Automatic detection and visualization system for coronary artery calcification using optical frequency domain imaging

Artificial Life and Robotics - Tập 28 - Trang 460-470 - 2023
Ryo Oikawa1, Akio Doi1, Masaru Ishida2, Basabi Chakraborty3,4
1Faculty of Software and Information Sciences, Iwate Prefectural University, Iwate, Japan
2Department of Internal Medicine, Division of Cardiology, Iwate Medical University, Iwate, Japan
3Madanapalle Institute of Technology, Madanapalle, India
4Emeritus, Iwate Prefectural University, Iwate, Japan

Tóm tắt

Percutaneous coronary intervention (PCI) is mainly used in the treatment of stenosis of the coronary arteries of the heart characteristic of coronary artery disease, and it is important that the level of calcification is evaluated in advance of this procedure. A physician typically examines cross-sectional OFDI images of the coronary artery and decides whether PCI is applicable. However, it takes a lot of time to interpret many sliced images. It is difficult to accurately assess the entire calcified area from the individual slices. To solve these problems, we propose an automatic detection and visualization system for coronary artery calcification by using images obtained from optical frequency domain imaging (OFDI). This system assists physicians by automatically detecting and intuitively visualizing calcified areas in a short period of time. The system is built using DeepLabv3+ , a deep-learning network for semantic segmentation. The deep neural network was trained using 2149 coronary OFDI images labeled by physicians.

Tài liệu tham khảo

Maehara A, Matsumura M, Ali ZA, Mintz GS, Stone GW (2017) IVUS-guided versus OCT-guided coronary stent implantation: a critical appraisal. JACC Cardiovasc Imaging 10(12):1487–1503 Wang X, Matsumura M, Mintz GS, Lee T, Zhang W, Cao Y, Fujino A, Lin Y, Usui E, Kanaji Y, Murai T, Yonetsu T, Kakuta T, Maehara A (2017) In vivo calcium detection by comparing optical coherence tomography, intravascular ultrasound, and angiography. JACC Cardiovasc Imaging 10(8):869–879 Fujino A, Mintz GS, Lee T, Hoshino M, Usui E, Kanaji Y, Murai T, Yonetsu T, Matsumura M, Ali ZA, Jeremias A, Moses JW, Shlofmitz RA, Kakuta T, Maehara A (2018) Predictors of calcium fracture derived from balloon angioplasty and its efect on stent expansion assessed by optical coherence tomography. JACC Cardiovasc Interv 11(10):1015–1017 Guedeney P, Claesse BE, Mehran R, Mintz GS, Liu M, Sorrentino S, Giustino G, Farhan S, Leon MB, Serruys PW, Smits PC, von Birgelen C, Ali ZA, Généreux P, Redfors B, Madhavan MV, Ben-Yehuda O, Stone GW (2020) Coronary calcification and long-term outcomes according to drug-eluting stent generation. JACC Cardiovasc Interv 13(12):1417–1428 Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV Fujino A, Mintz GS, Matsumura M, Lee T, Kim SY, Hoshino M, Usui E, Yonetsu T, Haag ES, Shlofmitz RA, Kakuta T, Maehara A (2018) A new optical coherence tomography-based calcium scoring system to predict stent underexpansion. EuroIntervention 13(18):2182–2189 He S, Zheng J, Maehara A, Mintz GS, Tang D, Anastasio M, Li H (2018) Convolutional neural network based automatic plaque characterization from intracoronary optical coherence tomography images. Medical Imaging 10574:800–806 Min H-S, Yoo JH, Kang S-J, Lee J-G, Cho H, Lee PH, Ahn J-M, Park D-W, Lee S-W, Kim Y-H, Lee CW, Seong-Wook P, Seung-Jung P (2020) Detection of optical coherence tomography-defined thin-cap fibroatheroma in the coronary artery using deep learning. EuroIntervention 16(5):404–412 Chu M, Jia H, Chico JLG, Maehara A, Ali ZA, Zeng X, He L, Zhao C, Matsumura M, Wu P, Zeng M, Kubo T, Xu B, Chen L, Yu B, Mintz GS, Wijns W, Holm NR, Tu S (2021) Artificial intelligence and optical coherence tomography for the automatic characterisation of human atherosclerotic plaques. EuroIntervention 17(1):41–50 ULTREON™ 1.0 SOFTWARE Website. https://www.cardiovascular.abbott/int/en/hcp/products/percutaneous-coronary-intervention/intravascular-imaging/ultreon-software/about.html. Accessed 14 Oct 2021 Oikawa R, Kato T, Doi A, Chakraborty B, Ishida M (2021) Extraction of calcified regions from OCT images using deep learning. In: IEICE-MI2021–12, pp15–19 He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778 Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. IJCV 115(3):211–252 Lunawave™Coronary Optical Coherence Tomography Imaging System Website. https://www.terumo-europe.com/en-emea/products/lunawave%E2%84%A2-coronary-optical-coherence-tomography-imaging-system. Accessed 19 Aug 2022 Otsu N (1980) An automatic thresholding based on discrimination and least squares criteria. Trans Inst Electorn Commun Eng Jpn (D) 63(4):349–356 Kittler J, Illingworth J (1986) Minimum error thresholding. Pattern Recogn 19(1):41–47 Shervin M, Yuri B, Fatih P, Antonio P, Nasser K, Demetri T (2020) Image segmentation using deep learning: a survey. arXiv:2001.05566 Hill JM, Kereiakes DJ, Shlofmitz RA, Klein AJ, Riley RF, Price MJ, Herrmann HC, Bachinsky W, Waksman R, Stone GW, on behalf of the Disrupt CAD III Investigators (2020) Intravascular lithotripsy for treatment of severely calcified coronary artery disease. JACC 76(22):2635–2646 De Maria GL, Scarsini R, Banning AP (2019) Management of calcific coronary artery lesions: is it time to change our interventional therapeutic approach? JACC 12(15):1465–1478 Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: NIPS Iizuka S, Simo-serra E, Ishikawa H (2017) Globally and locally consistent image completion. ACM Trans Graph 36(4):1–14