Lars Grimm

Positions:

Associate Professor of Radiology

Radiology, Breast Imaging
School of Medicine

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Education:

B.S. 2004

Stanford University

M.D. 2009

Yale University School of Medicine

M.H.S. 2009

Yale University

Residency, Diagnostic Radiology

Duke University School of Medicine

Fellowship, Radiology, Breast Imaging

Duke University School of Medicine

Grants:

Tomosynthesis Mammographic Imaging Screening Trial (TMIST)

Administered By
Radiology, Breast Imaging
Role
Principal Investigator
Start Date
End Date

Prediction of upstaging DCIS to invasive disease: performance comparison between breast radiologists and computer vision algorithms

Administered By
Radiology, Breast Imaging
Awarded By
Radiological Society of North America
Role
Principal Investigator
Start Date
End Date

Tomosynthesis Mammographic Imaging Screening Trial (TMIST)

Administered By
Radiology, Breast Imaging
Awarded By
ECOG-ACRIN Medical Research Foundation Inc.
Role
Principal Investigator
Start Date
End Date

Mixed Methods Study of Trainee Perceptions of Radiology with a Focus on Gender and Racial Inequality

Administered By
Radiology, Breast Imaging
Awarded By
Association of University Radiologists Research and Education Foundation
Role
Principal Investigator
Start Date
End Date

Publications:

Microcalcification localization and cluster detection using unsupervised convolutional autoencoders and structural similarity index

© 2020 SPIE. Detecting microcalcification clusters in mammograms is important to the diagnosis of breast diseases. Previous studies which mainly focused on supervised methods require abundant annotated training data but these data are usually hard to acquire. In this work, we leverage unsupervised convolutional autoencoders and structural similarity (SSIM) based post-processing to detect and localize microcalcification clusters in full-field digital mammograms (FFDMs). Our models were trained by patches extracted from 3,632 normal cases, in total with 16,702 mammograms. Evaluations were conducted in three aspects, including patch-based anomaly detection, pixel-wise microcalcification localization, and microcalcification cluster detection. Specifically, the receiver operating characteristic (ROC) analysis was used for patch-based anomaly detection. Then, a pixel-wise ROC analysis and a cluster-based free-response ROC (FROC) analysis were performed to assess our detection algorithms of individual microcalcifications and microcalcification clusters, respectively. We achieved a pixel-wise AUC of 0.97 as well as a cluster-based sensitivity of 0.62 at 1 false positive per image and 0.75 at 2.5 false positives per image. Both qualitative and quantitative results demonstrated the effectiveness of our method.
Authors
Peng, Y; Hou, R; Ren, Y; Grimm, LJ; Marks, JR; Hwang, ES; Lo, JY
MLA Citation
Peng, Y., et al. “Microcalcification localization and cluster detection using unsupervised convolutional autoencoders and structural similarity index.” Progress in Biomedical Optics and Imaging  Proceedings of Spie, vol. 11314, 2020. Scopus, doi:10.1117/12.2551263.
URI
https://scholars.duke.edu/individual/pub1447091
Source
scopus
Published In
Progress in Biomedical Optics and Imaging Proceedings of Spie
Volume
11314
Published Date
DOI
10.1117/12.2551263

A multitask deep learning method in simultaneously predicting occult invasive disease in ductal carcinoma in-situ and segmenting microcalcifications in mammography

© 2020 SPIE. We proposed a two-branch multitask learning convolutional neural network to solve two different but related tasks at the same time. Our main task is to predict occult invasive disease in biopsy proven Ductal Carcinoma in-situ (DCIS), with an auxiliary task of segmenting microcalcifications (MCs). In this study, we collected digital mammography from 604 patients, 400 of which were DCIS. The model used patches with size of 512×512 extracted within a radiologist masked ROIs as input, with outputs including noisy MC segmentations obtained from our previous algorithms, and classification labels from final diagnosis at patients' definite surgery. We utilized a deep multitask model by combining both Unet segmentation networks and prediction classification networks, by sharing first several convolutional layers. The model achieved a patch-based ROC-AUC of 0.69, with a case-based ROC-AUC of 0.61. Segmentation results achieved a dice coefficient of 0.49.
Authors
Hou, R; Grimm, LJ; Mazurowski, MA; Marks, JR; King, LM; Maley, CC; Hwang, ES; Lo, JY
MLA Citation
Hou, R., et al. “A multitask deep learning method in simultaneously predicting occult invasive disease in ductal carcinoma in-situ and segmenting microcalcifications in mammography.” Progress in Biomedical Optics and Imaging  Proceedings of Spie, vol. 11314, 2020. Scopus, doi:10.1117/12.2549669.
URI
https://scholars.duke.edu/individual/pub1447092
Source
scopus
Published In
Progress in Biomedical Optics and Imaging Proceedings of Spie
Volume
11314
Published Date
DOI
10.1117/12.2549669

Major Factors Driving Expert Opinion on Preoperative Breast MRI Do Not Predict Additional Disease

Authors
MLA Citation
Grimm, Lars J. “Major Factors Driving Expert Opinion on Preoperative Breast MRI Do Not Predict Additional Disease.” Radiology: Imaging Cancer, vol. 2, no. 4, Radiological Society of North America (RSNA), July 2020, pp. e200025–e200025. Crossref, doi:10.1148/rycan.2020200025.
URI
https://scholars.duke.edu/individual/pub1450795
Source
crossref
Published In
Radiology: Imaging Cancer
Volume
2
Published Date
Start Page
e200025
End Page
e200025
DOI
10.1148/rycan.2020200025

Editorial for "Harmonization of Quantitative Parenchymal Enhancement in T1-Weighted Breast MRI".

Authors
MLA Citation
Grimm, Lars J. “Editorial for "Harmonization of Quantitative Parenchymal Enhancement in T1-Weighted Breast MRI".J Magn Reson Imaging, June 2020. Pubmed, doi:10.1002/jmri.27211.
URI
https://scholars.duke.edu/individual/pub1446760
PMID
32491242
Source
pubmed
Published In
J Magn Reson Imaging
Published Date
DOI
10.1002/jmri.27211

Performance of preoperative breast MRI based on breast cancer molecular subtype.

PURPOSE: To assess the performance of preoperative breast MRI biopsy recommendations based on breast cancer molecular subtype. METHODS: All preoperative breast MRIs at a single academic medical center from May 2010 to March 2014 were identified. Reports were reviewed for biopsy recommendations. All pathology reports were reviewed to determine biopsy recommendation outcomes. Molecular subtypes were defined as Luminal A (ER/PR+ and HER2-), Luminal B (ER/PR+ and HER2+), HER2 (ER-, PR- and HER2+), and Basal (ER-, PR-, and HER2-). Logistic regression assessed the probability of true positive versus false positive biopsy and mastectomy versus lumpectomy. RESULTS: There were 383 patients included with a molecular subtype distribution of 253 Luminal A, 44 Luminal B, 20 HER2, and 66 Basal. Two hundred and thirteen (56%) patients and 319 sites were recommended for biopsy. Molecular subtype did not influence the recommendation for biopsy (p = 0.69) or the number of biopsy site recommendations (p = 0.30). The positive predictive value for a biopsy recommendation was 42% overall and 46% for Luminal A, 43% for Luminal B, 36% for HER2, and 29% for Basal subtype cancers. The multivariate logistic regression model showed no difference in true positive biopsy rate based on molecular subtype (p = 0.78). Fifty-one percent of patients underwent mastectomy and the multivariate model demonstrated that only a true positive biopsy (odds ratio: 5.3) was associated with higher mastectomy rates. CONCLUSION: Breast cancer molecular subtype did not influence biopsy recommendations, positive predictive values, or surgical approaches. Only true positive biopsies increased the mastectomy rate.
Authors
Devalapalli, A; Thomas, S; Mazurowski, MA; Saha, A; Grimm, LJ
MLA Citation
Devalapalli, Amrita, et al. “Performance of preoperative breast MRI based on breast cancer molecular subtype.Clin Imaging, vol. 67, May 2020, pp. 130–35. Pubmed, doi:10.1016/j.clinimag.2020.05.017.
URI
https://scholars.duke.edu/individual/pub1450728
PMID
32619774
Source
pubmed
Published In
Clin Imaging
Volume
67
Published Date
Start Page
130
End Page
135
DOI
10.1016/j.clinimag.2020.05.017