[go: up one dir, main page]

WO2008117231A1 - Procédé, système et programme d'ordinateur pour générer de manière automatique un rapport médical sur la base d'images médicales - Google Patents

Procédé, système et programme d'ordinateur pour générer de manière automatique un rapport médical sur la base d'images médicales Download PDF

Info

Publication number
WO2008117231A1
WO2008117231A1 PCT/IB2008/051094 IB2008051094W WO2008117231A1 WO 2008117231 A1 WO2008117231 A1 WO 2008117231A1 IB 2008051094 W IB2008051094 W IB 2008051094W WO 2008117231 A1 WO2008117231 A1 WO 2008117231A1
Authority
WO
WIPO (PCT)
Prior art keywords
images
dictation
screen
medical report
patient
Prior art date
Application number
PCT/IB2008/051094
Other languages
English (en)
Inventor
Matthias Helletzgruber
Ljubomir Milanovic
Kresimir R. Rajic
Mehmet M. Oez
Original Assignee
Koninklijke Philips Electronics N.V.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Koninklijke Philips Electronics N.V. filed Critical Koninklijke Philips Electronics N.V.
Publication of WO2008117231A1 publication Critical patent/WO2008117231A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS

Definitions

  • the invention relates to a method for automatically generating a medical report based on medical images of a patient, wherein a practitioner or medical specialist, particularly a radiologist chooses different images of a patient and visually presents these images on the screen of at least one displaying device.
  • the radiologist creates a dictation file by dictating a medical report while viewing the images on the screen of each displaying device. Thereafter, a final medical report is automatically generated by a speech recognition of the dictation file.
  • This medical report can be sent back to the radiologist for correction. After possible corrections, the reporting radiologist finally signs the corrected report and the final report is created and delivered.
  • the invention further relates to a system for automatically generating a medical report based on medical images of a patient.
  • the invention further relates to a computer program product comprising a computer-readable medium bearing computer-executable instructions for carrying out a method as described above.
  • Modern medical information systems use so called picture archiving and communication systems (,,PACS”) for storing, observing and analyzing images obtained in medical applications.
  • the PACS may be used with several technologies for observing the interior anatomy of a living being. Imaging can be done by X-ray ultrasound-computed tomography, magnetic resonance imaging (MRI), position emission tomography, mammography, endoscopy and the like. Different images of a patient or parts of a patient are stored in the data base of the PACS.
  • the PACS can be connected to a radiology-hospital information system (RIS-HIS) containing additional information about the patient.
  • RIS-HIS radiology-hospital information system
  • the practitioner or medical specialist uses a client of the PACS for viewing the images of the patient during generation of the medical report.
  • the radiologist is frequently examining a large number of images on the screen of at least one client of the PACS.
  • the speech file is automatically converted to written text by means of an appropriate speech recognition system.
  • Only a small number of images is relevant for the final decision of the reporting radiologist.
  • These pictures are usually flagged as ,,key images", however, after the report has been finished, the connection between a relevant subset of all images and the sections of the report is lost.
  • the process of decision making is not transparent and the reader of the medical report cannot easily reconstruct the decision process.
  • US 6,766,297 Bl describes such a method for integrating a picture archiving and communication system (PACS) and a voice dictation or speech recognition system.
  • PACS picture archiving and communication system
  • US 5,995,936 A shows a report generation system and method for capturing both, audio and video by voice command and automatically linking sound and image to formatted text locations. Commands for image acquisition cause digital images to be added to the report or to a data base file. Nevertheless, it is necessary that the reporting person actively adds information to the report.
  • the object of the present invention is to provide a method and system for automatically generating a medical report based on medical images, which automatically adds information to the report.
  • the method for automatically generating a medical report based on medical images of a patient therefore comprises the following steps: visually presenting images of the patient on the screen of at least one displaying device, - creating a dictation file by dictating by a person the medical report while viewing the images on the screen of each displaying device, automatically generating a written final medical report by speech recognition of the dictation file, capturing the presentation of the images of the patient on the screen of each displaying device during dictating the medical report as a function of time into information, and storing the information of the captured images of the patient together with the dictation file.
  • the features of the present invention make it possible to automatically link the medical report to the images viewed by the radiologist during dictation of the medical report.
  • a kind of log file is created which shows the history during generation of the medical report. This information can be stored for later analysis or for documentation purposes as well as for training new physicians.
  • the method according to the present invention can be used for creating a document slowing the process decision in case of legal problems.
  • the duration of the presentation of each image on the screen of each displaying device is monitored and stored during dictation. Using this feature, that image will be defined as the most relevant image which has been viewed longest by the radiologist. Other images which have been viewed only over very short periods will be defined as not relevant.
  • the position of the eyes of the person viewing the images on the screen of each displaying device and creating the dictation file can be monitored and stored during dictation. Eye-tracking can be used to automatically provide even more detailed information. By monitoring the position of the radiologist's eyes not only the relevant images but also relevant parts within the image can be identified and included into the final medical report.
  • the position of a mouse pointer is monitored and stored during dictation.
  • This method can also provide more information about relevant areas of the image, since the radiologist usually moves the mouse pointer within the relevant areas.
  • physiological parameters of the person viewing the images on the screen of each displaying device and creating the dictation file can be monitored and stored during dictation.
  • physiological parameters as skin impedance, heart rate, body temperature or the like can provide additional information being important for the decision as to which images or areas of images are relevant with respect to the final medical report.
  • markers can be placed during dictation and stored together with the dictation file. By means of such markers, the radiologist can actively make connections between the images and the medical report.
  • indicators which indicate chapters of the medical report can be placed during dictation and stored together with the dictation file.
  • the most relevant image in relation to the dictation file is determined and stored together with the dictation file.
  • the most relevant areas of the images in relation to the dictation file are determined and stored together with the dictation file.
  • the stored dictation file together with the viewed images during generation of the dictation file can be played-back acoustically and visually on the screen of a displaying device.
  • the decision of the reporting medical doctor can be observed together with the information which is linked to the dictation file as described above.
  • a system for automatical generation of a medical report based on medical images of a patient comprising at least one displaying device with a screen for visual presentation of images of the patient, a dictation system for creation of a dictation file by dictation by a person of the medical report while viewing the images on the screen of each displaying device, a speech recognition system for automatical generation of a written final medical report, correction means for possible corrections of the medical report, means for capturing the presentation of the images of the patient on the screen of each displaying device during dictation of the medical report as a function of time into information, and means for storing the information of the captured images of the patient together with the dictation file.
  • a computer program product which can be loaded into the memory of a digital computer and which comprises computer executable instructions for carrying out the method described above when the program is running on the computer.
  • FIG. 1 shows a schematic block diagram illustrating a method for generating a medical report based on medical images according to the present state of the art
  • Fig. 2 shows a schematic block diagram illustrating a method for generating a medical report based on medical images according to the present invention
  • Fig. 3 shows a schematic time diagram during generating a medical report according to the present invention.
  • Fig. 4 shows an example of the representation of a medical report generated according to the present invention on the screen of a computer monitor.
  • Fig. 1 shows a schematic block diagram illustrating a method for generating a medical report based on medical images of a patient according to the present state of the art.
  • Modern medical information systems use so called picture archiving and communication systems (,,PACS”) 1 for storing, observing and analyzing images obtained in medical applications.
  • the PACS 1 may be used with several technologies for observing the interior anatomy of a living being. These imaging systems may include X-ray equipment or radiography 2, ultrasound equipment 3, computed tomography equipment 4 or other imaging systems (not shown), such as magnetic resonance imaging (MRI), position emission tomography, mammography or endoscopy. Different images of a patient or parts of a patient are stored in the database of the PACS 1.
  • MRI magnetic resonance imaging
  • the server of the PACS 1 is connected to clients 6 which provide or utilize the images.
  • the PACS 1 can be connected to a radiology/hospital information system (RIS/HIS) 5 containing additional information about the patients.
  • RIS/HIS radiology/hospital information system
  • the practitioner or medical specialist, particularly a radiologist Di uses a client 6 of the PACS 1 for viewing the images of the patient during generation of the medical report.
  • the author of the medical report, particularly a radiologist D 1 uses a dictation system 7 for generation of the medical report.
  • the radiologist Di is frequently examining a large number of images on the screen of at least one client 6 of the PACS 1. After having finished the dictation with the dictation system 7, the speech file is automatically converted to written text by means of an appropriate speech recognition system 8.
  • a transcriptionist usually corrects the report and sends the report back to the author, particularly the radiologist D 1 , for review. After possible corrections, the reporting radiologist Di finally signs the corrected report and the final report 9 is created and delivered.
  • a referring practitioner D 2 or the respective patient receives the final report 9 on different ways, for instance by mail, by fax or via internet by using a terminal being connected to the system where the final reports 9 are stored.
  • the final report 9 has to be provided with special codes, usually demanded by the insurance company. Coding can be done manually or computer- assisted in a coding system 10.
  • a billing system 11 the invoices are generated and sent to the insurance company or patient.
  • the generated billing documents can be stored in a data base 12 being connected to the billing system 11. According to block 13 someone, such as insurances or patients, pay for these services.
  • the radiologist Di is frequently examining a large number of images. However, often only a small number of images is relevant for the final decision of the radiologist D 1 . Such a final decision in the medical report typically includes a diagnosis and at least one possible therapy. Often, the connection between these so called “key images” and the medical report is lost, since the radiologist Di often does not indicate these "key images” or the relevant part of the "key images”. Therefore, the process of decision making by the radiologist Di is not transparent for the reader. Therefore, the reader, that is, for instance, the referring practitioner D 2 or the patient, cannot easily reconstruct the decision process of the reporting practitioner, particularly the radiologist D 1 .
  • Fig. 2 shows a schematic block diagram illustrating one embodiment of a method for generating a medical report based on medical images of a patient according to the present invention.
  • the difference to the method according to the state of the art according to Fig. 1 is the connection between the PACS 1 and the reporting radiologist Di with the dictation system 7.
  • the images chosen by the radiologist Di are automatically captured. This can be done by various means 14.
  • the images which are viewed by the radiologist Di on the screen of the client 6 of the PACS 1 can be stored in dependency on time during generation of the medical report in addition to the speech file. This additional information will be converted into adequate parameters during automatical speech recognition.
  • This additional information according to the present invention will be available for later analysis or for documentation purposes or can be used for training of new physicians. Also for legal aspects, this additional information can be helpful as a document showing the decision process in case of legal problems.
  • More information about the decision of the radiologist Di during report- generation can be obtained when not only the time of the viewed images on the screen of the client 6 and the identification of the images is recorded, but also the relevant parts of the viewed images are scanned. This can be done by mouse tracking means 15, which are capable of tracking the position of the mouse pointer, moved by the radiologist Di during generation of the report.
  • Eye tracking means 16 by which movement of the eyes of the radiologist Di can be monitored. Movement of the eyes on the images give information about relevant areas of the images viewed by the radiologist Di . If the radiologist Di spends relatively much time on viewing a special area of a special image, this could be an evidence for an important area of a "key image". Not only the time but also especially the kind of movement of the eyes can be taken into account for the decision process.
  • means 17 for monitoring physiological parameters of the radiologist D 1 such as skin impedance, heartbeat or the like, can be monitored, analyzed and stored together with the speech information of the dictation system 7.
  • RIS/HIS radiology/hospital information system
  • dictation system 7 also requests of the radiologist Di for additional information about the patient can be stored together with the speech information within the speech system 7.
  • the present invention makes it possible to create a history of report generation.
  • This kind of log file includes information about which images have been studied, how long the radiologist Di has examined every image, which text has been dictated as a result of particular image examination and so on. As mentioned above, this information can be stored for later analysis or for documentation purposes. Further, the information can also be used for training of new physicians to learn from the methods of experienced radiologists. The additional information can also be used as a document showing the decision process in case of legal problems.
  • Fig. 3 shows a schematic time diagram during generation of a medical report.
  • Diagram 1 shows the images I 1 displayed on the screen of the client 6 of the PACS 1 as a function of time.
  • the radiologist D 1 starts with image Ii followed by images I 2 and I3, then viewing again image Ii and so on.
  • the reporting medical doctor, particularly radiologist D 1 uses more than one screen or clients 6 of the PACS 1.
  • the images I 1 of all screens will be monitored as a function of time.
  • the radiologist Di often chooses image Ii . Therefore, it can be concluded that image Ii contains the most relevant information for the diagnosis by the radiologist D 1 .
  • Diagram Di in Fig. 3 shows the dictation activity of the radiologist Di during generation of the medical report. Between dictation phases there are intervals of various length, where nothing has been dictated. After having finished the dictation, the final report 9 is generated by speech recognition 8.
  • the final medical report 9 contains different parts I - IV which can be divided into the following subject areas, for instance: I Patient information
  • Fig. 4 shows an example of the representation of a medical report generated according to the present invention on the screen of a computer monitor 20.
  • the screen 20 shows the image 25 of the medical report in the right part.
  • At the lower side of the screen 20 there is an indicator 21 showing the position of the dictation during playback.
  • the time 22 of the playback can also be displayed on the screen 20.
  • buttons I - IV can show the position of the dictation in connection with the medical report as described above. Starting with I (Patient information), the report contains part II (History), part III (Findings) and finally part IV (Conclusion). Since the parts I - IV of the medical report will differ in length, the position of indicators II, III and IV will vary. Using the computer mouse (not shown), indicator 21 can be moved along the horizontal position. If indicator 21 is moved to the beginning of part IV
  • the relevant part in the image 25 of the report will be high- lighted and the most relevant image will be shown on the left part 24 of the screen 20. Therefore, the user gets very important additional information about the decision process of the report generation and a lot of time can be saved.
  • an arrow 26 the position of the mouse pointer during generation of the medical report by the radiologist Di can be shown, if the position of the mouse has been monitored by mouse tracking.
  • a cross 27 may indicate the position of the eyes of the radiologist Di during generation of the medical report, if eye tracking has been done. The present invention enables a considerable improvement in the field of generation of medical reports based on the output of medical images.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Public Health (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Primary Health Care (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

La présente invention porte sur un procédé et sur un système pour générer de manière automatique un rapport médical sur la base d'images médicales (Ii) d'un patient, comprenant les étapes consistant à : présenter visuellement les images (Ii) du patient sur l'écran d'au moins un dispositif d'affichage (6), créer un fichier de dictée par dictée du rapport médical lors de la visualisation des images (Ii) sur l'écran de chaque dispositif d'affichage (6), générer automatiquement un rapport (9) médical final écrit au moyen d'une reconnaissance vocale du fichier de dictée, réaliser des étapes de correction possibles, capturer la présentation des images (Ii) du patient sur l'écran de chaque dispositif d'affichage (6) pendant la dictée du rapport médical en fonction du temps, et stocker les informations des images capturées (Ii) du patient conjointement avec le fichier de dictée.
PCT/IB2008/051094 2007-03-27 2008-03-25 Procédé, système et programme d'ordinateur pour générer de manière automatique un rapport médical sur la base d'images médicales WO2008117231A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP07104956.3 2007-03-27
EP07104956 2007-03-27

Publications (1)

Publication Number Publication Date
WO2008117231A1 true WO2008117231A1 (fr) 2008-10-02

Family

ID=39651313

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2008/051094 WO2008117231A1 (fr) 2007-03-27 2008-03-25 Procédé, système et programme d'ordinateur pour générer de manière automatique un rapport médical sur la base d'images médicales

Country Status (1)

Country Link
WO (1) WO2008117231A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3004269A1 (fr) * 2013-04-05 2014-10-10 Systemx Procede et systeme permettant de generer des comptes rendus audio et video d'examens d'imagerie medicale

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6819785B1 (en) * 1999-08-09 2004-11-16 Wake Forest University Health Sciences Image reporting method and system
US20040254816A1 (en) * 2001-10-30 2004-12-16 Myers Gene E. Network-connected personal medical information and billing system
US20050267337A1 (en) * 2004-05-31 2005-12-01 Shuji Sakai Diagnosis assisting system and storage medium having diagnosis assisting program stored therein
US20060277073A1 (en) * 2005-06-06 2006-12-07 Heilbrunn Ken S Atlas reporting

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6819785B1 (en) * 1999-08-09 2004-11-16 Wake Forest University Health Sciences Image reporting method and system
US20040254816A1 (en) * 2001-10-30 2004-12-16 Myers Gene E. Network-connected personal medical information and billing system
US20050267337A1 (en) * 2004-05-31 2005-12-01 Shuji Sakai Diagnosis assisting system and storage medium having diagnosis assisting program stored therein
US20060277073A1 (en) * 2005-06-06 2006-12-07 Heilbrunn Ken S Atlas reporting

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3004269A1 (fr) * 2013-04-05 2014-10-10 Systemx Procede et systeme permettant de generer des comptes rendus audio et video d'examens d'imagerie medicale

Similar Documents

Publication Publication Date Title
US7698152B2 (en) Medical image viewing management and status system
US8526693B2 (en) Systems and methods for machine learning based hanging protocols
JP6422486B2 (ja) 高度医用画像処理ウィザード
CA2856261C (fr) Procedes et techniques de recueil, d'etablissement de rapports et de gestion d'informations relatives a des procedures de diagnostic medical
JP5525675B2 (ja) 医用画像診断支援装置、医用画像診断装置、又は医用画像診断支援システム
US8254648B2 (en) Method for providing adaptive hanging protocols for image reading
US11610667B2 (en) System and method for automated annotation of radiology findings
JP6464254B2 (ja) 造影剤ベースの医療処置での副作用を管理するシステム及び方法
US20040204965A1 (en) Method and system for facilitating selection of stored medical image files
US20140087342A1 (en) Training and testing system for advanced image processing
US20110150420A1 (en) Method and device for storing medical data, method and device for viewing medical data, corresponding computer program products, signals and data medium
JP2004267273A (ja) 医用システム
US20170083665A1 (en) Method and System for Radiology Structured Report Creation Based on Patient-Specific Image-Derived Information
CN111202537A (zh) 在成像过程期间实时捕获患者生命体征的方法和装置
US10825173B2 (en) Automatically linking a description of pathology in a medical image report to an image
CN111986182A (zh) 辅助诊断方法、系统、电子设备及存储介质
US8923582B2 (en) Systems and methods for computer aided detection using pixel intensity values
US20090245609A1 (en) Anatomical illustration selecting method, anatomical illustration selecting device, and medical network system
US20120200605A1 (en) Flow radiology user interface
US8218883B2 (en) Image compression method, image compression device, and medical network system
US20090125555A1 (en) Method and apparatus for flexible archiving
CN114093451A (zh) 一种pacs系统管理用户数据的方法及系统
WO2008117231A1 (fr) Procédé, système et programme d'ordinateur pour générer de manière automatique un rapport médical sur la base d'images médicales
US20050288568A1 (en) Real-time automatic searching system for medical image and method for the same
US8434005B2 (en) Audio/video interface as a supplement to radiology reports

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 08737628

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 08737628

Country of ref document: EP

Kind code of ref document: A1