International Business Machines Corporation

Ella Barkan

Eugene Walach

Pavel Kisilev

Asaf Tzadok

Amir Geva

Shay Ben-David

Vadim Ratner

Tal Drory

Alon Hazan

Sharbell Hashoul

Aviad Zlotnick

Doron Tal

Mattias Marder

Jonathan Bnayahu

Dan S Chevion

Andre Heilper

Amnon Ribak

Yaakov Navon

Simona Rabinovici-Cohen

Tal Tlusty Shapiro

Eyal Yair

Boaz Ophir

Daniel Khapun

Itoko Toshinari

André Heilper

An embodiment for generating balanced train-test splits for machine learning analysis. The embodiment may automatically extract low-level features and high-level features from a series of received datasets. The embodiment may automatically determine a series of impactful features for each of the received datasets correlating to a corresponding label. The embodiment may automatically select subsets of impactful features The embodiment may automatically cluster the received datasets to generate series of clusters, each of the generated series of clusters corresponding to one of the selected subsets of impactful features. The embodiment may automatically generate train-test split versions using datasets from each cluster in each of the generated series of clusters. The embodiment may automatically score each of the generated train-test split versions and select a highest-scoring train-test split version.

Generating balanced train-test splits for machine learning

There is provided a system and a method of generating an annotated structured dataset, comprising: receiving a medical classification term, searching over the unstructured patient data for extracting unclassified unstructured text fragments, presenting a subset of the unclassified unstructured text fragments, receiving an indication of a selection of none or at least one of the text fragments, and one of: (i) classifying non-selected unclassified unstructured text fragments according to the medical classification term, and classifying selected text fragments as not satisfying the medical classification term, and (ii) classifying selected unclassified unstructured text fragments according to the medical classification term, and classifying non-selected unclassified unstructured text fragments as not satisfying the medical classification term, and iterating the searching, and/or the presenting, until no text fragments are obtained by the search, wherein the annotated structured dataset is created by the classification of unclassified unstructured text fragments into the medical classification term.

Systems and methods for targeted annotation of data

Presented herein are methods, systems, devices, and computer-readable media for image annotation for medical procedures. The system operates in a parallel manner. In one flow, the system starts from clinical terms and image and applies image detection module in order to get visual candidates for related radiological finding and provide them with semantic descriptors. In the second (parallel) flow, the system produces a list of prioritized semantic descriptors (with probabilities). The second flow is done by application of a reverse inference algorithm that uses clinical terms and expert clinical knowledge. The results of both flows combined by matching module for detection the best candidate and with limited user input images can be annotated. The clinical terms are extracted from clinical documents by textual analysis.

Method for automatic visual annotation of radiological images from patient clinical data

Embodiments of the present systems and methods may provide techniques that are applicable to a variety of imaging modalities and that utilize prior knowledge of the dynamics of a physiological system to analytically generate augmented samples for machine learning. For example, in an embodiment, a method implemented in a computer comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, the method may comprise generating a transform for an image of tissue based on deformation of the tissue under compression, obtaining an image of tissue using an imaging modality, and generating an output image by transforming the image of the tissue using the transform.

Methods to induce non-rigid mesh transformation in-variance to CNN based medical imaging classifiers

A method comprising using at least one hardware processor for automatically receiving, using a user interface associated with the hardware processor(s), an annotation for a medical image of a patient, the medical image associated with a suspected disease of the patient and metadata of the patient. The hardware processor(s) are configured for performing a search query in real time on a database for the annotation. The hardware processor(s) are configured for receiving at least one result of the search query. The hardware processor(s) are configured for retrieving at least one other medical image comprising at least one other annotation, wherein the at least one other medical image is associated with the at least one result. The hardware processor(s) are configured for displaying, on the user interface, the at least one other medical image and the at least one other annotation.

Reduce discrepancy of human annotators in medical imaging by automatic visual comparison to similar cases

A computer implemented method, a computerized system and a computer program product for generating questions. The computer implemented method comprising obtaining a question, wherein the question comprises one or more elements that define an answer for the question. The method further comprising obtaining the answer. The method further comprises automatically generating, by a processor, a new question based on the question and the answer. The automatic generation comprises determining a variant of the one or more elements, wherein the variant defines the answer, wherein the new question comprises the variant.

Question generator based on elements of an existing question

A method comprising using at least one hardware processor for applying a mapping function to a medical image, to generate a semantic description of a visual finding in the medical image. The mapping function is optionally an MRF (Markov random field)-based, SVM (Support Vector Machine) mapping function.

Automatic generation of semantic description of visual findings in medical images

Machines, systems and methods for character recognition disambiguation are provided. The method comprises selecting a first set of characters that match a first visual profile based on results of a character recognition process applied to target content; selecting a subset of the first set based on criteria associated with at least one of confidence level with which characters grouped in the subset are recognized or fragmentation associated with the characters grouped in the subset; and disambiguating recognition results for the characters grouped in the subset by displaying the characters along with context information, wherein reviewing two or more of the characters on a display screen along with context information associated with said two or more characters allows a human operator to select one or more suspect characters from among the two or more characters.

Efficient verification or disambiguation of character recognition results

Systems and methods for detecting end of a transaction in a computing environment are provided. The method comprises determining a target area in a graphical user environment displayed on a display screen, wherein a change is expected to occur when end of a transaction is reached; masking the target area at least partially to remove content included in the target area that is present before or after the transaction was initiated; monitoring the target area for change in content; and detecting the end of the transaction when the content of the target area has changed.

Recognition techniques to enhance automation in a computing environment

A method, system, and computer program product for computer application analysis are provided. The method for computer application analysis includes monitoring a computer system on which an application to be analyzed is executed and interacted with by a user of the computer system. The monitoring includes: capturing screen data of the application as displayed on a display screen of the computer system including interpreting the screen data using optical character recognition (OCR); and capturing user inputs to the application to input devices of the computer system. The method further includes analyzing the captured screen data and user inputs to generate a summary of the usage of the application.

Computer application analysis

A method for optical character recognition (OCR) verification, the method includes: receiving a first character image that was obtained from applying an OCR process on a document; wherein the first character image is classified, by the OCR, as being associated with a first character; receiving a first character code of a text; replacing the first character code by the first character image; and evaluating a correctness of the OCR based upon a response of a user to a display of the text first character image.

Optical character recognition verification

A method for altering a recognition error correction data structure, the method includes: altering at least one key out of a set of semantically similar keys in response to text appearance probabilities of keys of the set of semantically similar keys to provide an at least one altered key; and replacing the at least one key by the at least one altered key.

Method and computer program product for recognition error correction data

A method for finding a predefined object in an image includes selecting a line belonging to the object, the line having a known stroke width and defining a maximum width and a minimum width that together define a range of widths therebetween that contains the stroke width. A feature in the image is found having a feature width within the range, and the feature is processed to determine whether it is a part of the object.

Growing community of inventors

Haifa, Israel

Ella Barkan