Fix inference pipeline: normalization, RAS orientation, state_dict check, debug logging

Increase file size limits: upload 1 GB, processing 2 GB

Update processing file size limit to 200 MB for medical imaging volumes

Fix critical issues: 50MB upload limit, report guardrails, T2 experimental status, API security, and indentation errors

Fix shape

Fix: Update remaining spatial priors and pass voxel_spacing to confidence calculation

Aggressive fixes: Higher T1 thresholds (0.60-0.80), stricter spatial priors, volume-based confidence penalty, reject <1000ml

Fix: Correct indentation errors and ensure PROCESSING_LOCK is threading.Lock()

Fix critical bugs: threading.Lock, NIfTI load once, z-axis calculations, confidence defaults, path guards

Fix preprocessing indentation error

Complete QC pipeline

Added advanced guards

Normalize Intensityd

Fixed preprocessing

Add T1 threshold 0.58, size-aware auto-tune, enhanced edge cleanup, centroid/Z-span guards, confidence score, remove emojis

Fix accuracy: match training preprocessing and use 0.5 threshold by default

Enhance medical report with detailed findings, clinical context, and quality assessment

Fix preprocessing, threshold, and post-processing for better predictions

Optimize torch.compile: default to reduce-overhead for faster first run, add compilation time warnings

Speed optimizations: GPU aggregation, max-autotune compile, increased batch/ROI, GPU utilization monitoring, quality guardrails

Add liver segmentation refinement pipeline: connected components, morphological cleanup, smoothing

Performance optimizations: warm-up, channels-last, TF32, GPU monitoring, memory-mapped I/O

please work

Major performance and stability improvements: disable torch.compile by default, GPU preprocessing, ROI auto-adjustment, timeout mechanism, validation, cuDNN benchmarking, version logging, concurrency limits

Refactor app.py into modular structure: config, model, processing, inference, and app modules