medical_records_processing · workflow
Accelerating DenseNet-121 medical imaging inference with GPU-native pipeline on MedNIST
Modern medical imaging workflows must process thousands of high-resolution scans rapidly, but CPU-based pipelines are slow and inefficient — cores run at low utilization while I/O stalls and host-to-device data copies add latency.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Data loading and labeling
Image files are read and class labels are assigned from approximately 64K MedNIST JPEGs across 6 classes.
Tools used
DenseNet-121DALIcuDFNVIDIA Tesla T4PyTorch DataLoaderPillowOpenCVpandasFP16NVMLPyTorchcuDNNcuBLAS
Outcome
The GPU-native pipeline achieved 3.3× higher throughput and 2.9× lower batch time versus CPU, with 88% GPU utilization and roughly 40% better energy efficiency measured in images per joule.
Results
Time saved~2.9×
Volume~3.3×
Grounding & classification
Source type: technical build writeup
38 fields verified against source quotes.
computer visionradiology imagemetric backedsource backedtools describedworkflow describedhealthcarecost reductioncycle time reductionthroughput increasetechnical build writeupmedical records processingextract classify route