Deep-Learning 18F-FDG Uptake Classification Enables Total Metabolic Tumor Volume Estimation in Diffuse Large B-Cell Lymphoma

Fully Automatic Quantitative Measurement of Equilibrium Radionuclide Angiocardiography Using a Convolutional Neural Network

PURPOSE

The aim of this study was to generate deep learning-based regions of interest (ROIs) from equilibrium radionuclide angiography datasets for left ventricular ejection fraction (LVEF) measurement.

PATIENTS AND METHODS

Manually drawn ROIs (mROIs) on end-systolic and end-diastolic images were extracted from reports in a Picture Archiving and Communications System. To reduce observer variability, preprocessed ROIs (pROIs) were delineated using a 41% threshold of the maximal pixel counts of the extracted mROIs and were labeled as ground-truth. Background ROIs were automatically created using an algorithm to identify areas with minimum counts within specified probability areas around the end-systolic ROI. A 2-dimensional U-Net convolutional neural network architecture was trained to generate deep learning-based ROIs (dlROIs) from pROIs. The model's performance was evaluated using Lin's concordance correlation coefficient (CCC). Bland-Altman plots were used to assess bias and 95% limits of agreement.

RESULTS

A total of 41,462 scans (19,309 patients) were included. Strong concordance was found between LVEF measurements from dlROIs and pROIs (CCC = 85.6%; 95% confidence interval, 85.4%-85.9%), and between LVEF measurements from dlROIs and mROIs (CCC = 86.1%; 95% confidence interval, 85.8%-86.3%). In the Bland-Altman analysis, the mean differences and 95% limits of agreement of the LVEF measurements were -0.6% and -6.6% to 5.3%, respectively, for dlROIs and pROIs, and -0.4% and -6.3% to 5.4% for dlROIs and mROIs, respectively. In 37,537 scans (91%), the absolute LVEF difference between dlROIs and mROIs was <5%.

CONCLUSIONS

Our 2-dimensional U-Net convolutional neural network architecture showed excellent performance in generating LV ROIs from equilibrium radionuclide angiography scans. It may enhance the convenience and reproducibility of LVEF measurements.

Metabolic tumour area: a novel prognostic indicator based on 18F-FDG PET/CT in patients with diffuse large B-cell lymphoma in the R-CHOP era

BACKGROUND

The metabolic tumour area (MTA) was found to be a promising predictor of prostate cancer. However, the role of MTA based on 18F-FDG PET/CT in diffuse large B-cell lymphoma (DLBCL) prognosis remains unclear. This study aimed to elucidate the prognostic significance of MTA and evaluate its incremental value to the National Comprehensive Cancer Network International Prognostic Index (NCCN-IPI) for DLBCL patients treated with first-line R-CHOP regimens.

METHODS

A total of 280 consecutive patients with newly diagnosed DLBCL and baseline 18F-FDG PET/CT data were retrospectively evaluated. Lesions were delineated via a semiautomated segmentation method based on a 41% SUVmax threshold to estimate semiquantitative metabolic parameters such as total metabolic tumour volume (TMTV) and MTA. Receiver operating characteristic (ROC) curve analysis was used to determine the optimal cut-off values. Progression-free survival (PFS) and overall survival (OS) were the endpoints that were used to evaluate the prognosis. PFS and OS were estimated via Kaplan‒Meier curves and compared via the log-rank test.

RESULTS

Univariate analysis revealed that patients with high MTA, high TMTV and NCCN-IPI ≥ 4 were associated with inferior PFS and OS (P < 0.0001 for all). Multivariate analysis indicated that MTA remained an independent predictor of PFS and OS [hazard ratio (HR), 2.506; 95% confidence interval (CI), 1.337-4.696; P = 0.004; and HR, 1.823; 95% CI, 1.005-3.310; P = 0.048], whereas TMTV was not. Further analysis using the NCCN-IPI model as a covariate revealed that MTA and NCCN-IPI were still independent predictors of PFS (HR, 2.617; 95% CI, 1.494-4.586; P = 0.001; and HR, 2.633; 95% CI, 1.650-4.203; P < 0.0001) and OS (HR, 2.021; 95% CI, 1.201-3.401; P = 0.008; and HR, 3.869; 95% CI, 1.959-7.640; P < 0.0001; respectively). Furthermore, MTA was used to separate patients with high NCCN-IPI risk scores into two groups with significantly different outcomes.

CONCLUSIONS

Pre-treatment MTA based on 18F-FDG PET/CT and NCCN-IPI were independent predictor of PFS and OS in DLBCL patients treated with R-CHOP. MTA has additional predictive value for the prognosis of patients with DLBCL, especially in high-risk patients with NCCN-IPI ≥ 4. In addition, the combination of MTA and NCCN-IPI may be helpful in further improving risk stratification and guiding individualised treatment options.

TRIAL REGISTRATION

This research was retrospectively registered with the Ethics Committee of the Third Affiliated Hospital of Soochow University, and the registration number was approval No. 155 (approved date: 31 May 2022).

Multicenter PET image harmonization using generative adversarial networks

PURPOSE

To improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches.

METHODS

GAN-harmonization was developed to harmonize whole-body PET scans to perform image style and texture translation between different centers and scanners. GAN-harmonization was evaluated by application to two retrospectively collected open datasets and different tasks. First, GAN-harmonization was performed on a dual-center lung cancer cohort (127 female, 138 male) where the reproducibility of radiomic features in healthy liver tissue was evaluated. Second, GAN-harmonization was applied to a head and neck cancer cohort (43 female, 154 male) acquired from three centers. Here, the clinical impact of GAN-harmonization was analyzed by predicting the development of distant metastases using a logistic regression model incorporating first-order statistics and texture features from baseline 18F-FDG PET before and after harmonization.

RESULTS

Image quality remained high (structural similarity: left kidney ≥ 0.800, right kidney ≥ 0.806, liver ≥ 0.780, lung ≥ 0.838, spleen ≥ 0.793, whole-body ≥ 0.832) after image harmonization across all utilized datasets. Using GAN-harmonization, inter-site reproducibility of radiomic features in healthy liver tissue increased at least by ≥ 5 ± 14% (first-order), ≥ 16 ± 7% (GLCM), ≥ 19 ± 5% (GLRLM), ≥ 16 ± 8% (GLSZM), ≥ 17 ± 6% (GLDM), and ≥ 23 ± 14% (NGTDM). In the head and neck cancer cohort, the outcome prediction improved from AUC 0.68 (95% CI 0.66-0.71) to AUC 0.73 (0.71-0.75) by application of GAN-harmonization.

CONCLUSIONS

GANs are capable of performing image harmonization and increase reproducibility and predictive performance of radiomic features derived from different centers and scanners.

Role of Novel Quantitative Imaging Techniques in Hematological Malignancies

Hematological malignancies exhibit a widespread distribution, necessitating evaluation of disease activity over the entire body. In clinical practice, visual analysis and semiquantitative parameters are used to assess 18F-FDGPET/CT imaging, which solely represents measurements of disease activity from limited area and may not adequately reflect global disease assessment. An efficient method for assessing the global disease burden of hematological malignancies is to employ PET/computed tomography based novel quantitative parameters. In this article, we explored novel quantitative parameters on PET/CT imaging for assessing global disease burden and the potential role of artificial intelligence (AI) to determine these parameters in evaluation of hematological malignancies.

Recent advances and impending challenges for the radiopharmaceutical sciences in oncology

This paper is the first of a Series on theranostics that summarises the current landscape of the radiopharmaceutical sciences as they pertain to oncology. In this Series paper, we describe exciting developments in radiochemistry and the production of radionuclides, the development and translation of theranostics, and the application of artificial intelligence to our field. These developments are catalysing growth in the use of radiopharmaceuticals to the benefit of patients worldwide. We also highlight some of the key issues to be addressed in the coming years to realise the full potential of radiopharmaceuticals to treat cancer.

Total metabolic tumor volume on 18F-FDG PET/CT is a game-changer for patients with metastatic lung cancer treated with immunotherapy

PURPOSE

Because of atypical response imaging patterns in patients with metastatic non-small cell lung cancer (NSCLC) treated with immune checkpoint inhibitors (ICPIs), new biomarkers are needed for a better monitoring of treatment efficacy. The aim of this prospective study was to evaluate the prognostic value of volume-derived positron-emission tomography (PET) parameters on baseline and follow-up 18F-fluoro-deoxy-glucose PET (18F-FDG-PET) scans and compare it with the conventional PET Response Criteria in Solid Tumors (PERCIST).

METHODS

Patients with metastatic NSCLC were included in two different single-center prospective trials. 18F-FDG-PET studies were performed before the start of immunotherapy (PETbaseline), after 6-8 weeks (PETinterim1) and after 12-16 weeks (PETinterim2) of treatment, using PERCIST criteria for tumor response assessment. Different metabolic parameters were evaluated: absolute values of maximum standardized uptake value (SUVmax) of the most intense lesion, total metabolic tumor volume (TMTV), total lesion glycolysis (TLG), but also their percentage changes between PET studies (ΔSUVmax, ΔTMTV and ΔTLG). The median follow-up of patients was 31 (7.3-31.8) months. Prognostic values and optimal thresholds of PET parameters were estimated by ROC (Receiver Operating Characteristic) curve analysis of 12-month overall survival (12M-OS) and 6-month progression-free survival (6M-PFS). Tumor progression needed to be confirmed by a multidisciplinary tumor board, considering atypical response patterns on imaging.

RESULTS

110 patients were prospectively included. On PETbaseline, TMTV was predictive of 12M-OS [AUC (Area Under Curve) =0.64; 95% CI: 0.61 to 0.66] whereas SUVmax and TLG were not. On PETinterim1 and PETinterim2, all metabolic parameters were predictive for 12M-OS and 6M-PFS, the residual TMTV on PETinterim1 (TMTV1) being the strongest prognostic biomarker (AUC=0.83 and 0.82; 95% CI: 0.74 to 0.91, for 12M-OS and 6M-PFS, respectively). Using the optimal threshold by ROC curve to classify patients into three TMTV1 subgroups (0 cm3; 0-57 cm3; >57 cm3), TMTV1 prognostic stratification was independent of PERCIST criteria on both PFS and OS, and significantly outperformed them. Subgroup analysis demonstrated that TMTV1 remained a strong prognostic biomarker of 12M-OS for non-responding patients (p=0.0003) according to PERCIST criteria. In the specific group of patients with PERCIST progression on PETinterim1, low residual tumor volume (<57 cm3) was still associated with a very favorable patients' outcome (6M-PFS=73%; 24M-OS=55%).

CONCLUSION

The absolute value of residual metabolic tumor volume, assessed 6-8 weeks after the start of ICPI, is an optimal and independent prognostic measure, exceeding and complementing conventional PERCIST criteria. Oncologists should consider it in patients with first tumor progression according to PERCIST criteria, as it helps identify patients who benefit from continued treatment.

TRIAL REGISTRATION NUMBER

2018-A02116-49; NCT03584334.

Does PET-CT Have a Role in the Evaluation of Tuberculosis Treatment in Phase 2 Clinical Trials?

Positron emission tomography-computed tomography (PET-CT) has the potential to revolutionize research in infectious diseases, as it has done with cancer. There is growing interest in it as a biomarker in the setting of early-phase tuberculosis clinical trials, particularly given the limitations of current biomarkers as adequate predictors of sterilizing cure for tuberculosis. PET-CT is a real-time tool that provides a 3-dimensional view of the spatial distribution of tuberculosis within the lung parenchyma and the nature of lesions with uptake (ie, whether nodular, consolidative, or cavitary). Its ability to provide functional data on changes in metabolism, drug penetration, and immune control of tuberculous lesions has the potential to facilitate drug development and regimen selection for advancement to phase 3 trials in tuberculosis. In this narrative review, we discuss the role that PET-CT may have in evaluating responses to drug therapy in active tuberculosis treatment and the challenges in taking PET-CT forward as predictive biomarker of relapse-free cure in the setting of phase 2 clinical trials.

Extracting value from total-body PET/CT image data - the emerging role of artificial intelligence

The evolution of Positron Emission Tomography (PET), culminating in the Total-Body PET (TB-PET) system, represents a paradigm shift in medical imaging. This paper explores the transformative role of Artificial Intelligence (AI) in enhancing clinical and research applications of TB-PET imaging. Clinically, TB-PET's superior sensitivity facilitates rapid imaging, low-dose imaging protocols, improved diagnostic capabilities and higher patient comfort. In research, TB-PET shows promise in studying systemic interactions and enhancing our understanding of human physiology and pathophysiology. In parallel, AI's integration into PET imaging workflows-spanning from image acquisition to data analysis-marks a significant development in nuclear medicine. This review delves into the current and potential roles of AI in augmenting TB-PET/CT's functionality and utility. We explore how AI can streamline current PET imaging processes and pioneer new applications, thereby maximising the technology's capabilities. The discussion also addresses necessary steps and considerations for effectively integrating AI into TB-PET/CT research and clinical practice. The paper highlights AI's role in enhancing TB-PET's efficiency and addresses the challenges posed by TB-PET's increased complexity. In conclusion, this exploration emphasises the need for a collaborative approach in the field of medical imaging. We advocate for shared resources and open-source initiatives as crucial steps towards harnessing the full potential of the AI/TB-PET synergy. This collaborative effort is essential for revolutionising medical imaging, ultimately leading to significant advancements in patient care and medical research.

Three-Direction Fusion for Accurate Volumetric Liver and Tumor Segmentation

Biomedical image segmentation of organs, tissues and lesions has gained increasing attention in clinical treatment planning and navigation, which involves the exploration of two-dimensional (2D) and three-dimensional (3D) contexts in the biomedical image. Compared to 2D methods, 3D methods pay more attention to inter-slice correlations, which offer additional spatial information for image segmentation. An organ or tumor has a 3D structure that can be observed from three directions. Previous studies focus only on the vertical axis, limiting the understanding of the relationship between a tumor and its surrounding tissues. Important information can also be obtained from sagittal and coronal axes. Therefore, spatial information of organs and tumors can be obtained from three directions, i.e. the sagittal, coronal and vertical axes, to understand better the invasion depth of tumor and its relationship with the surrounding tissues. Moreover, the edges of organs and tumors in biomedical image may be blurred. To address these problems, we propose a three-direction fusion volumetric segmentation (TFVS) model for segmenting 3D biomedical images from three perspectives in sagittal, coronal and transverse planes, respectively. We use the dataset of the liver task provided by the Medical Segmentation Decathlon challenge to train our model. The TFVS method demonstrates a competitive performance on the 3D-IRCADB dataset. In addition, the t-test and Wilcoxon signed-rank test are also performed to show the statistical significance of the improvement by the proposed method as compared with the baseline methods. The proposed method is expected to be beneficial in guiding and facilitating clinical diagnosis and treatment.

PrecisionLymphoNet: Advancing Malignant Lymphoma Diagnosis via Ensemble Transfer Learning with CNNs

Malignant lymphoma, which impacts the lymphatic system, presents diverse challenges in accurate diagnosis due to its varied subtypes-chronic lymphocytic leukemia (CLL), follicular lymphoma (FL), and mantle cell lymphoma (MCL). Lymphoma is a form of cancer that begins in the lymphatic system, impacting lymphocytes, which are a specific type of white blood cell. This research addresses these challenges by proposing ensemble and non-ensemble transfer learning models employing pre-trained weights from VGG16, VGG19, DenseNet201, InceptionV3, and Xception. For the ensemble technique, this paper adopts a stack-based ensemble approach. It is a two-level classification approach and best suited for accuracy improvement. Testing on a multiclass dataset of CLL, FL, and MCL reveals exceptional diagnostic accuracy, with DenseNet201, InceptionV3, and Xception exceeding 90% accuracy. The proposed ensemble model, leveraging InceptionV3 and Xception, achieves an outstanding 99% accuracy over 300 epochs, surpassing previous prediction methods. This study demonstrates the feasibility and efficiency of the proposed approach, showcasing its potential in real-world medical applications for precise lymphoma diagnosis.

Deep learning for [18F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: a dual-centre retrospective analysis

BACKGROUND

The rising global cancer burden has led to an increasing demand for imaging tests such as [18F]fluorodeoxyglucose ([18F]FDG)-PET-CT. To aid imaging specialists in dealing with high scan volumes, we aimed to train a deep learning artificial intelligence algorithm to classify [18F]FDG-PET-CT scans of patients with lymphoma with or without hypermetabolic tumour sites.

METHODS

In this retrospective analysis we collected 16 583 [18F]FDG-PET-CTs of 5072 patients with lymphoma who had undergone PET-CT before or after treatment at the Memorial Sloa Kettering Cancer Center, New York, NY, USA. Using maximum intensity projection (MIP), three dimensional (3D) PET, and 3D CT data, our ResNet34-based deep learning model (Lymphoma Artificial Reader System [LARS]) for [18F]FDG-PET-CT binary classification (Deauville 1-3 vs 4-5), was trained on 80% of the dataset, and tested on 20% of this dataset. For external testing, 1000 [18F]FDG-PET-CTs were obtained from a second centre (Medical University of Vienna, Vienna, Austria). Seven model variants were evaluated, including MIP-based LARS-avg (optimised for accuracy) and LARS-max (optimised for sensitivity), and 3D PET-CT-based LARS-ptct. Following expert curation, areas under the curve (AUCs), accuracies, sensitivities, and specificities were calculated.

FINDINGS

In the internal test cohort (3325 PET-CTs, 1012 patients), LARS-avg achieved an AUC of 0·949 (95% CI 0·942-0·956), accuracy of 0·890 (0·879-0·901), sensitivity of 0·868 (0·851-0·885), and specificity of 0·913 (0·899-0·925); LARS-max achieved an AUC of 0·949 (0·942-0·956), accuracy of 0·868 (0·858-0·879), sensitivity of 0·909 (0·896-0·924), and specificity of 0·826 (0·808-0·843); and LARS-ptct achieved an AUC of 0·939 (0·930-0·948), accuracy of 0·875 (0·864-0·887), sensitivity of 0·836 (0·817-0·855), and specificity of 0·915 (0·901-0·927). In the external test cohort (1000 PET-CTs, 503 patients), LARS-avg achieved an AUC of 0·953 (0·938-0·966), accuracy of 0·907 (0·888-0·925), sensitivity of 0·874 (0·843-0·904), and specificity of 0·949 (0·921-0·960); LARS-max achieved an AUC of 0·952 (0·937-0·965), accuracy of 0·898 (0·878-0·916), sensitivity of 0·899 (0·871-0·926), and specificity of 0·897 (0·871-0·922); and LARS-ptct achieved an AUC of 0·932 (0·915-0·948), accuracy of 0·870 (0·850-0·891), sensitivity of 0·827 (0·793-0·863), and specificity of 0·913 (0·889-0·937).

INTERPRETATION

Deep learning accurately distinguishes between [18F]FDG-PET-CT scans of lymphoma patients with and without hypermetabolic tumour sites. Deep learning might therefore be potentially useful to rule out the presence of metabolically active disease in such patients, or serve as a second reader or decision support tool.

FUNDING

National Institutes of Health-National Cancer Institute Cancer Center Support Grant.

Deep convolutional neural network for differentiating between sarcoidosis and lymphoma based on [18F]FDG maximum-intensity projection images

OBJECTIVES

To compare the [18F]FDG PET/CT findings of untreated sarcoidosis and malignant lymphoma (ML) and develop convolutional neural network (CNN) models to differentiate between these diseases using maximum intensity projection (MIP) [18F]FDG PET images.

METHODS

We retrospectively collected data on consecutive patients newly diagnosed with sarcoidosis and ML who underwent [18F]FDG PET/CT before treatment. Two nuclear radiologists reviewed the images. CNN models were created using MIP PET images and evaluated with k-fold cross-validation. The points of interest were visualized using gradient-weighted class activation mapping (Grad-CAM).

RESULTS

A total of 56 patients with sarcoidosis and 62 patients with ML were included. Patients with sarcoidosis had more prominent FDG accumulation in the mediastinal lymph nodes and lung lesions, while those with ML had more prominent accumulation in the cervical lymph nodes (all p < 0.001). For the mediastinal lymph nodes, sarcoidosis patients had significant FDG accumulation in the level 2, 4, 7, and 10 lymph nodes (all p < 0.01). Otherwise, the accumulation in ML patients tended to be in the level 1 lymph nodes (p = 0.08). The CNN model using frontal and lateral MIP images achieved an average accuracy of 0.890 (95% CI: 0.804-0.977), a sensitivity of 0.898 (95% CI: 0.782-1.000), a specificity of 0.907 (95% CI: 0.799-1.000), and an area under the curve of 0.963 (95% CI: 0.899-1.000). Grad-CAM showed that the model focused on the sites of abnormal FDG accumulation.

CONCLUSIONS

CNN models based on differences in FDG accumulation sites archive high performance in differentiating between sarcoidosis and ML.

CLINICAL RELEVANCE STATEMENT

We developed a CNN model using MIP images of [18F]FDG PET/CT to distinguish between sarcoidosis and malignant lymphoma. It achieved high performance and could be useful in diagnosing diseases with involvement across organs and lymph nodes.

KEY POINTS

• There are differences in FDG distribution when comparing whole-body [18F]FDG PET/CT findings in patients with sarcoidosis and malignant lymphoma before treatment. • Convolutional neural networks, a type of deep learning technique, trained with maximum-intensity projection PET images from two angles showed high performance. • A deep learning model that utilizes differences in FDG distribution may be helpful in differentiating between diseases with lesions that are characteristically widespread among organs and lymph nodes.

A hybrid few-shot multiple-instance learning model predicting the aggressiveness of lymphoma in PET/CT images

BACKGROUND AND OBJECTIVE

Patients with aggressive non-Hodgkin lymphoma (NHL) undergo distinct therapy strategies compared with indolent NHL patients. However, it is challenging to estimate NHL aggressiveness based on visual inspection of positron emission tomography (PET) or computed tomography (CT) images. Since diffuse large B-cell lymphoma (DLBCL) and Follicular lymphoma (FL) are the most typical and dominant aggressive and indolent NHL, respectively, this study aims to develop an artificial-intelligence-enabled model to distinguish DLBCL from FL in PET/CT images as the first step to tackle this challenge.

METHODS

We propose a hybrid few-shot multiple-instance learning model to predict the aggressiveness of the NHL. First, rotation-based self-supervision learning (SSL) has been employed to train the encoder on a large-scale, publicly available CT image dataset. Second, hybrid instance-level features are obtained for each NHL lesion by combining deep features with the radiomics features from both PET and CT modalities. Third, instance-level features are transformed into bag-level (or patient-level) representations. Finally, bag-level representations are fed into a distance-based classifier through few-shot learning to predict NHL aggressiveness.

RESULTS

Our model achieves an accuracy of 0.751 ± 0.008, a sensitivity of 0.787 ± 0.012, a specificity of 0.715 ± 0.013, an F1-score of 0.753 ± 0.009, and an area under the curve (AUC) of 0.795 ± 0.009 at the bag level. It outperforms the typical counterparts that use the radiomic features, random forest for feature selection, and support vector machines (SVMs) as classifiers. The three counterparts yield accuracies of 0.714 ± 0.023, 0.705 ± 0.008, and 0.698 ± 0.008, respectively. Moreover, settings of the SSL training dataset (Deep lesion) and task (rotation), hybrid CT and radiomic PET features, the pool-layer strategy of maximum, and distance-based classifier generate the best model.

CONCLUSIONS

A hybrid few-shot multiple-instance learning model can predict lymphoma aggressiveness in PET/CT images and could be a potential tool for determining therapy strategies. Hybrid features and the combination of SSL, few-shot learning, and weakly supervised learning are the two powerful pillars of the model, and these can be expanded to other medical applications with limited samples and incomplete annotations.

Application of machine learning in the management of lymphoma: Current practice and future prospects

In the past decade, digitization of medical records and multiomics data analysis in lymphoma has led to the accessibility of high-dimensional records. The digitization of medical records, the visualization of extensive volume data extracted from medical images, and the integration of multiomics methods into clinical decision-making have produced many datasets. As a promising auxiliary tool, machine learning (ML) intends to extract homologous features in large-scale data sets and encode them into various patterns to complete complicated tasks. At present, artificial intelligence and digital mining have shown promising prospects in the field of lymphoma pathological image analysis. The paradigm shift from qualitative analysis to quantitative analysis makes the pathological diagnosis more intelligent and the results more accurate and objective. ML can promote accurate lymphoma diagnosis and provide patients with prognostic information and more individualized treatment options. Based on the above, this comprehensive review of the general workflow of ML highlights recent advances in ML techniques in the diagnosis, treatment, and prognosis of lymphoma, and clarifies the boundedness and future orientation of the ML technique in the clinical practice of lymphoma.

Exploring the applicability of a lesion segmentation method on [18F]fluorothymidine PET/CT images in diffuse large B-cell lymphoma

BACKGROUND AND PURPOSE

The determination of the total metabolic tumour volume based on [18F]fluorothymidine ([18F]FLT) PET/CT images in diffuse large B-cell lymphoma has a potential clinical value for detecting early relapse in this type of heterogeneous lymphoproliferative tumours. Tumour segmentation is a key step in this process. For this purpose, our objective was to determine a segmentation threshold of [18F]FLT PET/CT images, based on a reference tissue uptake, on a cohort of patients with diffuse large B-cell lymphoma (DLBCL) that have been scanned at different stages of the treatment.

METHODS

We enrolled 23 adult patients with DLBCL confirmed in II-IV stages without nervous system compromise. All patients were scanned using [18F]FLT PET/CT at the time of diagnosis (baseline PET), interim PET (iPET), and at the end of treatment (fPET). The administered activity was 1.8-2.6 MBq/kg body weight, performed 60-70 min after injection and without use of contrast-enhanced CT. First, we assessed the [18F]FLT uptake stability in liver and bone marrow along the patient follow-up. For the lesion segmentation, three threshold values were assessed.

RESULTS

Both, liver, and bone marrow can be indistinctly taken as reference tissue. The SUV threshold for a voxel to be considered as belonging to a lesion is expressed in terms of a percentage relative to the patient's uptake in the reference tissue. Found thresholds were: for liver, 62%, 33%, 27%; and for bone marrow, 35%, 21% and 22%, for baseline, iPET and fPET stages, respectively. The relative threshold throughout the treatment has a decreasing tendency along the stages.

CONCLUSION

Based on the results obtained with [18F]FLT PET/CT during staging and follow-up in patients with DLBCL, reference values were obtained for each stage referring to liver and bone marrow uptake that could be used in clinical practice oncology.

Automatic Detection of Pancreatic Lesions and Main Pancreatic Duct Dilatation on Portal Venous CT Scans Using Deep Learning

OBJECTIVES

This study proposes and evaluates a deep learning method to detect pancreatic neoplasms and to identify main pancreatic duct (MPD) dilatation on portal venous computed tomography scans.

MATERIALS AND METHODS

A total of 2890 portal venous computed tomography scans from 9 institutions were acquired, among which 2185 had a pancreatic neoplasm and 705 were healthy controls. Each scan was reviewed by one in a group of 9 radiologists. Physicians contoured the pancreas, pancreatic lesions if present, and the MPD if visible. They also assessed tumor type and MPD dilatation. Data were split into a training and independent testing set of 2134 and 756 cases, respectively.A method to detect pancreatic lesions and MPD dilatation was built in 3 steps. First, a segmentation network was trained in a 5-fold cross-validation manner. Second, outputs of this network were postprocessed to extract imaging features: a normalized lesion risk, the predicted lesion diameter, and the MPD diameter in the head, body, and tail of the pancreas. Third, 2 logistic regression models were calibrated to predict lesion presence and MPD dilatation, respectively. Performance was assessed on the independent test cohort using receiver operating characteristic analysis. The method was also evaluated on subgroups defined based on lesion types and characteristics.

RESULTS

The area under the curve of the model detecting lesion presence in a patient was 0.98 (95% confidence interval [CI], 0.97-0.99). A sensitivity of 0.94 (469 of 493; 95% CI, 0.92-0.97) was reported. Similar values were obtained in patients with small (less than 2 cm) and isodense lesions with a sensitivity of 0.94 (115 of 123; 95% CI, 0.87-0.98) and 0.95 (53 of 56, 95% CI, 0.87-1.0), respectively. The model sensitivity was also comparable across lesion types with values of 0.94 (95% CI, 0.91-0.97), 1.0 (95% CI, 0.98-1.0), 0.96 (95% CI, 0.97-1.0) for pancreatic ductal adenocarcinoma, neuroendocrine tumor, and intraductal papillary neoplasm, respectively. Regarding MPD dilatation detection, the model had an area under the curve of 0.97 (95% CI, 0.96-0.98).

CONCLUSIONS

The proposed approach showed high quantitative performance to identify patients with pancreatic neoplasms and to detect MPD dilatation on an independent test cohort. Performance was robust across subgroups of patients with different lesion characteristics and types. Results confirmed the interest to combine a direct lesion detection approach with secondary features such as the MPD diameter, thus indicating a promising avenue for the detection of pancreatic cancer at early stages.

Deep Learning-Based Feature Extraction from Whole-Body PET/CT Employing Maximum Intensity Projection Images: Preliminary Results of Lung Cancer Data

Purpose

Deep learning (DL) has been widely used in various medical imaging analyses. Because of the difficulty in processing volume data, it is difficult to train a DL model as an end-to-end approach using PET volume as an input for various purposes including diagnostic classification. We suggest an approach employing two maximum intensity projection (MIP) images generated by whole-body FDG PET volume to employ pre-trained models based on 2-D images.

Methods

As a retrospective, proof-of-concept study, 562 [18F]FDG PET/CT images and clinicopathological factors of lung cancer patients were collected. MIP images of anterior and lateral views were used as inputs, and image features were extracted by a pre-trained convolutional neural network (CNN) model, ResNet-50. The relationship between the images was depicted on a parametric 2-D axes map using t-distributed stochastic neighborhood embedding (t-SNE), with clinicopathological factors.

Results

A DL-based feature map extracted by two MIP images was embedded by t-SNE. According to the visualization of the t-SNE map, PET images were clustered by clinicopathological features. The representative difference between the clusters of PET patterns according to the posture of a patient was visually identified. This map showed a pattern of clustering according to various clinicopathological factors including sex as well as tumor staging.

Conclusion

A 2-D image-based pre-trained model could extract image patterns of whole-body FDG PET volume by using anterior and lateral views of MIP images bypassing the direct use of 3-D PET volume that requires large datasets and resources. We suggest that this approach could be implemented as a backbone model for various applications for whole-body PET image analyses.

Deep learning-based diagnosis of osteoblastic bone metastases and bone islands in computed tomograph images: a multicenter diagnostic study

OBJECTIVE

To develop and validate a deep learning (DL) model based on CT for differentiating bone islands and osteoblastic bone metastases.

MATERIALS AND METHODS

The patients with sclerosing bone lesions (SBLs) were retrospectively included in three hospitals. The images from site 1 were randomly assigned to the training (70%) and intrinsic verification (10%) datasets for developing the two-dimensional (2D) DL model (single-slice input) and "2.5-dimensional" (2.5D) DL model (three-slice input) and to the internal validation dataset (20%) for evaluating the performance of both models. The diagnostic performance was evaluated using the internal validation set from site 1 and additional external validation datasets from site 2 and site 3. And statistically analyze the performance of 2D and 2.5D DL models.

RESULTS

In total, 1918 SBLs in 728 patients in site 1, 122 SBLs in 71 patients in site 2, and 71 SBLs in 47 patients in site 3 were used to develop and test the 2D and 2.5D DL models. The best performance was obtained using the 2.5D DL model, which achieved an AUC of 0.996 (95% confidence interval [CI], 0.995-0.996), 0.958 (95% CI, 0.958-0.960), and 0.952 (95% CI, 0.951-0.953) and accuracies of 0.950, 0.902, and 0.863 for the internal validation set, the external validation set from site 2 and site 3, respectively.

CONCLUSION

A DL model based on a three-slice CT image input (2.5D DL model) can improve the prediction of osteoblastic bone metastases, which can facilitate clinical decision-making.

KEY POINTS

• This study investigated the value of deep learning models in identifying bone islands and osteoblastic bone metastases. • Three-slice CT image input (2.5D DL model) outweighed the 2D model in the classification of sclerosing bone lesions. • The 2.5D deep learning model showed excellent performance using the internal (AUC, 0.996) and two external (AUC, 0.958; AUC, 0.952) validation sets.

Quantitative PET-based biomarkers in lymphoma: getting ready for primetime

The use of functional quantitative biomarkers extracted from routine PET-CT scans to characterize clinical responses in patients with lymphoma is gaining increased attention, and these biomarkers can outperform established clinical risk factors. Total metabolic tumour volume enables individualized estimation of survival outcomes in patients with lymphoma and has shown the potential to predict response to therapy suitable for  risk-adapted treatment approaches in clinical trials. The deployment of machine learning tools in molecular imaging research can assist in recognizing complex patterns and, with image classification, in tumour identification and segmentation of data from PET-CT scans. Initial studies using fully automated approaches to calculate metabolic tumour volume and other PET-based biomarkers have demonstrated appropriate correlation with calculations from experts, warranting further testing in large-scale studies. The extraction of computer-based quantitative tumour characterization through radiomics can provide a comprehensive view of phenotypic heterogeneity that better captures the molecular and functional features of the disease. Additionally, radiomics can be integrated with genomic data to provide more accurate prognostic information. Further improvements in PET-based biomarkers are imminent, although their incorporation into clinical decision-making currently has methodological shortcomings that need to be addressed with confirmatory prospective validation in selected patient populations. In this Review, we discuss the current knowledge, challenges and opportunities in the integration of quantitative PET-based biomarkers in clinical trials and the routine management of patients with lymphoma.

Modeling tumor size dynamics based on real-world electronic health records and image data in advanced melanoma patients receiving immunotherapy

The development of immune checkpoint inhibitors (ICIs) has revolutionized cancer therapy but only a fraction of patients benefits from this therapy. Model-informed drug development can be used to assess prognostic and predictive clinical factors or biomarkers associated with treatment response. Most pharmacometric models have thus far been developed using data from randomized clinical trials, and further studies are needed to translate their findings into the real-world setting. We developed a tumor growth inhibition model based on real-world clinical and imaging data in a population of 91 advanced melanoma patients receiving ICIs (i.e., ipilimumab, nivolumab, and pembrolizumab). Drug effect was modeled as an ON/OFF treatment effect, with a tumor killing rate constant identical for the three drugs. Significant and clinically relevant covariate effects of albumin, neutrophil to lymphocyte ratio, and Eastern Cooperative Oncology Group (ECOG) performance status were identified on the baseline tumor volume parameter, as well as NRAS mutation on tumor growth rate constant using standard pharmacometric approaches. In a population subgroup (n = 38), we had the opportunity to conduct an exploratory analysis of image-based covariates (i.e., radiomics features), by combining machine learning and conventional pharmacometric covariate selection approaches. Overall, we demonstrated an innovative pipeline for longitudinal analyses of clinical and imaging RWD with a high-dimensional covariate selection method that enabled the identification of factors associated with tumor dynamics. This study also provides a proof of concept for using radiomics features as model covariates.

Semiautomated Pipeline to Quantify Tumor Evolution From Real-World Positron Emission Tomography/Computed Tomography Imaging

PURPOSE

A semiautomated pipeline for the collection and curation of free-text and imaging real-world data (RWD) was developed to quantify cancer treatment outcomes in large-scale retrospective real-world studies. The objectives of this article are to illustrate the challenges of RWD extraction, to demonstrate approaches for quality assurance, and to showcase the potential of RWD for precision oncology.

METHODS

We collected data from patients with advanced melanoma receiving immune checkpoint inhibitors at the Lausanne University Hospital. Cohort selection relied on semantically annotated electronic health records and was validated using process mining. The selected imaging examinations were segmented using an automatic commercial software prototype. A postprocessing algorithm enabled longitudinal lesion identification across imaging time points and consensus malignancy status prediction. Resulting data quality was evaluated against expert-annotated ground-truth and clinical outcomes obtained from radiology reports.

RESULTS

The cohort included 108 patients with melanoma and 465 imaging examinations (median, 3; range, 1-15 per patient). Process mining was used to assess clinical data quality and revealed the diversity of care pathways encountered in a real-world setting. Longitudinal postprocessing greatly improved the consistency of image-derived data compared with single time point segmentation results (classification precision increased from 53% to 86%). Image-derived progression-free survival resulting from postprocessing was comparable with the manually curated clinical reference (median survival of 286 v 336 days, P = .89).

CONCLUSION

We presented a general pipeline for the collection and curation of text- and image-based RWD, together with specific strategies to improve reliability. We showed that the resulting disease progression measures match reference clinical assessments at the cohort level, indicating that this strategy has the potential to unlock large amounts of actionable retrospective real-world evidence from clinical records.

Molecular Imaging of Lymphoma: Future Directions and Perspectives

More than 250,000 patients die from Hodgkin or non-Hodgkin lymphoma each year. Currently, molecular imaging with ¹⁸F-FDG-PET/CT is the standard of care for lymphoma staging and therapy response assessment. In this review, we will briefly summarize the role of molecular imaging for lymphoma diagnosis, staging, outcome prediction, and prognostication. We discuss future directions in response assessment and surveillance with quantitative PET parameters, the utility of interim assessment, and the differences with response assessment to immunomodulatory therapy. Lastly, we will cover innovations in the field regarding novel tracers and artificial intelligence.

Role of Artificial Intelligence in PET/CT Imaging for Management of Lymphoma

Our review shows that AI-based analysis of lymphoma whole-body FDG-PET/CT can inform all phases of clinical management including staging, prognostication, treatment planning, and treatment response evaluation. We highlight advancements in the role of neural networks for performing automated image segmentation to calculate PET-based imaging biomarkers such as the total metabolic tumor volume (TMTV). AI-based image segmentation methods are at levels where they can be semi-automatically implemented with minimal human inputs and nearing the level of a second-opinion radiologist. Advances in automated segmentation methods are particularly apparent in the discrimination of lymphomatous vs non-lymphomatous FDG-avid regions, which carries through to automated staging. Automated TMTV calculators, in addition to automated calculation of measures such as Dmax are informing robust models of progression-free survival which can then feed into improved treatment planning.

Clinical application of AI-based PET images in oncological patients

Based on the advantages of revealing the functional status and molecular expression of tumor cells, positron emission tomography (PET) imaging has been performed in numerous types of malignant diseases for diagnosis and monitoring. However, insufficient image quality, the lack of a convincing evaluation tool and intra- and interobserver variation in human work are well-known limitations of nuclear medicine imaging and restrict its clinical application. Artificial intelligence (AI) has gained increasing interest in the field of medical imaging due to its powerful information collection and interpretation ability. The combination of AI and PET imaging potentially provides great assistance to physicians managing patients. Radiomics, an important branch of AI applied in medical imaging, can extract hundreds of abstract mathematical features of images for further analysis. In this review, an overview of the applications of AI in PET imaging is provided, focusing on image enhancement, tumor detection, response and prognosis prediction and correlation analyses with pathology or specific gene mutations in several types of tumors. Our aim is to describe recent clinical applications of AI-based PET imaging in malignant diseases and to focus on the description of possible future developments.

Technologist-Based Implementation of Total Metabolic Tumor Volume into Clinical Practice

Metabolic tumor volume (MTV) is defined as the total metabolically active tumor volume seen on ¹⁸F-FDG PET/CT examinations. Calculating MTV is often time-consuming, requiring a high degree of manual input. In this study, the MTV calculations of a board-certified nuclear radiologist were compared with those of 2 nuclear medicine technologists. As part of the technologists' educational program, after their classroom time they were trained by the radiologist for 30 min. The technologists calculated MTV within 7.5% of the radiologist's calculations in a set of patients who had diffuse large B-cell lymphoma and were undergoing initial staging ¹⁸F-FDG PET/CT. These findings suggest that nuclear medicine technologists may help accelerate implementation of MTV into clinical practice with favorable accuracy, possibly as an initial step followed by validation by the interpreting physician. The aim of this study was to explore whether efficiency is improved by integrating nuclear medicine technologists into a semiautomated workflow to calculate total MTV.

Prognostic value of metabolic tumor volume and lesion dissemination from baseline PET/CT in patients with diffuse large B-cell lymphoma: further risk stratification of the group with low-risk and high-risk NCCN-IPI

PURPOSE

The purpose of this study was to determine the prognostic value of metabolic tumor volume and lesion dissemination from baseline PET/CT in patients with diffuse large B-cell lymphoma (DLBCL) and the prognostic value of them in the National Comprehensive Cancer Network International Prognostic Index (NCCN-IPI) subgroups.

METHODS

A total of 113 patients who underwent ¹⁸F-FDG PET/CT examination in our institution were retrospectively collected. The MTV was measured by iterative adaptive algorithm. The location of the lesion was obtained according to its three-dimensional coordinates, and Dmax was obtained. SDmax is derived from Dmax standardized by body surface area (BSA). The X-tile method was used to determine the optimal cut-off values for MTV, Dmax and SDmax. Cox regression analysis was used to perform univariate and multivariate analyses. Patient survival rates were derived from Kaplan-Meier curves and compared using the log-rank test.

RESULTS

The median follow-up time was 24 months. The median of MTV was 196.86 cm³ (range 2.54-2925.37 cm³), and the optimal cut-off value was 489 cm³. The median of SDmax was 0.25 m^-1 (range 0.12-0.51 m^-1), and the best cut-off value was 0.31 m^-1. MTV and SDmax were independent prognostic factors of PFS (all P < 0.001). Combined with MTV and SDmax, the patients were divided into three groups, and the difference of PFS among the groups was statistically significant (P < 0.001), and was able to stratify the risk of NCCN-IPI patients in the low-risk (NCCN-IPI < 4) and high-risk (NCCN-IPI ≥ 4) groups (P = 0.001 and P = 0.031).

CONCLUSION

MTV and SDmax are independent prognostic factors for PFS in DCBCL patients, which describe tumor burden and tumor dissemination characteristics, respectively. The combination of the two could facilitate risk stratification between the low-risk and high-risk NCCN-IPI groups.

Evaluation of a convolution neural network for baseline total tumor metabolic volume on [18F]FDG PET in diffuse large B cell lymphoma

OBJECTIVES

New PET data-processing tools allow for automatic lesion selection and segmentation by a convolution neural network using artificial intelligence (AI) to obtain total metabolic tumor volume (TMTV) and total lesion glycolysis (TLG) routinely at the clinical workstation. Our objective was to evaluate an AI implemented in a new version of commercial software to verify reproducibility of results and time savings in a daily workflow.

METHODS

Using the software to obtain TMTV and TLG, two nuclear physicians applied five methods to retrospectively analyze data for 51 patients. Methods 1 and 2 were fully automated with exclusion of lesions ≤ 0.5 mL and ≤ 0.1 mL, respectively. Methods 3 and 4 were fully automated with physician review. Method 5 was semi-automated and used as reference. Time and number of clicks to complete the measurement were recorded for each method. Inter-instrument and inter-observer variation was assessed by the intra-class coefficient (ICC) and Bland-Altman plots.

RESULTS

Between methods 3 and 5, for the main user, the ICC was 0.99 for TMTV and 1.0 for TLG. Between the two users applying method 3, ICC was 0.97 for TMTV and 0.99 for TLG. Mean processing time (± standard deviation) was 20 s ± 9.0 for method 1, 178 s ± 125.7 for method 3, and 326 s ± 188.6 for method 5 (p < 0.05).

CONCLUSION

AI-enabled lesion detection software offers an automated, fast, reliable, and consistently performing tool for obtaining TMTV and TLG in a daily workflow.

KEY POINTS

• Our study shows that artificial intelligence lesion detection software is an automated, fast, reliable, and consistently performing tool for obtaining total metabolic tumor volume and total lesion glycolysis in a daily workflow.

The application of machine learning to imaging in hematological oncology: A scoping review

Background

Here, we conducted a scoping review to (i) establish which machine learning (ML) methods have been applied to hematological malignancy imaging; (ii) establish how ML is being applied to hematological cancer radiology; and (iii) identify addressable research gaps.

Methods

The review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews guidelines. The inclusion criteria were (i) pediatric and adult patients with suspected or confirmed hematological malignancy undergoing imaging (population); (ii) any study using ML techniques to derive models using radiological images to apply to the clinical management of these patients (concept); and (iii) original research articles conducted in any setting globally (context). Quality Assessment of Diagnostic Accuracy Studies 2 criteria were used to assess diagnostic and segmentation studies, while the Newcastle-Ottawa scale was used to assess the quality of observational studies.

Results

Of 53 eligible studies, 33 applied diverse ML techniques to diagnose hematological malignancies or to differentiate them from other diseases, especially discriminating gliomas from primary central nervous system lymphomas (n=18); 11 applied ML to segmentation tasks, while 9 applied ML to prognostication or predicting therapeutic responses, especially for diffuse large B-cell lymphoma. All studies reported discrimination statistics, but no study calculated calibration statistics. Every diagnostic/segmentation study had a high risk of bias due to their case-control design; many studies failed to provide adequate details of the reference standard; and only a few studies used independent validation.

Conclusion

To deliver validated ML-based models to radiologists managing hematological malignancies, future studies should (i) adhere to standardized, high-quality reporting guidelines such as the Checklist for Artificial Intelligence in Medical Imaging; (ii) validate models in independent cohorts; (ii) standardize volume segmentation methods for segmentation tasks; (iv) establish comprehensive prospective studies that include different tumor grades, comparisons with radiologists, optimal imaging modalities, sequences, and planes; (v) include side-by-side comparisons of different methods; and (vi) include low- and middle-income countries in multicentric studies to enhance generalizability and reduce inequity.

18F-FDG PET Maximum-Intensity Projections and Artificial Intelligence: A Win-Win Combination to Easily Measure Prognostic Biomarkers in DLBCL Patients

Total metabolic tumor volume (TMTV) and tumor dissemination (Dmax) calculated from baseline ¹⁸F-FDG PET/CT images are prognostic biomarkers in diffuse large B-cell lymphoma (DLBCL) patients. Yet, their automated calculation remains challenging. The purpose of this study was to investigate whether TMTV and Dmax features could be replaced by surrogate features automatically calculated using an artificial intelligence (AI) algorithm from only 2 maximum-intensity projections (MIPs) of the whole-body ¹⁸F-FDG PET images. Methods: Two cohorts of DLBCL patients from the REMARC (NCT01122472) and LNH073B (NCT00498043) trials were retrospectively analyzed. Experts delineated lymphoma lesions from the baseline whole-body ¹⁸F-FDG PET/CT images, from which TMTV and Dmax were measured. Coronal and sagittal MIP images and associated 2-dimensional reference lesion masks were calculated. An AI algorithm was trained on the REMARC MIP data to segment lymphoma regions. The AI algorithm was then used to estimate surrogate TMTV (sTMTV) and surrogate Dmax (sDmax) on both datasets. The ability of the original and surrogate TMTV and Dmax to stratify patients was compared. Results: Three hundred eighty-two patients (mean age ± SD, 62.1 y ± 13.4 y; 207 men) were evaluated. sTMTV was highly correlated with TMTV for REMARC and LNH073B datasets (Spearman r = 0.878 and 0.752, respectively), and so were sDmax and Dmax (r = 0.709 and 0.714, respectively). The hazard ratios for progression free survival of volume and MIP-based features derived using AI were similar, for example, TMTV: 11.24 (95% CI: 2.10-46.20), sTMTV: 11.81 (95% CI: 3.29-31.77), and Dmax: 9.0 (95% CI: 2.53-23.63), sDmax: 12.49 (95% CI: 3.42-34.50). Conclusion: Surrogate TMTV and Dmax calculated from only 2 PET MIP images are prognostic biomarkers in DLBCL patients and can be automatically estimated using an AI algorithm.

A Deep Learning-Aided Automated Method for Calculating Metabolic Tumor Volume in Diffuse Large B-Cell Lymphoma

Metabolic tumor volume (MTV) is a robust prognostic biomarker in diffuse large B-cell lymphoma (DLBCL). The available semiautomatic software for calculating MTV requires manual input limiting its routine application in clinical research. Our objective was to develop a fully automated method (AM) for calculating MTV and to validate the method by comparing its results with those from two nuclear medicine (NM) readers. The automated method designed for this study employed a deep convolutional neural network to segment normal physiologic structures from the computed tomography (CT) scans that demonstrate intense avidity on positron emission tomography (PET) scans. The study cohort consisted of 100 patients with newly diagnosed DLBCL who were randomly selected from the Alliance/CALGB 50,303 (NCT00118209) trial. We observed high concordance in MTV calculations between the AM and readers with Pearson's correlation coefficients and interclass correlations comparing reader 1 to AM of 0.9814 (p < 0.0001) and 0.98 (p < 0.001; 95%CI = 0.96 to 0.99), respectively; and comparing reader 2 to AM of 0.9818 (p < 0.0001) and 0.98 (p < 0.0001; 95%CI = 0.96 to 0.99), respectively. The Bland-Altman plots showed only relatively small systematic errors between the proposed method and readers for both MTV and maximum standardized uptake value (SUVmax). This approach may possess the potential to integrate PET-based biomarkers in clinical trials.

A whole-body FDG-PET/CT Dataset with manually annotated Tumor Lesions

We describe a publicly available dataset of annotated Positron Emission Tomography/Computed Tomography (PET/CT) studies. 1014 whole body Fluorodeoxyglucose (FDG)-PET/CT datasets (501 studies of patients with malignant lymphoma, melanoma and non small cell lung cancer (NSCLC) and 513 studies without PET-positive malignant lesions (negative controls)) acquired between 2014 and 2018 were included. All examinations were acquired on a single, state-of-the-art PET/CT scanner. The imaging protocol consisted of a whole-body FDG-PET acquisition and a corresponding diagnostic CT scan. All FDG-avid lesions identified as malignant based on the clinical PET/CT report were manually segmented on PET images in a slice-per-slice (3D) manner. We provide the anonymized original DICOM files of all studies as well as the corresponding DICOM segmentation masks. In addition, we provide scripts for image processing and conversion to different file formats (NIfTI, mha, hdf5). Primary diagnosis, age and sex are provided as non-imaging information. We demonstrate how this dataset can be used for deep learning-based automated analysis of PET/CT data and provide the trained deep learning model.

Measurement(s)	tumor lesions
Technology Type(s)	PET/CT
Sample Characteristic - Organism	Homo sapiens

Multimodal deep learning model on interim [18F]FDG PET/CT for predicting primary treatment failure in diffuse large B-cell lymphoma

OBJECTIVES

The prediction of primary treatment failure (PTF) is necessary for patients with diffuse large B-cell lymphoma (DLBCL) since it serves as a prominent means for improving front-line outcomes. Using interim ¹⁸F-fluoro-2-deoxyglucose ([¹⁸F]FDG) positron emission tomography/computed tomography (PET/CT) imaging data, we aimed to construct multimodal deep learning (MDL) models to predict possible PTF in low-risk DLBCL.

METHODS

Initially, 205 DLBCL patients undergoing interim [¹⁸F]FDG PET/CT scans and the front-line standard of care were included in the primary dataset for model development. Then, 44 other patients were included in the external dataset for generalization evaluation. Based on the powerful backbone of the Conv-LSTM network, we incorporated five different multimodal fusion strategies (pixel intermixing, separate channel, separate branch, quantitative weighting, and hybrid learning) to make full use of PET/CT features and built five corresponding MDL models. Moreover, we found the best model, that is, the hybrid learning model, and optimized it by integrating the contrastive training objective to further improve its prediction performance.

RESULTS

The final model with contrastive objective optimization, named the contrastive hybrid learning model, performed best, with an accuracy of 91.22% and an area under the receiver operating characteristic curve (AUC) of 0.926, in the primary dataset. In the external dataset, its accuracy and AUC remained at 88.64% and 0.925, respectively, indicating its good generalization ability.

CONCLUSIONS

The proposed model achieved good performance, validated the predictive value of interim PET/CT, and holds promise for directing individualized clinical treatment.

KEY POINTS

• The proposed multimodal models achieved accurate prediction of primary treatment failure in DLBCL patients. • Using an appropriate feature-level fusion strategy can make the same class close to each other regardless of the modal heterogeneity of the data source domain and positively impact the prediction performance. • Deep learning validated the predictive value of interim PET/CT in a way that exceeded human capabilities.

Full automation of total metabolic tumor volume from FDG-PET/CT in DLBCL for baseline risk assessments

Background

Current radiological assessments of ¹⁸fluorodeoxyglucose-positron emission tomography (FDG-PET) imaging data in diffuse large B-cell lymphoma (DLBCL) can be time consuming, do not yield real-time information regarding disease burden and organ involvement, and hinder the use of FDG-PET to potentially limit the reliance on invasive procedures (e.g. bone marrow biopsy) for risk assessment.

Methods

Our aim is to enable real-time assessment of imaging-based risk factors at a large scale and we propose a fully automatic artificial intelligence (AI)-based tool to rapidly extract FDG-PET imaging metrics in DLBCL. On availability of a scan, in combination with clinical data, our approach generates clinically informative risk scores with minimal resource requirements. Overall, 1268 patients with previously untreated DLBCL from the phase III GOYA trial (NCT01287741) were included in the analysis (training: n = 846; hold-out: n = 422).

Results

Our AI-based model comprising imaging and clinical variables yielded a tangible prognostic improvement compared to clinical models without imaging metrics. We observed a risk increase for progression-free survival (PFS) with hazard ratios [HR] of 1.87 (95% CI: 1.31–2.67) vs 1.38 (95% CI: 0.98–1.96) (C-index: 0.59 vs 0.55), and a risk increase for overall survival (OS) (HR: 2.16 (95% CI: 1.37–3.40) vs 1.40 (95% CI: 0.90–2.17); C-index: 0.59 vs 0.55). The combined model defined a high-risk population with 35% and 42% increased odds of a 4-year PFS and OS event, respectively, versus the International Prognostic Index components alone. The method also identified a subpopulation with a 2-year Central Nervous System (CNS)-relapse probability of 17.1%.

Conclusion

Our tool enables an enhanced risk stratification compared with IPI, and the results indicate that imaging can be used to improve the prediction of central nervous system relapse in DLBCL. These findings support integration of clinically informative AI-generated imaging metrics into clinical workflows to improve identification of high-risk DLBCL patients.

Trial Registration

Registered clinicaltrials.gov number: NCT01287741.

Graphical Abstract

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-022-00476-0.

Automated Classification of PET‐CT Lesions in Lung Cancer: An Independent Validation Study

Introduction

Recently, a tool called the positron emission tomography (PET)‐assisted reporting system (PARS) was developed and presented to classify lesions in PET/computed tomography (CT) studies in patients with lung cancer or lymphoma. The aim of this study was to validate PARS with an independent group of lung‐cancer patients using manual lesion segmentations as a reference standard, as well as to evaluate the association between PARS‐based measurements and overall survival (OS).

Methods

This study retrospectively included 115 patients who had undergone clinically indicated (18F)‐fluorodeoxyglucose (FDG) PET/CT due to suspected or known lung cancer. The patients had a median age of 66 years (interquartile range [IQR]: 61–72 years). Segmentations were made manually by visual inspection in a consensus reading by two nuclear medicine specialists and used as a reference. The research prototype PARS was used to automatically analyse all the PET/CT studies. The PET foci classified as suspicious by PARS were compared with the manual segmentations. No manual corrections were applied. Total lesion glycolysis (TLG) was calculated based on the manual and PARS‐based lung‐tumour segmentations. Associations between TLG and OS were investigated using Cox analysis.

Results

PARS showed sensitivities for lung tumours of 55.6% per lesion and 80.2% per patient. Both manual and PARS TLG were significantly associated with OS.

Conclusion

Automatically calculated TLG by PARS contains prognostic information comparable to manually measured TLG in patients with known or suspected lung cancer. The low sensitivity at both the lesion and patient levels makes the present version of PARS less useful to support clinical reading, reporting and staging.

Computer-aided detection and segmentation of malignant melanoma lesions on whole-body 18F-FDG PET/CT using an interpretable deep learning approach

BACKGROUND AND OBJECTIVE

In oncology, 18-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) / computed tomography (CT) is widely used to identify and analyse metabolically-active tumours. The combination of the high sensitivity and specificity from 18F-FDG PET and the high resolution from CT makes accurate assessment of disease status and treatment response possible. Since cancer is a systemic disease, whole-body imaging is of high interest. Moreover, whole-body metabolic tumour burden is emerging as a promising new biomarker predicting outcome for innovative immunotherapy in different tumour types. However, this comes with certain challenges such as the large amount of data for manual reading, different appearance of lesions across the body and cumbersome reporting, hampering its use in clinical routine. Automation of the reading can facilitate the process, maximise the information retrieved from the images and support clinicians in making treatment decisions.

METHODS

This work proposes a fully automated system for lesion detection and segmentation on whole-body 18F-FDG PET/CT. The novelty of the method stems from the fact that the same two-step approach used when manually reading the images was adopted, consisting of an intensity-based thresholding on PET followed by a classification that specifies which regions represent normal physiological uptake and which are malignant tissue. The dataset contained 69 patients treated for malignant melanoma. Baseline and follow-up scans together offered 267 images for training and testing.

RESULTS

On an unseen dataset of 53 PET/CT images, a median F1-score of 0.7500 was achieved with, on average, 1.566 false positive lesions per scan. Metabolically-active tumours were segmented with a median dice score of 0.8493 and absolute volume difference of 0.2986 ml.

CONCLUSIONS

The proposed fully automated method for the segmentation and detection of metabolically-active lesions on whole-body 18F-FDG PET/CT achieved competitive results. Moreover, it was compared to a direct segmentation approach which it outperformed for all metrics.

Automatic classification of lymphoma lesions in FDG-PET–Differentiation between tumor and non-tumor uptake

Introduction

The automatic classification of lymphoma lesions in PET is a main topic of ongoing research. An automatic algorithm would enable the swift evaluation of PET parameters, like texture and heterogeneity markers, concerning their prognostic value for patients outcome in large datasets. Moreover, the determination of the metabolic tumor volume would be facilitated. The aim of our study was the development and evaluation of an automatic algorithm for segmentation and classification of lymphoma lesions in PET.

Methods

Pre-treatment PET scans from 60 Hodgkin lymphoma patients from the EuroNet-PHL-C1 trial were evaluated. A watershed algorithm was used for segmentation. For standardization of the scan length, an automatic cropping algorithm was developed. All segmented volumes were manually classified into one of 14 categories. The random forest method and a nested cross-validation was used for automatic classification and evaluation.

Results

Overall, 853 volumes were segmented and classified. 203/246 tumor lesions and 554/607 non-tumor volumes were classified correctly by the automatic algorithm, corresponding to a sensitivity, a specificity, a positive and a negative predictive value of 83%, 91%, 79% and 93%. In 44/60 (73%) patients, all tumor lesions were correctly classified. In ten out of the 16 patients with misclassified tumor lesions, only one false-negative tumor lesion occurred. The automatic classification of focal gastrointestinal uptake, brown fat tissue and composed volumes consisting of more than one tissue was challenging.

Conclusion

Our algorithm, trained on a small number of patients and on PET information only, showed a good performance and is suitable for automatic lymphoma classification.

Predictors and Real-World Use of Prostate-Specific Radioligand Therapy: PSMA and Beyond

PSMA is a transmembrane protein that is markedly overexpressed in prostate cancer, making it an excellent target for imaging and treating patients with prostate cancer. Several small molecule inhibitors and antibodies of PSMA have been radiolabeled for use as therapeutic agents and are currently under clinical investigation. PSMA-based radionuclide therapy is a promising therapeutic option for men with metastatic prostate cancer. The phase II TheraP study demonstrated superior efficacy, lower side effects, and improved patient-reported outcomes compared with cabazitaxel. The phase III VISION study demonstrated that radionuclide therapy with β-emitter ¹⁷⁷Lu-PSMA-617 can prolong survival and improve quality of life when offered in addition to standard-of-care therapy in men with PSMA-positive metastatic castration-resistant prostate cancer whose disease had progressed with conventional treatments. Nevertheless, up to 30% of patients have inherent resistance to PSMA-based radionuclide therapy, and acquired resistance is inevitable. Hence, strategies to increase the efficacy of PSMA-based radionuclide therapy have been under clinical investigation. These include better patient selection; increased radiation damage delivery via dosimetry-based administered dose or use of α-emitters instead of β-emitters; or using combinatorial approaches to overcome radioresistance mechanisms (innate or acquired), such as with novel hormonal agents, PARP inhibitors, or immunotherapy.

Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development

The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations on technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations and then continuing with descriptions of how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.

Heart and bladder detection and segmentation on FDG PET/CT by deep learning

Purpose

Positron emission tomography (PET)/ computed tomography (CT) has been extensively used to quantify metabolically active tumors in various oncology indications. However, FDG-PET/CT often encounters false positives in tumor detection due to ¹⁸fluorodeoxyglucose (FDG) accumulation from the heart and bladder that often exhibit similar FDG uptake as tumors. Thus, it is necessary to eliminate this source of physiological noise. Major challenges for this task include: (1) large inter-patient variability in the appearance for the heart and bladder. (2) The size and shape of bladder or heart may appear different on PET and CT. (3) Tumors can be very close or connected to the heart or bladder.

Approach

A deep learning based approach is proposed to segment the heart and bladder on whole body PET/CT automatically. Two 3D U-Nets were developed separately to segment the heart and bladder, where each network receives the PET and CT as a multi-modal input. Data sets were obtained from retrospective clinical trials and include 575 PET/CT for heart segmentation and 538 for bladder segmentation.

Results

The models were evaluated on a test set from an independent trial and achieved a Dice Similarity Coefficient (DSC) of 0.96 for heart segmentation and 0.95 for bladder segmentation, Average Surface Distance (ASD) of 0.44 mm on heart and 0.90 mm on bladder.

Conclusions

This methodology could be a valuable component to the FDG-PET/CT data processing chain by removing FDG physiological noise associated with heart and/or bladder accumulation prior to image analysis by manual, semi- or automated tumor analysis methods.

Gross Tumor Volume Definition and Comparative Assessment for Esophageal Squamous Cell Carcinoma From 3D 18F-FDG PET/CT by Deep Learning-Based Method

Background

The accurate definition of gross tumor volume (GTV) of esophageal squamous cell carcinoma (ESCC) can promote precise irradiation field determination, and further achieve the radiotherapy curative effect. This retrospective study is intended to assess the applicability of leveraging deep learning-based method to automatically define the GTV from 3D 18F-FDG PET/CT images of patients diagnosed with ESCC.

Methods

We perform experiments on a clinical cohort with 164 18F-FDG PET/CT scans. The state-of-the-art esophageal GTV segmentation deep neural net is first employed to delineate the lesion area on PET/CT images. Afterwards, we propose a novel equivalent truncated elliptical cone integral method (ETECIM) to estimate the GTV value. Indexes of Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD) are used to evaluate the segmentation performance. Conformity index (CI), degree of inclusion (DI), and motion vector (MV) are used to assess the differences between predicted and ground truth tumors. Statistical differences in the GTV, DI, and position are also determined.

Results

We perform 4-fold cross-validation for evaluation, reporting the values of DSC, HD, and MSD as 0.72 ± 0.02, 11.87 ± 4.20 mm, and 2.43 ± 0.60 mm (mean ± standard deviation), respectively. Pearson correlations (R2) achieve 0.8434, 0.8004, 0.9239, and 0.7119 for each fold cross-validation, and there is no significant difference (t = 1.193, p = 0.235) between the predicted and ground truth GTVs. For DI, a significant difference is found (t = −2.263, p = 0.009). For position assessment, there is no significant difference (left-right in x direction: t = 0.102, p = 0.919, anterior–posterior in y direction: t = 0.221, p = 0.826, and cranial–caudal in z direction: t = 0.569, p = 0.570) between the predicted and ground truth GTVs. The median of CI is 0.63, and the gotten MV is small.

Conclusions

The predicted tumors correspond well with the manual ground truth. The proposed GTV estimation approach ETECIM is more precise than the most commonly used voxel volume summation method. The ground truth GTVs can be solved out due to the good linear correlation with the predicted results. Deep learning-based method shows its promising in GTV definition and clinical radiotherapy application.

Clinical Perspectives for 18F-FDG PET Imaging in Pediatric Oncology: Μetabolic Tumor Volume and Radiomics

Pediatric cancer, although rare, requires the most optimized treatment approach to obtain high survival rates and minimize serious long-term side effects in early adulthood. 18F-FDG PET/CT is most helpful and widely used in staging, recurrence detection, and response assessment in pediatric oncology. The well-known 18F-FDG PET metabolic indices of metabolic tumor volume (MTV) and tumor lesion glycolysis (TLG) have already revealed an independent significant prognostic value for survival in oncologic patients, although the corresponding cut-off values remain study-dependent and not validated for use in clinical practice. Advanced tumor “radiomic” analysis sheds new light into these indices. Numerous patterns of texture 18F-FDG uptake features can be extracted from segmented PET tumor images due to new powerful computational systems supporting complex “deep learning” algorithms. This high number of “quantitative” tumor imaging data, although not decrypted in their majority and once standardized for the different imaging systems and segmentation methods, could be used for the development of new “clinical” models for specific cancer types and, more interestingly, for specific age groups. In addition, data from novel techniques of tumor genome analysis could reveal new genes as biomarkers for prognosis and/or targeted therapies in childhood malignancies. Therefore, this ever-growing information of “radiogenomics”, in which the underlying tumor “genetic profile” could be expressed in the tumor-imaging signature of “radiomics”, possibly represents the next model for precision medicine in pediatric cancer management. This paper reviews 18F-FDG PET image segmentation methods as applied to pediatric sarcomas and lymphomas and summarizes reported findings on the values of metabolic and radiomic features in the assessment of these pediatric tumors.

Deep learning-based tumour segmentation and total metabolic tumour volume prediction in the prognosis of diffuse large B-cell lymphoma patients in 3D FDG-PET images

OBJECTIVES

To demonstrate the effectiveness of automatic segmentation of diffuse large B-cell lymphoma (DLBCL) in 3D FDG-PET scans using a deep learning approach and validate its value in prognosis in an external validation cohort.

METHODS

Two PET datasets were retrospectively analysed: 297 patients from a local centre for training and 117 patients from an external centre for validation. A 3D U-Net architecture was trained on patches randomly sampled within the PET images. Segmentation performance was evaluated by six metrics, including the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), sensitivity (Se), positive predictive value (PPV), Hausdorff distance 95 (HD 95), and average symmetric surface distance (ASSD). Finally, the prognostic value of predictive total metabolic tumour volume (pTMTV) was validated in real clinical applications.

RESULTS

The mean DSC, JSC, Se, PPV, HD 95, and ASSD (with standard deviation) for the validation cohort were 0.78 ± 0.25, 0.69 ± 0.26, 0.81 ± 0.27, 0.82 ± 0.25, 24.58 ± 35.18, and 4.46 ± 8.92, respectively. The mean ground truth TMTV (gtTMTV) and pTMTV were 276.6 ± 393.5 cm³ and 301.9 ± 510.5 cm³ in the validation cohort, respectively. Perfect homogeneity in the Bland-Altman analysis and a strong positive correlation in the linear regression analysis (R² linear = 0.874, p < 0.001) were demonstrated between gtTMTV and pTMTV. pTMTV (≥ 201.2 cm³) (PFS: HR = 3.097, p = 0.001; OS: HR = 6.601, p < 0.001) was shown to be an independent factor of PFS and OS.

CONCLUSIONS

The FCN model with a U-Net architecture can accurately segment lymphoma lesions and allow fully automatic assessment of TMTV on PET scans for DLBCL patients. Furthermore, pTMTV is an independent prognostic factor of survival in DLBCL patients.

KEY POINTS

•The segmentation model based on a U-Net architecture shows high performance in the segmentation of DLBCL patients on FDG-PET images. •The proposed method can provide quantitative information as a predictive TMTV for predicting the prognosis of DLBCL patients.

Deep Learning Approach to Automatize TMTV Calculations Regardless of Segmentation Methodology for Major FDG-Avid Lymphomas

The total metabolic tumor volume (TMTV) is a new prognostic factor in lymphomas that could benefit from automation with deep learning convolutional neural networks (CNN). Manual TMTV segmentations of 1218 baseline 18FDG-PET/CT have been used for training. A 3D V-NET model has been trained to generate segmentations with soft dice loss. Ground truth segmentation has been generated using a combination of different thresholds (TMTVprob), applied to the manual region of interest (Otsu, relative 41% and SUV 2.5 and 4 cutoffs). In total, 407 and 405 PET/CT were used for test and validation datasets, respectively. The training was completed in 93 h. In comparison with the TMTVprob, mean dice reached 0.84 in the training set, 0.84 in the validation set and 0.76 in the test set. The median dice scores for each TMTV methodology were 0.77, 0.70 and 0.90 for 41%, 2.5 and 4 cutoff, respectively. Differences in the median TMTV between manual and predicted TMTV were 32, 147 and 5 mL. Spearman’s correlations between manual and predicted TMTV were 0.92, 0.95 and 0.98. This generic deep learning model to compute TMTV in lymphomas can drastically reduce computation time of TMTV.

Pre-treatment total metabolic tumour volumes in lymphoma: Does quantity matter?

Positron emission tomography/computed tomography (PET/CT) is used for the staging of lymphomas. Clinical information, such as Ann Arbor stage and number of involved sites, is derived from baseline staging and correlates with tumour volume. With modern imaging software, exact measures of total metabolic tumour volumes (tMTV) can be determined, in a semi- or fully-automated manner. Several technical factors, such as tumour segmentation and PET/CT technology influence tMTV and there is no consensus on a standardized uptake value (SUV) thresholding method, or how to include the volumes in the bone marrow and spleen. In diffuse large B-cell lymphoma, follicular lymphoma, peripheral T-cell lymphoma, and Hodgkin lymphoma, tMTV has been shown to predict progression-free survival and/or overall survival, after adjustments for clinical risk scores. However, most studies have used receiver operating curves to determine the optimal cut-off for tMTV and many studies did not include a training-validation approach, which led to the risk of overestimation of the independent prognostic value of tMTV. The identified cut-off values are heterogeneous, even when the same SUV thresholding method is used. Future studies should focus on testing tMTV in homogeneously-treated cohorts and seek to validate identified cut-off values externally so that a prognostic value can be documented, over and above currently used clinical surrogates for tumour volume.

A PET in a time of need: toward early PET-adapted therapy in DLBCL in first relapse

Salvage chemotherapy and autologous stem cell transplant remain a standard of care in the management of diffuse large B cell lymphoma (DLBCL) at first relapse. However, this paradigm is increasingly being challenged by novel immunotherapies, such as chimeric antigen receptor T-cells (CART-cells). Traditional positron emission tomography-based (PET) prognostication takes place after salvage and before autologous stem cell transplant (ASCT), and while useful, for many patients this information comes too late and at the expense of unnecessary toxicity. In this edition of Leukemia & Lymphoma, two groups present their findings on the use of early quantitative PET markers and the correlation with outcomes in patients embarking on second line salvage chemotherapy. These approaches have the potential to better identify patients who are destined for treatment failure and help guide appropriate sequencing of alternative therapies or the development of PET-adapted clinical trials.

Metabolic Volume Measurements in Multiple Myeloma

Multiple myeloma (MM) accounts for 10-15% of all hematologic malignancies, as well as 20% of deaths related to hematologic malignant tumors, predominantly affecting bone and bone marrow. Positron emission tomography/computed tomography with 18F-fluorodeoxyglucose (FDG-PET/CT) is an important method to assess the tumor burden of these patients. It is often challenging to classify the extent of disease involvement in the PET scans for many of these patients because both focal and diffuse bone lesions may coexist, with varying degrees of FDG uptake. Different metrics involving volumetric parameters and texture features have been proposed to objectively assess these images. Here, we review some metabolic parameters that can be extracted from FDG-PET/CT images of MM patients, including technical aspects and predicting MM outcome impact. Metabolic tumor volume (MTV) and total lesion glycolysis (TLG) are volumetric parameters known to be independent predictors of MM outcome. However, they have not been adopted in clinical practice due to the lack of measuring standards. CT-based segmentation allows automated, and therefore reproducible, calculation of bone metabolic metrics in patients with MM, such as maximum, mean and standard deviation of the standardized uptake values (SUV) for the entire skeleton. Intensity of bone involvement (IBI) is a new parameter that also takes advantage of this approach with promising results. Other indirect parameters obtained from FDG-PET/CT images, such as visceral adipose tissue glucose uptake and subcutaneous adipose tissue radiodensity, may also be useful to evaluate the prognosis of MM patients. Furthermore, the use and quantification of new radiotracers can address different metabolic aspects of MM and may have important prognostic implications.