Automatic Medical Report Generation via Latent Space Conditioning and Transformers

This paper presents a comprehensive exploration of integrating artificial intelligence (AI) in the healthcare sector, focusing on the development and implementation of a novel framework called VAE-GPT. Our architecture combines Variational Autoencoder (VAE) and Generative Pre-trained Transformer (GP...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE International Conference on Dependable, Autonomic and Secure Computing (Online) s. 0428 - 0435
Hlavní autoři: Adornetto, Carlo, Guzzo, Antonella, Vasile, Andrea
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 14.11.2023
Témata:
ISSN:2837-0740
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This paper presents a comprehensive exploration of integrating artificial intelligence (AI) in the healthcare sector, focusing on the development and implementation of a novel framework called VAE-GPT. Our architecture combines Variational Autoencoder (VAE) and Generative Pre-trained Transformer (GPT), to generate high-quality medical reports. The VAE component enables the model to learn a latent space representation of the images, capturing the underlying patterns and structures. The GPT component leverages the power of transformer-based language models to generate coherent and contextually relevant text. Additionally, a novel metric, Medical Embeddings Attention Distance (MEAD), is proposed in order to capture the semantic similarity between the generated and training medical reports, taking into account the importance of specific words determined by the attention module. Experiments on real dataset demonstrate that our framework achieves state-of-the-art comparable performances in generating accurate and informative medical reports.
AbstractList This paper presents a comprehensive exploration of integrating artificial intelligence (AI) in the healthcare sector, focusing on the development and implementation of a novel framework called VAE-GPT. Our architecture combines Variational Autoencoder (VAE) and Generative Pre-trained Transformer (GPT), to generate high-quality medical reports. The VAE component enables the model to learn a latent space representation of the images, capturing the underlying patterns and structures. The GPT component leverages the power of transformer-based language models to generate coherent and contextually relevant text. Additionally, a novel metric, Medical Embeddings Attention Distance (MEAD), is proposed in order to capture the semantic similarity between the generated and training medical reports, taking into account the importance of specific words determined by the attention module. Experiments on real dataset demonstrate that our framework achieves state-of-the-art comparable performances in generating accurate and informative medical reports.
Author Vasile, Andrea
Adornetto, Carlo
Guzzo, Antonella
Author_xml – sequence: 1
  givenname: Carlo
  surname: Adornetto
  fullname: Adornetto, Carlo
  email: carlo.adornetto@unical.it
  organization: University of Calabria,Rende,Italy
– sequence: 2
  givenname: Antonella
  surname: Guzzo
  fullname: Guzzo, Antonella
  email: antonella.guzzo@unical.it
  organization: University of Calabria,Rende,Italy
– sequence: 3
  givenname: Andrea
  surname: Vasile
  fullname: Vasile, Andrea
  email: andrea.vasile99@gmail.com
  organization: University of Calabria,Rende,Italy
BookMark eNo1kF1LwzAYRqMoOOf-gRf5A13fJG3TXNbOTWGibPN6pOkbiaxJSauwf-_8ggfOxYFz8VyTCx88EpIymDMGKl1U2zp9cXXo0vpu8YNjriRjcw5czBmIggkOZ2SmpCpFDgKyAvg5mfBSyARkBldkNgzvACcFipViQjbVxxg6PTpDn7B1Rh_oBvsQR7pCj_EkgqefTtO1HtGPdNtrg7QOvnXfyvk3qn1Ld1H7wYbYYRxuyKXVhwFnf5yS1-X9rn5I1s-rx7paJ44xNSYtN1kLTWOA50IYxU5roSiN1aB4w4pGSWNtI0Fa1A0HZVEVMlMFZjnLuZiS29-uQ8R9H12n43H_f4P4Aq0QWQg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/DASC/PiCom/CBDCom/Cy59711.2023.10361320
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350304602
EISSN 2837-0740
EndPage 0435
ExternalDocumentID 10361320
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IM
6IN
AAJGR
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i119t-d2c4d0bbc02533c91c91d068cfa092b16b97cffb707feab209fe967496e451523
IEDL.DBID RIE
IngestDate Wed Aug 27 02:24:16 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i119t-d2c4d0bbc02533c91c91d068cfa092b16b97cffb707feab209fe967496e451523
PageCount 8
ParticipantIDs ieee_primary_10361320
PublicationCentury 2000
PublicationDate 2023-Nov.-14
PublicationDateYYYYMMDD 2023-11-14
PublicationDate_xml – month: 11
  year: 2023
  text: 2023-Nov.-14
  day: 14
PublicationDecade 2020
PublicationTitle IEEE International Conference on Dependable, Autonomic and Secure Computing (Online)
PublicationTitleAbbrev DASC/PICOM/CBDCOM/CYBERSCITECH
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003009183
Score 1.8871486
Snippet This paper presents a comprehensive exploration of integrating artificial intelligence (AI) in the healthcare sector, focusing on the development and...
SourceID ieee
SourceType Publisher
StartPage 0428
SubjectTerms Computer architecture
deep learning
Focusing
GPT
healthcare
Measurement
medical report generation
Medical services
Semantics
Training
Transformers
VAE
Title Automatic Medical Report Generation via Latent Space Conditioning and Transformers
URI https://ieeexplore.ieee.org/document/10361320
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA5uiHhSceJvcvDaLWlq0xzn5vAwxnBTdhtN8gK9dDK7gf-9L2k38eBBKLT08Cjv6yNf3sv3HiEPJhPaJjaPHOgk8vXbSIFIo0crBWRMOxcmz72P5WSSLRZq2ojVgxYGAMLhM-j6x1DLtyuz8akyjHCReslvi7SkTGux1j6hIpAt4P95VM845kz1hv3ZoDctMLB6g6dhuH0hf-Z-WxiL7s7ar7kqYVkZnfzzg05J50egR6f7peeMHEB5Tl77m2oVOrDSpvxCa3pN697SHgK6LXI6Rn5ZVnSG22WgaNEWTVaW5qWl8x2VRWLYIW-j5_ngJWpGJkQF56qKbGwSy7Q2SGWEMIrjZVmaGZczFWueaiWNc1oy6SDXMVMOVCoTlUKCzCYWF6Rdrkq4JBRBsjHainPmMMqNThBNqR0HbhDG_Ip0vEOWH3VXjOXOF9d_vL8hx97tXsfHk1vSrtYbuCOHZlsVn-v7gOU3hUigsQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46RT2pOPG3OXjtljRZ2xzndEysY7gpu43mF_TSyewG_ve-pN3EgwehkNLDI-TrI1_ey_ceQncqYVJznQXWSB64_G0gDIuCjo6ZSYi01neee0_j4TCZTsWoFqt7LYwxxl8-My336nP5eq6WLlQGHs4iJ_ndRjsdDnYrudYmpMKAL8Afuld1OaZEtB-64157lINrtXv3D374AgZN3cEwZK21vV-dVfzG0j_855SOUPNHoodHm83nGG2Z4gS9dpfl3NdgxXUCBlcEG1fVpR0IeJVnOAWGWZR4DAdmg8Gizuu4LM4KjSdrMgvUsIne-o-T3iComyYEOaWiDHSouCZSKiAzjClB4dEkSpTNiAgljaSIlbUyJrE1mQyJsEZEMReR4cBtQnaKGsW8MGcIA0w6BFthRiz4uZIc8IylpYYqADI7R023ILOPqi7GbL0WF398v0X7g8lLOkufhs-X6MBB4FR9lF-hRrlYmmu0q1Zl_rm48bh-AxB9o_g
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Conference+on+Dependable%2C+Autonomic+and+Secure+Computing+%28Online%29&rft.atitle=Automatic+Medical+Report+Generation+via+Latent+Space+Conditioning+and+Transformers&rft.au=Adornetto%2C+Carlo&rft.au=Guzzo%2C+Antonella&rft.au=Vasile%2C+Andrea&rft.date=2023-11-14&rft.pub=IEEE&rft.eissn=2837-0740&rft.spage=0428&rft.epage=0435&rft_id=info:doi/10.1109%2FDASC%2FPiCom%2FCBDCom%2FCy59711.2023.10361320&rft.externalDocID=10361320