WO2024054167A1 - Artificial intelligence supported archive inquiry system and method - Google Patents
Artificial intelligence supported archive inquiry system and method Download PDFInfo
- Publication number
- WO2024054167A1 WO2024054167A1 PCT/TR2022/050962 TR2022050962W WO2024054167A1 WO 2024054167 A1 WO2024054167 A1 WO 2024054167A1 TR 2022050962 W TR2022050962 W TR 2022050962W WO 2024054167 A1 WO2024054167 A1 WO 2024054167A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- queried
- pathology
- archive
- query
- client device
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 28
- 230000007170 pathology Effects 0.000 claims abstract description 69
- 238000003745 diagnosis Methods 0.000 claims abstract description 18
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 10
- 201000011510 cancer Diseases 0.000 claims abstract description 10
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 7
- 239000011521 glass Substances 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 210000000056 organ Anatomy 0.000 claims description 6
- 238000010186 staining Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007447 staining method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 3
- 206010006187 Breast cancer Diseases 0.000 description 2
- 208000026310 Breast neoplasm Diseases 0.000 description 2
- 238000013434 data augmentation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003211 malignant effect Effects 0.000 description 2
- 238000010827 pathological analysis Methods 0.000 description 2
- 238000004513 sizing Methods 0.000 description 2
- 208000035977 Rare disease Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 210000004789 organ system Anatomy 0.000 description 1
- 239000012188 paraffin wax Substances 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Definitions
- the present invention reiates to an artificial intelligence supported archive query system and method used for diagnosis via microscopic image in the diagnosis of cancer diseases in the field of medical pathology.
- the present invention reiates to an artificial intelligence supported archive query system and method that provides uploading pathology slide image data obtained with a slide scanner or microscope camera to a database and creating possible diagnostic opinions on similar cases by querying the images of the patient studied (to be diagnosed) in the aforementioned database and using the database records efficiently in diagnosis of pathology.
- Pathology which plays a major role in the diagnosis and treatment of cancer, is of great importance.
- Pathology science is based on visual evaluation of microscopic visual data by pathologists. Since the pathological diagnosis cannot be expressed with precise rules and numerical values, it may vary according to the experience of the pathologist and daily intensity. Therefore, pathologists are forced to make decisions on their own, especially in rare disease states, and require consultation. It is difficult to reach a consultant specialist who has the expertise of different organ systems in a timely manner and to get his/her opinion with the increasing number of patients.
- the physician compares the case he/she found out of the archive with the case he/she had difficulty in diagnosing under the microscope. These processes are repeated until the correct archive patient is found. After the patient to be diagnosed and the confirmed case from the archive are matched with the physician's eye, parallel diagnosis is created by accessing the written report of the patient withdrawn from the archive. At the end of the process, the glass slides taken from the archive must be sent back to the archive.
- said process is a method that can work and the whole process can take hours, sometimes days. Physicians working in centers with limited number and content of cases in the archive have to start the process of searching for a co-diagnosis again by applying to the archives in large pathology centers with special permissions. In such cases, the process takes weeks.
- the present invention relates to an artificial intelligence supported archive inquiry system and method water treatment system which eliminates the abovementioned disadvantages and brings new advantages to the relevant technical field.
- the main aim of the invention is to reveal an artificial intelligence supported archive query system and method that provides uploading pathology slide image data obtained with a slide scanner or microscope camera to a database and creating possible diagnostic opinions on similar cases by querying the images of the patient studied (to be diagnosed) in the aforementioned database.
- the aim of the invention is to provide a digital decision support system that uses second opinion, data mining, image processing and artificial intelligence methods that are needed in pathological diagnosis.
- Another aim of the invention is to ensure the efficient use of digital archives in diagnosing pathology.
- Another aim of the present invention is to provide a highly accurate, reproducible and useful approach in diagnosing pathology, by obtaining second opinion from artificial intelligence and finding cases with rapid, definitive diagnosis.
- Another aim of the invention is to reveal an artificial intelligence supported archive query system and method that can be used for every cancer type and new data can be added to the database.
- Another aim of the invention is to make idle pathology archives functional by querying them with artificial intelligence.
- an artificial intelligence supported archive query system that can be installed on a client device (10) such as a computer, tablet or smartphone, to be used in the diagnosis of cancer diseases in the field of medical pathology for diagnosis via microscopic image, characterized by comprising of the following; an interface on the client device used to query the pathology slide images to be queried by the user,
- the present invention is also an artificial intelligence supported archive query method used for diagnosis via microscopic image in the diagnosis of cancer diseases in the field of medical pathology, characterized by comprising of the following process steps; a) sending the pathology slide image to be queried by the user via the user interface on the client device to the server, b) extracting the feature vectors using the deep neural network on the pathology slide image loaded by the client device by means of the query module running on the server, c) comparing the features obtained on the pathology slide image to be queried with the vectors in the archive database by the query module and identifying the slides and patients closest to the pathology slide image to be queried, d) filtering the cluster to be queried in the archive database according to the entered clinical information in the query module and transmitting the visual and textual data of the patients with the detected slide to the client device in case of entering clinical information such as age, gender, organ of the patient being queried from which the sample was taken or the pathology slide image to be queried, method of glass staining etc.
- Figure 1 Is a block diagram of the inventive artificial intelligence supported archive inquiry system.
- the artificial intelligence supported archive query system and method basically comprises of the following; a client device (10) having a user interface (11) used for querying the pathology slide images (S) to be queried by the user, a server (20) having an archive database containing pathology slide images, clinical data of patients and pathology result reports (21) and a query module (22) that finds the pathology slide images closest to the pathology slide image to be queried (S) in the archive database (21) by artificial intelligence-based methods using the deep artificial neural network and sends the necessary information to the client device (10) communication channel (30) that provides the network connection between the client device (10) and the server (20).
- the user uses a client device (10) to query the pathology slide images (S) to be queried.
- Said client device (10) may be a computer, tablet or smartphone.
- the client device (10) has a web-based user interface (11) that establishes secure communication between the server (20) and the user.
- Clinical information patient age, gender, sample organ, glass staining method, etc.
- Clinical information can also be installed optionally to the server (20) via the user interface (11) over the client device (10). This clinical information is used to increase query speed and performance by narrowing the archive query.
- Pathology slide image (S) to be questioned is the pathology slide image of the patient to be diagnosed and obtained with a whole slide scanner or digital camera.
- the server (20), which constitutes the main structure of the inventive artificial intelligence supported archive query system basically has at least one archive database (21) and query module (22).
- Said archive database (21) contains pathology slide images, clinical data of the patients and pathology result reports.
- the query module (22) finds the pathology slide images closest to the pathology slide image to be queried (S) in the archive database (21) by artificial intelligence-based methods using the deep artificial neural network and sends the necessary information to the client device (10).
- Said query module (22) extracts the feature vectors using the deep neural network on the pathology slide image loaded to be queried (S) by the client device (10).
- the features obtained on the pathology slide image to be queried (S) are compared with the vectors in the archive database (21) and the slides and patients closest to the pathology slide image to be queried (S) are identified.
- the network connection between the client device (10) and the server (20) is provided via the communication channel (30).
- the process steps of the inventive artificial intelligence supported archive query method is as follows; a) Sending the pathology slide image to be queried (S) by the user via the user interface (11) on the client device (10) to the server (20), b) Extracting the feature vectors using the deep neural network on the pathology slide image loaded to be queried (S) by the client device (10) by means of the query module (22) running on the server (20), c) Comparing the features obtained on the pathology slide image to be queried (S) with the vectors in the archive database (21) by the query module (22) and identifying the slides and patients closest to the pathology slide image to be queried (S), d) Filtering the cluster to be queried in the archive database (21) according to the entered clinical information in the query module (22) and transmitting the visual and textual data of the patients with the detected slide to the client device (10) in case of entering clinical information such as age, gender, organ of the patient being questioned from which the sample was taken or the pathology slide image to be queried (S), method of glass stain
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Radiology & Medical Imaging (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention relates to an artificial intelligence supported archive query system and method used for diagnosis via microscopic image in the diagnosis of cancer diseases in the field of medical pathology.
Description
ARTIFICIAL INTELLIGENCE SUPPORTED ARCHIVE INQUIRY SYSTEM AND METHOD
Field of the Invention
The present invention reiates to an artificial intelligence supported archive query system and method used for diagnosis via microscopic image in the diagnosis of cancer diseases in the field of medical pathology.
The present invention reiates to an artificial intelligence supported archive query system and method that provides uploading pathology slide image data obtained with a slide scanner or microscope camera to a database and creating possible diagnostic opinions on similar cases by querying the images of the patient studied (to be diagnosed) in the aforementioned database and using the database records efficiently in diagnosis of pathology.
State of the Art
Pathology, which plays a major role in the diagnosis and treatment of cancer, is of great importance. Pathology science is based on visual evaluation of microscopic visual data by pathologists. Since the pathological diagnosis cannot be expressed with precise rules and numerical values, it may vary according to the experience of the pathologist and daily intensity. Therefore, pathologists are forced to make decisions on their own, especially in rare disease states, and require consultation. It is difficult to reach a consultant specialist who has the expertise of different organ systems in a timely manner and to get his/her opinion with the increasing number of patients.
In the state of the art, patients diagnosed in the pathology archive are classified and stored by the date of the case record and the patient record number. Glass slides stained with thin sections of the parts taken from the patient are usually requested through the registration number with the personnel in charge of the archive in cases where the physician has difficulty in diagnosis, when it is necessary to investigate similar cases from the archive. The archive personnel deliver the glass slides of the requested patient to the physician who will
make the inquiry after finding them in the archive. The physician examines the glass slides under the microscope to check whether it is the correct case or not. At the same time, the paraffin cassette containing all the tissue can be accessed separately from the archive in case the glass slide has faded and a new glass slide is prepared by taking thin sections and re-staining with the help of a microtome. The physician compares the case he/she found out of the archive with the case he/she had difficulty in diagnosing under the microscope. These processes are repeated until the correct archive patient is found. After the patient to be diagnosed and the confirmed case from the archive are matched with the physician's eye, parallel diagnosis is created by accessing the written report of the patient withdrawn from the archive. At the end of the process, the glass slides taken from the archive must be sent back to the archive. In case there is a patient in the archive that is the same archive as the patient who is trying to be diagnosed, said process is a method that can work and the whole process can take hours, sometimes days. Physicians working in centers with limited number and content of cases in the archive have to start the process of searching for a co-diagnosis again by applying to the archives in large pathology centers with special permissions. In such cases, the process takes weeks.
As a result of a research in the state of the art, the article titled "Breast Cancer Detection in Histopathological Images Using Deep Neural Networks" published in 2020 was found. Said article describes a study for the detection of breast cancer on histopathological images using deep neural networks. In said study, first images of the patient are taken and a sizing process is applied to ensure that these image inputs are the same size and the data set is expanded with data augmentation, thus adding more case studies to the network. After the sizing and data augmentation process, the images of the patient are compared with the samples in the archive, to determine whether the patient's cancer is benign or malignant. Here, a method is proposed to detect whether the cancer is benign or malignant, however, it is not possible to query the images of the patient that is studied, that is, to be diagnosed, to identify similar cases and present them to the physician with this method. Here, it is not possible for the expert examining the case to form possible diagnostic opinions on similar cases. Thus, the expert cannot use the database records efficiently in diagnosing pathology. Even if a digital method was used in disease detection with the aforementioned study, at the point where the physician has difficulty in diagnosing, it is not possible to obtain and examine similar cases easily and quickly.
Although there are intensive scientific studies on digital pathology and computer-based pathological decision support systems to fill the above-mentioned gap in current practices, there is no artificial intelligence supported archive query system that pathologists can use routinely. Today, pathology archives are too dysfunctional and in a bad state to query the patient's slide and to find the past slide of the relevant patient. Developing digital pathology technologies will enable the digitization of pathology archives over time. However, the storage of this dense digital data in server environments will mean that the archive will still be dysfunctional. Although all slide scanners are used in the state of the art, decision support systems have not been developed yet, which find similar cases with visual comparison algorithms by querying the high-dimensional images formed in the pathology archive.
As a result of the aforementioned issues and the limited supply of available solutions, it became necessary to carry out an improvement in the relevant technical field.
Aim of the Invention
The present invention relates to an artificial intelligence supported archive inquiry system and method water treatment system which eliminates the abovementioned disadvantages and brings new advantages to the relevant technical field.
The main aim of the invention is to reveal an artificial intelligence supported archive query system and method that provides uploading pathology slide image data obtained with a slide scanner or microscope camera to a database and creating possible diagnostic opinions on similar cases by querying the images of the patient studied (to be diagnosed) in the aforementioned database.
The aim of the invention is to provide a digital decision support system that uses second opinion, data mining, image processing and artificial intelligence methods that are needed in pathological diagnosis.
Another aim of the invention is to ensure the efficient use of digital archives in diagnosing pathology.
Another aim of the present invention is to provide a highly accurate, reproducible and useful approach in diagnosing pathology, by obtaining second opinion from artificial intelligence and finding cases with rapid, definitive diagnosis.
Another aim of the invention is to reveal an artificial intelligence supported archive query system and method that can be used for every cancer type and new data can be added to the database.
Another aim of the invention is to make idle pathology archives functional by querying them with artificial intelligence.
In order to fulfill all the aims mentioned above and which may arise from the detailed explanation; an artificial intelligence supported archive query system that can be installed on a client device (10) such as a computer, tablet or smartphone, to be used in the diagnosis of cancer diseases in the field of medical pathology for diagnosis via microscopic image, characterized by comprising of the following; an interface on the client device used to query the pathology slide images to be queried by the user,
Archive database containing pathology slide images, clinical data such as patients' age, gender, sample organ, glass staining method, and pathology result reports, a server with a query module that finds the pathology slide images closest to the pathology slide image to be queried in the archive database by artificial intelligence-based methods using the deep artificial neural network and sends the necessary information to the client device, communication channel that provides the network connection between the client device and the server.
The present invention is also an artificial intelligence supported archive query method used for diagnosis via microscopic image in the diagnosis of cancer diseases in the field of medical pathology, characterized by comprising of the following process steps; a) sending the pathology slide image to be queried by the user via the user interface on the client device to the server,
b) extracting the feature vectors using the deep neural network on the pathology slide image loaded by the client device by means of the query module running on the server, c) comparing the features obtained on the pathology slide image to be queried with the vectors in the archive database by the query module and identifying the slides and patients closest to the pathology slide image to be queried, d) filtering the cluster to be queried in the archive database according to the entered clinical information in the query module and transmitting the visual and textual data of the patients with the detected slide to the client device in case of entering clinical information such as age, gender, organ of the patient being queried from which the sample was taken or the pathology slide image to be queried, method of glass staining etc. e) selecting the entire archive database as a query set in the query module and transmitting the visual and textual data of the patients with the slide, which is found to be similar to the pathology slide image to be queried as a result of the query, to the client device to be shown to the user in case the clinical information of the queried patient or the pathology slide image to be queried is not entered.
The structural and characteristic features of the present invention will be understood clearly by the following drawings and the detailed description made with reference to these drawings. Therefore the evaluation shall be made by taking these figures and the detailed description into consideration.
Figures Clarifying the Invention
Figure 1: Is a block diagram of the inventive artificial intelligence supported archive inquiry system.
Description of the Part References
10. Client device
11. User interface
20. Server
21. Archive database
22. Query module
30. Communication Channel
Q. Pathology slide image to query
Detailed Description of the Invention
In this detailed description, the preferred alternatives of the inventive artificial intelligence supported archive query system and method is described only for clarifying the subject matter such that no limiting effect is created.
In Figure 1, the block diagram of the inventive artificial intelligence supported archive query system and method which is the subject of the invention is given. Accordingly the artificial intelligence supported archive query system and method basically comprises of the following; a client device (10) having a user interface (11) used for querying the pathology slide images (S) to be queried by the user, a server (20) having an archive database containing pathology slide images, clinical data of patients and pathology result reports (21) and a query module (22) that finds the pathology slide images closest to the pathology slide image to be queried (S) in the archive database (21) by artificial intelligence-based methods using the deep artificial neural network and sends the necessary information to the client device (10) communication channel (30) that provides the network connection between the client device (10) and the server (20).
In the inventive artificial intelligence supported archive query system, the user uses a client device (10) to query the pathology slide images (S) to be queried. Said client device (10) may be a computer, tablet or smartphone. The client device (10) has a web-based user interface (11) that establishes secure communication between the server (20) and the user. Clinical information (patient age, gender, sample organ, glass staining method, etc.) of the patient, or the pathology slide image (S) to be queried can also be installed optionally to the server (20) via the user interface (11) over the client device (10). This clinical information is used to increase query speed and performance by narrowing the archive query.
Pathology slide image (S) to be questioned is the pathology slide image of the patient to be diagnosed and obtained with a whole slide scanner or digital camera.
The server (20), which constitutes the main structure of the inventive artificial intelligence supported archive query system basically has at least one archive database (21) and query module (22). Said archive database (21) contains pathology slide images, clinical data of the patients and pathology result reports. The query module (22) finds the pathology slide images closest to the pathology slide image to be queried (S) in the archive database (21) by artificial intelligence-based methods using the deep artificial neural network and sends the necessary information to the client device (10). Said query module (22) extracts the feature vectors using the deep neural network on the pathology slide image loaded to be queried (S) by the client device (10). The features obtained on the pathology slide image to be queried (S) are compared with the vectors in the archive database (21) and the slides and patients closest to the pathology slide image to be queried (S) are identified.
The network connection between the client device (10) and the server (20) is provided via the communication channel (30).
The process steps of the inventive artificial intelligence supported archive query method is as follows; a) Sending the pathology slide image to be queried (S) by the user via the user interface (11) on the client device (10) to the server (20), b) Extracting the feature vectors using the deep neural network on the pathology slide image loaded to be queried (S) by the client device (10) by means of the query module (22) running on the server (20), c) Comparing the features obtained on the pathology slide image to be queried (S) with the vectors in the archive database (21) by the query module (22) and identifying the slides and patients closest to the pathology slide image to be queried (S), d) Filtering the cluster to be queried in the archive database (21) according to the entered clinical information in the query module (22) and transmitting the visual and textual data of the patients with the detected slide to the client device (10) in case of entering clinical information such as age, gender, organ of the patient being questioned from which the sample was taken or the pathology slide image to be queried (S), method of glass staining etc.
e) Selecting the entire archive database (21) as a query set in the query module (22) and transmitting the visual and textual data of the patients with the slide, which is found to be similar to the pathology slide image to be queried (S) as a result of the query, to the client device (10) to be shown to the user in case the clinical information of the queried patient or the pathology slide image to be queried is not entered.
Claims
1. An artificial intelligence supported archive query system that can be installed on a client device (10) such as a computer, tablet or smartphone, to be used in the diagnosis of cancer diseases in the field of medical pathology for diagnosis via microscopic image, characterized by comprising of the following; an interface (11) on the client device (10) used to query the pathology slide images to be queried (S) by the user, archive database (21) containing pathology slide images, clinical data such as patients' age, gender, sample organ, glass staining method, and pathology result reports, a server (20) with a query module (22) that finds the pathology slide images closest to the pathology slide image to be queried (S) in the archive database (21) by artificial intelligence-based methods using the deep artificial neural network and sends the necessary information to the client device (10), communication channel (30) that provides the network connection between the client device (10) and the server (20).
2. An artificial intelligence supported archive query method used for diagnosis via microscopic image in the diagnosis of cancer diseases in the field of medical pathology, characterized by comprising of the following process steps; a) Sending the pathology slide image to be queried (S) by a user via the user interface (11) on the client device (10) to a server (20), b) Extracting the feature vectors using the deep neural network on the pathology slide image loaded to be queried (S) by the client device (10) by means of a query module (22) running on the server (20), c) Comparing the features obtained on the pathology slide image to be queried (S) with the vectors in the archive database (21) by the query module (22) and identifying the slides and patients closest to the pathology slide image to be queried (S), d) selecting the entire archive database (21) as a query set in the query module
(22) and transmitting the visual and textual data of the patients with the
slide, which is found to be similar to the pathology slide image to be queried (S) as a result of the query, to the client device (10) to be shown to the user. An artificial intelligence supported archive query method according to claim 2, characterized in that, it comprises the following process step of filtering the cluster to be queried in the archive database (21) according to the entered clinical information in the query module and transmitting the visual and textual data of the patients with the detected slide to the client device (10) in case of entering clinical information such as age, gender, organ of the patient being queried from which the sample was taken or the pathology slide image to be queried (S), method of glass staining etc.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/TR2022/050962 WO2024054167A1 (en) | 2022-09-08 | 2022-09-08 | Artificial intelligence supported archive inquiry system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/TR2022/050962 WO2024054167A1 (en) | 2022-09-08 | 2022-09-08 | Artificial intelligence supported archive inquiry system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024054167A1 true WO2024054167A1 (en) | 2024-03-14 |
Family
ID=90191655
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/TR2022/050962 WO2024054167A1 (en) | 2022-09-08 | 2022-09-08 | Artificial intelligence supported archive inquiry system and method |
Country Status (1)
| Country | Link |
|---|---|
| WO (1) | WO2024054167A1 (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008124138A1 (en) * | 2007-04-05 | 2008-10-16 | Aureon Laboratories, Inc. | Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition |
| WO2019157078A1 (en) * | 2018-02-06 | 2019-08-15 | The Regents Of The University Of Michigan | Systems and methods for analysis and remote interpretation of optical histologic images |
| WO2022094732A1 (en) * | 2020-11-24 | 2022-05-12 | Huron Technologies International Inc. | Systems and methods for generating encoded representations for multiple magnifications of image data |
-
2022
- 2022-09-08 WO PCT/TR2022/050962 patent/WO2024054167A1/en unknown
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008124138A1 (en) * | 2007-04-05 | 2008-10-16 | Aureon Laboratories, Inc. | Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition |
| WO2019157078A1 (en) * | 2018-02-06 | 2019-08-15 | The Regents Of The University Of Michigan | Systems and methods for analysis and remote interpretation of optical histologic images |
| WO2022094732A1 (en) * | 2020-11-24 | 2022-05-12 | Huron Technologies International Inc. | Systems and methods for generating encoded representations for multiple magnifications of image data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tschandl et al. | The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions | |
| US7929733B1 (en) | Biometric identification and analysis | |
| US20060159367A1 (en) | System and method for creating variable quality images of a slide | |
| US20060159325A1 (en) | System and method for review in studies including toxicity and risk assessment studies | |
| US20020106119A1 (en) | Collaborative diagnostic systems | |
| US11955227B2 (en) | Methods, systems and computer program products for retrospective data mining | |
| CN113793305A (en) | Pathological image classification and identification method and system integrating multiple information | |
| Romo et al. | Learning regions of interest from low level maps in virtual microscopy | |
| Mattie et al. | PathMaster: content-based cell image retrieval using automated feature extraction | |
| US10892042B2 (en) | Augmenting datasets using de-identified data and selected authorized records | |
| Bozkurt et al. | Skin strata delineation in reflectance confocal microscopy images using recurrent convolutional networks with attention | |
| Deserno et al. | Gaps in content-based image retrieval | |
| US11769582B2 (en) | Systems and methods of managing medical images | |
| CN117316392A (en) | Medical image information management system and method based on intelligent medical treatment | |
| WO2024054167A1 (en) | Artificial intelligence supported archive inquiry system and method | |
| US20230230709A1 (en) | Systems and methods for automatically managing image data | |
| CN117716397A (en) | System and method for processing images for image matching | |
| Van Molle et al. | Dermatologist versus artificial intelligence confidence in dermoscopy diagnosis: Complementary information that may affect decision‐making | |
| Bodzas et al. | A high-resolution large-scale dataset of pathological and normal white blood cells | |
| Dubey et al. | Design and development methodology for healthcare monitoring system based on IoT and machine learning approach | |
| Zewde et al. | Artificial Intelligence-Based Breast and Cervical Cancer Diagnosis and Management System | |
| CN117859123A (en) | Full slide image search | |
| Miao et al. | CRAM: Conv-Resnet34-Adatriplet module forContent based Medical Image retrieval | |
| CN116013552A (en) | Remote consultation method and system based on blockchain | |
| CN118072085A (en) | Big data screening method based on cervical cancer liquid-based cytological pathology image |
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: 22958267 Country of ref document: EP Kind code of ref document: A1 |