An Extensive Review on Deep Learning and Machine Learning Intervention in Prediction and Classification of Types of Aneurysms

被引:7
作者
Sinnaswamy, Renugadevi Ammapalayam [1 ]
Palanisamy, Natesan [2 ]
Subramaniam, Kavitha [2 ]
Muthusamy, Suresh [1 ]
Lamba, Ravita [3 ]
Sekaran, Sreejith [4 ]
机构
[1] Kongu Engn Coll Autonomous, Dept Elect & Commun Engn, Erode, Tamil Nadu, India
[2] Kongu Engn Coll Autonomous, Dept Comp Sci & Engn, Erode, Tamil Nadu, India
[3] Malaviya Natl Inst Technol Jaipur, Dept Elect Engn, Jaipur, Rajasthan, India
[4] Natl Inst Technol Silchar, Dept Elect Engn, Silchar, Assam, India
关键词
Aneurysm; Detection; Machine learning; Deep learning; ABDOMINAL AORTIC-ANEURYSM; RISK;
D O I
10.1007/s11277-023-10532-y
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Aneurysm (Rupture of blood vessels) may happen in the cerebrum, abdominal aorta and thoracic aorta of humans, which has a high fatal rate. The advancement of the artificial technologies specifically machine learning algorithms and deep learning models have attempted to predict the aneurysm, which may reduce the death rate. The main objective of this paper is to provide the review of various algorithms and models for the early prediction of the various types of aneurysms. The focused literature review was conducted from the preferred journals from 2007 to 2022 on various parameters such as way of collecting images, the techniques used, number of images used in data set, performance metrics and future work. The summarized overview of advances in prediction of aneurysms using the machine learning algorithms from non linear kernel support regression algorithm to 3D Unet architecture of deep learning models starting from CT scan images to final performance analysis in prediction. The range of sensitivity, specificity and area under receiving operating characteristic was from 0. 7 to 1 for the abdominal aortic aneurysm detection, intracranial aneurysm detection. The thoracic aortic aneurysm was not concentrated much in the literature review, so the prediction of thoracic aortic aneurysm using machine learning as well as deep learning model is recommended.
引用
收藏
页码:2055 / 2080
页数:26
相关论文
共 63 条
  • [1] Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms
    Ahn, Jun Hyong
    Kim, Heung Cheol
    Rhim, Jong Kook
    Park, Jeong Jin
    Sigmund, Dick
    Park, Min Chan
    Jeong, Jae Hoon
    Jeon, Jin Pyeong
    [J]. JOURNAL OF PERSONALIZED MEDICINE, 2021, 11 (04):
  • [2] [Anonymous], 2022, EUR J RADIOL
  • [3] Development of an integrated hardware and software platform for the rapid detection of cerebral aneurysm rupture
    Bhadri, Prashant R.
    Kumar, Suresh A.
    Salgaonkar, Vasant A.
    Beyette, Fred R., Jr.
    Clark, Joseph F.
    [J]. ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING, 2008, 56 (1-2) : 127 - 134
  • [4] Bodapati J. D., 2019, J. Cyber Secur. Mobil., V8, P261, DOI [10.13052/JCSM2245-1439.825, DOI 10.13052/JCSM2245-1439.825]
  • [5] Hardware Architecture for Nanorobot Application in Cerebral Aneurysm
    Cavalcanti, Adriano
    Shirinzadeh, Bijan
    Fukuda, Toshio
    Ikeda, Seiichi
    [J]. 2007 7TH IEEE CONFERENCE ON NANOTECHNOLOGY, VOL 1-3, 2007, : 237 - +
  • [6] Chabert S., 2017, RES IDEAS OUTCOMES, V3, pe11731, DOI [DOI 10.3897/RIO.3.E11731, 10.3897/rio.3.e11731]
  • [7] Development and validation of machine learning prediction model based on computed tomography angiography-derived hemodynamics for rupture status of intracranial aneurysms: a Chinese multicenter study
    Chen, Guozhong
    Lu, Mengjie
    Shi, Zhao
    Xia, Shuang
    Ren, Yuan
    Liu, Zhen
    Liu, Xiuxian
    Li, Zhiyong
    Mao, Li
    Li, Xiu Li
    Zhang, Bo
    Zhang, Long Jiang
    Lu, Guang Ming
    [J]. EUROPEAN RADIOLOGY, 2020, 30 (09) : 5170 - 5182
  • [8] Dense, deep learning-based intracranial aneurysm detection on TOF MRI using two-stage regularized U-Net
    Claux, Frederic
    Baudouin, Maxime
    Bogey, Clement
    Rouchaud, Aymeric
    [J]. JOURNAL OF NEURORADIOLOGY, 2023, 50 (01) : 9 - 15
  • [9] Deep learning approach for the segmentation of aneurysmal ascending aorta
    Comelli, Albert
    Dahiya, Navdeep
    Stefano, Alessandro
    Benfante, Viviana
    Gentile, Giovanni
    Agnese, Valentina
    Raffa, Giuseppe M.
    Pilato, Michele
    Yezzi, Anthony
    Petrucci, Giovanni
    Pasta, Salvatore
    [J]. BIOMEDICAL ENGINEERING LETTERS, 2021, 11 (01) : 15 - 24
  • [10] Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge
    Di Noto, Tommaso
    Marie, Guillaume
    Tourbier, Sebastien
    Aleman-Gomez, Yasser
    Esteban, Oscar
    Saliou, Guillaume
    Cuadra, Meritxell Bach
    Hagmann, Patric
    Richiardi, Jonas
    [J]. NEUROINFORMATICS, 2023, 21 (01) : 21 - 34