SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.15063 · 2024

Towards a Comprehensive, Efficient and Promptable Anatomic Structure Segmentation Model using 3D Whole-body CT Scans

arXiv · PDF · Open in the Atlas

Code that ran

4 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.15063.json · badge: /api/ran/2403.15063.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
alibaba-damo-academy/ct-sam3d canonical (classifier label)
classifier basis: census
4 ran · 6 no recorded run
FunctionStatusWhere it lives
gaussian3D Ran
ran, honoured the contract we drafted
alibaba-damo-academy/ct-sam3d/ct_sam/utils/gaussian_target.py
code served (permissive licence) · get_code("6a9e9980bf9e889d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (7, 7, 7) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    'radius': 3,
    'sigma': 2,
    'dtype': torch.float32,
    'device': 'cpu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (7, 7, 7) — shape (7, 7, 7) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_local_maximum Ran
ran; our contract draft was wrong, not the code
alibaba-damo-academy/ct-sam3d/ct_sam/utils/gaussian_target.py
code served (permissive licence) · get_code("4ba1cdcf5b7124b3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 5, dtype family float, shape (2, 1, 4, 3, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small 3D heatmap tensor
# Shape: (batch=2, channels=1, depth=4, height=3, width=5)
heat = torch.rand(2, 1, 4, 3, 5)

# Define arguments for get_local_maximum
ARGS = {
    "heat": heat,
    "kernel": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 5, dtype family float, shape (2, 1, 4, 3, 5) — shape (2, 1, 4, 3, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_topk_from_heatmap Ran
ran; our contract draft was wrong, not the code
alibaba-damo-academy/ct-sam3d/ct_sam/utils/gaussian_target.py
code served (permissive licence) · get_code("84c7ce06c891d321")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct a small heatmap tensor with shape [batch, num_classes, width, height, depth]
# The function unpacks this as: batch, _, width, height, depth = scores.size()
# So we need a 5D tensor
batch_size = 2
num_classes = 4
width = 3
height = 5
depth = 6

# Create random scores tensor with shape [batch, num_classes, width, height, depth]
scores = torch.randn(batch_size, num_classes, width, height, depth)

k = 24

ARGS = {
    "scores": scores,
    "k": k,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
partial_weight_update Ran
ran; our contract draft was wrong, not the code
alibaba-damo-academy/ct-sam3d/ct_sam/utils/network.py
code served (permissive licence) · get_code("b1c4fac402715a6f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned SimpleModel. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Create model instance
model = SimpleModel()

# Create a pretrained state dict with some overlapping keys
pretrained_state = {
    'linear1.weight': torch.randn(3, 4),
    'linear1.bias': torch.randn(3),
    'linear2.weight': torch.randn(2, 3),
    'linear2.bias': torch.randn(2),
    'extra_layer.weight': torch.randn(5, 5),  # This key won't be in model_state
}

ARGS = {
    'model': model,
    'pretrained_state': pretrained_state,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_sam_vit_b Not yet run
unverified (harvested, no recorded run)
alibaba-damo-academy/ct-sam3d/ct_sam/builder.py
code served (permissive licence) · get_code("2f903a1d8b06697f")
How it ran

no invocation recorded.

build_sam_vit_h Not yet run
unverified (harvested, no recorded run)
alibaba-damo-academy/ct-sam3d/ct_sam/builder.py
code served (permissive licence) · get_code("4bfe3eb5a28153f2")
How it ran

no invocation recorded.

build_sam_vit_l Not yet run
unverified (harvested, no recorded run)
alibaba-damo-academy/ct-sam3d/ct_sam/builder.py
code served (permissive licence) · get_code("bdb954e979dda5a5")
How it ran

no invocation recorded.

restv2_base Not yet run
unverified (harvested, no recorded run)
alibaba-damo-academy/ct-sam3d/ct_sam/models/rest_v2.py
code served (permissive licence) · get_code("6c539928d0946d16")
How it ran

no invocation recorded.

restv2_small Not yet run
unverified (harvested, no recorded run)
alibaba-damo-academy/ct-sam3d/ct_sam/models/rest_v2.py
code served (permissive licence) · get_code("ac26a4c6c80c693c")
How it ran

no invocation recorded.

restv2_tiny Not yet run
unverified (harvested, no recorded run)
alibaba-damo-academy/ct-sam3d/ct_sam/models/rest_v2.py
code served (permissive licence) · get_code("0e77f0801a7185b2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Segment anything model (SAM) demonstrates strong generalization ability on natural image segmentation. However, its direct adaptation in medical image segmentation tasks shows significant performance drops. It also requires an excessive number of prompt points to obtain a reasonable accuracy. Although quite a few studies explore adapting SAM into medical image volumes, the efficiency of 2D adaptation methods is unsatisfactory and 3D adaptation methods are only capable of segmenting specific organs/tumors. In this work, we propose a comprehensive and scalable 3D SAM model for whole-body CT segmentation, named CT-SAM3D. Instead of adapting SAM, we propose a 3D promptable segmentation model using a (nearly) fully labeled CT dataset. To train CT-SAM3D effectively, ensuring the model's accurate responses to higher-dimensional spatial prompts is crucial, and 3D patch-wise training is required due to GPU memory constraints. Therefore, we propose two key technical developments: 1) a progressively and spatially aligned prompt encoding method to effectively encode click prompts in local 3D space; and 2) a cross-patch prompt scheme to capture more 3D spatial context, which is beneficial for reducing the editing workloads when interactively prompting on large organs. CT-SAM3D is trained using a curated dataset of 1204 CT scans containing 107 whole-body anatomies and extensively validated using five datasets, achieving significantly better results against all previous SAM-derived models. Code, data, and our 3D interactive segmentation tool with quasi-real-time responses are available at https://github.com/alibaba-damo-academy/ct-sam3d.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.15063")
get_code_for_paper("2403.15063")
have("2403.15063")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.15063.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.15063.svg)](https://syntology.ai/paper/2403.15063)

Connect an agent — have() is free.