Development of Clinical Radiomics-Based Models to Predict Survival Outcome in Pancreatic Ductal Adenocarcinoma: A Multicenter Retrospective Study.

PURPOSE: This multicenter retrospective study aims to identify reliable clinical and radiomic features to build machine learning models that predict progression-free survival (PFS) and overall survival (OS) in pancreatic ductal adenocarcinoma (PDAC) patients. METHODS: Between 2010 and 2020 pre-treatment contrast-enhanced CT scans of 287 pathology-confirmed PDAC patients from two sites of the Hopital Universitaire de Bruxelles (HUB) and from 47 hospitals within the HUB network were retrospectively analysed. Demographic, clinical, and survival data were also collected. Gross tumour volume (GTV) and non-tumoral pancreas (RPV) were semi-manually segmented and radiomics features were extracted. Patients from two HUB sites comprised the training dataset, while those from the remaining 47 hospitals of the HUB network constituted the testing dataset. A three-step method was used for feature selection. Based on the GradientBoostingSurvivalAnalysis classifier, different machine learning models were trained and tested to predict OS and PFS. Model performances were assessed using the C-index and Kaplan-Meier curves. SHAP analysis was applied to allow for post hoc interpretability. RESULTS: A total of 107 radiomics features were extracted from each of the GTV and RPV. Fourteen subgroups of features were selected: clinical, GTV, RPV, clinical & GTV, clinical & GTV & RPV, GTV-volume and RPV-volume both for OS and PFS. Subsequently, 14 Gradient Boosting Survival Analysis models were trained and tested. In the testing dataset, the clinical & GTV model demonstrated the highest performance for OS (C-index: 0.72) among all other models, while for PFS, the clinical model exhibited a superior performance (C-index: 0.70). CONCLUSIONS: An integrated approach, combining clinical and radiomics features, excels in predicting OS, whereas clinical features demonstrate strong performance in PFS prediction.

Tumor Size Is Not Everything: Advancing Radiomics as a Precision Medicine Biomarker in Oncology Drug Development and Clinical Care. A Report of a Multidisciplinary Workshop Coordinated by the RECIST Working Group.

Radiomics, the science of extracting quantifiable data from routine medical images, is a powerful tool that has many potential applications in oncology. The Response Evaluation Criteria in Solid Tumors Working Group (RWG) held a workshop in May 2022, which brought together various stakeholders to discuss the potential role of radiomics in oncology drug development and clinical trials, particularly with respect to response assessment. This article summarizes the results of that workshop, reviewing radiomics for the practicing oncologist and highlighting the work that needs to be done to move forward the incorporation of radiomics into clinical trials.

Multiplex genetic manipulations in Clostridium butyricum and Clostridium sporogenes to secrete recombinant antigen proteins for oral-spore vaccination.

BACKGROUND: Clostridium spp. has demonstrated therapeutic potential in cancer treatment through intravenous or intratumoral administration. This approach has expanded to include non-pathogenic clostridia for the treatment of various diseases, underscoring the innovative concept of oral-spore vaccination using clostridia. Recent advancements in the field of synthetic biology have significantly enhanced the development of Clostridium-based bio-therapeutics. These advancements are particularly notable in the areas of efficient protein overexpression and secretion, which are crucial for the feasibility of oral vaccination strategies. Here, we present two examples of genetically engineered Clostridium candidates: one as an oral cancer vaccine and the other as an antiviral oral vaccine against SARS-CoV-2. RESULTS: Using five validated promoters and a signal peptide derived from Clostridium sporogenes, a series of full-length NY-ESO-1/CTAG1, a promising cancer vaccine candidate, expression vectors were constructed and transformed into C. sporogenes and Clostridium butyricum. Western blotting analysis confirmed efficient expression and secretion of NY-ESO-1 in clostridia, with specific promoters leading to enhanced detection signals. Additionally, the fusion of a reported bacterial adjuvant to NY-ESO-1 for improved immune recognition led to the cloning difficulties in E. coli. The use of an AUU start codon successfully mitigated potential toxicity issues in E. coli, enabling the secretion of recombinant proteins in C. sporogenes and C. butyricum. We further demonstrate the successful replacement of PyrE loci with high-expression cassettes carrying NY-ESO-1 and adjuvant-fused NY-ESO-1, achieving plasmid-free clostridia capable of secreting the antigens. Lastly, the study successfully extends its multiplex genetic manipulations to engineer clostridia for the secretion of SARS-CoV-2-related Spike_S1 antigens. CONCLUSIONS: This study successfully demonstrated that C. butyricum and C. sporogenes can produce the two recombinant antigen proteins (NY-ESO-1 and SARS-CoV-2-related Spike_S1 antigens) through genetic manipulations, utilizing the AUU start codon. This approach overcomes challenges in cloning difficult proteins in E. coli. These findings underscore the feasibility of harnessing commensal clostridia for antigen protein secretion, emphasizing the applicability of non-canonical translation initiation across diverse species with broad implications for medical or industrial biotechnology.

Tumor-targeting bacteria as immune stimulants - the future of cancer immunotherapy?

Cancer immunotherapies have been widely hailed as a breakthrough for cancer treatment in the last decade, epitomized by the unprecedented results observed with checkpoint blockade. Even so, only a minority of patients currently achieve durable remissions. In general, responsive patients appear to have either a high number of tumor neoantigens, a preexisting immune cell infiltrate in the tumor microenvironment, or an 'immune-active' transcriptional profile, determined in part by the presence of a type I interferon gene signature. These observations suggest that the therapeutic efficacy of immunotherapy can be enhanced through strategies that release tumor neoantigens and/or produce a pro-inflammatory tumor microenvironment. In principle, exogenous tumor-targeting bacteria offer a unique solution for improving responsiveness to immunotherapy. This review discusses how tumor-selective bacterial infection can modulate the immunological microenvironment of the tumor and the potential for combination with cancer immunotherapy strategies to further increase therapeutic efficacy. In addition, we provide a perspective on the clinical translation of replicating bacterial therapies, with a focus on the challenges that must be resolved to ensure a successful outcome.

A clinically relevant computed tomography (CT) radiomics strategy for intracranial rodent brain tumour monitoring.

Here, we establish a CT-radiomics based method for application in invasive, orthotopic rodent brain tumour models. Twenty four NOD/SCID mice were implanted with U87R-Luc2 GBM cells and longitudinally imaged via contrast enhanced (CE-CT) imaging. Pyradiomics was employed to extract CT-radiomic features from the tumour-implanted hemisphere and non-tumour-implanted hemisphere of acquired CT-scans. Inter-correlated features were removed (Spearman correlation > 0.85) and remaining features underwent predictive analysis (recursive feature elimination or Boruta algorithm). An area under the curve of the receiver operating characteristic curve was implemented to evaluate radiomic features for their capacity to predict defined outcomes. Firstly, we identified a subset of radiomic features which distinguish the tumour-implanted hemisphere and non- tumour-implanted hemisphere (i.e, tumour presence from normal tissue). Secondly, we successfully translate preclinical CT-radiomic pipelines to GBM patient CT scans (n = 10), identifying similar trends in tumour-specific feature intensities (E.g. 'glszm Zone Entropy'), thereby suggesting a mouse-to-human species conservation (a conservation of radiomic features across species). Thirdly, comparison of features across timepoints identify features which support preclinical tumour detection earlier than is possible by visual assessment of CT scans. This work establishes robust, preclinical CT-radiomic pipelines and describes the application of CE-CT for in-depth orthotopic brain tumour monitoring. Overall we provide evidence for the role of pre-clinical 'discovery' radiomics in the neuro-oncology space.

Promising Diagnostic and Therapeutic Approaches Based on VHHs for Cancer Management.

The discovery of the distinctive structure of heavy chain-only antibodies in species belonging to the Camelidae family has elicited significant interest in their variable antigen binding domain (VHH) and gained attention for various applications, such as cancer diagnosis and treatment. This article presents an overview of the characteristics, advantages, and disadvantages of VHHs as compared to conventional antibodies, and their usage in diverse applications. The singular properties of VHHs are explained, and several strategies that can augment their utility are outlined. The preclinical studies illustrating the diagnostic and therapeutic efficacy of distinct VHHs in diverse formats against solid cancers are summarized, and an overview of the clinical trials assessing VHH-based agents in oncology is provided. These investigations demonstrate the enormous potential of VHHs for medical research and healthcare.

Surface modification effect on contrast agent efficiency for X-ray based spectral photon-counting scanner/luminescence imaging: from fundamental study to in vivo proof of concept.

X-Ray imaging techniques are among the most widely used modalities in medical imaging and their constant evolution has led to the emergence of new technologies. The new generation of computed tomography (CT) systems - spectral photonic counting CT (SPCCT) and X-ray luminescence optical imaging - are examples of such powerful techniques. With these new technologies the rising demand for new contrast agents has led to extensive research in the field of nanoparticles and the possibility to merge the modalities appears to be highly attractive. In this work, we propose the design of lanthanide-based nanocrystals as a multimodal contrast agent with the two aforementioned technologies, allowing SPCCT and optical imaging at the same time. We present a systematic study on the effect of the Tb3+ doping level and surface modification on the generation of contrast with SPCCT and the luminescence properties of GdF3:Tb3+ nanocrystals (NCs), comparing different surface grafting with organic ligands and coatings with silica to make these NCs bio-compatible. A comparison of the luminescence properties of these NCs with UV revealed that the best results were obtained for the Gd0.9Tb0.1F3 composition. This property was confirmed under X-ray excitation in microCT and with SPCCT. Moreover, we could demonstrate that the intensity of the luminescence and the excited state lifetime are strongly affected by the surface modification. Furthermore, whatever the chemical nature of the ligand, the contrast with SPCCT did not change. Finally, the successful proof of concept of multimodal imaging was performed in vivo with nude mice in the SPCCT taking advantage of the so-called color K-edge imaging method.

Deep Learning of Multimodal Ultrasound: Stratifying the Response to Neoadjuvant Chemotherapy in Breast Cancer Before Treatment.

BACKGROUND: Not only should resistance to neoadjuvant chemotherapy (NAC) be considered in patients with breast cancer but also the possibility of achieving a pathologic complete response (PCR) after NAC. Our study aims to develop 2 multimodal ultrasound deep learning (DL) models to noninvasively predict resistance and PCR to NAC before treatment. METHODS: From January 2017 to July 2022, a total of 170 patients with breast cancer were prospectively enrolled. All patients underwent multimodal ultrasound examination (grayscale 2D ultrasound and ultrasound elastography) before NAC. We combined clinicopathological information to develop 2 DL models, DL_Clinical_resistance and DL_Clinical_PCR, for predicting resistance and PCR to NAC, respectively. In addition, these 2 models were combined to stratify the prediction of response to NAC. RESULTS: In the test cohort, DL_Clinical_resistance had an AUC of 0.911 (95%CI, 0.814-0.979) with a sensitivity of 0.905 (95%CI, 0.765-1.000) and an NPV of 0.882 (95%CI, 0.708-1.000). Meanwhile, DL_Clinical_PCR achieved an AUC of 0.880 (95%CI, 0.751-0.973) and sensitivity and NPV of 0.875 (95%CI, 0.688-1.000) and 0.895 (95%CI, 0.739-1.000), respectively. By combining DL_Clinical_resistance and DL_Clinical_PCR, 37.1% of patients with resistance and 25.7% of patients with PCR were successfully identified by the combined model, suggesting that these patients could benefit by an early change of treatment strategy or by implementing an organ preservation strategy after NAC. CONCLUSIONS: The proposed DL_Clinical_resistance and DL_Clinical_PCR models and combined strategy have the potential to predict resistance and PCR to NAC before treatment and allow stratified prediction of NAC response.

Edge Magnetism in MoS2 Nanoribbons: Insights from a Simple One-Dimensional Model.

Edge magnetism in zigzag nanoribbons of monolayer MoS2 has been investigated with both density functional theory and a tight-binding plus Hubbard (TB+U) Hamiltonian. Both methods revealed that one band crossing the Fermi level is more strongly influenced by spin polarization than any other bands. This band originates from states localized on the sulfur edge of the nanoribbon. Its dispersion closely resembles that of the energy branch obtained in a linear chain of atoms with first-neighbor interaction. By exploiting this resemblance, a toy model has been designed to study the energetics of different spin configurations of the nanoribbon edge.

An Interpretable Radiomics Model Based on Two-Dimensional Shear Wave Elastography for Predicting Symptomatic Post-Hepatectomy Liver Failure in Patients with Hepatocellular Carcinoma.

OBJECTIVE: The aim of this study was to develop and validate an interpretable radiomics model based on two-dimensional shear wave elastography (2D-SWE) for symptomatic post-hepatectomy liver failure (PHLF) prediction in patients undergoing liver resection for hepatocellular carcinoma (HCC). METHODS: A total of 345 consecutive patients were enrolled. A five-fold cross-validation was performed during training, and the models were evaluated in the independent test cohort. A multi-patch radiomics model was established based on the 2D-SWE images for predicting symptomatic PHLF. Clinical features were incorporated into the models to train the clinical-radiomics model. The radiomics model and the clinical-radiomics model were compared with the clinical model comprising clinical variables and other clinical predictive indices, including the model for end-stage liver disease (MELD) score and albumin-bilirubin (ALBI) score. Shapley Additive exPlanations (SHAP) was used for post hoc interpretability of the radiomics model. RESULTS: The clinical-radiomics model achieved an AUC of 0.867 (95% CI 0.787-0.947) in the five-fold cross-validation, and this score was higher than that of the clinical model (AUC: 0.809; 95% CI: 0.715-0.902) and the radiomics model (AUC: 0.746; 95% CI: 0.681-0.811). The clinical-radiomics model showed an AUC of 0.822 in the test cohort, higher than that of the clinical model (AUC: 0.684, p = 0.007), radiomics model (AUC: 0.784, p = 0.415), MELD score (AUC: 0.529, p < 0.001), and ALBI score (AUC: 0.644, p = 0.016). The SHAP analysis showed that the first-order radiomics features, including first-order maximum 64 × 64, first-order 90th percentile 64 × 64, and first-order 10th percentile 32 × 32, were the most important features for PHLF prediction. CONCLUSION: An interpretable clinical-radiomics model based on 2D-SWE and clinical variables can help in predicting symptomatic PHLF in HCC.

Development of a CRISPR-Cas12a system for efficient genome engineering in clostridia.

IMPORTANCE: Continued efforts in developing the CRISPR-Cas systems will further enhance our understanding and utilization of Clostridium species. This study demonstrates the development and application of a genome-engineering tool in two Clostridium strains, Clostridium butyricum and Clostridium sporogenes, which have promising potential as probiotics and oncolytic agents. Particular attention was given to the folding of precursor crRNA and the role of this process in off-target DNA cleavage by Cas12a. The results provide the guidelines necessary for efficient genome engineering using this system in clostridia. Our findings not only expand our fundamental understanding of genome-engineering tools in clostridia but also improve this technology to allow use of its full potential in a plethora of biotechnological applications.

MSCDA: Multi-level semantic-guided contrast improves unsupervised domain adaptation for breast MRI segmentation in small datasets.

Deep learning (DL) applied to breast tissue segmentation in magnetic resonance imaging (MRI) has received increased attention in the last decade, however, the domain shift which arises from different vendors, acquisition protocols, and biological heterogeneity, remains an important but challenging obstacle on the path towards clinical implementation. In this paper, we propose a novel Multi-level Semantic-guided Contrastive Domain Adaptation (MSCDA) framework to address this issue in an unsupervised manner. Our approach incorporates self-training with contrastive learning to align feature representations between domains. In particular, we extend the contrastive loss by incorporating pixel-to-pixel, pixel-to-centroid, and centroid-to-centroid contrasts to better exploit the underlying semantic information of the image at different levels. To resolve the data imbalance problem, we utilize a category-wise cross-domain sampling strategy to sample anchors from target images and build a hybrid memory bank to store samples from source images. We have validated MSCDA with a challenging task of cross-domain breast MRI segmentation between datasets of healthy volunteers and invasive breast cancer patients. Extensive experiments show that MSCDA effectively improves the model's feature alignment capabilities between domains, outperforming state-of-the-art methods. Furthermore, the framework is shown to be label-efficient, achieving good performance with a smaller source dataset. The code is publicly available at https://github.com/ShengKuangCN/MSCDA.

Overcoming radioresistance with the hypoxia-activated prodrug CP-506: A pre-clinical study of local tumour control probability.

BACKGROUND AND PURPOSE: Tumour hypoxia is an established radioresistance factor. A novel hypoxia-activated prodrug CP-506 has been proven to selectively target hypoxic tumour cells and to cause anti-tumour activity. The current study investigates whether CP-506 improves outcome of radiotherapy in vivo. MATERIALS AND METHODS: Mice bearing FaDu and UT-SCC-5 xenografts were randomized to receive 5 daily injections of CP-506/vehicle followed by single dose (SD) irradiation. In addition, CP-506 was combined once per week with fractionated irradiation (30 fractions/6 weeks). Animals were followed-up to score all recurrences. In parallel, tumours were harvested to evaluate pimonidazole hypoxia, DNA damage (γH2AX), expression of oxidoreductases. RESULTS: CP-506 treatment significantly increased local control rate after SD in FaDu, 62% vs. 27% (p = 0.024). In UT-SCC-5, this effect was not curative and only marginally significant. CP-506 induced significant DNA damage in FaDu (p = 0.009) but not in UT- SCC-5. Hypoxic volume (HV) was significantly smaller (p = 0.038) after pretreatment with CP-506 as compared to vehicle in FaDu but not in less responsive UT-SCC-5. Adding CP-506 to fractionated radiotherapy in FaDu did not result in significant benefit. CONCLUSION: The results support the use of CP-506 in combination with radiation in particular using hypofractionation schedules in hypoxic tumours. The magnitude of effect depends on the tumour model, therefore it is expected that applying appropriate patient stratification strategy will further enhance the benefit of CP-506 treatment for cancer patients. A phase I-IIA clinical trial of CP-506 in monotherapy or in combination with carboplatin or a checkpoint inhibitor has been approved (NCT04954599).

Combining Deep Learning and Handcrafted Radiomics for Classification of Suspicious Lesions on Contrast-enhanced Mammograms.

Background Handcrafted radiomics and deep learning (DL) models individually achieve good performance in lesion classification (benign vs malignant) on contrast-enhanced mammography (CEM) images. Purpose To develop a comprehensive machine learning tool able to fully automatically identify, segment, and classify breast lesions on the basis of CEM images in recall patients. Materials and Methods CEM images and clinical data were retrospectively collected between 2013 and 2018 for 1601 recall patients at Maastricht UMC+ and 283 patients at Gustave Roussy Institute for external validation. Lesions with a known status (malignant or benign) were delineated by a research assistant overseen by an expert breast radiologist. Preprocessed low-energy and recombined images were used to train a DL model for automatic lesion identification, segmentation, and classification. A handcrafted radiomics model was also trained to classify both human- and DL-segmented lesions. Sensitivity for identification and the area under the receiver operating characteristic curve (AUC) for classification were compared between individual and combined models at the image and patient levels. Results After the exclusion of patients without suspicious lesions, the total number of patients included in the training, test, and validation data sets were 850 (mean age, 63 years ± 8 [SD]), 212 (62 years ± 8), and 279 (55 years ± 12), respectively. In the external data set, lesion identification sensitivity was 90% and 99% at the image and patient level, respectively, and the mean Dice coefficient was 0.71 and 0.80 at the image and patient level, respectively. Using manual segmentations, the combined DL and handcrafted radiomics classification model achieved the highest AUC (0.88 [95% CI: 0.86, 0.91]) (P < .05 except compared with DL, handcrafted radiomics, and clinical features model, where P = .90). Using DL-generated segmentations, the combined DL and handcrafted radiomics model showed the highest AUC (0.95 [95% CI: 0.94, 0.96]) (P < .05). Conclusion The DL model accurately identified and delineated suspicious lesions on CEM images, and the combined output of the DL and handcrafted radiomics models achieved good diagnostic performance. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Bahl and Do in this issue.

Predicting the Tumour Response to Radiation by Modelling the Five Rs of Radiotherapy Using PET Images.

Despite the intensive use of radiotherapy in clinical practice, its effectiveness depends on several factors. Several studies showed that the tumour response to radiation differs from one patient to another. The non-uniform response of the tumour is mainly caused by multiple interactions between the tumour microenvironment and healthy cells. To understand these interactions, five major biologic concepts called the "5 Rs" have emerged. These concepts include reoxygenation, DNA damage repair, cell cycle redistribution, cellular radiosensitivity and cellular repopulation. In this study, we used a multi-scale model, which included the five Rs of radiotherapy, to predict the effects of radiation on tumour growth. In this model, the oxygen level was varied in both time and space. When radiotherapy was given, the sensitivity of cells depending on their location in the cell cycle was taken in account. This model also considered the repair of cells by giving a different probability of survival after radiation for tumour and normal cells. Here, we developed four fractionation protocol schemes. We used simulated and positron emission tomography (PET) imaging with the hypoxia tracer 18F-flortanidazole (18F-HX4) images as input data of our model. In addition, tumour control probability curves were simulated. The result showed the evolution of tumours and normal cells. The increase in the cell number after radiation was seen in both normal and malignant cells, which proves that repopulation was included in this model. The proposed model predicts the tumour response to radiation and forms the basis for a more patient-specific clinical tool where related biological data will be included.

External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients.

The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32-1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.

External validation of 18 F-FDG PET-based radiomic models on identification of residual oesophageal cancer after neoadjuvant chemoradiotherapy.

OBJECTIVES: Detection of residual oesophageal cancer after neoadjuvant chemoradiotherapy (nCRT) is important to guide treatment decisions regarding standard oesophagectomy or active surveillance. The aim was to validate previously developed 18 F-FDG PET-based radiomic models to detect residual local tumour and to repeat model development (i.e. 'model extension') in case of poor generalisability. METHODS: This was a retrospective cohort study in patients collected from a prospective multicentre study in four Dutch institutes. Patients underwent nCRT followed by oesophagectomy between 2013 and 2019. Outcome was tumour regression grade (TRG) 1 (0% tumour) versus TRG 2-3-4 (≥1% tumour). Scans were acquired according to standardised protocols. Discrimination and calibration were assessed for the published models with optimism-corrected AUCs >0.77. For model extension, the development and external validation cohorts were combined. RESULTS: Baseline characteristics of the 189 patients included [median age 66 years (interquartile range 60-71), 158/189 male (84%), 40/189 TRG 1 (21%) and 149/189 (79%) TRG 2-3-4] were comparable to the development cohort. The model including cT stage plus the feature 'sum entropy' had best discriminative performance in external validation (AUC 0.64, 95% confidence interval 0.55-0.73), with a calibration slope and intercept of 0.16 and 0.48 respectively. An extended bootstrapped LASSO model yielded an AUC of 0.65 for TRG 2-3-4 detection. CONCLUSION: The high predictive performance of the published radiomic models could not be replicated. The extended model had moderate discriminative ability. The investigated radiomic models appeared inaccurate to detect local residual oesophageal tumour and cannot be used as an adjunct tool for clinical decision-making in patients.

From Head and Neck Tumour and Lymph Node Segmentation to Survival Prediction on PET/CT: An End-to-End Framework Featuring Uncertainty, Fairness, and Multi-Region Multi-Modal Radiomics.

Automatic delineation and detection of the primary tumour (GTVp) and lymph nodes (GTVn) using PET and CT in head and neck cancer and recurrence-free survival prediction can be useful for diagnosis and patient risk stratification. We used data from nine different centres, with 524 and 359 cases used for training and testing, respectively. We utilised posterior sampling of the weight space in the proposed segmentation model to estimate the uncertainty for false positive reduction. We explored the prognostic potential of radiomics features extracted from the predicted GTVp and GTVn in PET and CT for recurrence-free survival prediction and used SHAP analysis for explainability. We evaluated the bias of models with respect to age, gender, chemotherapy, HPV status, and lesion size. We achieved an aggregate Dice score of 0.774 and 0.760 on the test set for GTVp and GTVn, respectively. We observed a per image false positive reduction of 19.5% and 7.14% using the uncertainty threshold for GTVp and GTVn, respectively. Radiomics features extracted from GTVn in PET and from both GTVp and GTVn in CT are the most prognostic, and our model achieves a C-index of 0.672 on the test set. Our framework incorporates uncertainty estimation, fairness, and explainability, demonstrating the potential for accurate detection and risk stratification.

Automated detection and delineation of lymph nodes in haematoxylin & eosin stained digitised slides.

Treatment of patients with oesophageal and gastric cancer (OeGC) is guided by disease stage, patient performance status and preferences. Lymph node (LN) status is one of the strongest prognostic factors for OeGC patients. However, survival varies between patients with the same disease stage and LN status. We recently showed that LN size from patients with OeGC might also have prognostic value, thus making delineations of LNs essential for size estimation and the extraction of other imaging biomarkers. We hypothesized that a machine learning workflow is able to: (1) find digital H&E stained slides containing LNs, (2) create a scoring system providing degrees of certainty for the results, and (3) delineate LNs in those images. To train and validate the pipeline, we used 1695 H&E slides from the OE02 trial. The dataset was divided into training (80%) and validation (20%). The model was tested on an external dataset of 826 H&E slides from the OE05 trial. U-Net architecture was used to generate prediction maps from which predefined features were extracted. These features were subsequently used to train an XGBoost model to determine if a region truly contained a LN. With our innovative method, the balanced accuracies of the LN detection were 0.93 on the validation dataset (0.83 on the test dataset) compared to 0.81 (0.81) on the validation (test) datasets when using the standard method of thresholding U-Net predictions to arrive at a binary mask. Our method allowed for the creation of an "uncertain" category, and partly limited false-positive predictions on the external dataset. The mean Dice score was 0.73 (0.60) per-image and 0.66 (0.48) per-LN for the validation (test) datasets. Our pipeline detects images with LNs more accurately than conventional methods, and high-throughput delineation of LNs can facilitate future LN content analyses of large datasets.

Deep learning based identification of bone scintigraphies containing metastatic bone disease foci.

PURPOSE: Metastatic bone disease (MBD) is the most common form of metastases, most frequently deriving from prostate cancer. MBD is screened with bone scintigraphy (BS), which have high sensitivity but low specificity for the diagnosis of MBD, often requiring further investigations. Deep learning (DL) - a machine learning technique designed to mimic human neuronal interactions- has shown promise in the field of medical imaging analysis for different purposes, including segmentation and classification of lesions. In this study, we aim to develop a DL algorithm that can classify areas of increased uptake on bone scintigraphy scans. METHODS: We collected 2365 BS from three European medical centres. The model was trained and validated on 1203 and 164 BS scans respectively. Furthermore we evaluated its performance on an external testing set composed of 998 BS scans. We further aimed to enhance the explainability of our developed algorithm, using activation maps. We compared the performance of our algorithm to that of 6 nuclear medicine physicians. RESULTS: The developed DL based algorithm is able to detect MBD on BSs, with high specificity and sensitivity (0.80 and 0.82 respectively on the external test set), in a shorter time compared to the nuclear medicine physicians (2.5 min for AI and 30 min for nuclear medicine physicians to classify 134 BSs). Further prospective validation is required before the algorithm can be used in the clinic.