پیوندهای مفید
آمار
| تعداد نشریات | 22 |
| تعداد شمارهها | 713 |
| تعداد مقالات | 10,263 |
| تعداد مشاهده مقاله | 72,057,807 |
| تعداد دریافت فایل اصل مقاله | 63,817,718 |
تولید خودکار گزارش برای تصاویر قفسه سینه با استفاده از ترکیب مدل کانولوشنی بازگشتی و معماری توجه محور | ||
| مدل سازی در مهندسی | ||
| دوره 24، شماره 85، تیر 1405، صفحه 1-15 اصل مقاله (765.74 K) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22075/jme.2025.35811.2749 | ||
| نویسندگان | ||
| فردین قادری؛ محمدباقر خدابخشی* ؛ شهریار جاماسب | ||
| گروه مهندسی پزشکی، دانشکده مهندسی پزشکی و مکانیک، دانشگاه صنعتی همدان، همدان، ایران | ||
| تاریخ دریافت: 15 آبان 1403، تاریخ بازنگری: 09 خرداد 1404، تاریخ پذیرش: 31 خرداد 1404 | ||
| چکیده | ||
| در مطالعات علوم پزشکی، از تصاویر پزشکی برای تشخیص و طراحی پروتکل درمان بیماری ها بصورت گسترده استفاده میشود. برای پزشکان کمتجربه، نوشتن گزارش پزشکی به شکل متنی ممکن است مستعد خطا باشد، زیرا این کار نیازمند درک عمیق نسبت به بیماری و تجزیه و تحلیل آن است. همچنین برای متخصصان، این کار به دلیل تعدد بیمارانی که در یک روز مراجعه میکنند زمانبر و پر زحمت است. از دیدگاه دیگر، وجود گزارش های الگو برای پزشکان میتواند به میزان قابل توجهی دقت آن ها را در تشخیص بیماری افزایش دهد و خطای ناشی از عدم توجه به جزئیات را کاهش دهد. این پژوهش یک مدل مبتنی بر یادگیری عمیق را برای تولید خودکار گزارشهای تصاویر رادیولوژی ارائه نموده است. این مدل بر پایه ترکیب یک ساختار کانولوشنی بازگشتی و معماری توجه محور است که با نام Res-LSTM-Attn معرفی گردیده است. در این مدل ابتدا از تصاویر پزشکی با استفاده از شبکه عصبی کانولوشنی رِزنت ویژگی ها استخراج خواهند شد و بر اساس یک مدل چند برچسبی کلمات یک گزارش پیش بینی خواهند شد. در ادامه با استفاده از شبکه عصبی بازگشتی LSTM و لایه های توجه چندسر گزارش نهایی تولید میشود. عملکرد مدل های پیشنهادی بر اساس معیارهای BLEU 1-4 و ROUGE-L و CIDEr-D مورد ارزیابی قرار گرفت. نتایج نشان داد مدل پیشنهادی از نظر معیار CIDEr-D و ROUGE-L در تولید گزارشات طولانی بر مطالعات پیشین غلبه کرده است و این مقادیر بترتیب به میزان 7/2 و 3/2 درصد بهبود یافته اند. | ||
| کلیدواژهها | ||
| تصاویر پزشکی؛ شبکه عصبی عمیق بازگشتی؛ تولید خودکار گزارش؛ رمزگشا؛ رمزگذار؛ مکانیسم توجه | ||
| عنوان مقاله [English] | ||
| Medical Report Generation for Chest X-rays Using Convolutional Recurrent and Attention-Based Architectures | ||
| نویسندگان [English] | ||
| Fardin Ghaderi؛ Mohammad Bagher Khodabakhshi؛ Shahriar Jamasb | ||
| Biomedical Engineering Department, Hamedan University of Technology, Hamedan, Iran | ||
| چکیده [English] | ||
| Medical images are extensively used in medical science for diagnosis and treatment protocol design. Writing medical reports in text form can be error-prone for inexperienced physicians due to the deep understanding of the disease and its analysis. It is also time-consuming and laborious for experts due to the large number of patients they see in a day. Also, the existence of template reports for physicians can significantly increase their accuracy in diagnosing diseases and reduce errors caused by inattention to details. This research presents a deep learning-based model for the automatic generation of radiology reports. This model is based on a combination of a convolutional recurrent structure and an attention-based architecture called Res-LSTM-Attn. In this model, features are first extracted from medical images using a convolutional residual network, and based on a multi-label word model, a report is predicted. Then, using the LSTM recurrent neural network and multi-head attention layers, the final report is generated. The performance of the proposed models was evaluated based on the BLEU 1-4, ROUGE-L, and CIDEr-D criteria. The results showed that the proposed model outperformed previous studies in generating long reports in terms of CIDEr-D and ROUGE-L metrics, with improvements of 7.2% and 3.2%, respectively. | ||
| کلیدواژهها [English] | ||
| Medical image processing, Recurrent deep neural networks, Automatic image captioning, Encoder, Decoder, Attention mechanism | ||
|
سایر فایل های مرتبط با مقاله
|
||
| مراجع | ||
|
[1] Jing, Baoyu, Pengtao Xie, and Eric Xing. “On the Automatic Generation of Medical Imaging Reports.” ArXiv Preprint ArXiv:1711.08195, 2017. [2] Krause, Jonathan, Justin Johnson, Ranjay Krishna, and Li Fei-Fei. “A Hierarchical Approach for Generating Descriptive Image Paragraphs.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 317–25, 2017. [3] Harzig, Philipp, Yan-Ying Chen, Francine Chen, and Rainer Lienhart. “Addressing Data Bias Problems for Chest X-Ray Image Report Generation.” ArXiv Preprint ArXiv:1908.02123, 2019. [4] Yang, Shaokang, Jianwei Niu, Jiyan Wu, Yong Wang, Xuefeng Liu, and Qingfeng Li. “Automatic Ultrasound Image Report Generation with Adaptive Multimodal Attention Mechanism.” Neurocomputing 427 (2021): 40–49. [5] Han, Zhongyi, Benzheng Wei, Stephanie Leung, Jonathan Chung, and Shuo Li. “Towards Automatic Report Generation in Spine Radiology Using Weakly Supervised Framework.” In Medical Image Computing and Computer Assisted Intervention–MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part IV 11, 185–93. Springer, 2018. [6] Xue, Yuan, Tao Xu, L Rodney Long, Zhiyun Xue, Sameer Antani, George R Thoma, and Xiaolei Huang. “Multimodal Recurrent Model with Attention for Automated Radiology Report Generation.” In Medical Image Computing and Computer Assisted Intervention–MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part I, 457–66. Springer, 2018. [7] Li, Yuan, Xiaodan Liang, Zhiting Hu, and Eric P Xing. “Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation.” Advances in Neural Information Processing Systems 31 (2018). [8] Shi, Jijun, Shanshe Wang, Ronggang Wang, and Siwei Ma. “AIMNet: Adaptive Image-Tag Merging Network For Automatic Medical Report Generation.” In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7737–41. IEEE, 2022. [9] Lee, Jinhyuk, Wonjin Yoon, Sungdong Kim, Donghyeon Kim, Sunkyu Kim, Chan Ho So, and Jaewoo Kang. “BioBERT: A Pre-Trained Biomedical Language Representation Model for Biomedical Text Mining.” Bioinformatics 36, no. 4 (2020): 1234–40. [10] Luo, Renqian, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, and Tie-Yan Liu. “BioGPT: Generative Pre-Trained Transformer for Biomedical Text Generation and Mining.” Briefings in Bioinformatics 23, no. 6 (2022): bbac409. [11] Zhang, Yixiao, Xiaosong Wang, Ziyue Xu, Qihang Yu, Alan Yuille, and Daguang Xu. “When Radiology Report Generation Meets Knowledge Graph.” In Proceedings of the AAAI Conference on Artificial Intelligence, 34:12910–17, 2020. [12] Goel, Navya, Aditi Arora, Priyanshu Kashyap, and Sagar Varshney. “An Analysis of Image Captioning Models Using Deep Learning.” In 2023 International Conference on Disruptive Technologies (ICDT), 131–36. IEEE, 2023. [13] Xu, Liming, Quan Tang, Jiancheng Lv, Bochuan Zheng, Xianhua Zeng, and Weisheng Li. "Deep image captioning: A review of methods, trends and future challenges." Neurocomputing 546 (2023): 126287. [14] Lin, Chin-Yew. "Rouge: A package for automatic evaluation of summaries." In Text summarization branches out, pp. 74-81. 2004. [15] Vedantam, Ramakrishna, C. Lawrence Zitnick, and Devi Parikh. "Cider: Consensus-based image description evaluation." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566-4575. 2015. [16] Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. “Bleu: A Method for Automatic Evaluation of Machine Translation.” In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–18. 2002. [17] Park, Hyeryun, Kyungmo Kim, Seongkeun Park, and Jinwook Choi. “Medical Image Captioning Model to Convey More Details: Methodological Comparison of Feature Difference Generation.” IEEE Access 9 (2021): 150560–68. [18] Alfarghaly, Omar, Rana Khaled, Abeer Elkorany, Maha Helal, and Aly Fahmy. “Automated Radiology Report Generation Using Conditioned Transformers.” Informatics in Medicine Unlocked 24 (2021): 100557. [19] Singh, Sonit, Sarvnaz Karimi, Kevin Ho-Shon, and Len Hamey. "From chest x-rays to radiology reports: a multimodal machine learning approach." In 2019 Digital Image Computing: Techniques and Applications (DICTA), pp. 1-8. IEEE, 2019. [20] Huang, Xin, Fengqi Yan, Wei Xu, and Maozhen Li. “Multi-Attention and Incorporating Background Information Model for Chest x-Ray Image Report Generation.” IEEE Access 7 (2019): 154808–17. [21] Xie, Xiancheng, Yun Xiong, Philip S. Yu, Kangan Li, Suhua Zhang, and Yangyong Zhu. "Attention-based abnormal-aware fusion network for radiology report generation." In International Conference on Database Systems for Advanced Applications, pp. 448-452. Cham: Springer International Publishing, 2019. [22] Yin, Changchang, Buyue Qian, Jishang Wei, Xiaoyu Li, Xianli Zhang, Yang Li, and Qinghua Zheng. "Automatic generation of medical imaging diagnostic report with hierarchical recurrent neural network." In 2019 IEEE International Conference on Data Mining (ICDM), pp. 728-737. IEEE, 2019. [23] Biswal, Siddharth, Cao Xiao, Lucas M. Glass, Brandon Westover, and Jimeng Sun. "Clara: clinical report auto-completion." In Proceedings of the Web Conference 2020, pp. 541-550. 2020. [24] Jing, Baoyu, Zeya Wang, and Eric Xing. “Show, Describe and Conclude: On Exploiting the Structure Information of Chest x-Ray Reports.” ArXiv Preprint ArXiv:2004.12274, 2020. [25] Xiong, Yuxuan, Bo Du, and Pingkun Yan. "Reinforced transformer for medical image captioning." In International Workshop on Machine Learning in Medical Imaging, pp. 673-680. Cham: Springer International Publishing, 2019. [26] Li, Christy Y., Xiaodan Liang, Zhiting Hu, and Eric P. Xing. "Knowledge-driven encode, retrieve, paraphrase for medical image report generation." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 6666-6673. 2019. [27] Li, Xin, Rui Cao, and Dongxiao Zhu. "Vispi: Automatic visual perception and interpretation of chest x-rays." arXiv Preprint arXiv:1906.05190 (2019). | ||
|
آمار تعداد مشاهده مقاله: 454 تعداد دریافت فایل اصل مقاله: 142 |
||
