Spleen Volume Reduction Is a Reliable and Independent Biomarker for Long-Term Risk of Leukopenia Development in Peptide Receptor Radionuclide Therapy.

177Lu-DOTATATE therapy is an effective treatment for advanced neuroendocrine tumors, despite its dose-limiting hematotoxicity. Herein, the significance of off-target splenic irradiation is unknown. Our study aims to identify predictive markers of peptide receptor radionuclide therapy-induced leukopenia. Methods: We retrospectively analyzed blood counts and imaging data of 88 patients with histologically confirmed, unresectable metastatic neuroendocrine tumors who received 177Lu-DOTATATE treatment at our institution from February 2009 to July 2021. Inclusion criterium was a tumor uptake equivalent to or greater than that in the liver on baseline receptor imaging. We excluded patients with less than 24 mo of follow-up and those patients who received fewer than 4 treatment cycles, additional therapies, or blood transfusions during follow-up. Results: Our study revealed absolute and relative white blood cell counts and relative spleen volume reduction as independent predictors of radiation-induced leukopenia at 24 mo. However, a 30% decline in spleen volume 12 mo after treatment most accurately predicted patients proceeding to leukopenia at 24 mo (receiver operating characteristic area under the curve of 0.91, sensitivity of 0.93, and specificity of 0.90), outperforming all other parameters by far. Conclusion: Automated splenic volume assessments demonstrated superior predictive capabilities for the development of leukopenia in patients undergoing 177Lu-DOTATATE treatment compared with conventional laboratory parameters. The reduction in spleen size proves to be a valuable, routinely available, and quantitative imaging-based biomarker for predicting radiation-induced leukopenia. This suggests potential clinical applications for risk assessment and management.

Evaluation and mitigation of the limitations of large language models in clinical decision-making.

Clinical decision-making is one of the most impactful parts of a physician's responsibilities and stands to benefit greatly from artificial intelligence solutions and large language models (LLMs) in particular. However, while LLMs have achieved excellent performance on medical licensing exams, these tests fail to assess many skills necessary for deployment in a realistic clinical decision-making environment, including gathering information, adhering to guidelines, and integrating into clinical workflows. Here we have created a curated dataset based on the Medical Information Mart for Intensive Care database spanning 2,400 real patient cases and four common abdominal pathologies as well as a framework to simulate a realistic clinical setting. We show that current state-of-the-art LLMs do not accurately diagnose patients across all pathologies (performing significantly worse than physicians), follow neither diagnostic nor treatment guidelines, and cannot interpret laboratory results, thus posing a serious risk to the health of patients. Furthermore, we move beyond diagnostic accuracy and demonstrate that they cannot be easily integrated into existing workflows because they often fail to follow instructions and are sensitive to both the quantity and order of information. Overall, our analysis reveals that LLMs are currently not ready for autonomous clinical decision-making while providing a dataset and framework to guide future studies.

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.

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.

Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study.

Data privacy mechanisms are essential for rapidly scaling medical training databases to capture the heterogeneity of patient data distributions toward robust and generalizable machine learning systems. In the current COVID-19 pandemic, a major focus of artificial intelligence (AI) is interpreting chest CT, which can be readily used in the assessment and management of the disease. This paper demonstrates the feasibility of a federated learning method for detecting COVID-19 related CT abnormalities with external validation on patients from a multinational study. We recruited 132 patients from seven multinational different centers, with three internal hospitals from Hong Kong for training and testing, and four external, independent datasets from Mainland China and Germany, for validating model generalizability. We also conducted case studies on longitudinal scans for automated estimation of lesion burden for hospitalized COVID-19 patients. We explore the federated learning algorithms to develop a privacy-preserving AI model for COVID-19 medical image diagnosis with good generalization capability on unseen multinational datasets. Federated learning could provide an effective mechanism during pandemics to rapidly develop clinically useful AI across institutions and countries overcoming the burden of central aggregation of large amounts of sensitive data.

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.

Intensive Care Risk Estimation in COVID-19 Pneumonia Based on Clinical and Imaging Parameters: Experiences from the Munich Cohort.

The evolving dynamics of coronavirus disease 2019 (COVID-19) and the increasing infection numbers require diagnostic tools to identify patients at high risk for a severe disease course. Here we evaluate clinical and imaging parameters for estimating the need of intensive care unit (ICU) treatment. We collected clinical, laboratory and imaging data from 65 patients with confirmed COVID-19 infection based on polymerase chain reaction (PCR) testing. Two radiologists evaluated the severity of findings in computed tomography (CT) images on a scale from 1 (no characteristic signs of COVID-19) to 5 (confluent ground glass opacities in over 50% of the lung parenchyma). The volume of affected lung was quantified using commercially available software. Machine learning modelling was performed to estimate the risk for ICU treatment. Patients with a severe course of COVID-19 had significantly increased interleukin (IL)-6, C-reactive protein (CRP), and leukocyte counts and significantly decreased lymphocyte counts. The radiological severity grading was significantly increased in ICU patients. Multivariate random forest modelling showed a mean ± standard deviation sensitivity, specificity and accuracy of 0.72 ± 0.1, 0.86 ± 0.16 and 0.80 ± 0.1 and a receiver operating characteristic-area under curve (ROC-AUC) of 0.79 ± 0.1. The need for ICU treatment is independently associated with affected lung volume, radiological severity score, CRP, and IL-6.

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.