David Mills

David Mills

Auto-generated profile, based on publicly available information

David Mills

GE HealthCare Technology & Innovation Center, Niskayuna, NY, 12309, USA

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2007 in The Journal of the Acoustical Society of America
Verified
Journal Article
Closed access
DMDavid M. Mills
David M. Mills
MFM. Patrick Feeney
M. Patrick Feeney
EDEli J. Drake
Eli J. Drake
RFRichard C. Folsom
Richard C. Folsom
LSLianne Sheppard
Lianne Sheppard
NSNoah S. Seixas
Noah S. Seixas
Characteristics of distortion product otoacoustic emission (DPOAE) measurements were investigated by comparing responses from two different emission measurement systems in 40 volunteers (78 ears) and making test-retest measurements of each system in 20 ears. For transformation of results between systems, it was shown that the minimum data set consisted of input-output (growth) functions obtained by stepping stimulus levels across a wide range, for each set of stimulus frequencies (1-8 kHz). Linear transformations were considered which involved either recalibration of the emission amplitude (vertical transformation) or of the stimulus levels (horizontal transformation). Horizontal transformations provided better agreement between growth functions from the two systems. For frequencies 4-8 kHz, the means of the horizontal shifts required ranged from 8 to 14 dB, clearly exceeding test-retest variability. The optimal horizontal transformation was derived and applied uniformly to all emission measurements; correlations r=0.81-0.89 were found between transformed emission amplitudes. To minimize the necessity for such transformations and to reduce the variability found both within and between systems, development of standardized equipment and methods is suggested for DPOAE measurements, including: (1) an optimized in-ear probe assembly; (2) use of intensity calibration; and (3) a focus on emission "threshold" measurement and analysis.

1 July 2021 in Physica Medica
Verified
Journal Article
Closed access
BBBryan P. Bednarz
Bryan P. Bednarz
SJSydney Jupitz
Sydney Jupitz
WLWarren Lee
Warren Lee
DMDavid Mills
David Mills
HCHeather Chan
Heather Chan
TFThomas K. Foo
Thomas K. Foo

19 April 2005
Verified
Conference Paper
Closed access
MZM.J. Zipparo
M.J. Zipparo
COC.G. Oakley
C.G. Oakley
DMD.M. Mills
D.M. Mills
ADA.M. Dentinger
A.M. Dentinger
LSL.S. Smith
L.S. Smith

5 April 2025 in Bioengineering
Verified
Journal Article
Open access
PDF file
JQJianwei Qiu
Jianwei Qiu
GKGrigorios M. Karageorgos
Grigorios M. Karageorgos
XPXiaorui Peng
Xiaorui Peng
SGSoumya Ghose
Soumya Ghose
ZYZhaoyuan Yang
Zhaoyuan Yang
DMDavid Mills
David Mills
Rheumatoid arthritis (RA) is a chronic autoimmune disease that can cause severe joint damage and functional impairment. Ultrasound imaging has shown promise in providing real-time assessment of synovium inflammation associated with the early stages of RA. Accurate segmentation of the synovium region and quantification of inflammation-specific imaging biomarkers are crucial for assessing and grading RA. However, automatic segmentation of the synovium in 3D ultrasound is challenging due to ambiguous boundaries, variability in synovium shape, and inhomogeneous intensity distribution. In this work, we introduce a novel network architecture, Swin Transformers with Deep Attentive Features for 3D segmentation (SwinDAF3D), which integrates Swin Transformers into a Deep Attentive Features framework. The developed architecture leverages the hierarchical structure and shifted windows of Swin Transformers to capture rich, multi-scale and attentive contextual information, improving the modeling of long-range dependencies and spatial hierarchies in 3D ultrasound images. In a six-fold cross-validation study with 3D ultrasound images of RA patients’ finger joints (n = 72), our SwinDAF3D model achieved the highest performance with a Dice Score (DSC) of 0.838 ± 0.013, an Intersection over Union (IoU) of 0.719 ± 0.019, and Surface Dice Score (SDSC) of 0.852 ± 0.020, compared to 3D UNet (DSC: 0.742 ± 0.025; IoU: 0.589 ± 0.031; SDSC: 0.661 ± 0.029), DAF3D (DSC: 0.813 ± 0.017; IoU: 0.689 ± 0.022; SDSC: 0.817 ± 0.013), Swin UNETR (DSC: 0.808 ± 0.025; IoU: 0.678 ± 0.032; SDSC: 0.822 ± 0.039), UNETR++ (DSC: 0.810 ± 0.014; IoU: 0.684 ± 0.018; SDSC: 0.829 ± 0.027) and TransUNet (DSC: 0.818 ± 0.013; IoU: 0.692 ± 0.017; SDSC: 0.815 ± 0.016) models. This ablation study demonstrates the effectiveness of combining a Swin Transformers feature pyramid with a deep attention mechanism, improving the segmentation accuracy of the synovium in 3D ultrasound. This advancement shows great promise in enabling more efficient and standardized RA screening using ultrasound imaging.

24 June 2026 in Photoacoustics
Verified
Journal Article
Open access
XPXiaorui Peng
Xiaorui Peng
KKKyoungmo Koo
Kyoungmo Koo
JQJianwei Qiu
Jianwei Qiu
GKGrigorios Karageorgos
Grigorios Karageorgos
ADAaron Dentinger
Aaron Dentinger
Xueding WangXueding Wang
Xueding Wang
Aiming at an intelligent point-of-care imaging technology for rheumatology clinics, a fully automatic 3D photoacoustic (PA) and ultrasound (US) dual-modality system driven by a robot and powered by deep learning (DL)-based image processing was developed. Automated scanning of volumetric images from patient joints, plus DL-based tissue segmentation and quantification of imaging biomarkers, ensures that the measurements from this system are objective and reproducible. Clinical validation was conducted via a longitudinal study on 43 finger joints from patients affected by inflammatory arthritis. Using manual segmentations as the gold standard, our DL algorithm utilizing the 3D Deep Attentive Feature (DAF3D) model showed satisfactory performance in automatic segmentation of joint space and synovial region and achieved a Dice score of 0.77±0.03 and an IoU of 0.64±0.03. Based on the tissue segmentations facilitated by the DAF3D model, six volumetric imaging biomarkers reflecting the activity of arthritis and its change in response to the treatment were quantified, including hyperemia, blood oxygenation, US power Doppler, joint space echogenicity, joint space volume, and synovial volume. The imaging biomarkers quantified from DL-based segmentation and manual segmentation showed moderate to strong correlations (R: 0.41−0.86). Hyperemia quantified from PA imaging has the strongest association with the disease activity indicated by Clinical Assessment Questionnaire (CAQ) scores, with R2=0.41. Linear models combining the two biomarkers from PA imaging, the four biomarkers from US imaging, and all six imaging biomarkers rendered moderate to very strong associations with the disease activity scores, with R2 of 0.41, 0.26, and 0.52, respectively.

16 March 2020
Verified
Conference Paper
Closed access
PDF file
SGSoumya Ghose
Soumya Ghose
DMDavid M. Mills
David M. Mills
JMJhimli Mitra
Jhimli Mitra
LSL. Scott Smith
L. Scott Smith
Desmond Teck Beng YeoDesmond Teck Beng Yeo
Desmond Teck Beng Yeo
TFThomas F. Foo
Thomas F. Foo
Image guidance aids neurosurgeons in making critical clinical decisions of safe maximal resection of diseased tissue. The brain however undergoes significant non-linear structural deformation on account of dura opening and tumor resection. Deformable registration of pre-operative ultrasound to intra-operative ultrasound may be used in mapping of pre-operative planning MRI to intraoperative ultrasound. Such mapping may aid in determining tumor resection margins during surgery. In this work, brain structures visible in pre- and intra-operative 3D ultrasound were used for automatic deformable registration. A Gaussian mixture model was used to automatically segment structures of interest in pre- and intra-operative ultrasound and patch-based normalized cross-correlation was used to establish correspondences between segmented structures. An affine registration based on correspondences was followed by B-spline based deformable registration to register pre- and intra-operative ultrasound. Manually labelled landmarks in pre- and intra-operative ultrasound were used to quantify the mean target registration error. We achieve a mean target registration error of 1.43±0.8 mm when validated with 17 pre- and intra-operative ultrasound image volumes of a public dataset.