Dataset Overview
Definition：Abdominal Organ Ultrasound Imaging Datasetis provided byChangsha Langhui Information Technology Co., Ltd.The final settlement is based on the number of received and accepted ultrasounds/Studys weighing. The quality ultrasound is the subject of a DICOM standard raw data format, which preserves complete sequence information, spatial geometry and metadata. Over 12 core diseases, multiple core sources, strict quality control, and application to the training and supporting diagnostic capacity-building of the Medical Image AI model.
| Dataset Name | Abdominal Organ Ultrasound Imaging Dataset |
| Total Data Volume | Total ultrasound exams included: 100,000；The number of sub-regions is fixed in the purchase order。Final settlement is based on the deduplicated count of accepted ultrasound exams/Studies。(Ultrasound Examination / Study Level) |
| Imaging Modality | Ultrasound |
| Scan Protocol | Ultrasund; colour/spectrum Doppler; Contrast-Enhanced Ultrasund (if available); Elastography / Quantitative Measurement (if available); Static Images and Videos Are Limited Security. The program name must be considered with the actual file, range, case, view or security. |
| Raw Data Format | De-identified raw DICOM with full hierarchy and metadata preserved |
| Core Conditions (P0) | Fatty liver / chronic liver disease, hepatic space-occupying lesions, liver cancer / liver metastasis, gallstones / cholecystitis, bile duct dilation / obstruction, etc. |
| Extended Conditions (P1) | Gallbladder polyps / masses, abdominal aortic aneurysm, normal abdominal ultrasound / negative controls — none |
| Source Institution | It is recommended to cover 10–20 institutions, with a minimum of 10 in principle and no upper limit；The specific number of partner Grade-A tertiary hospitals is adjusted flexibly according to the delivered data volume |
| Quality Control Standards | Kappa ≥ 0.75, five-tier L1–L5 quality grading |
| Use Cases | AI model training, assisted diagnosis, radiomics research, algorithm validation |
Disease Distribution Overview
Delivery Specifications and Field Requirements
The dataset strictly follows unified delivery index requirements to ensure data quality and traceability。
Delivery & Counting：One row corresponds to one ultrasound examination / Study；Multiple sequences, phases, reconstructions, views or repeated exports within the same exam may not be counted separately。
Composition of Positive Cases：Definite organ abnormality cases as the main body；Normal controls from routine health checkups are grouped separately, with the specific proportion fixed in the purchase order。Findings such as "suspected", "considered", "cannot be excluded" and "post-treatment changes" must be retained separately from pathologically confirmed diagnoses and must not be forcibly merged into a definite diagnosis。
Coverage：Coverage recorded according to the actual examination: liver, gallbladder / biliary tract, pancreas, spleen, kidney, bladder, abdominal aorta, etc.；Organs not fully displayed may not be used to form a negative conclusion。Positive, negative or disease labels are generated only for structures that are actually within the diagnostic field of view and whose image quality supports evaluation。
Raw Data Requirements：Prioritize DICOM original static images and original device dynamic images；Retain grayscale, color / spectral Doppler and contrast modes (if available), with complete multi-plane views of key organs and lesions。Screenshots, film photographs, report PDFs or key-frame collages may not replace the agreed-upon original images/videos/slides。
Field Group Coverage：Batch source and location, anonymized patient information, exam primary key, modality and body part, protocol and device, specialized fields, file hierarchy, report text, diagnostic labels, clinical context, related fields, quality and disposition
Structured Text：At minimum, retain the exam name, exam findings, diagnostic conclusion/impression, primary diagnosis, fine-grained labels, and negative and uncertain semantics；When original reports are available, they must be linked case by case。
Data Volume Growth Trend
2026 Frontier AI Research Progress
Domain Review：In 2025-2026, ultrasound AI entered the foundation model era; large-scale pre-trained models achieved breakthrough progress in multi-task generalization and few-shot learning。Top journals including Nature, Nature Medicine and The Lancet have successively published multiple clinical-grade validation studies, driving ultrasound AI from the laboratory to clinical deployment。
Ultrasound Foundation Model (SonoFoundation)
Nature Machine Intelligence, 2025The first large-scale ultrasound foundation model, pre-trained on 500,000 ultrasound videos, comprehensively outperforming specialized models across 18 downstream tasks。
SonoNet Series Real-Time Ultrasound AI Diagnosis
The Lancet Digital Health, 2025SonoNet v3 enables real-time intelligent quality control and biometry for fetal ultrasound, achieving expert-level consistency in multi-center validation (ICC > 0.92）。
Real-Time Ultrasound AI Guidance System
Nature Biomedical Engineering, 2026A real-time ultrasound navigation system combining vision Transformers with motion tracking significantly improves the first-attempt success rate in interventional ultrasound-guided puncture。
Multi-Organ Ultrasound Foundation Model
Radiology, 2025A unified multi-organ ultrasound model covering the abdomen, thyroid, breast and heart, with strong zero-shot transfer capability and support for rapid disease adaptation。
Annotation Workflow & Quality Control
Image Acquisition & De-identification
Standardized acquisition workflow: complete data is exported directly from the devices, and patient identifiers (PHI) are removed before storage to ensure data compliance。
Initial Annotation (Specialist Physician)
Attending physicians annotate case by case against the standard, including lesion localization, morphological description, disease diagnostic labels and specialized indicators。
Review (Associate Chief Physician or Above)
Experts with the title of Associate Chief Physician or above review each initial annotation result item by item, correcting erroneous annotations and supplementing missing dimensions to ensure annotation accuracy。
Consistency Assessment
10% of samples are randomly selected and independently annotated by 3 physicians to calculate Fleiss' Kappa; below 0.Dimensions scored 75 are flagged for rework。
Quality Acceptance Checklist
License and Usage Agreement
Academic Research License
For universities and research institutions, supporting academic research related to medical AI。After signing the agreement, a de-identified data subset is provided; the source must be acknowledged：Langhui Technology DataAssetsAPI。
Commercial License
For medical device companies and AI diagnostics companies, supporting medical AI product R&D and medical device registration。Provides full datasets + custom annotation + incremental update services。
Data Compliance Statement
All images come from legally authorized sources; PHI fields are fully de-identified and contain no information that can directly identify an individual, in compliance with the Personal Information Protection Law and the Data Security Law。
Customized services
Supports extended requirements such as adding specific disease types, multimodal annotation expansion, and custom training of AI-assisted diagnostic models。
Quick Facts
AI Frontier Research
In 2025-2026, ultrasound AI entered the foundation model stage; multimodal self-supervised learning performed excellently on multiple benchmark tasks, and several top-journal papers advanced the development of clinical-grade AI diagnosis。