Synthetic PET from CT improves diagnosis and prognosis for lung cancer: Proof of concept.

[18F]Fluorodeoxyglucose positron emission tomography (FDG-PET) and computed tomography (CT) are indispensable components in modern medicine. Although PET can provide additional diagnostic value, it is costly and not universally accessible, particularly in low-income countries. To bridge this gap, we have developed a conditional generative adversarial network pipeline that can produce FDG-PET from diagnostic CT scans based on multi-center multi-modal lung cancer datasets (n = 1,478). Synthetic PET images are validated across imaging, biological, and clinical aspects. Radiologists confirm comparable imaging quality and tumor contrast between synthetic and actual PET scans. Radiogenomics analysis further proves that the dysregulated cancer hallmark pathways of synthetic PET are consistent with actual PET. We also demonstrate the clinical values of synthetic PET in improving lung cancer diagnosis, staging, risk prediction, and prognosis. Taken together, this proof-of-concept study testifies to the feasibility of applying deep learning to obtain high-fidelity PET translated from CT.

A radiomic- and dosiomic-based machine learning regression model for pretreatment planning in 177 Lu-DOTATATE therapy.

BACKGROUND: Standardized patient-specific pretreatment dosimetry planning is mandatory in the modern era of nuclear molecular radiotherapy, which may eventually lead to improvements in the final therapeutic outcome. Only a comprehensive definition of a dosage therapeutic window encompassing the range of absorbed doses, that is, helpful without being detrimental can lead to therapy individualization and improved outcomes. As a result, setting absorbed dose safety limits for organs at risk (OARs) requires knowledge of the absorbed dose-effect relationship. Data sets of consistent and reliable inter-center dosimetry findings are required to characterize this relationship. PURPOSE: We developed and standardized a new pretreatment planning model consisting of a predictive dosimetry procedure for OARs in patients with neuroendocrine tumors (NETs) treated with 177 Lu-DOTATATE (Lutathera). In the retrospective study described herein, we used machine learning (ML) regression algorithms to predict absorbed doses in OARs by exploiting a combination of radiomic and dosiomic features extracted from patients' imaging data. METHODS: Pretreatment and posttreatment data for 20 patients with NETs treated with 177 Lu-DOTATATE were collected from two clinical centers. A total of 3412 radiomic and dosiomic features were extracted from the patients' computed tomography (CT) scans and dose maps, respectively. All dose maps were generated using Monte Carlo simulations. An ML regression model was designed based on ML algorithms for predicting the absorbed dose in every OAR (liver, left kidney, right kidney, and spleen) before and after the therapy and between each therapy session, thus predicting any possible radiotoxic effects. RESULTS: We evaluated nine ML regression algorithms. Our predictive model achieved a mean absolute dose error (MAE, in Gy) of 0.61 for the liver, 1.58 for the spleen, 1.30 for the left kidney, and 1.35 for the right kidney between pretherapy 68 Ga-DOTATOC positron emission tomography (PET)/CT and posttherapy 177 Lu-DOTATATE single photon emission (SPECT)/CT scans. Τhe best predictive performance observed was based on the gradient boost for the liver, the left kidney and the right kidney, and on the extra tree regressor for the spleen. Evaluation of the model's performance according to its ability to predict the absorbed dose in each OAR in every possible combination of pretherapy 68 Ga-DOTATOC PET/CT and any posttherapy 177 Lu-DOTATATE treatment cycle SPECT/CT scans as well as any 177 Lu-DOTATATE SPECT/CT treatment cycle and the consequent 177 Lu-DOTATATE SPECT/CT treatment cycle revealed mean absorbed dose differences ranges from -0.55 to 0.68 Gy. Incorporating radiodosiomics features from the 68 Ga-DOTATOC PET/CT and first 177 Lu-DOTATATE SPECT/CT treatment cycle scans further improved the precision and minimized the standard deviation of the predictions in nine out of 12 instances. An average improvement of 57.34% was observed (range: 17.53%-96.12%). However, it's important to note that in three instances (i.e., Ga,C.1 â†’ C3 in spleen and left kidney, and Ga,C.1 â†’ C2 in right kidney) we did not observe an improvement (absolute differences of 0.17, 0.08, and 0.05 Gy, respectively). Wavelet-based features proved to have high correlated predictive value, whereas non-linear-based ML regression algorithms proved to be more capable than the linear-based of producing precise prediction in our case. CONCLUSIONS: The combination of radiomics and dosiomics has potential utility for personalized molecular radiotherapy (PMR) response evaluation and OAR dose prediction. These radiodosiomic features can potentially provide information on any possible disease recurrence and may be highly useful in clinical decision-making, especially regarding dose escalation issues.

Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study.

BACKGROUND: Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying cancer biology. We aimed to investigate the application of deep learning on chest CT scans to derive an imaging signature of response to immune checkpoint inhibitors and evaluate its added value in the clinical context. METHODS: In this retrospective modelling study, 976 patients with metastatic, EGFR/ALK negative NSCLC treated with immune checkpoint inhibitors at MD Anderson and Stanford were enrolled from Jan 1, 2014, to Feb 29, 2020. We built and tested an ensemble deep learning model on pretreatment CTs (Deep-CT) to predict overall survival and progression-free survival after treatment with immune checkpoint inhibitors. We also evaluated the added predictive value of the Deep-CT model in the context of existing clinicopathological and radiological metrics. FINDINGS: Our Deep-CT model demonstrated robust stratification of patient survival of the MD Anderson testing set, which was validated in the external Stanford set. The performance of the Deep-CT model remained significant on subgroup analyses stratified by PD-L1, histology, age, sex, and race. In univariate analysis, Deep-CT outperformed the conventional risk factors, including histology, smoking status, and PD-L1 expression, and remained an independent predictor after multivariate adjustment. Integrating the Deep-CT model with conventional risk factors demonstrated significantly improved prediction performance, with overall survival C-index increases from 0·70 (clinical model) to 0·75 (composite model) during testing. On the other hand, the deep learning risk scores correlated with some radiomics features, but radiomics alone could not reach the performance level of deep learning, indicating that the deep learning model effectively captured additional imaging patterns beyond known radiomics features. INTERPRETATION: This proof-of-concept study shows that automated profiling of radiographic scans through deep learning can provide orthogonal information independent of existing clinicopathological biomarkers, bringing the goal of precision immunotherapy for patients with NSCLC closer. FUNDING: National Institutes of Health, Mark Foundation Damon Runyon Foundation Physician Scientist Award, MD Anderson Strategic Initiative Development Program, MD Anderson Lung Moon Shot Program, Andrea Mugnaini, and Edward L C Smith.

Institutional Strategies to Maintain and Grow Imaging Research During the COVID-19 Pandemic.

Understanding imaging research experiences, challenges, and strategies for academic radiology departments during and after COVID-19 is critical to prepare for future disruptive events. We summarize key insights and programmatic initiatives at major academic hospitals across the world, based on literature review and meetings of the Radiological Society of North America Vice Chairs of Research (RSNA VCR) group. Through expert discussion and case studies, we provide suggested guidelines to maintain and grow radiology research in the postpandemic era.

Multimodality annotated hepatocellular carcinoma data set including pre- and post-TACE with imaging segmentation.

Hepatocellular carcinoma (HCC) is the most common primary liver neoplasm, and its incidence has doubled over the past two decades owing to increasing risk factors. Despite surveillance, most HCC cases are diagnosed at advanced stages and can only be treated using transarterial chemo-embolization (TACE) or systemic therapy. TACE failure may occur with incidence reaching up to 60% of cases, leaving patients with a financial and emotional burden. Radiomics has emerged as a new tool capable of predicting tumor response to TACE from pre-procedural computed tomography (CT) studies. This data report defines the HCC-TACE data collection of confirmed HCC patients who underwent TACE and have pre- and post-procedure CT imaging studies and available treatment outcomes (time-to-progression and overall survival). Clinically curated segmentation of pre-procedural CT studies was done for the purpose of algorithm training for prediction and automatic liver tumor segmentation.

AAPM Report 373: The content, structure, and value of the Professional Doctorate in Medical Physics (DMP).

The Professional Doctorate in Medical Physics (DMP) was originally conceived as a solution to the shortage of medical physics residency training positions. While this shortage has now been largely satisfied through conventional residency training positions, the DMP has expanded to multiple institutions and grown into an educational pathway that provides specialized clinical training and extends well beyond the creation of additional training spots. As such, it is important to reevaluate the purpose and the value of the DMP. Additionally, it is important to outline the defining characteristics of the DMP to assure that all existing and future programs provide this anticipated value. Since the formation and subsequent accreditation of the first DMP program in 2009-2010, four additional programs have been created and accredited. However, no guidelines have yet been recommended by the American Association of Physicists in Medicine. CAMPEP accreditation of these programs has thus far been based only on the respective graduate and residency program standards. This allows the development and operation of DMP programs which contain only the requisite Master of Science (MS) coursework and a 2-year clinical training program. Since the MS plus 2-year residency pathway already exists, this form of DMP does not provide added value, and one may question why this existing pathway should be considered a doctorate. Not only do we, as a profession, need to outline the defining characteristics of the DMP, we need to carefully evaluate the potential advantages and disadvantages of this pathway within our education and training infrastructure. The aims of this report from the Working Group on the Professional Doctorate Degree for Medical Physicists (WGPDMP) are to (1) describe the current state of the DMP within the profession, (2) make recommendations on the structure and content of the DMP for existing and new DMP programs, and (3) evaluate the value of the DMP to the profession of medical physics.

Chronic Lymphocytic Leukemia Progression Diagnosis with Intrinsic Cellular Patterns via Unsupervised Clustering.

Identifying the progression of chronic lymphocytic leukemia (CLL) to accelerated CLL (aCLL) or transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications as it prompts a major change in patient management. However, the differentiation between these disease phases may be challenging in routine practice. Unsupervised learning has gained increased attention because of its substantial potential in data intrinsic pattern discovery. Here, we demonstrate that cellular feature engineering, identifying cellular phenotypes via unsupervised clustering, provides the most robust analytic performance in analyzing digitized pathology slides (accuracy = 0.925, AUC = 0.978) when compared to alternative approaches, such as mixed features, supervised features, unsupervised/mixed/supervised feature fusion and selection, as well as patch-based convolutional neural network (CNN) feature extraction. We further validate the reproducibility and robustness of unsupervised feature extraction via stability and repeated splitting analysis, supporting its utility as a diagnostic aid in identifying CLL patients with histologic evidence of disease progression. The outcome of this study serves as proof of principle using an unsupervised machine learning scheme to enhance the diagnostic accuracy of the heterogeneous histology patterns that pathologists might not easily see.

One-Pot, One-Step Synthesis of Drug-Loaded Magnetic Multimicelle Aggregates.

Lipid-based formulations provide a nanotechnology platform that is widely used in a variety of biomedical applications because it has several advantageous properties including biocompatibility, reduced toxicity, relative ease of surface modifications, and the possibility for efficient loading of drugs, biologics, and nanoparticles. A combination of lipid-based formulations with magnetic nanoparticles such as iron oxide was shown to be highly advantageous in a growing number of applications including magnet-mediated drug delivery and image-guided therapy. Currently, lipid-based formulations are prepared by multistep protocols. Simplification of the current multistep procedures can lead to a number of important technological advantages including significantly decreased processing time, higher reaction yield, better product reproducibility, and improved quality. Here, we introduce a one-pot, single-step synthesis of drug-loaded magnetic multimicelle aggregates (MaMAs), which is based on controlled flow infusion of an iron oxide nanoparticle/lipid mixture into an aqueous drug solution under ultrasonication. Furthermore, we prepared molecular-targeted MaMAs by directional antibody conjugation through an Fc moiety using Cu-free click chemistry. Fluorescence imaging and quantification confirmed that antibody-conjugated MaMAs showed high cell-specific targeting that was enhanced by magnetic delivery.

Artificial intelligence-assisted mapping of proliferation centers allows the distinction of accelerated phase from large cell transformation in chronic lymphocytic leukemia.

Chronic lymphocytic leukemia/small lymphocytic lymphoma (CLL) is characterized morphologically by numerous small lymphocytes and pale nodules composed of prolymphocytes and paraimmunoblasts known as proliferation centers (PCs). Patients with CLL can undergo transformation to a more aggressive lymphoma, most often diffuse large B-cell lymphoma (DLBCL), known as Richter transformation (RT). An accelerated phase of CLL (aCLL) also may be observed which correlates with subsequent transformation to DLBCL, and may represent an early stage of transformation. Distinguishing PCs in CLL from aCLL or RT can be diagnostically challenging, particularly in small needle biopsy specimens. Available guidelines pertaining to distinguishing CLL from its' progressive forms are limited, subject to the morphologist's experience and are often not completely helpful in the assessment of scant biopsy specimens. To objectively assess the extent of PCs in aCLL and RT, and enhance diagnostic accuracy, we sought to design an artificial intelligence (AI)-based tool to identify and delineate PCs based on feature analysis of the combined individual nuclear size and intensity, designated here as the heat value. Using the mean heat value from the generated heat value image of all cases, we were able to reliably separate CLL, aCLL and RT with sensitive diagnostic predictive values.

A model combining pretreatment MRI radiomic features and tumor-infiltrating lymphocytes to predict response to neoadjuvant systemic therapy in triple-negative breast cancer.

PURPOSE: We aimed to develop a predictive model based on pretreatment MRI radiomic features (MRIRF) and tumor-infiltrating lymphocyte (TIL) levels, an established prognostic marker, to improve the accuracy of predicting pathologic complete response (pCR) to neoadjuvant systemic therapy (NAST) in triple-negative breast cancer (TNBC) patients. METHODS: This Institutional Review Board (IRB) approved retrospective study included a preliminary set of 80 women with biopsy-proven TNBC who underwent NAST, pretreatment dynamic contrast enhanced MRI, and biopsy-based pathologic assessment of TIL. A threshold of ≥ 20% was used to define high TIL. Patients were classified into pCR and non-pCR based on pathologic evaluation of post-NAST surgical specimens. pCR was defined as the absence of invasive carcinoma in the surgical specimen. Segmentation and MRIRF extraction were done using a Food and Drug Administration (FDA) approved software QuantX. The top five features were combined into a single MRIRF signature value. RESULTS: Of 145 extracted MRIRF, 38 were significantly correlated with pCR. Five nonredundant imaging features were identified: volume, uniformity, peak timepoint variance, homogeneity, and variance. The accuracy of the MRIRF model, P = .001, 72.7% positive predictive value (PPV), 72.0% negative predictive value (NPV), was similar to the TIL model (P = .038, 65.5% PPV, 72.6% NPV). When MRIRF and TIL models were combined, we observed improved prognostic accuracy (P < .001, 90.9% PPV, 81.4% NPV). The models area under the receiver operating characteristic curve (AUC) was 0.632 (TIL), 0.712 (MRIRF) and 0.752 (TIL + MRIRF). CONCLUSION: A predictive model combining pretreatment MRI radiomic features with TIL level on pretreatment core biopsy improved accuracy in predicting pCR to NAST in TNBC patients.

Lesion-Based Radiomics Signature in Pretherapy 18F-FDG PET Predicts Treatment Response to Ibrutinib in Lymphoma.

PURPOSE: The aim of this study was to develop a pretherapy PET/CT-based prediction model for treatment response to ibrutinib in lymphoma patients. PATIENTS AND METHODS: One hundred sixty-nine lymphoma patients with 2441 lesions were studied retrospectively. All eligible lymphomas on pretherapy 18F-FDG PET images were contoured and segmented for radiomic analysis. Lesion- and patient-based responsiveness to ibrutinib was determined retrospectively using the Lugano classification. PET radiomic features were extracted. A radiomic model was built to predict ibrutinib response. The prognostic significance of the radiomic model was evaluated independently in a test cohort and compared with conventional PET metrics: SUVmax, metabolic tumor volume, and total lesion glycolysis. RESULTS: The radiomic model had an area under the receiver operating characteristic curve (ROC AUC) of 0.860 (sensitivity, 92.9%, specificity, 81.4%; P < 0.001) for predicting response to ibrutinib, outperforming the SUVmax (ROC AUC, 0.519; P = 0.823), metabolic tumor volume (ROC AUC, 0.579; P = 0.412), total lesion glycolysis (ROC AUC, 0.576; P = 0.199), and a composite model built using all 3 (ROC AUC, 0.562; P = 0.046). The radiomic model increased the probability of accurately predicting ibrutinib-responsive lesions from 84.8% (pretest) to 96.5% (posttest). At the patient level, the model's performance (ROC AUC = 0.811; P = 0.007) was superior to that of conventional PET metrics. Furthermore, the radiomic model showed robustness when validated in treatment subgroups: first (ROC AUC, 0.916; P < 0.001) versus second or greater (ROC AUC, 0.842; P < 0.001) line of defense and single treatment (ROC AUC, 0.931; P < 0.001) versus multiple treatments (ROC AUC, 0.824; P < 0.001). CONCLUSIONS: We developed and validated a pretherapy PET-based radiomic model to predict response to treatment with ibrutinib in a diverse cohort of lymphoma patients.

A deep-learning-based prediction model for the biodistribution of 90 Y microspheres in liver radioembolization.

BACKGROUND: Radioembolization with 90 Y microspheres is a treatment approach for liver cancer. Currently, employed dosimetric calculations exhibit low accuracy, lacking consideration of individual patient, and tissue characteristics. PURPOSE: The purpose of the present study was to employ deep learning (DL) algorithms to differentiate patterns of pretreatment distribution of 99m Tc-macroaggregated albumin on SPECT/CT and post-treatment distribution of 90 Y microspheres on PET/CT and to accurately predict how the 90 Y-microspheres will be distributed in the liver tissue by radioembolization therapy. METHODS: Data for 19 patients with liver cancer (10 with hepatocellular carcinoma, 5 with intrahepatic cholangiocarcinoma, 4 with liver metastases) who underwent radioembolization with 90 Y microspheres were used for the DL training. We developed a 3D voxel-based variation of the Pix2Pix model, which is a special type of conditional GANs designed to perform image-to-image translation. SPECT and CT scans along with the clinical target volume for each patient were used as inputs, as were their corresponding post-treatment PET scans. The real and predicted absorbed PET doses for the tumor and the whole liver area were compared. Our model was evaluated using the leave-one-out method, and the dose calculations were measured using a tissue-specific dose voxel kernel. RESULTS: The comparison of the real and predicted PET/CT scans showed an average absorbed dose difference of 5.42% ± 19.31% and 0.44% ± 1.64% for the tumor and the liver area, respectively. The average absorbed dose differences were 7.98 ± 31.39 Gy and 0.03 ± 0.25 Gy for the tumor and the non-tumor liver parenchyma, respectively. Our model had a general tendency to underpredict the dosimetric results; the largest differences were noticed in one case, where the model underestimated the dose to the tumor area by 56.75% or 72.82 Gy. CONCLUSIONS: The proposed deep-learning-based pretreatment planning method for liver radioembolization accurately predicted 90 Y microsphere biodistribution. Its combination with a rapid and accurate 3D dosimetry method will render it clinically suitable and could improve patient-specific pretreatment planning.

Findings of the AAPM Ad Hoc committee on magnetic resonance imaging in radiation therapy: Unmet needs, opportunities, and recommendations.

The past decade has seen the increasing integration of magnetic resonance (MR) imaging into radiation therapy (RT). This growth can be contributed to multiple factors, including hardware and software advances that have allowed the acquisition of high-resolution volumetric data of RT patients in their treatment position (also known as MR simulation) and the development of methods to image and quantify tissue function and response to therapy. More recently, the advent of MR-guided radiation therapy (MRgRT) - achieved through the integration of MR imaging systems and linear accelerators - has further accelerated this trend. As MR imaging in RT techniques and technologies, such as MRgRT, gain regulatory approval worldwide, these systems will begin to propagate beyond tertiary care academic medical centers and into more community-based health systems and hospitals, creating new opportunities to provide advanced treatment options to a broader patient population. Accompanying these opportunities are unique challenges related to their adaptation, adoption, and use including modification of hardware and software to meet the unique and distinct demands of MR imaging in RT, the need for standardization of imaging techniques and protocols, education of the broader RT community (particularly in regards to MR safety) as well as the need to continue and support research, and development in this space. In response to this, an ad hoc committee of the American Association of Physicists in Medicine (AAPM) was formed to identify the unmet needs, roadblocks, and opportunities within this space. The purpose of this document is to report on the major findings and recommendations identified. Importantly, the provided recommendations represent the consensus opinions of the committee's membership, which were submitted in the committee's report to the AAPM Board of Directors. In addition, AAPM ad hoc committee reports differ from AAPM task group reports in that ad hoc committee reports are neither reviewed nor ultimately approved by the committee's parent groups, including at the council and executive committee level. Thus, the recommendations given in this summary should not be construed as being endorsed by or official recommendations from the AAPM.

Machine learning-based texture analysis for differentiation of radiologically indeterminate small adrenal tumors on adrenal protocol CT scans.

GOAL: To evaluate the ability of radiomic feature extraction and a machine learning algorithm to differentiate between benign and malignant indeterminate adrenal lesions on contrast-enhanced computed tomography (CT) studies. BACKGROUND: Adrenal "incidentalomas" are adrenal lesions that are accidentally discovered during workup not related to the adrenal glands; they have an incidence as high as 5%. Small adrenal incidentalomas (< 4 cm) with high attenuation values on pre-contrast CT(> 10 HU) need further evaluation to calculate the absolute percentage of washout (APW). If the APW is < 60%, these lesions are considered non-adenomas and commonly classified as indeterminate adrenal lesions. Further workup for indeterminate lesions includes more complicated and expensive radiological studies or invasive procedures like biopsy or surgical resection. METHODS: We searched our institutional database for indeterminate adrenal lesions with the following characteristics: < 4 cm, pre-attenuation value > 10 HU, and APW < 60%. Exclusion criteria included pheochromocytoma and no histopathological examination. CT images were converted to Nifti format, and adrenal tumors were segmented using Amira software. Radiomic features from the adrenal mask were extracted using PyRadiomics software after removing redundant features (highly pairwise correlated features and low-variance features) using recursive feature extraction to select the final discriminative set of features. Lastly, the final features were used to build a binary classification model using a random forest algorithm, which was validated and tested using leave-one-out cross-validation, confusion matrix, and receiver operating characteristic curve. RESULTS: We found 40 indeterminate adrenal lesions (21 benign and 19 malignant). Feature extraction resulted in 3947 features, which reduced down to 62 features after removing redundancies. Recursive feature elimination resulted in the following top 4 discriminative features: gray-level size zone matrix-derived size zone non-uniformity from pre-contrast and delayed phases, gray-level dependency matrix-derived large dependence high gray-level emphasis from venous-phase, and gray-level co-occurrence matrix-derived cluster shade from delayed-phase. A binary classification model with leave-one-out cross-validation showed AUC = 0.85, sensitivity = 84.2%, and specificity = 71.4%. CONCLUSION: Machine learning and radiomic features extraction can differentiate between benign and malignant indeterminate adrenal tumors and can be used to direct further workup with high sensitivity and specificity.

Clinical Evaluation of a Three-Dimensional Internal Dosimetry Technique for Liver Radioembolization with 90Y Microspheres Using Dose Voxel Kernels.

Background: The purpose of this study was to develop a rapid, reliable, and efficient tool for three-dimensional (3D) dosimetry treatment planning and post-treatment evaluation of liver radioembolization with 90Y microspheres, using tissue-specific dose voxel kernels (DVKs) that can be used in everyday clinical practice. Materials and Methods: Two tissue-specific DVKs for 90Y were calculated through Monte Carlo (MC) simulations. DVKs for the liver and lungs were generated, and the dose distribution was compared with direct MC simulations. A method was developed to produce a 3D dose map by convolving the calculated DVKs with the activity biodistribution derived from clinical single-photon emission computed tomography (SPECT) or positron emission tomography (PET) images. Image registration for the SPECT or PET images with the corresponding computed tomography scans was performed before dosimetry calculation. The authors first compared the DVK convolution dosimetry with a direct full MC simulation on an XCAT anthropomorphic phantom. They then tested it in 25 individual clinical cases of patients who underwent 90Y therapy. All MC simulations were carried out using the GATE MC toolkit. Results: Comparison of the measured absorbed dose using tissue-specific DVKs and direct MC simulation on 25 patients revealed a mean difference of 1.07% ± 1.43% for the liver and 1.03% ± 1.21% for the tumor tissue, respectively. The largest difference between DVK convolution and full MC dosimetry was observed for the lung tissue (10.16% ± 1.20%). The DVK statistical uncertainty was <0.75% for both media. Conclusions: This semiautomatic algorithm is capable of performing rapid, accurate, and efficient 3D dosimetry. The proposed method considers tissue and activity heterogeneity using tissue-specific DVKs. Furthermore, this method provides results in <1 min, making it suitable for everyday clinical practice.

Deep learning networks on chronic liver disease assessment with fine-tuning of shear wave elastography image sequences.

Chronic liver disease (CLD) is currently one of the major causes of death worldwide. If not treated, it may lead to cirrhosis, hepatic carcinoma and death. Ultrasound (US) shear wave elastography (SWE) is a relatively new, popular, non-invasive technique among radiologists. Although many studies have been published validating the SWE technique either in a clinical setting, or by applying machine learning on SWE elastograms, minimal work has been done on comparing the performance of popular pre-trained deep learning networks on CLD assessment. Currently available literature reports suggest technical advancements on specific deep learning structures, with specific inputs and usually on a limited CLD fibrosis stage class group, with limited comparison on competitive deep learning schemes fed with different input types. The aim of the present study is to compare some popular deep learning pre-trained networks using temporally stable and full elastograms, with or without augmentation as well as propose suitable deep learning schemes for CLD diagnosis and progress assessment. 200 liver biopsy validated patients with CLD, underwent US SWE examination. Four images from the same liver area were saved to extract elastograms and processed to exclude areas that were temporally unstable. Then, full and temporally stable masked elastograms for each patient were separately fed into GoogLeNet, AlexNet, VGG16, ResNet50 and DenseNet201 with and without augmentation. The networks were tested for differentiation of CLD stages in seven classification schemes over 30 repetitions using liver biopsy as the reference. All networks achieved maximum mean accuracies ranging from 87.2%-97.4% and area under the receiver operating characteristic curves (AUCs) ranging from 0.979-0.990 while the radiologists had AUCs ranging from 0.800-0.870. ResNet50 and DenseNet201 had better average performance than the other networks. The use of the temporal stability mask led to improved performance on about 50% of inputs and network combinations while augmentation led to lower performance for all networks. These findings can provide potential networks with higher accuracy and better setting in the CLD diagnosis and progress assessment. A larger data set would help identify the best network and settings for CLD assessment in clinical practice.

Feasibility of Automated Volumetric Assessment of Large Hepatocellular Carcinomas' Responses to Transarterial Chemoembolization.

Background: Hepatocellular carcinoma (HCC) is the most common liver malignancy and the leading cause of death in patients with cirrhosis. Various treatments for HCC are available, including transarterial chemoembolization (TACE), which is the commonest intervention performed in HCC. Radiologic tumor response following TACE is an important prognostic factor for patients with HCC. We hypothesized that, for large HCC tumors, assessment of treatment response made with automated volumetric response evaluation criteria in solid tumors (RECIST) might correlate with the assessment made with the more time- and labor-intensive unidimensional modified RECIST (mRECIST) and manual volumetric RECIST (M-vRECIST) criteria. Accordingly, we undertook this retrospective study to compare automated volumetric RECIST (A-vRECIST) with M-vRECIST and mRESIST for the assessment of large HCC tumors' responses to TACE. Methods:We selected 42 pairs of contrast-enhanced computed tomography (CT) images of large HCCs. Images were taken before and after TACE, and in each of the images, the HCC was segmented using both a manual contouring tool and a convolutional neural network. Three experienced radiologists assessed tumor response to TACE using mRECIST criteria. The intra-class correlation coefficient was used to assess inter-reader reliability in the mRECIST measurements, while the Pearson correlation coefficient was used to assess correlation between the volumetric and mRECIST measurements. Results:Volumetric tumor assessment using automated and manual segmentation tools showed good correlation with mRECIST measurements. For A-vRECIST and M-vRECIST, respectively, r = 0.597 vs. 0.622 in the baseline studies; 0.648 vs. 0.748 in the follow-up studies; and 0.774 vs. 0.766 in the response assessment (P < 0.001 for all). The A-vRECIST evaluation showed high correlation with the M-vRECIST evaluation (r = 0.967, 0.937, and 0.826 in baseline studies, follow-up studies, and response assessment, respectively, P < 0.001 for all). Conclusion:Volumetric RECIST measurements are likely to provide an early marker for TACE monitoring, and automated measurements made with a convolutional neural network may be good substitutes for manual volumetric measurements.

A machine learning model to predict hepatocellular carcinoma response to transcatheter arterial chemoembolization.

PURPOSE: Some patients with hepatocellular carcinoma (HCC) are more likely to experience disease progression despite transcatheter arterial chemoembolization (TACE) treatment, and thus would benefit from early switching to other therapeutic regimens. We sought to evaluate a fully automated machine learning algorithm that uses pre-therapeutic quantitative computed tomography (CT) image features and clinical factors to predict HCC response to TACE. MATERIALS AND METHODS: Outcome information from 105 patients receiving first-line treatment with TACE was evaluated retrospectively. The primary clinical endpoint was time to progression (TTP) based on follow-up CT radiological criteria (mRECIST). A 14-week cutoff was used to classify patients as TACE-susceptible (TTP ≥14 weeks) or TACE-refractory (TTP <14 weeks). Response to TACE was predicted using a random forest classifier with the Barcelona Clinic Liver Cancer (BCLC) stage and quantitative image features as input as well as the BCLC stage alone as a control. RESULTS: The model's response prediction accuracy rate was 74.2% (95% CI=64%-82%) using a combination of the BCLC stage plus quantitative image features versus 62.9% (95% CI= 52%-72%) using the BCLC stage alone. Shape image features of the tumor and background liver were the dominant features correlated to the TTP as selected by the Boruta method and were used to predict the outcome. CONCLUSION: This preliminary study demonstrates that quantitative image features obtained prior to therapy can improve the accuracy of predicting response of HCC to TACE. This approach is likely to provide useful information for aiding HCC patient selection for TACE.

Automated Volumetric Assessment of Hepatocellular Carcinoma Response to Sorafenib: A Pilot Study.

PURPOSE: This pilot study evaluates the feasibility of automated volumetric quantification of hepatocellular carcinoma (HCC) as an imaging biomarker to assess treatment response for sorafenib. METHODS: In this institutional review board-approved, Health Insurance Portability and Accountability Act-compliant retrospective study, a training database of manually labeled background liver, enhancing and nonenhancing tumor tissue was established using pretherapy and first posttherapy multiphasic computed tomography images from a registry of 13 HCC patients. For each patient, Hounsfield density and geometry-based feature images were generated from registered multiphasic computed tomography data sets and used as the input for a random forest-based classifier of enhancing and nonenhancing tumor tissue. Leave-one-out cross-validation of the dice similarity measure was applied to quantify the classifier accuracy. A Cox regression model was used to confirm volume changes as predictors of time to progression (TTP) of target lesions for both manual and automatic methods. RESULTS: When compared with manual labels, an overall classification accuracy of dice similarity coefficient of 0.71 for pretherapy and 0.66 posttherapy enhancing tumor labels and 0.45 for pretherapy and 0.59 for posttherapy nonenhancing tumor labels was observed. Automated methods for quantifying volumetric changes in the enhancing lesion agreed with manual methods and were observed as a significant predictor of TTP. CONCLUSIONS: Automated volumetric analysis was determined to be feasible for monitoring HCC response to treatment. The information extracted using automated volumetrics is likely to reproduce labor-intensive manual data and provide a good predictor for TTP. Further work will extend these studies to additional treatment modalities and larger patient populations.

Temporal stability assessment in shear wave elasticity images validated by deep learning neural network for chronic liver disease fibrosis stage assessment.

PURPOSE: To automatically detect and isolate areas of low and high stiffness temporal stability in shear wave elastography (SWE) image sequences and define their impact in chronic liver disease (CLD) diagnosis improvement by means of clinical examination study and deep learning algorithm employing convolutional neural networks (CNNs). MATERIALS AND METHODS: Two hundred SWE image sequences from 88 healthy individuals (F0 fibrosis stage) and 112 CLD patients (46 with mild fibrosis (F1), 16 with significant fibrosis (F2), 22 with severe fibrosis (F3), and 28 with cirrhosis (F4)) were analyzed to detect temporal stiffness stability between frames. An inverse Red, Green, Blue (RGB) colormap-to-stiffness process was performed for each image sequence, followed by a wavelet transform and fuzzy c-means clustering algorithm. This resulted in a binary mask depicting areas of high and low stiffness temporal stability. The mask was then applied to the first image of the SWE sequence, and the derived, masked SWE image was used to estimate its impact in standard clinical examination and CNN classification. Regarding the impact of the masked SWE image in clinical examination, one measurement by two radiologists was performed in each SWE image and two in the corresponding masked image measuring areas with high and low stiffness temporal stability. Then, stiffness stability parameters, interobserver variability evaluation and diagnostic performance by means of ROC analysis were assessed. The masked and unmasked sets of SWE images were fed into a CNN scheme for comparison. RESULTS: The clinical impact evaluation study showed that the masked SWE images decreased the interobserver variability of the radiologists' measurements in the high stiffness temporal stability areas (interclass correlation coefficient (ICC) = 0.92) compared to the corresponding unmasked ones (ICC = 0.76). In terms of diagnostic accuracy, measurements in the high-stability areas of the masked SWE images (area-under-the-curve (AUC) ranging from 0.800 to 0.851) performed similarly to those in the unmasked SWE images (AUC ranging from 0.805 to 0.893). Regarding the measurements in the low stiffness temporal stability areas of the masked SWE images, results for interobserver variability (ICC = 0.63) and diagnostic accuracy (AUC ranging from 0.622 to 0.791) were poor. Regarding the CNN classification, the masked SWE images showed improved accuracy (ranging from 82.5% to 95.5%) compared to the unmasked ones (ranging from 79.5% to 93.2%) for various CLD stage combinations. CONCLUSION: Our detection algorithm excludes unreliable areas in SWE images, reduces interobserver variability, and augments CNN's accuracy scores for many combinations of fibrosis stages.