A comprehensive dataset of germinoma on MRI/CT with clinical and radiomic data

Intracranial germ cell tumors (GCTs) are rare neoplasms with a peak incidence in adolescents. Germinoma is the most common histological subtype of intracranial GCTs. Its symptoms include intracranial hypertension, visual field defects, and hormonal disorders, affecting the physical health of adolescents. Germinoma is sensitive to chemo-radiotherapy, and most patients do not require neurosurgical resection. Therefore, improving the accuracy of germinoma diagnosis helps to avoid unnecessary surgery. At present, the application of artificial intelligence (AI) in medical imaging has improved the accuracy of disease diagnosis. However, few studies focused on the AI model to diagnosis germinoma and there are no publicly available imaging datasets for germinoma. This study aimed to create a comprehensive dataset for germinoma using magnetic resonance imaging/computed tomography findings with clinical and radiomic data to train and validate AI models. Featuring 65 pathologically confirmed germinomas, the dataset included axial T2-weighted imaging, T2-weighted fluid-attenuated inversion recovery, T1-weighted imaging, T1-weighted imaging with contrast enhancement, diffusion-weighted MR imaging, CT images, clinical data, and morphological and radiomic-based features obtained by segmentation.

A Tumor Volume Segmentation Algorithm Based on Radiomics Features in FDG-PET in Lung Cancer Patients, Validated Using Surgical Specimens

BACKGROUND

Although the integration of positron emission tomography into radiation therapy treatment planning has become part of clinical routine, the best method for tumor delineation is still a matter of debate. In this study, therefore, we analyzed a novel, radiomics-feature-based algorithm in combination with histopathological workup for patients with non-small-cell lung cancer.

METHODS

A total of 20 patients with biopsy-proven lung cancer who underwent [18F]fluorodeoxyglucose positron emission/computed tomography (FDG-PET/CT) examination before tumor resection were included. Tumors were segmented in positron emission tomography (PET) data using previously reported algorithms based on three different radiomics features, as well as a threshold-based algorithm. To obtain gold-standard results, lesions were measured after resection. Pathological volumes and maximal diameters were then compared with the results of the segmentation algorithms.

RESULTS

A total of 20 lesions were analyzed. For all algorithms, segmented volumes correlated well with pathological volumes. In general, the threshold-based volumes exhibited a tendency to be smaller than the radiomics-based volumes. For all lesions, conventional threshold-based segmentation produced coefficients of variation which corresponded best with pathologically based volumes; however, for lesions larger than 3 ccm, the algorithm based on Local Entropy performed best, with a significantly better coefficient of variation (p = 0.0002) than the threshold-based algorithm.

CONCLUSIONS

We found that, for small lesions, results obtained using conventional threshold-based segmentation compared well with pathological volumes. For lesions larger than 3 ccm, the novel algorithm based on Local Entropy performed best. These findings confirm the results of our previous phantom studies. This algorithm is therefore worthy of inclusion in future studies for further confirmation and application.

Development of an MRI Radiomic Machine-Learning Model to Predict Triple-Negative Breast Cancer Based on Fibroglandular Tissue of the Contralateral Unaffected Breast in Breast Cancer Patients

AIM

The purpose of this study was to develop a radiomic-based machine-learning model to predict triple-negative breast cancer (TNBC) based on the contralateral unaffected breast's fibroglandular tissue (FGT) in breast cancer patients.

MATERIALS AND METHODS

This study retrospectively included 541 patients (mean age, 51 years; range, 26-82) who underwent a screening breast MRI between November 2016 and September 2018 and who were subsequently diagnosed with biopsy-confirmed, treatment-naïve breast cancer. Patients were divided into training (n = 250) and validation (n = 291) sets. In the training set, 132 radiomic features were extracted using the open-source CERR platform. Following feature selection, the final prediction model was created, based on a support vector machine with a polynomial kernel of order 2.

RESULTS

In the validation set, the final prediction model, which included four radiomic features, achieved an F1 score of 0.66, an area under the curve of 0.71, a sensitivity of 54% [47-60%], a specificity of 74% [65-84%], a positive predictive value of 84% [78-90%], and a negative predictive value of 39% [31-47%].

CONCLUSIONS

TNBC can be predicted based on radiomic features extracted from the FGT of the contralateral unaffected breast of patients, suggesting the potential for risk prediction specific to TNBC.

Application value of volumetric CT value in quantifying the activity of a pulmonary tuberculoma

OBJECTIVE

The purpose of this study was to explore the auxiliary diagnostic value of volumetric CT value in quantifying the activity of a pulmonary tuberculoma.

METHODS

Chest CT image data of 112 patients with pulmonary tuberculomas who were diagnosed clinically between October 16, 2013 and March 21, 2023 were selected. With the shortest diameter axis>5 mm on the mediastinal window serving as the inclusion criterion, 108 active tuberculomas and 64 non-active tuberculomas were selected. The focused image was manually segmented using ITK-SNAP software, the volumetric CT value of the focus was calculated, and the ROC curve was analyzed. Using the final clinical diagnosis as the reference standard, the auxiliary diagnostic efficacy and consistency of the conventional CT film reading method and volumetric CT value in determining the activity of a pulmonary tuberculoma were compared.

RESULTS

The volumetric CT value of 108 active pulmonary tuberculoma lesions (33.39 [28.17,36.23] HU) was significantly less than 64 inactive pulmonary tuberculoma lesions (78.91 [57.81,120.31] HU); the difference was statistically significant (Z = -10.888. P < 0.001). ROC curve analysis showed that at a maximum Yoden index value of 0.963, the optimal volumetric CT threshold value was 45.32 HU, the sensitivity and specificity of the volumetric CT value in determining the activity of a pulmonary tuberculoma were 97.2% and 100.0%, respectively, and the maximum area under the ROC curve was 0.998. Taking the final clinical diagnosis as the reference standard, the sensitivity, specificity, consistency, and kappa value of the conventional CT film reading method for determining the activity of a pulmonary tuberculoma were 72.2% (78/108), 70.3% (45/64), 71.5% (123/172), and 0.413, respectively, while the corresponding volumetric CT values were 97.2% (105/108), 100.0% (64/64), 98.3% (168/172), and 0.951, respectively.

CONCLUSION

Accurately quantifying the volumetric CT value of a pulmonary tuberculoma focus determines the activity of a pulmonary tuberculoma, which has very important auxiliary diagnostic value.

Unsupervised machine learning cluster analysis to identification EVAR patients clinical phenotypes based on radiomics

OBJECTIVE

This study used unsupervised machine learning (UML) cluster analysis to explore clinical phenotypes of endovascular aortic repair (EVAR) for abdominal aortic aneurysm (AAA) patients based on radiomics.

METHOD

We retrospectively reviewed 1785 patients with infra-renal AAA who underwent elective EVAR procedures between January 2010 and December 2020. Pyradiomics was used to extract the radiomics features. Statistical analysis was applied to determine the radiomics features that related to severe adverse events (SAEs) after EVAR. The selected features were used for UML cluster analysis in training set and validation in test set. Comparison of basic characteristics and radiomics features of different clusters. The Kaplan-Meier analysis was conducted to generate the cumulative incidence of freedom from SAEs rate.

RESULT

A total of 1180 patients were enrolled. During the follow-up, 353 patients experienced EVAR-related SAEs. In total, 1223 radiomics features were extracted from each patient, of which 23 radiomics features were finally preserved to identify different clinical phenotypes. 944 patients were allocated to the training set. Three clusters were identified in training set, in which patients had identical clinical characteristics and morphological features, while varied considerably of selected radiomics features. This encouraging performance was further approved in the test set. In addition, each cluster was well differentiated from other clusters and Kaplan-Meier analysis showed significant differences of freedom from SAEs rate between different clusters both in the training (p = .0216) and test sets (p = .0253).

CONCLUSION

Based on radiomics, UML cluster analysis can identify clinical phenotypes in EVAR patients with distinct long-term outcomes.

Feasibility of [18F]fluoropivalate hybrid PET/MRI for imaging lower and higher grade glioma: a prospective first-in-patient pilot study

PURPOSE

MRI and PET are used in neuro-oncology for the detection and characterisation of lesions for malignancy to target surgical biopsy and to plan surgical resections or stereotactic radiosurgery. The critical role of short-chain fatty acids (SCFAs) in brain tumour biology has come to the forefront. The non-metabolised SCFA radiotracer, [18F]fluoropivalate (FPIA), shows low background signal in most tissues except eliminating organs and has appropriate human dosimetry. Tumour uptake of the radiotracer is, however, unknown. We investigated the uptake characteristics of FPIA in this pilot PET/MRI study.

METHODS

Ten adult glioma subjects were identified based on radiological features using standard-of-care MRI prior to any surgical intervention, with subsequent histopathological confirmation of glioma subtype and grade (lower-grade - LGG - and higher-grade - HGG - patients). FPIA was injected as an intravenous bolus injection (range 342-368 MBq), and dynamic PET and MRI data were acquired simultaneously over 66 min.

RESULTS

All patients tolerated the PET/MRI protocol. Three patients were reclassified following resection and histology. Tumour maximum standardised uptake value (SUVmax,60) increased in the order LGG (WHO grade 2) < HGG (WHO grade 3) < HGG (WHO grade 4). The net irreversible solute transfer, Ki, and influx rate constant, K1, were significantly higher in HGG (p < 0.05). Of the MRI variables studied, DCE-MRI-derived extravascular-and-extracellular volume fraction (ve) was high in tumours of WHO grade 4 compared with other grades (p < 0.05). SLC25A20 protein expression was higher in HGG compared with LGG.

CONCLUSION

Tumoural FPIA PET uptake is higher in HGG compared to LGG. This study supports further investigation of FPIA PET/MRI for brain tumour imaging in a larger patient population.

CLINICAL TRIAL REGISTRATION

Clinicaltrials.gov, NCT04097535.

Developing an Artificial Intelligence Solution to Autosegment the Edentulous Mandibular Bone for Implant Planning

OBJECTIVE

 Dental implants are considered the optimum solution to replace missing teeth and restore the mouth's function and aesthetics. Surgical planning of the implant position is critical to avoid damage to vital anatomical structures; however, the manual measurement of the edentulous (toothless) bone on cone beam computed tomography (CBCT) images is time-consuming and is subject to human error. An automated process has the potential to reduce human errors and save time and costs. This study developed an artificial intelligence (AI) solution to identify and delineate edentulous alveolar bone on CBCT images before implant placement.

MATERIALS AND METHODS

 After obtaining the ethical approval, CBCT images were extracted from the database of the University Dental Hospital Sharjah based on predefined selection criteria. Manual segmentation of the edentulous span was done by three operators using ITK-SNAP software. A supervised machine learning approach was undertaken to develop a segmentation model on a "U-Net" convolutional neural network (CNN) in the Medical Open Network for Artificial Intelligence (MONAI) framework. Out of the 43 labeled cases, 33 were utilized to train the model, and 10 were used for testing the model's performance.

STATISTICAL ANALYSIS

 The degree of 3D spatial overlap between the segmentation made by human investigators and the model's segmentation was measured by the dice similarity coefficient (DSC).

RESULTS

 The sample consisted mainly of lower molars and premolars. DSC yielded an average value of 0.89 for training and 0.78 for testing. Unilateral edentulous areas, comprising 75% of the sample, resulted in a better DSC (0.91) than bilateral cases (0.73).

CONCLUSION

 Segmentation of the edentulous spans on CBCT images was successfully conducted by machine learning with good accuracy compared to manual segmentation. Unlike traditional AI object detection models that identify objects present in the image, this model identifies missing objects. Finally, challenges in data collection and labeling are discussed, together with an outlook at the prospective stages of a larger project for a complete AI solution for automated implant planning.

uRP: An integrated research platform for one-stop analysis of medical images

Introduction

Medical image analysis is of tremendous importance in serving clinical diagnosis, treatment planning, as well as prognosis assessment. However, the image analysis process usually involves multiple modality-specific software and relies on rigorous manual operations, which is time-consuming and potentially low reproducible.

Methods

We present an integrated platform - uAI Research Portal (uRP), to achieve one-stop analyses of multimodal images such as CT, MRI, and PET for clinical research applications. The proposed uRP adopts a modularized architecture to be multifunctional, extensible, and customizable.

Results and Discussion

The uRP shows 3 advantages, as it 1) spans a wealth of algorithms for image processing including semi-automatic delineation, automatic segmentation, registration, classification, quantitative analysis, and image visualization, to realize a one-stop analytic pipeline, 2) integrates a variety of functional modules, which can be directly applied, combined, or customized for specific application domains, such as brain, pneumonia, and knee joint analyses, 3) enables full-stack analysis of one disease, including diagnosis, treatment planning, and prognosis assessment, as well as full-spectrum coverage for multiple disease applications. With the continuous development and inclusion of advanced algorithms, we expect this platform to largely simplify the clinical scientific research process and promote more and better discoveries.

Towards a better understanding of annotation tools for medical imaging: a survey

Medical imaging refers to several different technologies that are used to view the human body to diagnose, monitor, or treat medical conditions. It requires significant expertise to efficiently and correctly interpret the images generated by each of these technologies, which among others include radiography, ultrasound, and magnetic resonance imaging. Deep learning and machine learning techniques provide different solutions for medical image interpretation including those associated with detection and diagnosis. Despite the huge success of deep learning algorithms in image analysis, training algorithms to reach human-level performance in these tasks depends on the availability of large amounts of high-quality training data, including high-quality annotations to serve as ground-truth. Different annotation tools have been developed to assist with the annotation process. In this survey, we present the currently available annotation tools for medical imaging, including descriptions of graphical user interfaces (GUI) and supporting instruments. The main contribution of this study is to provide an intensive review of the popular annotation tools and show their successful usage in annotating medical imaging dataset to guide researchers in this area.

Assessing PD-L1 Expression Status Using Radiomic Features from Contrast-Enhanced Breast MRI in Breast Cancer Patients: Initial Results

Simple Summary

To our knowledge, this is the first study assessing radiomics coupled with machine learning from MRI-derived features to predict PD-L1 expression status in biopsy-proven triple negative breast cancers and comparing the performance of this approach with the performance of qualitative assessment by two radiologists. This pilot study shows that radiomics analysis coupled with machine learning of DCE-MRI is a promising approach to derive prognostic and predictive information and to select patients who could benefit from anti-PD-1/PD-L1 treatment. This technique could also be used to monitor PD-L1 expression, as it can vary over time and between different regions of the tumor, thus avoiding repeated biopsies.

Abstract

The purpose of this retrospective study was to assess whether radiomics analysis coupled with machine learning (ML) based on standard-of-care dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict PD-L1 expression status in patients with triple negative breast cancer, and to compare the performance of this approach with radiologist review. Patients with biopsy-proven triple negative breast cancer who underwent pre-treatment breast MRI and whose PD-L1 status was available were included. Following 3D tumor segmentation and extraction of radiomic features, radiomic features with significant differences between PD-L1+ and PD-L1− patients were determined, and a final predictive model to predict PD-L1 status was developed using a coarse decision tree and five-fold cross-validation. Separately, all lesions were qualitatively assessed by two radiologists independently according to the BI-RADS lexicon. Of 62 women (mean age 47, range 31–81), 27 had PD-L1− tumors and 35 had PD-L1+ tumors. The final radiomics model to predict PD-L1 status utilized three MRI parameters, i.e., variance (FO), run length variance (RLM), and large zone low grey level emphasis (LZLGLE), for a sensitivity of 90.7%, specificity of 85.1%, and diagnostic accuracy of 88.2%. There were no significant associations between qualitative assessed DCE-MRI imaging features and PD-L1 status. Thus, radiomics analysis coupled with ML based on standard-of-care DCE-MRI is a promising approach to derive prognostic and predictive information and to select patients who could benefit from anti-PD-1/PD-L1 treatment.

Prediction of Genetic Alterations in Oncogenic Signaling Pathways in Squamous Cell Carcinoma of the Head and Neck: Radiogenomic Analysis Based on Computed Tomography Images

OBJECTIVE

This study investigated the role of radiomics in evaluating the alterations of oncogenic signaling pathways in head and neck cancer.

METHODS

Radiomics features were extracted from 106 enhanced computed tomography images with head and neck squamous cell carcinoma. Support vector machine-recursive feature elimination was used for feature selection. Support vector machine algorithm was used to develop radiomics scores to predict genetic alterations in oncogenic signaling pathways. The performance was evaluated by the area under the curve (AUC) of the receiver operating characteristic curve.

RESULTS

The alterations of the Cell Cycle, HIPPO, NOTCH, PI3K, RTK RAS, and TP53 signaling pathways were predicted by radiomics scores. The AUC values of the training cohort were 0.94, 0.91, 0.94, 0.93, 0.87, and 0.93, respectively. The AUC values of the validation cohort were all greater than 0.7.

CONCLUSIONS

Radiogenomics is a new method for noninvasive acquisition of tumor molecular information at the genetic level.

Fully Integrated Quantitative Multiparametric Analysis of Non-Small Cell Lung Cancer at 3-T PET/MRI: Toward One-Stop-Shop Tumor Biological Characterization at the Supervoxel Level

INTRODUCTION

The aim of this study was to study the feasibility of a fully integrated multiparametric imaging framework to characterize non-small cell lung cancer (NSCLC) at 3-T PET/MRI.

PATIENTS AND METHODS

An 18F-FDG PET/MRI multiparametric imaging framework was developed and prospectively applied to 11 biopsy-proven NSCLC patients. For each tumor, 12 parametric maps were generated, including PET full kinetic modeling, apparent diffusion coefficient, T1/T2 relaxation times, and DCE full kinetic modeling. Gaussian mixture model-based clustering was applied at the whole data set level to define supervoxels of similar multidimensional PET/MRI behaviors. Taking the multidimensional voxel behaviors as input and the supervoxel class as output, machine learning procedure was finally trained and validated voxelwise to reveal the dominant PET/MRI characteristics of these supervoxels at the whole data set and individual tumor levels.

RESULTS

The Gaussian mixture model-based clustering clustering applied at the whole data set level (17,316 voxels) found 3 main multidimensional behaviors underpinned by the 12 PET/MRI quantitative parameters. Four dominant PET/MRI parameters of clinical relevance (PET: k2, k3 and DCE: ve, vp) predicted the overall supervoxel behavior with 97% of accuracy (SD, 0.7; 10-fold cross-validation). At the individual tumor level, these dimensionality-reduced supervoxel maps showed mean discrepancy of 16.7% compared with the original ones.

CONCLUSIONS

One-stop-shop PET/MRI multiparametric quantitative analysis of NSCLC is clinically feasible. Both PET and MRI parameters are useful to characterize the behavior of tumors at the supervoxel level. In the era of precision medicine, the full capabilities of PET/MRI would give further insight of the characterization of NSCLC behavior, opening new avenues toward image-based personalized medicine in this field.

Review of Artificial Intelligence Training Tools and Courses for Radiologists

Artificial intelligence (AI) systems play an increasingly important role in all parts of the imaging chain, from image creation to image interpretation to report generation. In order to responsibly manage radiology AI systems and make informed purchase decisions about them, radiologists must understand the underlying principles of AI. Our task force was formed by the Radiology Research Alliance (RRA) of the Association of University Radiologists to identify and summarize a curated list of current educational materials available for radiologists.

The application of artificial intelligence and radiomics in lung cancer

Lung cancer is one of the most leading causes of death throughout the world, and there is an urgent requirement for the precision medical management of it. Artificial intelligence (AI) consisting of numerous advanced techniques has been widely applied in the field of medical care. Meanwhile, radiomics based on traditional machine learning also does a great job in mining information through medical images. With the integration of AI and radiomics, great progress has been made in the early diagnosis, specific characterization, and prognosis of lung cancer, which has aroused attention all over the world. In this study, we give a brief review of the current application of AI and radiomics for precision medical management in lung cancer.

18F-FDG PET and DCE kinetic modeling and their correlations in primary NSCLC: first voxel-wise correlative analysis of human simultaneous [18F]FDG PET-MRI data

OBJECTIVES

To decipher the correlations between PET and DCE kinetic parameters in non-small-cell lung cancer (NSCLC), by using voxel-wise analysis of dynamic simultaneous [18F]FDG PET-MRI.

MATERIAL AND METHODS

Fourteen treatment-naïve patients with biopsy-proven NSCLC prospectively underwent a 1-h dynamic [18F]FDG thoracic PET-MRI scan including DCE. The PET and DCE data were normalized to their corresponding T1-weighted MR morphological space, and tumors were masked semi-automatically. Voxel-wise parametric maps of PET and DCE kinetic parameters were computed by fitting the dynamic PET and DCE tumor data to the Sokoloff and Extended Tofts models respectively, by using in-house developed procedures. Curve-fitting errors were assessed by computing the relative root mean square error (rRMSE) of the estimated PET and DCE signals at the voxel level. For each tumor, Spearman correlation coefficients (rs) between all the pairs of PET and DCE kinetic parameters were estimated on a voxel-wise basis, along with their respective bootstrapped 95% confidence intervals (n = 1000 iterations).

RESULTS

Curve-fitting metrics provided fit errors under 20% for almost 90% of the PET voxels (median rRMSE = 10.3, interquartile ranges IQR = 8.1; 14.3), whereas 73.3% of the DCE voxels showed fit errors under 45% (median rRMSE = 31.8%, IQR = 22.4; 46.6). The PET-PET, DCE-DCE, and PET-DCE voxel-wise correlations varied according to individual tumor behaviors. Beyond this wide variability, the PET-PET and DCE-DCE correlations were mainly high (absolute rs values > 0.7), whereas the PET-DCE correlations were mainly low to moderate (absolute rs values < 0.7). Half the tumors showed a hypometabolism with low perfused/vascularized profile, a hallmark of hypoxia, and tumor aggressiveness.

CONCLUSION

A dynamic "one-stop shop" procedure applied to NSCLC is technically feasible in clinical practice. PET and DCE kinetic parameters assessed simultaneously are not highly correlated in NSCLC, and these correlations showed a wide variability among tumors and patients. These results tend to suggest that PET and DCE kinetic parameters might provide complementary information. In the future, this might make PET-MRI a unique tool to characterize the individual tumor biological behavior in NSCLC.

Reinventing radiation therapy with machine learning and imaging bio-markers (radiomics): State-of-the-art, challenges and perspectives

Radiation therapy is a pivotal cancer treatment that has significantly progressed over the last decade due to numerous technological breakthroughs. Imaging is now playing a critical role on deployment of the clinical workflow, both for treatment planning and treatment delivery. Machine-learning analysis of predefined features extracted from medical images, i.e. radiomics, has emerged as a promising clinical tool for a wide range of clinical problems addressing drug development, clinical diagnosis, treatment selection and implementation as well as prognosis. Radiomics denotes a paradigm shift redefining medical images as a quantitative asset for data-driven precision medicine. The adoption of machine-learning in a clinical setting and in particular of radiomics features requires the selection of robust, representative and clinically interpretable biomarkers that are properly evaluated on a representative clinical data set. To be clinically relevant, radiomics must not only improve patients' management with great accuracy but also be reproducible and generalizable. Hence, this review explores the existing literature and exposes its potential technical caveats, such as the lack of quality control, standardization, sufficient sample size, type of data collection, and external validation. Based upon the analysis of 165 original research studies based on PET, CT-scan, and MRI, this review provides an overview of new concepts, and hypotheses generating findings that should be validated. In particular, it describes evolving research trends to enhance several clinical tasks such as prognostication, treatment planning, response assessment, prediction of recurrence/relapse, and prediction of toxicity. Perspectives regarding the implementation of an AI-based radiotherapy workflow are presented.

Standardized thresholds of volume-based PET/CT parameters predicting survival of patients with pancreatic head cancer treated with stereotactic body radiation therapy

OBJECTIVE

To explore standardized relative thresholds of volume-based parameters on FDG PET/CT, and define the optimal prognosticator among the relative thresholds for patients with locally advanced pancreatic head cancer (LAPHC) treated by stereotactic body radiation therapy (SBRT).

METHODS

Thirty-five patients with LAPHC were enrolled, and all underwent SBRT and baseline FDG PET/CT scan. Maximum standardized uptake value (SUVmax) was measured, and metabolic tumor volume (MTV) and total lesion glycolysis (TLG) were calculated under the relative (30%, 40%, and 50%) thresholds of SUVmax. Survival analysis was performed via univariate and multivariate analyses, and independent prognostic factors were determined by Cox proportional hazard models and corresponding survival curves and scatter diagram were drawn.

RESULTS

The median overall survival (OS) and progression-free survival (PFS) were 13.8 and 9.8 months, respectively. On univariate analysis, MTV(40%) < 5.6 cm³, accumulated dose (AD) ≥ 36 Gy and the absence of pancreatic duct (PD) stents were significantly correlated with both superior OS and PFS, TLG (40%) < 29.9 was related to better OS and biological effective dose (BED₁₀) ≥ 57.6 Gy was related to better PFS (all with p < 0.05). Further, multivariate analysis demonstrated both MTV (40%) and AD were independent prognosticators for OS and PFS, and BED₁₀ was an independent predictor for PFS (all with p < 0.05). Scatter diagram showed BED₁₀ to be a stronger clinical prognosis predictor for PFS than AD.

CONCLUSIONS

MTV (40%) was the optimal prognosticator among the relative thresholds of SUVmax for tumor delineation on PET/CT for LAPHC patients receiving SBRT. AD was also favorable indicators for OS and PFS of patients, and BED₁₀ was more sensitive than AD in predicting the PFS of patients.

Comparison of bone structure and microstructure in the metacarpal heads between patients with psoriatic arthritis and healthy controls: an HR-pQCT study

Human cadaveric study has indicated that the metacarpal head (MCH) is intracapsular in location. We hypothesized that exposure to the intra-articular inflammatory milieu in psoriatic arthritis (PsA) will lead to bone loss in the MCH.

INTRODUCTION

To compare the bone structure and microstructure in the MCH between patients with PsA and healthy controls by high-resolution peripheral quantitative CT (HR-pQCT), and to ascertain factors associated with bone loss in PsA patients.

METHODS

Sixty-two PsA patients without joint destruction and 62 age-, gender-, and body mass index-matched healthy subjects underwent HR-pQCT imaging of the second and third MCH (MCH 2&3). The number and volume of bone erosion and enthesiophytes, as well as volumetric bone mineral density (vBMD) and microstructure at the MCH 2&3, were recorded. Correlation analysis and multivariable linear regression models were used to determine the association of demographic and disease-specific variables with compromised bone structure and microstructure in PsA.

RESULTS

At the MCH 2&3, bone erosion (p = 0.003) and enthesiophyte (p = 0.000) volumes in PsA patients were significantly larger than healthy controls. In PsA patients, older age was associated with a larger erosion and enthesiophyte volume. Concerning the mean vBMD and microstructure at the MCH 2&3, PsA patients had significantly lower mean vBMD (average vBMD - 6.9%, trabecular vBMD - 8.8%, peri-trabecular vBMD - 7.7%, meta-trabecular vBMD - 9.8%), trabecular bone volume fraction (- 8.8%), and trabecular thickness (- 8.1%) compared with control subjects. Multivariable regression analysis revealed that older age and a higher C-reactive protein level were associated with trabecular bone loss.

CONCLUSIONS

PsA patients had a higher burden of bone damages (erosions and enthesiophytes) and trabecular bone loss compared with healthy control at the MCH. Inflammation contributed to the deterioration in trabecular microstructure in these patients.

Diffusion-weighted Imaging Voxelwise-matched Analyses of Lung Cancer at 3.0-T PET/MRI: Reverse Phase Encoding Approach for Echo-planar Imaging Distortion Correction

Background PET/MRI has drawn increasing interest in thoracic oncology due to the simultaneous acquisition of PET and MRI data. Geometric distortions related to diffusion-weighted imaging (DWI) limit the evaluation of voxelwise multimodal analyses. Purpose To assess the effectiveness of reverse phase encoding in correcting DWI geometric distortion for multimodal PET/MRI voxelwise lung tumor analyses. Materials and Methods In this prospective study, reverse phase encoding method was implemented with 3.0-T PET/MRI to correct geometric distortions related to DWI. The method was validated in dedicated phantom and then applied to 12 consecutive patients (mean age, 66 years ± 13 [standard deviation]; 10 men) suspected of having lung cancer who underwent fluorodeoxyglucose PET/MRI between October 2018 and April 2019. The effects on DWI-related image matching and apparent diffusion coefficient (ADC) regional map computation were assessed. Consequences on multimodal PET/MRI voxelwise lung tumor analyses were evaluated. Spearman correlation coefficients (r_s) between the standardized uptake value (SUV) and ADC data corrected for distortion were computed from optimal realigned DWI PET data, along with bootstrap confidence intervals. Results Phantom results showed that in highly distorted areas, correcting the distortion significantly reduced the mean error against the ground truth (-25% ± 10.6 to -18.4% ± 12.6; P < .001) and the number of voxels with more than 20% error (from 85.3% to 31.4%). In the 12 patients, the coregistration of multimodal PET/MRI tumor data was improved by using the reverse phase encoding method (0.4%-44%). In all tumors, voxelwise correlations (r_s) between ADC and SUV revealed null or weak monotonic relationships (mean r_s of 0.016 ± 0.24 with none above 0.5). Conclusion Reverse phase encoding is a simple-to-implement method for improved diffusion-weighted multimodal PET/MRI voxelwise-matched analyses in lung cancer. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Colletti in this issue.

Assessing PD-L1 Expression Level by Radiomic Features From PET/CT in Nonsmall Cell Lung Cancer Patients: An Initial Result

RATIONALE AND OBJECTIVES

To explore the potential value of radiomic features-derived approach in assessing PD-L1 expression status in nonsmall cell lung cancer (NSCLC) patients.

MATERIALS AND METHODS

A cohort of 399 stage I-IV NSCLC patients were enrolled. Tumor segmentation was performed to select essential primary lesions of NSCLC cases after PET/CT images acquisition. Features were extracted, then filtered with automatic relevance determination and minimized with LASSO model based on its relevance of PD-L1 expression status. Finally, we built predictive models with features from the CT, the PET, and the PET/CT images, respectively, for differentiating different status of specific PD-L1 types. Five-fold cross validation was practiced to evaluate the signatures' accuracy, and the receiver operating characteristic as well as the corresponding area under the curve (AUC) was reckoned for each model.

RESULTS

With the total of 24 selected features which were significantly associated with PD-L1 expression levels, models based on CT-, PET-, PET/CT-derived features were built and compared. For PD-L1 (SP142) expression level over 1% prediction, models that comprised radiomic features from the CT, the PET, and the PET/CT images resulted in an AUC of 0.97, 0.61, and 0.97, respectively; models for over 50% prediction resulted with AUC of 0.80, 0.65, and 0.77. For PD-L1 (28-8) expression level prediction, predictive models of over 1% expression scored at 0.86, 0.62, and 0.85; and signatures of over 50% expression reached the score of AUCs at 0.91, 0.75, and 0.88, respectively.

CONCLUSION

The radiomic-based predictive approach, especially CT-derived predictive model, may anticipate PD-L1 expression status in NSCLC patients relatively accurate. It may be helpful in guiding immunotherapy in clinical practice and deserves further analysis.

Multiparametric quantitative and texture 18F-FDG PET/CT analysis for primary malignant tumour grade differentiation

Background

¹⁸F-FDG positron emission tomography/computed tomography (PET/CT) is a successfully used imaging modality in oncology. The aim of the study was to investigate a connection of epithelial tumour differentiation grade with both semiquantitative and quantitative metabolic PET data focusing on creation of multiparametric model of tumour grade prediction utilising both standardised uptake value-based and texture-based ¹⁸F-FDG PET parameters and to investigate an influence of different image segmentation techniques on these parameters and modelling.

Methods

¹⁸F-FDG PET/CT data from 84 patients with epithelial malignant tumours was retrospectively analysed to create sets of both conventional semiquantitative (based on standardised uptake values), volumetric, and quantitative texture metabolic parameters of primary tumours with four different segmentation techniques.

Results

Most of the calculated volumetric and texture parameters showed to be influenced by segmentation technique. There was no significant difference in values of only three parameters, in all four segmentation methods: homogeneity, energy, and sphericity. Almost every extracted parameter in all segmentation technique subsets showed significant ability to discriminate individual tumour grade versus the subset of remaining two tumour grades. No parameters were able to discriminate all three tumour grades separately simultaneously or without the overlapping of threshold values. Group method of data handling (GMDH) modelling included all the above-mentioned extracted parameters. The highest value to discriminate tumour grade was achieved using ITK-SNAP segmentation, with an accuracy ranging from 91 to 100%.

Conclusions

Multiparametric modelling with GMDH utilising both semiquantitative and quantitative texture metabolic PET parameters seems to be an interesting tool for non-invasive malignant epithelial tumours grade differentiation.

Usefulness of gradient tree boosting for predicting histological subtype and EGFR mutation status of non-small cell lung cancer on 18F FDG-PET/CT

OBJECTIVE

To develop and evaluate a radiomics approach for classifying histological subtypes and epidermal growth factor receptor (EGFR) mutation status in lung cancer on PET/CT images.

METHODS

PET/CT images of lung cancer patients were obtained from public databases and used to establish two datasets, respectively to classify histological subtypes (156 adenocarcinomas and 32 squamous cell carcinomas) and EGFR mutation status (38 mutant and 100 wild-type samples). Seven types of imaging features were obtained from PET/CT images of lung cancer. Two types of machine learning algorithms were used to predict histological subtypes and EGFR mutation status: random forest (RF) and gradient tree boosting (XGB). The classifiers used either a single type or multiple types of imaging features. In the latter case, the optimal combination of the seven types of imaging features was selected by Bayesian optimization. Receiver operating characteristic analysis, area under the curve (AUC), and tenfold cross validation were used to assess the performance of the approach.

RESULTS

In the classification of histological subtypes, the AUC values of the various classifiers were as follows: RF, single type: 0.759; XGB, single type: 0.760; RF, multiple types: 0.720; XGB, multiple types: 0.843. In the classification of EGFR mutation status, the AUC values were: RF, single type: 0.625; XGB, single type: 0.617; RF, multiple types: 0.577; XGB, multiple types: 0.659.

CONCLUSIONS

The radiomics approach to PET/CT images, together with XGB and Bayesian optimization, is useful for classifying histological subtypes and EGFR mutation status in lung cancer.

Development and validation of a prognostic index for efficacy evaluation and prognosis of first-line chemotherapy in stage III-IV lung squamous cell carcinoma

OBJECTIVES

To establish a pre-therapy prognostic index model (PIM) of the first-line chemotherapy aiming to achieve accurate prediction of time to progression (TTP) and overall survival among the patients diagnosed with locally advanced (stage III) or distant metastasis (stage IV) lung squamous cell carcinoma (LSCC).

METHODS

Ninety-six LSCC patients treated with first-line chemotherapy were retrospectively enrolled to build the model. Fourteen epidermal growth factor receptor (EGFR)-mutant LSCC patients treated with first-line EGFR-tyrosine kinase inhibitor (TKI) therapy were enrolled for validation dataset. From CT images, 56,000 phenotype features were initially computed. PIM was constructed by integrating a CT phenotype signature selected by the least absolute shrinkage and selection operator and the significant blood-based biomarkers selected by multivariate Cox regression. PIM was then compared with other four prognostic models constructed by the CT phenotype signature, clinical factors, post-therapy tumor response, and Glasgow Prognostic Score.

RESULTS

The signature includes eight optimal features extracted from co-occurrence, run length, and Gabor features. By using PIM, chemotherapy efficacy of patients categorized in the low-risk, intermediate-risk, and high-risk progression subgroups (median TTP = 7.2 months, 3.4 months, and 1.8 months, respectively) was significantly different (p < 0.0001, log-rank test). Chemotherapy efficacy of the low-risk progression subgroup was comparable with EGFR-TKI therapy (p = 0.835, log-rank test). Prognostic prediction of chemotherapy efficacy by PIM was significantly higher than other models (p < 0.05, z test).

CONCLUSION

The study demonstrated that the PIM yielded significantly higher performance to identify individual stage III-IV LSCC patients who can potentially benefit most from first-line chemotherapy, and predict the risk of failure from chemotherapy for individual patients.

KEY POINTS

• TTP and OS of first-line chemotherapy in individual stage III-IV LSCC patients could be predicted by pre-therapy blood-based biomarkers and image-based signatures. • Risk status of pre-therapy indicators affected the efficacy of first-line chemotherapy in stage III-IV LSCC patients. • Those stage III-IV LSCC patients who were able to achieve similar efficacy to EGFR-TKI therapy through chemotherapy were identified.