TMTV-Net: fully automated total metabolic tumor volume segmentation in lymphoma PET/CT images — a multi-center generalizability analysis

• Published in: European journal of nuclear medicine and molecular imaging 2024-06, Vol.51 (7), p.1937-1954
• Main Authors: Yousefirizi, Fereshteh, Klyuzhin, Ivan S., O, Joo Hyun, Harsini, Sara, Tie, Xin, Shiri, Isaac, Shin, Muheon, Lee, Changhee, Cho, Steve Y., Bradshaw, Tyler J., Zaidi, Habib, Bénard, François, Sehn, Laurie H., Savage, Kerry J., Steidl, Christian, Uribe, Carlos F., Rahmim, Arman
• Format: Article
• Language: English
• Subjects: Automation; Biomarkers; Cardiology; Computed tomography; Datasets; Female; Fluorodeoxyglucose F18; Hodgkin's lymphoma; Humans; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Imaging; Lung cancer; Lymphoma; Lymphoma - diagnostic imaging; Male; Medical imaging; Medicine; Medicine & Public Health; Melanoma; Metabolism; Nuclear Medicine; Oncology; Original Article; Orthopedics; Outliers (statistics); Performance enhancement; Positron emission; Positron Emission Tomography Computed Tomography - methods; Predictions; Qualitative analysis; Quantitative analysis; Radiology; Resampling; Segmentation; Testing time; Tumor Burden; Tumors; Visual observation
• ISSN: 1619-7070; 1619-7089; 1619-7089
• DOI: 10.1007/s00259-024-06616-x

Purpose Total metabolic tumor volume (TMTV) segmentation has significant value enabling quantitative imaging biomarkers for lymphoma management. In this work, we tackle the challenging task of automated tumor delineation in lymphoma from PET/CT scans using a cascaded approach. Methods Our study included 1418 2-[ 18 F]FDG PET/CT scans from four different centers. The dataset was divided into 900 scans for development/validation/testing phases and 518 for multi-center external testing. The former consisted of 450 lymphoma, lung cancer, and melanoma scans, along with 450 negative scans, while the latter consisted of lymphoma patients from different centers with diffuse large B cell, primary mediastinal large B cell, and classic Hodgkin lymphoma cases. Our approach involves resampling PET/CT images into different voxel sizes in the first step, followed by training multi-resolution 3D U-Nets on each resampled dataset using a fivefold cross-validation scheme. The models trained on different data splits were ensemble. After applying soft voting to the predicted masks, in the second step, we input the probability-averaged predictions, along with the input imaging data, into another 3D U-Net. Models were trained with semi-supervised loss. We additionally considered the effectiveness of using test time augmentation (TTA) to improve the segmentation performance after training. In addition to quantitative analysis including Dice score (DSC) and TMTV comparisons, the qualitative evaluation was also conducted by nuclear medicine physicians. Results Our cascaded soft-voting guided approach resulted in performance with an average DSC of 0.68 ± 0.12 for the internal test data from developmental dataset, and an average DSC of 0.66 ± 0.18 on the multi-site external data ( n  = 518), significantly outperforming ( p