially fatal disease, underscores the need for early and accurate detection to improve patient outcomes. Traditional histopathological examination, the current gold standard for diagnosis, faces limitations like subjectivity and low efficiency. In response, this research seeks to revolutionize breast cancer diagnostics by using deep learning techniques to classify invasive and noninvasive breast cancer types from histopathological images. Non-invasive cancers, like DCIS and LCIS, are confined to milk ducts or lobules, while invasive cancers spread to surrounding tissue and make up 70% of cases, often leading to poorer outcomes. The proposed AI model aims to enhance diagnostic accuracy and efficiency, surpassing manual methods, and providing a scalable solution for diverse healthcare settings. By automating image analysis, the model seeks to democratize cancer screening, making it accessible in underserved populations and adaptable to different resources and equipment. Ultimately, this research aims to advance breast cancer detection, improve patient care, and contribute to better treatment outcomes globally.

Conditions

Breast Cancer

Keywords

Breast Cancer; Histopathology; Deep Learning

Outcome Measures

Primary Outcomes (1)

• Accuracy of Deep Learning Model in Classifying Breast Tissue as Normal Benign, In Situ, or Invasive.

  The primary outcome of this study is the diagnostic accuracy of the deep learning model in classifying histopathological images from breast biopsies into three categories: benign, in situ (noninvasive), and invasive breast cancer. Accuracy will be measured by comparing the model's predictions to the ground truth diagnoses determined by expert pathologists.

  Measured at the time of histopathological image analysis (within 1 week of biopsy or mastectomy).

Study Arms (1)

Women who undergo biopsy for suspected abnormal cell growth in the breast

The cohort includes women who have undergone a biopsy due to suspected abnormal cell growth in the breast. This cohort captures a wide range of potential diagnoses, including benign conditions, noninvasive (in situ) breast cancers, and invasive breast cancers. All participants have histopathological samples collected for analysis, which serve as the basis for determining the presence and type of abnormal cell growth. The cohort will be studied using deep learning techniques to classify the biopsy samples into specific categories (normal, benign, in situ, or invasive), with the goal of improving diagnostic accuracy and efficiency in detecting breast cancer. By focusing on women undergoing biopsy, this study aims to address the diagnostic challenges faced in distinguishing between various breast tissue abnormalities, contributing to earlier detection and better clinical outcomes.

Diagnostic Test: Biopsy, Mastectomy, Histopathology

Interventions

Biopsy, Mastectomy, Histopathology DIAGNOSTIC_TEST

Biopsy: This intervention involves the collection of breast tissue samples through a biopsy procedure. These samples are obtained from women undergoing investigation for unusual cell growth and are analyzed to detect potential abnormalities, including benign, in situ, or invasive cancerous changes. Mastectomy: This intervention refers to the surgical removal of breast tissue, typically performed to treat or prevent the spread of breast cancer. It may involve the removal of part or all of the breast and is considered in cases of invasive breast cancer or high-risk noninvasive breast cancer. Histopathology: This intervention focuses on the microscopic examination of breast tissue samples collected through biopsy or mastectomy. Histopathological analysis is conducted to assess cellular abnormalities, determine the presence of cancer, and classify the tissue as benign, in situ, or invasive, providing the basis for diagnosis and treatment decisions.

Women who undergo biopsy for suspected abnormal cell growth in the breast

Eligibility Criteria

• Gender Eligibility Details: This study is open to female participants only. The focus is on women who are undergoing breast biopsies or mastectomies due to suspected abnormal cell growth, as breast cancer predominantly affects women.
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

The study population includes women who are undergoing breast biopsies or mastectomies due to suspected abnormal cell growth. Participants are drawn from hospitals and clinics where breast cancer screening and diagnostic procedures are conducted. This population includes individuals with a range of breast conditions, from benign abnormalities to noninvasive (in situ) and invasive breast cancers, representing various stages of breast disease for classification and diagnostic purposes.

You may qualify if:

• Female patients of any age can be selected as subjects.
• Individuals willing to participate in breast cancer screening.
• Availability for biopsy examination.
• Women with no current or prior diagnosis of breast cancer.
• Availability of relevant medical records for confirmation and comparison purposes.

You may not qualify if:

• Pregnant women are excluded due to potential impacts on screening results and the necessity for special considerations during pregnancy.
• Individuals with severe medical conditions or circumstances that may render histopathologic examination inappropriate or unsafe are excluded.
• Patients with conditions that could interfere with the accuracy of screening results are excluded.
• Follow-up screenings are not included in this study.

Sponsors & Collaborators

• Taufiq Hasan, PhD: lead
• National Institute of Cancer Research & Hospital, Bangladesh: collaborator

Study Sites (1)

National Institute of Cancer Research & Hospital (NICRH)

Dhaka, 1212, Bangladesh

RECRUITING

MeSH Terms

Conditions

Breast Neoplasms

Interventions

Biopsy

Condition Hierarchy (Ancestors)

Neoplasms by Site; Neoplasms; Breast Diseases; Skin Diseases; Skin and Connective Tissue Diseases

Intervention Hierarchy (Ancestors)

Cytodiagnosis; Cytological Techniques; Clinical Laboratory Techniques; Diagnostic Techniques and Procedures; Diagnosis; Specimen Handling; Diagnostic Techniques, Surgical; Surgical Procedures, Operative; Investigative Techniques

Study Officials

• Taufiq Hasan, PhD

  Department of Biomedical Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka - 1205.

  PRINCIPAL INVESTIGATOR

• Farida Arjuman, FCPS, MCPS

  Department of Histopathology, National Institute of Cancer Research and Hospital (NICRH)

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Taufiq Hasan, PhD

CONTACT

+8801817579844; taufiq@bme.buet.ac.bd

Samiha Jainab, B.Sc.

CONTACT

+8801914556073; jainab.samiha@gmail.com

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: December 1, 2024
• First Posted: December 5, 2024
• Study Start: January 11, 2024
• Primary Completion: February 11, 2025
• Study Completion: February 11, 2025
• Last Updated: December 5, 2024

Record last verified: 2024-12

Locations

BA (1)