Artificial intelligence-based, semi-automated segmentation for the extraction of ultrasound-derived radiomics features in breast cancer: a prospective multicenter study.

PURPOSE: To investigate the feasibility of an artificial intelligence (AI)-based semi-automated segmentation for the extraction of ultrasound (US)-derived radiomics features in the characterization of focal breast lesions (FBLs). MATERIAL AND METHODS: Two expert radiologists classified according to US BI-RADS criteria 352 FBLs detected in 352 patients (237 at Center A and 115 at Center B). An AI-based semi-automated segmentation was used to build a machine learning (ML) model on the basis of B-mode US of 237 images (center A) and then validated on an external cohort of B-mode US images of 115 patients (Center B). RESULTS: A total of 202 of 352 (57.4%) FBLs were benign, and 150 of 352 (42.6%) were malignant. The AI-based semi-automated segmentation achieved a success rate of 95.7% for one reviewer and 96% for the other, without significant difference (p = 0.839). A total of 15 (4.3%) and 14 (4%) of 352 semi-automated segmentations were not accepted due to posterior acoustic shadowing at B-Mode US and 13 and 10 of them corresponded to malignant lesions, respectively. In the validation cohort, the characterization made by the expert radiologist yielded values of sensitivity, specificity, PPV and NPV of 0.933, 0.9, 0.857, 0.955, respectively. The ML model obtained values of sensitivity, specificity, PPV and NPV of 0.544, 0.6, 0.416, 0.628, respectively. The combined assessment of radiologists and ML model yielded values of sensitivity, specificity, PPV and NPV of 0.756, 0.928, 0.872, 0.855, respectively. CONCLUSION: AI-based semi-automated segmentation is feasible, allowing an instantaneous and reproducible extraction of US-derived radiomics features of FBLs. The combination of radiomics and US BI-RADS classification led to a potential decrease of unnecessary biopsy but at the expense of a not negligible increase of potentially missed cancers.

Time series radiomics for the prediction of prostate cancer progression in patients on active surveillance.

Serial MRI is an essential assessment tool in prostate cancer (PCa) patients enrolled on active surveillance (AS). However, it has only moderate sensitivity for predicting histopathological tumour progression at follow-up, which is in part due to the subjective nature of its clinical reporting and variation among centres and readers. In this study, we used a long short-term memory (LSTM) recurrent neural network (RNN) to develop a time series radiomics (TSR) predictive model that analysed longitudinal changes in tumour-derived radiomic features across 297 scans from 76 AS patients, 28 with histopathological PCa progression and 48 with stable disease. Using leave-one-out cross-validation (LOOCV), we found that an LSTM-based model combining TSR and serial PSA density (AUC 0.86 [95% CI: 0.78-0.94]) significantly outperformed a model combining conventional delta-radiomics and delta-PSA density (0.75 [0.64-0.87]; p = 0.048) and achieved comparable performance to expert-performed serial MRI analysis using the Prostate Cancer Radiologic Estimation of Change in Sequential Evaluation (PRECISE) scoring system (0.84 [0.76-0.93]; p = 0.710). The proposed TSR framework, therefore, offers a feasible quantitative tool for standardising serial MRI assessment in PCa AS. It also presents a novel methodological approach to serial image analysis that can be used to support clinical decision-making in multiple scenarios, from continuous disease monitoring to treatment response evaluation. KEY POINTS: •LSTM RNN can be used to predict the outcome of PCa AS using time series changes in tumour-derived radiomic features and PSA density. •Using all available TSR features and serial PSA density yields a significantly better predictive performance compared to using just two time points within the delta-radiomics framework. •The concept of TSR can be applied to other clinical scenarios involving serial imaging, setting out a new field in AI-driven radiology research.

Calibrating the Dice Loss to Handle Neural Network Overconfidence for Biomedical Image Segmentation.

The Dice similarity coefficient (DSC) is both a widely used metric and loss function for biomedical image segmentation due to its robustness to class imbalance. However, it is well known that the DSC loss is poorly calibrated, resulting in overconfident predictions that cannot be usefully interpreted in biomedical and clinical practice. Performance is often the only metric used to evaluate segmentations produced by deep neural networks, and calibration is often neglected. However, calibration is important for translation into biomedical and clinical practice, providing crucial contextual information to model predictions for interpretation by scientists and clinicians. In this study, we provide a simple yet effective extension of the DSC loss, named the DSC++ loss, that selectively modulates the penalty associated with overconfident, incorrect predictions. As a standalone loss function, the DSC++ loss achieves significantly improved calibration over the conventional DSC loss across six well-validated open-source biomedical imaging datasets, including both 2D binary and 3D multi-class segmentation tasks. Similarly, we observe significantly improved calibration when integrating the DSC++ loss into four DSC-based loss functions. Finally, we use softmax thresholding to illustrate that well calibrated outputs enable tailoring of recall-precision bias, which is an important post-processing technique to adapt the model predictions to suit the biomedical or clinical task. The DSC++ loss overcomes the major limitation of the DSC loss, providing a suitable loss function for training deep learning segmentation models for use in biomedical and clinical practice. Source code is available at https://github.com/mlyg/DicePlusPlus .

FiCoS: A fine-grained and coarse-grained GPU-powered deterministic simulator for biochemical networks.

Mathematical models of biochemical networks can largely facilitate the comprehension of the mechanisms at the basis of cellular processes, as well as the formulation of hypotheses that can be tested by means of targeted laboratory experiments. However, two issues might hamper the achievement of fruitful outcomes. On the one hand, detailed mechanistic models can involve hundreds or thousands of molecular species and their intermediate complexes, as well as hundreds or thousands of chemical reactions, a situation generally occurring in rule-based modeling. On the other hand, the computational analysis of a model typically requires the execution of a large number of simulations for its calibration, or to test the effect of perturbations. As a consequence, the computational capabilities of modern Central Processing Units can be easily overtaken, possibly making the modeling of biochemical networks a worthless or ineffective effort. To the aim of overcoming the limitations of the current state-of-the-art simulation approaches, we present in this paper FiCoS, a novel "black-box" deterministic simulator that effectively realizes both a fine-grained and a coarse-grained parallelization on Graphics Processing Units. In particular, FiCoS exploits two different integration methods, namely, the Dormand-Prince and the Radau IIA, to efficiently solve both non-stiff and stiff systems of coupled Ordinary Differential Equations. We tested the performance of FiCoS against different deterministic simulators, by considering models of increasing size and by running analyses with increasing computational demands. FiCoS was able to dramatically speedup the computations up to 855×, showing to be a promising solution for the simulation and analysis of large-scale models of complex biological processes.

Comparative performance of MRI-derived PRECISE scores and delta-radiomics models for the prediction of prostate cancer progression in patients on active surveillance.

OBJECTIVES: To compare the performance of the PRECISE scoring system against several MRI-derived delta-radiomics models for predicting histopathological prostate cancer (PCa) progression in patients on active surveillance (AS). METHODS: The study included AS patients with biopsy-proven PCa with a minimum follow-up of 2 years and at least one repeat targeted biopsy. Histopathological progression was defined as grade group progression from diagnostic biopsy. The control group included patients with both radiologically and histopathologically stable disease. PRECISE scores were applied prospectively by four uro-radiologists with 5-16 years' experience. T2WI- and ADC-derived delta-radiomics features were computed using baseline and latest available MRI scans, with the predictive modelling performed using the parenclitic networks (PN), least absolute shrinkage and selection operator (LASSO) logistic regression, and random forests (RF) algorithms. Standard measures of discrimination and areas under the ROC curve (AUCs) were calculated, with AUCs compared using DeLong's test. RESULTS: The study included 64 patients (27 progressors and 37 non-progressors) with a median follow-up of 46 months. PRECISE scores had the highest specificity (94.7%) and positive predictive value (90.9%), whilst RF had the highest sensitivity (92.6%) and negative predictive value (92.6%) for predicting disease progression. The AUC for PRECISE (84.4%) was non-significantly higher than AUCs of 81.5%, 78.0%, and 80.9% for PN, LASSO regression, and RF, respectively (p = 0.64, 0.43, and 0.57, respectively). No significant differences were observed between AUCs of the three delta-radiomics models (p-value range 0.34-0.77). CONCLUSIONS: PRECISE and delta-radiomics models achieved comparably good performance for predicting PCa progression in AS patients. KEY POINTS: • The observed high specificity and PPV of PRECISE are complemented by the high sensitivity and NPV of delta-radiomics, suggesting a possible synergy between the two image assessment approaches. • The comparable performance of delta-radiomics to PRECISE scores applied by expert readers highlights the prospective use of the former as an objective and standardisable quantitative tool for MRI-guided AS follow-up. • The marginally superior performance of parenclitic networks compared to conventional machine learning algorithms warrants its further use in radiomics research.

MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction.

BACKGROUND: Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a 2D/3D single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer's disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with either disease stages, various (i.e., more than two types of) diseases, or multi-sequence magnetic resonance imaging (MRI) scans. RESULTS: We propose unsupervised medical anomaly detection generative adversarial network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 [Formula: see text] loss-trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones-reconstructs unseen healthy/abnormal scans; (Diagnosis) Average [Formula: see text] loss per scan discriminates them, comparing the ground truth/reconstructed slices. For training, we use two different datasets composed of 1133 healthy T1-weighted (T1) and 135 healthy contrast-enhanced T1 (T1c) brain MRI scans for detecting AD and brain metastases/various diseases, respectively. Our self-attention MADGAN can detect AD on T1 scans at a very early stage, mild cognitive impairment (MCI), with area under the curve (AUC) 0.727, and AD at a late stage with AUC 0.894, while detecting brain metastases on T1c scans with AUC 0.921. CONCLUSIONS: Similar to physicians' way of performing a diagnosis, using massive healthy training data, our first multiple MRI slice reconstruction approach, MADGAN, can reliably predict the next 3 slices from the previous 3 ones only for unseen healthy images. As the first unsupervised various disease diagnosis, MADGAN can reliably detect the accumulation of subtle anatomical anomalies and hyper-intense enhancing lesions, such as (especially late-stage) AD and brain metastases on multi-sequence MRI scans.

Ultrasound-guided targeted biopsies of CT-based radiomic tumour habitats: technical development and initial experience in metastatic ovarian cancer.

PURPOSE: To develop a precision tissue sampling technique that uses computed tomography (CT)-based radiomic tumour habitats for ultrasound (US)-guided targeted biopsies that can be integrated in the clinical workflow of patients with high-grade serous ovarian cancer (HGSOC). METHODS: Six patients with suspected HGSOC scheduled for US-guided biopsy before starting neoadjuvant chemotherapy were included in this prospective study from September 2019 to February 2020. The tumour segmentation was performed manually on the pre-biopsy contrast-enhanced CT scan. Spatial radiomic maps were used to identify tumour areas with similar or distinct radiomic patterns, and tumour habitats were identified using the Gaussian mixture modelling. CT images with superimposed habitat maps were co-registered with US images by means of a landmark-based rigid registration method for US-guided targeted biopsies. The dice similarity coefficient (DSC) was used to assess the tumour-specific CT/US fusion accuracy. RESULTS: We successfully co-registered CT-based radiomic tumour habitats with US images in all patients. The median time between CT scan and biopsy was 21 days (range 7-30 days). The median DSC for tumour-specific CT/US fusion accuracy was 0.53 (range 0.79 to 0.37). The CT/US fusion accuracy was high for the larger pelvic tumours (DSC: 0.76-0.79) while it was lower for the smaller omental metastases (DSC: 0.37-0.53). CONCLUSION: We developed a precision tissue sampling technique that uses radiomic habitats to guide in vivo biopsies using CT/US fusion and that can be seamlessly integrated in the clinical routine for patients with HGSOC. KEY POINTS: • We developed a prevision tissue sampling technique that co-registers CT-based radiomics-based tumour habitats with US images. • The CT/US fusion accuracy was high for the larger pelvic tumours (DSC: 0.76-0.79) while it was lower for the smaller omental metastases (DSC: 0.37-0.53).

CT texture-based radiomics analysis of carotid arteries identifies vulnerable patients: a preliminary outcome study.

PURPOSE: To assess the potential role of computed tomography (CT) texture analysis (CTTA) in identifying vulnerable patients with carotid artery atherosclerosis. METHODS: In this case-control pilot study, 12 patients with carotid atherosclerosis and a subsequent history of transient ischemic attack or stroke were age and sex matched with 12 control cases with asymptomatic carotid atherosclerosis (follow-up time 103.58 ± 9.2 months). CTTA was performed using a commercially available research software package (TexRAD) by an operator blinded to clinical data. CTTA comprised a filtration-histogram technique to extract features at different scales corresponding to spatial scale filter (fine = 2 mm, medium = 3 mm, coarse = 4 mm), followed by quantification using histogram-based statistical parameters: mean, kurtosis, skewness, entropy, standard deviation, and mean value of positive pixels. A single axial slice was selected to best represent the largest cross-section of the carotid bifurcation or the greatest degree of stenosis, in presence of an atherosclerotic plaque, on each side. RESULTS: CTTA revealed a statistically significant difference in skewness between symptomatic and asymptomatic patients at the medium (0.22 ± 0.35 vs - 0.18 ± 0.39, p < 0.001) and coarse (0.23 ± 0.22 vs 0.03 ± 0.29, p = 0.003) texture scales. At the fine-texture scale, skewness (0.20 ± 0.59 vs - 0.18 ± 0.58, p = 0.009) and standard deviation (366.11 ± 117.19 vs 300.37 ± 82.51, p = 0.03) were significant before correction. CONCLUSION: Our pilot study highlights the potential of CTTA to identify vulnerable patients in stroke and TIA. CT texture may have the potential to act as a novel risk stratification tool in patients with carotid atherosclerosis.

Recent advances of HCI in decision-making tasks for optimized clinical workflows and precision medicine.

The ever-increasing amount of biomedical data is enabling new large-scale studies, even though ad hoc computational solutions are required. The most recent Machine Learning (ML) and Artificial Intelligence (AI) techniques have been achieving outstanding performance and an important impact in clinical research, aiming at precision medicine, as well as improving healthcare workflows. However, the inherent heterogeneity and uncertainty in the healthcare information sources pose new compelling challenges for clinicians in their decision-making tasks. Only the proper combination of AI and human intelligence capabilities, by explicitly taking into account effective and safe interaction paradigms, can permit the delivery of care that outperforms what either can do separately. Therefore, Human-Computer Interaction (HCI) plays a crucial role in the design of software oriented to decision-making in medicine. In this work, we systematically review and discuss several research fields strictly linked to HCI and clinical decision-making, by subdividing the articles into six themes, namely: Interfaces, Visualization, Electronic Health Records, Devices, Usability, and Clinical Decision Support Systems. However, these articles typically present overlaps among the themes, revealing that HCI inter-connects multiple topics. With the goal of focusing on HCI and design aspects, the articles under consideration were grouped into four clusters. The advances in AI can effectively support the physicians' cognitive processes, which certainly play a central role in decision-making tasks because the human mental behavior cannot be completely emulated and captured; the human mind might solve a complex problem even without a statistically significant amount of data by relying upon domain knowledge. For this reason, technology must focus on interactive solutions for supporting the physicians effectively in their daily activities, by exploiting their unique knowledge and evidence-based reasoning, as well as improving the various aspects highlighted in this review.

GenHap: a novel computational method based on genetic algorithms for haplotype assembly.

BACKGROUND: In order to fully characterize the genome of an individual, the reconstruction of the two distinct copies of each chromosome, called haplotypes, is essential. The computational problem of inferring the full haplotype of a cell starting from read sequencing data is known as haplotype assembly, and consists in assigning all heterozygous Single Nucleotide Polymorphisms (SNPs) to exactly one of the two chromosomes. Indeed, the knowledge of complete haplotypes is generally more informative than analyzing single SNPs and plays a fundamental role in many medical applications. RESULTS: To reconstruct the two haplotypes, we addressed the weighted Minimum Error Correction (wMEC) problem, which is a successful approach for haplotype assembly. This NP-hard problem consists in computing the two haplotypes that partition the sequencing reads into two disjoint sub-sets, with the least number of corrections to the SNP values. To this aim, we propose here GenHap, a novel computational method for haplotype assembly based on Genetic Algorithms, yielding optimal solutions by means of a global search process. In order to evaluate the effectiveness of our approach, we run GenHap on two synthetic (yet realistic) datasets, based on the Roche/454 and PacBio RS II sequencing technologies. We compared the performance of GenHap against HapCol, an efficient state-of-the-art algorithm for haplotype phasing. Our results show that GenHap always obtains high accuracy solutions (in terms of haplotype error rate), and is up to 4× faster than HapCol in the case of Roche/454 instances and up to 20× faster when compared on the PacBio RS II dataset. Finally, we assessed the performance of GenHap on two different real datasets. CONCLUSIONS: Future-generation sequencing technologies, producing longer reads with higher coverage, can highly benefit from GenHap, thanks to its capability of efficiently solving large instances of the haplotype assembly problem. Moreover, the optimization approach proposed in GenHap can be extended to the study of allele-specific genomic features, such as expression, methylation and chromatin conformation, by exploiting multi-objective optimization techniques. The source code and the full documentation are available at the following GitHub repository: https://github.com/andrea-tango/GenHap .

A framework for data-driven adaptive GUI generation based on DICOM.

Computer applications for diagnostic medical imaging provide generally a wide range of tools to support physicians in their daily diagnosis activities. Unfortunately, some functionalities are specialized for specific diseases or imaging modalities, while other ones are useless for the images under investigation. Nevertheless, the corresponding Graphical User Interface (GUI) widgets are still present on the screen reducing the image visualization area. As a consequence, the physician may be affected by cognitive overload and visual stress causing a degradation of performances, mainly due to unuseful widgets. In clinical environments, a GUI must represent a sequence of steps for image investigation following a well-defined workflow. This paper proposes a software framework aimed at addressing the issues outlined before. Specifically, we designed a DICOM based mechanism of data-driven GUI generation, referring to the examined body part and imaging modality as well as to the medical image analysis task to perform. In this way, the self-configuring GUI is generated on-the-fly, so that just specific functionalities are active according to the current clinical scenario. Such a solution provides also a tight integration with the DICOM standard, which considers various aspects of the technology in medicine but does not address GUI specification issues. The proposed workflow is designed for diagnostic workstations with a local file system on an interchange media acting inside or outside the hospital ward. Accordingly, the DICOMDIR conceptual data model, defined by a hierarchical structure, is exploited and extended to include the GUI information thanks to a new Information Object Module (IOM), which reuses the DICOM information model. The proposed framework exploits the DICOM standard representing an enabling technology for an auto-consistent solution in medical diagnostic applications. In this paper we present a detailed description of the framework, its software design, and a proof-of-concept implementation as a suitable plug-in of the OsiriX imaging software.

Robustness and classification capabilities of MRI radiomic features in identifying carotid plaque vulnerability.

OBJECTIVES: To assess how radiomic features may be combined with plaque morphological and compositional features identified by multi-contrast MRI to improve upon conventional risk assessment models in determining culprit carotid artery lesions. METHODS: Fifty-five patients (mean age: 62.6; 35 males) with bilateral carotid stenosis who experienced transient ischaemic attack (TIA) or stroke were included from the CARE-II multi-centre carotid imaging trial (ClinicalTrials.gov Identifier: NCT02017756). They underwent MRI within 2 weeks of the event. Classification capability in distinguishing culprit lesions was assessed by machine learning. Repeatability and reproducibility of the results were investigated by assessing the robustness of the radiomic features. RESULTS: Radiomics combined with a relatively conventional plaque morphological and compositional metric-based model provided incremental value over a conventional model alone (area under curve [AUC], 0.819 ± 0.002 vs 0.689 ± 0.019, respectively, P = .014). The radiomic model alone also provided value over the conventional model (AUC, 0.805 ± 0.003 vs 0.689 ± 0.019, respectively, P = .031). T2-weighted imaging-based radiomic features had consistently higher robustness and classification capabilities compared with T1-weighted images. Higher-dimensional radiomic features outperformed first-order features. Grey Level Co-occurrence Matrix, Grey Level Dependence Matrix, and Grey Level Size Zone Matrix sub-types were particularly useful in identifying textures which could detect vulnerable lesions. CONCLUSIONS: The combination of MRI-based radiomic features and lesion morphological and compositional parameters provided added value to the reference-standard risk assessment for carotid atherosclerosis. This may improve future risk stratification for individuals at risk of major adverse ischaemic cerebrovascular events. ADVANCES IN KNOWLEDGE: The clinical relevance of this work is that it addresses the need for a more comprehensive method of risk assessment for patients at risk of ischaemic stroke, beyond conventional stenosis measurement. This paper shows that in the case of carotid stroke, high-dimensional radiomics features can improve classification capabilities compared with stenosis measurement alone.

IMPA-Net: Interpretable Multi-Part Attention Network for Trustworthy Brain Tumor Classification from MRI.

Deep learning (DL) networks have shown attractive performance in medical image processing tasks such as brain tumor classification. However, they are often criticized as mysterious "black boxes". The opaqueness of the model and the reasoning process make it difficult for health workers to decide whether to trust the prediction outcomes. In this study, we develop an interpretable multi-part attention network (IMPA-Net) for brain tumor classification to enhance the interpretability and trustworthiness of classification outcomes. The proposed model not only predicts the tumor grade but also provides a global explanation for the model interpretability and a local explanation as justification for the proffered prediction. Global explanation is represented as a group of feature patterns that the model learns to distinguish high-grade glioma (HGG) and low-grade glioma (LGG) classes. Local explanation interprets the reasoning process of an individual prediction by calculating the similarity between the prototypical parts of the image and a group of pre-learned task-related features. Experiments conducted on the BraTS2017 dataset demonstrate that IMPA-Net is a verifiable model for the classification task. A percentage of 86% of feature patterns were assessed by two radiologists to be valid for representing task-relevant medical features. The model shows a classification accuracy of 92.12%, of which 81.17% were evaluated as trustworthy based on local explanations. Our interpretable model is a trustworthy model that can be used for decision aids for glioma classification. Compared with black-box CNNs, it allows health workers and patients to understand the reasoning process and trust the prediction outcomes.

Multiparametric MRI dataset for susceptibility-based radiomic feature extraction and analysis.

Multiple sclerosis (MS) is a progressive demyelinating disease impacting the central nervous system. Conventional Magnetic Resonance Imaging (MRI) techniques (e.g., T2w images) help diagnose MS, although they sometimes reveal non-specific lesions. Quantitative MRI techniques are capable of quantifying imaging biomarkers in vivo, offering the potential to identify specific signs related to pre-clinical inflammation. Among those techniques, Quantitative Susceptibility Mapping (QSM) is particularly useful for studying processes that influence the magnetic properties of brain tissue, such as alterations in myelin concentration. Because of its intrinsic quantitative nature, it is particularly well-suited to be analyzed through radiomics, including techniques that extract a high number of complex and multi-dimensional features from radiological images. The dataset presented in this work provides information about normal-appearing white matter (NAWM) in a cohort of MS patients and healthy controls. It includes QSM-based radiomic features from NAWM and its tracts, and MR sequences necessary to implement the pipeline: T1w, T2w, QSM, DWI. The workflow is outlined in this article, along with an application showing feature reliability assessment.

Radiomics and Radiogenomics of Ovarian Cancer: Implications for Treatment Monitoring and Clinical Management.

Ovarian cancer, one of the deadliest gynecologic malignancies, is characterized by high intra- and inter-site genomic and phenotypic heterogeneity. The traditional information provided by the conventional interpretation of diagnostic imaging studies cannot adequately represent this heterogeneity. Radiomics analyses can capture the complex patterns related to the microstructure of the tissues and provide quantitative information about them. This review outlines how radiomics and its integration with other quantitative biological information, like genomics and proteomics, can impact the clinical management of ovarian cancer.

Calibrating ensembles for scalable uncertainty quantification in deep learning-based medical image segmentation.

Uncertainty quantification in automated image analysis is highly desired in many applications. Typically, machine learning models in classification or segmentation are only developed to provide binary answers; however, quantifying the uncertainty of the models can play a critical role for example in active learning or machine human interaction. Uncertainty quantification is especially difficult when using deep learning-based models, which are the state-of-the-art in many imaging applications. The current uncertainty quantification approaches do not scale well in high-dimensional real-world problems. Scalable solutions often rely on classical techniques, such as dropout, during inference or training ensembles of identical models with different random seeds to obtain a posterior distribution. In this paper, we present the following contributions. First, we show that the classical approaches fail to approximate the classification probability. Second, we propose a scalable and intuitive framework for uncertainty quantification in medical image segmentation that yields measurements that approximate the classification probability. Third, we suggest the usage of k-fold cross-validation to overcome the need for held out calibration data. Lastly, we motivate the adoption of our method in active learning, creating pseudo-labels to learn from unlabeled images and human-machine collaboration.

Assessing robustness of quantitative susceptibility-based MRI radiomic features in patients with multiple sclerosis.

Multiple Sclerosis (MS) is an autoimmune demyelinating disease characterised by changes in iron and myelin content. These biomarkers are detectable by Quantitative Susceptibility Mapping (QSM), an advanced Magnetic Resonance Imaging technique detecting magnetic properties. When analysed with radiomic techniques that exploit its intrinsic quantitative nature, QSM may furnish biomarkers to facilitate early diagnosis of MS and timely assessment of progression. In this work, we explore the robustness of QSM radiomic features by varying the number of grey levels (GLs) and echo times (TEs), in a sample of healthy controls and patients with MS. We analysed the white matter in total and within six clinically relevant tracts, including the cortico-spinal tract and the optic radiation. After optimising the number of GLs (n = 64), at least 65% of features were robust for each Volume of Interest (VOI), with no difference (p > .05) between left and right hemispheres. Different outcomes in feature robustness among the VOIs depend on their characteristics, such as volume and variance of susceptibility values. This study validated the processing pipeline for robustness analysis and established the reliability of QSM-based radiomics features against GLs and TEs. Our results provide important insights for future radiomics studies using QSM in clinical applications.

Epicardial and thoracic subcutaneous fat texture analysis in patients undergoing cardiac CT.

Introduction: The aim of our study was to evaluate the feasibility of texture analysis of epicardial fat (EF) and thoracic subcutaneous fat (TSF) in patients undergoing cardiac CT (CCT). Materials and methods: We compared a consecutive population of 30 patients with BMI ≤25 kg/m2 (Group A, 60.6 ± 13.7 years) with a control population of 30 patients with BMI >25 kg/m2 (Group B, 63.3 ± 11 years). A dedicated computer application for quantification of EF and a texture analysis application for the study of EF and TSF were employed. Results: The volume of EF was higher in group B (mean 116.1 cm3 vs. 86.3 cm3, p = 0.014), despite no differences were found neither in terms of mean density (-69.5 ± 5 HU vs. -68 ± 5 HU, p = 0.28), nor in terms of quartiles distribution (Q1, p = 0.83; Q2, p = 0.22, Q3, p = 0.83, Q4, p = 0.34). The discriminating parameters of the histogram class were mean (p = 0.02), 0,1st (p = 0.001), 10th (p = 0.002), and 50th percentiles (p = 0.02). DifVarnc was the discriminating parameter of the co-occurrence matrix class (p = 0.007).The TSF thickness was 15 ± 6 mm in group A and 19.5 ± 5 mm in group B (p = 0.003). The TSF had a mean density of -97 ± 19 HU in group A and -95.8 ± 19 HU in group B (p = 0.75). The discriminating parameters of texture analysis were 10th (p = 0.03), 50th (p = 0.01), 90th percentiles (p = 0.04), S(0,1)SumAverg (p = 0.02), S(1,-1)SumOfSqs (p = 0.02), S(3,0)Contrast (p = 0.03), S(3,0)SumAverg (p = 0.02), S(4,0)SumAverg (p = 0.04), Horzl_RLNonUni (p = 0.02), and Vertl_LngREmph (p = 0.0005). Conclusions: Texture analysis provides distinctive radiomic parameters of EF and TSF. EF and TSF had different radiomic features as the BMI varies.

Lesion-specific 3D-printed moulds for image-guided tissue multi-sampling of ovarian tumours: A prospective pilot study.

Background: High-Grade Serous Ovarian Carcinoma (HGSOC) is the most prevalent and lethal subtype of ovarian cancer, but has a paucity of clinically-actionable biomarkers due to high degrees of multi-level heterogeneity. Radiogenomics markers have the potential to improve prediction of patient outcome and treatment response, but require accurate multimodal spatial registration between radiological imaging and histopathological tissue samples. Previously published co-registration work has not taken into account the anatomical, biological and clinical diversity of ovarian tumours. Methods: In this work, we developed a research pathway and an automated computational pipeline to produce lesion-specific three-dimensional (3D) printed moulds based on preoperative cross-sectional CT or MRI of pelvic lesions. Moulds were designed to allow tumour slicing in the anatomical axial plane to facilitate detailed spatial correlation of imaging and tissue-derived data. Code and design adaptations were made following each pilot case through an iterative refinement process. Results: Five patients with confirmed or suspected HGSOC who underwent debulking surgery between April and December 2021 were included in this prospective study. Tumour moulds were designed and 3D-printed for seven pelvic lesions, covering a range of tumour volumes (7 to 133 cm3) and compositions (cystic and solid proportions). The pilot cases informed innovations to improve specimen and subsequent slice orientation, through the use of 3D-printed tumour replicas and incorporation of a slice orientation slit in the mould design, respectively. The overall research pathway was compatible with implementation within the clinically determined timeframe and treatment pathway for each case, involving multidisciplinary clinical professionals from Radiology, Surgery, Oncology and Histopathology Departments. Conclusions: We developed and refined a computational pipeline that can model lesion-specific 3D-printed moulds from preoperative imaging for a variety of pelvic tumours. This framework can be used to guide comprehensive multi-sampling of tumour resection specimens.