DeepDOF Imaging for Cervical Cancer

Overseen By Kathleen M Schmeler, MD

Age: 18 - 65

Sex: Female

Trial Phase: Academic

Sponsor: M.D. Anderson Cancer Center

Disqualifiers: Under 25, Over 49, Pregnant

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 1

Duration: Immediate

400 Participants Needed

Trial Summary

Do I need to stop taking my current medications for the trial?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the DeepDOF Images treatment for cervical cancer?

The research shows that deep learning techniques can help in diagnosing and segmenting cervical cancer tumors from MRI images, which might improve treatment planning. Although not directly about DeepDOF Images, these studies suggest that advanced imaging techniques can aid in better understanding and managing cervical cancer. ^{1 2 3 4 5}

How does the DeepDOF Imaging treatment for cervical cancer differ from other treatments?

DeepDOF Imaging for cervical cancer is unique because it utilizes advanced deep learning techniques to automatically segment and analyze tumors from MRI images, potentially improving diagnosis and treatment planning. This approach contrasts with traditional methods that rely heavily on manual interpretation by radiologists, offering a more automated and potentially more accurate assessment. ^{1 2 6 7 8}

What is the purpose of this trial?

All patients will be enrolled in Mozambique and Brazil. They will provide informed consent to use their cervical biopsy and/or LEEP specimens for imaging with DeepDOF prior to sending for standard of care processing and interpretation.

Research Team

Kathleen M Schmeler, MD

Principal Investigator

M.D. Anderson Cancer Center

Eligibility Criteria

This trial is for women aged 25-49 in Mozambique and Brazil who are undergoing cervical biopsy or LEEP, not pregnant, and able to give informed consent. Pregnant women, those outside the age range, or not having the procedures cannot participate.

Inclusion Criteria

I am having a cervical biopsy or LEEP procedure.

I am not pregnant and have a recent negative pregnancy test.

I am a woman aged between 25 and 49.

Exclusion Criteria

I am not pregnant.

I am a woman under 25 or over 49 years old.

I am not scheduled for a cervical biopsy or LEEP procedure.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants undergo cervical biopsy and/or LEEP procedures, and specimens are imaged using DeepDOF at the point of care

Immediate

1 visit (in-person)

Follow-up

Participants are monitored for safety and effectiveness after treatment

1 year

Treatment Details

Interventions

• DeepDOF Images

Trial Overview The study tests a new optical microscope called DeepDOF on cervical biopsies and LEEP specimens from participants to see if it can provide detailed images similar to traditional histology without delaying standard care.

Participant Groups

Group I: DeepDOF Images Experimental Treatment 1 Intervention

Participants will be approached by a trained research assistant. After informed consent is obtained, each participant will collect two cervical swabs (self-collected and/or provider-collected) as an optional procedure and stored for future research. VIA and/or colposcopy will be performed per standard of care. Cervical biopsy(ies) and/or LEEP will be performed per standard of care. The specimens will be imaged immediately using DeeDOF at the point of care and then submitted for standard histopathologic analysis as shown in Figure 1.

Who Is Running the Clinical Trial?

M.D. Anderson Cancer Center

Lead Sponsor

Trials

3,107

Recruited

1,813,000+

References

1. Ireland pubmed.ncbi.nlm.nih.gov

Diagnosing uterine cervical cancer on a single T2-weighted image: Comparison between deep learning versus radiologists. [2021]

2. Switzerland pubmed.ncbi.nlm.nih.gov

Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer. [2022]

3. England pubmed.ncbi.nlm.nih.gov

Comparison between readout-segmented and single-shot echo-planar imaging in the evaluation of cervical cancer staging. [2020]

4. Germany pubmed.ncbi.nlm.nih.gov

The PRICE study: The role of conventional and diffusion-weighted magnetic resonance imaging in assessment of locally advanced cervical cancer patients administered by chemoradiation followed by radical surgery. [2020]

5. Germany pubmed.ncbi.nlm.nih.gov

Using deep learning to predict survival outcome in non-surgical cervical cancer patients based on pathological images. [2023]

6. United States pubmed.ncbi.nlm.nih.gov

Dynamic contrast-enhanced MR imaging of uterine cervical cancer: pharmacokinetic analysis with histopathologic correlation and its importance in predicting the outcome of radiation therapy. [2022]

7. Switzerland pubmed.ncbi.nlm.nih.gov

A Deep Learning Radiomics Nomogram to Predict Response to Neoadjuvant Chemotherapy for Locally Advanced Cervical Cancer: A Two-Center Study. [2023]

8. England pubmed.ncbi.nlm.nih.gov

A Combination Analysis of IVIM-DWI Biomarkers and T2WI-Based Texture Features for Tumor Differentiation Grade of Cervical Squamous Cell Carcinoma. [2022]