John Charnley Award: Deep Learning Prediction of Hip Joint Center on Standard Pelvis Radiographs

Jang, Seong Jun; Kunze, Kyle N.; Vigdorchik, Jonathan M.; Jerabek, Seth A.; Mayman, David J.; Sculco, Peter K.

doi:10.1016/j.arth.2022.03.033

Cited by 20 publications

(17 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…21 Such technology-assisted systems are dependent on computer modeling capabilities to enable surgeons and manufacturers to anticipate component placement based on individual anatomy derived from patient imaging, and therefore, it is plausible that this technology cluster has also experienced exponential patent growth. Moreover, advancements in the application of artificial intelligence [42][43][44][45] and virtual reality [46][47][48][49] have been observed using technological advancements in computer modeling and user interfaces for surgical systems, which may also explain its recent growth.…”

Section: Discussionmentioning

confidence: 99%

Quantifying 30 Years of Technological Innovation in Total Hip Arthroplasty

Kunze

Rullán

Potluri

et al. 2023

The Journal of Hip Surgery

Self Cite

View full text Add to dashboard Cite

Technological innovation in total hip arthroplasty (THA) is a critical component of health care delivery for improving patient outcomes. Analyzing the content of patents and trends in their activity over time can leverage insight into innovations in THA; however, these investigations remain underutilized. We aimed to quantify patent activity and relative growth pertaining to technologies in THA over a 30-year period. A query for patents relating to “hip replacement” or “hip arthroplasty” between 1989 and 2019 using an open-source patent database yielded 24,071 unique patents for analysis. These were grouped into 12 independent technology clusters using Cooperative Patent Classification codes. Annual patent activity for each cluster was normalized with a validated formula to control for exponential growth. The 5-, 10-, and 30-year compound annual growth rates (CAGR) for each cluster were quantified and compared between clusters. Annual cumulative patent activity increased from 151 patents in 1989 to 1,182 patents in 2019, representing a 682.8% increase. The largest technology clusters concerned “drugs” (n = 6,429 patents), “instruments” (n = 4,014 patents), “materials” (n = 2,037 patents), and “components” (n = 1,946 patents). One-half of the identified clusters concerned developments in technology-assisted THA (patient-specific instrumentation, navigation, robotics, design/manufacturing, instruments, and computer modeling). The most rapidly growing technology within the past 5, 10, and 30 years was robotics (CAGR = 15.82%, 20.11%, and 9.50%, respectively). Within the past 5- and 10-year trial prostheses (CAGR = 10.76%) and design/manufacturing processes (CAGR = 10.27%), computer modeling (CAGR = 12.91%) and navigation (CAGR = 11.25%) were among the most rapidly growing clusters, respectively. The majority of patents pertaining to THA over the past 30 years have concerned developments in drugs, instruments, materials, and components. Within the past 10-years, substantial growth has been observed in patent domains related to technology-assisted THA. Monitoring of emerging technologies through patent metrics may provide valuable information for regulatory bodies and assess progress in the field of THA. This is a cross-sectional study with level of evidence IV.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantifying 30 Years of Technological Innovation in Total Hip Arthroplasty

Kunze

Rullán

Potluri

et al. 2023

The Journal of Hip Surgery

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI) has gained considerable attention as a set of statistical methods capable of interpreting imaging in a rapid and objective manner [2, 8, 15, 27]. The application of AI offers a solution to limitations inherent in manual imaging assessments such as human subjectivity and difficulty with interpreting images of poor quality [9]. Deep learning, a specific subdivision of AI commonly used to perform imaging‐based tasks, has demonstrated high performance when developed to automate clinically relevant measurements in orthopedic patients such as prediction of the hip joint center, acetabular component angles, and spinopelvic parameters [7, 9, 18, 21, 26].…”

Section: Introductionmentioning

confidence: 99%

Radiographic findings involved in knee osteoarthritis progression are associated with pain symptom frequency and baseline disease severity: a population-level analysis using deep learning

Kunze

Jang

et al. 2022

Knee Surg Sports Traumatol Arthrosc

Self Cite

View full text Add to dashboard Cite

PurposeTo (1) develop a deep‐learning (DL) algorithm capable of producing limb‐length and knee‐alignment measurements, and (2) determine the association between limb‐length discrepancy (LLD), coronal‐plane alignment, osteoarthritis (OA) severity, and patient‐reported knee pain. MethodsA multicenter, prospective patient cohort from the Osteoarthritis Initiative between 2004 and 2015 with full‐limb standing radiographs at 12 month follow‐up was included. A convolutional neural network was developed to automate measurements of the hip–knee–ankle (HKA) angle, femur, and tibia lengths, and LLD. At 12 month follow‐up, patients reported their frequency of knee pain since enrollment and current level of knee pain. ResultsA total of 1011 patients (2022 knees, 52.3% female) with an average age of 61.2 ± 9.0 years were included. The algorithm performed 12,312 measurements in 5.4 h. ICC values of HKA and LLD ranged between 0.87 and 1.00 when compared against trained radiologist measurements. Knees producing pain most days of the month were significantly more varus (mean HKA:− 3.9° ± 2.8°) or valgus (mean HKA:2.8° ± 2.3°) compared to knees that did not produce any pain (p < 0.05). In varus knees, those producing pain on most days were part of the shorter limb compared to nonpainful knees (p < 0.05). Baseline Kellgren–Lawrence grade was significantly associated with HKA magnitude, LLD, and pain frequency at 12 month follow‐up (p < 0.05 all). ConclusionA higher frequency of knee pain was associated with more severe coronal plane deformity, with valgus deviation being one degree less than varus on average, suggesting that the knee tolerates less valgus deformation before symptoms become more consistent. Knee pain frequency was also associated with greater LLD and baseline KL grade, suggesting an association between radiographically apparent joint degeneration and pain frequency. Level of evidenceIV case series.

show abstract

“…object segmentation). 11,12 We are just beginning to see the potential of the applications of deep learning in our specialty.…”

mentioning

confidence: 99%

“…Algorithms of computer vision can also interpret immense numbers of images that are impossible or prohibitively time-consuming for a human to analyze. 11,12 As Gurung et al 24 report in this issue, few or no studies using deep learning have described the use of these tools in external settings. Nonetheless, the internal validation of deep learning models will continue to push the boundaries of what is possible in orthopaedic surgery.…”

mentioning

confidence: 99%