Introduction to image analysis and processing

Category

Capabilities

Description

Medical image analysis

COVID-19 computer-aided diagnosis

Analyzes input DICOM images, such as a single 5 mm sequence, for COVID-19. The API accepts only single sequences.

Chest CT lung nodule detection

Performs computer-aided diagnosis of lung nodules on input DICOM images from conventional chest CT scans, such as a single 5 mm sequence. The API accepts only single sequences.

Chest CT registration

Registers chest CT scans of the same patient taken at different times. Input two standard DICOM datasets as the reference image and the image to be registered. The output is an HTTP download path for the registration result.

Coronary artery calcium scoring

Calculates the coronary artery calcium score based on a non-contrast chest CT scan. Input an image in standard DICOM or NIFTI format. The output is the calcium score value and an HTTP download path for the segmentation result.

Medical AI Q&A

Provides answers to common questions and similar questions about pediatric diseases for public health education.

Skin disease detection

Predicts and classifies skin diseases from input natural images of pediatric skin conditions.

Rib fracture detection

Performs computer-aided diagnosis of rib fractures based on chest CT imaging. It outputs the location and type of the fracture.

Non-contrast chest CT screening

Detects and quantitatively analyzes multiple organs and diseases in the chest based on conventional chest CT images. The main features are as follows:

1. Automatically measures the coronary artery calcium score from a conventional chest CT scan.

2. Automatically detects lung nodules and outputs the nodule volume, average grayscale value, and an AI-powered structured report.

3. Automatically segments pneumonia lesions in the lung lobe area and outputs information such as lesion size and pneumonia type.

4. Detects rib fractures and provides the fracture type.

5. Detects enlarged lymph nodes in non-contrast or contrast-enhanced chest CT scans, including mediastinal, hilar, and supraclavicular lymph nodes.

6. Assesses the risk of pancreatic cancer based on an input non-contrast chest CT scan.

Aortic aneurysm and pulmonary hypertension detection

This feature segments the aorta and pulmonary artery from input non-contrast chest CT DICOM image data. It then extracts their centerlines to generate optimal-view images: Stretch CPR, Cross Section, and Straightened CPR. The feature also returns the maximum diameter of each vessel, the vessel's cross-sectional area at 1 mm intervals perpendicular to the centerline, and the positions of these points in the patient coordinate system of the original image.

Lymph node detection

Detects enlarged lymph nodes in non-contrast or contrast-enhanced chest CT scans, including mediastinal, hilar, and supraclavicular lymph nodes.

Pancreatic cancer detection

Assesses the risk of pancreatic cancer based on an input non-contrast chest CT scan.

Multi-organ segmentation

For radiotherapy scenarios, it identifies and segments organs at risk based on input chest CT images.

Esophageal cancer detection

Assesses the risk of esophageal cancer based on an input non-contrast chest CT scan.

Radiotherapy target volume contouring

Performs intelligent target volume contouring based on input non-contrast or contrast-enhanced chest CT scans. Specify the cancer type and target volume type.

Radiotherapy lymphatic station segmentation

Performs lymphatic station segmentation based on input non-contrast or contrast-enhanced chest CT scans. Specify the target region.

Bone mineral density estimation

Performs vertebra localization, labeling, and bone mineral density estimation based on input chest or abdominal CT imaging.

Fatty liver detection

Performs liver and spleen localization and segmentation based on input chest or abdominal CT imaging. It also performs global or local density statistical measurements of the liver and spleen. Based on the measurement results and a deep learning model, it determines the presence and severity of fatty liver disease.

Gastric cancer detection

Detects gastric cancer and non-cancerous lesions from input non-contrast CT scans that cover the stomach, such as chest or abdominal scans.

Liver cancer detection

Detects various types of liver tumors from input non-contrast CT scans that cover the liver.

Cardiovascular disease (CVD) adverse event detection

Based on non-contrast chest or thoracoabdominal CT scans (gated or non-gated), this feature provides quantitative values for 13 indicators, including coronary artery calcium score, aortic calcium score, and epicardial fat. It also provides the probability of the patient experiencing a cardiovascular adverse event.

Colorectal cancer detection

Detects colorectal cancer (CRC) from input non-contrast CT scans that cover the colorectum, such as non-contrast chest or abdominal CT scans.