Development and application evaluation of a medical image diagnosis teaching assistant system supported by multi-modal deep learning
Hilzati Kuzati
Xinjiang Hetian College
Baihetiya Mutalipu
Xinjiang Hetian College
DOI: https://doi.org/10.59429/esta.v12i2.10563
Keywords: Multimodal deep learning; Medical image diagnosis; Teaching assistance system; Image fusion
Abstract
With the rapid development of medical imaging technology, medical images collected by different sensors containing different pathological information are also known as multi-modal medical images, which are indispensable tools for modern medical analysis and disease diagnosis. Due to the inability of single-modal images to provide complete pathological information for disease diagnosis, medical staff need to observe multiple images of different modalities simultaneously, and this kind of image examination has errors, which increases the uncertainty of clinical diagnosis. Therefore, some scholars have proposed multi-modal medical image fusion technology, which can not only demonstrate the application advantages of different modal images but also effectively make up for the application problems of single images, providing a reasonable basis for disease diagnosis in the new era. Therefore, this paper mainly discusses the development and application effect of a medical image diagnosis teaching assistant system supported by multi-modal deep learning.
References
[1]Juanjuan Wang, Jie Ma, Chunyan Yi, et al. Diagnostic performance analysis of ductal carcinoma in situ of the breast based on deep learning multimodal imaging examination [J]. Journal of Medical Imaging, 2024, 34(4):49-53.
[2]Shan Xiong, Wenze Wu, Sibin Liu, et al. Application value of deep learning-assisted diagnostic system for rib fractures in emergency elderly patients [J]. Imaging Science and Photochemistry, 2024, 42(5):443-450.
[3]Huichang Yu, Shiyuan Liu. Application of deep learning in super-resolution reconstruction of magnetic resonance images [J]. Chinese Journal of Medical Physics, 2024, 41(10):1243-1248. DOI:10.3969/j.issn.1005-202X.2024.10.008.
[4]Chengyi Qian, Yuanjun Wang. Research progress on deep learning-based classification of Alzheimer’s disease imaging [J]. Journal of Spectroscopy, 2023, 40(2):220-238. DOI:10.11938/cjmr20223013.
[5]Dingyang Lv, Weibing Shuang. Research progress on precision diagnosis and treatment of renal cancer using radiomics and deep learning [J]. Journal of Urology (Electronic Edition), 2024, 16(2):50-54.
[6]Yiman Liu, Xiaoxiang Han, Yuqi Zhang, et al. Application of deep learning in automatic intelligent recognition of standard sections in pediatric cardiac ultrasound [J]. Journal of Naval Medical University, 2023, 44(7):822-829. DOI:10.16781/j.CN31-2187/R.20220936.
[7]Shiwei Zhong, Dayou Wei, Chaojun Wu, et al. Application value of deep learning ultrasound radiomics in distinguishing between mass breast inflammation and breast cancer [J]. Chinese Journal of Ultrasound Medicine, 2023, 39(12):1341-1344. DOI:10.3969/j.issn.1002-0101.2023.12.006.
[8]Wenjiang Wang, Jiaojiao Li, Zimeng Wang, et al. Application of deep learning integrated T2WI and DCEMRI model in classification of breast lesions [J]. Clinical Radiology Journal, 2024, 43(11):1871-1876.
[9]Skaramagkas V, Pentari A, Kefalopoulou Z, Tsiknakis M. Multi-Modal Deep Learning Diagnosis of Parkinson’s Disease-A Systematic Review. IEEE Trans NeuralSyst Rehabil Eng.2023;31:2399-2423.
[10]Tran KA, Kondrashova O, Bradley A, Williams ED, Pearson JV, Waddell N. Deeplearning in cancer diagnosis, prognosis and treatment selection. Genome Med.2021 Sep 27;13(1):152.
[11] Pfänder L, Schneider L, Büttner M, Krois J, Meyer-Lueckel H, Schwendicke F.Multi-modal deep learning for automated assembly of periapical radiographs. JDent. 2023 Aug;135:104588.