Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

67 results about "Diagnostic modalities" patented technology

Diagnostic Modalities are used to image the identified structure which is of concern. Diagnostic modalities enhance or confirm the diagnosis made by the clinician.

Wireless capsule endoscope-based computer-aided detection system and detection method for pathological changes in small intestine

The invention discloses a wireless capsule endoscope small intestine lesion computer auxiliary detection system and method. At present, the technology of the capsule endoscope in the aspect of intelligent lesion identification and accurate positioning is very limited. The data input module is used for acquiring the video data of the wireless capsule endoscope of the patient, and an image of the capsule endoscope is obtained by extracting a video frame technology; the image preprocessing module is used for preprocessing the image of the wireless capsule endoscope, the small intestine image recognition module is used for recognizing and extracting a small intestine image and an image sequence in the preprocessed capsule endoscope image; the small intestine lesion analysis and positioning module is used for identifying and classifying the small intestine lesion and extracting the specific position of the focus; the user interaction module forms an auxiliary diagnosis result according to the small intestine lesion information and the analysis result of the positioning module, and the doctor can confirm, modify or input the medical advice so as to form a diagnosis report. According to the invention, the practical value of the capsule endoscope in clinic is promoted, so that a more efficient and more standard diagnosis mode is formed.
Owner:HANGZHOU DIANZI UNIV

Diagnosis marker suitable for early-stage esophageal squamous cell cancer diagnosis and screening method of diagnosis marker

The invention discloses a diagnosis marker suitable for an early-stage esophageal squamous cell cancer diagnosis and a screening method of the diagnosis marker. Twenty five kinds of serum metabolic markers and ten relevant metabolic pathways are discovered; through the combination of the twenty five kinds of serum metabolic markers, the diagnosis marker used for an esophagus cancer diagnosis can be obtained. The screening method of the diagnosis marker has high operability; the diagnosis marker can be used for building a diagnosis model; the diagnosis model has the advantages of good effect, high sensitivity and good specificity, is suitable for a late-stage esophagus cancer diagnosis and is also suitable for the early-stage esophagus cancer diagnosis. The diagnosis model built by adopting the diagnosis marker provided by the invention has the advantages that the diagnosis can be realized only through blood sampling; the noninvasive effect is achieved; the cost is low; the modern internal invasive diagnosis mode can be well replaced; the pain of a patient is greatly reduced; in addition, the diagnosis speed is high; convenience is realized; the required time is short; the work efficiency is improved; the early discovery and early treatment of an esophagus cancer can be favorably realized; good clinic use and popularization value is realized.
Owner:SHANDONG RES INST OF TUMOUR PREVENTION TREATMENT

Method for pylorus and ileocecal valve positioning through wireless capsule endoscope images

The invention discloses a method for pylorus and ileocecal valve positioning through wireless capsule endoscope images. When a wireless capsule endoscope is used for examination, the starting point and the stopping point of the small intestine are accurately found so that the workload of a doctor for viewing the images can be reduced, and missed diagnosis is reduced. According to the method, a deep learning thought serves as a technical core, a transfer learning strategy is also used, and a convolution neural network algorithm in a deep learning model is used for building an area image classifier; features of the wireless capsule endoscope images are obtained through automatic learning by means of training of the model, and then an area image identification result sequence is analyzed through an area positioning algorithm, so that pylorus and ileocecal valve positioning in the wireless capsule endoscope images is achieved. The method makes up for the blank of an existing capsule endoscope in the field of intelligent identification and accurate positioning, the working intensity of a doctor is greatly reduced, the working efficiency and the diagnosis rate are improved, the practicalvalue of the capsule endoscope in the clinical diagnosis of digestive tract diseases is further promoted, and a more efficient and more standard diagnosis mode is formed.
Owner:HANGZHOU DIANZI UNIV

Bi-clustering mining and AdaBoost-based tumor classification method

The invention discloses a bi-clustering mining and AdaBoost-based tumor classification method. The method comprises the following steps of: firstly selecting digitalized scoring data of tumor lesion features to construct an original data set, screening features effective for distinguishing benign and malignant tumors from original features according to feature statistic information, mining important tumor diagnosis modes hidden behind the feature scoring data from the feature scoring data by utilizing a bi-clustering algorithm, and determining benign and malignant attributes of the diagnosis modes by adoption of support rate indexes according to benign and malignant priori knowledges, so as to convert locally consistent modes into effective diagnosis rules; constructing a simple weak classifier which is capable of carrying out classification in different feature spaces by adoption of a method of pairwise coupling benign and malignant rules, wherein the weak classifier takes similarity of matching between test samples and the benign and malignant rules as a classification rule; and finally training a high-correctness strong classifier from the weak classifier by adoption of an AdaBoost integration algorithm. The method plays an important role in improving the clinical diagnosis correctness of tumors.
Owner:SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products