Invented by Hanbo Chen, Hao Chen, Youbing YIN, Shanhui Sun, Qi Song, Keya Medical Technology Co Ltd

The market for System and Method for Medical Image Management has witnessed significant growth in recent years, driven by the increasing adoption of digital healthcare solutions and the growing need for efficient management of medical images. Medical imaging plays a crucial role in the diagnosis, treatment, and monitoring of various medical conditions. With the advancements in technology, medical imaging has evolved from traditional film-based systems to digital imaging modalities such as X-ray, ultrasound, MRI, and CT scans. These digital images are easier to store, share, and analyze, leading to improved patient care and outcomes. However, the increasing volume of medical images generated by healthcare facilities has created a need for robust image management systems. Traditional methods of storing and managing medical images, such as physical film archives or local storage systems, are becoming obsolete due to their limitations in terms of accessibility, scalability, and security. System and Method for Medical Image Management provide healthcare providers with a comprehensive solution to store, retrieve, and share medical images securely and efficiently. These systems typically include features such as image acquisition, storage, retrieval, viewing, and sharing capabilities. They also incorporate advanced technologies like cloud computing, artificial intelligence, and machine learning to enhance image analysis and interpretation. One of the key drivers of the market for System and Method for Medical Image Management is the increasing adoption of electronic health records (EHRs) and picture archiving and communication systems (PACS) by healthcare facilities. These systems enable seamless integration of medical images with patient records, allowing healthcare professionals to access and analyze images alongside other clinical data. This integration improves workflow efficiency, reduces errors, and enhances patient care. Moreover, the growing demand for telemedicine and remote healthcare services has further fueled the market for medical image management systems. With the ability to securely transmit medical images over the internet, healthcare providers can collaborate with specialists in real-time, regardless of geographical barriers. This has proven particularly beneficial in rural or underserved areas where access to specialized medical expertise is limited. Furthermore, the increasing focus on precision medicine and personalized healthcare has created a need for advanced image analysis and interpretation tools. System and Method for Medical Image Management leverage artificial intelligence and machine learning algorithms to automate image analysis, detect abnormalities, and assist radiologists in making accurate diagnoses. These technologies not only save time but also improve diagnostic accuracy, leading to better patient outcomes. In terms of market segmentation, the market for System and Method for Medical Image Management can be categorized based on the type of system (cloud-based or on-premise), end-user (hospitals, diagnostic centers, research institutions, etc.), and region (North America, Europe, Asia Pacific, Latin America, and Middle East & Africa). North America currently dominates the market, driven by the presence of advanced healthcare infrastructure, favorable government initiatives, and a high adoption rate of digital healthcare solutions. However, the Asia Pacific region is expected to witness significant growth in the coming years, owing to the increasing healthcare expenditure, rising awareness about the benefits of digital healthcare, and the growing demand for telemedicine services. In conclusion, the market for System and Method for Medical Image Management is experiencing rapid growth due to the increasing adoption of digital healthcare solutions, the need for efficient management of medical images, and the advancements in technology. These systems provide healthcare providers with secure, scalable, and efficient solutions to store, retrieve, and analyze medical images, ultimately improving patient care and outcomes.

The Keya Medical Technology Co Ltd invention works as follows

The present disclosure relates to a device and method for managing medical information. The method can include receiving medical images of multiple patient cases captured by at least one imaging device. A processor may also determine diagnosis results from the medical image data by using artificial intelligence. The method can also include the processor determining priority scores for medical image files based on their respective diagnosis results and sorting the medical images by the processor based upon the priority score. The method can also include displaying a queue of medical image data according to their sorted order on a display.

Background for System and Method for Medical Image Management

Medical images are essential for clinical diagnosis. Radiologists must examine and label the majority of images after they are acquired. The radiologist will then provide a pathological diagnosis to the physicians. Most hospitals and Internet-based remote diagnostic platforms use queueing systems in order to manage images due to the large volume of images to be analyzed. The order of the images in the queue can be used by radiologists to select which medial images they want to process.

In general a traditional system can sort patient cases based on the time taken to acquire their medical images. This sorting allows patients to be seen on a first-come, first-served basis. A system could also take into account the time taken to collect the data, the urgency of the disease, and the workloads of the doctors in order to schedule and distribute medical data. As an example, cerebral hemorrhage or cerebral thrombosis is a common acute disease. Both cerebral blood diseases have different treatment methods, even though they are both cerebral blood diseases. The risk of these diseases can be reduced significantly if the doctor is able to make the correct diagnosis and treat the patient in the early hours after the illness. Rehabilitation can also be improved. The queuing system can assign such images a higher priority and place them on top of the line. It may also label patient cases as emergencies. When an urgent emergency case is placed in the queue, radiologists can rearrange the non-emergency work and deal with the case immediately.

It should be noted that the priority of medical images is typically determined by the priority of disease conditions in the patient cases. A physician is usually the one to decide the priority of a condition (e.g. based on symptoms). This type of decision is susceptible to errors in diagnosis (e.g. the physician could misdiagnose a patient’s illness). In this way, the priority of some cases can be underrated, and optimal treatment times may be missed. In order to make an informed decision, doctors often need to consult the examination results of radiologists. Sorting medical images in certain cases before examination results become available may not be useful. The radiologists who are tasked with sorting the medical images could be overloaded, leading to human error. This can further reduce the accuracy and efficiency.

In one aspect, this disclosure relates to a computerized method for managing medical information. The method can include receiving medical images of multiple patient cases captured by at least one imaging device. A processor may also determine diagnosis results from the medical image data by using artificial intelligence. The method can also include the processor determining priority scores for medical image files based on their respective diagnosis results and sorting the medical images by the processor based upon the priority score. The method can also include presenting the queue of medical image data in a display according the the sorted order.

The present disclosure is also directed at a medical imaging management system that can be communicatively linked with at least one device for image acquisition. The system can include a communication device configured to receive image data from a plurality patient cases captured by the image acquisition device. The system can also include a processor configured to determine diagnosis results for the medical images data using artificial intelligence, determine priority scores based on each diagnosis result, and sort medical image files based upon the priority score. The system can also include a display that is configured to show a queue of medical image data in the order they were sorted.

In a third aspect, the disclosure is directed at a non-transitory medium with instructions. When executed by a computer, the instructions perform a method of managing medical data. The method can include receiving medical images of a plurality patient cases captured by at least one device for image acquisition. The method can also include determining the diagnosis results from the medical image data by using artificial intelligence. The method can also include determining the priority scores of the medical images data based upon the diagnosis results and sorting them based on that priority score. The method can also include displaying a queue of medical image data in a display based on the sorted order.

It is understood that both the general description above and the detailed description below are only illustrative and informative, and do not restrict the invention as claimed.

Now, we will refer in detail to the exemplary examples that are shown in the drawings.” The same reference numbers are used to refer to similar or identical parts wherever possible.

Medical image data” is used throughout this disclosure to refer to the medical image data, but it does not limit itself to that. It can also include other related information such as attribute information (such as acquisition time, upload time and data source) of the medial images. “Medical image data” is used throughout the disclosure to refer to the data that includes the images themselves, as well as other data related to the images. For example, attribute data (such as upload time, acquisition time, data source, etc.) and subject attributes (such age, height and weight of the subject, gender and medical history, etc.). The term “sort” is used throughout this disclosure. It includes but is not limited to prioritizing the medical image data, such as arranging the sequence of the medical image data based on at least their priority score. The term’sort,’ used throughout this disclosure includes but is not limited to prioritizing medical image information such as by arranging the sequence based at least on the priority score. The medical image data that have a higher priority can be ranked higher on the sequence (queue).

Embodiments in the present disclosure provide an image management method for medical images.” The method can be implemented using a computer. The method can be used to analyze and process medical image information after it has been acquired. This will give a score based on the priority of the image. This analysis can be used to make a preliminary judgement by using artificial intelligence modules. Final sorting is based on priority scores. Additional factors can be taken into account by the method. These factors include, but aren’t limited to, the physician?s judgment, attribute information from the medical images, including the time of data acquisition, and the artificial intelligence module?s decision. In non-emergency situations, the method may also take into account the doctor’s workload in the scheduling process.

FIG. The present disclosure is illustrated in FIG. 1, which shows a particular embodiment of a method for managing medical images 10. The method 10 can include the following steps: acquiring medical images data (Steps 101 and 102); processing the image data by a processor to obtain at the very least a score for the image data in terms of priority (Steps 103 and 104); and sorting the image data by the processor based at the very least on the score.

The processor can be a device that includes a number of general processing units, including a microprocessor or central processing unit, graphics processing unit, and so on. The processor can be a microprocessor that uses a complex instruction-set computing (CISC), a microprocessor with a reduced instruction-set computing (RISC), a microprocessor running a very long instructions word (VLIW), a microprocessor that runs other instruction sets or a microprocessor which runs a mixture of instruction sets. The processor can also be one or several dedicated processing devices, such as Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), Digital Signal Processors (DSPs), System-on-Chip (SoCs), etc.

The processor can be connected to the storage via a communication link and be configured to execute the computer-executable instruction stored on it. Each of the above steps may be stored in the storage as computer-executable commands. The storage can include a read-only memory (ROM), flash memory, random memory access (RAM), static memory, etc. The storage can store computer-executable instruction of any of Steps 101 to 104 and data generated or used while executing the computer-executable instruction, such as priority score, queue for medical image data and processing result.

The respective priority score can be used to evaluate the level of urgency of a patient’s case (e.g. the priority of medical image data for the patient in a doctor’s processing queue). A processor can automatically process medical image data using method 10. The method 10 can sort the image data into a queue and then present it to the radiologist in real-time for processing. Method 10 can be used to process newly acquired image data. Method 10 can, for example, sort all the medical image data in real-time and then present it to the radiologist.

FIG. The block diagram in Figure 2 is a medical image-management system 100. System 100 can be implemented on a computer or server. In some embodiments system 100 can have multiple modules on a single device such as a chip integrated with an integrated circuit, an ASIC or FPGA, or it may be implemented as separate devices. In some embodiments one or more of the components in system 100 can be in a cloud or alternatively located at a single place (such as an imaging center), or in distributed locations. The components of the system 100 can be integrated into a single device or located at multiple locations, but still communicate through a network.

As shown in FIG. The medical image management system includes an image storage unit 130, which uploads medical image data to the image acquisition unit 110. The medical image management system includes a storage scheduling unit 130 that is connected to the image acquisition unit and the data processing module 120. It can be used for scheduling, scheduling data, sorting data (based on analysis results of the data processing module 120) and recording results. The medical image management system 100 includes a data processor 120 that is configured to receive and process medical image data sent by the data scheduling unit 130. It then analyzes the medical image data and sends the results back to the data scheduling unit 130 to be sorted and scheduled. The medical image management system includes a display 140 that is communicatively coupled with the data storage unit 130. This display unit displays various browsing interfaces and display contents to a user (e.g. a radiologist or administrator), according to the sort order and scheduling. In some embodiments the display contents may include a presentation of medical image data in a queue. Note that the image acquisition module 110 is not always an internal component of system 100. In some embodiments image acquisition unit may be an external device that is communicatively linked with system 100. The system 100 downloads medical images from the scheduling unit 130 and obtains them.

In some embodiments, data storage scheduling unit is responsible for receiving and transmitting medical image data, storing it, sorting it, and scheduling. The image acquisition unit 110 can upload medical image data directly to the data scheduling unit 130, whether it is a remote or local imaging system. The image acquisition unit 110 can use a variety of imaging modalities, including but not limited to magnetic resonance imaging images (MRI), 3D MRIs, 2D fluidized MRIs, 4D volume MRIs, computed-tomography images (CT), cone-beam CTs, positron-emission tomography images (PET), functional MRI images such as fMRIs, DCEMRIs, diffusion MRIs, X-rays, fluorescences, ultrasound Image acquisition unit 110 can be an MRI device, a CT device, a PET device, an ultrasonic device, a fluorescent device, a SPECT device or any other medical imaging device used to acquire one or more images of a person. The image acquisition unit 110 can also be a multimodality imaging system that uses two or more imaging modalities. The images acquired may be stored as medical image data or imaging data in a database. The database may be connected via a communication link to the data storage unit 130 to retrieve medical image data. The acquired images can be stored on the storage system of the medical image management 100 to be retrieved by the data storage unit 130.

The data storage scheduling unit may acquire medical image data in addition to that from the image acquisition unit. It may, for example, obtain from an electronic medical record or hospital information system the type of medical examination prescribed, age, weight, height, gender and medical history of the patient.

A B/S structure-based service can be designed to receive image data. The user simply needs to log in using their user name and password and then they can upload data. The labeling of each uploaded data includes, but is not restricted to, the uploading time, the data source and the acquisition time. The data is then placed in a queue and prepared for sequential feeding by the data storage unit 130 to the data processing unit to perform analysis and calculations to obtain an analytical result.

Accordingly to the analysis results fed back by data processing unit 120 the data storage scheduling units 130 performs the corresponding data transfer and scheduling. If the result of feedback is that image quality is not satisfactory, then the data storage unit 130 will forward the feedback result to the image acquisition unit 110. The data storage scheduling 130 will receive an automatic diagnosis from the data processing 120 for data that are satisfactory. If there is an issue with the automatic diagnostic result, according to the sorted-order and scheduling rules, the data storage planning unit 130 sends the data, which may include the autodiagnosis result, to a first physician and waits to receive the diagnosis from the first physician. The automatic diagnosis can be compared to the result of the first physician’s diagnosis after receiving the result. The data storage scheduling unit sends the results to other doctors to perform a comprehensive diagnostic to reduce the likelihood of misdiagnosis if the comparison result is inconclusive. The data processing unit can determine whether the result of the diagnosis is true by using a comprehensive module 124. The comprehensive analysis unit 124 instructs data storage scheduling module 130 to perform corresponding data transfer according to the determination results, for example send the data to the first physician and receive the diagnosis result. The comprehensive analysis module can also compare the automatic diagnostic result with the result of the doctor’s diagnosis and instruct the data-storage scheduling unit 130 on how to proceed based on the comparison result. For example, it could send the data (which may include the automatic diagnosis) to the first physician and receive a diagnosis from him.

The data storage scheduling unit returns the final diagnostic result to the physician who prescribed the imaging examination and/or to the patient. The data storage scheduling device 130 may, in some embodiments record the incorrect diagnosis results as a reference to future developments.

Click here to view the patent on Google Patents.