1
|
Vaz SC, Woll JPP, Cardoso F, Groheux D, Cook GJR, Ulaner GA, Jacene H, Rubio IT, Schoones JW, Peeters MJV, Poortmans P, Mann RM, Graff SL, Dibble EH, de Geus-Oei LF. Joint EANM-SNMMI guideline on the role of 2-[ 18F]FDG PET/CT in no special type breast cancer : (endorsed by the ACR, ESSO, ESTRO, EUSOBI/ESR, and EUSOMA). Eur J Nucl Med Mol Imaging 2024; 51:2706-2732. [PMID: 38740576 PMCID: PMC11224102 DOI: 10.1007/s00259-024-06696-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2024] [Accepted: 03/20/2024] [Indexed: 05/16/2024]
Abstract
INTRODUCTION There is much literature about the role of 2-[18F]FDG PET/CT in patients with breast cancer (BC). However, there exists no international guideline with involvement of the nuclear medicine societies about this subject. PURPOSE To provide an organized, international, state-of-the-art, and multidisciplinary guideline, led by experts of two nuclear medicine societies (EANM and SNMMI) and representation of important societies in the field of BC (ACR, ESSO, ESTRO, EUSOBI/ESR, and EUSOMA). METHODS Literature review and expert discussion were performed with the aim of collecting updated information regarding the role of 2-[18F]FDG PET/CT in patients with no special type (NST) BC and summarizing its indications according to scientific evidence. Recommendations were scored according to the National Institute for Health and Care Excellence (NICE) criteria. RESULTS Quantitative PET features (SUV, MTV, TLG) are valuable prognostic parameters. In baseline staging, 2-[18F]FDG PET/CT plays a role from stage IIB through stage IV. When assessing response to therapy, 2-[18F]FDG PET/CT should be performed on certified scanners, and reported either according to PERCIST, EORTC PET, or EANM immunotherapy response criteria, as appropriate. 2-[18F]FDG PET/CT may be useful to assess early metabolic response, particularly in non-metastatic triple-negative and HER2+ tumours. 2-[18F]FDG PET/CT is useful to detect the site and extent of recurrence when conventional imaging methods are equivocal and when there is clinical and/or laboratorial suspicion of relapse. Recent developments are promising. CONCLUSION 2-[18F]FDG PET/CT is extremely useful in BC management, as supported by extensive evidence of its utility compared to other imaging modalities in several clinical scenarios.
Collapse
Affiliation(s)
- Sofia C Vaz
- Nuclear Medicine-Radiopharmacology, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal.
- Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands.
| | | | - Fatima Cardoso
- Breast Unit, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - David Groheux
- Nuclear Medicine Department, Saint-Louis Hospital, Paris, France
- University Paris-Diderot, INSERM U976, Paris, France
- Centre d'Imagerie Radio-Isotopique (CIRI), La Rochelle, France
| | - Gary J R Cook
- Department of Cancer Imaging, King's College London, London, UK
- King's College London and Guy's & St Thomas' PET Centre, London, UK
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Gary A Ulaner
- Molecular Imaging and Therapy, Hoag Family Cancer Institute, Newport Beach, CA, USA
- University of Southern California, Los Angeles, CA, USA
| | - Heather Jacene
- Dana-Farber Cancer Institute/Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
| | - Isabel T Rubio
- Breast Surgical Oncology, Clinica Universidad de Navarra, Madrid, Cancer Center Clinica Universidad de Navarra, Navarra, Spain
| | - Jan W Schoones
- Directorate of Research Policy, Leiden University Medical Center, Leiden, The Netherlands
| | - Marie-Jeanne Vrancken Peeters
- Department of Surgical Oncology, Netherlands Cancer Institute, Amsterdam, The Netherlands
- Department of Surgery, Amsterdam University Medical Center, Amsterdam, The Netherlands
| | - Philip Poortmans
- Department of Radiation Oncology, Iridium Netwerk, Antwerp, Belgium
- University of Antwerp, Wilrijk, Antwerp, Belgium
| | - Ritse M Mann
- Radiology Department, RadboudUMC, Nijmegen, The Netherlands
| | - Stephanie L Graff
- Lifespan Cancer Institute, Providence, Rhode Island, USA
- Legorreta Cancer Center at Brown University, Providence, Rhode Island, USA
| | - Elizabeth H Dibble
- Department of Diagnostic Imaging, The Warren Alpert Medical School of Brown University, Providence, Rhode Island, USA.
| | - Lioe-Fee de Geus-Oei
- Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands.
- Biomedical Photonic Imaging Group, University of Twente, Enschede, The Netherlands.
- Department of Radiation Science & Technology, Technical University of Delft, Delft, The Netherlands.
| |
Collapse
|
2
|
Llombart-Cussac A, Prat A, Pérez-García JM, Mateos J, Pascual T, Escrivà-de-Romani S, Stradella A, Ruiz-Borrego M, de Las Heras BB, Keyaerts M, Galvan P, Brasó-Maristany F, García-Mosquera JJ, Guiot T, Gion M, Sampayo-Cordero M, Di Cosimo S, Pérez-Escuredo J, de Frutos MA, Cortés J, Gebhart G. Clinicopathological and molecular predictors of [ 18F]FDG-PET disease detection in HER2-positive early breast cancer: RESPONSE, a substudy of the randomized PHERGain trial. Eur J Nucl Med Mol Imaging 2024; 51:2733-2743. [PMID: 38587643 PMCID: PMC11224085 DOI: 10.1007/s00259-024-06683-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Accepted: 03/10/2024] [Indexed: 04/09/2024]
Abstract
BACKGROUND The PHERGain study (NCT03161353) is assessing early metabolic responses to neoadjuvant treatment with trastuzumab-pertuzumab and chemotherapy de-escalation using a [18Fluorine]fluorodeoxyglucose-positron emission tomography ([18F]FDG-PET) and a pathological complete response-adapted strategy in HER2-positive (HER2+) early breast cancer (EBC). Herein, we present RESPONSE, a PHERGain substudy, where clinicopathological and molecular predictors of [18F]FDG-PET disease detection were evaluated. METHODS A total of 500 patients with HER2 + EBC screened in the PHERGain trial with a tumor size > 1.5 cm by magnetic resonance imaging (MRI) were included in the RESPONSE substudy. PET[-] criteria entailed the absence of ≥ 1 breast lesion with maximum standardized uptake value (SUVmax) ≥ 1.5 × SUVmean liver + 2 standard deviation. Among 75 PET[-] patients screened, 21 with SUVmax levels < 2.5 were randomly selected and matched with 21 PET[+] patients with SUVmax levels ≥ 2.5 based on patient characteristics associated with [18F]FDG-PET status. The association between baseline SUVmax and [18F]FDG-PET status ([-] or [+]) with clinicopathological characteristics was assessed. In addition, evaluation of stromal tumor-infiltrating lymphocytes (sTILs) and gene expression analysis using PAM50 and Vantage 3D™ Cancer Metabolism Panel were specifically compared in a matched cohort of excluded and enrolled patients based on the [18F]FDG-PET eligibility criteria. RESULTS Median SUVmax at baseline was 7.2 (range, 1-39.3). Among all analyzed patients, a higher SUVmax was associated with a higher tumor stage, larger tumor size, lymph node involvement, hormone receptor-negative status, higher HER2 protein expression, increased Ki67 proliferation index, and higher histological grade (p < 0.05). [18F]FDG-PET [-] criteria patients had smaller tumor size (p = 0.014) along with the absence of lymph node involvement and lower histological grade than [18F]FDG-PET [+] patients (p < 0.01). Although no difference in the levels of sTILs was found among 42 matched [18F]FDG-PET [-]/[+] criteria patients (p = 0.73), [18F]FDG-PET [-] criteria patients showed a decreased risk of recurrence (ROR) and a lower proportion of PAM50 HER2-enriched subtype than [18F]FDG-PET[+] patients (p < 0.05). Differences in the expression of genes involved in cancer metabolism were observed between [18F]FDG-PET [-] and [18F]FDG-PET[+] criteria patients. CONCLUSIONS These results highlight the clinical, biological, and metabolic heterogeneity of HER2+ breast cancer, which may facilitate the selection of HER2+ EBC patients likely to benefit from [18F]FDG-PET imaging as a tool to guide therapy. TRIAL REGISTRATION Clinicaltrials.gov; NCT03161353; registration date: May 15, 2017.
Collapse
Affiliation(s)
- Antonio Llombart-Cussac
- Hospital Arnau de Vilanova, FISABIO, Valencia, Spain.
- Universidad Católica de Valencia, Valencia, Spain.
- Medica Scientia Innovation Research (MEDSIR), Barcelona, Spain.
| | - Aleix Prat
- Hospital Clínic i Provincial de Barcelona, Barcelona, Spain
- University of Barcelona, Barcelona, Spain
- Translational Genomics and Targeted Therapies in Solid Tumors Lab., Barcelona, Spain
| | - José Manuel Pérez-García
- Medica Scientia Innovation Research (MEDSIR), Barcelona, Spain
- International Breast Cancer Center, Pangea Oncology, QuironSalud Group, Barcelona, Spain
| | | | - Tomás Pascual
- Hospital Clínic i Provincial de Barcelona, Barcelona, Spain
| | | | | | | | | | | | - Patricia Galvan
- Translational Genomics and Targeted Therapies in Solid Tumors Lab., Barcelona, Spain
| | - Fara Brasó-Maristany
- Translational Genomics and Targeted Therapies in Solid Tumors Lab., Barcelona, Spain
| | - Juan José García-Mosquera
- Dr. Rosell Oncology Institute (IOR), Dexeus University Hospital, Pangaea Oncology, Quironsalud Group, Barcelona, Spain
| | - Thomas Guiot
- Université Libre de Bruxelles, Hôpital Universitaire de Bruxelles, Institute Jules Bordet, Brussels, Belgium
| | | | | | | | | | - Manuel Atienza de Frutos
- Universidad Europea de Madrid, Faculty of Biomedical and Health Sciences, Department of Medicine, Madrid, Spain
| | - Javier Cortés
- Universidad Católica de Valencia, Valencia, Spain
- International Breast Cancer Center, Pangea Oncology, QuironSalud Group, Barcelona, Spain
- Universidad Europea de Madrid, Faculty of Biomedical and Health Sciences, Department of Medicine, Madrid, Spain
| | - Geraldine Gebhart
- Université Libre de Bruxelles, Hôpital Universitaire de Bruxelles, Institute Jules Bordet, Brussels, Belgium
| |
Collapse
|
3
|
Mori M, Fujioka T, Hara M, Katsuta L, Yashima Y, Yamaga E, Yamagiwa K, Tsuchiya J, Hayashi K, Kumaki Y, Oda G, Nakagawa T, Onishi I, Kubota K, Tateishi U. Deep Learning-Based Image Quality Improvement in Digital Positron Emission Tomography for Breast Cancer. Diagnostics (Basel) 2023; 13:diagnostics13040794. [PMID: 36832283 PMCID: PMC9955555 DOI: 10.3390/diagnostics13040794] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2023] [Revised: 02/14/2023] [Accepted: 02/18/2023] [Indexed: 02/22/2023] Open
Abstract
We investigated whether 18F-fluorodeoxyglucose positron emission tomography (PET)/computed tomography images restored via deep learning (DL) improved image quality and affected axillary lymph node (ALN) metastasis diagnosis in patients with breast cancer. Using a five-point scale, two readers compared the image quality of DL-PET and conventional PET (cPET) in 53 consecutive patients from September 2020 to October 2021. Visually analyzed ipsilateral ALNs were rated on a three-point scale. The standard uptake values SUVmax and SUVpeak were calculated for breast cancer regions of interest. For "depiction of primary lesion", reader 2 scored DL-PET significantly higher than cPET. For "noise", "clarity of mammary gland", and "overall image quality", both readers scored DL-PET significantly higher than cPET. The SUVmax and SUVpeak for primary lesions and normal breasts were significantly higher in DL-PET than in cPET (p < 0.001). Considering the ALN metastasis scores 1 and 2 as negative and 3 as positive, the McNemar test revealed no significant difference between cPET and DL-PET scores for either reader (p = 0.250, 0.625). DL-PET improved visual image quality for breast cancer compared with cPET. SUVmax and SUVpeak were significantly higher in DL-PET than in cPET. DL-PET and cPET exhibited comparable diagnostic abilities for ALN metastasis.
Collapse
Affiliation(s)
- Mio Mori
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Tomoyuki Fujioka
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
- Correspondence: ; Tel.: +81-3-5803-5311
| | - Mayumi Hara
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Leona Katsuta
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Yuka Yashima
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Emi Yamaga
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Ken Yamagiwa
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Junichi Tsuchiya
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Kumiko Hayashi
- Department of Surgery, Breast Surgery, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Yuichi Kumaki
- Department of Surgery, Breast Surgery, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Goshi Oda
- Department of Surgery, Breast Surgery, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Tsuyoshi Nakagawa
- Department of Surgery, Breast Surgery, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Iichiroh Onishi
- Department of Comprehensive Pathology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| | - Kazunori Kubota
- Department of Radiology, Dokkyo Medical University Saitama Medical Center, 2-1-50 Minamiko-shigaya, Koshigaya 343-8555, Japan
| | - Ukihide Tateishi
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan
| |
Collapse
|
4
|
Fujioka T, Satoh Y, Imokawa T, Mori M, Yamaga E, Takahashi K, Kubota K, Onishi H, Tateishi U. Proposal to Improve the Image Quality of Short-Acquisition Time-Dedicated Breast Positron Emission Tomography Using the Pix2pix Generative Adversarial Network. Diagnostics (Basel) 2022; 12:diagnostics12123114. [PMID: 36553120 PMCID: PMC9777139 DOI: 10.3390/diagnostics12123114] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Revised: 11/26/2022] [Accepted: 12/07/2022] [Indexed: 12/14/2022] Open
Abstract
This study aimed to evaluate the ability of the pix2pix generative adversarial network (GAN) to improve the image quality of low-count dedicated breast positron emission tomography (dbPET). Pairs of full- and low-count dbPET images were collected from 49 breasts. An image synthesis model was constructed using pix2pix GAN for each acquisition time with training (3776 pairs from 16 breasts) and validation data (1652 pairs from 7 breasts). Test data included dbPET images synthesized by our model from 26 breasts with short acquisition times. Two breast radiologists visually compared the overall image quality of the original and synthesized images derived from the short-acquisition time data (scores of 1−5). Further quantitative evaluation was performed using a peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In the visual evaluation, both readers revealed an average score of >3 for all images. The quantitative evaluation revealed significantly higher SSIM (p < 0.01) and PSNR (p < 0.01) for 26 s synthetic images and higher PSNR for 52 s images (p < 0.01) than for the original images. Our model improved the quality of low-count time dbPET synthetic images, with a more significant effect on images with lower counts.
Collapse
Affiliation(s)
- Tomoyuki Fujioka
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Tokyo 113-8510, Japan
| | - Yoko Satoh
- Yamanashi PET Imaging Clinic, Chuo City 409-3821, Japan
- Department of Radiology, University of Yamanashi, Chuo City 409-3898, Japan
- Correspondence:
| | - Tomoki Imokawa
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Tokyo 113-8510, Japan
| | - Mio Mori
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Tokyo 113-8510, Japan
| | - Emi Yamaga
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Tokyo 113-8510, Japan
| | - Kanae Takahashi
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Tokyo 113-8510, Japan
| | - Kazunori Kubota
- Department of Radiology, Dokkyo Medical University Saitama Medical Center, Koshigaya 343-8555, Japan
| | - Hiroshi Onishi
- Department of Radiology, University of Yamanashi, Chuo City 409-3898, Japan
| | - Ukihide Tateishi
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Tokyo 113-8510, Japan
| |
Collapse
|
5
|
Comparison of 18F-fluorothymidine Positron Emission Tomography/Computed Tomography and 18F-fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in Patients with Breast Cancer. Tomography 2022; 8:2533-2546. [PMID: 36287810 PMCID: PMC9611609 DOI: 10.3390/tomography8050211] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2022] [Revised: 10/08/2022] [Accepted: 10/09/2022] [Indexed: 11/07/2022] Open
Abstract
The uptake of 18F-fluorothymidine (18F-FLT) depends on cells' proliferative rates. We compared the characteristics of 18F-FLT positron emission tomography/computed tomography (PET/CT) with those of 18F-fluorodeoxyglucose (18F-FDG) PET/CT for breast cancer. We prospectively diagnosed patients with breast cancer who underwent 18F-FLT PET/CT and 18F-FDG PET/CT. Subsequently, significant differences and correlation coefficients of the maximum standardized uptake value (SUVmax) in primary breast cancer and axillary lymph nodes were statistically evaluated. We enrolled eight patients with breast cancer. In six treatment-naive patients, the SUVmax for primary lesions showed a significant difference (mean, 2.1 vs. 4.1, p = 0.031) and a strong correlation (r = 0.969) between 18F-FLT and 18F-FDG. Further, although the SUVmax for the axillary lymph nodes did not show a significant difference between 18F-FLT and 18F-FDG (P = 0.246), there was a strong correlation between the two (r = 0.999). In a patient-by-patient study, there were cases in which only 18F-FDG uptake was observed in lymph nodes and normal breasts. Bone metastases demonstrated lower accumulation than bone marrow on the 18F-FLT PET/CT. In conclusion, a strong correlation was observed between the 18F-FLT PET/CT and 18F-FDG PET/CT uptake. Differences in the biochemical characteristics of 18F-FLT and 18F-FDG were reflected in the accumulation differences for breast cancer, metastatic lesions, and normal organs.
Collapse
|
6
|
Groheux D. FDG-PET/CT for Primary Staging and Detection of Recurrence of Breast Cancer. Semin Nucl Med 2022; 52:508-519. [PMID: 35636977 DOI: 10.1053/j.semnuclmed.2022.05.001] [Citation(s) in RCA: 26] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Accepted: 05/04/2022] [Indexed: 12/22/2022]
Abstract
Breast cancer is the most frequent cancer diagnosed in women worldwide. Accurate baseline staging is necessary to plan optimal breast cancer management. Early detection and staging of recurrence are also essential for optimal therapeutic management. Hybrid FDG-PET/CT imaging offers high sensitivity in detecting extra axillary lymph nodes and distant metastases. Although FDG-PET/CT has some limitations for low proliferative tumors, low-grade tumors and for well-differentiated luminal breast cancer, PET/CT is useful for the initial staging of breast cancer, regardless of tumor phenotype (luminal, triple negative, or HER2+) and of tumor grade. Although FDG-PET/CT performs better for invasive ductal carcinoma (invasive carcinoma of no specific subtype), it is also helpful for staging invasive lobular carcinomas. At initial staging, FDG-PET/CT becomes very useful for staging from clinical stage IIB (T2N1 or T3N0). FDG-PET/CT could be useful in patients with clinical stage IIA (T1N1 or T2N0), but there is not enough strong evidence to recommend routine use in this subgroup. For clinical stage I (T1N0) patients, FDG-PET/CT offers no added value. In patients with recurrent breast cancer, FDG-PET/CT is more effective than conventional imaging in detecting locoregional or distant recurrence, whether suspected by clinical examination, conventional imaging, or elevation of a tumor marker (CA 15.3 or CEA). PET/CT is effective even in the presence of normal tumor markers. PET/CT is also a powerful imaging modality for performing a whole-body workup of a known recurrence and for determining whether or not the recurrence is isolated.
Collapse
Affiliation(s)
- David Groheux
- Department of Nuclear Medicine, Saint-Louis Hospital, Paris, France; University Paris-Diderot, INSERM U976, HIPI, Paris, France; Centre d'Imagerie Radio-isotopique, La Rochelle, France.
| |
Collapse
|
7
|
Satoh Y, Imokawa T, Fujioka T, Mori M, Yamaga E, Takahashi K, Takahashi K, Kawase T, Kubota K, Tateishi U, Onishi H. Deep learning for image classification in dedicated breast positron emission tomography (dbPET). Ann Nucl Med 2022; 36:401-410. [PMID: 35084712 DOI: 10.1007/s12149-022-01719-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2021] [Accepted: 01/13/2022] [Indexed: 11/27/2022]
Abstract
OBJECTIVE This study aimed to investigate and determine the best deep learning (DL) model to predict breast cancer (BC) with dedicated breast positron emission tomography (dbPET) images. METHODS Of the 1598 women who underwent dbPET examination between April 2015 and August 2020, a total of 618 breasts on 309 examinations for 284 women who were diagnosed with BC or non-BC were analyzed in this retrospective study. The Xception-based DL model was trained to predict BC or non-BC using dbPET images from 458 breasts of 109 BCs and 349 non-BCs, which consisted of mediallateral and craniocaudal maximum intensity projection images, respectively. It was tested using dbPET images from 160 breasts of 43 BC and 117 non-BC. Two expert radiologists and two radiology residents also interpreted them. Sensitivity, specificity, and area under the receiver operating characteristic curves (AUCs) were calculated. RESULTS Our DL model had a sensitivity and specificity of 93% and 93%, respectively, while radiologists had a sensitivity and specificity of 77-89% and 79-100%, respectively. Diagnostic performance of our model (AUC = 0.937) tended to be superior to that of residents (AUC = 0.876 and 0.868, p = 0.073 and 0.073), although not significantly different. Moreover, no significant differences were found between the model and experts (AUC = 0.983 and 0.941, p = 0.095 and 0.907). CONCLUSIONS Our DL model could be applied to dbPET and achieve the same diagnostic ability as that of experts.
Collapse
Affiliation(s)
- Yoko Satoh
- Yamanashi PET Imaging Clinic, Chuo City, Yamanashi Prefecture, Japan
- Department of Radiology, University of Yamanashi, Chuo City, Yamanashi Prefecture, Japan
| | - Tomoki Imokawa
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan
| | - Tomoyuki Fujioka
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan.
| | - Mio Mori
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan
| | - Emi Yamaga
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan
| | - Kanae Takahashi
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan
| | - Keiko Takahashi
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan
| | - Takahiro Kawase
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan
| | - Kazunori Kubota
- Department of Radiology, Dokkyo Medical University Saitama Medical Center, Koshigaya City, Saitama Prefecture, Japan
| | - Ukihide Tateishi
- Department of Diagnostic Radiology, Tokyo Medical and Dental University, Bunkyo Ku, Tokyo, Japan
| | - Hiroshi Onishi
- Department of Radiology, University of Yamanashi, Chuo City, Yamanashi Prefecture, Japan
| |
Collapse
|