ABSTRACT
Purpose: Automatic quantification of longitudinal changes in PET scans for lymphoma patients has proven challenging, as residual disease in interim-therapy scans is often subtle and difficult to detect. Our goal was to develop a longitudinally-aware segmentation network (LAS-Net) that can quantify serial PET/CT images for pediatric Hodgkin lymphoma patients. Materials and Methods: This retrospective study included baseline (PET1) and interim (PET2) PET/CT images from 297 patients enrolled in two Children's Oncology Group clinical trials (AHOD1331 and AHOD0831). LAS-Net incorporates longitudinal cross-attention, allowing relevant features from PET1 to inform the analysis of PET2. Model performance was evaluated using Dice coefficients for PET1 and detection F1 scores for PET2. Additionally, we extracted and compared quantitative PET metrics, including metabolic tumor volume (MTV) and total lesion glycolysis (TLG) in PET1, as well as qPET and ΔSUVmax in PET2, against physician measurements. We quantified their agreement using Spearman's ρ correlations and employed bootstrap resampling for statistical analysis. Results: LAS-Net detected residual lymphoma in PET2 with an F1 score of 0.606 (precision/recall: 0.615/0.600), outperforming all comparator methods (P<0.01). For baseline segmentation, LAS-Net achieved a mean Dice score of 0.772. In PET quantification, LAS-Net's measurements of qPET, ΔSUVmax, MTV and TLG were strongly correlated with physician measurements, with Spearman's ρ of 0.78, 0.80, 0.93 and 0.96, respectively. The performance remained high, with a slight decrease, in an external testing cohort. Conclusion: LAS-Net achieved high performance in quantifying PET metrics across serial scans, highlighting the value of longitudinal awareness in evaluating multi-time-point imaging datasets.
ABSTRACT
Large language models (LLMs) have shown promise in accelerating radiology reporting by summarizing clinical findings into impressions. However, automatic impression generation for whole-body PET reports presents unique challenges and has received little attention. Our study aimed to evaluate whether LLMs can create clinically useful impressions for PET reporting. To this end, we fine-tuned twelve open-source language models on a corpus of 37,370 retrospective PET reports collected from our institution. All models were trained using the teacher-forcing algorithm, with the report findings and patient information as input and the original clinical impressions as reference. An extra input token encoded the reading physician's identity, allowing models to learn physician-specific reporting styles. To compare the performances of different models, we computed various automatic evaluation metrics and benchmarked them against physician preferences, ultimately selecting PEGASUS as the top LLM. To evaluate its clinical utility, three nuclear medicine physicians assessed the PEGASUS-generated impressions and original clinical impressions across 6 quality dimensions (3-point scales) and an overall utility score (5-point scale). Each physician reviewed 12 of their own reports and 12 reports from other physicians. When physicians assessed LLM impressions generated in their own style, 89% were considered clinically acceptable, with a mean utility score of 4.08/5. On average, physicians rated these personalized impressions as comparable in overall utility to the impressions dictated by other physicians (4.03, P = 0.41). In summary, our study demonstrated that personalized impressions generated by PEGASUS were clinically useful in most cases, highlighting its potential to expedite PET reporting by automatically drafting impressions.
ABSTRACT
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-[18F]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 < 0.001) state-of-the-art (SOTA) approaches including nnU-Net and SWIN UNETR. While TTA yielded enhanced performance gains for some of the comparator methods, its impact on our cascaded approach was found to be negligible (DSC: 0.66 ± 0.16). Our approach reliably quantified TMTV, with a correlation of 0.89 with the ground truth (p < 0.001). Furthermore, in terms of visual assessment, concordance between quantitative evaluations and clinician feedback was observed in the majority of cases. The average relative error (ARE) and the absolute error (AE) in TMTV prediction on external multi-centric dataset were ARE = 0.43 ± 0.54 and AE = 157.32 ± 378.12 (mL) for all the external test data (n = 518), and ARE = 0.30 ± 0.22 and AE = 82.05 ± 99.78 (mL) when the 10% outliers (n = 53) were excluded. CONCLUSION: TMTV-Net demonstrates strong performance and generalizability in TMTV segmentation across multi-site external datasets, encompassing various lymphoma subtypes. A negligible reduction of 2% in overall performance during testing on external data highlights robust model generalizability across different centers and cancer types, likely attributable to its training with resampled inputs. Our model is publicly available, allowing easy multi-site evaluation and generalizability analysis on datasets from different institutions.
Subject(s)
Image Processing, Computer-Assisted , Lymphoma , Positron Emission Tomography Computed Tomography , Tumor Burden , Humans , Positron Emission Tomography Computed Tomography/methods , Lymphoma/diagnostic imaging , Image Processing, Computer-Assisted/methods , Fluorodeoxyglucose F18 , Automation , Male , FemaleABSTRACT
Purpose: To determine if fine-tuned large language models (LLMs) can generate accurate, personalized impressions for whole-body PET reports. Materials and Methods: Twelve language models were trained on a corpus of PET reports using the teacher-forcing algorithm, with the report findings as input and the clinical impressions as reference. An extra input token encodes the reading physician's identity, allowing models to learn physician-specific reporting styles. Our corpus comprised 37,370 retrospective PET reports collected from our institution between 2010 and 2022. To identify the best LLM, 30 evaluation metrics were benchmarked against quality scores from two nuclear medicine (NM) physicians, with the most aligned metrics selecting the model for expert evaluation. In a subset of data, model-generated impressions and original clinical impressions were assessed by three NM physicians according to 6 quality dimensions (3-point scale) and an overall utility score (5-point scale). Each physician reviewed 12 of their own reports and 12 reports from other physicians. Bootstrap resampling was used for statistical analysis. Results: Of all evaluation metrics, domain-adapted BARTScore and PEGASUSScore showed the highest Spearman's ρ correlations (ρ=0.568 and 0.563) with physician preferences. Based on these metrics, the fine-tuned PEGASUS model was selected as the top LLM. When physicians reviewed PEGASUS-generated impressions in their own style, 89% were considered clinically acceptable, with a mean utility score of 4.08 out of 5. Physicians rated these personalized impressions as comparable in overall utility to the impressions dictated by other physicians (4.03, P=0.41). Conclusion: Personalized impressions generated by PEGASUS were clinically useful, highlighting its potential to expedite PET reporting.
ABSTRACT
BACKGROUND: The implication of residual metaiodobenzylguanidine (MIBG)-positive disease in the era of tandem high-dose chemotherapy (HDCT) with autologous stem cell transplantation (auto-SCT) has not yet been established in neuroblastoma. Moreover, most published studies have not evaluated the long-term prognosis of patients with residual MIBG-positive disease following treatment completion. Therefore, we investigated the prognostic significance of residual MIBG-positive disease at each treatment phase and after treatment completion. METHODS: We assessed MIBG scans labeled with either iodine-123 (123 I) or 131 I from 150 patients with MIBG-avid and high-risk neuroblastoma enrolled in the NB-2004, -2009, and -2014 trials at postinduction, posttandem HDCT/auto-SCT, and completion of treatment. RESULTS: The residual MIBG-positive disease at postinduction and posttandem HDCT/auto-SCT evaluation was highly correlated with the risk of progression. However, at treatment completion, there was no significant difference in survival and risk of progression between patients with residual MIBG-positive disease and MIBG-negative patients. Patients with persistent MIBG-positive disease at the end of treatment were more likely to have indolent tumor characteristics, such as favorable histology at diagnosis, lower incidence of MYCN amplification, and slow response to chemotherapy. CONCLUSION: Residual MIBG-positive disease during treatment predicted unfavorable outcomes for patients with high-risk neuroblastoma, even under tandem HDCT/auto-SCT. However, persistent MIBG uptake at the completion of all treatments may not always indicate an active disease.
Subject(s)
Hematopoietic Stem Cell Transplantation , Neuroblastoma , 3-Iodobenzylguanidine , Antineoplastic Combined Chemotherapy Protocols/therapeutic use , Follow-Up Studies , Humans , Infant , Neoplasm, Residual/drug therapy , Neuroblastoma/drug therapy , Neuroblastoma/therapy , Stem Cell Transplantation , Transplantation, AutologousABSTRACT
PURPOSE: 99mTc-labeled sestamibi scintigraphy combined with single-photon emission computed tomography (SPECT) has a high positive predictive value for localizing hyperfunctioning parathyroid lesions in primary hyperparathyroidism (pHPT) but relatively low sensitivity and specificity in secondary hyperparathyroidism (sHPT) and tertiary hyperparathyroidism (tHPT). The purpose of this study is to investigate the usefulness of 99mTc-sestamibi scintigraphy in persistent hyperparathyroidism after kidney transplant (KT). METHODS: Retrospectively evaluated 50 patients who received parathyroidectomy after KT at a single medical center. The parathyroid lesion with the highest sestamibi uptake intensity of a patient was graded from 0 to 3. Uptake intensity was analyzed in correlation with parathyroid hormone (PTH), calcium, ionized calcium, phosphorus, and vitamin D. RESULTS: Per-patient analysis, 43 patients had hyperplasia, 6 patients had adenomas, and 1 patient had a carcinoma. Only 3 patients with hyperplasia did not demonstrate any sestamibi uptake in the parathyroid scans. Out of the 148 pathologically confirmed parathyroid lesions, SPECT/CT images were able to identify 89 lesions (60%) and planar images of 71 lesions (48%). The average of sestamibi uptake intensity was mild at grade 1.6. Uptake intensity showed a positive correlation with parathyroid hormone (PTH) level but not with phosphorus, calcium, ionized calcium, or vitamin D levels. The largest lesion showed a high positive predictive value, especially in lesions with a diameter over 1.0 cm. CONCLUSIONS: Regardless of relatively low and less discrete uptake in KT patients, it well depicts the largest and the most hyperfunctioning lesion.
ABSTRACT
PURPOSE: This study investigated 18F-FDG PET/CT features of adenovirus-vectored vaccination against COVID-19 in healthy subjects. PATIENTS AND METHODS: Thirty-one health care workers had been vaccinated Vaxzevria and underwent FDG PET/CT as an optional test for a cancer screening program. Size and FDG uptake of the hypermetabolic lymph nodes were measured. Uptake value of spleen was also measured with liver for comparison. RESULTS: All examinees who underwent FDG PET/CT within 14 days' interval showed hypermetabolic lymphadenopathies ipsilateral to vaccine injection. All examinees with hypermetabolic lymphadenopathy had simultaneous muscular uptakes until 23 days' interval. Among 12 examinees who underwent FDG PET/CT more than 15 days after vaccination, only 3 male examinees did not show hypermetabolism in the axillary lymph nodes. There was no female examinee with negative hypermetabolic lymphadenopathy until 29 days after vaccination. CONCLUSIONS: Hypermetabolic reactive lymphadenopathy in the ipsilateral axillary area with or without supraclavicular area is most likely to occur in a healthy person with recent adenovirus-vectored COVID-19 vaccination on FDG PET/CT.
Subject(s)
Adenovirus Vaccines , COVID-19 , Lymphadenopathy , Adenoviridae , COVID-19 Vaccines , Fluorodeoxyglucose F18 , Humans , Lymphadenopathy/diagnostic imaging , Male , Positron Emission Tomography Computed Tomography , SARS-CoV-2 , VaccinationABSTRACT
This study aimed to identify the prognostic subgroups of stage 4 high-risk neuroblastoma based on metastatic burden and explore their distinct clinical and genomic features. Patients aged ≥18 months with stage 4 and metaiodobenzylguanidine-avid neuroblastoma were enrolled. One hundred and thirty eligible patients were treated under the tandem high-dose chemotherapy scheme. Prognostic significance of metastatic burden measured by the modified Curie score was analyzed using a competing risk approach, and the optimal cut-point was determined. Metastasis-specific subgroups (cut-point: 26) were compared using clinicopathological variables, and differential gene expression analysis and gene set variation analysis (GSVA) were performed using RNA sequencing (RNA-seq). Metastatic burden at diagnosis showed a progressive association with relapse/progression. After applying the cut-point, patients with high metastatic burden showed >3-fold higher risk of relapse/progression than those with low metastatic burden. Moreover, patients with high metastatic burden showed smaller primary tumors and higher biochemical marker levels than those with low metastatic burden. In the genomic analysis, 51 genes were found to be differentially expressed based on the set criteria. GSVA revealed 55 gene sets, which significantly distinguished patients with high metastatic burden from those with low metastatic burden at a false discovery rate <0.25. The results indicated the prognostic significance of metastatic burden in stage 4 high-risk neuroblastoma, and we identified the distinct clinicopathological and genomic features based on metastatic burden. This study may aid in the better understanding and risk-stratification of stage 4 high-risk neuroblastoma patients.
ABSTRACT
PURPOSE: Considerable discrepancies are observed between clinical staging and pathological staging after surgical resection in patients with esophageal squamous cell carcinoma (ESCC). In this study, we examined the relationships between tumor SUVs on FDG PET/CT and aggressive pathological features in resected ESCC patients. METHODS: A total of 220 patients with surgically resected clinical stage I-II ESCC without neoadjuvant treatment were retrospectively analyzed. SUVmax of the primary tumor was measured on pretreatment FDG PET/CT. Pathological features included depth of tumor invasion, lymph node metastasis, tumor differentiation, lymphatic vessel tumor embolus, perineural invasion, Ki-67 index, and p53 protein expression. Receiver operating characteristic curve analysis was used to determine an optimal cutoff of SUVmax to predict pathologically advanced disease. Differences in pathological features associated with SUVmax were examined by t test or χ test. RESULTS: The number of patients upstaged from clinical stage I-II to pathological stage III-IV was 43 (19.5%). Receiver operating characteristic curve analysis showed that the optimal cutoff SUVmax of 4.0 had good performance for predicting locally advanced disease (area under the receiver operating characteristic curve = 0.844, P < 0.001). Higher tumor SUVmax was significantly associated with advanced depth of tumor invasion (deeper than submucosa, P < 0.001), positive lymph node metastasis (P < 0.001), presence of lymphatic vessel tumor embolus (P < 0.001), presence of perineural invasion (P < 0.001), higher Ki-67 index (P = 0.025), and poor tumor differentiation (P = 0.039). CONCLUSIONS: SUVmax measured on pretreatment FDG PET/CT is significantly associated with aggressive pathological features and may help clinicians identify patients at risk of advanced disease.