ihcinfer

Fast, patch-based IHC whole-slide inference — powered by DeepLIIF.
From IHC glass slide to cell-counting CSVs, heatmaps, and visual overlays — in one command.

中文 · What's New · Quick Start · Docs · Benchmarks

---

📰 What's New

v0.2.1

• 🖼️ MIRAX (.mrxs) support — tissue segmentation now suppresses black out-of-scan regions; thumbnails and overlays are cropped to the scanned bounds so tissue fills the frame.
• 🔍 Better thumbnail quality for bounded slides — OpenSlideReader exposes bounds; read_slide_thumbnail upscales before cropping when bounds are present.
• 📝 Renamed thumbnail output — WSI thumbnail is now saved as wsi_thumbnail.jpg instead of he_thumbnail.jpg.
• 🎚️ IHC background tuning — TissueSegmenter gains a black_v_thresh parameter to filter dark scanner background in IHC mode.

v0.2.0

• 🚀 Unified ihc CLI — one command for tissue_seg, patch_infer, and infer.
• 🧫 IHC Tissue Segmentation — default ihc mode optimized for immunohistochemistry backgrounds; he mode for H&E.
• ⚡ Scoring-only Fast Path — skip intermediate PIL images during WSI inference to lower memory and boost throughput.
• ⬇️ Automatic Model Download — the DeepLIIF TorchScript model is downloaded from Zenodo the first time model_dir is omitted.
• 🧩 Cross-chunk Batch Tiling — large slides are read in chunks and patches are batched across chunk boundaries for better GPU utilization.

---

ihcinfer is a lightweight Python library for batch immunohistochemistry (IHC) inference on SVS / KFB whole-slide images and PNG / JPEG patches. It reorganizes patch buffering, chunk tiling, tissue-mask pre-filtering, and a scoring-only fast path on top of DeepLIIF's TorchScript model, while exposing both a Python API (IHCAnalyzer) and a command-line tool (ihc).

---

✨ Core Features

	Feature	Description
🔬	Whole-slide image support	Native SVS / KFB reading via OpenSlide and custom readers.
🧩	Patch input	Batch inference on PNG / JPEG patches or directories.
⚡	Batch GPU inference	Cross-chunk patch buffer improves GPU utilization on large slides.
📊	Quantitative outputs	Per-patch total / positive cell counts and positive ratios as CSV + coordinates.
🗺️	Visual outputs	Heatmaps, H&E thumbnails, overlays, region / patch samples.
🧠	Automatic model loading	DeepLIIF model auto-downloaded from Zenodo when model_dir is omitted.
🧫	Tissue segmentation	Standalone ihc / he tissue masks, no model required.
🚀	Dramatic speedups	Up to 14.79× faster than original DeepLIIF for the full GPU pipeline.

---

🧑‍🔬 What Can You Do With It?

🩺 Pathologist / Researcher — Quantify a whole IHC slide

ihc infer \
  --slide_path "path/to/CD3.svs" \
  --output_dir ./ihc_outputs \
  --gpu_ids 0 \
  --batch_size 8

Produces patch_scoring.csv, heatmap.jpg, and overlay.jpg for downstream statistical analysis.

🧬 Bioinformatician — Integrate IHC scoring into a pipeline

from ihcinfer import IHCAnalyzer
import pandas as pd

analyzer = IHCAnalyzer(gpu_ids=[0], batch_size=16)
result = analyzer.infer_wsi(
    slide_path="path/to/slide.svs",
    output_dir="./outputs",
)

df = pd.read_csv(result.csv_path)

WSIResult exposes paths to the CSV, heatmap, thumbnail, overlay, and sample directories directly.

💻 Developer — Embed tissue segmentation or patch inference

from ihcinfer import segment_tissue

mask = segment_tissue("slide.svs", mode="ihc")
print(mask.mask.shape)

Patch-level workflow: ihc patch_infer --input patch.png --output_dir ./out.

🔒 Offline / HPC User — Disable auto-download and use a local model

export IHCINFER_MODEL_DIR="/path/to/DeepLIIF_Latest_Model"
ihc infer --slide_path slide.svs --output_dir ./out --model_dir "$IHCINFER_MODEL_DIR"

In Python, set auto_download=False.

---

📋 Supported Platforms & Inputs

Platform	Python	Notes
Linux	3.10+	Primary development and test platform.
Windows	3.10+	OpenSlide binaries installed automatically via openslide-bin.
macOS	3.10+	Requires OpenSlide to be installed on the system.

Input type	Formats	Usage
Whole-slide images	SVS, KFB	ihc infer, ihc tissue_seg, IHCAnalyzer.infer_wsi()
Patch images	PNG, JPEG	ihc patch_infer, IHCAnalyzer.infer_patches()

Model: DeepLIIF TorchScript model (~3 GB). It is downloaded automatically from Zenodo the first time model_dir is omitted, or you can point to a local copy.

---

⚡ 30-Second Quick Start

# Install
pip install ihcinfer

# 1. Tissue segmentation (no model required)
ihc tissue_seg --input "slide.svs" --output_dir ./tissue_mask --overlay

# 2. Patch inference
ihc patch_infer --input patch.png --output_dir ./patch_outputs

# 3. Whole-slide IHC inference
ihc infer --slide_path slide.svs --output_dir ./ihc_outputs --gpu_ids 0

🐍 Prefer the Python API? Click to expand

from ihcinfer import IHCAnalyzer

analyzer = IHCAnalyzer(
    model_dir="/path/to/DeepLIIF_Latest_Model",  # omit to auto-download
    gpu_ids=[0],
    batch_size=16,
)

result = analyzer.infer_wsi(
    slide_path="/path/to/slide.svs",
    output_dir="/path/to/output",
)

print(result.csv_path)
print(result.heatmap_path)
print(f"Region samples: {len(result.region_sample_paths) // 2}")
print(f"Patch samples: {len(result.patch_sample_dirs)}")

---

🐍 Python API

IHCAnalyzer is the unified entry point for most users:

from ihcinfer import IHCAnalyzer

analyzer = IHCAnalyzer(gpu_ids=[0], batch_size=16)

# Whole-slide inference
result = analyzer.infer_wsi("slide.svs", output_dir="./outputs")

# Patch inference
patch_result = analyzer.infer_patches(["p1.png", "p2.png"], output_dir="./patch_outputs")

# Tissue segmentation
mask = analyzer.segment_tissue("slide.svs", mode="ihc")

---

🚀 Why ihcinfer?

Metric	Original DeepLIIF	ihcinfer	Speedup
Full patch pipeline (CPU, 4 patches)	28.54 s	19.50 s	1.46×
Inference only (GPU)	1.75 s	0.55 s	3.17×
Full patch pipeline (GPU)	10.21 s	0.69 s	14.79×
WSI end-to-end (1453 patches, GPU, estimated)	~10 min	~4 min	~2.5–3×

Test environment: 6× NVIDIA RTX 3090 / 24 GiB. Reproduction scripts are in benchmarks/.

Charts generated by benchmarks/plot_benchmarks.py from the table above.

---

🏗️ Pipeline Architecture

graph LR
    A[WSI: SVS / KFB] --> B[Tissue Segmentation<br/>ihc / he mode]
    B --> C[Chunked Patch Tiler]
    C --> D[DeepLIIF Batch Inference]
    D --> E[Cell Scoring]
    E --> F[CSV + Heatmap]
    E --> G[H&E Thumbnail + Overlay]
    E --> H[Region / Patch Samples]

Loading

---

📚 Documentation & Resources

Resource	Link	Description
Example scripts	examples/	Patch inference, WSI inference, and tissue-segmentation examples
CLI details	examples/README.md	ihc command and subcommand reference
Benchmarks	benchmarks/	Reproducible comparisons against original DeepLIIF

---

🛠️ CLI Reference

ihc --help

# Subcommands
ihc tissue_seg --input <slide> --output_dir <dir> [--overlay] [--mode ihc|he]
ihc patch_infer --input <patch_or_dir> --output_dir <dir> [--model_dir <dir>]
ihc infer --slide_path <slide> --output_dir <dir> [--gpu_ids 0] [--batch_size 8]

---

🔧 Advanced Usage

from ihcinfer.inference import PatchInference, RegionInference
from ihcinfer.models import DeepLIIFModel
from ihcinfer.prep import Tiler, TissueSegmenter, segment_tissue
from ihcinfer.readers import create_reader
from ihcinfer.scoring import compute_scoring, extract_cells
from ihcinfer.outputs import build_patch_output, save_patch_output, build_heatmap

---

📈 Benchmarks

All numbers can be reproduced with the scripts in benchmarks/:

# Patch-level comparison (original DeepLIIF repo must be on PYTHONPATH)
PYTHONPATH=/path/to/DeepLIIF uv run python benchmarks/bench_patch_vs_original.py --device cuda:0

# Region-level comparison
PYTHONPATH=/path/to/DeepLIIF uv run python benchmarks/bench_region_inference.py

# WSI 50-patch comparison
PYTHONPATH=/path/to/DeepLIIF uv run python benchmarks/bench_wsi_50_vs_original.py

# Full IHC WSI pipeline timing
uv run python examples/infer_ihc.py \
  --slide_path /path/to/slide.svs \
  --output_dir ./ihc_outputs \
  --gpu_ids 0 --batch_size 8 \
  --patch_size 512 --region_size 2048

---

🤝 Contributing

Issues and PRs are welcome.

---

📄 License

This project is licensed under the MIT License.