Preserving fairness and diagnostic accuracy in private large-scale AI models for medical imaging.

BACKGROUND: Artificial intelligence (AI) models are increasingly used in the medical domain. However, as medical data is highly sensitive, special precautions to ensure its protection are required. The gold standard for privacy preservation is the introduction of differential privacy (DP) to model training. Prior work indicates that DP has negative implications on model accuracy and fairness, which are unacceptable in medicine and represent a main barrier to the widespread use of privacy-preserving techniques. In this work, we evaluated the effect of privacy-preserving training of AI models regarding accuracy and fairness compared to non-private training. METHODS: We used two datasets: (1) A large dataset (N = 193,311) of high quality clinical chest radiographs, and (2) a dataset (N = 1625) of 3D abdominal computed tomography (CT) images, with the task of classifying the presence of pancreatic ductal adenocarcinoma (PDAC). Both were retrospectively collected and manually labeled by experienced radiologists. We then compared non-private deep convolutional neural networks (CNNs) and privacy-preserving (DP) models with respect to privacy-utility trade-offs measured as area under the receiver operating characteristic curve (AUROC), and privacy-fairness trade-offs, measured as Pearson's r or Statistical Parity Difference. RESULTS: We find that, while the privacy-preserving training yields lower accuracy, it largely does not amplify discrimination against age, sex or co-morbidity. However, we find an indication that difficult diagnoses and subgroups suffer stronger performance hits in private training. CONCLUSIONS: Our study shows that - under the challenging realistic circumstances of a real-life clinical dataset - the privacy-preserving training of diagnostic deep learning models is possible with excellent diagnostic accuracy and fairness.

Artificial intelligence (AI), in which computers can learn to do tasks that normally require human intelligence, is particularly useful in medical imaging. However, AI should be used in a way that preserves patient privacy. We explored the balance between maintaining patient data privacy and AI performance in medical imaging. We use an approach called differential privacy to protect the privacy of patients' images. We show that, although training AI with differential privacy leads to a slight decrease in accuracy, it does not substantially increase bias against different age groups, genders, or patients with multiple health conditions. However, we notice that AI faces more challenges in accurately diagnosing complex cases and specific subgroups when trained under these privacy constraints. These findings highlight the importance of designing AI systems that are both privacy-conscious and capable of reliable diagnoses across patient groups.

Development of an image-based Random Forest classifier for prediction of surgery duration of laparoscopic sigmoid resections.

PURPOSE: Sigmoid diverticulitis is a disease with a high socioeconomic burden, accounting for a high number of left-sided colonic resections worldwide. Modern surgical scheduling relies on accurate prediction of operation times to enhance patient care and optimize healthcare resources. This study aims to develop a predictive model for surgery duration in laparoscopic sigmoid resections, based on preoperative CT biometric and demographic patient data. METHODS: This retrospective single-center cohort study included 85 patients who underwent laparoscopic sigmoid resection for diverticular disease. Potentially relevant procedure-specific anatomical parameters recommended by a surgical expert were measured in preoperative CT imaging. After random split into training and test set (75% / 25%) multiclass logistic regression was performed and a Random Forest classifier was trained on CT imaging parameters, patient age, and sex in the training cohort to predict categorized surgery duration. The models were evaluated in the test cohort using established performance metrics including receiver operating characteristics area under the curve (AUROC). RESULTS: The Random Forest model achieved a good average AUROC of 0.78. It allowed a very good prediction of long (AUROC = 0.89; specificity 0.71; sensitivity 1.0) and short (AUROC = 0.81; specificity 0.77; sensitivity 0.56) procedures. It clearly outperformed the multiclass logistic regression model (AUROC: average = 0.33; short = 0.31; long = 0.22). CONCLUSION: A Random Forest classifier trained on demographic and CT imaging biometric patient data could predict procedure duration outliers of laparoscopic sigmoid resections. Pending validation in a multicenter study, this approach could potentially improve procedure scheduling in visceral surgery and be scaled to other procedures.

Encrypted federated learning for secure decentralized collaboration in cancer image analysis.

Artificial intelligence (AI) has a multitude of applications in cancer research and oncology. However, the training of AI systems is impeded by the limited availability of large datasets due to data protection requirements and other regulatory obstacles. Federated and swarm learning represent possible solutions to this problem by collaboratively training AI models while avoiding data transfer. However, in these decentralized methods, weight updates are still transferred to the aggregation server for merging the models. This leaves the possibility for a breach of data privacy, for example by model inversion or membership inference attacks by untrusted servers. Somewhat-homomorphically-encrypted federated learning (SHEFL) is a solution to this problem because only encrypted weights are transferred, and model updates are performed in the encrypted space. Here, we demonstrate the first successful implementation of SHEFL in a range of clinically relevant tasks in cancer image analysis on multicentric datasets in radiology and histopathology. We show that SHEFL enables the training of AI models which outperform locally trained models and perform on par with models which are centrally trained. In the future, SHEFL can enable multiple institutions to co-train AI models without forsaking data governance and without ever transmitting any decryptable data to untrusted servers.

A distinct stimulatory cDC1 subpopulation amplifies CD8+ T cell responses in tumors for protective anti-cancer immunity.

Type 1 conventional dendritic cells (cDC1) can support T cell responses within tumors but whether this determines protective versus ineffective anti-cancer immunity is poorly understood. Here, we use imaging-based deep learning to identify intratumoral cDC1-CD8+ T cell clustering as a unique feature of protective anti-cancer immunity. These clusters form selectively in stromal tumor regions and constitute niches in which cDC1 activate TCF1+ stem-like CD8+ T cells. We identify a distinct population of immunostimulatory CCR7neg cDC1 that produce CXCL9 to promote cluster formation and cross-present tumor antigens within these niches, which is required for intratumoral CD8+ T cell differentiation and expansion and promotes cancer immune control. Similarly, in human cancers, CCR7neg cDC1 interact with CD8+ T cells in clusters and are associated with patient survival. Our findings reveal an intratumoral phase of the anti-cancer T cell response orchestrated by tumor-residing cDC1 that determines protective versus ineffective immunity and could be exploited for cancer therapy.

Computed high-b-value high-resolution DWI improves solid lesion detection in IPMN of the pancreas.

OBJECTIVES: To examine the effect of high-b-value computed diffusion-weighted imaging (cDWI) on solid lesion detection and classification in pancreatic intraductal papillary mucinous neoplasm (IPMN), using endoscopic ultrasound (EUS) and histopathology as a standard of reference. METHODS: Eighty-two patients with known or suspected IPMN were retrospectively enrolled. Computed high-b-value images at b = 1000 s/mm2 were calculated from standard (b = 0, 50, 300, and 600 s/mm2) DWI images for conventional full field-of-view (fFOV, 3 × 3 × 4 mm3 voxel size) DWI. A subset of 39 patients received additional high-resolution reduced-field-of-view (rFOV, 2.5 × 2.5 × 3 mm3 voxel size) DWI. In this cohort, rFOV cDWI was compared against fFOV cDWI additionally. Two experienced radiologists evaluated (Likert scale 1-4) image quality (overall image quality, lesion detection and delineation, fluid suppression within the lesion). In addition, quantitative image parameters (apparent signal-to-noise ratio (aSNR), apparent contrast-to-noise ratio (aCNR), contrast ratio (CR)) were assessed. Diagnostic confidence regarding the presence/absence of diffusion-restricted solid nodules was assessed in an additional reader study. RESULTS: High-b-value cDWI at b = 1000 s/mm2 outperformed acquired DWI at b = 600 s/mm2 regarding lesion detection, fluid suppression, aCNR, CR, and lesion classification (p = < .001-.002). Comparing cDWI from fFOV and rFOV revealed higher image quality in high-resolution rFOV-DWI compared to conventional fFOV-DWI (p ≤ .001-.018). High-b-value cDWI images were rated non-inferior to directly acquired high-b-value DWI images (p = .095-.655). CONCLUSIONS: High-b-value cDWI may improve the detection and classification of solid lesions in IPMN. Combining high-resolution imaging and high-b-value cDWI may further increase diagnostic precision. CLINICAL RELEVANCE STATEMENT: This study shows the potential of computed high-resolution high-sensitivity diffusion-weighted magnetic resonance imaging for solid lesion detection in pancreatic intraductal papillary mucinous neoplasia (IPMN). The technique may enable early cancer detection in patients under surveillance. KEY POINTS: • Computed high-b-value diffusion-weighted imaging (cDWI) may improve the detection and classification of intraductal papillary mucinous neoplasms (IPMN) of the pancreas. • cDWI calculated from high-resolution imaging increases diagnostic precision compared to cDWI calculated from conventional-resolution imaging. • cDWI has the potential to strengthen the role of MRI for screening and surveillance of IPMN, particularly in view of the rising incidence of IPMNs combined with now more conservative therapeutic approaches.

The Liver Tumor Segmentation Benchmark (LiTS).

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.

Algorithmic transparency and interpretability measures improve radiologists' performance in BI-RADS 4 classification.

OBJECTIVE: To evaluate the perception of different types of AI-based assistance and the interaction of radiologists with the algorithm's predictions and certainty measures. METHODS: In this retrospective observer study, four radiologists were asked to classify Breast Imaging-Reporting and Data System 4 (BI-RADS4) lesions (n = 101 benign, n = 99 malignant). The effect of different types of AI-based assistance (occlusion-based interpretability map, classification, and certainty) on the radiologists' performance (sensitivity, specificity, questionnaire) were measured. The influence of the Big Five personality traits was analyzed using the Pearson correlation. RESULTS: Diagnostic accuracy was significantly improved by AI-based assistance (an increase of 2.8% ± 2.3%, 95 %-CI 1.5 to 4.0 %, p = 0.045) and trust in the algorithm was generated primarily by the certainty of the prediction (100% of participants). Different human-AI interactions were observed ranging from nearly no interaction to humanization of the algorithm. High scores in neuroticism were correlated with higher persuasibility (Pearson's r = 0.98, p = 0.02), while higher consciousness and change of accuracy showed an inverse correlation (Pearson's r = -0.96, p = 0.04). CONCLUSION: Trust in the algorithm's performance was mostly dependent on the certainty of the predictions in combination with a plausible heatmap. Human-AI interaction varied widely and was influenced by personality traits. KEY POINTS: • AI-based assistance significantly improved the diagnostic accuracy of radiologists in classifying BI-RADS 4 mammography lesions. • Trust in the algorithm's performance was mostly dependent on the certainty of the prediction in combination with a reasonable heatmap. • Personality traits seem to influence human-AI collaboration. Radiologists with specific personality traits were more likely to change their classification according to the algorithm's prediction than others.

Functional biomarkers derived from computed tomography and magnetic resonance imaging differentiate PDAC subgroups and reveal gemcitabine-induced hypo-vascularization.

PURPOSE: Pancreatic ductal adenocarcinoma (PDAC) is a molecularly heterogeneous tumor entity with no clinically established imaging biomarkers. We hypothesize that tumor morphology and physiology, including vascularity and perfusion, show variations that can be detected by differences in contrast agent (CA) accumulation measured non-invasively. This work seeks to establish imaging biomarkers for tumor stratification and therapy response monitoring in PDAC, based on this hypothesis. METHODS AND MATERIALS: Regional CA accumulation in PDAC was correlated with tumor vascularization, stroma content, and tumor cellularity in murine and human subjects. Changes in CA distribution in response to gemcitabine (GEM) were monitored longitudinally with computed tomography (CT) Hounsfield Units ratio (HUr) of tumor to the aorta or with magnetic resonance imaging (MRI) ΔR1 area under the curve at 60 s tumor-to-muscle ratio (AUC60r). Tissue analyses were performed on co-registered samples, including endothelial cell proliferation and cisplatin tissue deposition as a surrogate of chemotherapy delivery. RESULTS: Tumor cell poor, stroma-rich regions exhibited high CA accumulation both in human (meanHUr 0.64 vs. 0.34, p < 0.001) and mouse PDAC (meanAUC60r 2.0 vs. 1.1, p < 0.001). Compared to the baseline, in vivo CA accumulation decreased specifically in response to GEM treatment in a subset of human (HUr -18%) and mouse (AUC60r -36%) tumors. Ex vivo analyses of mPDAC showed reduced cisplatin delivery (GEM: 0.92 ± 0.5 mg/g, vs. vehicle: 3.1 ± 1.5 mg/g, p = 0.004) and diminished endothelial cell proliferation (GEM: 22.3% vs. vehicle: 30.9%, p = 0.002) upon GEM administration. CONCLUSION: In PDAC, CA accumulation, which is related to tumor vascularization and perfusion, inversely correlates with tumor cellularity. The standard of care GEM treatment results in decreased CA accumulation, which impedes drug delivery. Further investigation is warranted into potentially detrimental effects of GEM in combinatorial therapy regimens.

Efficient, high-performance semantic segmentation using multi-scale feature extraction.

The success of deep learning in recent years has arguably been driven by the availability of large datasets for training powerful predictive algorithms. In medical applications however, the sensitive nature of the data limits the collection and exchange of large-scale datasets. Privacy-preserving and collaborative learning systems can enable the successful application of machine learning in medicine. However, collaborative protocols such as federated learning require the frequent transfer of parameter updates over a network. To enable the deployment of such protocols to a wide range of systems with varying computational performance, efficient deep learning architectures for resource-constrained environments are required. Here we present MoNet, a small, highly optimized neural-network-based segmentation algorithm leveraging efficient multi-scale image features. MoNet is a shallow, U-Net-like architecture based on repeated, dilated convolutions with decreasing dilation rates. We apply and test our architecture on the challenging clinical tasks of pancreatic segmentation in computed tomography (CT) images as well as brain tumor segmentation in magnetic resonance imaging (MRI) data. We assess our model's segmentation performance and demonstrate that it provides performance on par with compared architectures while providing superior out-of-sample generalization performance, outperforming larger architectures on an independent validation set, while utilizing significantly fewer parameters. We furthermore confirm the suitability of our architecture for federated learning applications by demonstrating a substantial reduction in serialized model storage requirement as a surrogate for network data transfer. Finally, we evaluate MoNet's inference latency on the central processing unit (CPU) to determine its utility in environments without access to graphics processing units. Our implementation is publicly available as free and open-source software.

[18F]FDG PET/MRI enables early chemotherapy response prediction in pancreatic ductal adenocarcinoma.

PURPOSE: In this prospective exploratory study, we evaluated the feasibility of [18F]fluorodeoxyglucose ([18F]FDG) PET/MRI-based chemotherapy response prediction in pancreatic ductal adenocarcinoma at two weeks upon therapy onset. MATERIAL AND METHODS: In a mixed cohort, seventeen patients treated with chemotherapy in neoadjuvant or palliative intent were enrolled. All patients were imaged by [18F]FDG PET/MRI before and two weeks after onset of chemotherapy. Response per RECIST1.1 was then assessed at 3 months [18F]FDG PET/MRI-derived parameters (MTV50%, TLG50%, MTV2.5, TLG2.5, SUVmax, SUVpeak, ADCmax, ADCmean and ADCmin) were assessed, using multiple t-test, Man-Whitney-U test and Fisher's exact test for binary features. RESULTS: At 72 ± 43 days, twelve patients were classified as responders and five patients as non-responders. An increase in ∆MTV50% and ∆ADC (≥ 20% and 15%, respectively) and a decrease in ∆TLG50% (≤ 20%) at 2 weeks after chemotherapy onset enabled prediction of responders and non-responders, respectively. Parameter combinations (∆TLG50% and ∆ADCmax or ∆MTV50% and ∆ADCmax) further improved discrimination. CONCLUSION: Multiparametric [18F]FDG PET/MRI-derived parameters, in particular indicators of a change in tumor glycolysis and cellularity, may enable very early chemotherapy response prediction. Further prospective studies in larger patient cohorts are recommended to their clinical impact.

Prediction of Tumor Cellularity in Resectable PDAC from Preoperative Computed Tomography Imaging.

BACKGROUND: PDAC remains a tumor entity with poor prognosis and a 5-year survival rate below 10%. Recent research has revealed invasive biomarkers, such as distinct molecular subtypes, predictive for therapy response and patient survival. Non-invasive prediction of individual patient outcome however remains an unresolved task. METHODS: Discrete cellularity regions of PDAC resection specimen (n = 43) were analyzed by routine histopathological work up. Regional tumor cellularity and CT-derived Hounsfield Units (HU, n = 66) as well as iodine concentrations were regionally matched. One-way ANOVA and pairwise t-tests were performed to assess the relationship between different cellularity level in conventional, virtual monoenergetic 40 keV (monoE 40 keV) and iodine map reconstructions. RESULTS: A statistically significant negative correlation between regional tumor cellularity in histopathology and CT-derived HU from corresponding image regions was identified. Radiological differentiation was best possible in monoE 40 keV CT images. However, HU values differed significantly in conventional reconstructions as well, indicating the possibility of a broad clinical application of this finding. CONCLUSION: In this study we establish a novel method for CT-based prediction of tumor cellularity for in-vivo tumor characterization in PDAC patients.

Hyperpolarized 13C pyruvate magnetic resonance spectroscopy for in vivo metabolic phenotyping of rat HCC.

The in vivo assessment of tissue metabolism represents a novel strategy for the evaluation of oncologic disease. Hepatocellular carcinoma (HCC) is a high-prevalence, high-mortality tumor entity often discovered at a late stage. Recent evidence indicates that survival differences depend on metabolic alterations in tumor tissue, with particular focus on glucose metabolism and lactate production. Here, we present an in vivo imaging technique for metabolic tumor phenotyping in rat models of HCC. Endogenous HCC was induced in Wistar rats by oral diethyl-nitrosamine administration. Peak lactate-to-alanine signal ratios (L/A) were assessed with hyperpolarized magnetic resonance spectroscopic imaging (HPMRSI) after [1-13C]pyruvate injection. Cell lines were derived from a subset of primary tumors, re-implanted in nude rats, and assessed in vivo with dynamic hyperpolarized magnetic resonance spectroscopy (HPMRS) after [1-13C]pyruvate injection and kinetic modelling of pyruvate metabolism, taking into account systemic lactate production and recirculation. For ex vivo validation, enzyme activity and metabolite concentrations were spectroscopically quantified in cell and tumor tissue extracts. Mean peak L/A was higher in endogenous HCC compared to non-tumorous tissue. Dynamic HPMRS revealed higher pyruvate-to-lactate conversion rates (kpl) and lactate signal in subcutaneous tumors derived from high L/A tumor cells, consistent with ex vivo measurements of higher lactate dehydrogenase (LDH) levels in these cells. In conclusion, HPMRS and HPMRSI reveal distinct tumor phenotypes corresponding to differences in glycolytic metabolism in HCC tumor tissue.

Deep Convolutional Neural Network-Assisted Feature Extraction for Diagnostic Discrimination and Feature Visualization in Pancreatic Ductal Adenocarcinoma (PDAC) versus Autoimmune Pancreatitis (AIP).

The differentiation of autoimmune pancreatitis (AIP) and pancreatic ductal adenocarcinoma (PDAC) poses a relevant diagnostic challenge and can lead to misdiagnosis and consequently poor patient outcome. Recent studies have shown that radiomics-based models can achieve high sensitivity and specificity in predicting both entities. However, radiomic features can only capture low level representations of the input image. In contrast, convolutional neural networks (CNNs) can learn and extract more complex representations which have been used for image classification to great success. In our retrospective observational study, we performed a deep learning-based feature extraction using CT-scans of both entities and compared the predictive value against traditional radiomic features. In total, 86 patients, 44 with AIP and 42 with PDACs, were analyzed. Whole pancreas segmentation was automatically performed on CT-scans during the portal venous phase. The segmentation masks were manually checked and corrected if necessary. In total, 1411 radiomic features were extracted using PyRadiomics and 256 features (deep features) were extracted using an intermediate layer of a convolutional neural network (CNN). After feature selection and normalization, an extremely randomized trees algorithm was trained and tested using a two-fold shuffle-split cross-validation with a test sample of 20% (n = 18) to discriminate between AIP or PDAC. Feature maps were plotted and visual difference was noted. The machine learning (ML) model achieved a sensitivity, specificity, and ROC-AUC of 0.89 ± 0.11, 0.83 ± 0.06, and 0.90 ± 0.02 for the deep features and 0.72 ± 0.11, 0.78 ± 0.06, and 0.80 ± 0.01 for the radiomic features. Visualization of feature maps indicated different activation patterns for AIP and PDAC. We successfully trained a machine learning model using deep feature extraction from CT-images to differentiate between AIP and PDAC. In comparison to traditional radiomic features, deep features achieved a higher sensitivity, specificity, and ROC-AUC. Visualization of deep features could further improve the diagnostic accuracy of non-invasive differentiation of AIP and PDAC.

Joint Imaging Platform for Federated Clinical Data Analytics.

PURPOSE: Image analysis is one of the most promising applications of artificial intelligence (AI) in health care, potentially improving prediction, diagnosis, and treatment of diseases. Although scientific advances in this area critically depend on the accessibility of large-volume and high-quality data, sharing data between institutions faces various ethical and legal constraints as well as organizational and technical obstacles. METHODS: The Joint Imaging Platform (JIP) of the German Cancer Consortium (DKTK) addresses these issues by providing federated data analysis technology in a secure and compliant way. Using the JIP, medical image data remain in the originator institutions, but analysis and AI algorithms are shared and jointly used. Common standards and interfaces to local systems ensure permanent data sovereignty of participating institutions. RESULTS: The JIP is established in the radiology and nuclear medicine departments of 10 university hospitals in Germany (DKTK partner sites). In multiple complementary use cases, we show that the platform fulfills all relevant requirements to serve as a foundation for multicenter medical imaging trials and research on large cohorts, including the harmonization and integration of data, interactive analysis, automatic analysis, federated machine learning, and extensibility and maintenance processes, which are elementary for the sustainability of such a platform. CONCLUSION: The results demonstrate the feasibility of using the JIP as a federated data analytics platform in heterogeneous clinical information technology and software landscapes, solving an important bottleneck for the application of AI to large-scale clinical imaging data.

[Artificial intelligence and machine learning in oncologic imaging]. / Künstliche Intelligenz und maschinelles Lernen in der onkologischen Bildgebung.

Machine learning (ML) is entering many areas of society, including medicine. This transformation has the potential to drastically change medicine and medical practice. These aspects become particularly clear when considering the different stages of oncologic patient care and the involved interdisciplinary and intermodality interactions. In recent publications, computers-in collaboration with humans or alone-have been outperforming humans regarding tumor identification, tumor classification, estimating prognoses, and evaluation of treatments. In addition, ML algorithms, e.g., artificial neural networks (ANNs), which constitute the drivers behind many of the latest achievements in ML, can deliver this level of performance in a reproducible, fast, and inexpensive manner. In the future, artificial intelligence applications will become an integral part of the medical profession and offer advantages for oncologic diagnostics and treatment.

Implementing cell-free DNA of pancreatic cancer patient-derived organoids for personalized oncology.

One of the major challenges in using pancreatic cancer patient-derived organoids (PDOs) in precision oncology is the time from biopsy to functional characterization. This is particularly true for endoscopic ultrasound-guided fine-needle aspiration biopsies, typically resulting in specimens with limited tumor cell yield. Here, we tested conditioned media of individual PDOs for cell-free DNA to detect driver mutations already early on during the expansion process to accelerate the genetic characterization of PDOs as well as subsequent functional testing. Importantly, genetic alterations detected in the PDO supernatant, collected as early as 72 hours after biopsy, recapitulate the mutational profile of the primary tumor, indicating suitability of this approach to subject PDOs to drug testing in a reduced time frame. In addition, we demonstrated that this workflow was practicable, even in patients for whom the amount of tumor material was not sufficient for molecular characterization by established means. Together, our findings demonstrate that generating PDOs from very limited biopsy material permits molecular profiling and drug testing. With our approach, this can be achieved in a rapid and feasible fashion with broad implications in clinical practice.

Multiparametric Modelling of Survival in Pancreatic Ductal Adenocarcinoma Using Clinical, Histomorphological, Genetic and Image-Derived Parameters.

RATIONALE: Pancreatic ductal adenocarcinoma (PDAC) remains a tumor entity of exceptionally poor prognosis, and several biomarkers are under current investigation for the prediction of patient prognosis. Many studies focus on promoting newly developed imaging biomarkers without a rigorous comparison to other established parameters. To assess the true value and leverage the potential of all efforts in this field, a multi-parametric evaluation of the available biomarkers for PDAC survival prediction is warranted. Here we present a multiparametric analysis to assess the predictive value of established parameters and the added contribution of newly developed imaging features such as biomarkers for overall PDAC patient survival. METHODS: 103 patients with resectable PDAC were retrospectively enrolled. Clinical and histopathological data (age, sex, chemotherapy regimens, tumor size, lymph node status, grading and resection status), morpho-molecular and genetic data (tumor morphology, molecular subtype, tp53, kras, smad4 and p16 genetics), image-derived features and the combination of all parameters were tested for their prognostic strength based on the concordance index (CI) of multivariate Cox proportional hazards survival modelling after unsupervised machine learning preprocessing. RESULTS: The average CIs of the out-of-sample data were: 0.63 for the clinical and histopathological features, 0.53 for the morpho-molecular and genetic features, 0.65 for the imaging features and 0.65 for the combined model including all parameters. CONCLUSIONS: Imaging-derived features represent an independent survival predictor in PDAC and enable the multiparametric, machine learning-assisted modelling of postoperative overall survival with a high performance compared to clinical and morpho-molecular/genetic parameters. We propose that future studies systematically include imaging-derived features to benchmark their additive value when evaluating biomarker-based model performance.

Image-Based Molecular Phenotyping of Pancreatic Ductal Adenocarcinoma.

To bridge the translational gap between recent discoveries of distinct molecular phenotypes of pancreatic cancer and tangible improvements in patient outcome, there is an urgent need to develop strategies and tools informing and improving the clinical decision process. Radiomics and machine learning approaches can offer non-invasive whole tumor analytics for clinical imaging data-based classification. The retrospective study assessed baseline computed tomography (CT) from 207 patients with proven pancreatic ductal adenocarcinoma (PDAC). Following expert level manual annotation, Pyradiomics was used for the extraction of 1474 radiomic features. The molecular tumor subtype was defined by immunohistochemical staining for KRT81 and HNF1a as quasi-mesenchymal (QM) vs. non-quasi-mesenchymal (non-QM). A Random Forest machine learning algorithm was developed to predict the molecular subtype from the radiomic features. The algorithm was then applied to an independent cohort of histopathologically unclassifiable tumors with distinct clinical outcomes. The classification algorithm achieved a sensitivity, specificity and ROC-AUC (area under the receiver operating characteristic curve) of 0.84 ± 0.05, 0.92 ± 0.01 and 0.93 ± 0.01, respectively. The median overall survival for predicted QM and non-QM tumors was 16.1 and 20.9 months, respectively, log-rank-test p = 0.02, harzard ratio (HR) 1.59. The application of the algorithm to histopathologically unclassifiable tumors revealed two groups with significantly different survival (8.9 and 39.8 months, log-rank-test p < 0.001, HR 4.33). The machine learning-based analysis of preoperative (CT) imaging allows the prediction of molecular PDAC subtypes highly relevant for patient survival, allowing advanced pre-operative patient stratification for precision medicine applications.

Combined DCE-MRI- and FDG-PET enable histopathological grading prediction in a rat model of hepatocellular carcinoma.

PURPOSE: To test combined dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and 18F-FDG positron emission tomography (FDG-PET)-derived parameters for prediction of histopathological grading in a rat Diethyl Nitrosamine (DEN)-induced hepatocellular carcinoma (HCC) model. METHODS: 15 male Wistar rats, aged 10 weeks were treated with oral DEN 0.01 % in drinking water and monitored until HCCs were detectable. DCE-MRI and PET were performed consecutively on small animal scanners. 38 tumors were identified and manually segmented based on HCC-specific contrast enhancement patterns. Grading (G2/3: 24 tumors, G1:14 tumors) alongside other histopathological parameters, tumor volume, contrast agent and 18F-FDG uptake metrics were noted. Class imbalance was addressed using SMOTE and collinearity was removed using hierarchical clustering and principal component analysis. A logistic regression model was fit separately to the individual parameter groups (DCE-MRI-derived, PET-derived, tumor volume) and the combined parameters. RESULTS: The combined model using all imaging-derived parameters achieved a mean ± STD sensitivity of 0.88 ± 0.16, specificity of 0.70 ± 0.20 and AUC of 0.90 ± 0.03. No correlation was found between tumor grading and tumor volume, morphology, necrosis, extracellular matrix, immune cell infiltration or underlying liver fibrosis. CONCLUSION: A combination of DCE-MRI- and 18F-FDG-PET-derived parameters provides high accuracy for histopathological grading of hepatocellular carcinoma in a relevant translational model system.

Prognostic factors in hepatocellular carcinoma patients undergoing transarterial chemoembolization and radioembolization: a retrospective study.

OBJECTIVE: Most patients with hepatocellular carcinoma are diagnosed at intermediate or advanced stages (BCLC B or C) and undergo palliative local treatments such as transarterial chemoembolization or selective internal radiation therapy, also called radioembolization. In terms of liver function and tumor extent, stages BCLC B and C comprise a wide spectrum of tumor manifestations. Predictors of survival in these patients undergoing transarterial chemoembolization and selective internal radiation therapy might help stratification into different prognostic groups and help to select the optimal treatment modality. METHODS: In this retrospective study, all patients with hepatocellular carcinoma who underwent transarterial chemoembolization between January 2010 and December 2014 and all hepatocellular carcinoma patients who underwent selective internal radiation therapy between August 2012 and December 2016 were recruited. The prognostic value of pretherapeutic clinical and laboratory parameters for the prediction of overall survival was analyzed using uni- and multi-variable Cox regression models. RESULTS: We enrolled 129 patients in the transarterial chemoembolization group and 34 patients in the selective internal radiation therapy group. The predictive value of the albumin-bilirubin grade was validated for both the transarterial chemoembolization and the selective internal radiation therapy group. Multivariable analysis identified albumin-bilirubin grade and tumor size as independent predictors for the transarterial chemoembolization group and tumor size, serum albumin and serum sodium as independent predictors for the selective internal radiation therapy group. CONCLUSION: While measures of liver dysfunction predicted survival similarly in both cohorts, we found tumor size to predict survival differently in transarterial chemoembolization- and selective internal radiation therapy-treated patients. Tumor size might help to select the most appropriate treatment in hepatocellular carcinoma patients, although this finding has to be validated in further studies.