Computer-implemented method, medical engineering system and computer program product for automatic medical image evaluation and / or image assessment, and use thereof

Abstract

The invention relates to a multi-stage computer-implemented method, medical engineering system and computer program product for automatic medical image evaluation and / or image assessment. The multi-stage method, system and computer program product implement the following stages: a first stage (103, 104) for automatically evaluating medical data (ID, SD), in particular medical image data (ID, SD), wherein a probability measure and / or a probability distribution (hij) of the absence of findings for the medical data (ID, SD) are / is determined; and a second stage (106) for automatically determining deviations of the probability measure and / or the probability distribution (hij) of the absence of findings from a probability measure threshold value (hSij) and / or from a probability measure criterion (hCij) of the absence of findings; and optionally a third stage (107) for automatically creating medical findings.

Description

[0001]202324035 1 Description Computer-implemented method, medical-technical system and computer program product for automatic medical image evaluation and / or image diagnosis and the use thereof. The invention relates to a computer-implemented method, a medical-technical system and a computer program product for automatic medical image evaluation and / or image diagnosis and the use thereof, as well as a computer-implemented training method. The invention is particularly concerned with supporting physicians in the creation and / or evaluation and / or presentation of medical image data and / or medical findings based on acquired and / or stored imaging data, in particular with regard to the automatic or automated evaluation and diagnosis of radiological and / or medical-technical and / or general image content in the context of the creation and / or evaluation and / or presentation of medicalFindings. Physicians in many disciplines are responsible for conducting diagnostic examinations over a patient's treatment period. Examples of this include imaging examinations and the observation of various patient information, such as symptoms, blood values, tumor markers, and measured values ​​associated with the patient's physical condition (e.g., characterization of organs, tissue condition, and potentially pathological tissue changes, etc.). Previous automatic or automated creation and / or evaluation and / or presentation and / or reporting of radiological and / or medical-technical image content 202324035 2 and / or general image content relating to medical findings - for example, in radiology and other medical disciplines - can be improved, in particular, using computer-implemented, trainable functions such as neural networks, in particular using so-calledConvolutional Neural Networks (CNNs for short) are used, which are generally known from the general technical knowledge of computer-implemented methods, see, for example: https: / / en.wikipedia.org / wiki / Convolutional_neural_network. The use of CNNs in the context of automatic or automated creation and / or evaluation and / or presentation and / or diagnosis of radiological and / or medical-technical image data and / or medical image content and / or general data and / or image content relating to medical findings is generally known from the following earlier patent applications or patents of the applicant of this patent application: The document US 10,595,727 B2 describes a machine learning-based segmentation for cardiological medical imaging. For cardiac segmentation in magnetic resonance or other medical imaging methods, deep learning trains a neural network. The neural network,such as U-net, contains at least one long-short-term memory (LSTM), such as a convolutional LSTM. The LSTM integrates the temporal properties with the spatial ones to improve the accuracy of the segmentation by the machine-learned network. The document US 10,7796,917 B2 describes a method and system for compensating motion artifacts using machine learning. A method is used to train a convolutional neural network of a compensation unit. The 202324035 3 method comprises: providing a machine learning device, wherein the machine learning device is configured to train the convolutional neural network; providing a starting compensation unit, including an untrained convolutional neural network, on or at the machine learning device; Providing a training image dataset comprising a plurality of medical training input images and at least oneTraining output image, wherein a reference object is shown substantially without motion artifacts in the at least one training output image, and the respective reference object is included in the plurality of medical training input images with different motion artifacts; and training the convolutional neural network of the compensation unit in accordance with a machine learning principle using the training image dataset. A compensation unit, a machine learning device, and a control device for controlling a medical imaging system are also disclosed. Document US 10,452,899 B2 describes deep representation learning for the fine-grained recognition of body parts. This document discloses a method and a device for deep learning-based fine-grained body part recognition in medical imaging data. A paired convolutional neural network(P-CNN) for the slice order is trained on the basis of unannotated (unlabeled) medical image volumes. A convolutional neural network (CNN) for the fine-grained recognition of body parts is trained by fine-tuning the learned weights of the trained P-CNN for the slice order. The CNN for the fine-grained body part recognition is trained to calculate a normalized height value for a transverse input slice of a medical imaging volume, which indicates a normalized height of the transverse input slice in the human body. 202324035 4 The general technical background of the use of CNNs in the context of automatic or automated creation and / or evaluation and / or presentation and / or reporting of radiological and / or medical image data and / or medical image content and / or general data and / or image content relating to medical findings isIt should be noted that computer-implemented neural networks – particularly CNNs – as the core technology of computer vision over the last 10 years of computer-implemented data processing or information processing, are modeled on the visual cortex of the human brain. Visual content is translated into higher-dimensional feature maps, in which, for example, spatial relationships of characteristic image content are encoded. Objects can be identified and classified automatically based on this trained content. A fundamental problem with this approach in radiology, medical imaging examinations, and medicine in general is the large number of potentially automated or automatically found imaging and / or medical indications. For example, a chest X-ray image, as a relatively simple case in medical imaging, can only provide imaging and / or medical information.Indications for around 150 different known diseases. For each possible disease, a trainable function such as a neural network, for example a CNN, must be trained globally, which requires corresponding training data for each disease – especially training image data. Statistically necessary data sets of hundreds to thousands of images are not uncommon. In multiplication, this means hundreds of thousands to millions of annotated image and health data in high quality as necessary training data for the 202324035 5 aforementioned trainable functions, especially neural networks such as CNNs. The necessary data and training effort is currently a major reason and technical obstacle to the current and foreseeable failure of differential diagnostics based on imaging data, particularly in radiology – or in other medical disciplines.cannot be achieved with CNN-based products. In addition, even in individual applications, the inherent "bias" of the data is a significant problem. The training and validation data would have to contain, among other things, an equal distribution of gender, ethnicity, and age in order to obtain an appropriate representation of the respective disease to be classified in its real-life manifestation in the population. This is virtually impossible in practice. Any compromise leads to significantly worse model performance in reality. It should also be noted that the trained classifications are often linked to a specific imaging device and its specific technical parameters and calibrations, and may, under certain circumstances, deliver different results on a different imaging device, for example, function significantly worse or at least lack sufficient comparability or reproducibility ofResults were obtained. Current neural networks such as CNNs and derivatives are therefore generally only able to determine specific medical indications in an automated or automatic manner in special cases. Radiographs and CT images of the lungs have so far been the primary means of doing this. Comprehensive automated or automatic differential diagnostics generally do not occur. The technical teaching and the technical features as well as combinations or sub-combinations of technical features 202324035 6 of the aforementioned earlier patent application or patents US 10,595,727 B2, US 10,7796,917 B2, US 10,452,899 B2 of the patent applicant as well as the aforementioned technical features of the general technical background and / or technical expertise are hereby incorporated into the disclosure of the present invention as possible developments and / or possible further or supplementary embodiments of the present invention.In particular, those individual technical aspects of the aforementioned prior patent application of the patent applicant are incorporated into the disclosure of the present invention which a person skilled in the art would consider helpful or supportive for further development or for the implementation of the present invention. It is an object of the present invention to provide an improved computer-implemented method, an improved medical technology system and an improved computer program product for medical image evaluation and / or image diagnosis and the use thereof, as well as an improved training method. This object is achieved according to the invention by the subject matter of the independent patent claims. Advantageous embodiments and expedient further developments are the subject matter of the dependent claims. Aspects of the present invention are described below. The inventive aspects and / orFeatures of the described aspects can, within the scope of each aspect and / or within the scope of each combination or sub-combination of features of the present invention, be designed or further developed in particular as - a method, in particular as a computer-implemented method, comprising one or more of the steps described in this 202324035 7 document in any combination or sub-combination of features and / or aspects of the invention as described in this document, and / or - as a medical-technical data processing unit or medical-technical system, in particular designed to carry out a method according to one of the aspects described in this document or according to a combination or sub-combination of features and / or a method according to one of the aspects described in this document, and / or - as a computer program product or computer program system consisting of severalComputer program product modules, each with individual program steps, each individually or jointly designed to carry out corresponding steps of a method according to one of the aspects described in this document and / or designed to interact with a medical data processing unit or medical system according to one of the aspects described in this document. Within the scope of the present invention, a multi-stage method or a multi-stage computer program product and a multi-stage medical data processing unit or medical system for automatic medical image evaluation and / or image diagnosis are provided: In a first stage, a (particularly location-dependent)or spatial) probability measure and / or a (particularly location-dependent or spatial) 202324035 8 probability distribution is determined. Stored medical data may contain historical image data from previous imaging examinations (i.e., from preliminary imaging examinations) and may additionally contain personal data of the patient in question and / or historical medical data from non-imaging examinations (i.e., from further preliminary examinations) and / or historical findings data (i.e., findings data based on preliminary examinations) of the patient in question and / or of reference patients and / or data on the complete medical history of the patient in question and / or of reference patients. The said location-dependent probability measure and / or the said spatial probability distribution indicates how likely a pixel or image region corresponds to an expectation of freedom from findings (in otherwords of "normal health") for the patient in question or the examination object. The acquired and / or stored medical image data contain at least one-, two-, or three-dimensional image content. In addition, other medical and / or personal and / or historical data such as patient age and gender, previous medical findings, etc. may also be used if necessary. In a second stage, the determined (particularly location-dependent or spatial) probability distribution is examined for significant deviations from an expectation of freedom from findings (in other words, from "normal health"). In individual (particularly segmented) data regions - especially image regions - a local procedure is applied based on the information from the first stage to identify, classify, or quantify a local potential finding. In other words, potentially finding-related local data regions -in particular image regions - are determined and evaluated. These local procedures can be different and, for example, optimized for individual organ systems, previous findings, etc. 202324035 9 In a third, optional stage, in addition to the results of the first two stages, i.e., in addition to the determined data of the (particularly location-dependent or spatial) probability distribution of an expectation of freedom from findings and the determined data of the determination or localization and evaluation of potentially finding-related data regions - in particular image regions - further stored or determined medical and / or personal data and information such as size, malignancy, organ affiliation, etc. of a determined medical finding, patient age and sex, previous findings, etc. can also be used, on the basis of which, in conjunction with the aforementioned results of the first two stages, automatically and computer-implementeda medical report can be created and made available to a user such as, for example, a treating physician, a radiologist, or a nuclear medicine specialist. According to one aspect of the present invention, a computer-implemented method for automatic medical image evaluation and / or image diagnosis is therefore provided, which can be further developed with features or a subcombination of features of any further aspect of the present invention, wherein the computer-implemented method is designed as a multi-stage method and comprises the following stages: - a first stage for the automatic computer-implemented evaluation of acquired and / or stored medical data, in particular medical image data, wherein a probability measure and / or a probability distribution of the absence of findings for the acquired medical data and / or for the storedmedical data is determined; and 202324035 10 - a second stage for the automatic computer-implemented determination of deviations of the probability measure and / or the probability distribution of the absence of findings from at least one probability measure threshold and / or from at least one probability measure criterion of the absence of findings of the recorded and / or stored medical data; and optionally - a third stage for the automatic computer-implemented creation of medical findings based on the recorded and / or stored medical data and the determined deviations of the determined probability measure and / or the determined probability distribution of the absence of findings from at least one probability measure threshold and / or from at least one probability measure criterion of the absence of findings, and for the automatic computer-implemented provision of the createdmedical findings for a user by means of a display unit. According to one aspect of the present invention, a computer-implemented method for automatic medical image evaluation and / or image diagnosis is provided, in particular according to the aforementioned aspect or according to features of the aforementioned aspect of the invention, wherein the computer-implemented method comprises the following steps: - automatically reading in acquired medical image data and / or stored medical data representing at least one one-dimensional, two-dimensional, or three-dimensional medical image content; - automatically applying a first function, trained using predominantly finding-free and / or exclusively finding-free training data and computer-implemented in a 202324035 11 neural network computing unit, to the acquired medical image data and / or to the storedmedical data; - automatically determining a location-dependent probability measure and / or a spatial probability distribution of the absence of findings for the acquired medical image data and / or for the stored medical data by means of the trained computer-implemented function; and - automatically displaying a spatial representation of the location-dependent probability measure and / or the spatial probability distribution by means of a display unit; and / or - automatically applying a second function trained using training data with findings and computer-implemented in a neural network computing unit to such acquired medical image data and / or to such stored medical data whose determined probability measure falls below or exceeds a predefined and / or learned probability measure threshold and / or a function associated with the medicalImage content correlated probability measure criterion is met, for the automatic determination of findings data; and - automatically determining and displaying findings data of the determined findings data for a user by means of a display unit. According to one aspect of the present invention, a computer-implemented method for automatic medical image evaluation and / or image diagnosis is provided, in particular according to one of the aforementioned aspects of the invention 202324035 12 or according to features of an aforementioned aspect of the invention, wherein the computer-implemented method comprises the following steps: - automatically reading in acquired medical image data and / or stored medical data representing at least one one-dimensional, two-dimensional, or three-dimensional medical image content; - automatically segmenting and / or encoding the image data into a plurality of image segments; -Automatic application of a first function, trained using predominantly finding-free and / or exclusively finding-free training data and computer-implemented in a neural network processing unit, to the image segments; - Automatic determination of a probability measure of the absence of findings for each of the image segments using the trained computer-implemented function; and - Automatic display of a spatial representation of the probability measure using a display unit; and / or - Automatic application of a second function, trained using finding-related training data and computer-implemented in a neural network processing unit, to image segments with a probability measure that falls below or exceeds a predefined and / or learned probability measure threshold and / or fulfills a probability measure criterion correlated with the medical image content, forAutomatic determination of diagnostic data; and - Automatic determination and presentation of diagnostic data of the determined diagnostic data for a user by means of a presentation unit. 202324035 13 A method according to each of the aforementioned aspects of the invention is designed as a computer-implemented method, and it can be implemented in conjunction with each individual feature from each further aspect of the invention, in conjunction with each further aspect of the invention, or in conjunction with any combination or subcombination of further features and / or aspects of the invention as described in this document. Within the scope of each of the aforementioned aspects of the present invention, as well as within the scope of each further aspect of the present invention, a computer-implemented method, in particular a computer-implemented method for automatic medical image evaluation and / or image diagnosis, can be implemented.or a computer-implemented training method for automatically training computer-implemented trainable functions, which comprise or additionally comprise the following steps: - automatically training a first computer-implemented function using predominantly finding-free and / or exclusively finding-free image training data to learn parameters for automatically characterizing a probability measure of finding-free image data and / or at least one probability measure threshold of finding-free image data and / or at least one probability measure criterion of finding-free image data correlated with medical image content, and - automatically training a second computer-implemented function using finding-related training data to learn parameters for automatically characterizing finding data. It can be used within the framework of any of the aforementionedAspects of the present invention and within the scope of any further 202324035 14 aspect of the present invention, a computer-implemented method, in particular a computer-implemented method for automatic medical image evaluation and / or image diagnosis or a computer-implemented training method for automatically training computer-implemented trainable functions, may comprise or additionally comprise individual, several or all of the following features and / or steps: - Automatic application of a second function, trained using training data with findings and computer-implemented in a neural network computing unit, to image segments with a probability measure which falls below or exceeds a predefined and / or learned probability measure threshold and / or fulfills a probability measure criterion correlated with the medical image content, taking into accountand / or in correlation with stored medical data, for the automatic determination of diagnosis data; and - automatic display of acquired medical image data and / or stored medical data as well as automatically determined diagnosis data, in particular location-dependent diagnosis data, for a user by means of a display unit. Within the scope of each of the aforementioned aspects of the present invention, as well as within the scope of each further aspect of the present invention, a computer-implemented method, in particular a computer-implemented method for automatic medical image evaluation and / or image diagnosis or a computer-implemented training method for the automatic training of computer-implemented trainable functions, may comprise or additionally comprise individual, several or all of the following features and / or steps: 202324035 15 - automatic training of a secondcomputer-implemented function using training data with findings and stored medical data to learn parameters for the automatic characterization of findings data and for learning a language model for the linguistic description of automatically determined and / or stored findings data; - automatically applying the second function, trained using training data with findings and computer-implemented in a neural network processing unit, for the automatic determination of findings data and for the automatic creation of a linguistic description based on the learned language model to such acquired medical image data and / or to such stored medical data and / or to such image segments with a probability measure which falls below or exceeds a predefined and / or learned probability measure threshold and / or a probability measure associated with the medical image contentcorrelated probability measure criterion is met by including and / or correlating with stored medical data; and - automatically displaying the determined findings data as well as the linguistic description of the determined findings data automatically created on the basis of the learned language model for a user by means of a display unit. Within the scope of each of the aforementioned aspects of the present invention as well as within the scope of each further aspect of the present invention, a computer-implemented method, in particular a computer-implemented method for automatic medical image evaluation and / or image diagnosis or a computer-implemented 202324035 16 training method for automatically training computer-implemented trainable functions, may comprise or additionally comprise individual, several or all of the following features and / or steps: - automatic segmentation and / orEncoding the image data into a plurality of image segments using a neural transformer network architecture (e.g., a vision transformer architecture) and / or a generative neural network architecture (e.g., a generative adversarial network architecture); - automatically applying a first neural network function, trained using predominantly finding-free and / or exclusively finding-free training data and computer-implemented in a neural network processing unit, to the image segments; and - automatically applying a second neural network function, trained using finding-related training data and computer-implemented in a neural network processing unit, to image segments with a probability measure that falls below or exceeds a predefined and / or learned probability measure threshold and / or a probability measure that correlates with the medical image content.lated probability measure criterion is met, for the automatic determination of diagnostic data. Image segmentation using a Vision Transformer (ViT) architecture is basically known from the state of the art and essentially follows the same principles as other image segmentation methods, but uses a transformer-based approach. The basic process of computer-implemented image segmentation with a Vision Transformer architecture is divided into an input preprocessing step, a transformation step, a segmentation step, a training step, and an inference step. In the input preprocessing step, an input image is divided into so-called patches. Each patch can be generated as a vector and then used as input for the actual transformer. Position information of the patches relative to each other or about the position in the input image is usually obtained using position embeddings.added. In the transformation step, the patches are encoded using a transformer, with the transformer architecture consisting of so-called attention layers that enable the model to capture both local and global context information. In the segmentation step, a decoder processes the output of the transformer-encoder to generate, for example, pixel-wise, region-wise, or segment-wise predictions. It can consist of upsampling layers to restore spatial resolution and generate segmentation masks. In a training step, the model can be trained, in particular, with annotated (labeled) data, in which each pixel, region, or segment in an image is assigned a corresponding class or segmentation label. In the inference step, the trained model is applied to new, previously unprocessed images to generate segmentation masks. These masksrepresent the predicted class labels for each pixel, region, or segment in the image. Convolutional Neural Networks (CNNs) are generally known from the state of the art and represent a special type of computer-implemented, trainable neural network that is particularly well-suited for image processing. CNNs use special layers, so-called convolutional layers, to extract features from the input data. The basic sequential elements by which a computer-implemented convolutional neural network typically functions are: one or more convolutional layers, a pooling layer, one or more fully connected layers, one or more flatten layers, and an output layer. A convolutional layer of a CNN is essentially a filter that is passed over input data, calculating the dot product between the filter values ​​and the input data. ThisThe process is repeated for different sections of the input data, creating so-called feature maps. One or more convolutional layers are usually followed by a pooling layer. This pooling serves to reduce the dimensions of the feature maps while still preserving the relevant information. The convolutional and pooling layers can be followed by fully connected layers, which convert the previously extracted information or features into a form suitable for classification or regression. Such fully connected layers learn weights for the various features. One or more flatten layers can be used before the fully connected layers to convert multidimensional feature maps into lower-dimensional representations such as vectors, which then serve as input for the fully connected layers. Each CNN ends with an output layer, which, depending on the task (classification, regression, etc.), can be used.has a corresponding number of neurons. According to a further aspect of the present invention, a computer-implemented training method for automatically training computer-implemented trainable functions using medical image data is provided, wherein the computer-implemented training method comprises the following steps: - automatically training a first computer-implemented function using predominantly free of findings and / or exclusively free of findings image training data for learning parameters for automatically characterizing a probability measure of the freedom from findings of image data and / or of at least one probability measure threshold of the freedom from findings of image data and / or of at least one probability measure criterion of the freedom from findings of image data correlated with medical image content, and - automatically training a second computer-im-implemented function by means of training data with findings for learning organ-specific and / or tissue structure-specific parameters for the automatic characterization of disease-specific findings data. Within the scope of each of the aforementioned aspects of the present invention as well as within the scope of each further aspect of the present invention, a computer-implemented method, in particular a computer-implemented method for automatic medical image evaluation and / or image diagnosis or a computer-implemented training method for automatically training computer-implemented trainable functions, may comprise or additionally comprise individual, several or all of the following features and / or the following step or steps: - automatic training of a second computer-implemented function by means of training data with findings and by means of stored medical data for learningorgan-specific and / or tissue structure-specific parameters for the automatic characterization of disease-specific findings data and for learning a language model for the linguistic description of automatically determined and / or stored findings data. 202324035 20 According to a further aspect of the present invention, a medical data processing unit or medical system is provided, in particular designed to carry out a computer-implemented method according to one of the aforementioned aspects of the present invention and within the scope of any further aspect of the present invention, and such a medical data processing unit or medical system can be used in conjunction with each individual feature from any further aspect of the invention, in conjunction with any further aspect of the invention or in conjunction with any combination or subcombination offurther features and / or aspects of the invention as described in this document, wherein the medical-technical data processing unit or the medical-technical system comprises at least the following units which are in data communication with one another: - at least one image acquisition unit designed for the automatic acquisition of medical image data; - at least one storage unit designed for the storage of medical data; - at least one image data processing unit designed for the automatic processing of medical image data, in particular designed for the automatic segmentation and / or encoding of medical image data into a plurality of image segments; - at least one neural network computing unit designed for the automatic application of trainable and / or trained computer-implemented functions to medical image data and / or to stored medical data; - at least oneDisplay unit configured for the automatic display of medical image data and / or stored medical data and / or medical findings data; 202324035 21 wherein the neural network computing unit is configured to - automatically apply a first computer-implemented neural network function, trained using predominantly finding-free and / or exclusively finding-free training data, to the image segments; and - automatically apply a second computer-implemented neural network function, trained using finding-related training data, to image segments with a probability measure that falls below or exceeds a predefined and / or learned probability measure threshold and / or fulfills a probability measure criterion correlated with the medical image content, for the automatic determination of findings data. According to a further aspect of the present inventiona computer program product or computer program system consisting of several computer program product modules is provided, in particular designed to carry out a computer-implemented method according to one of the aforementioned aspects of the present invention and within the scope of any further aspect of the present invention, and in particular designed to interact with a medical data processing unit or medical system according to one of the aforementioned aspects of the present invention and within the scope of any further aspect of the present invention, and such a computer program product or computer program system consisting of several computer program product modules can be used in conjunction with each individual feature from each further aspect of the invention, in conjunction with each further aspect of the invention or in conjunction with any combination or subcombination of furtherFeatures and / or aspects of the invention as described in this document. The computer program product or computer program system consisting of several computer program product modules comprises instructions which, when the computer program product or the computer program product modules are executed by a data processing unit, cause this data processing unit to carry out program steps of a computer-implemented method according to one of the aforementioned aspects of the present invention or according to any further aspect of the present invention, in particular in cooperation with a medical-technical data processing unit or medical-technical system according to one of the aforementioned aspects of the present invention or according to any further aspect of the present invention. The aforementioned computer program product or computer program system comprises, in particular, instructions which, whenthe execution of the computer program product or the computer program product modules by a data processing unit, causing this data processing unit to execute the following computer-implemented program steps: - program steps of a first program stage for the automatic computer-implemented evaluation of acquired and / or stored medical data, in particular medical image data, wherein a probability measure and / or a probability distribution of the absence of findings is determined for the acquired medical data and / or for the stored medical data; and - program steps of a second program stage for the automatic computer-implemented determination of deviations of the probability measure and / or the probability distribution of the absence of findings from at least one probability measure threshold value and / or from at least one probability measure criterion of theFreedom from findings recorded 202324035 23 and / or stored medical data; and optionally - program steps of a third program stage for the automatic computer-implemented creation of medical findings based on the recorded and / or stored medical data and the determined deviations of the determined probability measure and / or the determined probability distribution of freedom from findings from at least one probability measure threshold value and / or from at least one probability measure criterion of freedom from findings, and for the automatic computer-implemented provision of the created medical findings to a user by means of a display unit. Within the scope of each of the aforementioned aspects of the present invention, as well as within the scope of each further aspect of the present invention, a computer program product or computer program system consisting of several computer-computer program product modules comprise or additionally comprise individual, several or all of the following features and / or the following program step or the following program steps: - Program step for the automatic computer-implemented reading of acquired medical image data and / or stored medical data, which represent at least one one-dimensional, two-dimensional or three-dimensional medical image content; - Program step for the automatic computer-implemented application of a first function, trained using predominantly finding-free and / or using exclusively finding-free training data and computer-implemented in a neural network computing unit, to the acquired medical image data and / or to the stored medical data; - Program step for the automatic computer-implemented determination of a probability measure of freedom from findings for the acquiredmedical image data and / or for the stored medical data by means of the trained computer-implemented function; and - program step for the automatic computer-implemented display (S105) of a spatial representation of the probability measure by means of a display unit; and / or - program step for the automatic computer-implemented application of a second function trained by means of training data with findings and computer-implemented in a neural network computing unit to such acquired medical image data and / or to such stored medical data whose determined probability measure falls below or exceeds a predefined and / or learned probability measure threshold and / or fulfills a probability measure criterion correlated with the medical image content, for the automatic determination of findings data; and - program step for the automaticcomputer-implemented presentation of the determined diagnostic data for a user by means of a display unit. Within the scope of each of the aforementioned aspects of the present invention, as well as within the scope of each further aspect of the present invention, a computer program product or computer program system consisting of several computer program product modules can comprise or additionally comprise individual, several, or all of the following features and / or the following program step or steps: 202324035 25 - program step for the automatic computer-implemented reading of acquired medical image data and / or stored medical data representing at least one one-dimensional, two-dimensional, or three-dimensional medical image content; - program step for the automatic computer-implemented segmentation and / or encoding of the image data into a plurality of image segments; -Program step for the automatic computer-implemented application of a first function, trained using predominantly finding-free and / or exclusively finding-free training data and computer-implemented in a neural network computing unit, to the image segments; - Program step for the automatic computer-implemented determination of a probability measure of finding-freeness for each of the image segments using the trained computer-implemented function; and - Program step for the automatic computer-implemented display of a spatial representation of the probability measure using a display unit; and / or - Program step for the automatic computer-implemented application of a second function, trained using finding-related training data and computer-implemented in a neural network computing unit, to image segments with a probability measure which has a predefinedand / or falls below or exceeds the learned probability measure threshold and / or fulfills a probability measure criterion correlated with the medical image content, for the automatic determination of findings data; and 202324035 26 - program step for the automatic computer-implemented presentation of the determined findings data for a user by means of a presentation unit. Within the scope of each of the aforementioned aspects of the present invention as well as within the scope of each further aspect of the present invention, a computer program product or computer program system consisting of several computer program product modules can comprise or additionally comprise individual, several or all of the following features and / or the following program step or the following program steps: - program step for the automatic computer-implemented training of a first computer-implemented function by means of predominantly findings-free and / orexclusively finding-free image training data for learning parameters for the automatic characterization of a probability measure of the absence of findings in image data and / or of at least one probability measure threshold of the absence of findings in image data and / or of at least one probability measure criterion of the absence of findings in image data correlated with medical image content, as well as - program step for the automatic computer-implemented training of a second computer-implemented function using finding-related training data for learning organ-specific and / or tissue structure-specific parameters for the automatic characterization of disease-specific finding data. Each of the aforementioned aspects of the present invention as well as any further aspect of the present invention or any combination or subcombination of further features and / or aspects of the invention as in this202324035 27 document, in particular a computer-implemented method for automatic medical image evaluation and / or image diagnosis and / or a medical-technical data processing unit or a medical-technical system and / or a computer program product or computer program system according to one aspect of the present invention or according to any combination or subcombination of further features and / or aspects of the invention as described in this document, can be used for automatic medical image evaluation and / or image diagnosis of radiological image data and / or nuclear medicine image data and / or ultrasound image data and / or optical image data. A further aspect of the present invention is therefore such a aforementioned use of a computer-implemented method for automatic medical image evaluation and / or image diagnosis and / or a medical-technicalData processing unit or a medical technology system and / or a computer program product or computer program system. Within the scope of the inventive methods, in the aspects of the invention described above and / or in further aspects of the invention described in this document, in particular an automatic application of a trained, computer-implemented function takes place. Each trained function described within the scope of the present invention can in particular be designed as a trained neural network function, but can also be designed as another data processing function suitable and adapted for the respective data processing step. A trained function, in particular a trained neural network function, generally maps input data to output data. In this case, the output data can in particular depend on one or more parameters of the trained function 202324035 28. The one or moreParameters of the trained function can be determined and / or adjusted through training. The determination and / or adjustment of the one or more parameters of the trained function can be based in particular on a pair of training input data and associated training output data, wherein the trained function is applied to the training input data to generate training image data. In particular, it can be provided that, within the scope of one or more aspects of the present invention, automatic, in particular computer-implemented feedback loops are provided to change the training basis. This means that the training basis can be changed via feedback loops - ie, can improve over time - because feedback via the training data - such as image training data without findings and / or exclusively image training data without findings from patients and / or with findingsTraining data, such as, in particular, image training data from patients with findings, allows the underlying model to be adapted in further development, and a better set of training data can be used for further automatic medical image evaluations and / or image assessments of new patients. In particular, the determination and / or adaptation can be based on a comparison of the training image data and the training output data. For the purposes of this invention, a trainable function, i.e., a function with parameters that have not yet been adapted, is also understood as a trained function. In particular, the trained function can be contained in a single filter component of the data filter. In addition, the data filter can have further filter components that do not include trained functions because they operate, for example, in a rule-based manner. Furthermore, the data filter can also have multiple trained functions. 202324035 29 AA trained function within the meaning of this invention can be designed as a trained mapping rule, a mapping rule with trained parameters, a function with trained parameters, an algorithm based on artificial intelligence, or a machine learning algorithm. An example of a trained function is an artificial neural network, such as a convolutional neural network. Parameters within the meaning of the invention can in particular be weight parameters of neurons of an input layer and / or an output layer and / or of one or more hidden layers of such an artificial neural network. Values ​​described within the scope of the invention for a probability measure and / or a probability criterion and / or for probability measure thresholds of functions can be used as error values ​​or cost values ​​of one or more error functions or cost functions of an aforementioned neural network.network, or as values ​​derived from such error values ​​or cost values. A method according to one of the aforementioned aspects of the invention, as well as according to a further aspect as described in this document, can in particular enable the integration of multidisciplinary previous (i.e., historical within the meaning of the invention) analytical, medical, and / or diagnostic information and the automatic evaluation of the relevance of such information. A method according to one of the aforementioned aspects of the invention, as well as according to a further aspect as described in this document, can alternatively or additionally support, in particular, the assessment of current evidence, such as the assessment of current image examinations based on medical imaging methods, in particular through 202324035 30 context-specific integration of relevant previous (i.e., historical within the meaning of the invention)Evidence from the same patient and / or reference patients, such as previous imaging information and clinical patient information, in order to increase diagnostic certainty and to assist in the creation of findings and the subsequent quantification of findings. The properties, features and advantages of aspects of the invention and the manner in which these can be achieved are explained below by way of example using specific exemplary embodiments which are described in conjunction with the drawings. These specific exemplary embodiments do not limit the invention to these exemplary embodiments. In different figures, identical components are provided with identical reference numerals. The figures are generally not to scale. DESCRIPTION OF THE FIGURES Shown are: Fig. 1 a schematic representation of a specific embodiment of a medical-technical data processing unit according to the invention ora medical-technical system, designed to carry out a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis; Fig. 2 is a schematic representation of steps of a specific embodiment of a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis, in particular using a 202324035 31 medical-technical data processing unit according to the invention or a medical-technical system according to Fig. 1; Fig. 3 is a schematic representation of steps of an alternative specific embodiment of a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis, in particular using a medical-technical data processing unit according to the invention or a medical-technical system according to Fig. 1; Fig. 4 is aschematic representation of steps of a specific embodiment of a computer-implemented convolutional neural network according to the invention, in particular in the form of a computer program product; Fig. 5 shows a schematic representation of steps of a specific embodiment of a computer-implemented training method for automatically training computer-implemented trainable functions and of steps of a specific embodiment of a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis, in particular using a medical-technical data processing unit according to the invention or a medical-technical system according to Fig. 1; and Fig. 6 shows a schematic representation of program steps of a specific embodiment of a computer program product or computer program system consisting of severalComputer program product modules, with program steps for carrying out a computer-implemented training method for automatically training computer-implemented trainable functions and of program steps of a specific embodiment of a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis, in particular according to the embodiments according to Fig. 1 to Fig. 4 and / or using a medical-technical data processing unit according to the invention or a medical-technical system according to Fig. 1. The embodiment according to Fig. 1 shows a schematic representation of a specific embodiment of a medical-technical data processing unit according to the invention or a medical-technical system SYS, designed to carry out a computer-implemented method according to the invention for automatic medical image evaluation and / orImage diagnosis, as further explained in particular in the following Figures 2 to 6 including the associated description. The medical-technical data processing unit or the medical-technical system SYS has the following units, which are connected to one another: - an image acquisition unit IDCU, designed for the automatic acquisition of medical image data ID (for example, radiological image data and / or nuclear medicine image data and / or ultrasound image data and / or optical medical image data such as endoscopy image data or colonoscopy image data or eye examination image data or skin cancer scan image data), which represent a one-dimensional, two-dimensional, or three-dimensional medical image content B(r) (for example, a body region, an organ, a tissue region, or a tissue sample), - a storage unit SDMU designed for storing medical dataSD (for example, from current or historical patient data, medical findings data, medical image data, medical findings texts, each as current and / or historical personal data and / or medical data of the same patient and / or of other patients and / or collected data from reference patients and / or from medical reference image data and / or from medical reference texts), - at least one image data processing unit IDPU designed for the automatic processing of medical image data ID, SD, in particular designed for the automatic segmentation and / or encoding of medical image data ID, SD into a plurality of image segments IS ij(for example by means of a Vision Transformer architecture, as will be explained further below with reference to Fig. 2 and Fig. 3), - at least one neural network computing unit NNCU designed for the automatic application of trainable and / or trained computer-implemented functions TF1, TF2 (for example application of one or more trained neural network functions, in particular convolutional neural network functions,as will be explained further below with reference to Fig. 4) to the aforementioned captured medical image data ID and / or to the aforementioned stored medical data SD (in particular to stored medical image data and / or to stored medical text data SD); - at least one display unit DU designed for automatic display for a user of the 202324035 34 medical-technical data processing unit or the medical-technical system SYS (for example for a treating physician, a radiologist, a nuclear medicine specialist, a medical diagnostician,an employee of a medical technology institute or a medical technology research facility) of medical image data ID and / or of stored medical data SD and / or of automatically and computer-implemented method results of the automatic application of the aforementioned trainable and / or trained computer-implemented functions TF1, TF2 to the aforementioned acquired medical image data ID and / or to the aforementioned stored medical data SD, in particular for the automatic display of automatically and computer-implemented generated medical findings data MD(r) and / or in particular for the automatic display of automatically and computer-implemented determined spatial representation of a probability measure h, ij(r) the absence of medical findings and / or the presence of medical findings for the captured medical image data ID and / or for the stored medical data SD, as will be explained in more detail below. The medical-technical data processing unit or the medical-technical system SYS is designed to carry out a computer-implemented method for automatic medical image evaluation and / or image diagnosis according to Fig. 5 or a computer program product according to Fig. 6, wherein the computer-implemented method orthe computer program product is designed in several stages and comprises the following stages, as will be explained in more detail below with reference to Figures 5 and 6: 202324035 35 - a first stage 103, 104, S103, S104 for the automatic computer-implemented evaluation of recorded and / or stored medical data ID, SD, in particular medical image data ID, SD, wherein a probability measure and / or a probability distribution h. ij the absence of findings for the recorded medical data ID) and / or for the stored medical data SD; and - a second stage 106, S106 for the automatic computer-implemented determination of deviations in the probability measure and / or the probability distribution h ij the absence of findings of at least one probability measure threshold hS ij and / or of at least one probability measure criterion hC ijof the freedom from findings recorded and / or stored medical data ID, SD; and optionally - a third stage 107, S107 for the automatic computer-implemented creation of medical findings based on the recorded and / or stored medical data ID, SD and the determined deviations of the determined probability measure and / or the determined probability distribution h ij the absence of findings of at least one probability measure threshold hS ij and / or at least one probability measure criterion hC ijthe absence of findings, and for the automatic computer-implemented provision of the created medical findings to a user by means of a display unit DU. The aforementioned neural network computing unit NNCU, schematically shown in Fig. 1, is designed according to the exemplary embodiment according to Fig. 1 for the automatic computer-implemented determination of findings data, in particular, as schematically shown in Fig. 1, for the automatic application of a first computer-implemented neural network function TF1, trained using predominantly finding-free and / or exclusively finding-free training data TD1, to the image segments IS ij , as well as for automatically applying a second computer-implemented neural network function TF2, trained using training data TD2 with findings, to such image segments IS ij, for which a probability measure h is automatically and computer-implemented ij which has a predefined and / or learned probability measure threshold hS ij falls below or exceeds and / or a probability measure criterion hC correlated with the medical image content B(r) ijfulfilled (which depends, for example, on the typical and / or expected nature of a body region, an organ, a tissue region, or a tissue sample, whereby these data can in particular also be correlated with stored data SD, such as current or historical patient data, medical findings data, medical image data, medical findings texts, each as current and / or historical personal data and / or medical data of the same patient and / or of other patients and / or collected data from reference patients and / or from medical reference image data and / or from medical reference texts). As shown in Fig.1, a computer-implemented training method for automatically training the computer-implemented trainable functions TF1, TF2 can be carried out using medical image data, in particular using training data TD1 without findings and training data TD2 with findings, which are stored in the medical-technical data processing unit or in the medical-technical system SYS in a training data storage unit TDMU, wherein this training data 202324035 37 storage unit TDMU can be partially or completely identical to the data storage unit SDMU or the training data TD1, TD2 can be partially or completely identical to the stored data SD.The computer-implemented training method for automatically training the computer-implemented trainable functions TF1, TF2 using medical image data, in particular using training data TD1 without findings and training data TD2 with findings, can also be carried out separately from the medical-technical data processing unit or in the medical-technical system SYS in a separate data processing unit not shown in Fig. 1. According to a specific embodiment of a computer-implemented training method for automatically training computer-implemented trainable functions, the first step involves the practical training and learning of data that represent freedom from findings, or in other words, training and learning of "normal health."The training of computer-implemented trainable functions and thus their learning from data that represent freedom from findings can be carried out by "unsupervised learning" on the basis of as much image and, if necessary, secondary data of healthy, i.e., finding-free, references (reference image data). Alternatively, the training of computer-implemented trainable functions and thus their learning from data that represent freedom from findings can be carried out by "supervised learning". The finding-free (i.e., "normally healthy") references can be obtained using different approaches, in particular by means of the following process steps, which can be implemented and carried out automatically and computer-implemented: 202324035 38 a) A model orA computer-implemented trainable function is trained on areas in medical images and clinical parameters that are obviously not affected by a medical finding indication or diagnosis and that are also not mentioned in stored data such as stored doctor's report data. Simple example: When diagnosing a collarbone fracture, medical image data that exhibit this medical finding indication are excluded from the training process, and a model or a computer-implemented trainable function is trained as free of findings or as "normally healthy" based on the remaining available or stored data, which are characterized, classified, or assumed to be free of a medical finding indication or diagnosis. b) A model orA computer-implemented trainable function learns based on data from completed diagnostic processes or based on data that represents and / or documents current and / or historical disease progression. The advantage here is that the additional trained parameters, although training-intensive, also have a stabilizing effect on the model or the computer-implemented trainable function and its parameters (in particular, weight parameters of neurons in an input layer and / or an output layer and / or one or more hidden layers of a neural network) because the variance from invisible parameters decreases. c) A model or a computer-implemented trainable function learns based on medical image data with non-actionable disease (NAD) classification.This represents a compromise and a special form of 202324035 39 “supervised learning,” in which a finite list of clinical pictures has been excluded by subject experts for the medical image data, and the medical image data can be described as NAD-normal-healthy. d) In addition, an interpretation of the difference between asymptomatic (i.e., “normal-healthy”) and diagnosed (i.e., medical “abnormality”) is often tied to additional parameters beyond pure medical image data and, in particular, correlates with personal parameters and data of a specific patient or patient group (such as age, gender, ethnicity, weight, laboratory parameters, etc.). Simple example: the size of the liver correlates with the size of the patient, but also with gender and age.The assessment of an abnormality can also be time-dependent, so that follow-up examinations can also play a role in training and analysis. Such non-image-based data or parameters can be made available to a model or a computer-implemented trainable function in a training process and to a trained computer-implemented function as part of an automatic medical image evaluation and / or image reporting. This can be image-data-based, but also text-data-based, for example, using a large language model process (e.g., GPT) based on the stored text data and / or image data (SD) of a patient file. e) A general model or a general computer-implemented trainable function can be trained from image, text 202324035 40, and other quantitative information, which can assess the absence of findings (normality) or the presence of findings (abnormality) overall.f) Computer-implemented or computer-readable information from medical guidelines and medical textbooks stored electronically or available in electronic databases can also be included in the training. This not only trains relevant medical example images, but also correlations typical for cases of illness between medical image data and other medical and / or personal data, such as laboratory values. Fig. 2 shows a schematic representation of steps of a specific embodiment of a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis, in particular using a medical-technical data processing unit according to the invention or a medical-technical system according to Fig. 1. The system shown in Fig.2 schematically illustrated method comprises the following automatic computer-implemented steps: automatic acquisition and reading of acquired medical image data ID which represents a one-dimensional or two-dimensional or three-dimensional medical image content B(r), automatic segmentation IS (and if necessary encoding) of the image data ID into a plurality of image segments IS. ij , where these image segments IS ij contain location information r1, r2, automatically applying a first computer-implemented function TF1 trained using predominantly finding-free and / or exclusively finding-free training data to the image segments ISij, automatically determining a (location-dependent) probability measure h ij (r1, r2) of the absence of findings for each 202324035 41 of the image segments IS ijusing the trained computer-implemented function TF1; and automatically displaying a spatial or location-dependent representation of the probability measure h ij (r), in particular by means of a display unit DU as shown in Fig. 1. The aforementioned image segmentation can in principle be carried out using a suitable image segmentation method known from the prior art. An input image is divided into so-called patches. Each patch can be represented as a group of individual image segments IS ij generated, as shown schematically in Fig. 2, and then used as input for an actual transformer. As already explained at the beginning, position information of the patches relative to each other or about the position in the input image is added with position embeddings in order to obtain location information IS ij (r1, r2) of the individual image segments IS ijA decoder can then process the output of the transformer encoder to obtain IS ij To generate predictions regarding certain parameters, in the example of Fig. 2 regarding a (location-dependent) probability measure h ij (r1, r2) of the absence of findings. A sufficiently trained model of such image segmentation, transformation, encoding, and decoding can be applied to new, previously unprocessed images to generate corresponding segmentation masks. These masks represent the predicted class labels for each individual image segment IS ij. Fig. 3 shows a schematic representation of steps of a special embodiment of a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis, which is an alternative to the embodiment according to Fig. 2, in particular using a medical-technical data processing unit according to the invention or a medical-technical system according to Fig. 1. The aforementioned image segmentation according to Fig. 3 can be carried out in particular with a Vision Transformer (ViT) architecture already mentioned at the beginning, the basic process of which, as already explained at the beginning, is divided into an input preprocessing step, a transformation step, a segmentation step IS and an inference step. In the input preprocessing step, an input image or input image data ID is divided into so-called patches. Each patch can be generated as a vector that contains individual image segments ISij , as schematically shown in Fig. 3, and then used as input for the actual transformer. As already explained, position information IS(r) of the patches relative to each other or about the position in the input image can be added using position embeddings. In the segmentation step, a decoder processes the output of the transformer encoder IE to generate IS for each individual image segment. ij To generate predictions regarding certain parameters, in the example of Fig. 3 regarding a (location-dependent) probability measure h i (r) of the absence of findings. A sufficiently trained model of such image segmentation, transformation, encoding, and decoding can be applied to new, previously unprocessed images to generate corresponding segmentation masks. These masks represent the predicted class labels for each individual image segment IS ij. Fig. 4 shows a schematic representation of steps of a specific embodiment of a computer-implemented convolutional neural network TF1, TF2 according to the invention, as shown in Fig. 1 and already described at the beginning, in particular in the form of a computer program product or a computer-implemented neural network. 202324035 43 As already stated at the beginning, convolutional neural networks TF1, TF2 are basically known from the prior art and represent a special type of computer-implemented trainable neural networks that are particularly well suited for image processing. CNNs use convolutional layers that are generated by convolution steps C1, C2 to extract features from input data I. The basic sequential elements according to which such a computer-implemented convolutional neural network usually functions are shown in Fig.4: one or more convolutional layers CL1, CL2, one or more pooling layers PL1, PL2, one or more fully connected layers FCL and an output layer OL. A convolutional layer of a convolutional neural network TF1, TF2 is essentially a filter that is pushed over input data. This process is repeated for different areas of the input data, creating so-called feature maps FM1, FM2, FM3, FM4. After one or more convolutional layers CL1, CL2 in Fig. 4, a subsampling S1, S2 follows in Fig. 4 to form a pooling layer PL1, PL2. This pooling serves to reduce the dimensions of the feature maps FM1, FM3 generated using the convolutions C1, 2 while still preserving the relevant information. After the Convolutional Layers CL1, CL2 and the Pooling Layers PL1, PL2, a Fully Connected Layer FCL follows, which contains the previously extracted information orConvert features into a form suitable for classification or regression and convert the generated multidimensional feature maps FM1, FM2, FM3, FM4, in particular the final feature map FM4, into a lower-dimensional representation and finally flow into an output layer OL, which has a corresponding number of neurons depending on the task (classification, regression, etc.). 202324035 44 Fig. 5 shows a schematic representation of steps of a specific embodiment of a computer-implemented training method for automatically training computer-implemented trainable functions and of steps of a specific embodiment of a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis, in particular using a medical-technical data processing unit according to the invention or a medical-technical system according to Fig.1. The computer-implemented training method for automatically training computer-implemented trainable functions and the (subsequent) computer-implemented method for automatic medical image evaluation and / or image diagnosis have the following method steps: - automatic training 100a of a first computer-implemented function TF1 using predominantly free of findings and / or using exclusively free of findings image training data TD1 for learning parameters for automatically characterizing a probability measure h of the freedom from findings of image data ID and / or of at least one probability measure threshold value hS. ij the absence of findings from image data ID and / or from at least one probability measure criterion hC correlated with medical image content B(r) ijthe absence of findings from image data ID, and - automatic training 100b of a second computer-implemented function TF2 using training data TD2 containing findings to learn parameters for the automatic characterization of findings data, and furthermore the steps: - automatic reading 101 of acquired medical image data ID and / or of stored medical data SD, which represent at least one one-dimensional, two-dimensional, or three-dimensional medical image content B(r), - automatic segmentation 102 and / or encoding of the image data ID, SD into a plurality of image segments IS ij , - automatically applying 103 a first function TF1, trained using predominantly free and / or exclusively free training data TD1 and computer-implemented in a neural network computing unit NNCU, to the image segments IS ij, - automatic determination 104 of a probability measure h ij the absence of findings for each of the image segments IS ij using the trained computer-implemented function TF1, and either as a further step: - automatically displaying 105 a spatial representation of the probability measure h ij (r) by means of a display unit DU, or alternatively as further steps: - automatically applying 106 a second function TF2 trained by means of training data TD2 and computer-implemented in a neural network computing unit NNCU to image segments IS ij with a probability measure h ij which has a predefined and / or learned probability measure threshold hS ij falls below or exceeds and / or a probability measure criterion hC correlated with the medical image content B(r) ijfulfilled, for the automatic determination of findings data, and - automatic display 107 of the determined findings data for a user by means of a display unit DU. 202324035 46 For the last two aforementioned steps 106 and 107 (as well as in the context of the program steps S106 and S107 described below), the following can be provided: Within the scope of the automatic application 106 of a second computer-implemented function TF2, in particular organ- and structure-specific detectors for specific clinical pictures can be selected and executed. Here, too, the aforementioned training of the local models of a second computer-implemented function TF2 can be carried out purely image-based or with the help of optional secondary information. The training can either be supervised, and existing solutions with CNNs can be used. Alternatively, it can be provided,that, for example, Vision Transformer-like models generate or learn locally specialized detectors for specific indications and organ systems solely from annotated training data from image annotation and, if applicable, secondary annotation. Fig. 6 shows a schematic representation of program steps of a specific embodiment of a computer program product or computer program system consisting of several computer program product modules, with program steps for carrying out a computer-implemented training method for automatically training computer-implemented trainable functions and of program steps of a specific embodiment of a computer-implemented method according to the invention for automatic medical image evaluation and / or image diagnosis.in particular according to the embodiments according to Fig. 1 to Fig. 4 and / or using a medical-technical data processing unit according to the invention or a medical-technical system according to Fig. 1. The special embodiment of a computer program product or computer program system according to Fig. 6 comprises instructions which, when the computer program product or the computer program product modules are executed by a data processing unit, cause this data processing unit toto execute the following program steps: - Program step for the automatic computer-implemented training S100a of a first computer-implemented function TF1 using predominantly free of findings and / or exclusively free of findings image training data TD1 for learning parameters for the automatic characterization of a probability measure h of the absence of findings in image data ID and / or of at least one probability measure threshold value hSij of the absence of findings in image data ID and / or of at least one probability measure criterion hCij of the absence of findings in image data ID correlated with medical image content B(r),and - program step for the automatic computer-implemented training S100b of a second computer-implemented function TF2 using training data TD2 containing findings for learning organ-specific and / or tissue structure-specific parameters for the automatic characterization of disease-specific findings data, and furthermore the program steps: - program step for the automatic computer-implemented reading S101 of acquired medical image data ID and / or of stored medical data SD, which represent at least one one-dimensional or two-dimensional or three-dimensional medical image content B(r), - program step for the automatic computer-implemented segmentation S102 and / or encoding of the 202324035 48 image data ID, SD into a plurality of image segments IS, ij, - Program step for the automatic computer-implemented application S103 of a first function TF1, trained using predominantly finding-free and / or exclusively finding-free training data TD1 and computer-implemented in a neural network computing unit NNCU, to the image segments IS ij ; - Program step for the automatic computer-implemented determination S104 of a probability measure h ij the absence of findings for each of the image segments IS ij by means of the trained computer-implemented function TF1, and either as a further program step: - Program step for the automatic computer-implemented representation S105 of a spatial representation of the probability measure h ij(r) by means of a display unit DU, or alternatively as further program steps: - Program step for the automatic computer-implemented application S106 of a second function TF2, trained by means of training data (TD2) with findings and computer-implemented in a neural network computing unit NNCU, to image segments ISij with a probability measure h ij which has a predefined and / or learned probability measure threshold (hS ij ) falls below or exceeds and / or a probability measure criterion hC correlated with the medical image content B(r) ijfulfilled, for the automatic determination of findings data, and - program step for the automatic computer-implemented presentation S107 of the determined findings data for a user by means of a presentation unit DU.202324035 49 A computer-implemented method for automatic medical image evaluation and / or image diagnosis and / or a medical data processing unit or a medical system and / or a computer program product or computer program system as shown in Figures 1 to 6 and as described above can be used for automatic medical image evaluation and / or image diagnosis of any type of medical image, such as for automatic medical image evaluation and / or image diagnosis of radiological image data and / or nuclear medicine image data and / or ultrasound image data and / or optical image data, but they can also be used for evaluation and / or analysis for general vision tasks. In summary, the aspects of the present invention represent methods and data processing devices orSystems and computer program products are available which, by means of the exclusion principle, exclude healthy biological systems and regions from further diagnostics, and then analyze and evaluate abnormal regions for specific localized findings. The described aspects, features, and embodiments of the invention, in comparison to the prior art, solve essential problems of automatic medical image evaluation and / or image reporting through the described multi-stage procedure. As described, in a first stage, we train non-specifically for "free of findings" or "normally healthy" - and thus, inversely, for non-specific abnormalities. This is also possible "unsupervised" with a large amount of radiological data from healthy references. Similar to how large language models learn the structure of language and content with large amounts of data, in a first stage, "free of findings" or "normally healthy" can be non-specifically determined."normally healthy" and evaluated globally. In a second stage, trained functions such as neural networks or CNNs and derivatives can be used, or new approaches such as vision transformers can be applied. Unlike the state of the art, they can be trained in a more localized manner and may also advantageously receive relevant prior information from the first stage. This reduces the need for specially annotated image sets. In vision transformers, the property of the transformers being able to learn patterns from relatively few individual cases using attention mechanisms is advantageous. The aforementioned multi-stage approach or combination also has the advantage of reducing the number of false positive reports in the overall system, since all general abnormalities are double-checked by a local model.A further advantage is that "unclear findings" can also be localized in the second stage and presented to another decision-making body (e.g., a human radiologist or a computer-implemented second model, etc.) for review, analysis, and / or evaluation. It is also possible to have several alternative models test the same finding in the second stage. The result can be no finding, a finding, or a need for clarification. The described multi-stage procedure with an optional third stage for automatic medical reporting 202324035 51 can enable extensive automation of a medical procedure and / or a medical device, and relieve users of such procedures and devices, such as treating physicians, radiologists, or nuclear medicine specialists, of routine work.Regardless of the grammatical gender of a particular term, persons with male, female or other gender identity are included.

Claims

202324035 52 patent claims 1. Computer-implemented method for automatic medical image evaluation and / or image diagnosis, wherein the computer-implemented method is designed as a multi-stage method and comprises the following stages: - a first stage (103, 104) for automatic computer-implemented evaluation of recorded and / or stored medical data (ID, SD), in particular of medical image data (ID, SD), wherein a probability measure and / or a probability distribution (h ij ) of the absence of findings for the recorded medical data (ID) and / or for the stored medical data (SD); and - a second stage (106) for the automatic computer-implemented determination of deviations in the probability measure and / or the probability distribution (h ij ) the absence of findings of at least one probability measure threshold (hS ij) and / or at least one probability measure criterion (hC ij ) the absence of findings in the recorded and / or stored medical data (ID, SD); and optionally - a third stage (107) for the automatic computer-implemented creation of medical findings based on the recorded and / or stored medical data (ID, SD) and the determined deviations of the determined probability measure and / or the determined probability distribution (h ij ) the absence of findings from at least one probability measure threshold (hS ij ) and / or at least one probability measure criterion (hC ij ) of the absence of findings, and for the automatic computer-implemented provision of the created 202324035 53 medical findings for a user using a display unit (DU). 2.Computer-implemented method for automatic medical image evaluation and / or image diagnosis according to claim 1, wherein the computer-implemented method comprises the following steps: - automatically reading in (101) acquired medical image data (ID) and / or stored medical data (SD), which represent at least one one-dimensional, two-dimensional, or three-dimensional medical image content (B(r)); - automatically applying (103) a first function (TF1), trained using predominantly finding-free and / or exclusively finding-free training data (TD1) and computer-implemented in a neural network computing unit (NNCU), to the acquired medical image data (ID) and / or to the stored medical data (SD); - automatically determining (104) a location-dependent probability measure and / or a spatial probability distribution (h. ij(r)) the absence of findings for the acquired medical image data (ID) and / or for the stored medical data (SD) by means of the trained computer-implemented function (TF1); and - automatically displaying (105) a spatial representation of the location-dependent probability measure and / or the spatial probability distribution (h ij (r)) by means of a display unit (DU); and / or - automatically applying (106) a second training data (TD2) trained by means of findings-related training data and stored in a neural network computing unit 202324035 54 (NNCU) computer-implemented function (TF2) to such acquired medical image data (ID) and / or to such stored medical data (SD), whose determined probability measure (h ij ) a predefined and / or learned probability measure threshold (hS ij) falls below or exceeds and / or a probability criterion (hC ij ) for the automatic determination of findings data; and - automatically determining and displaying findings data (107) for a user by means of a display unit (DU).

3. A computer-implemented method for automatic medical image evaluation and / or image diagnosis according to claim 1 or 2, wherein the computer-implemented method comprises the following steps: - automatically reading (101) acquired medical image data (ID) and / or stored medical data (SD), which represent at least one one-dimensional, two-dimensional, or three-dimensional medical image content (B(r)); - automatically segmenting (102) and / or encoding the image data (ID, SD) into a plurality of image segments (IS ij); - automatically applying (103) a first function (TF1) trained by means of predominantly finding-free and / or exclusively finding-free training data (TD1) and computer-implemented in a neural network computing unit (NNCU) to the image segments (IS ij ); - automatically determining (104) a probability measure (h ij ) of freedom from findings for each of the 202324035 55 image segments (IS ij ) by means of the trained computer-implemented function (TF1); and - automatically displaying (105) a spatial representation of the probability measure (h ij (r)) by means of a display unit (DU); and / or - automatically applying (106) a second function (TF2) trained by means of training data (TD2) and computer-implemented in a neural network computing unit (NNCU) to image segments (IS ij ) with a probability measure (h ij) which has a predefined and / or learned probability measure threshold (hS ij ) and / or a probability measure criterion (hC) correlated with the medical image content (B(r)) ij) for the automatic determination of findings data; and - automatic determination and display (107) of findings data for a user by means of a display unit (DU).

4. A computer-implemented method for automatic medical image evaluation and / or image diagnosis according to one of claims 1 to 3, wherein the computer-implemented method additionally comprises the following steps: - automatic training (100a) of a first computer-implemented function (TF1) using predominantly finding-free and / or exclusively finding-free image training data (TD1) for learning parameters for the automatic characterization of a probability measure (h) of the finding-free state of image data (ID) and / or of at least one probability measure threshold value (hS ij ) the absence of findings from image data (ID) and / or from at least one with medical image content (B(r)) 202324035 56 correlated probability measure criterion (hC ij ) the absence of findings in image data (ID), and - automatically training (100b) a second computer-implemented function (TF2) using training data (TD2) with findings to learn parameters for automatically characterizing findings data.

5. A computer-implemented method for automatic medical image evaluation and / or image reporting according to one of claims 1 to 4, wherein the computer-implemented method comprises the following steps: - automatically applying (106) a second function (TF2) trained using training data (TD2) with findings and computer-implemented in a neural network computing unit (NNCU) to image segments (IS ij ) with a probability measure (hij) which exceeds a predefined and / or learned probability measure threshold (hS ij) and / or a probability measure criterion (hC) correlated with the medical image content (B(r)) ij ), including and / or correlating with stored medical data (SD), for the automatic determination of diagnosis data; and - automatic display (107) of acquired medical image data (ID) and / or stored medical data (SD) as well as of automatically determined diagnosis data (MD(r)), in particular of location-dependent diagnosis data (MD(r)), for a user by means of a display unit (DU).

6. A computer-implemented method for automatic medical image evaluation and / or image diagnosis according to one of claims 1 to 5, wherein the computer-implemented method comprises the following steps: 202324035 57 - automatically training (100b) a second computer-implemented function (TF2) using training data (TD2) containing findings and stored medical data (SD) to learn parameters for automatically characterizing findings data and for learning a language model for linguistically describing automatically determined and / or stored findings data; - automatically applying (106) the second function (TF2) trained using training data (TD2) containing findings and computer-implemented in a neural network computing unit (NNCU) to automatically determine findings data and to automatically create a linguistic description based on the learned language model to such acquired medical image data (ID) and / or to such stored medical data (SD) and / or to such image segments (IS ij ) with a probability measure (h ij) which has a predefined and / or learned probability measure threshold (hS ij ) and / or a probability measure criterion (hC ij ) is fulfilled by including and / or correlating with stored medical data (SD); and - automatically displaying (107) the determined findings data and the linguistic description of the determined findings data automatically created on the basis of the learned language model for a user by means of a display unit (DU).

7. A computer-implemented method for automatic medical image evaluation and / or image diagnosis according to one of claims 1 to 6, wherein the computer-implemented method comprises the following steps: 202324035 58 - automatic segmentation (102) and / or encoding of the image data (ID, SD) by means of a neural transformer network architecture and / or by means of a generative neural network architecture into a plurality of image segments (IS ij ); - automatically applying (103) a first neural network function (TF1) trained using predominantly finding-free and / or exclusively finding-free training data (TD1) and computer-implemented in a neural network computing unit (NNCU) to the image segments (IS ij ); and - automatically applying (106) a second neural network function (TF2) trained by means of training data (TD2) and computer-implemented in a neural network computing unit (NNCU) to image segments (IS ij ) with a probability measure (h ij ) which has a predefined and / or learned probability measure threshold (hS ij) and / or a probability measure criterion (hC ij ) for the automatic determination of findings data.

8. Computer-implemented training method for the automatic training of computer-implemented trainable functions using medical image data, wherein the computer-implemented training method comprises the following steps: - automatic training (100a) of a first computer-implemented function (TF1) using predominantly finding-free and / or exclusively finding-free image training data (TD1) for learning parameters for the automatic characterization of a probability measure (h) of the finding-free nature of 202324035 59 image data (ID) and / or at least one probability measure threshold (hS ij) the absence of findings from image data (ID) and / or from at least one probability measure criterion (hC) correlated with medical image content (B(r)) ij) the absence of findings in image data (ID), and - automatic training (100b) of a second computer-implemented function (TF2) using training data (TD2) containing findings in order to learn organ-specific and / or tissue structure-specific parameters for the automatic characterization of disease-specific findings data.

9. The computer-implemented training method according to claim 8, wherein the computer-implemented training method comprises the following step: - automatically training (100b) a second computer-implemented function (TF2) using training data (TD2) containing findings and stored medical data (SD) to learn organ-specific and / or tissue-structure-specific parameters for automatically characterizing disease-specific findings and to learn a language model for linguistically describing automatically determined and / or stored findings. 10.Medical-technical data processing unit or medical-technical system (SYS), in particular designed to carry out a computer-implemented method according to one of claims 1 to 7, wherein the medical-technical data processing unit or the medical-technical system (SYS) has at least the following units which are in data communication with one another:. 202324035 60 - at least one image acquisition unit (IDCU) designed for the automatic acquisition of medical image data (ID); - at least one storage unit (SDMU) designed for the storage of medical data (SD); - at least one image data processing unit (IDPU) designed for the automatic processing of medical image data (ID, SD), in particular designed for the automatic segmentation (102) and / or encoding of medical image data (ID, SD) into a plurality of image segments (IS ij); - at least one neural network computing unit (NNCU) designed to automatically apply trainable and / or trained computer-implemented functions (TF1, TF2) to medical image data (ID) and / or to stored medical data (SD); - at least one display unit (DU) designed to automatically display medical image data (ID) and / or stored medical data (SD) and / or medical findings data (MD(r)); wherein the neural network computing unit (NNCU) is designed to - automatically apply (103) a first computer-implemented neural network function (TF1) trained using predominantly finding-free and / or exclusively finding-free training data (TD1) to the image segments (IS ij); and for - automatically applying (106) a second computer-implemented neural network function (TF2) trained by means of training data (TD2) to image segments (IS ij ) with a probability measure (h ij ) which has a predefined and / or learned probability measure threshold (hS ij ) falls below or exceeds and / or a 202324035 61 probability measure criterion (hC) correlated with the medical image content (B(r)) ij) for the automatic determination of diagnostic data.

11. A computer program product or computer program system consisting of several computer program product modules, comprising instructions which, when the computer program product or the computer program product modules are executed by a data processing unit, cause this data processing unit to execute program steps for carrying out a computer-implemented method according to one of claims 1 to 7;in particular in cooperation with a medical-technical data processing unit or medical-technical system (SYS) according to claim 10, comprising instructions which, when the computer program product or the computer program product modules are executed by a data processing unit, cause this data processing unit to carry out the following computer-implemented program steps: - program steps (S103, S104) of a first program stage for the automatic computer-implemented evaluation of recorded and / or stored medical data (ID, SD), in particular of medical image data (ID, SD), wherein a probability measure and / or a probability distribution (h; ij) the absence of findings for the recorded medical data (ID) and / or for the stored medical data (SD); and - program steps (S106) of a second program stage for the automatic computer-implemented determination of deviations of the probability measure and / or the probability distribution (h ij ) the absence of findings of at least one probability measure threshold (hS ij ) and / or at least 202324035 62 a probability measure criterion (hC ij ) of the freedom from findings recorded and / or stored medical data (ID, SD); and optionally - program steps (S107) of a third program stage for the automatic computer-implemented creation of medical findings based on the recorded and / or stored medical data (ID, SD) and the determined deviations of the determined probability measure and / or the determined probability distribution (hij ) the absence of findings of at least one probability measure threshold value (hS ij ) and / or at least one probability measure criterion (hC ij) of the absence of findings, and for the automatic computer-implemented provision of the created medical findings to a user via a display unit (DU). 12.Computer program product or computer program system consisting of a plurality of computer program product modules according to claim 11, comprising instructions which, when the computer program product or the computer program product modules are executed by a data processing unit, cause this data processing unit to carry out the following computer-implemented program steps: - program step for the automatic computer-implemented reading (S101) of acquired medical image data (ID) and / or of stored medical data (SD), which represent at least one one-dimensional or two-dimensional or three-dimensional medical image content (B(r)); - program step for the automatic computer-implemented application (S103) of a first training data (TD1) which has been trained using predominantly finding-free and / or using exclusively finding-free training data (TD1) and which is stored in. 202324035 63 a neural network computing unit (NNCU) computer-implemented function (TF1) on the acquired medical image data (ID) and / or on the stored medical data (SD); - program step for the automatic computer-implemented determination (S104) of a probability measure (h ij ) the absence of findings for the acquired medical image data (ID) and / or for the stored medical data (SD) by means of the trained computer-implemented function (TF1); and - program step for the automatic computer-implemented display (S105) of a spatial representation of the probability measure (h ij(r)) by means of a display unit (DU); and / or - program step for the automatic computer-implemented application (S106) of a second function (TF2) trained by means of training data (TD2) containing findings and computer-implemented in a neural network computing unit (NNCU) to such acquired medical image data (ID) and / or to such stored medical data (SD), the determined probability measure (h ij ) a predefined and / or learned probability measure threshold (hS ij ) falls below or exceeds and / or a probability criterion (hC) correlated with the medical image content (B(r)) ij) for the automatic determination of findings data; and - program step for the automatic computer-implemented presentation (S107) of the determined findings data for a user by means of a presentation unit (DU).

13. Computer program product or computer program system consisting of several computer program product modules 202324035 64 according to claim 11, comprising instructions which, when the computer program product or the computer program product modules are executed by a data processing unit, cause this data processing unit to carry out the following steps: - program step for the automatic computer-implemented reading (S101) of acquired medical image data (ID) and / or of stored medical data (SD), which represent at least one one-dimensional, two-dimensional, or three-dimensional medical image content (B(r)); - program step for the automatic computer-implemented segmentation (S102) and / or encoding of the image data (ID, SD) into a plurality of image segments (IS ij); - program step for the automatic computer-implemented application (S103) of a first function (TF1) trained using predominantly finding-free and / or exclusively finding-free training data (TD1) and computer-implemented in a neural network computing unit (NNCU) to the image segments (IS ij ); - program step for the automatic computer-implemented determination (S104) of a probability measure (h ij ) of the absence of findings for each of the image segments (IS ij ) by means of the trained computer-implemented function (TF1); and - program step for the automatic computer-implemented display (S105) of a spatial representation of the probability measure (h ij(r)) by means of a display unit (DU); and / or - program step for the automatic computer-implemented application (S106) of a second training data (TD2) trained by means of findings-based training data and stored in a neural network computing unit (NNCU) 202324035 65 computer-implemented function (TF2) on image segments (IS ij ) with a probability measure (h ij ) which has a predefined and / or learned probability measure threshold (hS ij ) and / or a probability measure criterion (hC) correlated with the medical image content (B(r)) ij) for the automatic determination of findings data; and - program step for the automatic computer-implemented presentation (S107) of the determined findings data for a user by means of a presentation unit (DU). 14.Computer program product or computer program system consisting of a plurality of computer program product modules according to claim 11, comprising instructions which, when the computer program product or the computer program product modules are executed by a data processing unit, cause this data processing unit to carry out the following steps: - program step for the automatic computer-implemented training (S100a) of a first computer-implemented function (TF1) using predominantly free of findings and / or exclusively free of findings image training data (TD1) for learning parameters for the automatic characterization of a probability measure (h) of the freedom from findings of image data (ID) and / or of at least one probability measure threshold value (hS. ij ) the absence of findings from image data (ID) and / or from at least one probability measure criterion (hC) correlated with medical image content (B(r)) ij) the absence of findings in image data (ID), as well as - program step for automatic computer-implemented training (S100b) of a second computer- 202324035 66 implemented function (TF2) using training data (TD2) with findings for learning organ-specific and / or tissue structure-specific parameters for the automatic characterization of disease-specific finding data.

15. Use of a computer-implemented method for automatic medical image evaluation and / or image diagnosis according to one of claims 1 to 7 and / or use of a medical-technical data processing unit or a medical-technical system (SYS) according to claim 10 and / or use of a computer program product or computer program system according to one of claims 11 to 14 for automatic medical image evaluation and / or image diagnosis of radiological image data and / or nuclear medicine image data and / or ultrasound image data and / or optical image data.

Images