5
|
Fabian ID, Abdallah E, Abdullahi SU, Abdulqader RA, Abdulrahaman AA, Abouelnaga S, Ademola-Popoola DS, Adio A, Afifi MA, Afshar AR, Aggarwal P, Aghaji AE, Ahmad A, Akib MNR, Akinsete A, Al Harby L, Al Mesfer S, Al Ani MH, Alarcón Portabella S, Al-Badri SAF, Alcasabas APA, Al-Dahmash SA, Alejos A, Alemany-Rubio E, Alfa Bio AI, Alfonso Carreras Y, Al-Haddad CE, Al-Hussaini HHY, Ali AM, Alia DB, Al-Jadiry MF, Al-Jumaily U, Alkatan HM, All-Eriksson C, Al-Mafrachi AARM, Almeida AA, Alsawidi KM, Al-Shaheen AASM, Al-Shammary EH, Amankwaa-Frempong D, Amiruddin PO, Armytasari I, Astbury NJ, Atalay HT, Ataseven E, Atchaneeyasakul LO, Atsiaya R, Autrata R, Balaguer J, Balayeva R, Barranco H, Bartoszek P, Bartuma K, Bascaran C, Bechrakis NE, Beck Popovic M, Begimkulova AS, Benmiloud S, Berete RC, Berry JL, Bhaduri A, Bhat S, Bhattacharyya A, Biewald EM, Binkley E, Blum S, Bobrova N, Boldt H, Bonanomi MTBC, Bouda GC, Bouguila H, Brennan RC, Brichard BG, Buaboonnam J, Budiongo A, Burton MJ, Calderón-Sotelo P, Calle Jara DA, Camuglia JE, Cano MR, Capra M, Caspi S, Cassoux N, Castela G, Castillo L, Català-Mora J, Cavieres I, Chandramohan A, Chantada GL, Chaudhry S, Chawla B, Chen W, Chiwanga FS, Chuluunbat T, Cieslik K, Clark A, Cockcroft RL, Comsa C, Correa Llano MG, Corson TW, Couitchere L, Cowan-Lyn KE, Csóka M, Dangboon W, Das A, Das P, Das S, Davanzo JM, Davidson A, De Francesco S, De Potter P, Quintero D K, Demirci H, Desjardins L, Díaz Coronado RY, Dimaras H, Dodgshun AJ, Donato Macedo CR, Dragomir MD, Du Y, Du Bruyn M, Du Plessis J, Dudeja G, Eerme K, Eka Sutyawan IW, El Kettani A, Elbahi AM, Elder JE, Elhaddad AM, Elhassan MMA, Elzembely MM, Ericksen C, Essuman VA, Evina TGA, Ezegwui IR, Fadoo Z, Fandiño AC, Faranoush M, Fasina O, Fernández DDPG, Fernández-Teijeiro A, Foster A, Frenkel S, Fu LD, Fuentes-Alabi SL, Garcia JL, García Aldana D, Garcia Pacheco HN, Geel JA, Ghassemi F, Girón AV, Goenz MA, Gold AS, Goldberg H, Gole GA, Gomel N, Gonzalez E, Gonzalez Perez G, González-Rodríguez L, Gorfine M, Graells J, Gregersen PA, Grigorovski NDAK, Guedenon KM, Gunasekera DS, Gündüz AK, Gupta H, Gupta S, Gupta V, Hadjistilianou T, Hamel P, Hamid SA, Hamzah N, Hansen ED, Harbour JW, Hartnett ME, Hasanreisoglu M, Muhammad H, Hassan S, Hassan S, Hautz W, Haydar H, Hederova S, Hessissen L, Hongeng S, Hordofa DF, Hubbard GB, Hummelen M, Husakova K, Hussein Al-Janabi AN, Ibanga A, Ida R, Ilic VR, Islamov Z, Jairaj V, Janjua T, Jeeva I, Ji X, Jo DH, Jones MM, Kabesha Amani TB, Kabore RL, Kaliki S, Kalinaki A, Kamsang P, Kantar M, Kapelushnik N, Kardava T, Kebudi R, Keomisy J, Kepak T, Ketteler P, Khan ZJ, Khaqan HA, Khetan V, Khodabande A, Khotenashvili Z, Kim JW, Kim JH, Kiratli H, Kivela TT, Klett A, Koç I, Kosh Komba Palet JE, Krivaitiene D, Kruger M, Kulvichit K, Kuntorini MW, Kyara A, Lam GC, Larson SA, Latinović S, Laurenti KD, Lavy Y, Lavric Groznik A, Leverant AA, Li C, Li K, Limbu B, Liu CH, Quah B, López JP, Lukamba RM, Luna-Fineman S, Lutfi D, Lysytsia L, Madgar S, Magrath GN, Mahajan A, Maitra P, Maka E, Makimbetov EK, Maktabi A, Maldonado C, Mallipatna A, Manudhane R, Manzhuova L, Martín-Begue N, Masud S, Matende IO, Mattosinho CCDS, Matua M, Mayet I, Mbumba FB, McKenzie JD, Mehrvar A, Mengesha AA, Menon V, Mercado GJV, Mets MB, Midena E, Miller A, Mishra DKC, Mndeme FG, Mohamedani AA, Mohammad MT, Moll AC, Montero MM, Moreira C, Mruthyunjaya P, Msina MS, Msukwa G, Mudaliar SS, Muma KIM, Munier FL, Murray TG, Musa KO, Mushtaq A, Musika AA, Mustak H, Mustapha T, Muyen OM, Myezo KH, Naidu G, Naidu N, Nair AG, Natarajan S, Naumenko L, Ndoye Roth PA, Nency YM, Neroev V, Ng Y, Nikitovic M, Nkanga ED, Nkumbe HE, Numbi MN, Nummi K, Nuruddin M, Nyaywa M, Nyirenda C, Obono-Obiang G, Oliver SCN, Oporto J, Ortega-Hernández M, Oscar AH, Ossandon D, Pagarra H, Paintsil V, Paiva L, Palanivelu MS, Papyan R, Parrozzani R, Pascual Morales CR, Paton KE, Pe'er J, Peralta Calvo J, Perić S, Pham CTM, Philbert R, Plager DA, Pochop P, Polania RA, Polyakov V, Ponce J, Qadir AO, Qayyum S, Qian J, Refaeli D, Rahman A, Rajkarnikar P, Ramanjulu R, Ramasubramanian A, Ramirez-Ortiz MA, Randhawa JK, Randrianarisoa HL, Raobela L, Rashid R, Reddy M, Renner LA, Reynders D, Ribadu D, Ritter-Sovinz P, Rogowska A, Rojanaporn D, Romero L, Roy SR, Saab RH, Saakyan S, Sabhan AH, Sagoo MS, Said AMA, Saiju R, Salas B, San Román Pacheco S, Sánchez GL, Sanchez Orozco AJ, Sayalith P, Scanlan TA, Schlüter S, Schwab C, Sedaghat A, Seth R, Sgroi M, Shah AS, Shakoor SA, Sharma MK, Sherief ST, Shields CL, Sia D, Siddiqui SN, Sidi cheikh S, Silva S, Singh AD, Singh U, Singha P, Sitorus RS, Skalet AH, Soebagjo HD, Sorochynska T, Ssali G, Stacey AW, Staffieri SE, Stahl ED, Steinberg DM, Stones DK, Strahlendorf C, Suarez MEC, Sultana S, Sun X, Superstein R, Supriyadi E, Surukrattanaskul S, Suzuki S, Svojgr K, Sylla F, Tamamyan G, Tan D, Tandili A, Tang J, Tarrillo Leiva FF, Tashvighi M, Tateshi B, Teh KH, Tehuteru ES, Teixeira LF, Tekavcic Pompe M, Thawaba ADM, Theophile T, Toledano H, Trang DL, Traoré F, Tripathy D, Tuncer S, Tyau-Tyau H, Umar AB, Unal E, Uner OE, Urbak SF, Ushakova TL, Usmanov RH, Valeina S, Valente P, van Hoefen Wijsard M, Vasquez Anchaya JK, Vaughan LO, Veleva-Krasteva NV, Verma N, Victor AA, Viksnins M, Villacís Chafla EG, Villegas VM, Vishnevskia-Dai V, Waddell K, Wali AH, Wang YZ, Wangtiraumnuay N, Wetter J, Widiarti W, Wilson MW, Wime ADC, Wiwatwongwana A, Wiwatwongwana D, Wolley Dod C, Wong ES, Wongwai P, Wu SQ, Xiang D, Xiao Y, Xu B, Xue K, Yaghy A, Yam JC, Yang H, Yanga JM, Yaqub MA, Yarovaya VA, Yarovoy AA, Ye H, Yee RI, Yousef YA, Yuliawati P, Zapata López AM, Zein E, Zhang Y, Zhilyaeva K, Zia N, Ziko OAO, Zondervan M, Bowman R. The Global Retinoblastoma Outcome Study: a prospective, cluster-based analysis of 4064 patients from 149 countries. The Lancet Global Health 2022; 10:e1128-e1140. [PMID: 35839812 PMCID: PMC9397647 DOI: 10.1016/s2214-109x(22)00250-9] [Citation(s) in RCA: 19] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2022] [Revised: 05/06/2022] [Accepted: 05/23/2022] [Indexed: 02/01/2023] Open
Abstract
Background Retinoblastoma is the most common intraocular cancer worldwide. There is some evidence to suggest that major differences exist in treatment outcomes for children with retinoblastoma from different regions, but these differences have not been assessed on a global scale. We aimed to report 3-year outcomes for children with retinoblastoma globally and to investigate factors associated with survival. Methods We did a prospective cluster-based analysis of treatment-naive patients with retinoblastoma who were diagnosed between Jan 1, 2017, and Dec 31, 2017, then treated and followed up for 3 years. Patients were recruited from 260 specialised treatment centres worldwide. Data were obtained from participating centres on primary and additional treatments, duration of follow-up, metastasis, eye globe salvage, and survival outcome. We analysed time to death and time to enucleation with Cox regression models. Findings The cohort included 4064 children from 149 countries. The median age at diagnosis was 23·2 months (IQR 11·0–36·5). Extraocular tumour spread (cT4 of the cTNMH classification) at diagnosis was reported in five (0·8%) of 636 children from high-income countries, 55 (5·4%) of 1027 children from upper-middle-income countries, 342 (19·7%) of 1738 children from lower-middle-income countries, and 196 (42·9%) of 457 children from low-income countries. Enucleation surgery was available for all children and intravenous chemotherapy was available for 4014 (98·8%) of 4064 children. The 3-year survival rate was 99·5% (95% CI 98·8–100·0) for children from high-income countries, 91·2% (89·5–93·0) for children from upper-middle-income countries, 80·3% (78·3–82·3) for children from lower-middle-income countries, and 57·3% (52·1-63·0) for children from low-income countries. On analysis, independent factors for worse survival were residence in low-income countries compared to high-income countries (hazard ratio 16·67; 95% CI 4·76–50·00), cT4 advanced tumour compared to cT1 (8·98; 4·44–18·18), and older age at diagnosis in children up to 3 years (1·38 per year; 1·23–1·56). For children aged 3–7 years, the mortality risk decreased slightly (p=0·0104 for the change in slope). Interpretation This study, estimated to include approximately half of all new retinoblastoma cases worldwide in 2017, shows profound inequity in survival of children depending on the national income level of their country of residence. In high-income countries, death from retinoblastoma is rare, whereas in low-income countries estimated 3-year survival is just over 50%. Although essential treatments are available in nearly all countries, early diagnosis and treatment in low-income countries are key to improving survival outcomes. Funding Queen Elizabeth Diamond Jubilee Trust.
Collapse
|
12
|
Thian YL, Li Y, Jagmohan P, Sia D, Chan VEY, Tan RT. Convolutional Neural Networks for Automated Fracture Detection and Localization on Wrist Radiographs. Radiol Artif Intell 2019; 1:e180001. [PMID: 33937780 PMCID: PMC8017412 DOI: 10.1148/ryai.2019180001] [Citation(s) in RCA: 59] [Impact Index Per Article: 11.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2018] [Revised: 10/01/2018] [Accepted: 12/10/2018] [Indexed: 05/08/2023]
Abstract
PURPOSE To demonstrate the feasibility and performance of an object detection convolutional neural network (CNN) for fracture detection and localization on wrist radiographs. MATERIALS AND METHODS Institutional review board approval was obtained with waiver of consent for this retrospective study. A total of 7356 wrist radiographic studies were extracted from a hospital picture archiving and communication system. Radiologists annotated all radius and ulna fractures with bounding boxes. The dataset was split into training (90%) and validation (10%) sets and used to train fracture localization models for frontal and lateral images. Inception-ResNet Faster R-CNN architecture was implemented as a deep learning model. The models were tested on an unseen test set of 524 consecutive emergency department wrist radiographic studies with two radiologists in consensus as the reference standard. Per-fracture, per-image (ie, per-view), and per-study sensitivity and specificity were determined. Area under the receiver operating characteristic curve (AUC) analysis was performed. RESULTS The model detected and correctly localized 310 (91.2%) of 340 and 236 (96.3%) of 245 of all radius and ulna fractures on the frontal and lateral views, respectively. The per-image sensitivity, specificity, and AUC were 95.7% (95% confidence interval [CI]: 92.4%, 97.8%), 82.5% (95% CI: 77.4%, 86.8%), and 0.918 (95% CI: 0.894, 0.941), respectively, for the frontal view and 96.7% (95% CI: 93.6%, 98.6%), 86.4% (95% CI: 81.9%, 90.2%), and 0.933 (95% CI: 0.912, 0.954), respectively, for the lateral view. The per-study sensitivity, specificity, and AUC were 98.1% (95% CI: 95.6%, 99.4%), 72.9% (95% CI: 67.1%, 78.2%), and 0.895 (95% CI: 0.870, 0.920), respectively. CONCLUSION The ability of an object detection CNN to detect and localize radius and ulna fractures on wrist radiographs with high sensitivity and specificity was demonstrated.© RSNA, 2019.
Collapse
Affiliation(s)
- Yee Liang Thian
- From the Department of Diagnostic Imaging (Y.L.T., P.J., D.S., V.E.Y.C.) and Department of Electrical and Computer Engineering (Y.L., R.T.T.), National University of Singapore, 5 Lower Kent Ridge Rd, Singapore 119074; and Science Division, Yale-NUS College, Singapore (R.T.T.)
| | - Yiting Li
- From the Department of Diagnostic Imaging (Y.L.T., P.J., D.S., V.E.Y.C.) and Department of Electrical and Computer Engineering (Y.L., R.T.T.), National University of Singapore, 5 Lower Kent Ridge Rd, Singapore 119074; and Science Division, Yale-NUS College, Singapore (R.T.T.)
| | - Pooja Jagmohan
- From the Department of Diagnostic Imaging (Y.L.T., P.J., D.S., V.E.Y.C.) and Department of Electrical and Computer Engineering (Y.L., R.T.T.), National University of Singapore, 5 Lower Kent Ridge Rd, Singapore 119074; and Science Division, Yale-NUS College, Singapore (R.T.T.)
| | - David Sia
- From the Department of Diagnostic Imaging (Y.L.T., P.J., D.S., V.E.Y.C.) and Department of Electrical and Computer Engineering (Y.L., R.T.T.), National University of Singapore, 5 Lower Kent Ridge Rd, Singapore 119074; and Science Division, Yale-NUS College, Singapore (R.T.T.)
| | - Vincent Ern Yao Chan
- From the Department of Diagnostic Imaging (Y.L.T., P.J., D.S., V.E.Y.C.) and Department of Electrical and Computer Engineering (Y.L., R.T.T.), National University of Singapore, 5 Lower Kent Ridge Rd, Singapore 119074; and Science Division, Yale-NUS College, Singapore (R.T.T.)
| | - Robby T. Tan
- From the Department of Diagnostic Imaging (Y.L.T., P.J., D.S., V.E.Y.C.) and Department of Electrical and Computer Engineering (Y.L., R.T.T.), National University of Singapore, 5 Lower Kent Ridge Rd, Singapore 119074; and Science Division, Yale-NUS College, Singapore (R.T.T.)
| |
Collapse
|