Artificial Intelligence Automation of Proptosis Measurement: An Indicator for Pediatric Orbital Abscess Surgery

被引:3
作者
Fu, Roxana [1 ]
Bandos, Andriy [2 ]
Leader, Joseph K. K. [3 ,4 ]
Melachuri, Samyuktha [5 ]
Pradeep, Tejus [6 ]
Bhatia, Aashim [7 ]
Narayanan, Srikala [8 ]
Campbell, Ashley A. A. [9 ]
Zhang, Matthew [10 ]
Sahel, Jose-Alain [1 ]
Pu, Jiantao [3 ,4 ]
机构
[1] Univ Pittsburgh, Dept Ophthalmol, Pittsburgh, PA USA
[2] Univ Pittsburgh, Dept Biostat, Pittsburgh, PA USA
[3] Univ Pittsburgh, Dept Radiol, Pittsburgh, PA USA
[4] Univ Pittsburgh, Dept Bioengn, Pittsburgh, PA USA
[5] Univ Pittsburgh, Sch Med, 1400 Locust St,Suite 500, Pittsburgh, PA 15219 USA
[6] Univ Penn, Dept Ophthalmol, Philadelphia, PA USA
[7] Childrens Hosp Philadelphia, Dept Radiol, Philadelphia, PA USA
[8] Childrens Hosp Pittsburgh, Dept Radiol, Pittsburgh, PA USA
[9] Johns Hopkins, Wilmer Eye Inst, Dept Ophthalmol, Baltimore, MD USA
[10] Univ Washington, Dept Ophthalmol, Seattle, WA USA
基金
美国国家卫生研究院;
关键词
Orbital cellulitis; Subperiosteal orbital abscess; Proptosis; Computed tomography (CT); Automation; SUBPERIOSTEAL ABSCESS; COMPUTED-TOMOGRAPHY; HERTEL EXOPHTHALMOMETRY; SURGICAL-MANAGEMENT; MEDICAL-MANAGEMENT; GLOBE POSITION; CELLULITIS; SINUSITIS; CRITERIA; COMPLICATIONS;
D O I
10.1007/s40123-023-00754-5
中图分类号
R77 [眼科学];
学科分类号
100212 ;
摘要
IntroductionTo evaluate the ability of artificial intelligence (AI) software to quantify proptosis for identifying patients who need surgical drainage.MethodsWe pursued a retrospective study including 56 subjects with a clinical diagnosis of subperiosteal orbital abscess (SPOA) secondary to sinusitis at a tertiary pediatric hospital from 2002 to 2016. AI computer software was developed to perform 3D visualization and quantitative assessment of proptosis from computed tomography (CT) images acquired at the time of hospital admission. The AI software automatically computed linear and volume metrics of proptosis to provide more practice-consistent and informative measures. Two experienced physicians independently measured proptosis using the interzygomatic line method on axial CT images. The AI software and physician proptosis assessments were evaluated for association with eventual treatment procedures as standalone markers and in combination with the standard predictors.ResultsTo treat the SPOA, 31 of 56 (55%) children underwent surgical intervention, including 18 early surgeries (performed within 24 h of admission), and 25 (45%) were managed medically. The physician measurements of proptosis were strongly correlated (Spearman r = 0.89, 95% CI 0.82-0.93) with 95% limits of agreement of & PLUSMN; 1.8 mm. The AI linear measurement was on average 1.2 mm larger (p = 0.007) and only moderately correlated with the average physicians' measurements (r = 0.53, 95% CI 0.31-0.69). Increased proptosis of both AI volumetric and linear measurements were moderately predictive of surgery (AUCs of 0.79, 95% CI 0.68-0.91, and 0.78, 95% CI 0.65-0.90, respectively) with the average physician measurement being poorly to fairly predictive (AUC of 0.70, 95% CI 0.56-0.84). The AI proptosis measures were also significantly greater in the early as compared to the late surgery groups (p = 0.02, and p = 0.04, respectively). The surgical and medical groups showed a substantial difference in the abscess volume (p < 0.001).ConclusionAI proptosis measures significantly differed from physician assessments and showed a good overall ability to predict the eventual treatment. The volumetric AI proptosis measurement significantly improved the ability to predict the likelihood of surgery compared to abscess volume alone. Further studies are needed to better characterize and incorporate the AI proptosis measurements for assisting in clinical decision-making.
引用
收藏
页码:2479 / 2491
页数:13
相关论文
共 39 条
[1]   Pediatric Subperiosteal Abscess Secondary to Acute Sinusitis: A Systematic Review and Meta-analysis [J].
Adil, Eelam A. ;
Muir, Molly E. ;
Kawai, Kosuke ;
Dombrowski, Natasha D. ;
Cunningham, Michael J. .
LARYNGOSCOPE, 2020, 130 (12) :2906-2912
[2]   Axial Globe Position Measurement: A Prospective Multicenter Study by the International Thyroid Eye Disease Society [J].
Bingham, Chad M. ;
Sivak-Callcott, Jennifer A. ;
Gurka, Matthew J. ;
Nguyen, John ;
Hogg, Jeffery P. ;
Feldon, Steve E. ;
Fay, Aaron ;
Seah, Lay-Leng ;
Strianese, Diego ;
Durairaj, Vikram D. ;
Uddin, Jimmy ;
Devoto, Martin H. ;
Harris, Matheson ;
Saunders, Justin ;
Osaki, Tammy H. ;
Looi, Audrey ;
Teo, Livia ;
Davies, Brett W. ;
Elefante, Andrea ;
Shen, Sunny ;
Realini, Tony ;
Fischer, William ;
Kazim, Michael .
OPHTHALMIC PLASTIC AND RECONSTRUCTIVE SURGERY, 2016, 32 (02) :106-112
[3]  
Bland JM, 1999, STAT METHODS MED RES, V8, P135, DOI 10.1177/096228029900800204
[4]   Pediatric medial subperiosteal orbital abscess: Medical management where possible [J].
Brown, CL ;
Graham, SM ;
Griffin, MC ;
Smith, RJH ;
Carter, KD ;
Nerad, JA ;
Bauman, NM .
AMERICAN JOURNAL OF RHINOLOGY, 2004, 18 (05) :321-327
[5]   Assessment of Orbital Computed Tomography (CT) Imaging Biomarkers in Patients with Thyroid Eye Disease [J].
Chaganti, Shikha ;
Mundy, Kevin ;
DeLisi, Michael P. ;
Nelson, Katrina M. ;
Harrigan, Robert L. ;
Galloway, Robert L. ;
Landman, Bennett A. ;
Mawn, Louise A. .
JOURNAL OF DIGITAL IMAGING, 2019, 32 (06) :987-994
[6]  
Danishyar A, 2022, ORBITAL CELLULITIS
[7]  
DAVANGER M, 1970, ACTA OPHTHALMOL, V48, P625
[8]   ORBITAL COMPLICATIONS OF SINUSITIS - AVOID DELAYS IN DIAGNOSIS [J].
DAVIS, JP ;
STEARNS, MP .
POSTGRADUATE MEDICAL JOURNAL, 1994, 70 (820) :108-110
[9]   COMPARING THE AREAS UNDER 2 OR MORE CORRELATED RECEIVER OPERATING CHARACTERISTIC CURVES - A NONPARAMETRIC APPROACH [J].
DELONG, ER ;
DELONG, DM ;
CLARKEPEARSON, DI .
BIOMETRICS, 1988, 44 (03) :837-845
[10]   Automated delineation of orbital abscess depicted on CT scan using deep learning [J].
Fu, Roxana ;
Leader, Joseph K. ;
Pradeep, Tejus ;
Shi, Junli ;
Meng, Xin ;
Zhang, Yanchun ;
Pu, Jiantao .
MEDICAL PHYSICS, 2021, 48 (07) :3721-3729