Timothy Lee Kline

Timothy Lee Kline

Auto-generated profile, based on publicly available information

Timothy Lee Kline

Department of Radiology, Mayo Clinic, Rochester, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
26 May 2017 in Journal of Digital Imaging
Verified
Journal Article
Open access
PDF file
TKTimothy L. Kline
Timothy L. Kline
PKPanagiotis Korfiatis
Panagiotis Korfiatis
MEMarie E. Edwards
Marie E. Edwards
JBJaime D. Blais
Jaime D. Blais
FCFrank S. Czerwiec
Frank S. Czerwiec
BEBradley J. Erickson
Bradley J. Erickson
Deep learning techniques are being rapidly applied to medical imaging tasks—from organ and lesion segmentation to tissue and tumor classification. These techniques are becoming the leading algorithmic approaches to solve inherently difficult image processing tasks. Currently, the most critical requirement for successful implementation lies in the need for relatively large datasets that can be used for training the deep learning networks. Based on our initial studies of MR imaging examinations of the kidneys of patients affected by polycystic kidney disease (PKD), we have generated a unique database of imaging data and corresponding reference standard segmentations of polycystic kidneys. In the study of PKD, segmentation of the kidneys is needed in order to measure total kidney volume (TKV). Automated methods to segment the kidneys and measure TKV are needed to increase measurement throughput and alleviate the inherent variability of human-derived measurements. We hypothesize that deep learning techniques can be leveraged to perform fast, accurate, reproducible, and fully automated segmentation of polycystic kidneys. Here, we describe a fully automated approach for segmenting PKD kidneys within MR images that simulates a multi-observer approach in order to create an accurate and robust method for the task of segmentation and computation of TKV for PKD patients. A total of 2000 cases were used for training and validation, and 400 cases were used for testing. The multi-observer ensemble method had mean ± SD percent volume difference of 0.68 ± 2.2% compared with the reference standard segmentations. The complete framework performs fully automated segmentation at a level comparable with interobserver variability and could be considered as a replacement for the task of segmentation of PKD kidneys by a human.

14 May 2019 in Journal of Digital Imaging
Verified
Journal Article
Open access
PDF file
KPKenneth A. Philbrick
Kenneth A. Philbrick
AWAlexander D. Weston
Alexander D. Weston
ZEYNETTIN AKKUSZEYNETTIN AKKUS
ZEYNETTIN AKKUS
TKTimothy L. Kline
Timothy L. Kline
PKPanagiotis Korfiatis
Panagiotis Korfiatis
BEBradley J. Erickson
Bradley J. Erickson
Deep-learning algorithms typically fall within the domain of supervised artificial intelligence and are designed to “learn” from annotated data. Deep-learning models require large, diverse training datasets for optimal model convergence. The effort to curate these datasets is widely regarded as a barrier to the development of deep-learning systems. We developed RIL-Contour to accelerate medical image annotation for and with deep-learning. A major goal driving the development of the software was to create an environment which enables clinically oriented users to utilize deep-learning models to rapidly annotate medical imaging. RIL-Contour supports using fully automated deep-learning methods, semi-automated methods, and manual methods to annotate medical imaging with voxel and/or text annotations. To reduce annotation error, RIL-Contour promotes the standardization of image annotations across a dataset. RIL-Contour accelerates medical imaging annotation through the process of annotation by iterative deep learning (AID). The underlying concept of AID is to iteratively annotate, train, and utilize deep-learning models during the process of dataset annotation and model development. To enable this, RIL-Contour supports workflows in which multiple-image analysts annotate medical images, radiologists approve the annotations, and data scientists utilize these annotations to train deep-learning models. To automate the feedback loop between data scientists and image analysts, RIL-Contour provides mechanisms to enable data scientists to push deep newly trained deep-learning models to other users of the software. RIL-Contour and the AID methodology accelerate dataset annotation and model development by facilitating rapid collaboration between analysts, radiologists, and engineers.

29 July 2022 in Gynecologic Oncology
Verified
Journal Article
Open access
PSPallabi Shrestha
Pallabi Shrestha
BPBhavya Poudyal
Bhavya Poudyal
SYSepideh Yadollahi
Sepideh Yadollahi
DWDarryl E. Wright
Darryl E. Wright
AGAdriana V. Gregory
Adriana V. Gregory
TKTimothy L. Kline
Timothy L. Kline
Machine learning, deep learning, and artificial intelligence (AI) are terms that have made their way into nearly all areas of medicine. In the case of medical imaging, these methods have become the state of the art in nearly all areas from image reconstruction to image processing and automated analysis. In contrast to other areas, such as brain and breast imaging, the impacts of AI have not been as strongly felt in gynecologic imaging. In this review article, we: (i) provide a background of clinically relevant AI concepts, (ii) describe methods and approaches in computer vision, and (iii) highlight prior work related to image classification tasks utilizing AI approaches in gynecologic imaging. A comprehensive search of several databases from each database's inception to March 18th, 2021, English language, was conducted. The databases included Ovid MEDLINE(R) and Epub Ahead of Print, In-Process & Other Non-Indexed Citations, and Daily, Ovid EMBASE, Ovid Cochrane Central Register of Controlled Trials, and Ovid Cochrane Database of Systematic Reviews and ClinicalTrials.gov. We performed an extensive literature review with 61 articles curated by three reviewers and subsequent sorting by specialists using specific inclusion and exclusion criteria. We summarize the literature grouped by each of the three most common gynecologic malignancies: endometrial, cervical, and ovarian. For each, a brief introduction encapsulating the AI methods, imaging modalities, and clinical parameters in the selected articles is presented. We conclude with a discussion of current developments, trends and limitations, and suggest directions for future study. This review article should prove useful for collaborative teams performing research studies targeted at the incorporation of radiological imaging and AI methods into gynecological clinical practice.

3 July 2019 in Journal of the American Society of Nephrology
Verified
Journal Article
Closed access
PDF file
MGMaatje D.A. van Gastel
Maatje D.A. van Gastel
MEMarie E. Edwards
Marie E. Edwards
VTVicente E. Torres
Vicente E. Torres
BEBradley J. Erickson
Bradley J. Erickson
RGRon T. Gansevoort
Ron T. Gansevoort
TKTimothy L. Kline
Timothy L. Kline
Significance Statement: Because renal function often remains stable in the early stages of autosomal dominant polycystic kidney disease (ADPKD), total kidney volume (TKV) is the most important biomarker of disease severity and progression. The authors developed and validated a fully automated method of simultaneously measuring TKV and total liver volume (TLV) as well as their growth rates from magnetic resonance images. Their findings indicate that the method’s performance is equivalent to the gold standard of manual tracing while requiring a fraction of the time and skill. This approach may address the unmet need for rapid and reliable assessment of TKV and TLV, allowing identification of patients with rapidly progressing ADPKD for emerging drug treatments and serving as a reliable alternative for assessment of disease progression in clinical trials. Background: The formation and growth of cysts in kidneys, and often liver, in autosomal dominant polycystic kidney disease (ADPKD) cause progressive increases in total kidney volume (TKV) and liver volume (TLV). Laborious and time-consuming manual tracing of kidneys and liver is the current gold standard. We developed a fully automated segmentation method for TKV and TLV measurement that uses a deep learning network optimized to perform semantic segmentation of kidneys and liver. Methods: We used 80% of a set of 440 abdominal magnetic resonance images (T2-weighted HASTE coronal sequences) from patients with ADPKD to train the network and the remaining 20% for validation. Both kidneys and liver were also segmented manually. To evaluate the method’s performance, we used an additional test set of images from 100 patients, 45 of whom were also involved in longitudinal analyses. Results: TKV and TLV measured by the automated approach correlated highly with manually traced TKV and TLV (intraclass correlation coefficients, 0.998 and 0.996, respectively), with low bias and high precision (<0.1%±2.7% for TKV and −1.6%±3.1% for TLV); this was comparable with inter-reader variability of manual tracing (<0.1%±3.5% for TKV and −1.5%±4.8% for TLV). For longitudinal analysis, bias and precision were <0.1%±3.2% for TKV and 1.4%±2.9% for TLV growth. Conclusions: These findings demonstrate a fully automated segmentation method that measures TKV, TLV, and changes in these parameters as accurately as manual tracing. This technique may facilitate future studies in which automated and reproducible TKV and TLV measurements are needed to assess disease severity, disease progression, and treatment response.

6 August 2020 in JCI Insight
Verified
Journal Article
Closed access
PDF file
SLSravanthi Lavu
Sravanthi Lavu
LVLisa E. Vaughan
Lisa E. Vaughan
SSSarah R. Senum
Sarah R. Senum
TKTimothy L. Kline
Timothy L. Kline
ACArlene B. Chapman
Arlene B. Chapman
PHPeter C. Harris
Peter C. Harris
BACKGROUND: A treatment option for autosomal dominant polycystic kidney disease (ADPKD) has highlighted the need to identify rapidly progressive patients. Kidney size/age and genotype have predictive power for renal outcomes, but their relative and additive value, plus associated trajectories of disease progression, are not well defined. METHODS: The value of genotypic and/or kidney imaging data (Mayo Imaging Class; MIC) to predict the time to functional (end-stage kidney disease [ESKD] or decline in estimated glomerular filtration rate [eGFR]) or structural (increase in height-adjusted total kidney volume [htTKV]) outcomes were evaluated in a Mayo Clinic PKD1/PKD2 population, and eGFR and htTKV trajectories from 20–65 years of age were modeled and independently validated in similarly defined CRISP and HALT PKD patients. RESULTS: Both genotypic and imaging groups strongly predicted ESKD and eGFR endpoints, with genotype improving the imaging predictions and vice versa; a multivariate model had strong discriminatory power (C-index = 0.845). However, imaging but not genotypic groups predicted htTKV growth, although more severe genotypic and imaging groups had larger kidneys at a young age. The trajectory of eGFR decline was linear from baseline in the most severe genotypic and imaging groups, but it was curvilinear in milder groups. Imaging class trajectories differentiated htTKV growth rates; severe classes had rapid early growth and large kidneys, but growth later slowed. CONCLUSION: The value of imaging, genotypic, and combined data to identify rapidly progressive patients was demonstrated, and reference values for clinical trials were provided. Our data indicate that differences in kidney growth rates before adulthood significantly define patients with severe disease. FUNDING: NIDDK grants: Mayo DK058816 and DK090728; CRISP DK056943, DK056956, DK056957, and DK056961; and HALT PKD DK062410, DK062408, DK062402, DK082230, DK062411, and DK062401.

19 July 2018 in Clinical Journal of the American Society of Nephrology
Verified
Journal Article
Closed access
PDF file
MEMarie E. Edwards
Marie E. Edwards
FCFouad T. Chebib
Fouad T. Chebib
MIMaria V. Irazabal
Maria V. Irazabal
TOTroy G. Ofstie
Troy G. Ofstie
LBLisa A. Bungum
Lisa A. Bungum
VTVicente E. Torres
Vicente E. Torres
Background and objectives: In the 3-year Tolvaptan Efficacy and Safety in Management of ADPKD and Its Outcomes (TEMPO) 3:4 and 1-year Replicating Evidence of Preserved Renal Function: an Investigation of Tolvaptan Safety and Efficacy in ADPKD (REPRISE) trials, tolvaptan slowed the decline of eGFR in patients with autosomal dominant polycystic kidney disease at early and later stages of CKD, respectively. Our objective was to ascertain whether the reduction associated with the administration of tolvaptan is sustained, cumulative, and likely to delay the need for kidney replacement therapy. Design, setting, participants, & measurements: One hundred and twenty-eight patients with autosomal dominant polycystic kidney disease participated in clinical trials of tolvaptan at the Mayo Clinic. All had the opportunity to enroll into open-label extension studies. Twenty participated in short-term studies or received placebo only. The remaining 108 were analyzed for safety. Ninety seven patients treated with tolvaptan for ≥1 year (mean±SD, 4.6±2.8; range, 1.1–11.2) were analyzed for efficacy using three approaches: (1) comparison of eGFR slopes and outcome (33% reduction from baseline eGFR) to controls matched by sex, age, and baseline eGFR; (2) Stability of eGFR slopes with duration of follow-up; and (3) comparison of observed and predicted eGFRs at last follow-up. Results: Patients treated with tolvaptan had lower eGFR slopes from baseline (mean±SD, −2.20±2.18 ml/min per 1.73 m2 per year) and from month 1 (mean±SD, −1.97±2.44 ml/min per 1.73 m2 per year) compared with controls (mean±SD, −3.50±2.09 ml/min per 1.73 m2 per year; P<0.001), and lower risk of a 33% reduction in eGFR (risk ratio, 0.63; 95% confidence interval, 0.38 to 0.98 from baseline; risk ratio, 0.53; 95% confidence interval, 0.31 to 0.85 from month 1). Annualized eGFR slopes of patients treated with tolvaptan did not change during follow-up and differences between observed and predicted eGFRs at last follow-up increased with duration of treatment. Conclusions: Follow-up for up to 11.2 years (average 4.6 years) showed a sustained reduction in the annual rate of eGFR decline in patients treated with tolvaptan compared with controls and an increasing separation of eGFR values over time between the two groups.