ABSTRACT
Early cancer detection, guided by whole-body imaging, is important for the overall survival and well-being of the patients. While various computer-assisted systems have been developed to expedite and enhance cancer diagnostics and longitudinal monitoring, the detection and segmentation of tumors, especially from whole-body scans, remain challenging. To address this, we propose a novel end-to-end automated framework that first generates a tumor probability distribution map (TPDM), incorporating prior information about the tumor characteristics (e.g. size, shape, location). Subsequently, the TPDM is integrated with a state-of-the-art 3D segmentation network along with the original PET/CT or PET/MR images. This aims to produce more meaningful tumor segmentation masks compared to using the baseline 3D segmentation network alone. The proposed method was evaluated on three independent cohorts (autoPET, CAR-T, cHL) of images containing different cancer forms, obtained with different imaging modalities, and acquisition parameters and lesions annotated by different experts. The evaluation demonstrated the superiority of our proposed method over the baseline model by significant margins in terms of Dice coefficient, and lesion-wise sensitivity and precision. Many of the extremely small tumor lesions (i.e. the most difficult to segment) were missed by the baseline model but detected by the proposed model without additional false positives, resulting in clinically more relevant assessments. On average, an improvement of 0.0251 (autoPET), 0.144 (CAR-T), and 0.0528 (cHL) in overall Dice was observed. In conclusion, the proposed TPDM-based approach can be integrated with any state-of-the-art 3D UNET with potentially more accurate and robust segmentation results.
ABSTRACT
BACKGROUND: Statistical atlases can provide population-based descriptions of healthy volunteers and/or patients and can be used for region- and voxel-based analysis. This work aims to develop whole-body diffusion atlases of healthy volunteers scanned at 1.5T and 3T. Further aims include evaluating the atlases by establishing whole-body Apparent Diffusion Coefficient (ADC) values of healthy tissues and including healthy tissue deviations in an automated tumour segmentation task. METHODS: Multi-station whole-body Diffusion Weighted Imaging (DWI) and water-fat Magnetic Resonance Imaging (MRI) of healthy volunteers (n = 45) were acquired at 1.5T (n = 38) and/or 3T (n = 29), with test-retest imaging for five subjects per scanner. Using deformable image registration, whole-body MRI data was registered and composed into normal atlases. Healthy tissue ADCmean was manually measured for ten tissues, with test-retest percentage Repeatability Coefficient (%RC), and effect of age, sex and scanner assessed. Voxel-wise whole-body analyses using the normal atlases were studied with ADC correlation analyses and an automated tumour segmentation task. For the latter, lymphoma patient MRI scans (n = 40) with and without information about healthy tissue deviations were entered into a 3D U-Net architecture. RESULTS: Sex- and Body Mass Index (BMI)-stratified whole-body high b-value DWI and ADC normal atlases were created at 1.5T and 3T. %RC of healthy tissue ADCmean varied depending on tissue assessed (4-48% at 1.5T, 6-70% at 3T). Scanner differences in ADCmean were visualised in Bland-Altman analyses of dually scanned subjects. Sex differences were measurable for liver, muscle and bone at 1.5T, and muscle at 3T. Volume of Interest (VOI)-based multiple linear regression, and voxel-based correlations in normal atlas space, showed that age and ADC were negatively associated for liver and bone at 1.5T, and positively associated with brain tissue at 1.5T and 3T. Adding voxel-wise information about healthy tissue deviations in an automated tumour segmentation task gave numerical improvements in the segmentation metrics Dice score, sensitivity and precision. CONCLUSIONS: Whole-body DWI and ADC normal atlases were created at 1.5T and 3T, and applied in whole-body voxel-wise analyses.
Subject(s)
Diffusion Magnetic Resonance Imaging , Magnetic Resonance Imaging , Humans , Female , Male , Whole Body Imaging , Liver , BenchmarkingABSTRACT
BACKGROUND: To find semi-quantitative and quantitative Positron Emission Tomography/Magnetic Resonance (PET/MR) imaging metrics of both tumor and non-malignant lymphoid tissue (bone marrow and spleen) for Progression Free Survival (PFS) and Overall Survival (OS) prediction in patients with relapsed/refractory (r/r) large B-cell lymphoma (LBCL) undergoing Chimeric Antigen Receptor (CAR) T-cell therapy. METHODS: A single-center prospective study of 16 r/r LBCL patients undergoing CD19-targeted CAR T-cell therapy. Whole body 18F-fluorodeoxyglucose (FDG) PET/MR imaging pre-therapy and 3 weeks post-therapy were followed by manual segmentation of tumors and lymphoid tissues. Semi-quantitative and quantitative metrics were extracted, and the metric-wise rate of change (Δ) between post-therapy and pre-therapy calculated. Tumor metrics included maximum Standardized Uptake Value (SUVmax), mean SUV (SUVmean), Metabolic Tumor Volume (MTV), Tumor Lesion Glycolysis (TLG), structural volume (V), total structural tumor burden (Vtotal) and mean Apparent Diffusion Coefficient (ADCmean). For lymphoid tissues, metrics extracted were SUVmean, mean Fat Fraction (FFmean) and ADCmean for bone marrow, and SUVmean, V and ADCmean for spleen. Univariate Cox regression analysis tested the relationship between extracted metrics and PFS and OS. Survival curves were produced using Kaplan-Meier analysis and compared using the log-rank test, with the median used for dichotomization. Uncorrected p-values < 0.05 were considered statistically significant. Correction for multiple comparisons was performed, with a False Discovery Rate (FDR) < 0.05 considered statistically significant. RESULTS: Pre-therapy (p < 0.05, FDR < 0.05) and Δ (p < 0.05, FDR > 0.05) total tumor burden structural and metabolic metrics were associated with PFS and/or OS. According to Kaplan-Meier analysis, a longer PFS was reached for patients with pre-therapy MTV ≤ 39.5 ml, ΔMTV≤1.35 and ΔTLG≤1.35. ΔSUVmax was associated with PFS (p < 0.05, FDR > 0.05), while ΔADCmean was associated with both PFS and OS (p < 0.05, FDR > 0.05). ΔADCmean > 0.92 gave longer PFS and OS in the Kaplan-Meier analysis. Pre-therapy bone marrow SUVmean was associated with PFS (p < 0.05, FDR < 0.05) and OS (p < 0.05, FDR > 0.05). For bone marrow FDG uptake, patient stratification was possible pre-therapy (SUVmean ≤ 1.8). CONCLUSIONS: MTV, tumor ADCmean and FDG uptake in bone marrow unaffected by tumor infiltration are possible PET/MR parameters for prediction of PFS and OS in r/r LBCL treated with CAR T-cells. TRIAL REGISTRATION: EudraCT 2016-004043-36.
