ABSTRACT
The American College of Radiology (ACR) has guidelines on appropriate ordering of Magnetic Resonance Imaging (MRI) brain scans. MRI requests are currently manually reviewed by radiologists to ensure compliance to these guidelines. In this paper, we implemented a stacked recurrent neural network (RNN) utilizing a bidirectional long short-term memory (Bi-LSTM) sequence with BioWordVec, a biomedical word embedding vector that uses word representations from a lexicon developed from medical publications, to develop an automated classification system for request audit. To overcome the problems of interpretation by black-box models, the RNN is integrated with a model agnostic explainer LIME (Local Interpretable Model-Agnostic Explanations) to provide explainable support for clinicians in the healthcare environment. The performance of the RNN is compared with a Random Forest (RF) algorithm that utilizes the bag-of-words concept. The RNN was trained and validated on 2470 rows of different patient free-text orders and tested on a separate 2711 orders, producing an accuracy of 82.51% and a ROC value of 0.89 which was either comparable to or surpassing RF both in performance and usability. The use of deep learning with explainable LIME in this study provided a good use case towards an augmented decision-making framework in healthcare.
- E. Pons, L. M. M. Braun, M. G. M. Hunink, and J. A. Kors, "Natural language processing in radiology: a systematic review," Radiology, vol. 279, no. 2, pp. 329--343, 2016.Google Scholar
- A. S. Lundervold and A. Lundervold, "An overview of deep learning in medical imaging focusing on MRI," Z. Med. Phys., vol. 29, no. 2, pp. 102--127, 2019.Google Scholar
- H. Li and Y. Fan, "Brain decoding from functional MRI using long short-term memory recurrent neural networks," in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 320--328, 2018.Google Scholar
- C. Qin, J. Schlemper, J. Caballero, A. N. Price, J. V Hajnal, and D. Rueckert, "Convolutional recurrent neural networks for dynamic MR image reconstruction," IEEE Trans. Med. Imaging, vol. 38, no. 1, pp. 280--290, 2018.Google Scholar
- I. Banerjee et al., "Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification," Artif. Intell. Med., vol. 97, pp. 79--88, 2019.Google ScholarDigital Library
- A. C. of Radiology, "ACR-ASNR-SPR practice parameter for the performance and interpretation of magnetic resonance imaging of the brain." 2015.Google Scholar
- D. Remedios, B. France, and M. Alexander, "Making the best value of clinical radiology: iRefer Guidelines," Clin. Radiol., vol. 72, no. 9, pp. 705--707, 2017.Google ScholarCross Ref
- H. T. Huhdanpaa et al., "Using Natural Language Processing of Free-Text Radiology Reports to Identify Type 1 Modic Endplate Changes," J. Digit. Imaging, vol. 31, no. 1, pp. 84--90, 2018.Google ScholarCross Ref
- L. T. E. Cheng, J. Zheng, G. K. Savova, and B. J. Erickson, "Discerning tumor status from unstructured MRI reports-completeness of information in existing reports and utility of automated natural language processing," J. Digit. Imaging, vol. 23, no. 2, pp. 119--132, 2010.Google ScholarCross Ref
- S. H. Lee, D. Levin, P. D. Finley, and C. M. Heilig, "Chief complaint classification with recurrent neural networks," J. Biomed. Inform., vol. 93, p. 103158, 2019.Google ScholarDigital Library
- A. Y. Zhang, S. S. W. Lam, N. Liu, Y. Pang, L. L. Chan, and P. H. Tang, "Development of a Radiology Decision Support System for the Classification of MRI Brain Scans," in 2018 IEEE/ACM 5th International Conference on Big Data Computing Applications and Technologies (BDCAT), pp. 107--115, 2018.Google Scholar
- L. Rokach, R. Romano, and O. Maimon, "Negation recognition in medical narrative reports," Inf. Retr. Boston., vol. 11, no. 6, pp. 499--538, 2008.Google ScholarDigital Library
- C. Francois, "Deep learning with Python." Manning Publications Company, 2017.Google Scholar
- Y. Zhang, Q. Chen, Z. Yang, H. Lin, and Z. Lu, "BioWordVec, improving biomedical word embeddings with subword information and MeSH," Sci. data, vol. 6, no. 1, p. 52, 2019.Google Scholar
- R. Socher, "CS224d: Deep Learning for Natural Language Processing." Stanford University CS224d: Deep Learning for Natural Language Processing.Google Scholar
- M. T. Ribeiro, S. Singh, and C. Guestrin, "Why should i trust you? Explaining the predictions of any classifier," in Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1135--1144, 2016.Google Scholar
Index Terms
- Explainable AI: Classification of MRI Brain Scans Orders for Quality Improvement
Recommendations
Cerebral LSTM: A Better Alternative for Single- and Multi-Stacked LSTM Cell-Based RNNs
AbstractDeep learning has rapidly transformed the natural language processing domain with its recurrent neural networks. LSTM is one such popular repeating cell unit used for building these recurrent neural network-based deep learning architectures. In ...
Performance comparison of text-based sentiment analysis using recurrent neural network and convolutional neural network
ICCIP '17: Proceedings of the 3rd International Conference on Communication and Information ProcessingOne biggest challenge in sentiment analysis is that it should include Natural Language Processing (NLP), to make the machine understand the human language. With the current development of Artificial Neural Network (ANN), with its implementation, ...
Deep Generative Model-Driven Multimodal Prostate Segmentation in Radiotherapy
Artificial Intelligence in Radiation TherapyAbstractDeep learning has shown unprecedented success in a variety of applications, such as computer vision and medical image analysis. However, there is still potential to improve segmentation in multimodal images by embedding prior knowledge via ...
Comments