AI-assisted Colorectal Cancer Diagnosis System

About it

The Colorectal Biopsy AI-Assisted Diagnostic System automatically detects and grades colorectal cancer and adenomatous lesions.

It distinguishes adenocarcinoma, adenoma subtypes, and benign polyps, addressing missed serrated lesions and grading challenges.

By reducing analysis time and bias, it enhances diagnostic accuracy and supports adenoma–carcinoma risk assessment.

Accurate Lesion Detection

Optimized to detect high-risk serrated adenomas often missed in routine diagnosis.

Adenoma Subtype Classification

Automatically identifies tubular, villous, and tubulovillous adenomas and quantifies villous components for risk assessment.

Automated Grading & Segmentation

Visually segments lesions and grades low- vs. high-grade intraepithelial neoplasia.

Structured Report Output

Generates reports with adenoma subtype, grade, and heatmap visualization, ready for LIS/PIS integration.

Extensive Training Dataset

Trained on 20,000+ slides covering all colorectal regions and adenoma–carcinoma progression stages.

Proven Clinical Accuracy

Achieves 99% sensitivity and 95% specificity in multi-center validations.

Recognizable Lesion Types
Primary Category Secondary Attribute
Positive Cancer Adenocarcinoma / Signet Ring Cell Carcinoma / Mucinous Adenocarcinoma / Other Cancers (Developing)
High-grade Intraepithelial Neoplasia Serrated Lesion / Tubular Adenoma / Villous Adenoma / Tubulovillous Adenoma
Low-grade Intraepithelial Neoplasia Serrated Lesion / Tubular Adenoma / Villous Adenoma / Tubulovillous Adenoma
Glandular Lesion Changes (Developing)
Negative Acute Inflammation Mild / Moderate / Severe
Chronic Inflammation
Serrated Lesion without Dysplasia
Hyperplastic Polyp

Powering global digital pathology with performance, scale, and trust

The Numbers Behind Our Innovation

0%
99% Sensitivity Ensures accurate detection of colorectal neoplastic lesions across multiple centers.
0+
20000+ Slides ，Comprehensive dataset covering sigmoid colon, rectum, and other anatomical regions.
0%
95% Specificity，Minimizes false positives while maintaining diagnostic precision.
0%
97.2% Accuracy，Confirmed by large-scale validation at Adicon Laboratories and tertiary hospitals.
0%
96.72% Low-Grade Detection Rate , Validated in clinical trials at Wuhan Union Hospital.
0%
89.47% NPV ，Ensures reliable exclusion of negative cases for efficient screening.

Network and GPU Server Requirements

Parameter Category Minimum Requirement Recommended Configuration Remarks
Local Network Bandwidth Between server and client ≥100Mbps Between server and client ≥1Gbps (preferably optical) Core switch supports ≥10Gbps uplink
Network Latency ≤50ms (between LAN nodes) ≤20ms (between LAN nodes) Supports link aggregation (LACP) for improved stability
Network Topology Supports star/tree topology Supports redundancy (dual-core switch) Key nodes (e.g., database server) require dual-network binding
Interface Type Client RJ45 (10/100BASE-T) Server RJ45 (1000BASE-T) + Optical port (optional) Optical interface supports LC/SC connectors, transmission distance ≤5km
Parameter Category Minimum Requirement High-Performance Configuration (e.g., AI Training / Rendering) Remarks
GPU Model NVIDIA 2080Ti ×1 NVIDIA A4000 ×1
GPU Memory 11GB GDDR6 (ECC optional) 16GB HBM2e (ECC required)
GPU Quantity Single GPU per host Single GPU per host
CPU Intel Xeon E-2274G (4 cores, 8 threads, 3.8GHz) Intel Xeon E-2274G (8 cores, 16 threads, 3.8GHz) Main frequency ≥3.0GHz, cache ≥24MB
Memory 32GB DDR4-2666 (ECC) 64GB DDR5-4800 (ECC Registered)
Storage Interface 1×NVMe SSD (PCIe 3.0) 2×NVMe SSD (PCIe 4.0, RAID 0) Supports hot-swap, continuous read/write ≥3000MB/s
Power & Cooling 900W 80+ Gold PSU, air cooling 1600W 80+ Platinum PSU, liquid cooling system
OS Compatibility Supports Ubuntu 22.04 server version Supports Ubuntu 22.04 server version Docker pre-installed (ready for container deployment)