The DOI matches its Crossref record; 105 of the 105 references it cites were found in a registry or an index; 2 of the 31 sources its claims cite were checked for support.
Segment anything model for medical images?
Open accessAbstract
The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging because of the complex modalities, fine anatomical structures, uncertain and complex object boundaries, and wide-range object scales. To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks. We comprehensively analyzed different models and strategies on the so-called COSMOS 1050K dataset. Our findings mainly include the following: (1) SAM showed remarkable performance in some specific objects but was unstable, imperfect, or even totally failed in other situations. (2) SAM with the large ViT-H showed better overall performance than that with the small ViT-B. (3) SAM performed better with manual hints, especially box, than the Everything mode. (4) SAM could help human annotation with high labeling quality and less time. (5) SAM was sensitive to the randomness in the center point and tight box prompts, and may suffer from a serious performance drop. (6) SAM performed better than interactive methods with one or a few points, but will be outpaced as the number of points increases. (7) SAM's performance correlated to different factors, including boundary complexity, intensity differences, etc. (8) Finetuning the SAM on specific medical tasks could improve its average DICE performance by 4.39% and 6.68% for ViT-B and ViT-H, respectively. Codes and models are available at: https://github.com/yuhoo0302/Segment-Anything-Model-for-Medical-Images. We hope that this comprehensive report can help researchers explore the potential of SAM applications in MIS, and guide how to appropriately use and develop SAM.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
The paper builds COSMOS 1050K, a large medical segmentation benchmark from 53 public datasets, and comprehensively evaluates the Segment Anything Model (SAM) across modalities, objects, prompt strategies, and model sizes. SAM is highly variable in medical image segmentation—strong on some targets but unstable or failing on others—while box prompts, larger ViT-H, and task-specific finetuning improve performance.
Key findings
- SAM’s performance was unstable across medical objects: remarkable for some, but imperfect or totally failed in others. Manual prompts outperformed Everything mode, and box prompts were best; adding a point to a box did not obviously help (ViT-B DICE 0.49% ↓, ViT-H DICE 0.06% ↓). Increasing point prompts improved DICE from 56.02% to 63.81% for ViT-B and from 56.78% to 71.61% for ViT-H.
- ViT-H generally outperformed ViT-B. Under Everything mode, ViT-H exceeded ViT-B by 7.47% DICE and had 10.61 pixels lower HD. Modality-wise, SAM achieved the highest average DICE on X-ray for both models; histopathology, colonoscopy, and DW MRI also reached >90% DICE, while 6 (ViT-B) and 7 (ViT-H) modalities had DICE between 80 and 90 but with large standard deviations.
- SAM was sensitive to prompt randomness: for one positive point, DICE dropped by 2.67%, 7.38%, and 14.62% as shifting increased; for one box, shifts of 20–30 pixels caused a 24.11% decrease, and one box plus one point caused a 29.93% decrease. In interactive comparison, SAM beat FocalClick and SimpleClick with one or a few points but was outpaced as points increased, performing worse at 10 points.
- Finetuning SAM on specific medical tasks improved average DICE by 4.39% for ViT-B and 6.68% for ViT-H; 32/45 objects improved for ViT-B and 37/45 for ViT-H. DICE showed moderate correlation with Fourier order and intensity difference, weak correlation with size, and no correlation with modality or aspect ratio.
Methods
- The authors collected and standardized 53 public datasets into COSMOS 1050K: 18 modalities, 84 objects, 125 object-modality paired targets, 1,050,311 2D images/slices (1,003,809 slices from 8,653 3D volumes and 46,502 standalone 2D images), and 6,033,198 masks.
- They evaluated SAM with ViT-B (91M parameters, 12 transformer layers) and ViT-H (636M parameters, 32 transformer layers) under six strategies: S1 Everything; S2 one positive point; S3 five positive points; S4 five positive and five negative points; S5 one box; S6 one box and one positive point. Metrics were DICE, JAC, and HD, with a mask-matching mechanism; Spearman partial correlation analyzed 191,779 anatomical structures for size, aspect ratio, intensity difference, modality, and boundary complexity via Elliptical Fourier Descriptors/Fourier order.
- Finetuning used 45 common objects with box prompts, frozen image and prompt encoders, and only the mask decoder adjusted for 20 epochs at learning rate 1e-4 and batch size 2. A separate annotation study involved three doctors, 100 images, 55 objects, 620 masks, and 9 modalities, and SAM was compared with FocalClick and SimpleClick.
Limitations
- The paper states that SAM is unstable in medical image segmentation, has weak point-based multi-round iteration capability, is sensitive to prompt randomness, cannot output object categories/semantics, and was trained on natural images without medical data. It also notes that finetuning decreased performance for objects with small numbers, RGB color coding, etc., requiring more careful task-specific finetuning.
- Evident from the text: the evaluation is 2D-only, with 3D/4D data converted to 2D slices; the dataset excludes extremely small objects, objects that become significantly separated across slices, and discrete structures such as some histopathology and lung trachea trees.
- Evident from the text: the main paper presents detailed performance for only 40 objects, with full results in supplementary materials, and the text notes that SAM’s text prompt had not been released in the official repository at the time.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
58 Own result · 24 Own interpretation · 19 No basis given · 18 Not checked yet · 5 Own method · 1 Partly supported · 1 Not supported · accuracy not yet measured
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Most previous studies (Ji et al., 2023a; Mazurowski et al., 2023; Zhou et al., 2023) evaluated SAM with limited or even only one type of testing mode / strategy.”
What the sources say
- Not checked yetcites Ji et al., 2023a
- Disputedcites Mazurowski et al., 2023 sourceExperimental — accuracy not yet measured
Section 2.2 (Experiments) describes a thorough evaluation using non-iterative prompts, iterative prompts, and segment-everything mode, including five non-iterative prompting strategies. This paper therefore contradicts its use as an example of a study that evaluated SAM with limited or only one testing strategy. (LLM, conf=0.90)
Checked by a reasoning model — may be wrong.
- Not checked yetcites Zhou et al., 2023
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Thus, the correlation between SAM's segmentation performance and medical objects' attributes has not been conducted carefully (He et al., 2023; Mazurowski et al., 2023; Ma and Wang, 2023).”
What the sources say
- Not checked yetcites He et al., 2023
- Partly supportedcites Mazurowski et al., 2023 sourceExperimental — accuracy not yet measured
Section 3.5 examines the relationship between SAM performance and object size, so the paper does not support a blanket claim that correlations with object attributes have gone unexamined. It does acknowledge a limitation: its correlation analysis uses dataset-average object sizes and does not consider variation within datasets. The broader judgment that these correlations have not been studied carefully is not established by this paper. (LLM, conf=0.78)
- Not checked yetcites Ma and Wang, 2023
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks.”
- Also stated in: § 1.2. SAM in Medical Image Analysis · p. 5 · plain
“we build a large medical image dataset named COSMOS 1050K , including 1050 K images with 18 different modalities (see Fig. 1) and 84 objects ( e.g., anatomical structures, lesions, cells, tools, etc.), to cover the entire body (see Fig. 2).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 1.2. SAM in Medical Image Analysis · p. 5 · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks.”
- Also stated in: § 2.2. Dataset Preprocessing Specification · p. 7 · plain
“In total, COSMOS 1050K consists of 1,050,311 2D images or slices, with 1,003,809 slices originating from 8,653 3D volumes and 46,502 being standalone 2D images.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 2.2. Dataset Preprocessing Specification · p. 7 · plain
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“SAM was sensitive to the randomness in the center point and tight box prompts, and may suffer from a serious performance drop.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SAM performed better than interactive methods with one or a few points, but will be outpaced as the number of points increases.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SAM performed better with manual hints, especially box, than the Everything mode.”
- Also stated in: § 5. Conclusion · p. 19 · plain
“3) SAM performed better with manual hints, especially box, than the Everything mode.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5. Conclusion · p. 19 · plain
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“SAM could help human annotation with high labeling quality and less time.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“SAM performed better than interactive methods with one or a few points, but will be outpaced as the number of points increases.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Finetuning the SAM on specific medical tasks could improve its average DICE performance by 4.39% and 6.68% for ViT-B and ViT-H , respectively.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 25
- Probably not a substantial claim. 17
- The quote only partly states this claim. 1
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SAM showed remarkable performance in some specific objects but was unstable, imperfect, or even totally failed in other situations.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In total, COSMOS 1050K consists of 1,050,311 2D images or slices, with 1,003,809 slices originating from 8,653 3D volumes and 46,502 being standalone 2D images.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In total, COSMOS 1050K consists of 1,050,311 2D images or slices, with 1,003,809 slices originating from 8,653 3D volumes and 46,502 being standalone 2D images.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While for the manual prompt encoding and mask decoding ( S 2 -S 6), the reference times of different models and strategies are similar and less than 0.01s.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“There are 6 ( ViTB ) and 7 ( ViT-H ) modalities with DICE performance between 80 and 90, but most of them have large standard deviations.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The ground-truth masks used for evaluation accurately represent the true segmentation targets.
- Rests on an assumption: The selected datasets and anatomical structures are representative of medical images, so the evaluation results can provide general guidance.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“See BrainTumor in Table 2 and 3, its performance ranges from 71.76% to 77.74% in DICE and 13.02 pixels to 15.35 pixels in HD.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The ground-truth masks used for evaluation accurately represent the true segmentation targets.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SAM performs worse in the remaining modalities, and the results are also more unstable.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The ground-truth masks used for evaluation accurately represent the true segmentation targets.
- Rests on an assumption: The selected datasets and anatomical structures are representative of medical images, so the evaluation results can provide general guidance.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Accordingly, the image embeddings could be reused to relieve the computational burden of the inference pipeline. Thereby, the overall efficiency of the SAM testing could be improved by nearly n times.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The image embeddings computed once can be reused across different testing strategies for the same image without affecting segmentation results.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We observed that the process of image embedding extraction was time-consuming.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SAM with a box prompt yields the best performance, while adding one point to the box will not bring obvious changes (ViT-B: DICE 0.49% ↓ , ViT-H: DICE 0.06% ↓ ).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The ground-truth masks used for evaluation accurately represent the true segmentation targets.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“SAM generated multiple binary masks for each input image, but not all of them included the corresponding object.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“When different testing strategies were applied, only the corresponding npy files needed to be loaded, which significantly improved the testing efficiency (approximately n × ).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Rests on an assumption: The official GitHub implementation of SAM is correct and faithful.
- Rests on an assumption: The image embeddings computed once can be reused across different testing strategies for the same image without affecting segmentation results.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For the point prompts ( S 2 -S 4), adding more points will bring stable performance improvement (ViTB: DICE from 56.02% to 63.81%, ViT-H: DICE from 56.78% to 71.61%).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The ground-truth masks used for evaluation accurately represent the true segmentation targets.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can be observed from Fig. 6 that, under Everything mode ( S 1 ), ViT-H exceeds ViT-B with 7.47% at DICE and is 10.61 pixels lower than ViT-B on HD.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The ground-truth masks used for evaluation accurately represent the true segmentation targets.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The performance of objects with small numbers, RGB color coding, etc., decreases.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For S 2 (single point), the DICE performance dropped by 2.67%, 7.38%, and 14.62% as the shifting level increased.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Our study also preliminarily verified that SAM can greatly shorten the annotation time and improve the annotation quality.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“With the increase in the number of point prompts ( S 3 and S 4), the decline of DICE could be alleviated, and the stability of the model could be improved.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Based on the DICE results, our conclusion is that: 1) SAM outperformed FocalClick and SimpleClick in the first interaction with a single point; 2) As iterations progressed, SAM's performance increased slowly, or even declined, while the performance of the interactive method could be improved steadily; 3) Using 10 points, SAM performed worse than the interactive methods.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The selected 10 typical organs/tumors are representative of medical segmentation tasks for comparing SAM with interactive methods.
In the paper
“Notably, the text prompt has not been released yet on the official GitHub repository 4 .”
What the sources say
- Not checked yetcites [4] Bernal, 2015, WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians, Comput. Med. Imaging Graph. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Thus, we conducted a fair comparison by limiting the image size to 256 × 256 and setting the number of targets to 1.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Retain slices with the sum of the pixel values of their labels greater than 50 for any 3D image and label volumes. This ensures that each slice has the corresponding correct label.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Since the box actually tells the exact location of the target and also its potential intensity features given the limited region. However, points only represent the part features of the target, which can lead to confusion.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The ground-truth masks used for evaluation accurately represent the true segmentation targets.
In the paper
“As the Fourier order (FO) increases, the contour decoded from the Fourier series gets closer to the original contour (see Fig. 12)”
What the sources say
- Not checked yetcites Kuhl and Giardina, 1982
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“While evaluating SAM in medical images, one study used six medical datasets and found that there is no obvious winner among ViT-B , ViT-L , and ViT-H (Mattjie et al., 2023).”
What the sources say
- Not checked yetcites Mattjie et al., 2023
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“In Kirillov et al. (2023), ViT-H shows substantial performance improvements over ViT-B . However, the former requires multiplied testing time due to its increased complexity.”
What the sources say
- Not checked yetcites Kirillov et al. (2023)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Compared to the point prompt, the box prompt contains more region information about the object. Thus, it can better guide SAM with different models to achieve better segmentation performance.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
- Rests on an assumption: The ground-truth masks used for evaluation accurately represent the true segmentation targets.
In the paper
“It is noted that SAM can only find multiple targets in the image, without outputting their detailed categories (i.e., single-label: object or not).”
What the sources say
- Not checked yetcites Kirillov et al. (2023)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“SAM diverges from traditional segmentation frameworks by introducing a novel promptable segmentation task , which is supported by a flexible prompting-enabled model architecture and vast and diverse sources of training data .”
What the sources say
- Not checked yetcites Kirillov et al. (2023)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The above strategy can ensure the repeatability of the experiments.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We further established a unified rule for point selection to ensure randomness, repeatability, and accuracy.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Thus, for a fair comparison, we test the one-round interaction performance of SAM under the above five prompt strategies ( S 2 -S 6 ).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This can simply be extended to other multi-strategy testing scenarios of SAM.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Rests on an assumption: The image embeddings computed once can be reused across different testing strategies for the same image without affecting segmentation results.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“1) SAM showed remarkable performance in some specific objects but was unstable, imperfect, or even totally failed in other situations.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“They shorten the annotation time to three weeks with the help of multiple pre-trained segmentation models for generating pseudo labels, and other useful strategies.”
What the sources say
- Not checked yetcites Qu et al., 2023
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, most medical images are gray-scale, with unclear and complex object boundaries, similar back- and fore-ground, and wide-range image size (especially containing some very small objects).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
In the paper
“The training dataset of SAM, i.e., SA-1B 5 contains 11 million photos, including natural locations, objects, and scenes, but without any medical images.”
What the sources say
- Not checked yetcites [5] Bernard, 2018, Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?, IEEE Trans. Med. Imaging source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It means that a single SAM network can be used to achieve the annotation of large-scale multi-modal, multi-class medical datasets, rather than using multiple task-specific models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Finally, we believe that, although SAM has the potential to become a general MIS model, its performance in the MIS task is not stable at present.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper relies on this without support.
Different medical objects often exhibit different characteristics and thus may have their own suitable modes for testing.
“However, different medical objects often exhibit different characteristics and thus may have their own suitable modes for testing.”
The paper relies on this without support.
The ground-truth masks used for evaluation accurately represent the true segmentation targets.
“we first calculated the center of mass of the ground truth (GT) mask”
“we calculated a set of dice scores { DICE n } N n = 1 between N binary predicted masks { P n } N n = 1 and the GT G .”
The paper relies on this without support.
The selected datasets and anatomical structures are representative of medical images, so the evaluation results can provide general guidance.
“We hope that a comprehensive evaluation of models of different sizes on large COSMOS 1050K can provide more inspirations for researchers.”
“we recorded the size, aspect ratio, intensity difference between foreground and background, modality, and boundary complexity of 191,779 anatomical structures.”
The paper relies on this without support.
The official GitHub implementation of SAM is correct and faithful.
“we implemented the testing pipeline of SAM basically following the official GitHub repository 4 .”
The paper relies on this without support.
The image embeddings computed once can be reused across different testing strategies for the same image without affecting segmentation results.
“since the same embedding could be reused for different testing strategies, we sought to optimize and accelerate this multi-extraction process.”
The paper relies on this without support.
The center of mass and tight bounding box of the ground truth represent the theoretical optimum prompts for SAM.
“Besides, we tend to test the theoretical optimum performance of SAM via the selection of the center of mass and tight box. Since they may include the most representative features of the target.”
The paper relies on this without support.
The 100 images randomly sampled from COSMOS 1050K with average DICE performance are representative of the broader medical image dataset for evaluating annotation time and quality.
“We randomly sampled 100 images with average DICE performance from COSMOS 1050K , to construct an evaluation subset comprising 55 objects and 620 masks across 9 modalities, including instances of the same object in different modalities.”
The paper relies on this without support.
The three doctors with 10 years of experience are representative of human annotators for evaluating annotation time and quality.
“We then invited three doctors with 10 years of experience to evaluate whether SAM's prediction under box prompts could improve annotation speed and quality.”
The paper relies on this without support.
The five attributes (size, aspect ratio, intensity difference, modality, Fourier order) adequately capture the factors that affect SAM's segmentation performance.
“We conducted an analysis of the partial correlation between the five attributes of the target objects mentioned above and the DICE score using Spearman's rank partial correlation coefficient under different testing strategies.”
The paper relies on this without support.
The Spearman partial correlation analysis assumptions (e.g., monotonic relationships, no unmeasured confounders) hold for the data.
“We conducted an analysis of the partial correlation between the five attributes of the target objects mentioned above and the DICE score using Spearman's rank partial correlation coefficient under different testing strategies.”
The paper relies on this without support.
The selected 10 typical organs/tumors are representative of medical segmentation tasks for comparing SAM with interactive methods.
“We selected 10 typical organs / tumors, covering various modalities, shapes, sizes, and intensity distributions.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“For example, the concurrent studies22,23 conducted a comprehensive assessment of SAM across a diverse array of medical images, underscoring that SAM achieved satisfactory segmentation outcomes primarily on targets characterized by distinct boundaries. However, the model exhibited substantial limitations in segmenting typical medical targets with weak boundaries or low contrast.”
From Segment anything in medical images (2024) · cites this paper as [23]
Citations
Cites
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Measures of the Amount of Ecologic Association Between Species
Dice, L. R. (1945) · Ecology · doi:10.2307/1932409 · Cited by 12,187
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00371 · Cited by 11,953
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J., & Maier-Hein, K. H. (2021) · Nature Methods · doi:10.1038/s41592-020-01008-z · Cited by 10,477 · cited 2×
“We describe the details of COSMOS 1050K in the following two aspects, including image collection and preprocessing specification.”
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489 · cited 1×
“Subsequently, a filtering mechanism is applied to remove duplicate and low-quality masks using the techniques of confidence score, stability evaluation based on threshold jitter, and non-maximal suppression (NMS).”
The multimodal brain tumor image segmentation benchmark (BRATS)
Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Burren, Y., Porz, N., Slotboom, J., Wiest, R., et al. (2015) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2377694 · Cited by 6,781 · cited 1×
“AbdomenCT-1K [22] Liver, kidney, spleen and pancreas CT ACDC [23] Left and right ventricle and left ventricular myocardium cine MRI AMOS 2022 [24] Abdominal multi-organ segmentation CT, MRI AutoLaparo [25] Integrated dataset with multiple image-based perception tasks Colonoscopy BrainPTM 2021 [26] white matter tracts…”
Tschandl, P., Rosendahl, C., & Kittler, H. (2018) · Scientific Data · doi:10.1038/sdata.2018.161 · Cited by 3,628
Bakas, S., Akbari, H., Sotiras, A., Bilello, M., Rozycki, M., Kirby, J. S., Freymann, J. B., Farahani, K., & Davatzikos, C. (2017) · Scientific Data · doi:10.1038/sdata.2017.117 · Cited by 3,049
Segment anything in medical images
Ma, J., He, Y., Li, F., Han, L., You, C., & Wang, B. (2024) · Nature Communications · doi:10.1038/s41467-024-44824-z · Cited by 2,913
Codella, N. C. F., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., et al. (2018) · 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) · doi:10.1109/isbi.2018.8363547 · Cited by 2,620
Research works printed but not linked: 3
- Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al., 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: International Conference on Learning Representations.
- Huazhu, 2019, PALM: PAthoLogic myopia challenge, Comput. Vis. Med. Imaging
- Lee, S., Shim, H., Park, S.H., Yun, I.D., Lee, S.U., 2010. Learning local shape and appearance for segmentation of knee cartilage in 3D MRI. In: Medical Image Analysis for the Clinic: A Grand Challenge. in Proceedings of the 13th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2010), Beijing, China. pp. 231–240.
Cited by
Sorted by citations
Segment anything in medical images
Ma, J., He, Y., Li, F., Han, L., You, C., & Wang, B. (2024) · Nature Communications · doi:10.1038/s41467-024-44824-z · Cited by 2,913
“However, their application to medical image segmentation has been challenging due to the substantial domain gap [6] (Supplementary Related work).”
Segment anything model for medical image analysis: An experimental study
Mazurowski, M. A., Dong, H., Gu, H., Yang, J., Konz, N., & Zhang, Y. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102918 · Cited by 802
Medical SAM adapter: Adapting segment anything model for medical image segmentation
Wu, J., Wang, Z., Hong, M., Ji, W., Fu, H., Xu, Y., Xu, M., & Jin, Y. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103547 · Cited by 1,187
Segment anything model for medical image segmentation: Current applications and future directions
Zhang, Y., Shen, Z., & Jiao, R. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108238 · Cited by 364
On the challenges and perspectives of foundation models for medical image analysis
Zhang, S., & Metaxas, D. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102996 · Cited by 340
Metadata
- Authors
- Huang, Y., Yang, X., Liu, L., Zhou, H., Chang, A., Zhou, X., Chen, R., Yu, J., Chen, J., Chen, C., Liu, S., Chi, H., Hu, X., Yue, K., Li, L., Grau, V., Fan, D.-P., Dong, F., & Ni, D.
- Affiliations
- Shenzhen University (CN)
- Zhejiang University (CN)
- Hunan First Normal University (CN)
- University of Oxford (GB)
- ETH Zurich (CH)
- Jinan University (CN)
- Corresponding author
- Dong, Fajin
- Ni, Dong
- ORCID
- Venue
- Medical Image Analysis
- Publisher
- Elsevier BV
- Published
- 2024-02
- Volume
- 92
- Pages
- 103061
- ISSN
- 1361-8415 (ISSN-L)
- OpenAlex
- W4389430914
- Semantic Scholar
- 057ddecf9b9dedd35f824c8b289c30316b4fa22e
- Cited by
- 536
- References
- 101
- Citations by year
- 2026: 134 · 2025: 230 · 2024: 154
- FWCI
- 48.56
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Medical Image Analysis (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- ePrints Soton (University of Southampton) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China
- Shenzhen Science and Technology Innovation Committee
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- Segment Anything Model, medical image segmentation, foundation models, point prompts, interactive segmentation, fine-tuning, boundary complexity
- MeSH terms
- Diagnostic Imaging, Humans, Image Processing, Computer-Assisted
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
