Prediction uncertainty estimates elucidate the limitation of current NSCLC subtype classification in representing mutational heterogeneity

The heterogeneous pathogenesis and treatment response of non-small cell lung cancer (NSCLC) has led clinical treatment decisions to be guided by NSCLC subtypes, with lung adenocarcinoma and lung squamous cell carcinoma being the most common subtypes. While histology-based subtyping remains challenging, NSCLC subtypes were found to be distinct at the transcriptomic level. However, unlike genomic alterations, gene expression is generally not assessed in clinical routine. Since subtyping of NSCLC has remained elusive using mutational data, we aimed at developing a neural network model that simultaneously learns from adenocarcinoma and squamous cell carcinoma samples of other tissue types and is regularized using a neural network model trained from gene expression data. While substructures of the expression-based manifold were captured in the mutation-based manifold, NSCLC classification accuracy did not significantly improve. However, performance was increased when rejecting inconclusive samples using an ensemble-based approach capturing prediction uncertainty. Importantly, SHAP analysis of misclassified samples identified co-occurring mutations indicative of both NSCLC subtypes, questioning the current NSCLC subtype classification to adequately represent inherent mutational heterogeneity. Since our model captures mutational patterns linked to clinical heterogeneity, we anticipate it to be suited as foundational model of genomic data for clinically relevant prognostic or predictive downstream tasks.

Concordance and generalization of an AI algorithm with real-world clinical data in the pre-omicron and omicron era

All viruses, including SARS-CoV-2, the virus responsible for COVID-19, continue to evolve, which can lead to new variants. The objective of this study is to assess the agreement between real-world clinical data and an algorithm that utilizes laboratory markers and age to predict the progression of disease severity in COVID-19 patients during the pre-Omicron and Omicron variant periods. The study evaluated the performance of a deep learning (DL) algorithm in predicting disease severity scores for COVID-19 patients using data from the USA, Spain, and Turkey (Ankara City Hospital (ACH) data set). The algorithm was developed and validated using pre-Omicron era data and was tested on both pre-Omicron and Omicron-era data. The predictions were compared to the actual clinical outcomes using a multidisciplinary approach. The concordance index values for all datasets ranged from 0.71 to 0.81. In the ACH cohort, a negative predictive value (NPV) of 0.78 or higher was observed for severe patients in both the pre-Omicron and Omicron eras, which is consistent with the algorithm's performance in the development cohort.

Comparison of a Deep Learning-Accelerated vs. Conventional T2-Weighted Sequence in Biparametric MRI of the Prostate

BACKGROUND

Demand for prostate MRI is increasing, but scan times remain long even in abbreviated biparametric MRIs (bpMRI). Deep learning can be leveraged to accelerate T2-weighted imaging (T2WI).

PURPOSE

To compare conventional bpMRIs (CL-bpMRI) with bpMRIs including a deep learning-accelerated T2WI (DL-bpMRI) in diagnosing prostate cancer.

STUDY TYPE

Retrospective.

POPULATION

Eighty consecutive men, mean age 66 years (47-84) with suspected prostate cancer or prostate cancer on active surveillance who had a prostate MRI from December 28, 2020 to April 28, 2021 were included. Follow-up included prostate biopsy or stability of prostate-specific antigen (PSA) for 1 year.

FIELD STRENGTH AND SEQUENCES

A 3 T MRI. Conventional axial and coronal T2 turbo spin echo (CL-T2), 3-fold deep learning-accelerated axial and coronal T2-weighted sequence (DL-T2), diffusion weighted imaging (DWI) with b = 50 sec/mm2 , 1000 sec/mm2 , calculated b = 1500 sec/mm2 .

ASSESSMENT

CL-bpMRI and DL-bpMRI including the same conventional diffusion-weighted imaging (DWI) were presented to three radiologists (blinded to acquisition method) and to a deep learning computer-assisted detection algorithm (DL-CAD). The readers evaluated image quality using a 4-point Likert scale (1 = nondiagnostic, 4 = excellent) and graded lesions using Prostate Imaging Reporting and Data System (PI-RADS) v2.1. DL-CAD identified and assigned lesions of PI-RADS 3 or greater.

STATISTICAL TESTS

Quality metrics were compared using Wilcoxon signed rank test, and area under the receiver operating characteristic curve (AUC) were compared using Delong's test.

SIGNIFICANCE

P = 0.05.

RESULTS

Eighty men were included (age: 66 ± 9 years; 17/80 clinically significant prostate cancer). Overall image quality results by the three readers (CL-T2, DL-T2) are reader 1: 3.72 ± 0.53, 3.89 ± 0.39 (P = 0.99); reader 2: 3.33 ± 0.82, 3.31 ± 0.74 (P = 0.49); reader 3: 3.67 ± 0.63, 3.51 ± 0.62. In the patient-based analysis, the reader results of AUC are (CL-bpMRI, DL-bpMRI): reader 1: 0.77, 0.78 (P = 0.98), reader 2: 0.65, 0.66 (P = 0.99), reader 3: 0.57, 0.60 (P = 0.52). Diagnostic statistics from DL-CAD (CL-bpMRI, DL-bpMRI) are sensitivity (0.71, 0.71, P = 1.00), specificity (0.59, 0.44, P = 0.05), positive predictive value (0.23, 0.24, P = 0.25), negative predictive value (0.88, 0.88, P = 0.48).

CONCLUSION

Deep learning-accelerated T2-weighted imaging may potentially be used to decrease acquisition time for bpMRI.

EVIDENCE LEVEL

3.

TECHNICAL EFFICACY

Stage 2.

Automated deep-learning system in the assessment of MRI-visible prostate cancer: comparison of advanced zoomed diffusion-weighted imaging and conventional technique

BACKGROUND

Deep-learning-based computer-aided diagnosis (DL-CAD) systems using MRI for prostate cancer (PCa) detection have demonstrated good performance. Nevertheless, DL-CAD systems are vulnerable to high heterogeneities in DWI, which can interfere with DL-CAD assessments and impair performance. This study aims to compare PCa detection of DL-CAD between zoomed-field-of-view echo-planar DWI (z-DWI) and full-field-of-view DWI (f-DWI) and find the risk factors affecting DL-CAD diagnostic efficiency.

METHODS

This retrospective study enrolled 354 consecutive participants who underwent MRI including T2WI, f-DWI, and z-DWI because of clinically suspected PCa. A DL-CAD was used to compare the performance of f-DWI and z-DWI both on a patient level and lesion level. We used the area under the curve (AUC) of receiver operating characteristics analysis and alternative free-response receiver operating characteristics analysis to compare the performances of DL-CAD using f- DWI and z-DWI. The risk factors affecting the DL-CAD were analyzed using logistic regression analyses. P values less than 0.05 were considered statistically significant.

RESULTS

DL-CAD with z-DWI had a significantly better overall accuracy than that with f-DWI both on patient level and lesion level (AUC_patient: 0.89 vs. 0.86; AUC_lesion: 0.86 vs. 0.76; P < .001). The contrast-to-noise ratio (CNR) of lesions in DWI was an independent risk factor of false positives (odds ratio [OR] = 1.12; P < .001). Rectal susceptibility artifacts, lesion diameter, and apparent diffusion coefficients (ADC) were independent risk factors of both false positives (OR_{rectal susceptibility artifact} = 5.46; OR_diameter, = 1.12; OR_ADC = 0.998; all P < .001) and false negatives (OR_{rectal susceptibility artifact} = 3.31; OR_diameter = 0.82; OR_ADC = 1.007; all P ≤ .03) of DL-CAD.

CONCLUSIONS

Z-DWI has potential to improve the detection performance of a prostate MRI based DL-CAD.

TRIAL REGISTRATION

ChiCTR, NO. ChiCTR2100041834 . Registered 7 January 2021.

Prostate gland volume estimation: anteroposterior diameters measured on axial versus sagittal ultrasonography and magnetic resonance images

PURPOSE

The aim of this study was to evaluate the accuracy of prostate volume estimates calculated from the ellipsoid formula using the anteroposterior (AP) diameter measured on axial and sagittal images obtained through ultrasonography (US) and magnetic resonance imaging (MRI).

METHODS

This retrospective study included 456 patients with transrectal US and MRI from two university hospitals. Two radiologists independently measured the prostate gland diameters on US and MRI: AP diameters on axial and sagittal images, transverse, and longitudinal diameters on midsagittal images. The volume estimates, volumeax and volumesag, were calculated from the ellipsoid formula by using the AP diameter on axial and sagittal images, respectively. The prostate volume extracted from MRI-based whole-gland segmentation was considered the gold standard. The intraclass correlation coefficient (ICC) was used to evaluate the inter-method agreement between volumeax and volumesag, and agreement with the gold standard. The Wilcoxon signedrank test was used to analyze the differences between the volume estimates and the gold standard.

RESULTS

The prostate gland volume estimates showed excellent inter-method agreement, and excellent agreement with the gold standard (ICCs >0.9). Compared with the gold standard, the volume estimates were significantly larger on MRI and significantly smaller on US (P<0.001). The volume difference (segmented volume-volume estimate) was greater in patients with larger prostate glands, especially on US.

CONCLUSION

Volumeax and volumesag showed excellent inter-method agreement and excellent agreement with the gold standard on both US and MRI. However, prostate volume was overestimated on MRI and underestimated on US.

Image-Based Deep Neural Network for Individualizing Radiotherapy Dose Is Transportable Across Health Systems

PURPOSE

We developed a deep neural network that queries the lung computed tomography-derived feature space to identify radiation sensitivity parameters that can predict treatment failures and hence guide the individualization of radiotherapy dose. In this article, we examine the transportability of this model across health systems.

METHODS

This multicenter cohort-based registry included 1,120 patients with cancer in the lung treated with stereotactic body radiotherapy. Pretherapy lung computed tomography images from the internal study cohort (n = 849) were input into a multitask deep neural network to generate an image fingerprint score that predicts time to local failure. Deep learning (DL) scores were input into a regression model to derive iGray, an individualized radiation dose estimate that projects a treatment failure probability of < 5% at 24 months. We validated our findings in an external, holdout cohort (n = 271).

RESULTS

There were substantive differences in the baseline patient characteristics of the two study populations, permitting an assessment of model transportability. In the external cohort, radiation treatments in patients with high DL scores failed at a significantly higher rate with 3-year cumulative incidences of local failure of 28.5% (95% CI, 19.8 to 37.8) versus 10.2% (95% CI, 5.9 to 16.2; hazard ratio, 3.3 [95% CI, 1.74 to 6.49]; P < .001). A model that included DL score alone predicted treatment failures with a concordance index of 0.68 (95% CI, 0.59 to 0.77), which had a similar performance to a nested model derived from within the internal cohort (0.70 [0.64 to 0.75]). External cohort patients with iGray values that exceeded the delivered doses had proportionately higher rates of local failure (P < .001).

CONCLUSION

Our results support the development and implementation of new DL-guided treatment guidance tools in the image-replete and highly standardized discipline of radiation oncology.

Deterministic small-scale undulations of image-based risk predictions from the deep learning of lung tumors in motion

INTRODUCTION

Deep learning (DL) models that use medical images to predict clinical outcomes are poised for clinical translation. For tumors that reside in organs that move, however, the impact of motion (i.e., degenerated object appearance or blur) on DL model accuracy remains unclear. We examine the impact of tumor motion on an image-based DL framework that predicts local failure risk after lung stereotactic body radiotherapy (SBRT).

METHODS

We input pre-therapy free breathing (FB) computed tomography (CT) images from 849 patients treated with lung SBRT into a multitask deep neural network to generate an image fingerprint signature (or DL score) that predicts time-to-event local failure outcomes. The network includes a convolutional neural network encoder for extracting imaging features and building a task-specific fingerprint, a decoder for estimating handcrafted radiomic features, and a task-specific network for generating image signature for radiotherapy outcome prediction. The impact of tumor motion on the DL scores was then examined for a holdout set of 468 images from 39 patients comprising: (1) FB CT, (2) four-dimensional (4D) CT, and (3) maximum-intensity projection (MIP) images. Tumor motion was estimated using a 3D vector of the maximum distance traveled, and its association with DL score variance was assessed by linear regression.

FINDINGS

The variance and amplitude in 4D CT image-derived DL scores were associated with tumor motion (R²  = 0.48 and 0.46, respectively). Specifically, DL score variance was deterministic and represented by sinusoidal undulations in phase with the respiratory cycle. DL scores, but not tumor volumes, peaked near end-exhalation. The mean of the scores derived from 4D CT images and the score obtained from FB CT images were highly associated (Pearson r = 0.99). MIP-derived DL scores were significantly higher than 4D- or FB-derived risk scores (p < 0.0001).

INTERPRETATION

An image-based DL risk score derived from a series of 4D CT images varies in a deterministic, sinusoidal trajectory in a phase with the respiratory cycle. These results indicate that DL models of tumors in motion can be robust to fluctuations in object appearance due to movement and can guide standardization processes in the clinical translation of DL models for patients with lung cancer.

Multimodal image synthesis based on disentanglement representations of anatomical and modality specific features, learned using uncooperative relativistic GAN

Growing number of methods for attenuation-coefficient map estimation from magnetic resonance (MR) images have recently been proposed because of the increasing interest in MR-guided radiotherapy and the introduction of positron emission tomography (PET) MR hybrid systems. We propose a deep-network ensemble incorporating stochastic-binary-anatomical encoders and imaging-modality variational autoencoders, to disentangle image-latent spaces into a space of modality-invariant anatomical features and spaces of modality attributes. The ensemble integrates modality-modulated decoders to normalize features and image intensities based on imaging modality. Besides promoting disentanglement, the architecture fosters uncooperative learning, offering ability to maintain anatomical structure in a cross-modality reconstruction. Introduction of a modality-invariant structural consistency constraint further enforces faithful embedding of anatomy. To improve training stability and fidelity of synthesized modalities, the ensemble is trained in a relativistic generative adversarial framework incorporating multiscale discriminators. Analyses of priors and network architectures as well as performance validation were performed on computed tomography (CT) and MR pelvis datasets. The proposed method demonstrated robustness against intensity inhomogeneity, improved tissue-class differentiation, and offered synthetic CT in Hounsfield units with intensities consistent and smooth across slices compared to the state-of-the-art approaches, offering median normalized mutual information of 1.28, normalized cross correlation of 0.97, and gradient cross correlation of 0.59 over 324 images.

A concurrent, deep learning-based computer-aided detection system for prostate multiparametric MRI: a performance study involving experienced and less-experienced radiologists

OBJECTIVES

To evaluate the effect of a deep learning-based computer-aided diagnosis (DL-CAD) system on experienced and less-experienced radiologists in reading prostate mpMRI.

METHODS

In this retrospective, multi-reader multi-case study, a consecutive set of 184 patients examined between 01/2018 and 08/2019 were enrolled. Ground truth was combined targeted and 12-core systematic transrectal ultrasound-guided biopsy. Four radiologists, two experienced and two less-experienced, evaluated each case twice, once without (DL-CAD-) and once assisted by DL-CAD (DL-CAD+). ROC analysis, sensitivities, specificities, PPV and NPV were calculated to compare the diagnostic accuracy for the diagnosis of prostate cancer (PCa) between the two groups (DL-CAD- vs. DL-CAD+). Spearman's correlation coefficients were evaluated to assess the relationship between PI-RADS category and Gleason score (GS). Also, the median reading times were compared for the two reading groups.

RESULTS

In total, 172 patients were included in the final analysis. With DL-CAD assistance, the overall AUC of the less-experienced radiologists increased significantly from 0.66 to 0.80 (p = 0.001; cutoff ISUP GG ≥ 1) and from 0.68 to 0.80 (p = 0.002; cutoff ISUP GG ≥ 2). Experienced radiologists showed an AUC increase from 0.81 to 0.86 (p = 0.146; cutoff ISUP GG ≥ 1) and from 0.81 to 0.84 (p = 0.433; cutoff ISUP GG ≥ 2). Furthermore, the correlation between PI-RADS category and GS improved significantly in the DL-CAD + group (0.45 vs. 0.57; p = 0.03), while the median reading time was reduced from 157 to 150 s (p = 0.023).

CONCLUSIONS

DL-CAD assistance increased the mean detection performance, with the most significant benefit for the less-experienced radiologist; with the help of DL-CAD less-experienced radiologists reached performances comparable to that of experienced radiologists.

KEY POINTS

• DL-CAD used as a concurrent reading aid helps radiologists to distinguish between benign and cancerous lesions in prostate MRI. • With the help of DL-CAD, less-experienced radiologists may achieve detection performances comparable to that of experienced radiologists. • DL-CAD assistance increases the correlation between PI-RADS category and cancer grade.

A deep learning approach for predicting severity of COVID-19 patients using a parsimonious set of laboratory markers

The SARS-CoV-2 virus has caused tremendous healthcare burden worldwide. Our focus was to develop a practical and easy-to-deploy system to predict the severe manifestation of disease in patients with COVID-19 with an aim to assist clinicians in triage and treatment decisions. Our proposed predictive algorithm is a trained artificial intelligence-based network using 8,427 COVID-19 patient records from four healthcare systems. The model provides a severity risk score along with likelihoods of various clinical outcomes, namely ventilator use and mortality. The trained model using patient age and nine laboratory markers has the prediction accuracy with an area under the curve (AUC) of 0.78, 95% CI: 0.77–0.82, and the negative predictive value NPV of 0.86, 95% CI: 0.84–0.88 for the need to use a ventilator and has an accuracy with AUC of 0.85, 95% CI: 0.84–0.86, and the NPV of 0.94, 95% CI: 0.92–0.96 for predicting in-hospital 30-day mortality.

•

Algorithm using 9 laboratory markers & age may predict severity in patients with COVID-19

•

Model was trained and tested on a multicenter sample of 10,937 patients

•

Algorithm can predict ventilator use (NPV, 0.86) and mortality (NPV, 0.94)

•

High NPV suggests utility as an adjunct to aid in triaging of patients with COVID-19

A Novel Deep Learning Based Computer-Aided Diagnosis System Improves the Accuracy and Efficiency of Radiologists in Reading Biparametric Magnetic Resonance Images of the Prostate: Results of a Multireader, Multicase Study

OBJECTIVE

The aim of this study was to evaluate the effect of a deep learning based computer-aided diagnosis (DL-CAD) system on radiologists' interpretation accuracy and efficiency in reading biparametric prostate magnetic resonance imaging scans.

MATERIALS AND METHODS

We selected 100 consecutive prostate magnetic resonance imaging cases from a publicly available data set (PROSTATEx Challenge) with and without histopathologically confirmed prostate cancer. Seven board-certified radiologists were tasked to read each case twice in 2 reading blocks (with and without the assistance of a DL-CAD), with a separation between the 2 reading sessions of at least 2 weeks. Reading tasks were to localize and classify lesions according to Prostate Imaging Reporting and Data System (PI-RADS) v2.0 and to assign a radiologist's level of suspicion score (scale from 1-5 in 0.5 increments; 1, benign; 5, malignant). Ground truth was established by consensus readings of 3 experienced radiologists. The detection performance (receiver operating characteristic curves), variability (Fleiss κ), and average reading time without DL-CAD assistance were evaluated.

RESULTS

The average accuracy of radiologists in terms of area under the curve in detecting clinically significant cases (PI-RADS ≥4) was 0.84 (95% confidence interval [CI], 0.79-0.89), whereas the same using DL-CAD was 0.88 (95% CI, 0.83-0.94) with an improvement of 4.4% (95% CI, 1.1%-7.7%; P = 0.010). Interreader concordance (in terms of Fleiss κ) increased from 0.22 to 0.36 (P = 0.003). Accuracy of radiologists in detecting cases with PI-RADS ≥3 was improved by 2.9% (P = 0.10). The median reading time in the unaided/aided scenario was reduced by 21% from 103 to 81 seconds (P < 0.001).

CONCLUSIONS

Using a DL-CAD system increased the diagnostic accuracy in detecting highly suspicious prostate lesions and reduced both the interreader variability and the reading time.

Detection and PI-RADS classification of focal lesions in prostate MRI: Performance comparison between a deep learning-based algorithm (DLA) and radiologists with various levels of experience

PURPOSE

To compare the performance of lesion detection and Prostate Imaging-Reporting and Data System (PI-RADS) classification between a deep learning-based algorithm (DLA), clinical reports and radiologists with different levels of experience in prostate MRI.

METHODS

This retrospective study included 121 patients who underwent prebiopsy MRI and prostate biopsy. More than five radiologists (Reader groups 1, 2: residents; Readers 3, 4: less-experienced radiologists; Reader 5: expert) independently reviewed biparametric MRI (bpMRI). The DLA results were obtained using bpMRI. The reference standard was based on pathologic reports. The diagnostic performance of the PI-RADS classification of DLA, clinical reports, and radiologists was analyzed using AUROC. Dichotomous analysis (PI-RADS cutoff value ≥ 3 or 4) was performed, and the sensitivities and specificities were compared using McNemar's test.

RESULTS

Clinically significant cancer [CSC, Gleason score ≥ 7] was confirmed in 43 patients (35.5%). The AUROC of the DLA (0.828) for diagnosing CSC was significantly higher than that of Reader 1 (AUROC, 0.706; p = 0.011), significantly lower than that of Reader 5 (AUROC, 0.914; p = 0.013), and similar to clinical reports and other readers (p = 0.060-0.661). The sensitivity of DLA (76.7%) was comparable to those of all readers and the clinical reports at a PI-RADS cutoff value ≥ 4. The specificity of the DLA (85.9%) was significantly higher than those of clinical reports and Readers 2-3 and comparable to all others at a PI-RADS cutoff value ≥ 4.

CONCLUSIONS

The DLA showed moderate diagnostic performance at a level between those of residents and an expert in detecting and classifying according to PI-RADS. The performance of DLA was similar to that of clinical reports from various radiologists in clinical practice.

Evaluation of Deep Learning-based Approaches to Segment Bowel Air Pockets and Generate Pelvis Attenuation Maps from CAIPIRINHA-accelerated Dixon MR Images

Attenuation correction (AC) remains a challenge in pelvis PET/MR imaging. In addition to the segmentation/model-based approaches, deep learning methods have shown promise in synthesizing accurate pelvis attenuation maps (μ-maps). However, these methods often misclassify air pockets in the digestive tract, which can introduce bias in the reconstructed PET images. The aims of this work were to develop deep learning-based methods to automatically segment air pockets and generate pseudo-CT images from CAIPIRINHA-accelerated MR Dixon images. Methods: A convolutional neural network (CNN) was trained to segment air pockets using 3D CAIPIRINHA-accelerated MR Dixon datasets from 35 subjects and was evaluated against semi-automated segmentations. A separate CNN was trained to synthesize pseudo-CT μ-maps from the Dixon images. Its accuracy was evaluated by comparing the deep learning-, model- and CT-based μ-maps using data from 30 of the subjects. Finally, the impact of different μ-maps and air pocket segmentation methods on the PET quantification was investigated. Results: Air pockets segmented using the CNN agreed well with semi-automated segmentations, with a mean Dice similarity coefficient of 0.75. Volumetric similarity score between two segmentations was 0.85 ± 0.14. The mean absolute relative change (RCs) with respect to the CT-based μ-maps were 2.6% and 5.1% in the whole pelvis for the deep learning and model-based μ-maps, respectively. The average RC between PET images reconstructed with deep learning and CT-based μ-maps was 2.6%. Conclusion: We presented a deep learning-based method to automatically segment air pockets from CAIPIRINHA-accelerated Dixon images with comparable accuracy to semi-automatic segmentations. We also showed that the μ-maps synthesized using a deep learning-based method from CAIPIRINHA-accelerated Dixon images are more accurate than those generated with the model-based approach available on integrated PET/MRI scanner.

Autonomous Detection and Classification of PI-RADS Lesions in an MRI Screening Population Incorporating Multicenter-Labeled Deep Learning and Biparametric Imaging: Proof of Concept

Background: Opportunistic prostate cancer (PCa) screening is a controversial topic. Magnetic resonance imaging (MRI) has proven to detect prostate cancer with a high sensitivity and specificity, leading to the idea to perform an image-guided prostate cancer (PCa) screening; Methods: We evaluated a prospectively enrolled cohort of 49 healthy men participating in a dedicated image-guided PCa screening trial employing a biparametric MRI (bpMRI) protocol consisting of T2-weighted (T2w) and diffusion weighted imaging (DWI) sequences. Datasets were analyzed both by human readers and by a fully automated artificial intelligence (AI) software using deep learning (DL). Agreement between the algorithm and the reports—serving as the ground truth—was compared on a per-case and per-lesion level using metrics of diagnostic accuracy and k statistics; Results: The DL method yielded an 87% sensitivity (33/38) and 50% specificity (5/10) with a k of 0.42. 12/28 (43%) Prostate Imaging Reporting and Data System (PI-RADS) 3, 16/22 (73%) PI-RADS 4, and 5/5 (100%) PI-RADS 5 lesions were detected compared to the ground truth. Targeted biopsy revealed PCa in six participants, all correctly diagnosed by both the human readers and AI. Conclusions: The results of our study show that in our AI-assisted, image-guided prostate cancer screening the software solution was able to identify highly suspicious lesions and has the potential to effectively guide the targeted-biopsy workflow.

An image-based deep learning framework for individualizing radiotherapy dose

Background

Radiotherapy continues to be delivered uniformly without consideration of individual tumor characteristics. To advance toward more precise treatments in radiotherapy, we queried the lung computed tomography (CT)-derived feature space to identify radiation sensitivity parameters that can predict treatment failure and hence guide the individualization of radiotherapy dose.

Methods

We used a cohort-based registry of 849 patients with cancer in the lung treated with high dose radiotherapy using stereotactic body radiotherapy. We input pre-therapy lung CT images into a multi-task deep neural network, Deep Profiler, to generate an image fingerprint that primarily predicts time to event treatment outcomes and secondarily approximates classical radiomic features. We validated our findings in an independent study population (n = 95). Deep Profiler was combined with clinical variables to derive iGray, an individualized dose that estimates treatment failure probability to be <5%.

Findings

Radiation treatments in patients with high Deep Profiler scores fail at a significantly higher rate than in those with low scores. The 3-year cumulative incidences of local failure were 20.3% (95% CI: 16.0-24.9) and 5.7% (95% CI: 3.5-8.8), respectively. Deep Profiler independently predicted local failure (hazard ratio 1.65, 95% 1.02-2.66, p = 0.04). Models that included Deep Profiler and clinical variables predicted treatment failures with a concordance index of 0.72 (95% CI: 0.67-0.77), a significant improvement compared to classical radiomics or clinical variables alone (p = <0.001 and <0.001, respectively). Deep Profiler performed well in an external study population (n = 95), accurately predicting treatment failures across diverse clinical settings and CT scanner types (concordance index = 0.77 [95% CI: 0.69-0.92]). iGray had a wide dose range (21.1-277 Gy, BED), suggested dose reductions in 23.3% of patients and can be safely delivered in the majority of cases.

Interpretation

Our results indicate that there are image-distinct subpopulations that have differential sensitivity to radiotherapy. The image-based deep learning framework proposed herein is the first opportunity to use medical images to individualize radiotherapy dose.

Automatic Tissue Differentiation Based on Confocal Endomicroscopic Images for Intraoperative Guidance in Neurosurgery

Diagnosis of tumor and definition of tumor borders intraoperatively using fast histopathology is often not sufficiently informative primarily due to tissue architecture alteration during sample preparation step. Confocal laser microscopy (CLE) provides microscopic information of tissue in real-time on cellular and subcellular levels, where tissue characterization is possible. One major challenge is to categorize these images reliably during the surgery as quickly as possible. To address this, we propose an automated tissue differentiation algorithm based on the machine learning concept. During a training phase, a large number of image frames with known tissue types are analyzed and the most discriminant image-based signatures for various tissue types are identified. During the procedure, the algorithm uses the learnt image features to assign a proper tissue type to the acquired image frame. We have verified this method on the example of two types of brain tumors: glioblastoma and meningioma. The algorithm was trained using 117 image sequences containing over 27 thousand images captured from more than 20 patients. We achieved an average cross validation accuracy of better than 83%. We believe this algorithm could be a useful component to an intraoperative pathology system for guiding the resection procedure based on cellular level information.

Comparison of Fractional Flow Reserve Based on Computational Fluid Dynamics Modeling Using Coronary Angiographic Vessel Morphology Versus Invasively Measured Fractional Flow Reserve

Invasive fractional flow reserve (FFRinvasive), although gold standard to identify hemodynamically relevant coronary stenoses, is time consuming and potentially associated with complications. We developed and evaluated a new approach to determine lesion-specific FFR on the basis of coronary anatomy as visualized by invasive coronary angiography (FFRangio): 100 coronary lesions (50% to 90% diameter stenosis) in 73 patients (48 men, 25 women; mean age 67 ± 9 years) were studied. On the basis of coronary angiograms acquired at rest from 2 views at angulations at least 30° apart, a PC-based computational fluid dynamics modeling software used personalized boundary conditions determined from 3-dimensional reconstructed angiography, heart rate, and blood pressure to derive FFRangio. The results were compared with FFRinvasive. Interobserver variability was determined in a subset of 25 narrowings. Twenty-nine of 100 coronary lesions were hemodynamically significant (FFRinvasive ≤ 0.80). FFRangio identified these with an accuracy of 90%, sensitivity of 79%, specificity of 94%, positive predictive value of 85%, and negative predictive value of 92%. The area under the receiver operating characteristic curve was 0.93. Correlation between FFRinvasive (mean: 0.84 ± 0.11) and FFRangio (mean: 0.85 ± 0.12) was r = 0.85. Interobserver variability of FFRangio was low, with a correlation of r = 0.88. In conclusion, estimation of coronary FFR with PC-based computational fluid dynamics modeling on the basis of lesion morphology as determined by invasive angiography is possible with high diagnostic accuracy compared to invasive measurements.

Near-infrared fluorescent digital pathology for the automation of disease diagnosis and biomarker assessment

Hematoxylin-eosin (H&E) staining of tissue has been the mainstay of pathology for more than a century. However, the learning curve for H&E tissue interpretation is long, whereas intra- and interobserver variability remain high. Computer-assisted image analysis of H&E sections holds promise for increased throughput and decreased variability but has yet to demonstrate significant improvement in diagnostic accuracy. Addition of biomarkers to H&E staining can improve diagnostic accuracy; however, coregistration of immunohistochemical staining with H&E is problematic as immunostaining is completed on slides that are at best 4 μm apart. Simultaneous H&E and immunostaining would alleviate coregistration problems; however, current opaque pigments used for immunostaining obscure H&E. In this study, we demonstrate that diagnostic information provided by two or more independent wavelengths of near-infrared (NIR) fluorescence leave the H&E stain unchanged while enabling computer-assisted diagnosis and assessment of human disease. Using prostate cancer as a model system, we introduce NIR digital pathology and demonstrate its utility along the spectrum from prostate biopsy to whole mount analysis of H&E-stained tissue.

Model based non-invasive estimation of PV loop from echocardiography

We introduce a model-based approach for the non-invasive estimation of patient specific, left ventricular PV loops. A lumped parameter circulation model is used, composed of the pulmonary venous circulation, left atrium, left ventricle and the systemic circulation. A fully automated parameter estimation framework is introduced for model personalization, composed of two sequential steps: first, a series of parameters are computed directly, and, next, a fully automatic optimization-based calibration method is employed to iteratively estimate the values of the remaining parameters. The proposed methodology is first evaluated for three healthy volunteers: a perfect agreement is obtained between the computed quantities and the clinical measurements. Additionally, for an initial validation of the methodology, we computed the PV loop for a patient with mild aortic valve regurgitation and compared the results against the invasively determined quantities: there is a close agreement between the time-varying LV and aortic pressures, time-varying LV volumes, and PV loops.

Towards Personalized Cardiology: Multi-Scale Modeling of the Failing Heart

BACKGROUND

Despite modern pharmacotherapy and advanced implantable cardiac devices, overall prognosis and quality of life of HF patients remain poor. This is in part due to insufficient patient stratification and lack of individualized therapy planning, resulting in less effective treatments and a significant number of non-responders.

METHODS AND RESULTS

State-of-the-art clinical phenotyping was acquired, including magnetic resonance imaging (MRI) and biomarker assessment. An individualized, multi-scale model of heart function covering cardiac anatomy, electrophysiology, biomechanics and hemodynamics was estimated using a robust framework. The model was computed on n=46 HF patients, showing for the first time that advanced multi-scale models can be fitted consistently on large cohorts. Novel multi-scale parameters derived from the model of all cases were analyzed and compared against clinical parameters, cardiac imaging, lab tests and survival scores to evaluate the explicative power of the model and its potential for better patient stratification. Model validation was pursued by comparing clinical parameters that were not used in the fitting process against model parameters.

CONCLUSION

This paper illustrates how advanced multi-scale models can complement cardiovascular imaging and how they could be applied in patient care. Based on obtained results, it becomes conceivable that, after thorough validation, such heart failure models could be applied for patient management and therapy planning in the future, as we illustrate in one patient of our cohort who received CRT-D implantation.

A novel coupling algorithm for computing blood flow in viscoelastic arterial models

We propose a novel coupling algorithm, based on the operator-splitting scheme, which implements the viscoelastic wall law at the coupling nodes of the vessels. Two different viscoelastic models are used (V1 and V2), leading to five different computational setups: elastic wall law, model V1 applied at interior and coupling grid points, model V1 applied only at the interior grid points (V1-int), model V2 applied at interior and coupling grid points, model V2 applied only at the interior grid points (V2-int). These have been tested with two arterial configurations: (i) single artery, and (ii) complete arterial tree. Models V1-int and V2-int lead to incorrect conclusions and to errors which can be of the same order as, and are at least 1/5 of, the difference between the results with the elastic and the viscoelastic laws. Both test cases demonstrate the importance of modeling the viscous component of the pressure-area relationship at all grid points, including the coupling points between vessels or at the inlet/outlet of the model.

Efficient Lattice Boltzmann Solver for Patient-Specific Radiofrequency Ablation of Hepatic Tumors

Radiofrequency ablation (RFA) is an established treatment for liver cancer when resection is not possible. Yet, its optimal delivery is challenged by the presence of large blood vessels and the time-varying thermal conductivity of biological tissue. Incomplete treatment and an increased risk of recurrence are therefore common. A tool that would enable the accurate planning of RFA is hence necessary. This manuscript describes a new method to compute the extent of ablation required based on the Lattice Boltzmann Method (LBM) and patient-specific, pre-operative images. A detailed anatomical model of the liver is obtained from volumetric images. Then a computational model of heat diffusion, cellular necrosis, and blood flow through the vessels and liver is employed to compute the extent of ablated tissue given the probe location, ablation duration and biological parameters. The model was verified against an analytical solution, showing good fidelity. We also evaluated the predictive power of the proposed framework on ten patients who underwent RFA, for whom pre- and post-operative images were available. Comparisons between the computed ablation extent and ground truth, as observed in postoperative images, were promising (DICE index: 42%, sensitivity: 67%, positive predictive value: 38%). The importance of considering liver perfusion while simulating electrical-heating ablation was also highlighted. Implemented on graphics processing units (GPU), our method simulates 1 minute of ablation in 1.14 minutes, allowing near real-time computation.

Stratification of coronary artery disease patients for revascularization procedure based on estimating adverse effects

Background

Percutaneous coronary intervention (PCI) is the most commonly performed treatment for coronary atherosclerosis. It is associated with a higher incidence of repeat revascularization procedures compared to coronary artery bypass grafting surgery. Recent results indicate that PCI is only cost-effective for a subset of patients. Estimating risks of treatment options would be an effort toward personalized treatment strategy for coronary atherosclerosis.

Methods

In this paper, we propose to model clinical knowledge about the treatment of coronary atherosclerosis to identify patient-subgroup-specific classifiers to predict the risk of adverse events of different treatment options. We constructed one model for each patient subgroup to account for subgroup-specific interpretation and availability of features and hierarchically aggregated these models to cover the entire data. In addition, we deviated from the current clinical workflow only for patients with high probability of benefiting from an alternative treatment, as suggested by this model. Consequently, we devised a two-stage test with optimized negative and positive predictive values as the main indicators of performance. Our analysis was based on 2,377 patients that underwent PCI. Performance was compared with a conventional classification model and the existing clinical practice by estimating effectiveness, safety, and costs for different endpoints (6 month angiographic restenosis, 12 and 36 month hazardous events).

Results

Compared to the current clinical practice, the proposed method achieved an estimated reduction in adverse effects by 25.0% (95% CI, 17.8 to 30.2) for hazardous events at 36 months and 31.2% (95% CI, 25.4 to 39.0) for hazardous events at 12 months. Estimated total savings per patient amounted to $693 and $794 at 12 and 36 months, respectively. The proposed subgroup-specific method outperformed conventional population wide regression: The median area under the receiver operating characteristic curve increased from 0.57 to 0.61 for prediction of angiographic restenosis and from 0.76 to 0.85 for prediction of hazardous events.

Conclusions

The results of this study demonstrated the efficacy of deployment of bare-metal stents and coronary artery bypass grafting surgery for subsets of patients. This is one effort towards development of personalized treatment strategies for patients with coronary atherosclerosis that could significantly impact associated treatment costs.

Electronic supplementary material

The online version of this article (doi:10.1186/s12911-015-0131-0) contains supplementary material, which is available to authorized users.

Patient-specific biomechanical model for the prediction of lung motion from 4-D CT images

This paper presents an approach to predict the deformation of the lungs and surrounding organs during respiration. The framework incorporates a computational model of the respiratory system, which comprises an anatomical model extracted from computed tomography (CT) images at end-expiration (EE), and a biomechanical model of the respiratory physiology, including the material behavior and interactions between organs. A personalization step is performed to automatically estimate patient-specific thoracic pressure, which drives the biomechanical model. The zone-wise pressure values are obtained by using a trust-region optimizer, where the estimated motion is compared to CT images at end-inspiration (EI). A detailed convergence analysis in terms of mesh resolution, time stepping and number of pressure zones on the surface of the thoracic cavity is carried out. The method is then tested on five public datasets. Results show that the model is able to predict the respiratory motion with an average landmark error of 3.40 ±1.0 mm over the entire respiratory cycle. The estimated 3-D lung motion may constitute as an advanced 3-D surrogate for more accurate medical image reconstruction and patient respiratory analysis.

Data-driven estimation of cardiac electrical diffusivity from 12-lead ECG signals

Diagnosis and treatment of dilated cardiomyopathy (DCM) is challenging due to a large variety of causes and disease stages. Computational models of cardiac electrophysiology (EP) can be used to improve the assessment and prognosis of DCM, plan therapies and predict their outcome, but require personalization. In this work, we present a data-driven approach to estimate the electrical diffusivity parameter of an EP model from standard 12-lead electrocardiograms (ECG). An efficient forward model based on a mono-domain, phenomenological Lattice-Boltzmann model of cardiac EP, and a boundary element-based mapping of potentials to the body surface is employed. The electrical diffusivity of myocardium, left ventricle and right ventricle endocardium is then estimated using polynomial regression which takes as input the QRS duration and electrical axis. After validating the forward model, we computed 9500 EP simulations on 19 different DCM patients in just under three seconds each to learn the regression model. Using this database, we quantify the intrinsic uncertainty of electrical diffusion for given ECG features and show in a leave-one-patient-out cross-validation that the regression method is able to predict myocardium diffusion within the uncertainty range. Finally, our approach is tested on the 19 cases using their clinical ECG. 84% of them could be personalized using our method, yielding mean prediction errors of 18.7ms for the QRS duration and 6.5° for the electrical axis, both values being within clinical acceptability. By providing an estimate of diffusion parameters from readily available clinical data, our data-driven approach could therefore constitute a first calibration step toward a more complete personalization of cardiac EP.

Graphics processing unit accelerated one-dimensional blood flow computation in the human arterial tree

One-dimensional blood flow models have been used extensively for computing pressure and flow waveforms in the human arterial circulation. We propose an improved numerical implementation based on a graphics processing unit (GPU) for the acceleration of the execution time of one-dimensional model. A novel parallel hybrid CPU-GPU algorithm with compact copy operations (PHCGCC) and a parallel GPU only (PGO) algorithm are developed, which are compared against previously introduced PHCG versions, a single-threaded CPU only algorithm and a multi-threaded CPU only algorithm. Different second-order numerical schemes (Lax-Wendroff and Taylor series) are evaluated for the numerical solution of one-dimensional model, and the computational setups include physiologically motivated non-periodic (Windkessel) and periodic boundary conditions (BC) (structured tree) and elastic and viscoelastic wall laws. Both the PHCGCC and the PGO implementations improved the execution time significantly. The speed-up values over the single-threaded CPU only implementation range from 5.26 to 8.10 × , whereas the speed-up values over the multi-threaded CPU only implementation range from 1.84 to 4.02 × . The PHCGCC algorithm performs best for an elastic wall law with non-periodic BC and for viscoelastic wall laws, whereas the PGO algorithm performs best for an elastic wall law with periodic BC.

A framework for personalization of coronary flow computations during rest and hyperemia

We introduce a Computational Fluid Dynamics (CFD) based method for performing patient-specific coronary hemodynamic computations under two conditions: at rest and during drug-induced hyperemia. The proposed method is based on a novel estimation procedure for determining the boundary conditions from non-invasively acquired patient data at rest. A multi-variable feedback control framework ensures that the computed mean arterial pressure and the flow distribution matches the estimated values for an individual patient during the rest state. The boundary conditions at hyperemia are derived from the respective rest-state values via a transfer function that models the vasodilation phenomenon. Simulations are performed on a coronary tree where a 65% diameter stenosis is introduced in the left anterior descending (LAD) artery, with the boundary conditions estimated using the proposed method. The results demonstrate that the estimation of the hyperemic resistances is crucial in order to obtain accurate values for pressure and flow rates. Results from an exhaustive sensitivity analysis have been presented for analyzing the variability of trans-stenotic pressure drop and Fractional Flow Reserve (FFR) values with respect to various measurements and assumptions.

Fast data-driven calibration of a cardiac electrophysiology model from images and ECG

Recent advances in computational electrophysiology (EP) models make them attractive for clinical use. We propose a novel data-driven approach to calibrate an EP model from standard 12-lead electrocardiograms (ECG), which are in contrast to invasive or dense body surface measurements widely available in clinical routine. With focus on cardiac depolarization, we first propose an efficient forward model of ECG by coupling a mono-domain, Lattice-Boltzmann model of cardiac EP to a boundary element formulation of body surface potentials. We then estimate a polynomial regression to predict myocardium, left ventricle and right ventricle endocardium electrical diffusion from QRS duration and ECG electrical axis. Training was performed on 4,200 ECG simulations, calculated in aproximately 3 s each, using different diffusion parameters on 13 patient geometries. This allowed quantifying diffusion uncertainty for given ECG parameters due to the ill-posed nature of the ECG problem. We show that our method is able to predict myocardium diffusion within the uncertainty range, yielding a prediction error of less than 5 ms for QRS duration and 2 degree for electrical axis. Prediction results compared favorably with those obtained with a standard optimization procedure, while being 60 times faster. Our data-driven model can thus constitute an efficient preliminary step prior to more refined EP personalization.

Global error minimization in image mosaicing using graph connectivity and its applications in microscopy

Several applications such as multiprojector displays and microscopy require the mosaicing of images (tiles) acquired by a camera as it traverses an unknown trajectory in 3D space. A homography relates the image coordinates of a point in each tile to those of a reference tile provided the 3D scene is planar. Our approach in such applications is to first perform pairwise alignment of the tiles that have imaged common regions in order to recover a homography relating the tile pair. We then find the global set of homographies relating each individual tile to a reference tile such that the homographies relating all tile pairs are kept as consistent as possible. Using these global homographies, one can generate a mosaic of the entire scene. We derive a general analytical solution for the global homographies by representing the pair-wise homographies on a connectivity graph. Our solution can accommodate imprecise prior information regarding the global homographies whenever such information is available. We also derive equations for the special case of translation estimation of an X-Y microscopy stage used in histology imaging and present examples of stitched microscopy slices of specimens obtained after radical prostatectomy or prostate biopsy. In addition, we demonstrate the superiority of our approach over tree-structured approaches for global error minimization.

A survey of medical image registration on graphics hardware

The rapidly increasing performance of graphics processors, improving programming support and excellent performance-price ratio make graphics processing units (GPUs) a good option for a variety of computationally intensive tasks. Within this survey, we give an overview of GPU accelerated image registration. We address both, GPU experienced readers with an interest in accelerated image registration, as well as registration experts who are interested in using GPUs. We survey programming models and interfaces and analyze different approaches to programming on the GPU. We furthermore discuss the inherent advantages and challenges of current hardware architectures, which leads to a description of the details of the important building blocks for successful implementations.

Linear intensity-based image registration by Markov random fields and discrete optimization

We propose a framework for intensity-based registration of images by linear transformations, based on a discrete Markov random field (MRF) formulation. Here, the challenge arises from the fact that optimizing the energy associated with this problem requires a high-order MRF model. Currently, methods for optimizing such high-order models are less general, easy to use, and efficient, than methods for the popular second-order models. Therefore, we propose an approximation to the original energy by an MRF with tractable second-order terms. The approximation at a certain point p in the parameter space is the normalized sum of evaluations of the original energy at projections of p to two-dimensional subspaces. We demonstrate the quality of the proposed approximation by computing the correlation with the original energy, and show that registration can be performed by discrete optimization of the approximated energy in an iteration loop. A search space refinement strategy is employed over iterations to achieve sub-pixel accuracy, while keeping the number of labels small for efficiency. The proposed framework can encode any similarity measure is robust to the settings of the internal parameters, and allows an intuitive control of the parameter ranges. We demonstrate the applicability of the framework by intensity-based registration, and 2D-3D registration of medical images. The evaluation is performed by random studies and real registration tasks. The tests indicate increased robustness and precision compared to corresponding standard optimization of the original energy, and demonstrate robustness to noise. Finally, the proposed framework allows the transfer of advances in MRF optimization to linear registration problems.

Recursive Green's function registration

Non-parametric image registration is still among the most challenging problems in both computer vision and medical imaging. Here, one tries to minimize a joint functional that is comprised of a similarity measure and a regularizer in order to obtain a reasonable displacement field that transforms one image to the other. A common way to solve this problem is to formulate a necessary condition for an optimizer, which in turn leads to a system of partial differential equations (PDEs). In general, the most time consuming part of the registration task is to find a numerical solution for such a system. In this paper, we present a generalized and efficient numerical scheme for solving such PDEs simply by applying 1-dimensional recursive filtering to the right hand side of the system based on the Green's function of the differential operator that corresponds to the chosen regularizer. So in the end we come up with a general linear algorithm. We present the associated Green's function for the diffusive and curvature regularizers and show how one may efficiently implement the whole process by using recursive filter approximation. Finally, we demonstrate the capability of the proposed method on realistic examples.

COMPUTER-AIDED GLEASON GRADING OF PROSTATE CANCER HISTOPATHOLOGICAL IMAGES USING TEXTON FORESTS

The Gleason score is the single most important prognostic indicator for prostate cancer candidates and plays a significant role in treatment planning. Histopathological imaging of prostate tissue samples provides the gold standard for obtaining the Gleason score, but the manual assignment of Gleason grades is a labor-intensive and error-prone process. We have developed a texture classification system for automatic and reproducible Gleason grading. Our system characterizes the texture in images belonging to a tumor grade by clustering extracted filter responses at each pixel into textons (basic texture elements). We have used random forests to cluster the filter responses into textons followed by the spatial pyramid match kernel in conjunction with an SVM classifier. We have demonstrated the efficacy of our system in distinguishing between Gleason grades 3 and 4.

Generation of a high-titer packaging cell line for the production of retroviral vectors in suspension and serum-free media

Several patients with severe combined immunodeficiency-X1 disease and adenosine deaminase deficiency have been cured by retroviral-mediated gene therapy. Despite the earlier success, the production of retroviral vectors for clinical gene therapy is cumbersome, costly and lacks safety features because of the adherent nature of packaging cells and the necessity to supplement the culture media with bovine serum. The aim of this study was to generate a retrovirus packaging cell line that could be used for the production of large clinical batch vectors. Bicistronic vectors containing an internal ribosomal entry site followed by a selection gene were used to express Moloney murine leukemia gag-pol and amphotropic envelope viral proteins in HEK293 cells. The candidate clone (293GP-A2) that was selected as the packaging cell line could release recombinant green fluorescent protein retroviruses at 4x10(7) infectious viral particles per ml. Similar titers were achieved after these cells were adapted to grow in suspension and serum-free media. Furthermore, using the same culture conditions viral titers proved to be stable for a 3-month culture period. The 293GP-A2 packaging cell line has the potential to be cultured in bioreactors, opening the possibility for large-scale use of retroviral vectors in late stage clinical trials.

Metabolic flux analysis of HEK-293 cells in perfusion cultures for the production of adenoviral vectors

To meet increasing needs of adenovirus vectors for gene therapy programs, development of efficient and reproducible production processes is required. Perfusion cultures were employed to allow infection at greater cell concentrations. In an effort to define culture conditions resulting in enhanced productivities, experiments performed at different feed rates and infected at various cell densities were compared using metabolic flux analysis. The highest specific product yields were achieved in experiments performed at high perfusion rates and/or low cell concentrations. The intracellular flux analysis revealed that these experiments exhibited greater glycolytic fluxes, slightly higher TCA fluxes, and greater ATP production rates at the time of infection. In contrast, cultures infected at high cell density and/or low medium renewal rates were characterized by a more efficient utilization of glucose at the time of infection, but the specific product yields achieved were lower. The intracellular flux analysis provided a rational basis for the implementation of a feeding strategy that allowed successful infection at a density of 5x10(6)cells/ml.

Transient gene expression in HEK293 cells: Peptone addition posttransfection improves recombinant protein synthesis

Gene expression by large-scale transfection of mammalian cells is becoming an established technology for the fast production of milligram and even gram amounts of recombinant proteins (r-proteins). However, efforts are still needed to optimize production parameters in order to maximize volumetric productivities while maintaining product quality. In this study, transfection efficiency and volumetric productivity following transient gene expression in HEK293 cells were evaluated using green fluorescent protein (GFP) and human placental secreted alkaline phosphatase (SEAP) as reporter genes. We show that a single pulse of peptones (protein hydrolysates) to the cultures performed in a low serum (1%, v/v) and in serum-free medium results in a significant increase in volumetric protein productivity. Sixteen peptones from different sources were tested and almost all of them showed a positive effect on r-protein production. This effect, however, is time- and concentration-dependent. By using Tryptone N1 (a casein peptone, TN1) to feed the cultures at 24 h posttransfection (hpt), a 2-fold increase in volumetric SEAP productivity was obtained 5 days posttransfection. This effect was shown to be equal to that obtained when the culture was fed with a supplementary 4% (v/v) of serum. The positive effect of TN1 on protein production was also demonstrated with Tie2 protein ectodomain produced in serum-free medium. HPLC analysis of amino acids consumption/production during control batch and TN1 pulse culture showed some major differences in amino acid metabolism when using TN1 pulse. Asparagine, glycine, histidine, threonine, leucine, and valine show accumulation in the medium over the cultivation period instead of being consumed as observed in unfed sample (except for asparagine, which remained unchanged). Isoleucine, tyrosine, methionine, and phenylalanine all remained unchanged or slightly fluctuated in TN1-fed culture after the feeding pulse, while they were all steadily consumed in the control run. The relative abundance of SEAP's mRNA suggests that the improvement in protein yield results both from an increase of the translational activity and transcription efficiency. Further understanding of mechanisms by which amino acids/peptides regulate transcriptional and translational machinery in mammalian cells should facilitate the design of new strategies for the improvement of r-protein production by large-scale transfection.

Low-protein medium affects the 293SF central metabolism during growth and infection with adenovirus

In this study the metabolism of 293SF cells grown in serum-free and low-protein medium was analyzed. This cell line is known for its ability to replicate recombinant adenovirus, mainly used in gene therapy applications. A complete model composed of the main glycolytic, glutaminolytic, and amino acids pathways, as well as the internalization fluxes of certain compounds into the mitochondria, is used for metabolic flux calculations. The pentose-phosphate cycle is also added to the biochemical reactions set and was independently measured with labeled 14C-glucose. Different feeding strategies in two different media were analyzed with the model, and the theoretical ATP production was also calculated. The two media were similar in their glucose and amino acid composition, but one contained BSA at 1g/L whereas the other had a very low protein content. Use of low-protein medium resulted in up to fourfold higher adenoviral vector production. In this medium, glucose utilization was more efficient, as it entered the TCA cycle more efficiently. Also, lower glutamine and amino acids consumption were observed as well as lower lactate and ammonia production. This increased TCA activity led to a twofold higher ATP production in the low-protein medium.

Validation of a high-performance liquid chromatographic assay for the quantification of adenovirus type 5 particles

An anion-exchange-high-performance liquid chromatography (AE-HPLC) method for the quantification of adenovirus type 5 (Ad5) total particles was validated according to performance criteria of precision, specificity, linearity of calibration and range, limit of detection, limit of quantification, accuracy and recovery. The viral particles were detected by absorbance at 260 nm using photodiode array detector (PDA). Cesium chloride (CsCl) purified Ad5 and lysate samples were used for the validation of the method. Relative standard deviations (RSDs) for the inter-day, intra-day precision and reproducibility for both the lysate and the Ad5 standard were less than 10 and 2% for the peak area and retention time, respectively. The method was specific for Ad5 which was eluted at 8.0 min. The presence of DNA does not affect the recovery of Ad5 particles for accurate quantification. Based on the error in prediction to be less than 10%, the working range was established between 2 x 10(10) and 7 x 10(10) VP/ml with correlation coefficient of 0.99975, standard deviation of 6.14 x 10(9) VP/ml and a slope of 3.04 x 10(5) VP/ml. The recovery of the method varied between 88 and 106% in all of the lysate samples investigated which is statistically similar to 100% recovery at 95% confidence interval.

Dystrophin expression in muscle following gene transfer with a fully deleted ("gutted") adenovirus is markedly improved by trans-acting adenoviral gene products

Helper-dependent adenoviruses (HDAd) are Ad vectors lacking all or most viral genes. They hold great promise for gene therapy of diseases such as Duchenne muscular dystrophy (DMD), because they are less immunogenic than E1/E3-deleted Ad (first-generation Ad or FGAd) and can carry the full-length (Fl) dystrophin (dys) cDNA (12 kb). We have compared the transgene expression of a HDAd (HDAdCMVDysFl) and a FGAd (FGAdCMV-dys) in cell culture (HeLa, C2C12 myotubes) and in the muscle of mdx mice (the mouse model for DMD). Both vectors encoded dystrophin regulated by the same cytomegalovirus (CMV) promoter. We demonstrate that the amount of dystrophin expressed was significantly higher after gene transfer with FGAdCMV-dys compared to HDAdCMVDysFl both in vitro and in vivo. However, gene transfer with HDAdCMVDysFl in the presence of a FGAd resulted in a significant increase of dystrophin expression indicating that gene products synthesized by the FGAd increase, in trans, the amount of dystrophin produced. This enhancement occurred in cell culture and after gene transfer in the muscle of mdx mice and dystrophic golden retriever (GRMD) dogs, another animal model for DMD. The E4 region of Ad is required for the enhancement, because no increase of dystrophin expression from HDAdCMVDysFl was observed in the presence of an E1/E4-deleted Ad in vitro and in vivo. The characterization of these enhancing gene products followed by their inclusion into an HDAd may be required to produce sufficient dystrophin to mitigate the pathology of DMD by HDAd-mediated gene transfer.

Improved high-performance liquid chromatographic method in the analysis of adenovirus particles

We developed a HPLC method on a novel continuous bed matrix (UNO Q, Bio-Rad) for the direct quantification of adenoviral type 5 (Ad5) particles produced in 293S Human Embryonic Kidney cells and compared this with an existing HPLC method on a conventional ion-exchange resin (Resource Q, Pharmacia). The 293S cell extract contained large amounts of DNA. This contaminated the viral peak on the Resource Q column and only after Benzonase treatment was it possible to quantify the viral particles in the cell extract. In contrast, the virus peak on the UNO Q column was resolved from the DNA which eliminates the need for pretreatment of the sample with Benzonase. Cross-analysis of the Ad5 fraction from the UNO Q column using a size-exclusion HPLC column revealed no additional contaminating peaks. We conclude that the purity of the Ad5 virus peak on the continuous bed matrix UNO Q column was superior to the purity of the virus on the conventional Resource Q column, which is essential for reliable quantification.

Monitoring motility, spreading, and mortality of adherent insect cells using an impedance sensor

An emerging sensor technology referred to as electric cell-substrate impedance sensing (ECIS) has been extended for monitoring the behavior of insect cells including attachment, motility, and mortality. In ECIS, adherent cells were cultured on an array of eight small gold electrodes deposited on the bottom of tissue culture wells and immersed in a culture medium. Upon the attachment and spreading of cells on the gold electrode, the impedance increased because the cells acted as insulating particles to restrict the current flow. Experimental data revealed that insect cells interacted differently with various proteins used to precoat the gold electrode with concanavalin A as the best promoter to accelerate the rate of cell attachment. After the cells were fully spread, the measured impedance continued to fluctuate to reflect the constant motion and metabolic activity of the cells. As the cell behavior was sensitive to external chemicals, the applicability of ECIS for inhibition assays was demonstrated with HgCl2, trinitrotoluene, trinitrobenzene (TNB), and 2-amino-4,6-dinitrotoluene as model systems. Unlike conventional assays, the quantitative data obtained in this study are taken in real time and in a continuous fashion to depict cell motility and mortality.