readme

Signed-off-by: Can-Zhao <[email protected]>

generation/maisi/README.md

@@ -125,17 +125,18 @@ Network definition is stored in [./configs/config_maisi.json](./configs/config_m
 
 ### 2. Model Inference
 #### Inference parameters:
-The information for the inference input, like body region and anatomy to generate, is stored in [./configs/config_infer.json](./configs/config_infer.json). Please feel free to play with it. Here are the details of the parameters.
-
-- `"num_output_samples"`: int, the number of output image/mask pairs it will generate.
-- `"spacing"`: voxel size of generated images. E.g., if set to `[1.5, 1.5, 2.0]`, it will generate images with a resolution of 1.5x1.5x2.0 mm.
-- `"output_size"`: volume size of generated images. E.g., if set to `[512, 512, 256]`, it will generate images with size of 512x512x256. They need to be divisible by 16. If you have a small GPU memory size, you should adjust it to small numbers. Note that `"spacing"` and `"output_size"` together decide the output field of view (FOV). For eample, if set them to `[1.5, 1.5, 2.0]`mm and `[512, 512, 256]`, the FOV is 768x768x512 mm. We recommend the FOV in x and y axis to be at least 256mm for head, and at least 384mm for other body regions like abdomen. There is no such restriction for z-axis.
-- `"controllable_anatomy_size"`: a list of controllable anatomy and its size scale (0--1). E.g., if set to `[["liver", 0.5],["hepatic tumor", 0.3]]`, the generated image will contain liver that have a median size, with size around 50% percentile, and hepatic tumor that is relatively small, with around 30% percentile. The output will contain paired image and segmentation mask for the controllable anatomy.
-- `"body_region"`: If "controllable_anatomy_size" is not specified, "body_region" will be used to constrain the region of generated images. It needs to be chosen from "head", "chest", "thorax", "abdomen", "pelvis", "lower".
-- `"anatomy_list"`: If "controllable_anatomy_size" is not specified, the output will contain paired image and segmentation mask for the anatomy in "./configs/label_dict.json".
-- `"autoencoder_sliding_window_infer_size"`: in order to save GPU memory, we use sliding window inference when decoding latents to image when `"output_size"` is large. This is the patch size of the sliding window. Small value will reduce GPU memory but increase time cost. They need to be divisible by 16. If GPU memory is large enough, please choose larger value of this parameter.
-- `"autoencoder_sliding_window_infer_overlap"`: float between 0 and 1. Large value will reduce the stitching artifacts when stitching patches during sliding window inference, but increase time cost. If you do not observe seam lines in the generated image result, you can use a smaller value to save inference time.
-- `"autoencoder_tp_num_splits"`: int, chosen from [1,2,4,8,16]. In order to save GPU memory, we use tensor parallel in the autoencoder. Large value will reduce GPU memory. If GPU memory is large enough, please choose smaller value of this parameter.
+The information for the inference input, such as the body region and anatomy to generate, is stored in [./configs/config_infer.json](./configs/config_infer.json). Feel free to experiment with it. Below are the details of the parameters:
+
+- `"num_output_samples"`: An integer specifying the number of output image/mask pairs to generate.
+- `"spacing"`: The voxel size of the generated images. For example, if set to `[1.5, 1.5, 2.0]`, it generates images with a resolution of 1.5x1.5x2.0 mm.
+- `"output_size"`: The volume size of the generated images. For example, if set to `[512, 512, 256]`, it generates images of size 512x512x256. The values must be divisible by 16. If GPU memory is limited, adjust these to smaller numbers. Note that `"spacing"` and `"output_size"` together determine the output field of view (FOV). For example, if set to `[1.5, 1.5, 2.0]` mm and `[512, 512, 256]`, the FOV is 768x768x512 mm. We recommend the FOV in the x and y axes to be at least 256 mm for the head and at least 384 mm for other body regions like the abdomen. There is no restriction for the z-axis.
+- `"controllable_anatomy_size"`: A list specifying controllable anatomy and their size scale (0–1). For example, if set to `[["liver", 0.5], ["hepatic tumor", 0.3]]`, the generated image will contain a liver of median size (around the 50th percentile) and a relatively small hepatic tumor (around the 30th percentile). The output will include paired images and segmentation masks for the controllable anatomy.
+- `"body_region"`: If `"controllable_anatomy_size"` is not specified, `"body_region"` will constrain the region of the generated images. It must be chosen from `"head"`, `"chest"`, `"thorax"`, `"abdomen"`, `"pelvis"`, or `"lower"`. Please set a reasonable `"body_region"` for the given FOV determined by `"spacing"` and `"output_size"`. For example, if FOV is only 128mm in z-axis, we should not expect `"body_region"` to contain all of [`"head"`, `"chest"`, `"thorax"`, `"abdomen"`, `"pelvis"`, `"lower"`].
+- `"anatomy_list"`: If `"controllable_anatomy_size"` is not specified, the output will include paired images and segmentation masks for the anatomy listed in `"./configs/label_dict.json"`.
+- `"autoencoder_sliding_window_infer_size"`: To save GPU memory, sliding window inference is used when decoding latents into images if `"output_size"` is large. This parameter specifies the patch size of the sliding window. Smaller values reduce GPU memory usage but increase the time cost. The values must be divisible by 16. If GPU memory is sufficient, select a larger value for this parameter.
+- `"autoencoder_sliding_window_infer_overlap"`: A float between 0 and 1. Larger values reduce stitching artifacts when patches are stitched during sliding window inference but increase the time cost. If you do not observe seam lines in the generated image, you can use a smaller value to save inference time.
+- `"autoencoder_tp_num_splits"`: An integer chosen from `[1, 2, 4, 8, 16]`. Tensor parallelism is used in the autoencoder to save GPU memory. Larger values reduce GPU memory usage. If GPU memory is sufficient, select a smaller value for this parameter.
+
 
 
 #### Recommended spacing for different output sizes: