1
|
Koç U, Sezer EA, Özkaya YA, Yarbay Y, Beşler MS, Taydaş O, Yalçın A, Evrimler Ş, Kızıloğlu HA, Kesimal U, Atasoy D, Oruç M, Ertuğrul M, Karakaş E, Karademir F, Sebik NB, Topuz Y, Aktan ME, Sezer Ö, Aydın Ş, Varlı S, Akdoğan E, Ülgü MM, Birinci Ş. Elevating healthcare through artificial intelligence: analyzing the abdominal emergencies data set (TR_ABDOMEN_RAD_EMERGENCY) at TEKNOFEST-2022. Eur Radiol 2023:10.1007/s00330-023-10391-y. [PMID: 37947834 DOI: 10.1007/s00330-023-10391-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Revised: 08/28/2023] [Accepted: 09/08/2023] [Indexed: 11/12/2023]
Abstract
OBJECTIVES The artificial intelligence competition in healthcare at TEKNOFEST-2022 provided a platform to address the complex multi-class classification challenge of abdominal emergencies using computer vision techniques. This manuscript aimed to comprehensively present the methodologies for data preparation, annotation procedures, and rigorous evaluation metrics. Moreover, it was conducted to introduce a meticulously curated abdominal emergencies data set to the researchers. METHODS The data set underwent a comprehensive central screening procedure employing diverse algorithms extracted from the e-Nabız (Pulse) and National Teleradiology System of the Republic of Türkiye, Ministry of Health. Full anonymization of the data set was conducted. Subsequently, the data set was annotated by a group of ten experienced radiologists. The evaluation process was executed by calculating F1 scores, which were derived from the intersection over union values between the predicted bounding boxes and the corresponding ground truth (GT) bounding boxes. The establishment of baseline performance metrics involved computing the average of the highest five F1 scores. RESULTS Observations indicated a progressive decline in F1 scores as the threshold value increased. Furthermore, it could be deduced that class 6 (abdominal aortic aneurysm/dissection) was relatively straightforward to detect compared to other classes, with class 5 (acute diverticulitis) presenting the most formidable challenge. It is noteworthy, however, that if all achieved outcomes for all classes were considered with a threshold of 0.5, the data set's complexity and associated challenges became pronounced. CONCLUSION This data set's significance lies in its pioneering provision of labels and GT-boxes for six classes, fostering opportunities for researchers. CLINICAL RELEVANCE STATEMENT The prompt identification and timely intervention in cases of emergent medical conditions hold paramount significance. The handling of patients' care can be augmented, while the potential for errors is minimized, particularly amidst high caseload scenarios, through the application of AI. KEY POINTS • The data set used in artificial intelligence competition in healthcare (TEKNOFEST-2022) provides a 6-class data set of abdominal CT images consisting of a great variety of abdominal emergencies. • This data set is compiled from the National Teleradiology System data repository of emergency radiology departments of 459 hospitals. • Radiological data on abdominal emergencies is scarce in literature and this annotated competition data set can be a valuable resource for further studies and new AI models.
Collapse
Affiliation(s)
- Ural Koç
- Department of Radiology, Ankara Bilkent City Hospital, Ankara, Türkiye.
| | - Ebru Akçapınar Sezer
- Artificial Intelligence Division, Department of Computer Engineering, Hacettepe University, Ankara, Türkiye
| | | | - Yasin Yarbay
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | | | - Onur Taydaş
- Department of Radiology, Faculty of Medicine, Sakarya University, Sakarya, Türkiye
| | - Ahmet Yalçın
- Department of Radiology, Faculty of Medicine, Erzurum Atatürk University, Erzurum, Türkiye
| | - Şehnaz Evrimler
- Department of Radiology, Ankara Etlik City Hospital, Ankara, Türkiye
| | | | - Uğur Kesimal
- Department of Radiology, Ankara Training and Research Hospital, Ankara, Türkiye
| | - Dilara Atasoy
- Department of Radiology, Sivas Numune State Hospital, Sivas, Türkiye
| | - Meltem Oruç
- Department of Radiology, Karaman Training and Research Hospital, Karaman, Türkiye
| | - Mustafa Ertuğrul
- Department of Radiology, Ürgüp State Hospital, Nevşehir, Türkiye
| | - Emrah Karakaş
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | | | - Nihat Barış Sebik
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | | | | | - Özgür Sezer
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | - Şahin Aydın
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | - Songül Varlı
- Health Institutes of Türkiye, İstanbul, Türkiye
- Department of Computer Engineering, Yıldız Technical University, İstanbul, Türkiye
| | - Erhan Akdoğan
- Health Institutes of Türkiye, İstanbul, Türkiye
- Department of Mechatronics Engineering, Faculty of Mechanical Engineering, Yıldız Technical University, İstanbul, Türkiye
| | - Mustafa Mahir Ülgü
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | | |
Collapse
|
2
|
Koç U, Akçapınar Sezer E, Özkaya YA, Yarbay Y, Taydaş O, Ayyıldız VA, Alper Kızıloğlu H, Kesimal U, Çankaya İ, Said Beşler M, Karakaş E, Karademir F, Sebik NB, Bahadır M, Sezer Ö, Yeşilyurt B, Varlı S, Akdoğan E, Mahir Ülgü M, Birinci Ş, Birinci S. Artificial Intelligence in Healthcare Competition (TEKNOFEST-2021): Stroke Data Set. Eurasian J Med 2022; 54:248-258. [PMID: 35943079 PMCID: PMC9797774 DOI: 10.5152/eurasianjmed.2022.22096] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/05/2023] Open
Abstract
OBJECTIVE The artificial intelligence competition in healthcare was organized for the first time at the annual aviation, space, and technology festival (TEKNOFEST), Istanbul/Türkiye, in September 2021. In this article, the data set preparation and competition processes were explained in detail; the anonymized and annotated data set is also provided via official website for further research. MATERIALS AND METHODS Data set recorded over the period covering 2019 and 2020 were centrally screened from the e-Pulse and Teleradiology System of the Republic of Türkiye, Ministry of Health using various codes and filtering criteria. The data set was anonymized. The data set was prepared, pooled, curated, and annotated by 7 radiologists. The training data set was shared with the teams via a dedicated file transfer protocol server, which could be accessed using private usernames and passwords given to the teams under a nondisclosure agreement signed by the representative of each team. RESULTS The competition consisted of 2 stages. In the first stage, teams were given 192 digital imaging and communications in medicine images that belong to 1 of 3 possible categories namely, hemorrhage, ischemic, or non-stroke. Teams were asked to classify each image as either stroke present or absent. In the second stage of the competition, qualifying 36 teams were given 97 digital imaging and communications in medicine images that contained hemorrhage, ischemia, or both lesions. Among the employed methods, Unet and DeepLabv3 were the most frequently observed ones. CONCLUSION Artificial intelligence competitions in healthcare offer good opportunities to collect data reflecting various cases and problems. Especially, annotated data set by domain experts is more valuable.
Collapse
Affiliation(s)
- Ural Koç
- Department of Radiology, Ankara City Hospital, Ankara, Türkiye
| | - Ebru Akçapınar Sezer
- Department of Computer Engineering, Artificial Intelligence Division, Hacettepe University, Ankara, Türkiye
| | | | - Yasin Yarbay
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | - Onur Taydaş
- Department of Radiology, Sakarya University Faculty of Medicine, Sakarya, Türkiye
| | - Veysel Atilla Ayyıldız
- Department of Radiology, Isparta Süleyman Demirel University Faculty of Medicine, Isparta, Türkiye
| | | | - Uğur Kesimal
- Department of Radiology, Ankara Training and Research Hospital, Ankara, Türkiye
| | - İmran Çankaya
- Department of Radiology, Van Training and Research Hospital, Van, Türkiye
| | | | - Emrah Karakaş
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | | | - Nihat Barış Sebik
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | - Murat Bahadır
- Department of Computer Engineering, Konya Technical University Faculty of Engineering and Natural Sciences, Konya, Türkiye
| | - Özgür Sezer
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | | | - Songul Varlı
- Health Institutes of Türkiye, İstanbul, Türkiye,Department of Computer Engineering, Yıldız Technical University, İstanbul, Türkiye
| | - Erhan Akdoğan
- Health Institutes of Türkiye, İstanbul, Türkiye,Department of Mechatronics Engineering, Yıldız Technical University Faculty of Mechanical Engineering, İstanbul, Türkiye
| | - Mustafa Mahir Ülgü
- General Directorate of Health Information Systems, Ministry of Health, Ankara, Türkiye
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
3
|
Abstract
Lingual hematoma is a severe situation, which is rare and endangers the airway. It can develop due to trauma, vascular abnormalities, and coagulopathy. Due to its sudden development, it can be clinically confused with angioedema. In patients who applied to the doctor with complaints of a swollen tongue, lingual hematoma can be confused with angioedema, in particular, at the beginning if the symptoms occurred after drug use. It should especially be considered that dystonia in the jaw can present as drug-induced hyperkinetic movement disorder. Early recognition of this rare clinical condition and taking precautions for providing airway patency are essential. In this case report, we will discuss mimicking angioedema and caused by a bite due to dystonia and separation of the tongue from the base of the mouth developing concurrently with lingual hematoma.
Collapse
Affiliation(s)
- Özgür Sezer
- Department of Emergency Medicine, Amasya University Sabuncuoglu Serefeddin Training and Research Hospital, Amasya, Turkey
| | - Ali Attila Aydin
- Department of Emergency Medicine, Acibadem Altunizade Hospital, Istanbul, Turkey
| | - Sedat Bilge
- Department of Emergency Medicine, Gulhane Training and Research Hospital, Ankara, Turkey
| | - Fatih Arslan
- Department of Otorhinolaryngology, Beytepe Murat Erdi Eker State Hospital, Ankara, Turkey
| | - Hasan Arslan
- Department of Otorhinolaryngology, Gulhane Training and Research Hospital, Ankara, Turkey
| |
Collapse
|
4
|
Sindermann J, Sezer Ö, Vahlhaus C, Robenek H, Hoffmeier A, Tjan TD, Scheld HH, Weissen-Plenz G. Aortic dissection associated with Cogans's syndrome: Role of GM-CSF for deleterious loss of vascular structural integrity. Thorac Cardiovasc Surg 2011. [DOI: 10.1055/s-0030-1269045] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
5
|
Sezer Ö, Stepper W, Schneider T, Welp H, Tjan TD, Sauerland C, Scheld HH, Hoffmeier A. Residual platelet activity in LVAD patients with stroke. Thorac Cardiovasc Surg 2011. [DOI: 10.1055/s-0030-1268994] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
6
|
Sezer Ö, Tjan T, Scheld H, Hoffmeier A, Welp H. Glomustumore. Z Herz- Thorax- Gefäßchir 2009. [DOI: 10.1007/s00398-009-0714-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
7
|
Welp H, Sezer Ö, Kaja E, Meyborg M, Breithardt G, Scheld H, Stypmann J. Doppler-echocardiographic longterm follow-up after orthotopic heart transplantation – the Münster single center experience. Thorac Cardiovasc Surg 2008. [DOI: 10.1055/s-2008-1037904] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
8
|
Klotz S, Tjan T, Sezer Ö, Debus V, Däbritz S, Scheld H. Pediatric cardiac transplantation – influence of prior LVAD support on outcome. Thorac Cardiovasc Surg 2008. [DOI: 10.1055/s-2008-1038002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
9
|
Sezer Ö, Sindermann J, Tjan T, Scheld H, Semik M. Surgical managemement of diagphragmatic paralysis following congenital cardiac surgery. Thorac Cardiovasc Surg 2008. [DOI: 10.1055/s-2008-1037915] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
10
|
Thielmann M, Massoudy P, Lehmann N, Marr A, Kleikamp G, Maleszka A, Zittermann A, Körfer R, Radu M, Krian A, Litmathe J, Gams E, Sezer Ö, Scheld H, Schiller W, Welz A, Dohmen G, Autschbach R, Slottosch I, Wahlers T, Neuhäuser M, Jöckel KH, Jakob H. Prognostic impact of previous percutaneous coronary interventions on coronary artery bypass graft surgery: A multicentric analysis from the German federal state north Rhine-Westphalia. Thorac Cardiovasc Surg 2008. [DOI: 10.1055/s-2008-1037690] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
11
|
Sezer Ö, Hoffmeier A, Krasemann T, Scheld HH. Pediatric cardiac tumors in advanced stages – is an operation justified? Thorac Cardiovasc Surg 2006. [DOI: 10.1055/s-2006-925688] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
12
|
Rothenburger M, Stypmann J, Welp H, Sezer Ö, Röttger C, Wichter T, Wenzelburger F, Schmid C, Scheld HH. CNI-free immunosupression using everolimus in long term heart transplant recipients -procedures of switching protocols and side effects. Thorac Cardiovasc Surg 2006. [DOI: 10.1055/s-2006-925721] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
13
|
Hoffmeier A, Schmid C, Ziethen J, Maintz D, Löher A, Sezer Ö, Etz C, Drees G, Tjan T, Scheld H. Aortic coarctation in adults - a single center 15-years-experience with anatomic and extraanatomic repair. Thorac Cardiovasc Surg 2005. [DOI: 10.1055/s-2005-862146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
|