ANTSJOINTFUSION(1)

✨ NAME ✨

Heyy bestie, meet antsJointFusion 🦋 It's part of the ANTS registration suite 💖

---

✨ DESCRIPTION ✨

💅 COMMAND 💅

antsJointFusion

okay so antsJointFusion is an image fusion algorithm made by Hongzhi Wang and Paul Yushkevich, and it literally won segmentation challenges at MICCAI 2012 and MICCAI 2013 🏆 the way that's so iconic 😭 The original label fusion framework got extended to handle intensities by Brian Avants 🧚 This version is based on Paul's original ITK-style implementation and Brian's ANTsR implementation 🌈

The receipts (bestie, you need to read these 🤓📚):

• 1) H. Wang, J. W. Suh, S. Das, J. Pluta, C. Craige, P. Yushkevich, Multi-atlas segmentation with joint label fusion IEEE Trans. on Pattern Analysis and Machine Intelligence, 35(3), 611-623, 2013.
• 2) H. Wang and P. A. Yushkevich, Multi-atlas segmentation with joint label fusion and corrective learning--an open source implementation, Front. Neuroinform., 2013.

---

🎀 OPTIONS 🎀

• -d, --image-dimensionality 2/3/4 — 🌸 Forces the image to be treated as a specified-dimensional image. If you don't set it, the program tries to figure out the dimensionality from the input image on its own 🙈
• -t, --target-image targetImage — 🎯 The target image (or multimodal target images) that's assumed to be aligned to a common image domain. Multimodal form: [targetImageModality0,targetImageModality1,...,targetImageModalityN]
• -g, --atlas-image atlasImage — 🗂️ The atlas image (or multimodal atlas images) that's assumed to be aligned to a common image domain. Multimodal form: [atlasImageModality0,atlasImageModality1,...,atlasImageModalityN]
• -l, --atlas-segmentation atlasSegmentation — ✂️ The atlas segmentation images. For label fusion, the number of segmentations you pass has to match the number of atlas image sets, no cap 💯
• -a, --alpha 0.1 — 🧪 A regularization term added to matrix Mx before calculating the inverse. Default = 0.1
• -b, --beta 2.0 — 📈 The exponent that maps intensity difference to the joint error. Default = 2.0
• -c, --constrain-nonnegative (0)/1 — 🔒 Constrains the solution to non-negative weights. Default is 0
• -p, --patch-radius 2 — 🩹 The patch radius for similarity measures, with the form 2x2x2. Default = 2x2x2
• -m, --patch-metric (PC)/MSQ — 🔍 The metric used to find the most similar neighborhood patch. You can pick Pearson's correlation (PC) or mean squares (MSQ). Default = PC (Pearson correlation) 💜
• -s, --search-radius 3 — 🔭 The search radius for similarity measures, which can be 3x3x3 or an image like 3x3x3 searchRadiusMap.nii.gz. Default = 3x3x3. Lowkey the cool part: you can also give it an image where each voxel's value sets the isotropic search radius at that voxel ✨
• -e, --exclusion-image label[exclusionImage] — 🚫 Specifies an exclusion region for the given label
• -x, --mask-image maskImageFilename — 🎭 If you specify a mask image, fusion only happens inside the mask region
• -o, --output labelFusionImage — 🎬 The output is the intensity and/or label fusion image. The full form is intensityFusionImageFileNameFormat [labelFusionImage,intensityFusionImageFileNameFormat,<labelPosteriorProbabilityImageFileNameFormat>,<atlasVotingWeightImageFileNameFormat>]. The extra optional outputs are the label posterior probability images and the atlas voting weight images 🦋
• --version — 🏷️ Gets the version information
• -v, --verbose (0)/1 — 🗣️ Verbose output
• -h — 🙋 Prints the help menu (short version)
• --help — 🆘 Prints the help menu. <VALUES>: 1

---

That's all, bestie 🫶 This was antsJointFusion 2.6.4+dfsg, December 2025 🌈 stay iconic and go fuse some labels 💅✨