Citations

Clear

12 citation(s) found for "Shukla, Dave".

AI and machine learning in medical imaging: key points from development to translation
Samala, Ravi K. , Chan, Heang‐Ping , Petrick, Nicholas , Mahmood, Usman , Summers, Ronald M. , Yoshida, Hiroyuki , Huo, Zhimin, Vergara, Daniel , Mazurchuk, Richard, Grizzard, Kevin , Suzuki, Kenji , Armato, Samuel G. , Shukla-Dave, Amita , Chan, Heang-Ping , Mahmood, Usman , Summers, Ronald M , Deserno, Thomas M , Yoshida, Hiroyuki , Drukker, Karen , Huisman, Henkjan , Samala, Ravi K , Drukker, Karen , Shukla‐Dave, Amita , Sahiner, Berkman , Greenspan, Hayit , Tourassi, Georgia D. , Regge, Daniele , Näppi, Janne J. , Chen, Quan , Morra, Lia , Hadjiiski, Lubomir M.

Mayo Clinic

BJR|Artificial Intelligence | April 29, 2024 | Volume: 1 | Issue: 1 | Pages: No page available

10.1093/bjrai/ubae006 | PMID 38828430 Get It

Abstract Innovation in medical imaging artificial intelligence (AI)/machine learning (ML) demands extensive data collection, algorithmic advancements, and rigorous performance assessments encompassing aspects such as generalizability, uncertainty, bias, fairness, trustworthiness, and interpretability. Achieving widespread integration of AI/ML algorithms into diverse clinical tasks will demand a steadfast commitment to overcoming issues in model design, development, and performance assessment. The complexities of AI/ML clinical translation present substantial challenges, requiring engagement with relevant stakeholders, assessment of cost-effectiveness for user and patient benefit, timely dissemination of information relevant to robust functioning throughout the AI/ML lifecycle, consideration of regulatory compliance, and feedback loops for real-world performance evidence. This commentary addresses several hurdles for the development and adoption of AI/ML technologies in medical imaging. Comprehensive attention to these underlying and often subtle factors is critical not only for tackling the challenges but also for exploring novel opportunities for the advancement of AI in radiology.
Artificial intelligence in medicine: mitigating risks and maximizing benefits via quality assurance, quality control, and acceptance testing
Mahmood, Usman , Chan, Heang‐Ping , Drukker, Karen , Samala, Ravi K. , Vergara, Daniel , Petrick, Nicholas , Huo, Zhimin, Summers, Ronald M. , Cha, Kenny H, Grizzard, Kevin , Yoshida, Hiroyuki , Mazurchuk, Richard, Suzuki, Kenji , Armato, Samuel G. , Chan, Heang-Ping , Drukker, Karen , Samala, Ravi K , Vergara, Daniel , Petrick, Nicholas , Summers, Ronald M , Deserno, Thomas M , Shukla‐Dave, Amita , Chen, Quan , Greenspan, Hayit , Sahiner, Berkman , Cha, Kenny H, Tourassi, Georgia D. , Näppi, Janne J. , Regge, Daniele , Morra, Lia , Huisman, Henkjan , Hadjiiski, Lubomir M.

Mayo Clinic

BJR|Artificial Intelligence | March 4, 2024 | Volume: 1 | Issue: 1 | Pages: No page available

10.1093/bjrai/ubae003 | PMID 38476957 Get It

Abstract The adoption of artificial intelligence (AI) tools in medicine poses challenges to existing clinical workflows. This commentary discusses the necessity of context-specific quality assurance (QA), emphasizing the need for robust QA measures with quality control (QC) procedures that encompass (1) acceptance testing (AT) before clinical use, (2) continuous QC monitoring, and (3) adequate user training. The discussion also covers essential components of AT and QA, illustrated with real-world examples. We also highlight what we see as the shared responsibility of manufacturers or vendors, regulators, healthcare systems, medical physicists, and clinicians to enact appropriate testing and oversight to ensure a safe and equitable transformation of medicine through AI.
The ISMRM Open Science Initiative for Perfusion Imaging (OSIPI): Results from the OSIPI–Dynamic Contrast‐Enhanced challenge
Shalom, Eve , Kim, Harrison , Heijden, Rianne A. van der , Ahmed, Zaki , Patel, Reyna, DiCarlo, Julie C. , Yankeelov, Thomas E. , Stokes, Ashley M. , Grech‐Sollars, Matthew , Sahoo, Prativa , Verma, Sanjay Kumar , Rathore, Divya, Kazerouni, Anum S. , LoCastro, Eve , Paudyal, Ramesh , Wolansky, Ivan A. , Shukla‐Dave, Amita , Schouten, Pepijn, Gurney‐Champion, Oliver J. , Macíček, Ondřej , Vitouš, Jiří , Das, Ayesha , Mikheev, Artem , Rusinek, Henry , Cristinacce, Penny L. Hubbard , Little, Ross A. , Cheung, Susan , O’Connor, James P.B. , Moloney, Brendan, Bobholz, Samuel , Duenweg, Savannah , Laue, Hendrik , Sung, Kyunghyun , Nabavizadeh, Ali , Rad, Hamidreza Saligheh , Hu, Leland , Kazerooni, Anahita Fathi , Shalom, Eve S , van der Heijden, Rianne A , Hormuth, David A , DiCarlo, Julie C , Yankeelov, Thomas E , Dortch, Richard D , Grech-Sollars, Matthew , Kazerouni, Anum S , Partridge, Savannah C , LoCastro, Eve , Wolansky, Ivan A , Jiřík, Radovan , Macíček, Ondřej , Bartoš, Michal , Vitouš, Jiří , Das, Ayesha Bharadwaj , Kim, S Gene , Rusinek, Henry , Berks, Michael , Hubbard Cristinacce, Penny L , O'Connor, James P B , Parker, Geoff J M , LaViolette, Peter S , Bobholz, Samuel , Duenweg, Savannah , Virostko, John , Sung, Kyunghyun , Saligheh Rad, Hamidreza , Sourbron, Steven , Bell, Laura C , Fathi Kazerooni, Anahita , Paudyal, Ramesh , Shukla-Dave, Amita , Sisco, Nicholas J. , Inglese, Marianna , Toschi, Nicola , Singh, Anup K. , Schouten, Pepijn, Bokacheva, Louisa , Bell, Laura C.

Mayo Clinic

Magnetic Resonance in Medicine | December 20, 2023 | Volume: 91 | Issue: 5 | Pages: 1803-1821

10.1002/mrm.29909 | PMID 38115695 Get It

AbstractPurpose has often been proposed as a quantitative imaging biomarker for diagnosis, prognosis, and treatment response assessment for various tumors. None of the many software tools for quantification are standardized. The ISMRM Open Science Initiative for Perfusion Imaging–Dynamic Contrast‐Enhanced (OSIPI‐DCE) challenge was designed to benchmark methods to better help the efforts to standardize measurement.MethodsA framework was created to evaluate values produced by DCE‐MRI analysis pipelines to enable benchmarking. The perfusion MRI community was invited to apply their pipelines for quantification in glioblastoma from clinical and synthetic patients. Submissions were required to include the entrants' values, the applied software, and a standard operating procedure. These were evaluated using the proposed score defined with accuracy, repeatability, and reproducibility components.ResultsAcross the 10 received submissions, the score ranged from 28% to 78% with a 59% median. The accuracy, repeatability, and reproducibility scores ranged from 0.54 to 0.92, 0.64 to 0.86, and 0.65 to 1.00, respectively (0–1 = lowest–highest). Manual arterial input function selection markedly affected the reproducibility and showed greater variability in analysis than automated methods. Furthermore, provision of a detailed standard operating procedure was critical for higher reproducibility.ConclusionsThis study reports results from the OSIPI‐DCE challenge and highlights the high inter‐software variability within estimation, providing a framework for ongoing benchmarking against the scores presented. Through this challenge, the participating teams were ranked based on the performance of their software tools in the particular setting of this challenge. In a real‐world clinical setting, many of these tools may perform differently with different benchmarking methodology.
Prospective Randomized Trial of Continuous Passive Motion Versus Physical Therapy After Arthroscopic Release of Elbow Contracture
O’Driscoll, Shawn W., Liévano, Jorge Rojas , Morrey, Mark E. , Sánchez‐Sotelo, Joaquín , Shukla, Dave R. , Olson, Tammy S. , O’Driscoll, Shawn W. , Vaichinger, Anthony M. , Shields, Maegan N. , Fitzsimmons, James S , Sanchez-Sotelo, J. , Morrey, Mark E , Lievano, Jorge Rojas , Shukla, Dave R. , Olson, Tammy S. , Vaichinger, Anthony M. , Shields, Maegan N.

Mayo Clinic

Journal of Bone and Joint Surgery | March 2, 2022 | Volume: 104 | Issue: 5 | Pages: 430-440

10.2106/jbjs.21.00685 | PMID 35234723 Get It

Background: Continuous passive motion (CPM) has been used for decades, but we are not aware of any randomized controlled trials (RCTs) in which CPM has been compared with physical therapy (PT) for rehabilitation following release of elbow contracture. Methods: In this single-blinded, single-center RCT, we randomly assigned patients undergoing arthroscopic release of elbow contracture to a rehabilitation protocol involving either CPM or PT. The primary outcomes were the rate of recovery and the arc of elbow motion (range of motion) at 1 year. The rate of recovery was evaluated by measuring range of motion at 6 weeks and 3 months. The secondary outcomes included other range-of-motion-related outcomes, patient-reported outcome measures (PROMs), flexion strength and endurance, grip strength, and forearm circumference at multiple time points. Results: A total of 24 patients were assigned to receive CPM, and 27 were assigned to receive PT. At 1 year, CPM was superior to PT with regard to the range of motion, with an estimated treatment difference of 9° (95% confidence interval [CI], 3° to 16°; p = 0.007). Similarly, the use of CPM led to a greater range of motion at 6 weeks and 3 months than PT. The percentage of lost motion recovered at 1 year was higher in the CPM group (51%) than in the PT group (36%) (p = 0.01). The probability of restoring a functional range of motion at 1 year was 62% higher in the CPM group than in the PT group (risk ratio for functional range of motion, 1.62; 95% CI, 1.01 to 2.61; p = 0.04). PROM scores were similar in the 2 groups at all time points, except for a difference in the American Shoulder and Elbow Surgeons (ASES) elbow function subscale, in favor of CPM, at 6 weeks. The use of CPM decreased swelling and reduced the loss of flexion strength, flexion endurance, and grip strength on day 3, with no between-group differences thereafter. Conclusions: Among patients undergoing arthroscopic release of elbow contracture, those who received CPM obtained a faster recovery and a greater range of motion at 1 year, with a higher chance of restoration of functional elbow motion than those who underwent routine PT. Level of Evidence: Therapeutic Level I . See Instructions for Authors for a complete description of levels of evidence.
Patients Use Fewer Opioids Than Prescribed After Arthroscopic Release of Elbow Contracture: An Evidence‐Based Opioid Prescribing Guideline to Reduce Excess
Liévano, Jorge Rojas , Rotman, Dani , Shields, Maegan N. , Sánchez‐Sotelo, Joaquín , Shukla, Dave R. , Olson, Tammy S. , Vaichinger, Anthony M. , O’Driscoll, Shawn W. , Rojas Lievano, Jorge, Sanchez-Sotelo, Joaquin, Fitzsimmons, James S. , O'Driscoll, Shawn W., Sanchez-Sotelo, J. , Fitzsimmons, James S , Morrey, Mark E. , Olson, Tammy, Lievano, Jorge Rojas , Shukla, Dave R.

Mayo Clinic

Arthroscopy, Sports Medicine, and Rehabilitation | November 17, 2021 | Volume: 3 | Issue: 6 | Pages: No page available

10.1016/j.asmr.2021.09.002 | PMID 34977643 Get It

Purpose To generate an evidence‐based opioid‐prescribing guideline by assessing the pattern of total opioid consumption and the factors that may predict opioid consumption following arthroscopic release of elbow contracture and to investigate whether the use of continuous passive motion (CPM), as compared to physical therapy (PT), was associated with a decrease in pain and opioid consumption after arthroscopic release of elbow contracture. Methods Data collected from a randomized controlled trial that compared continuous passive motion (CPM) ( n = 24) to physical therapy (PT) ( n = 27) following arthroscopic release of elbow contracture was analyzed for opioid use. Fifty‐one participants recorded their daily opioid consumption in a postoperative diary for 90 days. Multivariate analysis was performed to identify factors associated with opioid use. Recommended quantities for postoperative prescription were generated using the 50th percentile for patients without and the 75th percentile for patients with factors associated with higher opioid use. Results The median total opioid prescription was 437.5‐mg morphine milligram equivalents (MMEs) (58 pills of 5 mg oxycodone) and the median total opioid consumption was 75 MMEs (10 pills of 5‐mg oxycodone). Twenty‐two percent of patients took no opioid medication, 53% took ≤10 pills, 69% took ≤20 pills and 75% took ≤30 pills. Predictors of higher opioid use were preoperative opioid use, age <60 years and inflammatory arthritis. The total opioid consumption appeared similar between the CPM and the PT group. Seventy‐five percent of patient’s home opioid requirements would be satisfied using the following guideline: Patients undergoing contracture release for osteoarthritis or post‐traumatic contracture should be given a prescription for 10 pills of 5 mg oxycodone or its equivalent at discharge. Patients with inflammatory conditions or those taking preoperative opioids should be prescribed 30 pills of 5 mg oxycodone or its equivalent. Conclusion This study suggests that most patients undergoing arthroscopic release of elbow contracture use relatively few opioid pills after surgery. Use of an evidence‐based guideline could decrease opioid prescriptions substantially, while still effectively treating patients’ pain.
Precision Radiotherapy: Reduction in Radiation for Oropharyngeal Cancer in the 30 ROC Trial
Sherman, Eric J. , Pei, Xin , Grkovski, Milan , Paudyal, Ramesh , Katabi, Nora , Yamaguchi, Takafumi N. , Daniel, J. , Lee, Simon , Shah, Rachna , Ratnakumar, Abhirami , Salcedo, Adriana , Tsai, C. Jillian , McBride, Sean M. , Boyle, Jay, Singh, Bhuvanesh , Damerla, Rama Rao , Paula, Arnaud Da Cruz , Price, Katharine A. , Moore, Eric J. , García, Joaquín J. , Foote, Robert L. , Humm, John L. , Shukla‐Dave, Amita , Pfister, David G. , Lee, Nancy Y. , Pei, Xin , Grkovski, Milan , Paudyal, Ramesh , Yamaguchi, Takafumi N , Ma, Daniel , Shah, Rachna , Kumar, Rahul , Kuo, Fengshen , Ratnakumar, Abhirami , Tsai, Chiaojung J , Morris, Luc G T , Higginson, Daniel S , Price, Katharine, Moore, Eric J , Foote, Robert , Boutros, Paul C , Shukla-Dave, Amita , Riaz, Nadeem , Schöder, Heiko , Selenica, Pier , Kumar, Rahul , Kuo, Fengshen , Aleynick, Nathan , Brown, David N. , Zhang, Zhigang , Hatzoglou, Vaios , Liu, Lydia , Higginson, Daniel S. , Ho, Alan L. , Wong, Richard J. , Chan, Timothy An-thy , Powell, Simon N. , Boutros, Paul C. , Reis‐Filho, Jorge S. , Tsai, CJillian

Mayo Clinic

JNCI: Journal of the National Cancer Institute | November 11, 2020 | Volume: 113 | Issue: 6 | Pages: 742-751

10.1093/jnci/djaa184 | PMID 33429428 Get It

Abstract Background Patients with human papillomavirus–related oropharyngeal cancers have excellent outcomes but experience clinically significant toxicities when treated with standard chemoradiotherapy (70 Gy). We hypothesized that functional imaging could identify patients who could be safely deescalated to 30 Gy of radiotherapy. Methods In 19 patients, pre- and intratreatment dynamic fluorine-18-labeled fluoromisonidazole positron emission tomography (PET) was used to assess tumor hypoxia. Patients without hypoxia at baseline or intratreatment received 30 Gy; patients with persistent hypoxia received 70 Gy. Neck dissection was performed at 4 months in deescalated patients to assess pathologic response. Magnetic resonance imaging (weekly), circulating plasma cell-free DNA, RNA-sequencing, and whole-genome sequencing (WGS) were performed to identify potential molecular determinants of response. Samples from an independent prospective study were obtained to reproduce molecular findings. All statistical tests were 2-sided. Results Fifteen of 19 patients had no hypoxia on baseline PET or resolution on intratreatment PET and were deescalated to 30 Gy. Of these 15 patients, 11 had a pathologic complete response. Two-year locoregional control and overall survival were 94.4% (95% confidence interval = 84.4% to 100%) and 94.7% (95% confidence interval = 85.2% to 100%), respectively. No acute grade 3 radiation–related toxicities were observed. Microenvironmental features on serial imaging correlated better with pathologic response than tumor burden metrics or circulating plasma cell-free DNA. A WGS-based DNA repair defect was associated with response (P = .02) and was reproduced in an independent cohort (P = .03). Conclusions Deescalation of radiotherapy to 30 Gy on the basis of intratreatment hypoxia imaging was feasible, safe, and associated with minimal toxicity. A DNA repair defect identified by WGS was predictive of response. Intratherapy personalization of chemoradiotherapy may facilitate marked deescalation of radiotherapy.
Correlation between hemolytic profile and phylotype of Cutibacterium acnes (formerly Propionibacterium acnes ) and orthopedic implant infection
Lee, Julia , Quaintance, Kerryl E. Greenwood, Shukla, Dave R. , Cofield, Robert H. , Sperling, John W. , Patel, Robin , Sánchez‐Sotelo, Joaquín , Greenwood Quaintance, Kerryl E, Sanchez-Sotelo, J. , Patel, Robin , Schuetz, Audrey N. , Shukla, Dave R.

Mayo Clinic

Shoulder & Elbow | August 10, 2019 | Volume: 12 | Issue: 6 | Pages: 390-398

10.1177/1758573219865884 | PMID 33281943 Get It

Introduction Cutibacterium acnes is a recognized culprit for implant-associated infections, but positive cultures do not always indicate clinically relevant infection. Studies have shown a correlation between the β-hemolytic phenotype of C. acnes and its infectious capacity, but correlation with genetic phylotype has not been performed in literature. The purpose of this study is to evaluate β-hemolysis phenotype, genetic phylotype, and mid-term clinical outcomes of C. acnes isolated from orthopedic surgical sites. Methods Fifty-four C. acnes isolates previously obtained from surgical wounds of patients undergoing hip, knee, shoulder, or spine implant removal were re-cultured. There were 21 females and 33 males with an average age of 59 years (range, 18–84). Twenty-four were from clinically infected sites whereas 30 were considered contaminants. De novo β-hemolysis was analyzed and a retrospective chart review was performed to evaluate clinical outcomes at 7.1 years (range, 0.1–12.8). Results On Brucella agar with 5% rabbit blood, 46% of contaminant and 43% of infectious isolates were hemolytic. Type II phylotype was significantly more nonhemolytic regardless of infectious or contaminant status (p < 0.05). Type 1B correlated with a hemolytic-infectious phenotype and Type 1A with a hemolytic-contaminant phenotype but was not statistically significant. Conclusion The β-hemolytic profile of C. acnes did not correlate with phylotype or clinically relevant orthopedic infection.
Shoulder arthroplasty in patients with upper extremity lymphedema may result in transient or permanent lymphedema worsening
Lee, Julia , Nguyen, Ngoc Tram V. , Shukla, Dave R. , Sperling, John W. , Cofield, Robert H. , Sánchez‐Sotelo, Joaquín , Shukla, Dave, Sanchez-Sotelo, J. , Shukla, Dave R.

Mayo Clinic

Shoulder & Elbow | July 12, 2019 | Volume: 12 | Issue: 1_suppl | Pages: 53-60

10.1177/1758573219859473 | PMID 33343716 Get It

Introduction Upper extremity lymphedema can complicate mastectomy, lymph node dissection, and radiation. The purpose of this study is to present the outcomes of shoulder arthroplasty in patients with lymphedema. Methods The 19 shoulders with a shoulder arthroplasty and lymphedema on the surgical side (6 anatomic, 12 reverse, 1 hemiarthroplasty) were followed for four years (1–10 years). There were 2 males and 17 females; average age was 67.8 (48–86) years. Breast carcinoma was the most common reason for lymphedema (75%). A dedicated lymphedema questionnaire could be completed for 14 shoulders. Results Pain improved from moderate or severe preoperatively to no or mild in 18 shoulders. Motion improved in elevation (55° preoperatively, 107° at last follow-up), external rotation (14°, 43°), and internal rotation (sacrum, L5). Complications included an acromion stress fracture with a deep infection (1), deep infection (1), superficial infection (1), and glenoid loosening (1). Lymphedema worsened in nine cases, but worsening was permanent in only four. Currently, lymphedema treatment is being performed by 93% of survey respondents. No patients reported lymphangitis or lymphangiosarcoma. Conclusion Shoulder arthroplasty for an upper extremity with lymphedema provides substantial improvements in pain and motion; however, infection is a concerning complication. Fifty percent of the patients will experience worsening of their lymphedema and in 20% worsening may be permanent.
Automated three-dimensional measurements of version, inclination, and subluxation
Shukla, Dave R. , McLaughlin, Richard J. , Lee, Julia , Nguyen, Ngoc Tram V. , Sanchez-Sotelo, Joaquin, Sánchez‐Sotelo, Joaquín , Shukla, Dave R.

Mayo Clinic

Shoulder & Elbow | February 6, 2019 | Volume: 12 | Issue: 1 | Pages: 31-37

10.1177/1758573218825480 | PMID 32010231 Get It

Background Preoperative planning software has been developed to measure glenoid version, glenoid inclination, and humeral head subluxation on computed tomography (CT) for shoulder arthroplasty. However, most studies analyzing the effect of glenoid positioning on outcome were done prior to the introduction of planning software. Thus, measurements obtained from the software can only be extrapolated to predict failure provided they are similar to classic measurements. The purpose of this study was to compare measurements obtained using classic manual measuring techniques and measurements generated from automated image analysis software. Methods Ninety-five two-dimensional computed tomography scans of shoulders with primary glenohumeral osteoarthritis were measured for version according to Friedman method, inclination according to Maurer method, and subluxation according to Walch method. DICOM files were loaded into an image analysis software (Blueprint, Wright Medical) and the output was compared with values obtained manually using a paired sample t-test. Results Average manual measurements included 13.8° version, 13.2° inclination, and 56.2% subluxation. Average image analysis software values included 17.4° version (3.5° difference, p < 0.0001), 9.2° inclination (3.9° difference, p < 0.001), and 74.2% for subluxation (18% difference, p < 0.0001). Conclusions Glenoid version and inclination values from the software and manual measurement on two-dimensional computed tomography were relatively similar, within approximately 4°. However, subluxation measurements differed by approximately 20%.