Abstract: Provided are automated (computerized) methods and systems for analyzing digitized pathology images in a variety of tissues potentially containing diseased or neoplastic cells. The method utilizes a coarse-to-fine analysis, in which an entire image is tiled and shape, color, and texture features are extracted in each tile, as primary features. A representative subset of tiles is determined within a cluster of similar tiles. A statistical analysis (e.g. principal component analysis) reduces the substantial number of “coarse” features, decreasing computational complexity of the classification algorithm. Afterwards, a fine stage provides a detailed analysis of a single representative tile from each group. A second statistical step uses a regression algorithm (e.g. elastic net classifier) to produce a diagnostic decision value for each representative tile. A weighted voting scheme aggregates the decision values from these tiles to obtain a diagnosis at the whole slide level.

Abstract: Embodiments of the invention are generally directed to methods and systems for robust federated training of neural networks capable of overcoming sample size and/or label distribution heterogeneity. In various embodiments, a neural network is trained by performing a first number of training iterations using a first set of training data and performing a second number of training iterations using a second set of training data, where training methodology includes a function to compensate for at least one form of heterogeneity. Certain embodiments incorporate image generation networks to produce synthetic images used to train a neural network.

Abstract: Systems and methods for generating context-aware word embeddings in accordance with embodiments of the invention are illustrated. One embodiment includes a report annotation server, including a processor; and a memory containing a report annotation application, where the report annotation application configures the processor to obtain a plurality of case reports from at least one medical database, preprocess the plurality of case reports, segment the preprocessed plurality of case reports, reduce the term ambiguity of the segmented plurality of case reports, generate word embeddings, and generate a context-aware vector based on the word embeddings.

Abstract: Systems and methods for evaluating artificial intelligence applications with seamlessly embedded features in accordance with embodiments of the invention are illustrated. One embodiment includes an AI evaluation system including a plurality of collection servers, an AI evaluation server connected to the plurality of collection servers, including at least one processor and a memory, containing an AI evaluation application that directs the processor to obtain a plurality of ground truth data from the plurality of collection servers, where the ground truth data includes a plurality of image and annotation pairs, generate a first plurality of outputs by providing a first AI system with images from the plurality of image and annotation pairs, compare the first plurality of outputs with annotations from the plurality of image and annotation pairs, generate a first ranking metric of the first AI system based on the comparison, and store the first ranking metric in a database.

Abstract: Systems and methods for image segmentation in accordance with embodiments of the invention are illustrated. One embodiment includes a method for segmenting medical images, including obtaining a medical image of a patient, the medical image originating from a medical imaging device, providing the medical image of the patient to a fully convolutional neural network (FCN), where the FCN comprises a loss layer, and where the loss layer utilizes the CE-IOU loss function, segmenting the medical image such that at least one region of the medical image is classified as a particular biological structure, and providing the medical image via a display device.

Abstract: Provided are methods for characterizing a feature of interest in a digital image. In certain aspects, the methods use an adaptive local window and include obtaining an initial contour for a feature of interest, defining a region of interest around the contour, and segmenting the feature of interest by iteratively selecting a size of a local window surrounding each point on the contour. Non-transitory computer readable media and systems that find use in practicing the methods of the present disclosure are also provided.

Abstract: An example method for analyzing quantitative information obtained from radiological images includes identifying a ROI or a VOI in a radiological image, segmenting the ROI or the VOI from the radiological image and extracting quantitative features that describe the ROI or the VOI. The method also includes creating a radiological image record including the quantitative features, imaging parameters of the radiological image and clinical parameters and storing the radiological image record in a data structure containing a plurality of radiological image records. In addition, the method includes receiving a request with the patient's radiological image or information related thereto, analyzing the data structure to determine a statistical relationship between the request and the radiological image records and generating a patient report with a diagnosis, a prognosis or a recommended treatment regimen for the patient's disease based on a result of analyzing the data structure.

Abstract: Provided are automated (computerized) methods and systems for analyzing digitized pathology images in a variety of tissues potentially containing diseased or neoplastic cells. The method utilizes a coarse-to-fine analysis, in which an entire image is tiled and shape, color, and texture features are extracted in each tile, as primary features. A representative subset of tiles is determined within a cluster of similar tiles. A statistical analysis (e.g. principal component analysis) reduces the substantial number of “coarse” features, decreasing computational complexity of the classification algorithm. Afterwards, a fine stage provides a detailed analysis of a single representative tile from each group. A second statistical step uses a regression algorithm (e.g. elastic net classifier) to produce a diagnostic decision value for each representative tile. A weighted voting scheme aggregates the decision values from these tiles to obtain a diagnosis at the whole slide level.

Abstract: Systems and methods for performing image processing in accordance with embodiments of the invention are illustrated. One embodiment includes an imaging system including at least one processor, an input/output interface in communication with a medical imaging device, a display in communication with the processor, and a memory in communication with the processor, including image data obtained from a medical imaging device, where the image data describes at least one image describing at least one region of a patient's body, and an image processing application, where the image processing application directs the processor to preprocess the image data, identify pathological features within the preprocessed image data, calculate the likelihood that the at least one region described by the at least one image is afflicted by a disease, and provide a disease classification substantially instantaneously describing the disease and the likelihood of the disease being present in the region via the display.

Abstract: The present invention provides methods to predict the treatment response of brain tumors such as glioblastoma multiforme to anti-angiogenic therapy based on quantitative perfusion-weighted MRI that can optionally be combined with intra-tumor specific molecular profiling. Since only a subset of brain cancer patients will benefit from anti-angiogenic therapy, identification of this subset is critical so that the effectiveness of the patient's current anti-cancer treatment regimen and the patient's survival likelihood can be increased by the inclusion of an anti-angiogenic agent.

Abstract: Provided are computer-implemented methods of determining tissue composition by polychromatic absorptiometry. The methods include acquiring a raw intensity image of a tissue comprising dense tissue and adipose tissue. The image is generated using a polychromatic electromagnetic radiation source. The methods further include directly measuring the proportion of dense tissue and adipose tissue for each pixel of the raw intensity image and assigning a value to each pixel based on the directly measured proportion of dense tissue and adipose tissue. The composition of the tissue is determined based on the assigned value of each pixel. Systems for practicing the methods are also provided.

Abstract: An example method for analyzing quantitative information obtained from radiological images includes identifying a ROI or a VOI in a radiological image, segmenting the ROI or the VOI from the radiological image and extracting quantitative features that describe the ROI or the VOI. The method also includes creating a radiological image record including the quantitative features, imaging parameters of the radiological image and clinical parameters and storing the radiological image record in a data structure containing a plurality of radiological image records. In addition, the method includes receiving a request with the patient's radiological image or information related thereto, analyzing the data structure to determine a statistical relationship between the request and the radiological image records and generating a patient report with a diagnosis, a prognosis or a recommended treatment regimen for the patient's disease based on a result of analyzing the data structure.

Abstract: Disclosed is a miniaturized phantom that can be placed against breast tissue during mammography. The phantom is provided with various radiological features that can be compared to the image of the breast tissue. The phantom is situated to be included in one or more mammography images. The phantom is at least partially opaque to the radiation of the image and contains features such as step wedges of different density, pillars that show radiation incidence, sweep gratings that show variations of radiation amplitude and a unique bar code to identify patients. The phantoms can be used in images containing them to assess various radiological features in a quantitative way.

Abstract: Provided are methods for characterizing a feature of interest in a digital image. In certain aspects, the methods use an adaptive local window and include obtaining an initial contour for a feature of interest, defining a region of interest around the contour, and segmenting the feature of interest by iteratively selecting a size of a local window surrounding each point on the contour. Non-transitory computer readable media and systems that find use in practicing the methods of the present disclosure are also provided.

Abstract: Disclosed is a method for analyzing retinal image data obtained using spectral-domain optical coherence tomography (SD-OCT). The image data comprise a cross-section of the retina and an en face image of the retina of a subject having AMD (age-related macular degeneration). The image data are processed to obtain an accurate structure showing locations, shape, size, and other data on drusen (deposits under the retina). This structural information is processed to extract quantitative drusen features that are indicative of a risk of progression of AMD from the dry form to the wet form of the disease in a given subject and defined time period, including short time intervals (one year or less). Relevant drusen features used include number, en face area and volume of drusen detected; shape of drusen detected; density of drusen; and reflectivity of drusen.

Abstract: An example method for analyzing quantitative information obtained from radiological images includes identifying a ROI or a VOI in a radiological image, segmenting the ROI or the VOI from the radiological image and extracting quantitative features that describe the ROI or the VOI. The method also includes creating a radiological image record including the quantitative features, imaging parameters of the radiological image and clinical parameters and storing the radiological image record in a data structure containing a plurality of radiological image records. In addition, the method includes receiving a request with the patient's radiological image or information related thereto, analyzing the data structure to determine a statistical relationship between the request and the radiological image records and generating a patient report with a diagnosis, a prognosis or a recommended treatment regimen for the patient's disease based on a result of analyzing the data structure.

Abstract: An example method for analyzing quantitative information obtained from radiological images includes identifying a ROI or a VOI in a radiological image, segmenting the ROI or the VOI from the radiological image and extracting quantitative features that describe the ROI or the VOI. The method also includes creating a radiological image record including the quantitative features, imaging parameters of the radiological image and clinical parameters and storing the radiological image record in a data structure containing a plurality of radiological image records. In addition, the method includes receiving a request with the patient's radiological image or information related thereto, analyzing the data structure to determine a statistical relationship between the request and the radiological image records and generating a patient report with a diagnosis, a prognosis or a recommended treatment regimen for the patient's disease based on a result of analyzing the data structure.

Abstract: Disclosed is a method for analyzing retinal image data obtained using spectral-domain optical coherence tomography (SD-OCT). The image data comprise a cross-section of the retina and an en face image of the retina of a subject having AMD (age-related macular degeneration). The image data are processed to obtain an accurate structure showing locations, shape, size, and other data on drusen (deposits under the retina). This structural information is processed to extract quantitative drusen features that are indicative of a risk of progression of AMD from the dry form to the wet form of the disease in a given subject and defined time period, including short time intervals (one year or less). Relevant drusen features used include number, en face area and volume of drusen detected; shape of drusen detected; density of drusen; and reflectivity of drusen.

Abstract: Contrast agents comprising stable aqueous emulsions of iophendylate and their use in radiological examination of the small and large intestine after oral administration are described.