Mary Soo

Overview:

I am currently studying alternative and adjunctive imaging modalities for detecting carcinoma in the breast. This includes PET imaging, MRI and techniques for improvements in sonographic imaging. I am also studying various modalities for imaging breast implants.

Positions:

Professor of Radiology

Radiology, Breast Imaging
School of Medicine

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Education:

M.D. 1987

Wake Forest University

Grants:

Reducing Benign Breast Biopsies with Computer Modeling

Administered By
Radiology, Breast Imaging
Awarded By
National Institutes of Health
Role
Clinical Investigator
Start Date
End Date

FDG-PEM Detection - Characterization of Breast Cancer

Administered By
Radiology, Breast Imaging
Awarded By
National Institutes of Health
Role
Principal Investigator
Start Date
End Date

A novel strategy to see and treat breast cancer: translation to intra-operative breast margin assessment

Administered By
Biomedical Engineering
Awarded By
National Institutes of Health
Role
Co Investigator
Start Date
End Date

Pain, Distress and Mammography Use in Breast Cancer Patients

Administered By
Psychiatry & Behavioral Sciences, Behavioral Medicine
Awarded By
National Institutes of Health
Role
Co Investigator
Start Date
End Date

Computer-Aided Diagnosis Of Breast Cancer Invasion

Administered By
Radiology
Awarded By
National Institutes of Health
Role
Co Investigator
Start Date
End Date

Publications:

Ductal Carcinoma In Situ Biology, Language, and Active Surveillance: A Survey of Breast Radiologists' Knowledge and Opinions.

PURPOSE: To understand how breast radiologists perceive ductal carcinoma in situ (DCIS). MATERIALS AND METHODS: A 19-item survey was developed by the Society of Breast Imaging Patient Care and Delivery Committee and distributed to all Society of Breast Imaging members. The survey queried respondents' demographics, knowledge of DCIS biology, language used to discuss a new diagnosis of DCIS, and perspectives on active surveillance for DCIS. Five-point Likert scales (1 = strongly disagree, 3 = neutral, 5 = strongly agree) were used. RESULTS: There were 536 responses for a response rate of 41%. There was agreement that DCIS is the primary driver of overdiagnosis in breast cancer screening (median 4), and respondents provided mean and median overdiagnosis estimates of 29.7% and 25% for low-grade DCIS as well as 4.2% and 0% for high-grade DCIS, respectively. Responses varied in how to describe DCIS but most often used the word "cancer" with a qualifier such as "early" (32%) or "pre-invasive" (25%). Respondents disagreed (median 2) with removing the word "carcinoma" from DCIS. Finally, there was agreement that current standard of care therapy for some forms of DCIS is overtreatment (median 4) and that active surveillance as an alternative management strategy should be studied (mean 4), but felt that ultrasound (median 4) and MRI (median 4) should be used to exclude women with occult invasive disease before active surveillance. CONCLUSIONS: Breast radiologists' opinions about DCIS biology, language, and active surveillance are not homogenous, but general trends exist that can be used to guide research, education, and advocacy efforts.
Authors
Grimm, LJ; Destounis, SV; Rahbar, H; Soo, MS; Poplack, SP
MLA Citation
Grimm, Lars J., et al. “Ductal Carcinoma In Situ Biology, Language, and Active Surveillance: A Survey of Breast Radiologists' Knowledge and Opinions.J Am Coll Radiol, Apr. 2020. Pubmed, doi:10.1016/j.jacr.2020.03.004.
URI
https://scholars.duke.edu/individual/pub1436866
PMID
32278849
Source
pubmed
Published In
Journal of the American College of Radiology : Jacr
Published Date
DOI
10.1016/j.jacr.2020.03.004

Dreams prior to biopsy for suspected breast cancer: A preliminary survey.

Warning dreams prior to the onset of symptoms have been reported in a previous survey of self-selected women with breast cancer. There is no available data on how many women with suspected breast cancer have such dreams, so anonymous surveys were offered to women who came for biopsy at a university breast imaging center over a period of 3 months. 163 women completed the survey reporting that 64% usually remember their dreams, 41% have had dreams that came true, and 5% keep a dream diary. 5.5% reported dreaming the word "cancer," but only one woman was prompted to have a breast evaluation because of a dream. This pilot data will be used in planning a future study with pathological correlation.
Authors
Burk, L; Wehner, D; Soo, MS
MLA Citation
Burk, Larry, et al. “Dreams prior to biopsy for suspected breast cancer: A preliminary survey.Explore (Ny), Mar. 2020. Pubmed, doi:10.1016/j.explore.2020.03.002.
URI
https://scholars.duke.edu/individual/pub1436865
PMID
32268982
Source
pubmed
Published In
Explore (Ny)
Published Date
DOI
10.1016/j.explore.2020.03.002

Unmet spiritual care needs in women undergoing core needle breast biopsy

© Society of Breast Imaging 2020. All rights reserved. Objective: Spiritual care is an important part of healthcare, especially when patients face a possible diagnosis of a life-threatening disease. This study examined the extent to which women undergoing core-needle breast biopsy desired spiritual support and the degree to which women received the support they desired. Methods: Participants (N = 79) were women age 21 and older, who completed an ultrasound- or stereotactic-guided core-needle breast biopsy. Participants completed measures of spiritual needs and spiritual care. Medical and sociodemographic information were also collected. Independent sample t-tests and chi-square tests of examined differences based on demographic, medical, and biopsy-related variables. Results: Forty-eight participants (48/79; 60.8%) desired some degree of spiritual care during their breast biopsy, and 33 participants (33/78; 42.3%) wanted their healthcare team to address their spiritual needs. African American women were significantly more likely to desire some type of spiritual support compared to women who were not African American. Among the 79 participants, 16 (20.3%) reported a discrepancy between desired and received spiritual support. A significant association between discrepancies and biopsy results was found, χ2(1) = 4.19, P = .04, such that 2 (7.4%) of 27 participants with results requiring surgery reported discrepancies, while 14 (26.9%) of 52 participants with a benign result reported discrepancies. Conclusion: Most women undergoing core-needle breast biopsy desired some degree of spiritual care. Although most reported that their spiritual needs were addressed, a subset of women received less care than desired. Our results suggest that healthcare providers should be aware of patients' desires for spiritual support, particularly among those with benign results.
Authors
van Denburg, AN; Shelby, RA; Winger, JG; Zhang, L; Soo, AE; Pearce, MJ; Soo, MS
MLA Citation
van Denburg, A. N., et al. “Unmet spiritual care needs in women undergoing core needle breast biopsy.” Journal of Breast Imaging, vol. 2, no. 1, Mar. 2020, pp. 134–40. Scopus, doi:10.1093/jbi/wbz089.
URI
https://scholars.duke.edu/individual/pub1430842
Source
scopus
Published In
Journal of Breast Imaging
Volume
2
Published Date
Start Page
134
End Page
140
DOI
10.1093/jbi/wbz089

Computer aided prediction of breast implant rupture based on mammographic findings

© 1995 SPIE. All rights reserved. A computer aided diagnostic system has been developed to predict the status of a breast implant (intact/ruptured) based on mammographic findings. Mammograms were obtained from 112 patients who presented for surgical removal of breast implants. Findings were recorded by radiologists for each patient. Of these 112 cases, 77 were ruptured while 35 were intact at the time of surgery. An artificial neural network (ANN) was trained to output the implant status when given the mammographic findings as inputs. The ANN was a backpropagation network with nine inputs, one hidden layer with 4 nodes, and one output node (implant status). The network was trained using the round-robin technique and evaluated using ROC analysis. The network performed well with an ROC area of 0.84. This was better than the radiologists's performance with sensitivity of 0.67 and specificity of 0.72. At a sensitivity of 0.67 (to match the radiologists), the network had a specificity of 0.89. At a specificity of 0.72 (to match the radiologists), the network had a sensitivity of 0.78. An ANN has been developed which demonstrates encouraging diagnostic performance for predicting the status of breast implants from mammographic findings.
Authors
Floyd, CE; Soo, MS; Tourassi, GD; Kornguth, PJ
MLA Citation
Floyd, C. E., et al. “Computer aided prediction of breast implant rupture based on mammographic findings.” Proceedings of Spie  the International Society for Optical Engineering, vol. 2434, 1995, pp. 471–77. Scopus, doi:10.1117/12.208718.
URI
https://scholars.duke.edu/individual/pub1425312
Source
scopus
Published In
Smart Structures and Materials 2005: Active Materials: Behavior and Mechanics
Volume
2434
Published Date
Start Page
471
End Page
477
DOI
10.1117/12.208718

Machine learning-based prediction of future breast cancer using algorithmically measured background parenchymal enhancement on high-risk screening MRI.

BACKGROUND: Preliminary work has demonstrated that background parenchymal enhancement (BPE) assessed by radiologists is predictive of future breast cancer in women undergoing high-risk screening MRI. Algorithmically assessed measures of BPE offer a more precise and reproducible means of measuring BPE than human readers and thus might improve the predictive performance of future cancer development. PURPOSE: To determine if algorithmically extracted imaging features of BPE on screening breast MRI in high-risk women are associated with subsequent development of cancer. STUDY TYPE: Case-control study. POPULATION: In all, 133 women at high risk for developing breast cancer; 46 of these patients developed breast cancer subsequently over a follow-up period of 2 years. FIELD STRENGTH/SEQUENCE: 5 T or 3.0 T T1 -weighted precontrast fat-saturated and nonfat-saturated sequences and postcontrast nonfat-saturated sequences. ASSESSMENT: Automatic features of BPE were extracted with a computer algorithm. Subjective BPE scores from five breast radiologists (blinded to clinical outcomes) were also available. STATISTICAL TESTS: Leave-one-out crossvalidation for a multivariate logistic regression model developed using the automatic features and receiver operating characteristic (ROC) analysis were performed to calculate the area under the curve (AUC). Comparison of automatic features and subjective features was performed using a generalized regression model and the P-value was obtained. Odds ratios for automatic and subjective features were compared. RESULTS: The multivariate model discriminated patients who developed cancer from the patients who did not, with an AUC of 0.70 (95% confidence interval: 0.60-0.79, P < 0.001). The imaging features remained independently predictive of subsequent development of cancer (P < 0.003) when compared with the subjective BPE assessment of the readers. DATA CONCLUSION: Automatically extracted BPE measurements may potentially be used to further stratify risk in patients undergoing high-risk screening MRI. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2019;50:456-464.
Authors
Saha, A; Grimm, LJ; Ghate, SV; Kim, CE; Soo, MS; Yoon, SC; Mazurowski, MA
MLA Citation
Saha, Ashirbani, et al. “Machine learning-based prediction of future breast cancer using algorithmically measured background parenchymal enhancement on high-risk screening MRI.J Magn Reson Imaging, vol. 50, no. 2, Aug. 2019, pp. 456–64. Pubmed, doi:10.1002/jmri.26636.
URI
https://scholars.duke.edu/individual/pub1365279
PMID
30648316
Source
pubmed
Published In
J Magn Reson Imaging
Volume
50
Published Date
Start Page
456
End Page
464
DOI
10.1002/jmri.26636