PSMA PET Evaluation with a Deep Learning Platform Compared with a Standard Image Viewer and Histopathology.
Saved in:
| Title: | PSMA PET Evaluation with a Deep Learning Platform Compared with a Standard Image Viewer and Histopathology. |
|---|---|
| Authors: | Koehler D; Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; d.koehler@uke.de.; EAU Section of Imaging, EAU, Arnhem, The Netherlands., Shenas F; Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany., Sauer M; Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany., Apostolova I; Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany., Budäus L; EAU Section of Imaging, EAU, Arnhem, The Netherlands.; Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany; and.; Department of Urology, University Hospital Hamburg-Eppendorf, Hamburg, Germany., Falkenbach F; Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany; and., Maurer T; EAU Section of Imaging, EAU, Arnhem, The Netherlands.; Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany; and.; Department of Urology, University Hospital Hamburg-Eppendorf, Hamburg, Germany. |
| Source: | Journal of nuclear medicine : official publication, Society of Nuclear Medicine [J Nucl Med] 2025 Dec 03; Vol. 66 (12), pp. 2014-2019. Date of Electronic Publication: 2025 Dec 03. |
| Publication Type: | Journal Article; Comparative Study |
| Language: | English |
| Journal Info: | Publisher: Society of Nuclear Medicine Country of Publication: United States NLM ID: 0217410 Publication Model: Electronic Cited Medium: Internet ISSN: 1535-5667 (Electronic) Linking ISSN: 01615505 NLM ISO Abbreviation: J Nucl Med Subsets: MEDLINE |
| Imprint Name(s): | Publication: Reston, VA : Society of Nuclear Medicine Original Publication: [Chicago, Ill.] : S.N. Turiel & Assoc. |
| MeSH Terms: | Deep Learning* , Positron Emission Tomography Computed Tomography*/methods , Prostatic Neoplasms*/diagnostic imaging , Prostatic Neoplasms*/pathology , Prostatic Neoplasms*/metabolism , Prostatic Neoplasms*/surgery , Glutamate Carboxypeptidase II*/metabolism , Antigens, Surface*/metabolism , Image Processing, Computer-Assisted*/methods, Humans ; Male ; Aged ; Middle Aged ; Retrospective Studies ; Reproducibility of Results ; Gallium Radioisotopes |
| Abstract: | Standardized prostate-specific membrane antigen (PSMA) PET/CT evaluation and reporting was introduced to aid interpretation, reproducibility, and communication. Artificial intelligence may enhance these efforts. This study aimed to evaluate the performance of aPROMISE, a deep learning segmentation and reporting software for PSMA PET/CT, compared with a standard image viewer (IntelliSpace Portal [ISP]) in patients undergoing PSMA-radioguided surgery. This allowed the correlation of target lesions with histopathology as a standard of truth. Methods: [ 68 Ga]Ga-PSMA-I&T PET/CT of 96 patients with biochemical persistence or recurrence after prostatectomy (median prostate-specific antigen, 0.56 ng/mL; interquartile range, 0.31-1.24 ng/mL), who underwent PSMA-radioguided surgery, were retrospectively analyzed (twice with ISP and twice with aPROMISE) by 2 readers. Cohen κ with 95% CI was calculated to assess intra- and interrater agreement for miTNM stages. Differences between miTNM codelines were classified as no difference, minor difference (change of lymph node region without N/M change), and major difference (miTNM change). Results: Intrarater agreement rates were high for all categories, both readers, and systems (≥91.7%) with moderate to almost perfect κ values (reader 1, ISP, ≥0.51; range, 0.21-0.9; aPROMISE, ≥0.64; range, 0.41-0.99; reader 2, ISP, ≥0.83; range, 0.69-1; aPROMISE, ≥0.78; range, 0.63-1). Major differences occurred more frequently for reader 1 than for reader 2 (ISP, 26% vs. 13.5%; aPROMISE, 22.9% vs. 12.5%). Interrater agreement rates were high with both systems (≥92.2%), demonstrating substantial κ values (ISP, ≥0.73; range, 0.47-0.99; aPROMISE, ≥0.74; range, 0.54-1) with major miTNM staging differences in 21 (21.9%) cases. Readers identified 140 lesions by consensus, of which aPROMISE automatically segmented 129 (92.1%) lesions. Unsegmented lesions either were adjacent to high urine activity or demonstrated low PSMA expression. Agreement rates between imaging and histopathology were substantial (≥86.5%), corresponding to moderate to substantial κ values (≥0.6; range, 0.45-1) with major staging differences in 33 (34.4%) patients. This included 13 (13.5%) cases with metastases distant from targets identified on imaging. One of these lesions was automatically segmented by aPROMISE. Conclusion: Intra- and interreader agreement for PSMA PET/CT evaluation were similarly high with ISP and aPROMISE. The algorithm segmented 92.1% of all identified lesions. Software applications with artificial intelligence could be applied as support tools in PSMA PET/CT evaluation of early prostate cancer. (© 2025 by the Society of Nuclear Medicine and Molecular Imaging.) |
| Contributed Indexing: | Keywords: PSMA; biochemical recurrence; deep learning; prostate cancer; standardized reporting |
| Substance Nomenclature: | EC 3.4.17.21 (Glutamate Carboxypeptidase II) EC 3.4.17.21 (FOLH1 protein, human) 0 (Antigens, Surface) 0 (Gallium Radioisotopes) |
| Entry Date(s): | Date Created: 20251016 Date Completed: 20251203 Latest Revision: 20251203 |
| Update Code: | 20251204 |
| DOI: | 10.2967/jnumed.125.270242 |
| PMID: | 41101977 |
| Database: | MEDLINE |
Nájsť tento článok vo Web of Science | Abstract: | Standardized prostate-specific membrane antigen (PSMA) PET/CT evaluation and reporting was introduced to aid interpretation, reproducibility, and communication. Artificial intelligence may enhance these efforts. This study aimed to evaluate the performance of aPROMISE, a deep learning segmentation and reporting software for PSMA PET/CT, compared with a standard image viewer (IntelliSpace Portal [ISP]) in patients undergoing PSMA-radioguided surgery. This allowed the correlation of target lesions with histopathology as a standard of truth. Methods: [ <sup>68</sup> Ga]Ga-PSMA-I&T PET/CT of 96 patients with biochemical persistence or recurrence after prostatectomy (median prostate-specific antigen, 0.56 ng/mL; interquartile range, 0.31-1.24 ng/mL), who underwent PSMA-radioguided surgery, were retrospectively analyzed (twice with ISP and twice with aPROMISE) by 2 readers. Cohen κ with 95% CI was calculated to assess intra- and interrater agreement for miTNM stages. Differences between miTNM codelines were classified as no difference, minor difference (change of lymph node region without N/M change), and major difference (miTNM change). Results: Intrarater agreement rates were high for all categories, both readers, and systems (≥91.7%) with moderate to almost perfect κ values (reader 1, ISP, ≥0.51; range, 0.21-0.9; aPROMISE, ≥0.64; range, 0.41-0.99; reader 2, ISP, ≥0.83; range, 0.69-1; aPROMISE, ≥0.78; range, 0.63-1). Major differences occurred more frequently for reader 1 than for reader 2 (ISP, 26% vs. 13.5%; aPROMISE, 22.9% vs. 12.5%). Interrater agreement rates were high with both systems (≥92.2%), demonstrating substantial κ values (ISP, ≥0.73; range, 0.47-0.99; aPROMISE, ≥0.74; range, 0.54-1) with major miTNM staging differences in 21 (21.9%) cases. Readers identified 140 lesions by consensus, of which aPROMISE automatically segmented 129 (92.1%) lesions. Unsegmented lesions either were adjacent to high urine activity or demonstrated low PSMA expression. Agreement rates between imaging and histopathology were substantial (≥86.5%), corresponding to moderate to substantial κ values (≥0.6; range, 0.45-1) with major staging differences in 33 (34.4%) patients. This included 13 (13.5%) cases with metastases distant from targets identified on imaging. One of these lesions was automatically segmented by aPROMISE. Conclusion: Intra- and interreader agreement for PSMA PET/CT evaluation were similarly high with ISP and aPROMISE. The algorithm segmented 92.1% of all identified lesions. Software applications with artificial intelligence could be applied as support tools in PSMA PET/CT evaluation of early prostate cancer.<br /> (© 2025 by the Society of Nuclear Medicine and Molecular Imaging.) |
|---|---|
| ISSN: | 1535-5667 |
| DOI: | 10.2967/jnumed.125.270242 |