scholarly journals Analytical performance of aPROMISE: automated anatomic contextualization, detection, and quantification of [18F]DCFPyL (PSMA) imaging for standardized reporting

2021 ◽  
Author(s):  
Kerstin Johnsson ◽  
Johan Brynolfsson ◽  
Hannicka Sahlstedt ◽  
Nicholas G. Nickols ◽  
Matthew Rettig ◽  
...  
Keyword(s):  
Deep Learning ◽  
Lymph Nodes ◽  
Low Dose ◽  
Learning Algorithm ◽  
Blood Pool ◽  
Ct Scans ◽  
Deep Learning Algorithm ◽  
Psma Pet ◽  
Pet Ct ◽  
Standardized Reporting

Abstract Purpose The application of automated image analyses could improve and facilitate standardization and consistency of quantification in [18F]DCFPyL (PSMA) PET/CT scans. In the current study, we analytically validated aPROMISE, a software as a medical device that segments organs in low-dose CT images with deep learning, and subsequently detects and quantifies potential pathological lesions in PSMA PET/CT. Methods To evaluate the deep learning algorithm, the automated segmentations of the low-dose CT component of PSMA PET/CT scans from 20 patients were compared to manual segmentations. Dice scores were used to quantify the similarities between the automated and manual segmentations. Next, the automated quantification of tracer uptake in the reference organs and detection and pre-segmentation of potential lesions were evaluated in 339 patients with prostate cancer, who were all enrolled in the phase II/III OSPREY study. Three nuclear medicine physicians performed the retrospective independent reads of OSPREY images with aPROMISE. Quantitative consistency was assessed by the pairwise Pearson correlations and standard deviation between the readers and aPROMISE. The sensitivity of detection and pre-segmentation of potential lesions was evaluated by determining the percent of manually selected abnormal lesions that were automatically detected by aPROMISE. Results The Dice scores for bone segmentations ranged from 0.88 to 0.95. The Dice scores of the PSMA PET/CT reference organs, thoracic aorta and liver, were 0.89 and 0.97, respectively. Dice scores of other visceral organs, including prostate, were observed to be above 0.79. The Pearson correlation for blood pool reference was higher between any manual reader and aPROMISE, than between any pair of manual readers. The standard deviations of reference organ uptake across all patients as determined by aPROMISE (SD = 0.21 blood pool and SD = 1.16 liver) were lower compared to those of the manual readers. Finally, the sensitivity of aPROMISE detection and pre-segmentation was 91.5% for regional lymph nodes, 90.6% for all lymph nodes, and 86.7% for bone in metastatic patients. Conclusion In this analytical study, we demonstrated the segmentation accuracy of the deep learning algorithm, the consistency in quantitative assessment across multiple readers, and the high sensitivity in detecting potential lesions. The study provides a foundational framework for clinical evaluation of aPROMISE in standardized reporting of PSMA PET/CT.

scholarly journals Deep Learning Based Automated Orthotopic Lung Tumor Segmentation in Whole-Body Mouse CT-Scans

Cancers ◽  
2021 ◽  
Vol 13 (18) ◽  
pp. 4585
Author(s):  
Wouter R. P. H. van de Worp ◽  
Brent van der Heyden ◽  
Georgios Lappas ◽  
Ardy van Helvoort ◽  
Jan Theys ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Tumor Growth ◽  
Tumor Volume ◽  
Learning Algorithm ◽  
Lung Tumor ◽  
Whole Body ◽  
Ct Scans ◽  
Therapeutic Effects ◽  
Deep Learning Algorithm

Lung cancer is the leading cause of cancer related deaths worldwide. The development of orthotopic mouse models of lung cancer, which recapitulates the disease more realistically compared to the widely used subcutaneous tumor models, is expected to critically aid the development of novel therapies to battle lung cancer or related comorbidities such as cachexia. However, follow-up of tumor take, tumor growth and detection of therapeutic effects is difficult, time consuming and requires a vast number of animals in orthotopic models. Here, we describe a solution for the fully automatic segmentation and quantification of orthotopic lung tumor volume and mass in whole-body mouse computed tomography (CT) scans. The goal is to drastically enhance the efficiency of the research process by replacing time-consuming manual procedures with fast, automated ones. A deep learning algorithm was trained on 60 unique manually delineated lung tumors and evaluated by four-fold cross validation. Quantitative performance metrics demonstrated high accuracy and robustness of the deep learning algorithm for automated tumor volume analyses (mean dice similarity coefficient of 0.80), and superior processing time (69 times faster) compared to manual segmentation. Moreover, manual delineations of the tumor volume by three independent annotators was sensitive to bias in human interpretation while the algorithm was less vulnerable to bias. In addition, we showed that besides longitudinal quantification of tumor development, the deep learning algorithm can also be used in parallel with the previously published method for muscle mass quantification and to optimize the experimental design reducing the number of animals needed in preclinical studies. In conclusion, we implemented a method for fast and highly accurate tumor quantification with minimal operator involvement in data analysis. This deep learning algorithm provides a helpful tool for the noninvasive detection and analysis of tumor take, tumor growth and therapeutic effects in mouse orthotopic lung cancer models.

scholarly journals Multi-Institutional Validation of Deep Learning for Pretreatment Identification of Extranodal Extension in Head and Neck Squamous Cell Carcinoma

2020 ◽  
Vol 38 (12) ◽  
pp. 1304-1311 ◽  
Author(s):  
Benjamin H. Kann ◽  
Daniel F. Hicks ◽  
Sam Payabvash ◽  
Amit Mahajan ◽  
Justin Du ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Deep Learning ◽  
Lymph Nodes ◽  
Head And Neck ◽  
Learning Algorithm ◽  
Data Sets ◽  
Diagnostic Ability ◽  
Algorithm Performance ◽  
Extranodal Extension ◽  
Deep Learning Algorithm

PURPOSE Extranodal extension (ENE) is a well-established poor prognosticator and an indication for adjuvant treatment escalation in patients with head and neck squamous cell carcinoma (HNSCC). Identification of ENE on pretreatment imaging represents a diagnostic challenge that limits its clinical utility. We previously developed a deep learning algorithm that identifies ENE on pretreatment computed tomography (CT) imaging in patients with HNSCC. We sought to validate our algorithm performance for patients from a diverse set of institutions and compare its diagnostic ability to that of expert diagnosticians. METHODS We obtained preoperative, contrast-enhanced CT scans and corresponding pathology results from two external data sets of patients with HNSCC: an external institution and The Cancer Genome Atlas (TCGA) HNSCC imaging data. Lymph nodes were segmented and annotated as ENE-positive or ENE-negative on the basis of pathologic confirmation. Deep learning algorithm performance was evaluated and compared directly to two board-certified neuroradiologists. RESULTS A total of 200 lymph nodes were examined in the external validation data sets. For lymph nodes from the external institution, the algorithm achieved an area under the receiver operating characteristic curve (AUC) of 0.84 (83.1% accuracy), outperforming radiologists’ AUCs of 0.70 and 0.71 ( P = .02 and P = .01). Similarly, for lymph nodes from the TCGA, the algorithm achieved an AUC of 0.90 (88.6% accuracy), outperforming radiologist AUCs of 0.60 and 0.82 ( P < .0001 and P = .16). Radiologist diagnostic accuracy improved when receiving deep learning assistance. CONCLUSION Deep learning successfully identified ENE on pretreatment imaging across multiple institutions, exceeding the diagnostic ability of radiologists with specialized head and neck experience. Our findings suggest that deep learning has utility in the identification of ENE in patients with HNSCC and has the potential to be integrated into clinical decision making.

scholarly journals Highly Robust Prediction of Lung Nodule Malignancy by Deep Learning Model: A Multiracial, Multinational Study

2020 ◽  
Author(s):  
Hao Wu ◽  
Wen Tang ◽  
Chu Wu ◽  
Yufeng Deng ◽  
Rongguo Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Clinical Features ◽  
Learning Algorithm ◽  
Lung Nodule ◽  
Ct Scans ◽  
Multivariate Logistic Regression Model ◽  
Lung Nodules ◽  
Deep Learning Algorithm

AbstractPurposeAlthough statistical models have been employed to detect and classify lung nodules using deep learning-extracted and clinical features, there is a lack of model validation in independent, multinational datasets from computed tomography (CT) scans and patient clinical information. To this end, we developed a deep learning-based algorithm to predict the malignancy of pulmonary nodules and validated its performance in three independent datasets containing multiracial and multinational populations.MethodsIn this study, a convolutional neural network-based algorithm to predict lung nodule malignancy was built based on CT scans and patient-wise clinical features (i.e. sex, spiculation, and nodule location). The model consists of three steps: (1) a deep learning algorithm to automatically extract features from CT scans, (2) clinical features were concatenated with the nodule features after dimension reduction by the principal component analysis (PCA), and (3) a multivariate logistic regression model was employed to classify the malignancy of the lung nodules. The model was trained by a dataset containing 1,556 nodules from 813 patients from the National Lung Screening Trial (NLST). The performance of the model was evaluated on three independent, multi-institutional datasets LIDC and Infervision Multi-Center (IMC) dataset, which contains 562 nodules from 293 patients, and 2044 nodules from 589 patients, respectively. The model accuracy was measured by the area under curve (AUC) of receiver operating characteristic (ROC) analysis.ResultsThe study shows that the AUCs of ROCs on the NLST dataset, LIDC dataset, and IMC dataset are 0.91, 0.86, and 0.95, respectively. The inclusion of clinical features does not significantly improve the model performance. Quantitatively, the summed-up weight on the prediction accuracy of the 10 nodule features extracted by the deep learning algorithm equals to 0.091, while the weight of patient sex, nodule spiculation, and location is 0.031, 0.052, and 0.008, respectively.ConclusionThe convolutional neural network-based model for lung nodule classification could be generalized to multiple datasets containing diverse populations. The addition of three patient clinical features to the nodule features extracted by deep learning does not boost the performance of the model.

scholarly journals Day-to-day variability of [68Ga]Ga-PSMA-11 accumulation in primary prostate cancer: effects on tracer uptake and visual interpretation

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Judith olde Heuvel ◽  
Berlinda J. de Wit-van der Veen ◽  
Maarten L. Donswijk ◽  
Cornelis H. Slump ◽  
Marcel P. M. Stokkel
Keyword(s):  
Prostate Cancer ◽  
Blood Pool ◽  
Prostate Tumor ◽  
Ct Scans ◽  
Response Monitoring ◽  
Clinical Indication ◽  
Repeatability Coefficient ◽  
Normal Tissues ◽  
Psma Pet ◽  
Pet Ct

Abstract Purpose Prostate-specific membrane antigen (PSMA) agents, such as [68Ga]Ga-PSMA-11, have an unprecedented accuracy in staging prostate cancer (PCa) and detecting disease recurrence. PSMA PET/CT may also be used for response monitoring by displaying molecular changes, instead of morphological changes alone. However, there are still limited data available on the variability in biodistribution and intra-prostatic uptake of PSMA targeting radiotracers. Therefore, the aim of this study was to assess the repeatability of [68Ga]Ga-PSMA-11 uptake in primary PCa patients in a 4-week interval. Methods Twenty-four primary PCa patients were prospectively included, who already were scheduled for [68Ga]Ga-PSMA-11 PET/CT scan on clinical indication (≥ cT3, Gleason score ≥ 7 or PSA ≥ 20 ng/mL). These patients received two [68Ga]Ga-PSMA-11 PET/CT scans with a 4-week interval. No treatment was started in between the scans. Semiquantitative measurements (SULmax, SULmean, and SULpeak) were determined in the prostate tumor, normal tissues, and blood pool. The repeatability coefficient of every region was determined. All scans were visually analyzed by two nuclear medicine physicians. Results Within-subject coefficient of variation of [68Ga]Ga-PSMA-11 uptake between the two scans was on average 10% in the prostate tumor, normal tissues (liver, kidney, parotid), and blood pool. The repeatability coefficient of the prostate tumor was 18% for SULpeak and 22% for SULmax. Lesion uptake was visually different in 5 patients, though not clinically relevant. Conclusion Results of test-retest [68Ga]Ga-PSMA-11 PET/CT scans in a 4-week interval show that [68Ga]Ga-PSMA-11 uptake is repeatable, with a clinical irrelevant variation in tumor and physiological distribution. Based on the presented repeatable uptake, [68Ga]Ga-PSMA-11 PET/CT scans can potentially be used for disease surveillance and therapy response monitoring. Changes in uptake larger than the RC are therefore likely to reflect actual biological changes in PSMA expression. Trial registration NL8263 at Trialregister.nl retrospectively registered on 03-01-2020. https://www.trialregister.nl/trial/8263

scholarly journals A deep learning algorithm to detect coronavirus (COVID-19) disease using CT images

2021 ◽  
Vol 7 ◽  
pp. e345
Author(s):  
Mojtaba Mohammadpoor ◽  
Mehran Sheikhi karizaki ◽  
Mina Sheikhi karizaki
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Screening Method ◽  
Ct Scans ◽  
X Rays ◽  
Deep Learning Algorithm ◽  
Fast Screening ◽  
Proposed Model ◽  
Deep Learning Neural Network ◽  
Lung Ct

Background COVID-19 pandemic imposed a lockdown situation to the world these past months. Researchers and scientists around the globe faced serious efforts from its detection to its treatment. Methods Pathogenic laboratory testing is the gold standard but it is time-consuming. Lung CT-scans and X-rays are other common methods applied by researchers to detect COVID-19 positive cases. In this paper, we propose a deep learning neural network-based model as an alternative fast screening method that can be used for detecting the COVID-19 cases by analyzing CT-scans. Results Applying the proposed method on a publicly available dataset collected of positive and negative cases showed its ability on distinguishing them by analyzing each individual CT image. The effect of different parameters on the performance of the proposed model was studied and tabulated. By selecting random train and test images, the overall accuracy and ROC-AUC of the proposed model can easily exceed 95% and 90%, respectively, without any image pre-selecting or preprocessing.

scholarly journals Challenge for Diagnostic Assessment of Deep Learning Algorithm for Metastases Classification in Sentinel Lymph Nodes on Frozen Tissue Section Digital Slides in Women with Breast Cancer

2020 ◽  
Author(s):  
Young-Gon Kim ◽  
In Hye Song ◽  
Hyunna Lee ◽  
Dong Hyun Yang ◽  
Namkug Kim ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Lymph Nodes ◽  
Tissue Section ◽  
Learning Algorithm ◽  
Sentinel Lymph Nodes ◽  
Diagnostic Assessment ◽  
Deep Learning Algorithm ◽  
Frozen Tissue

Abstract The authors have withdrawn this preprint due to author disagreement.

Sign in / Sign up

Export Citation Format

Share Document