Yiftach Barash1,2, Gennadiy Guralnik3, Noam Tau1, Shelly Soffer1,2,4, Tal Levy2,3, Orit Shimon3, Eyal Zimlichman4, Eli Konen1, Eyal Klang5,6. 1. Division of Diagnostic Imaging, Sheba Medical Center, Sackler Faculty of Medicine, Tel Aviv University, Derech Sheba St 2, Ramat Gan, Israel. 2. DeepVision Lab, Sheba Medical Center, Ramat Gan, Israel. 3. Tel Aviv University, Tel Aviv, Israel. 4. Management, Sheba Medical Center, Sackler Faculty of Medicine, Tel Aviv University, Ramat Gan, Israel. 5. Division of Diagnostic Imaging, Sheba Medical Center, Sackler Faculty of Medicine, Tel Aviv University, Derech Sheba St 2, Ramat Gan, Israel. eyalkla@hotmail.com. 6. DeepVision Lab, Sheba Medical Center, Ramat Gan, Israel. eyalkla@hotmail.com.
Abstract
PURPOSE: Natural language processing (NLP) can be used for automatic flagging of radiology reports. We assessed deep learning models for classifying non-English head CT reports. METHODS: We retrospectively collected head CT reports (2011-2018). Reports were signed in Hebrew. Emergency department (ED) reports of adult patients from January to February for each year (2013-2018) were manually labeled. All other reports were used to pre-train an embedding layer. We explored two use cases: (1) general labeling use case, in which reports were labeled as normal vs. pathological; (2) specific labeling use case, in which reports were labeled as with and without intra-cranial hemorrhage. We tested long short-term memory (LSTM) and LSTM-attention (LSTM-ATN) networks for classifying reports. We also evaluated the improvement of adding Word2Vec word embedding. Deep learning models were compared with a bag-of-words (BOW) model. RESULTS: We retrieved 176,988 head CT reports for pre-training. We manually labeled 7784 reports as normal (46.3%) or pathological (53.7%), and 7.1% with intra-cranial hemorrhage. For the general labeling, LSTM-ATN-Word2Vec showed the best results (AUC = 0.967 ± 0.006, accuracy 90.8% ± 0.01). For the specific labeling, all methods showed similar accuracies between 95.0 and 95.9%. Both LSTM-ATN-Word2Vec and BOW had the highest AUC (0.970). CONCLUSION: For a general use case, word embedding using a large cohort of non-English head CT reports and ATN improves NLP performance. For a more specific task, BOW and deep learning showed similar results. Models should be explored and tailored to the NLP task.
PURPOSE: Natural language processing (NLP) can be used for automatic flagging of radiology reports. We assessed deep learning models for classifying non-English head CT reports. METHODS: We retrospectively collected head CT reports (2011-2018). Reports were signed in Hebrew. Emergency department (ED) reports of adult patients from January to February for each year (2013-2018) were manually labeled. All other reports were used to pre-train an embedding layer. We explored two use cases: (1) general labeling use case, in which reports were labeled as normal vs. pathological; (2) specific labeling use case, in which reports were labeled as with and without intra-cranial hemorrhage. We tested long short-term memory (LSTM) and LSTM-attention (LSTM-ATN) networks for classifying reports. We also evaluated the improvement of adding Word2Vec word embedding. Deep learning models were compared with a bag-of-words (BOW) model. RESULTS: We retrieved 176,988 head CT reports for pre-training. We manually labeled 7784 reports as normal (46.3%) or pathological (53.7%), and 7.1% with intra-cranial hemorrhage. For the general labeling, LSTM-ATN-Word2Vec showed the best results (AUC = 0.967 ± 0.006, accuracy 90.8% ± 0.01). For the specific labeling, all methods showed similar accuracies between 95.0 and 95.9%. Both LSTM-ATN-Word2Vec and BOW had the highest AUC (0.970). CONCLUSION: For a general use case, word embedding using a large cohort of non-English head CT reports and ATN improves NLP performance. For a more specific task, BOW and deep learning showed similar results. Models should be explored and tailored to the NLP task.
Entities:
Keywords:
Attention; Deep learning; Emergency service, hospital; Natural language processing; Tomography, X-ray computed
Authors: M Iorga; M Drakopoulos; A M Naidech; A K Katsaggelos; T B Parrish; V B Hill Journal: AJNR Am J Neuroradiol Date: 2022-04-28 Impact factor: 3.825
Authors: Shelly Soffer; Eyal Zimlichman; Matthew A Levin; Alexis M Zebrowski; Benjamin S Glicksberg; Robert Freeman; David L Reich; Eyal Klang Journal: Obes Sci Pract Date: 2022-03-24