A Survey on Deep Learning and Explainability for Automatic Report Generation from Medical Images. Messina, P., Pino, P., Parra, D., Soto, A., Besa, C., Uribe, S., Andía, M., Tejos, C., Prieto, C., & Capurro, D. ACM Computing Surveys, 54(10s):203:1–203:40, September, 2022. ![A Survey on Deep Learning and Explainability for Automatic Report Generation from Medical Images [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Every year physicians face an increasing demand of image-based diagnosis from patients, a problem that can be addressed with recent artificial intelligence methods. In this context, we survey works in the area of automatic report generation from medical images, with emphasis on methods using deep neural networks, with respect to (1) Datasets, (2) Architecture Design, (3) Explainability, and (4) Evaluation Metrics. Our survey identifies interesting developments but also remaining challenges. Among them, the current evaluation of generated reports is especially weak, since it mostly relies on traditional Natural Language Processing (NLP) metrics, which do not accurately capture medical correctness.
@article{messina_survey_2022,
title = {A {Survey} on {Deep} {Learning} and {Explainability} for {Automatic} {Report} {Generation} from {Medical} {Images}},
volume = {54},
issn = {0360-0300},
url = {https://doi.org/10.1145/3522747},
doi = {10.1145/3522747},
abstract = {Every year physicians face an increasing demand of image-based diagnosis from patients, a problem that can be addressed with recent artificial intelligence methods. In this context, we survey works in the area of automatic report generation from medical images, with emphasis on methods using deep neural networks, with respect to (1) Datasets, (2) Architecture Design, (3) Explainability, and (4) Evaluation Metrics. Our survey identifies interesting developments but also remaining challenges. Among them, the current evaluation of generated reports is especially weak, since it mostly relies on traditional Natural Language Processing (NLP) metrics, which do not accurately capture medical correctness.},
number = {10s},
urldate = {2023-10-16},
journal = {ACM Computing Surveys},
author = {Messina, Pablo and Pino, Pablo and Parra, Denis and Soto, Alvaro and Besa, Cecilia and Uribe, Sergio and Andía, Marcelo and Tejos, Cristian and Prieto, Claudia and Capurro, Daniel},
month = sep,
year = {2022},
keywords = {Medical report generation, deep learning, explainable artificial intelligence, medical image captioning, medical images, natural language report},
pages = {203:1--203:40},
}
Downloads: 0
{"_id":"LaWXjqEdS9LXzwfBz","bibbaseid":"messina-pino-parra-soto-besa-uribe-anda-tejos-etal-asurveyondeeplearningandexplainabilityforautomaticreportgenerationfrommedicalimages-2022","author_short":["Messina, P.","Pino, P.","Parra, D.","Soto, A.","Besa, C.","Uribe, S.","Andía, M.","Tejos, C.","Prieto, C.","Capurro, D."],"bibdata":{"bibtype":"article","type":"article","title":"A Survey on Deep Learning and Explainability for Automatic Report Generation from Medical Images","volume":"54","issn":"0360-0300","url":"https://doi.org/10.1145/3522747","doi":"10.1145/3522747","abstract":"Every year physicians face an increasing demand of image-based diagnosis from patients, a problem that can be addressed with recent artificial intelligence methods. In this context, we survey works in the area of automatic report generation from medical images, with emphasis on methods using deep neural networks, with respect to (1) Datasets, (2) Architecture Design, (3) Explainability, and (4) Evaluation Metrics. Our survey identifies interesting developments but also remaining challenges. Among them, the current evaluation of generated reports is especially weak, since it mostly relies on traditional Natural Language Processing (NLP) metrics, which do not accurately capture medical correctness.","number":"10s","urldate":"2023-10-16","journal":"ACM Computing Surveys","author":[{"propositions":[],"lastnames":["Messina"],"firstnames":["Pablo"],"suffixes":[]},{"propositions":[],"lastnames":["Pino"],"firstnames":["Pablo"],"suffixes":[]},{"propositions":[],"lastnames":["Parra"],"firstnames":["Denis"],"suffixes":[]},{"propositions":[],"lastnames":["Soto"],"firstnames":["Alvaro"],"suffixes":[]},{"propositions":[],"lastnames":["Besa"],"firstnames":["Cecilia"],"suffixes":[]},{"propositions":[],"lastnames":["Uribe"],"firstnames":["Sergio"],"suffixes":[]},{"propositions":[],"lastnames":["Andía"],"firstnames":["Marcelo"],"suffixes":[]},{"propositions":[],"lastnames":["Tejos"],"firstnames":["Cristian"],"suffixes":[]},{"propositions":[],"lastnames":["Prieto"],"firstnames":["Claudia"],"suffixes":[]},{"propositions":[],"lastnames":["Capurro"],"firstnames":["Daniel"],"suffixes":[]}],"month":"September","year":"2022","keywords":"Medical report generation, deep learning, explainable artificial intelligence, medical image captioning, medical images, natural language report","pages":"203:1–203:40","bibtex":"@article{messina_survey_2022,\n\ttitle = {A {Survey} on {Deep} {Learning} and {Explainability} for {Automatic} {Report} {Generation} from {Medical} {Images}},\n\tvolume = {54},\n\tissn = {0360-0300},\n\turl = {https://doi.org/10.1145/3522747},\n\tdoi = {10.1145/3522747},\n\tabstract = {Every year physicians face an increasing demand of image-based diagnosis from patients, a problem that can be addressed with recent artificial intelligence methods. In this context, we survey works in the area of automatic report generation from medical images, with emphasis on methods using deep neural networks, with respect to (1) Datasets, (2) Architecture Design, (3) Explainability, and (4) Evaluation Metrics. Our survey identifies interesting developments but also remaining challenges. Among them, the current evaluation of generated reports is especially weak, since it mostly relies on traditional Natural Language Processing (NLP) metrics, which do not accurately capture medical correctness.},\n\tnumber = {10s},\n\turldate = {2023-10-16},\n\tjournal = {ACM Computing Surveys},\n\tauthor = {Messina, Pablo and Pino, Pablo and Parra, Denis and Soto, Alvaro and Besa, Cecilia and Uribe, Sergio and Andía, Marcelo and Tejos, Cristian and Prieto, Claudia and Capurro, Daniel},\n\tmonth = sep,\n\tyear = {2022},\n\tkeywords = {Medical report generation, deep learning, explainable artificial intelligence, medical image captioning, medical images, natural language report},\n\tpages = {203:1--203:40},\n}\n\n\n\n","author_short":["Messina, P.","Pino, P.","Parra, D.","Soto, A.","Besa, C.","Uribe, S.","Andía, M.","Tejos, C.","Prieto, C.","Capurro, D."],"key":"messina_survey_2022","id":"messina_survey_2022","bibbaseid":"messina-pino-parra-soto-besa-uribe-anda-tejos-etal-asurveyondeeplearningandexplainabilityforautomaticreportgenerationfrommedicalimages-2022","role":"author","urls":{"Paper":"https://doi.org/10.1145/3522747"},"keyword":["Medical report generation","deep learning","explainable artificial intelligence","medical image captioning","medical images","natural language report"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/sarveshsoni","dataSources":["taWdMrienBzqHC2tC"],"keywords":["medical report generation","deep learning","explainable artificial intelligence","medical image captioning","medical images","natural language report"],"search_terms":["survey","deep","learning","explainability","automatic","report","generation","medical","images","messina","pino","parra","soto","besa","uribe","andía","tejos","prieto","capurro"],"title":"A Survey on Deep Learning and Explainability for Automatic Report Generation from Medical Images","year":2022}