Automatic computation of breast cancer biomarkers from multiple ^18 F-FDG PET image segmentation

Abstract Neoadjuvant chemotherapy is a standard clinical practice for tumor downsizing in breast cancer, with ^18 F-FDG Positron Emission Tomography (PET) being an essential tool for predicting complete pathological response and monitoring treatment. Our work aims to leverage PET imaging for automated segmentation of breast lesions and biomarker analysis before and after the first course of chemotherapy. We developed a system to segment primary tumor regions and extract biomarkers reflecting tumor evolution. A total of 243 baseline and 180 follow-up ^18 F-FDG PET scans were acquired. Ground truth annotations were generated semi-automatically for all baseline scans and manually for 12 test cases. A deep learning-based segmentation method was developed and evaluated using various architectures. The optimal baseline model, trained on baseline exams, was fine-tuned on 15 follow-up scans using active learning to segment tumors in follow-up exams. The pipeline extracts maximum standardized uptake value (SUV ₌₀ₗ), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) to assess tumor response. Quality control procedures were used to exclude outliers. Among the tested approaches, nnUNet achieved the best tumor segmentation on PET baseline scans, with a Dice similarity coefficient of 0. 89 0. 04 and a Hausdorff distance of 3. 52 0. 76 mm on the test set. After fine-tuning, performance on follow-up exams reached a Dice similarity coefficient of 0. 78 0. 03 and Hausdorff distance of 4. 95 0. 12 mm. Biomarker analysis showed strong correlations between manual and automatic segmentations. The average SUV₌₀ₗ, MTV, and TLG between 12 baseline and follow-up scans used for testing were -6. 02 1. 55 (p=0. 002), -9. 30 2. 33 cm ³ (p=0. 007), and -14. 09 6. 33 cm ³ (p=0. 010), respectively. The proposed method provides an effective automated system for breast tumor segmentation from ^18 F-FDG PET. Thanks to biomarkers extracted from the automatic segmentations on both baseline and follow-up exams, our method enables the automatic assessment of cancer progression.