Abstract
Chest radiography is a general method for diagnosing a patient’s condition and identifying important information. Therefore, a large amount of chest radiographs have been taken. In order to reduce the burden on medical professionals, methods for generating findings have been proposed. However, the study of generating chest radiograph findings has primarily focused on the English language, and to the best of our knowledge, no studies have studied Japanese data on this subject. The difficult points of the Japanese language are that the boundaries of words are not clear and that there are numerous orthographic variants. For deal with two problems, we proposed an end-to-end attention-based model that generates Japanese findings at the character-level from chest radiographs. We evaluated the method using a public dataset of Japanese chest radiograph findings. Furthermore, we confirmed via visual inspection that the attention mechanism captures the features and positional information of radiographs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anders, K., John, A.H.: A simple weight decay can improve generalization. In: NIPS (1992)
Baoyu, J., Pengtao, X., Eric, P.X.: On the automatic generation of medical imaging reports. In: ACL (2017)
Candemir, S., et al.: Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Trans. Med. Imaging 33, 577–590 (2014)
Chawla, V.N., Bowyer, W.K., Hall, O.L., Kegelmeyer, P.W.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Christy, Y.L., Xiaodan, L., Zhiting, H., Eric, P.X.: Knowledge-driven Encode. Retrieve, Paraphrase for Medical Image Report Generation. In: AAAI (2019)
Delrue, L., Gosselin, R., Ilsen, B., Landeghem, V.A., de Mey, J., Duyck, P.: Difficulties in the interpretation of chest radiography. In: Comparative Interpretation of CT and Standard Radiography of the Chest (2010)
Diederik, P.K., Jimmy, L.B.: Adam: a method for stochastic optimization. In: ICLR (2015)
Dzmitry, B., KyungHyun, C., Yoshua, B.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)
Hamada, A.A., Samir, B., Suziah, S.: A computer aided diagnosis system for lung cancer based on statistical and machine learning techniques. J. Comput. 9, 425–431 (2014)
He, H., Edwardo, A.G.: Learning from imbalanced data. Trans. Knowl. Data Eng. 21, 1263–1284 (2009)
Kaiming, H., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Kelvin, X., et al.: Show, attend and tell: neural image caption generation with visual attention. In: PMLR (2015)
Kishore, P., Salim, R., Todd, W., Wei, J.Z.: BLEU: a method for automatic evaluation of machine translation. In: ACL (2002)
Li, Y.C., Liang, X., Hu, Z., Xing, P.E.: Hybrid retrieval-generation reinforced agent for medical image report generation. In: NIPS (2018)
Nitish, S., Geoffrey, H., Alex, K., Ilya, S., Ruslan, S.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Rich, C., Steve, L., Lee, G.: Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. In: NIPS (2001)
Sepp, H., JĂ¼rgen, S.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Shiraishi, J., et al.: Development of a digital image database for chest radiographs with and without a lung nodule receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am. J. Roentgenol. 174, 71–74 (2000)
Wang, X., Peng, Y., Lu, L., Lu, Z., Summers, M.R.: TieNet: text-image embedding network for common thorax disease classification and reporting in chest X-rays. In: CVPR (2018)
Acknowledgements
This research was supported by Japan Society for the Promotion of Science (JSPS) Grant-in-Aid for Scientific Research JP25700032, JP15H05327, JP16H06562 and Japan Agency for Medical Research and Development (AMED) of ICT infrastructure construction research business such as clinical research in 2016.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Sakka, K. et al. (2021). Character-Level Japanese Text Generation with Attention Mechanism for Chest Radiography Diagnosis. In: Shaban-Nejad, A., Michalowski, M., Buckeridge, D.L. (eds) Explainable AI in Healthcare and Medicine. Studies in Computational Intelligence, vol 914. Springer, Cham. https://doi.org/10.1007/978-3-030-53352-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-53352-6_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-53351-9
Online ISBN: 978-3-030-53352-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)