Automatic Segmentation of Metastatic Breast Cancer Lesions on F-FDG PET/CT Longitudinal Acquisitions for Treatment Response Assessment

Overview

Journal Cancers (Basel)

Publisher MDPI

Specialty Oncology

Date 2022 Jan 11

PMID 35008265

Authors

Noemie Moreau

Caroline Rousseau

Constance Fourcade

Gianmarco Santini

Aislinn Brennan

Ludovic Ferrer

Marie Lacombe

Camille Guillerminet

Mathilde Colombie

Pascal Jezequel

Mario Campone

Nicolas Normand

Mathieu Rubeaux

Affiliations

Soon will be listed here.

Abstract

Metastatic breast cancer patients receive lifelong medication and are regularly monitored for disease progression. The aim of this work was to (1) propose networks to segment breast cancer metastatic lesions on longitudinal whole-body PET/CT and (2) extract imaging biomarkers from the segmentations and evaluate their potential to determine treatment response. Baseline and follow-up PET/CT images of 60 patients from the EPICUREseinmeta study were used to train two deep-learning models to segment breast cancer metastatic lesions: One for baseline images and one for follow-up images. From the automatic segmentations, four imaging biomarkers were computed and evaluated: SULpeak, Total Lesion Glycolysis (TLG), PET Bone Index (PBI) and PET Liver Index (PLI). The first network obtained a mean Dice score of 0.66 on baseline acquisitions. The second network obtained a mean Dice score of 0.58 on follow-up acquisitions. SULpeak, with a 32% decrease between baseline and follow-up, was the biomarker best able to assess patients' response (sensitivity 87%, specificity 87%), followed by TLG (43% decrease, sensitivity 73%, specificity 81%) and PBI (8% decrease, sensitivity 69%, specificity 69%). Our networks constitute promising tools for the automatic segmentation of lesions in patients with metastatic breast cancer allowing treatment response assessment with several biomarkers.

Citing Articles

Deep learning for oncologic treatment outcomes and endpoints evaluation from CT scans in liver cancer.

Xia Y, Zhou J, Xun X, Johnston L, Wei T, Gao R NPJ Precis Oncol. 2024; 8(1):263.

PMID: 39551847 PMC: 11570623. DOI: 10.1038/s41698-024-00754-z.

The Application of Radiomics and AI to Molecular Imaging for Prostate Cancer.

Tapper W, Carneiro G, Mikropoulos C, Thomas S, Evans P, Boussios S J Pers Med. 2024; 14(3).

PMID: 38541029 PMC: 10971024. DOI: 10.3390/jpm14030287.

Current Role and Future Prospects of Positron Emission Tomography (PET)/Computed Tomography (CT) in the Management of Breast Cancer.

Robson N, Thekkinkattil D Medicina (Kaunas). 2024; 60(2).

PMID: 38399608 PMC: 10889944. DOI: 10.3390/medicina60020321.

Impact of Imaging Biomarkers and AI on Breast Cancer Management: A Brief Review.

Saleh G, Batouty N, Gamal A, Elnakib A, Hamdy O, Sharafeldeen A Cancers (Basel). 2023; 15(21).

PMID: 37958390 PMC: 10650187. DOI: 10.3390/cancers15215216.

State-of-the-Art of Breast Cancer Diagnosis in Medical Images via Convolutional Neural Networks (CNNs).

Harrison P, Hasan R, Park K J Healthc Inform Res. 2023; 7(4):387-432.

PMID: 37927373 PMC: 10620373. DOI: 10.1007/s41666-023-00144-3.

References

Cook G, Azad G, Goh V . Imaging Bone Metastases in Breast Cancer: Staging and Response Assessment. J Nucl Med. 2016; 57 Suppl 1:27S-33S. DOI: 10.2967/jnumed.115.157867. View

Foster B, Bagci U, Mansoor A, Xu Z, Mollura D . A review on segmentation of positron emission tomography images. Comput Biol Med. 2014; 50:76-96. PMC: 4060809. DOI: 10.1016/j.compbiomed.2014.04.014. View

Youden W . Index for rating diagnostic tests. Cancer. 1950; 3(1):32-5. DOI: 10.1002/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2-3. View

Moreau N, Rousseau C, Fourcade C, Santini G, Ferrer L, Lacombe M . Deep learning approaches for bone and bone lesion segmentation on 18FDG PET/CT imaging in the context of metastatic breast cancer. Annu Int Conf IEEE Eng Med Biol Soc. 2020; 2020:1532-1535. DOI: 10.1109/EMBC44109.2020.9175904. View

Heller N, Isensee F, Maier-Hein K, Hou X, Xie C, Li F . The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge. Med Image Anal. 2020; 67:101821. PMC: 7734203. DOI: 10.1016/j.media.2020.101821. View

Eichbaum M, Kaltwasser M, Bruckner T, de Rossi T, Schneeweiss A, Sohn C . Prognostic factors for patients with liver metastases from breast cancer. Breast Cancer Res Treat. 2005; 96(1):53-62. DOI: 10.1007/s10549-005-9039-1. View

Antonelli M, Reinke A, Bakas S, Farahani K, Kopp-Schneider A, Landman B . The Medical Segmentation Decathlon. Nat Commun. 2022; 13(1):4128. PMC: 9287542. DOI: 10.1038/s41467-022-30695-9. View

Wahl R, Jacene H, Kasamon Y, Lodge M . From RECIST to PERCIST: Evolving Considerations for PET response criteria in solid tumors. J Nucl Med. 2009; 50 Suppl 1:122S-50S. PMC: 2755245. DOI: 10.2967/jnumed.108.057307. View

OShaughnessy J . Extending survival with chemotherapy in metastatic breast cancer. Oncologist. 2005; 10 Suppl 3:20-9. DOI: 10.1634/theoncologist.10-90003-20. View

10.

Gudi S, Ghosh-Laskar S, Agarwal J, Chaudhari S, Rangarajan V, Paul S . Interobserver Variability in the Delineation of Gross Tumour Volume and Specified Organs-at-risk During IMRT for Head and Neck Cancers and the Impact of FDG-PET/CT on Such Variability at the Primary Site. J Med Imaging Radiat Sci. 2019; 48(2):184-192. DOI: 10.1016/j.jmir.2016.11.003. View

11.

Riedl C, Pinker K, Ulaner G, Ong L, Baltzer P, Jochelson M . Comparison of FDG-PET/CT and contrast-enhanced CT for monitoring therapy response in patients with metastatic breast cancer. Eur J Nucl Med Mol Imaging. 2017; 44(9):1428-1437. PMC: 5526620. DOI: 10.1007/s00259-017-3703-7. View

12.

O J, Lodge M, Wahl R . Practical PERCIST: A Simplified Guide to PET Response Criteria in Solid Tumors 1.0. Radiology. 2016; 280(2):576-84. PMC: 4976461. DOI: 10.1148/radiol.2016142043. View

13.

Blanc-Durand P, Jegou S, Kanoun S, Berriolo-Riedinger A, Bodet-Milin C, Kraeber-Bodere F . Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network. Eur J Nucl Med Mol Imaging. 2020; 48(5):1362-1370. DOI: 10.1007/s00259-020-05080-7. View

14.

Kruger J, Opfer R, Gessert N, Ostwaldt A, Manogaran P, Kitzler H . Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks. Neuroimage Clin. 2020; 28:102445. PMC: 7554211. DOI: 10.1016/j.nicl.2020.102445. View

15.

Yang H, Liu T, Wang X, Xu Y, Deng S . Diagnosis of bone metastases: a meta-analysis comparing ¹⁸FDG PET, CT, MRI and bone scintigraphy. Eur Radiol. 2011; 21(12):2604-17. DOI: 10.1007/s00330-011-2221-4. View

16.

Tahari A, Chien D, Azadi J, Wahl R . Optimum lean body formulation for correction of standardized uptake value in PET imaging. J Nucl Med. 2014; 55(9):1481-4. PMC: 4337860. DOI: 10.2967/jnumed.113.136986. View

17.

Eisenhauer E, Therasse P, Bogaerts J, Schwartz L, Sargent D, Ford R . New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer. 2008; 45(2):228-47. DOI: 10.1016/j.ejca.2008.10.026. View

18.

Choi J, Kim H, Kim W, Lim I, Lee I, Byun B . Early prediction of neoadjuvant chemotherapy response for advanced breast cancer using PET/MRI image deep learning. Sci Rep. 2020; 10(1):21149. PMC: 7712787. DOI: 10.1038/s41598-020-77875-5. View

19.

Hong R, Halama J, Bova D, Sethi A, Emami B . Correlation of PET standard uptake value and CT window-level thresholds for target delineation in CT-based radiation treatment planning. Int J Radiat Oncol Biol Phys. 2007; 67(3):720-6. DOI: 10.1016/j.ijrobp.2006.09.039. View

20.

Sundquist M, Brudin L, Tejler G . Improved survival in metastatic breast cancer 1985-2016. Breast. 2016; 31:46-50. DOI: 10.1016/j.breast.2016.10.005. View