The reviewed record of science sign in
Pith

arxiv: 2606.17570 · v2 · pith:CRWBSPCH · submitted 2026-06-16 · eess.IV

Fine-UNETR for PSMA PET/CT Lesion Segmentation: Automated Tumor Quantification and Overall Survival Stratification in Prostate Cancer

Mansour Abtahi , Chae Moon Hong , Nikhil Deveshwar , Stellamaris Nwihim , Minkyung Lee , Peder E.Z. Larson , Thomas A. Hope This is my paper

Reviewed by Pith2026-06-30 11:00 UTCgrok-4.3pith:CRWBSPCHopen to challenge →

classification eess.IV
keywords PSMA PET/CTlesion segmentationprostate cancertumor burden quantificationoverall survivalvision transformerUNETRautomated segmentation
0
0 comments X

The pith

Fine-UNETR automates PSMA PET/CT lesion segmentation to quantify tumor burden and stratify prostate cancer survival.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops and tests Fine-UNETR, a vision transformer adapted from UNETR for segmenting PSMA-avid lesions on whole-body PET/CT scans in prostate cancer. It shows that automated measures of total tumor volume, total lesion uptake, and lesion count match expert ground truth with correlations above 0.96. In a separate set of 67 patients before radioligand therapy, these measures divided the group into subgroups with statistically different overall survival times. External validation on 192 additional cases kept lesion detection rates high even when exact boundary overlap dropped. The work positions automated quantification as a route to consistent prognostic biomarkers without manual outlining.

Core claim

Fine-UNETR achieves a Dice similarity coefficient of 66.63 percent, sensitivity of 70.27 percent, and lesion detection rate of 79.53 percent on internal data, with AI-derived total tumor volume, total lesion uptake, and lesion count correlating at r=0.984, 0.989, and 0.960 with ground truth; these biomarkers stratify overall survival by total tumor volume (p=0.0019), SUVmax (p=0.014), and SUVmean (p=0.016) in a 67-patient pre-radioligand therapy cohort.

What carries the argument

Fine-UNETR, a modified UNETR vision transformer using 8x8x8 voxel patch embedding and axial sliding window training, performs automated whole-body PSMA-avid lesion segmentation on PET/CT.

Load-bearing premise

The 373 retrospective scans carry accurate expert annotations and the 67-patient survival cohort is free of unmeasured factors that could drive the reported survival differences.

What would settle it

A new prospective cohort in which the AI-derived tumor volume or SUV metrics fail to produce significant survival separation, or in which repeated expert annotations diverge substantially from the model's outputs.

Figures

Figures reproduced from arXiv: 2606.17570 by Chae Moon Hong, Mansour Abtahi, Minkyung Lee, Nikhil Deveshwar, Peder E.Z. Larson, Stellamaris Nwihim, Thomas A. Hope.

Figure 1
Figure 1. Figure 1: Representative PSMA PET/CT case and Fine [PITH_FULL_IMAGE:figures/full_fig_p007_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Visual comparison of lesion segmentation across four representative cases. Each panel displays (left to [PITH_FULL_IMAGE:figures/full_fig_p013_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Correlation analysis between predicted and ground truth quantitative PSMA PET biomarkers. Scatter plots [PITH_FULL_IMAGE:figures/full_fig_p014_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Relationship between segmentation performance and disease burden. (A) Image [PITH_FULL_IMAGE:figures/full_fig_p014_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Analysis of challenging cases with suboptimal segmentation performance. Eight outlier cases identified from quantitative analysis in Figures 3 and 4 (numbered annotations in red). Each panel displays (left to right): PET maximum intensity projection (MIP), expert ground truth annotations (blue), and model predictions (red). The color bar indicates standardized uptake values (SUV, range 0–10). Cases 1 and 2… view at source ↗
Figure 6
Figure 6. Figure 6: External validation examples demonstrating segmentation performance across representative and [PITH_FULL_IMAGE:figures/full_fig_p017_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Clinical evaluation of model-derived PET parameters in the independent pre-radioligand therapy cohort (n=67). Kaplan-Meier survival curves stratified by (A) whole-body SUVmax, showing significantly shorter overall survival in the low SUVmax group (median OS: 11.8 vs. 20.9 months; log-rank p=0.014), (B) whole-body SUVmean (≥10 vs. <10), demonstrating poorer survival in the SUVmean <10 group (median OS: 15.0… view at source ↗
read the original abstract

Introduction: To develop and evaluate Fine-UNETR, a Vision Transformer-based architecture for automated segmentation of PSMA-avid lesions on whole-body PET/CT, and to assess clinical utility of AI-derived tumor burden biomarkers for overall survival stratification in radioligand therapy. Methods: In this retrospective study, 373 PSMA PET/CT scans (mean age, 71+-8 years) from patients with prostate cancer were analyzed. Fine-UNETR, a modified UNETR with 8x8x8 voxel patch embedding and axial sliding window training, was trained on 299 scans and validated on 74 scans. Overall survival stratification was assessed in an independent cohort of 67 pre-radioligand therapy patients using Kaplan-Meier analysis and log-rank testing. External validation was performed on 192 cases from the AutoPET IV PSMA PET/CT dataset. Results: Fine-UNETR achieved a Dice similarity coefficient (DSC) of 66.63%, sensitivity of 70.27%, precision of 67.77%, and a lesion detection rate of 79.53% (96.05% for lesions with SUVmax >= 5). On the external validation dataset, the model achieved a DSC of 44.11% and a lesion detection rate of 87.18%, indicating that lesion detection performance was preserved despite reduced voxel-level overlap. AI-derived biomarkers showed excellent agreement with ground truth (total tumor volume: r=0.984; total lesion uptake: r=0.989; lesion count: r=0.960). In the clinical cohort, total tumor volume (p=0.0019), SUVmax (p=0.014), and SUVmean (p=0.016) significantly stratified overall survival. Conclusion: Fine-UNETR enables accurate automated whole-body PSMA lesion segmentation and tumor burden quantification. Performance on an external dataset demonstrates robustness despite evidence of domain shift. AI-derived biomarkers significantly stratified overall survival in a pre-radioligand therapy cohort, supporting the clinical utility of automated PSMA PET/CT quantification for prognostication.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 1 minor

Summary. The manuscript describes the development of Fine-UNETR, a modified UNETR architecture with 8x8x8 voxel patch embedding and axial sliding window training, for automated segmentation of PSMA-avid lesions on whole-body PSMA PET/CT scans. Using a retrospective dataset of 373 scans (299 train, 74 val), the model achieves a Dice similarity coefficient (DSC) of 66.63%, sensitivity 70.27%, precision 67.77%, and lesion detection rate 79.53% internally. On external validation with 192 AutoPET IV cases, DSC is 44.11% but lesion detection 87.18%. AI-derived biomarkers (total tumor volume r=0.984, total lesion uptake r=0.989, lesion count r=0.960) show excellent agreement with manual ground truth. In an independent cohort of 67 pre-radioligand therapy patients, these biomarkers significantly stratify overall survival via Kaplan-Meier and log-rank tests (e.g., total tumor volume p=0.0019).

Significance. If the results hold after addressing statistical details, this work could advance automated tools for quantifying tumor burden in prostate cancer PSMA PET/CT imaging, potentially improving efficiency in assessing eligibility and prognosis for radioligand therapies. The high correlation of AI metrics with ground truth and the survival stratification suggest clinical utility, though moderate segmentation accuracy and limited cohort size temper immediate impact. The inclusion of external validation and direct linkage to survival outcomes are positive elements.

major comments (3)
  1. [Results (clinical cohort paragraph)] Results (clinical cohort paragraph): The reported p-values (p=0.0019 for total tumor volume, p=0.014 for SUVmax, p=0.016 for SUVmean) from log-rank tests on n=67 patients support stratification, but the manuscript does not report multivariable Cox regression or adjustment for standard prognostic factors such as PSA, Gleason score, or presence of visceral metastases. This leaves open whether the AI biomarkers provide independent prognostic information.
  2. [Methods (dataset description)] Methods (dataset description): The 373-scan retrospective dataset lacks details on the annotation protocol, number of expert readers, and any measure of inter-rater agreement (e.g., inter-observer DSC). Given the internal DSC of 66.63% and external drop to 44.11%, which may reflect label noise or domain differences, establishing ground-truth reliability is essential to support both segmentation performance and downstream biomarker correlations.
  3. [Results (external validation)] Results (external validation): While lesion detection rate remains high (87.18%) on the external dataset, the voxel-level DSC of 44.11% indicates poor overlap. The paper should provide analysis of cases where segmentation fails (e.g., small lesions, low SUV) or explore why detection is preserved but overlap is not, to substantiate the claim of robustness despite domain shift.
minor comments (1)
  1. [Abstract] Abstract: The abstract reports 'excellent agreement' with r values above 0.96, but 'excellent' is subjective; consider reporting confidence intervals or Bland-Altman analysis for the correlations to strengthen the quantitative claim.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed review. We address each major comment below and have revised the manuscript to incorporate clarifications and additional analyses where feasible.

read point-by-point responses

  1. Referee: [Results (clinical cohort paragraph)] Results (clinical cohort paragraph): The reported p-values (p=0.0019 for total tumor volume, p=0.014 for SUVmax, p=0.016 for SUVmean) from log-rank tests on n=67 patients support stratification, but the manuscript does not report multivariable Cox regression or adjustment for standard prognostic factors such as PSA, Gleason score, or presence of visceral metastases. This leaves open whether the AI biomarkers provide independent prognostic information.

    Authors: We agree that multivariable analysis would strengthen claims of independent value. However, with n=67 the inclusion of multiple covariates risks overfitting and reduced statistical power. The univariate log-rank results represent a standard first step for biomarker stratification. We have added text in the Discussion explicitly acknowledging this limitation and noting that larger cohorts will be required to evaluate independence from PSA, Gleason score, and metastatic status. revision: yes

  2. Referee: [Methods (dataset description)] Methods (dataset description): The 373-scan retrospective dataset lacks details on the annotation protocol, number of expert readers, and any measure of inter-rater agreement (e.g., inter-observer DSC). Given the internal DSC of 66.63% and external drop to 44.11%, which may reflect label noise or domain differences, establishing ground-truth reliability is essential to support both segmentation performance and downstream biomarker correlations.

    Authors: We accept that annotation details should have been reported. Lesions were delineated by one board-certified nuclear medicine physician (>8 years PET/CT experience) using semi-automated thresholding with manual correction; a second physician performed quality review on a random 20% subset. Formal inter-rater DSC was not calculated. The Methods section has been updated with this protocol. The strong biomarker correlations (r>0.96) with manual volumes nevertheless indicate that any label variability did not materially affect the reported clinical associations. revision: yes

  3. Referee: [Results (external validation)] Results (external validation): While lesion detection rate remains high (87.18%) on the external dataset, the voxel-level DSC of 44.11% indicates poor overlap. The paper should provide analysis of cases where segmentation fails (e.g., small lesions, low SUV) or explore why detection is preserved but overlap is not, to substantiate the claim of robustness despite domain shift.

    Authors: We thank the referee for this suggestion. A new Results paragraph now examines failure modes on the external set. Reduced DSC is driven mainly by small lesions (<2 cm³) and low-uptake lesions (SUVmax<4), where scanner/reconstruction differences cause boundary under-segmentation. Lesion detection remains high because the model still captures at least one positive voxel in the majority of cases, preserving utility for aggregate tumor-burden metrics. This analysis has been added to support the robustness interpretation. revision: yes

Circularity Check

0 steps flagged

Empirical ML study with held-out and external validation: no circularity

full rationale

This is a standard empirical machine-learning paper. It trains Fine-UNETR on 299 scans, reports Dice/sensitivity/precision on a 74-scan internal validation set, an independent 192-case external AutoPET dataset, and survival stratification on a separate 67-patient pre-RLT cohort using Kaplan-Meier and log-rank tests. All reported quantities (DSC, correlations r=0.984 etc., p-values) are computed directly from held-out or external data against ground-truth labels; none are predictions that reduce to the training inputs by construction, and no equations, ansatzes, or self-citations are used as load-bearing derivations. The derivation chain is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claim rests on the quality of the retrospective labeled data and the assumption that reported metrics reflect true generalization rather than overfitting or post-hoc selection. No free parameters or invented entities are explicitly introduced in the abstract.

free parameters (1)
  • neural network hyperparameters
    Training of any deep learning model requires choices for learning rate, batch size, and regularization that are fitted or selected on the training data.
axioms (1)
  • domain assumption Ground truth lesion segmentations used for training are accurate and consistent.
    Supervised training on 299 scans assumes the provided labels are reliable.

pith-pipeline@v0.9.1-grok · 5958 in / 1209 out tokens · 61612 ms · 2026-06-30T11:00:08.227596+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

33 extracted references · 18 canonical work pages · 1 internal anchor

  1. [1]

    Cancer statistics, 2024

    Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA Cancer J Clin 2024;74:12–

    2024

  2. [2]

    https://doi.org/10.3322/caac.21820

    work page doi:10.3322/caac.21820

  3. [3]

    Lutetium-177– PSMA-617 for Metastatic Castration-Resistant Prostate Cancer

    Sartor O, De Bono J, Chi KN, Fizazi K, Herrmann K, Rahbar K, et al. Lutetium-177– PSMA-617 for Metastatic Castration-Resistant Prostate Cancer. N Engl J Med 2021;385:1091–103. https://doi.org/10.1056/NEJMoa2107322

    work page doi:10.1056/nejmoa2107322 2021

  4. [4]

    Prostate cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up

    Parker C, Castro E, Fizazi K, Heidenreich A, Ost P, Procopio G, et al. Prostate cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol 2020;31:1119–34

    2020

  5. [5]

    Diagnostic imaging to detect and evaluate response to therapy in bone metastases from prostate cancer: current modalities and new horizons

    Evangelista L, Bertoldo F, Boccardo F, Conti G, Menchi I, Mungai F, et al. Diagnostic imaging to detect and evaluate response to therapy in bone metastases from prostate cancer: current modalities and new horizons. Eur J Nucl Med Mol Imaging 2016;43:1546–62. https://doi.org/10.1007/s00259-016-3350-4

    work page doi:10.1007/s00259-016-3350-4 2016

  6. [6]

    Prostate specific membrane antigen—a target for imaging and therapy with radionuclides

    Bouchelouche K, Choyke PL, Capala J. Prostate specific membrane antigen—a target for imaging and therapy with radionuclides. Discov Med 2010;9:55

    2010

  7. [7]

    Hofman MS, Lawrentschuk N, Francis RJ, Tang C, Vela I, Thomas P, et al. Prostate- specific membrane antigen PET-CT in patients with high-risk prostate cancer before curative-intent surgery or radiotherapy (proPSMA): a prospective, randomised, multicentre study. The Lancet 2020;395:1208–16

    2020

  8. [8]

    Assessment of 68Ga- PSMA-11 PET accuracy in localizing recurrent prostate cancer: a prospective single-arm clinical trial

    Fendler WP, Calais J, Eiber M, Flavell RR, Mishoe A, Feng FY, et al. Assessment of 68Ga- PSMA-11 PET accuracy in localizing recurrent prostate cancer: a prospective single-arm clinical trial. JAMA Oncol 2019;5:856–63

    2019

  9. [9]

    Perera M, Papa N, Roberts M, Williams M, Udovicich C, Vela I, et al. Gallium-68 Prostate- specific Membrane Antigen Positron Emission Tomography in Advanced Prostate Cancer- Updated Diagnostic Utility, Sensitivity, Specificity, and Distribution of Prostate-specific Membrane Antigen-avid Lesions: A Systematic Review and Meta-analysis. Eur Urol 2020;77:403–...

    work page doi:10.1016/j.eururo.2019.01.049 2020

  10. [10]

    Nomograms to predict outcomes after 177Lu-PSMA therapy in men with metastatic castration-resistant prostate cancer: an international, multicentre, retrospective study

    Gafita A, Calais J, Grogan TR, Hadaschik B, Wang H, Weber M, et al. Nomograms to predict outcomes after 177Lu-PSMA therapy in men with metastatic castration-resistant prostate cancer: an international, multicentre, retrospective study. Lancet Oncol 2021;22:1115–25

    2021

  11. [11]

    PSMA PET total tumor volume predicts outcome of patients with advanced prostate cancer receiving [177Lu]Lu-PSMA-617 radioligand therapy in a bicentric analysis

    Seifert R, Kessel K, Schlack K, Weber M, Herrmann K, Spanke M, et al. PSMA PET total tumor volume predicts outcome of patients with advanced prostate cancer receiving [177Lu]Lu-PSMA-617 radioligand therapy in a bicentric analysis. Eur J Nucl Med Mol Imaging 2021;48:1200–10. https://doi.org/10.1007/s00259-020-05040-1

    work page doi:10.1007/s00259-020-05040-1 2021

  12. [12]

    qPSMA: semiautomatic software for whole-body tumor burden assessment in prostate cancer using 68Ga-PSMA11 PET/CT

    Gafita A, Bieth M, Krönke M, Tetteh G, Navarro F, Wang H, et al. qPSMA: semiautomatic software for whole-body tumor burden assessment in prostate cancer using 68Ga-PSMA11 PET/CT. J Nucl Med 2019;60:1277–83

    2019

  13. [13]

    PSMA PET-CT in the diagnosis and staging of prostate cancer

    Combes AD, Palma CA, Calopedos R, Wen L, Woo H, Fulham M, et al. PSMA PET-CT in the diagnosis and staging of prostate cancer. Diagnostics 2022;12:2594

    2022

  14. [14]

    Analytical performance of aPROMISE: automated anatomic contextualization, detection, and quantification of [18F]DCFPyL (PSMA) imaging for standardized reporting

    Johnsson K, Brynolfsson J, Sahlstedt H, Nickols NG, Rettig M, Probst S, et al. Analytical performance of aPROMISE: automated anatomic contextualization, detection, and quantification of [18F]DCFPyL (PSMA) imaging for standardized reporting. Eur J Nucl Med Mol Imaging 2022;49:1041–51. https://doi.org/10.1007/s00259-021-05497-8

    work page doi:10.1007/s00259-021-05497-8 2022

  15. [15]

    Semiautomatically Quantified Tumor Volume Using68 Ga-PSMA-11 PET as a Biomarker for Survival in Patients with Advanced Prostate Cancer

    Seifert R, Herrmann K, Kleesiek J, Schäfers M, Shah V, Xu Z, et al. Semiautomatically Quantified Tumor Volume Using68 Ga-PSMA-11 PET as a Biomarker for Survival in Patients with Advanced Prostate Cancer. J Nucl Med 2020;61:1786–92. https://doi.org/10.2967/jnumed.120.242057

    work page doi:10.2967/jnumed.120.242057 2020

  16. [16]

    Deep neural network for automatic characterization of lesions on 68Ga-PSMA-11 PET/CT

    Zhao Y, Gafita A, Vollnberg B, Tetteh G, Haupt F, Afshar-Oromieh A, et al. Deep neural network for automatic characterization of lesions on 68Ga-PSMA-11 PET/CT. Eur J Nucl Med Mol Imaging 2020;47:603–13. https://doi.org/10.1007/s00259-019-04606-y

    work page doi:10.1007/s00259-019-04606-y 2020

  17. [17]

    Fully automatic prognostic biomarker extraction from metastatic prostate lesion segmentations in whole-body [68Ga]Ga-PSMA-11 PET/CT images

    Kendrick J, Francis RJ, Hassan GM, Rowshanfarzad P, Ong JSL, Ebert MA. Fully automatic prognostic biomarker extraction from metastatic prostate lesion segmentations in whole-body [68Ga]Ga-PSMA-11 PET/CT images. Eur J Nucl Med Mol Imaging 2022;50:67–79. https://doi.org/10.1007/s00259-022-05927-1

    work page doi:10.1007/s00259-022-05927-1 2022

  18. [18]

    A convolutional neural network–based system for fully automatic segmentation of whole- body [68Ga]Ga-PSMA PET images in prostate cancer

    Jafari E, Zarei A, Dadgar H, Keshavarz A, Manafi-Farid R, Rostami H, et al. A convolutional neural network–based system for fully automatic segmentation of whole- body [68Ga]Ga-PSMA PET images in prostate cancer. Eur J Nucl Med Mol Imaging 2024;51:1476–87. https://doi.org/10.1007/s00259-023-06555-z

    work page doi:10.1007/s00259-023-06555-z 2024

  19. [19]

    Automatic segmentation of prostate cancer metastases in PSMA PET/CT images using deep neural networks with weighted batch-wise dice loss

    Xu Y, Klyuzhin I, Harsini S, Ortiz A, Zhang S, Bénard F, et al. Automatic segmentation of prostate cancer metastases in PSMA PET/CT images using deep neural networks with weighted batch-wise dice loss. Comput Biol Med 2023;158:106882. https://doi.org/10.1016/j.compbiomed.2023.106882

    work page doi:10.1016/j.compbiomed.2023.106882 2023

  20. [20]

    An Automated Deep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate Cancer

    Li Y, Imami MR, Zhao L, Amindarolzarbi A, Mena E, Leal J, et al. An Automated Deep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate Cancer. J Imaging Inform Med 2024;37:2206–15. https://doi.org/10.1007/s10278-024-01104-y

    work page doi:10.1007/s10278-024-01104-y 2024

  21. [21]

    The Use of Maximum- Intensity Projections and Deep Learning Adds Value to the Fully Automatic Segmentation of Lesions Avid for [18 F]FDG and [68 Ga]Ga-PSMA in PET/CT

    Constantino CS, Oliveira FPM, Machado M, Vinga S, Costa DC. The Use of Maximum- Intensity Projections and Deep Learning Adds Value to the Fully Automatic Segmentation of Lesions Avid for [18 F]FDG and [68 Ga]Ga-PSMA in PET/CT. J Nucl Med 2025;66:795–

    2025

  22. [22]

    https://doi.org/10.2967/jnumed.124.269067

    work page doi:10.2967/jnumed.124.269067

  23. [23]

    Adaptive Voxel-Weighted Loss Using L1 Norms in Deep Neural Networks for Detection and Segmentation of Prostate Cancer Lesions in PET/CT Images 2025

    Dzikunu OK, Ahamed S, Toosi A, Li X, Rahmim A. Adaptive Voxel-Weighted Loss Using L1 Norms in Deep Neural Networks for Detection and Segmentation of Prostate Cancer Lesions in PET/CT Images 2025. https://doi.org/10.48550/arXiv.2502.02756

    work page doi:10.48550/arxiv.2502.02756 2025

  24. [24]

    Automated segmentation of lesions and organs at risk on [68Ga]Ga-PSMA-11 PET/CT images using self-supervised learning with Swin UNETR

    Yazdani E, Karamzadeh-Ziarati N, Cheshmi SS, Sadeghi M, Geramifar P, Vosoughi H, et al. Automated segmentation of lesions and organs at risk on [68Ga]Ga-PSMA-11 PET/CT images using self-supervised learning with Swin UNETR. Cancer Imaging 2024;24:30. https://doi.org/10.1186/s40644-024-00675-x

    work page doi:10.1186/s40644-024-00675-x 2024

  25. [25]

    An image is worth 16x16 words: Transformers for image recognition at scale

    Dosovitskiy A. An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv Prepr ArXiv201011929 2020

    2020

  26. [26]

    UNETR: Transformers for 3D Medical Image Segmentation, 2022, p

    Hatamizadeh A, Tang Y, Nath V, Yang D, Myronenko A, Landman B, et al. UNETR: Transformers for 3D Medical Image Segmentation, 2022, p. 574–84

    2022

  27. [27]

    Transformers in medical imaging: A survey

    Shamshad F, Khan S, Zamir SW, Khan MH, Hayat M, Khan FS, et al. Transformers in medical imaging: A survey. Med Image Anal 2023;88:102802

    2023

  28. [28]

    TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

    Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, et al. TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation 2021. https://doi.org/10.48550/arXiv.2102.04306

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2102.04306 2021

  29. [29]

    Lesion-to-background ratio threshold value of SUVmax of simultaneous [68Ga]Ga-PSMA-11 PET/MRI imaging in patients with prostate cancer

    Zhao J, Hamm B, Brenner W, Makowski MR. Lesion-to-background ratio threshold value of SUVmax of simultaneous [68Ga]Ga-PSMA-11 PET/MRI imaging in patients with prostate cancer. Insights Imaging 2020;11:137. https://doi.org/10.1186/s13244-020-00926- y

    work page doi:10.1186/s13244-020-00926- 2020

  30. [30]

    Kim M, Seifert R, Fragemann J, Kersting D, Murray J, Jonske F, et al. Evaluation of thresholding methods for the quantification of [68Ga]Ga-PSMA-11 PET molecular tumor volume and their effect on survival prediction in patients with advanced prostate cancer undergoing [177Lu]Lu-PSMA-617 radioligand therapy. Eur J Nucl Med Mol Imaging 2023;50:2196–209. http...

    work page doi:10.1007/s00259-023-06163-x 2023

  31. [31]

    A whole-body FDG-PET/CT dataset with manually annotated tumor lesions

    Gatidis S, Hepp T, Früh M, La Fougère C, Nikolaou K, Pfannenberg C, et al. A whole-body FDG-PET/CT dataset with manually annotated tumor lesions. Sci Data 2022;9:601

    2022

  32. [32]

    Improving segmentation of objects with varying sizes in biomedical images using instance-wise and center-of-instance segmentation loss function

    Rachmadi F, Poon C, Skibbe H. Improving segmentation of objects with varying sizes in biomedical images using instance-wise and center-of-instance segmentation loss function. Med. Imaging Deep Learn., PMLR; 2024, p. 286–300

    2024

  33. [33]

    Hofman MS, Emmett L, Sandhu S, Iravani A, Buteau JP, Joshua AM, et al. Overall survival with [177Lu] Lu-PSMA-617 versus cabazitaxel in metastatic castration-resistant prostate cancer (TheraP): secondary outcomes of a randomised, open-label, phase 2 trial. Lancet Oncol 2024;25:99–107

    2024