Multimodal representations of biomedical knowledge from limited training whole slide images and reports using deep learning.

The increasing availability of biomedical data creates valuable resources for developing new deep learning algorithms to support experts, especially in domains where collecting large volumes of annotated data is not trivial. Biomedical data include several modalities containing complementary information, such as medical images and reports: images are often large and encode low-level information, while reports include a summarized high-level description of the findings identified within data and often only concerning a small part of the image. However, only a few methods allow to effectively link the visual content of images with the textual content of reports, preventing medical specialists from properly benefitting from the recent opportunities offered by deep learning models. This paper introduces a multimodal architecture creating a robust biomedical data representation encoding fine-grained text representations within image embeddings. The architecture aims to tackle data scarcity (combining supervised and self-supervised learning) and to create multimodal biomedical ontologies. The architecture is trained on over 6,000 colon whole slide Images (WSI), paired with the corresponding report, collected from two digital pathology workflows. The evaluation of the multimodal architecture involves three tasks: WSI classification (on data from pathology workflow and from public repositories), multimodal data retrieval, and linking between textual and visual concepts. Noticeably, the latter two tasks are available by architectural design without further training, showing that the multimodal architecture that can be adopted as a backbone to solve peculiar tasks. The multimodal data representation outperforms the unimodal one on the classification of colon WSIs and allows to halve the data needed to reach accurate performance, reducing the computational power required and thus the carbon footprint. The combination of images and reports exploiting self-supervised algorithms allows to mine databases without needing new annotations provided by experts, extracting new information. In particular, the multimodal visual ontology, linking semantic concepts to images, may pave the way to advancements in medicine and biomedical analysis domains, not limited to histopathology.

The ACROBAT 2022 challenge: Automatic registration of breast cancer tissue.

The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, and availability of large WSI datasets have revolutionised WSI analysis. Therefore, the current state-of-the-art in WSI registration is unclear. To address this, we conducted the ACROBAT challenge, based on the largest WSI registration dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. The challenge objective was to align WSIs of tissue that was stained with routine diagnostic immunohistochemistry to its H&E-stained counterpart. We compare the performance of eight WSI registration algorithms, including an investigation of the impact of different WSI properties and clinical covariates. We find that conceptually distinct WSI registration methods can lead to highly accurate registration performances and identify covariates that impact performances across methods. These results provide a comparison of the performance of current WSI registration methods and guide researchers in selecting and developing methods.

A systematic comparison of deep learning methods for Gleason grading and scoring.

Prostate cancer is the second most frequent cancer in men worldwide after lung cancer. Its diagnosis is based on the identification of the Gleason score that evaluates the abnormality of cells in glands through the analysis of the different Gleason patterns within tissue samples. The recent advancements in computational pathology, a domain aiming at developing algorithms to automatically analyze digitized histopathology images, lead to a large variety and availability of datasets and algorithms for Gleason grading and scoring. However, there is no clear consensus on which methods are best suited for each problem in relation to the characteristics of data and labels. This paper provides a systematic comparison on nine datasets with state-of-the-art training approaches for deep neural networks (including fully-supervised learning, weakly-supervised learning, semi-supervised learning, Additive-MIL, Attention-Based MIL, Dual-Stream MIL, TransMIL and CLAM) applied to Gleason grading and scoring tasks. The nine datasets are collected from pathology institutes and openly accessible repositories. The results show that the best methods for Gleason grading and Gleason scoring tasks are fully supervised learning and CLAM, respectively, guiding researchers to the best practice to adopt depending on the task to solve and the labels that are available.

RegWSI: Whole slide image registration using combined deep feature- and intensity-based methods: Winner of the ACROBAT 2023 challenge.

BACKGROUND AND OBJECTIVE: The automatic registration of differently stained whole slide images (WSIs) is crucial for improving diagnosis and prognosis by fusing complementary information emerging from different visible structures. It is also useful to quickly transfer annotations between consecutive or restained slides, thus significantly reducing the annotation time and associated costs. Nevertheless, the slide preparation is different for each stain and the tissue undergoes complex and large deformations. Therefore, a robust, efficient, and accurate registration method is highly desired by the scientific community and hospitals specializing in digital pathology. METHODS: We propose a two-step hybrid method consisting of (i) deep learning- and feature-based initial alignment algorithm, and (ii) intensity-based nonrigid registration using the instance optimization. The proposed method does not require any fine-tuning to a particular dataset and can be used directly for any desired tissue type and stain. The registration time is low, allowing one to perform efficient registration even for large datasets. The method was proposed for the ACROBAT 2023 challenge organized during the MICCAI 2023 conference and scored 1st place. The method is released as open-source software. RESULTS: The proposed method is evaluated using three open datasets: (i) Automatic Nonrigid Histological Image Registration Dataset (ANHIR), (ii) Automatic Registration of Breast Cancer Tissue Dataset (ACROBAT), and (iii) Hybrid Restained and Consecutive Histological Serial Sections Dataset (HyReCo). The target registration error (TRE) is used as the evaluation metric. We compare the proposed algorithm to other state-of-the-art solutions, showing considerable improvement. Additionally, we perform several ablation studies concerning the resolution used for registration and the initial alignment robustness and stability. The method achieves the most accurate results for the ACROBAT dataset, the cell-level registration accuracy for the restained slides from the HyReCo dataset, and is among the best methods evaluated on the ANHIR dataset. CONCLUSIONS: The article presents an automatic and robust registration method that outperforms other state-of-the-art solutions. The method does not require any fine-tuning to a particular dataset and can be used out-of-the-box for numerous types of microscopic images. The method is incorporated into the DeeperHistReg framework, allowing others to directly use it to register, transform, and save the WSIs at any desired pyramid level (resolution up to 220k x 220k). We provide free access to the software. The results are fully and easily reproducible. The proposed method is a significant contribution to improving the WSI registration quality, thus advancing the field of digital pathology.

The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights.

Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.

Artifact Augmentation for Learning-based Quality Control of Whole Slide Images.

The acquisition of whole slide images is prone to artifacts that can require human control and re-scanning, both in clinical workflows and in research-oriented settings. Quality control algorithms are a first step to overcome this challenge, as they limit the use of low quality images. Developing quality control systems in histopathology is not straightforward, also due to the limited availability of data related to this topic. We address the problem by proposing a tool to augment data with artifacts. The proposed method seamlessly generates and blends artifacts from an external library to a given histopathology dataset. The datasets augmented by the blended artifacts are then used to train an artifact detection network in a supervised way. We use the YOLOv5 model for the artifact detection with a slightly modified training pipeline. The proposed tool can be extended into a complete framework for the quality assessment of whole slide images.Clinical relevance- The proposed method may be useful for the initial quality screening of whole slide images. Each year, millions of whole slide images are acquired and digitized worldwide. Numerous of them contain artifacts affecting the following AI-oriented analysis. Therefore, a tool operating at the acquisition phase and improving the initial quality assessment is crucial to increase the performance of digital pathology algorithms, e.g., early cancer diagnosis.

A scoping review of interpretability and explainability concerning artificial intelligence methods in medical imaging.

PURPOSE: To review eXplainable Artificial Intelligence/(XAI) methods available for medical imaging/(MI). METHOD: A scoping review was conducted following the Joanna Briggs Institute's methodology. The search was performed on Pubmed, Embase, Cinhal, Web of Science, BioRxiv, MedRxiv, and Google Scholar. Studies published in French and English after 2017 were included. Keyword combinations and descriptors related to explainability, and MI modalities were employed. Two independent reviewers screened abstracts, titles and full text, resolving differences through discussion. RESULTS: 228 studies met the criteria. XAI publications are increasing, targeting MRI (n = 73), radiography (n = 47), CT (n = 46). Lung (n = 82) and brain (n = 74) pathologies, Covid-19 (n = 48), Alzheimer's disease (n = 25), brain tumors (n = 15) are the main pathologies explained. Explanations are presented visually (n = 186), numerically (n = 67), rule-based (n = 11), textually (n = 11), and example-based (n = 6). Commonly explained tasks include classification (n = 89), prediction (n = 47), diagnosis (n = 39), detection (n = 29), segmentation (n = 13), and image quality improvement (n = 6). The most frequently provided explanations were local (78.1 %), 5.7 % were global, and 16.2 % combined both local and global approaches. Post-hoc approaches were predominantly employed. The used terminology varied, sometimes indistinctively using explainable (n = 207), interpretable (n = 187), understandable (n = 112), transparent (n = 61), reliable (n = 31), and intelligible (n = 3). CONCLUSION: The number of XAI publications in medical imaging is increasing, primarily focusing on applying XAI techniques to MRI, CT, and radiography for classifying and predicting lung and brain pathologies. Visual and numerical output formats are predominantly used. Terminology standardisation remains a challenge, as terms like "explainable" and "interpretable" are sometimes being used indistinctively. Future XAI development should consider user needs and perspectives.

On-cloud decision-support system for non-small cell lung cancer histology characterization from thorax computed tomography scans.

Non-Small Cell Lung Cancer (NSCLC) accounts for about 85% of all lung cancers. Developing non-invasive techniques for NSCLC histology characterization may not only help clinicians to make targeted therapeutic treatments but also prevent subjects from undergoing lung biopsy, which is challenging and could lead to clinical implications. The motivation behind the study presented here is to develop an advanced on-cloud decision-support system, named LUCY, for non-small cell LUng Cancer histologY characterization directly from thorax Computed Tomography (CT) scans. This aim was pursued by selecting thorax CT scans of 182 LUng ADenocarcinoma (LUAD) and 186 LUng Squamous Cell carcinoma (LUSC) subjects from four openly accessible data collections (NSCLC-Radiomics, NSCLC-Radiogenomics, NSCLC-Radiomics-Genomics and TCGA-LUAD), in addition to the implementation and comparison of two end-to-end neural networks (the core layer of whom is a convolutional long short-term memory layer), the performance evaluation on test dataset (NSCLC-Radiomics-Genomics) from a subject-level perspective in relation to NSCLC histological subtype location and grade, and the dynamic visual interpretation of the achieved results by producing and analyzing one heatmap video for each scan. LUCY reached test Area Under the receiver operating characteristic Curve (AUC) values above 77% in all NSCLC histological subtype location and grade groups, and a best AUC value of 97% on the entire dataset reserved for testing, proving high generalizability to heterogeneous data and robustness. Thus, LUCY is a clinically-useful decision-support system able to timely, non-invasively and reliably provide visually-understandable predictions on LUAD and LUSC subjects in relation to clinically-relevant information.

Modelling digital health data: The ExaMode ontology for computational pathology.

Computational pathology can significantly benefit from ontologies to standardize the employed nomenclature and help with knowledge extraction processes for high-quality annotated image datasets. The end goal is to reach a shared model for digital pathology to overcome data variability and integration problems. Indeed, data annotation in such a specific domain is still an unsolved challenge and datasets cannot be steadily reused in diverse contexts due to heterogeneity issues of the adopted labels, multilingualism, and different clinical practices. Material and methods: This paper presents the ExaMode ontology, modeling the histopathology process by considering 3 key cancer diseases (colon, cervical, and lung tumors) and celiac disease. The ExaMode ontology has been designed bottom-up in an iterative fashion with continuous feedback and validation from pathologists and clinicians. The ontology is organized into 5 semantic areas that defines an ontological template to model any disease of interest in histopathology. Results: The ExaMode ontology is currently being used as a common semantic layer in: (i) an entity linking tool for the automatic annotation of medical records; (ii) a web-based collaborative annotation tool for histopathology text reports; and (iii) a software platform for building holistic solutions integrating multimodal histopathology data. Discussion: The ontology ExaMode is a key means to store data in a graph database according to the RDF data model. The creation of an RDF dataset can help develop more accurate algorithms for image analysis, especially in the field of digital pathology. This approach allows for seamless data integration and a unified query access point, from which we can extract relevant clinical insights about the considered diseases using SPARQL queries.

Data-driven color augmentation for H&E stained images in computational pathology.

Computational pathology targets the automatic analysis of Whole Slide Images (WSI). WSIs are high-resolution digitized histopathology images, stained with chemical reagents to highlight specific tissue structures and scanned via whole slide scanners. The application of different parameters during WSI acquisition may lead to stain color heterogeneity, especially considering samples collected from several medical centers. Dealing with stain color heterogeneity often limits the robustness of methods developed to analyze WSIs, in particular Convolutional Neural Networks (CNN), the state-of-the-art algorithm for most computational pathology tasks. Stain color heterogeneity is still an unsolved problem, although several methods have been developed to alleviate it, such as Hue-Saturation-Contrast (HSC) color augmentation and stain augmentation methods. The goal of this paper is to present Data-Driven Color Augmentation (DDCA), a method to improve the efficiency of color augmentation methods by increasing the reliability of the samples used for training computational pathology models. During CNN training, a database including over 2 million H&E color variations collected from private and public datasets is used as a reference to discard augmented data with color distributions that do not correspond to realistic data. DDCA is applied to HSC color augmentation, stain augmentation and H&E-adversarial networks in colon and prostate cancer classification tasks. DDCA is then compared with 11 state-of-the-art baseline methods to handle color heterogeneity, showing that it can substantially improve classification performance on unseen data including heterogeneous color variations.

Empowering digital pathology applications through explainable knowledge extraction tools.

Exa-scale volumes of medical data have been produced for decades. In most cases, the diagnosis is reported in free text, encoding medical knowledge that is still largely unexploited. In order to allow decoding medical knowledge included in reports, we propose an unsupervised knowledge extraction system combining a rule-based expert system with pre-trained Machine Learning (ML) models, namely the Semantic Knowledge Extractor Tool (SKET). Combining rule-based techniques and pre-trained ML models provides high accuracy results for knowledge extraction. This work demonstrates the viability of unsupervised Natural Language Processing (NLP) techniques to extract critical information from cancer reports, opening opportunities such as data mining for knowledge extraction purposes, precision medicine applications, structured report creation, and multimodal learning. SKET is a practical and unsupervised approach to extracting knowledge from pathology reports, which opens up unprecedented opportunities to exploit textual and multimodal medical information in clinical practice. We also propose SKET eXplained (SKET X), a web-based system providing visual explanations about the algorithmic decisions taken by SKET. SKET X is designed/developed to support pathologists and domain experts in understanding SKET predictions, possibly driving further improvements to the system.

Unleashing the potential of digital pathology data by training computer-aided diagnosis models without human annotations.

The digitalization of clinical workflows and the increasing performance of deep learning algorithms are paving the way towards new methods for tackling cancer diagnosis. However, the availability of medical specialists to annotate digitized images and free-text diagnostic reports does not scale with the need for large datasets required to train robust computer-aided diagnosis methods that can target the high variability of clinical cases and data produced. This work proposes and evaluates an approach to eliminate the need for manual annotations to train computer-aided diagnosis tools in digital pathology. The approach includes two components, to automatically extract semantically meaningful concepts from diagnostic reports and use them as weak labels to train convolutional neural networks (CNNs) for histopathology diagnosis. The approach is trained (through 10-fold cross-validation) on 3'769 clinical images and reports, provided by two hospitals and tested on over 11'000 images from private and publicly available datasets. The CNN, trained with automatically generated labels, is compared with the same architecture trained with manual labels. Results show that combining text analysis and end-to-end deep neural networks allows building computer-aided diagnosis tools that reach solid performance (micro-accuracy = 0.908 at image-level) based only on existing clinical data without the need for manual annotations.

Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression.

Although for many diseases there is a progressive diagnosis scale, automatic analysis of grade-based medical images is quite often addressed as a binary classification problem, missing the finer distinction and intrinsic relation between the different possible stages or grades. Ordinal regression (or classification) considers the order of the values of the categorical labels and thus takes into account the order of grading scales used to assess the severity of different medical conditions. This paper presents a quantum-inspired deep probabilistic learning ordinal regression model for medical image diagnosis that takes advantage of the representational power of deep learning and the intrinsic ordinal information of disease stages. The method is evaluated on two different medical image analysis tasks: prostate cancer diagnosis and diabetic retinopathy grade estimation on eye fundus images. The experimental results show that the proposed method not only improves the diagnosis performance on the two tasks but also the interpretability of the results by quantifying the uncertainty of the predictions in comparison to conventional deep classification and regression architectures. The code and datasets are available at https://github.com/stoledoc/DQOR.

Semi-supervised training of deep convolutional neural networks with heterogeneous data and few local annotations: An experiment on prostate histopathology image classification.

Convolutional neural networks (CNNs) are state-of-the-art computer vision techniques for various tasks, particularly for image classification. However, there are domains where the training of classification models that generalize on several datasets is still an open challenge because of the highly heterogeneous data and the lack of large datasets with local annotations of the regions of interest, such as histopathology image analysis. Histopathology concerns the microscopic analysis of tissue specimens processed in glass slides to identify diseases such as cancer. Digital pathology concerns the acquisition, management and automatic analysis of digitized histopathology images that are large, having in the order of 100'0002 pixels per image. Digital histopathology images are highly heterogeneous due to the variability of the image acquisition procedures. Creating locally labeled regions (required for the training) is time-consuming and often expensive in the medical field, as physicians usually have to annotate the data. Despite the advances in deep learning, leveraging strongly and weakly annotated datasets to train classification models is still an unsolved problem, mainly when data are very heterogeneous. Large amounts of data are needed to create models that generalize well. This paper presents a novel approach to train CNNs that generalize to heterogeneous datasets originating from various sources and without local annotations. The data analysis pipeline targets Gleason grading on prostate images and includes two models in sequence, following a teacher/student training paradigm. The teacher model (a high-capacity neural network) automatically annotates a set of pseudo-labeled patches used to train the student model (a smaller network). The two models are trained with two different teacher/student approaches: semi-supervised learning and semi-weekly supervised learning. For each of the two approaches, three student training variants are presented. The baseline is provided by training the student model only with the strongly annotated data. Classification performance is evaluated on the student model at the patch level (using the local annotations of the Tissue Micro-Arrays Zurich dataset) and at the global level (using the TCGA-PRAD, The Cancer Genome Atlas-PRostate ADenocarcinoma, whole slide image Gleason score). The teacher/student paradigm allows the models to better generalize on both datasets, despite the inter-dataset heterogeneity and the small number of local annotations used. The classification performance is improved both at the patch-level (up to κ=0.6127±0.0133 from κ=0.5667±0.0285), at the TMA core-level (Gleason score) (up to κ=0.7645±0.0231 from κ=0.7186±0.0306) and at the WSI-level (Gleason score) (up to κ=0.4529±0.0512 from κ=0.2293±0.1350). The results show that with the teacher/student paradigm, it is possible to train models that generalize on datasets from entirely different sources, despite the inter-dataset heterogeneity and the lack of large datasets with local annotations.

The Discriminative Power and Stability of Radiomics Features With Computed Tomography Variations: Task-Based Analysis in an Anthropomorphic 3D-Printed CT Phantom.

OBJECTIVES: The aims of this study were to determine the stability of radiomics features against computed tomography (CT) parameter variations and to study their discriminative power concerning tissue classification using a 3D-printed CT phantom based on real patient data. MATERIALS AND METHODS: A radiopaque 3D phantom was developed using real patient data and a potassium iodide solution paper-printing technique. Normal liver tissue and 3 lesion types (benign cyst, hemangioma, and metastasis) were manually annotated in the phantom. The stability and discriminative power of 86 radiomics features were assessed in measurements taken from 240 CT series with 8 parameter variations of reconstruction algorithms, reconstruction kernels, slice thickness, and slice spacing. Pairwise parameter group and pairwise tissue class comparisons were performed using Wilcoxon signed rank tests. RESULTS: In total, 19,264 feature stability tests and 8256 discriminative power tests were performed. The 8 CT parameter variation pairwise group comparisons had statistically significant differences on average in 78/86 radiomics features. On the other hand, 84% of the univariate radiomics feature tests had a successful and statistically significant differentiation of the 4 classes of liver tissue. The 86 radiomics features were ranked according to the cumulative sum of successful stability and discriminative power tests. CONCLUSIONS: The differences in radiomics feature values obtained from different types of liver tissue are generally greater than the intraclass differences resulting from CT parameter variations.

Combining weakly and strongly supervised learning improves strong supervision in Gleason pattern classification.

BACKGROUND: One challenge to train deep convolutional neural network (CNNs) models with whole slide images (WSIs) is providing the required large number of costly, manually annotated image regions. Strategies to alleviate the scarcity of annotated data include: using transfer learning, data augmentation and training the models with less expensive image-level annotations (weakly-supervised learning). However, it is not clear how to combine the use of transfer learning in a CNN model when different data sources are available for training or how to leverage from the combination of large amounts of weakly annotated images with a set of local region annotations. This paper aims to evaluate CNN training strategies based on transfer learning to leverage the combination of weak and strong annotations in heterogeneous data sources. The trade-off between classification performance and annotation effort is explored by evaluating a CNN that learns from strong labels (region annotations) and is later fine-tuned on a dataset with less expensive weak (image-level) labels. RESULTS: As expected, the model performance on strongly annotated data steadily increases as the percentage of strong annotations that are used increases, reaching a performance comparable to pathologists ([Formula: see text]). Nevertheless, the performance sharply decreases when applied for the WSI classification scenario with [Formula: see text]. Moreover, it only provides a lower performance regardless of the number of annotations used. The model performance increases when fine-tuning the model for the task of Gleason scoring with the weak WSI labels [Formula: see text]. CONCLUSION: Combining weak and strong supervision improves strong supervision in classification of Gleason patterns using tissue microarrays (TMA) and WSI regions. Our results contribute very good strategies for training CNN models combining few annotated data and heterogeneous data sources. The performance increases in the controlled TMA scenario with the number of annotations used to train the model. Nevertheless, the performance is hindered when the trained TMA model is applied directly to the more challenging WSI classification problem. This demonstrates that a good pre-trained model for prostate cancer TMA image classification may lead to the best downstream model if fine-tuned on the WSI target dataset. We have made available the source code repository for reproducing the experiments in the paper: https://github.com/ilmaro8/Digital_Pathology_Transfer_Learning.

The importance of feature aggregation in radiomics: a head and neck cancer study.

In standard radiomics studies the features extracted from clinical images are mostly quantified with simple statistics such as the average or variance per Region of Interest (ROI). Such approaches may smooth out any intra-region heterogeneity and thus hide some tumor aggressiveness that may hamper predictions. In this paper we study the importance of feature aggregation within the standard radiomics workflow, which allows to take into account intra-region variations. Feature aggregation methods transform a collection of voxel values from feature response maps (over a ROI) into one or several scalar values that are usable for statistical or machine learning algorithms. This important step has been little investigated within the radiomics workflows, so far. In this paper, we compare several aggregation methods with standard radiomics approaches in order to assess the improvements in prediction capabilities. We evaluate the performance using an aggregation function based on Bags of Visual Words (BoVW), which allows for the preservation of piece-wise homogeneous information within heterogeneous regions and compared with standard methods. The different models are compared on a cohort of 214 head and neck cancer patients coming from 4 medical centers. Radiomics features were extracted from manually delineated tumors in clinical PET-FDG and CT images were analyzed. We compared the performance of standard radiomics models, the volume of the ROI alone and the BoVW model for survival analysis. The average concordance index was estimated with a five fold cross-validation. The performance was significantly better using the BoVW model 0.627 (95% CI: 0.616-0.637) as compared to standard radiomics0.505 (95% CI: 0.499-0.511), mean-var. 0.543 (95% CI: 0.536-0.549), mean0.547 (95% CI: 0.541-0.554), var.0.530 (95% CI: 0.524-0.536) or volume 0.577 (95% CI: 0.571-0.582). We conclude that classical aggregation methods are not optimal in case of heterogeneous tumors. We also showed that the BoVW model is a better alternative to extract consistent features in the presence of lesions composed of heterogeneous tissue.

Training Deep Neural Networks for Small and Highly Heterogeneous MRI Datasets for Cancer Grading.

Using medical images recorded in clinical practice has the potential to be a game-changer in the application of machine learning for medical decision support. Thousands of medical images are produced in daily clinical activity. The diagnosis of medical doctors on these images represents a source of knowledge to train machine learning algorithms for scientific research or computer-aided diagnosis. However, the requirement of manual data annotations and the heterogeneity of images and annotations make it difficult to develop algorithms that are effective on images from different centers or sources (scanner manufacturers, protocols, etc.). The objective of this article is to explore the opportunities and the limits of highly heterogeneous biomedical data, since many medical data sets are small and entail a challenge for machine learning techniques. Particularly, we focus on a small data set targeting meningioma grading. Meningioma grading is crucial for patient treatment and prognosis. It is normally performed by histological examination but recent articles showed that it is possible to do it also on magnetic resonance images (MRI), so non-invasive. Our data set consists of 174 T1-weighted MRI images of patients with meningioma, divided into 126 benign and 48 atypical/anaplastic cases, acquired using 26 different MRI scanners and 125 acquisition protocols, which shows the enormous variability in the data set. The performed preprocessing steps include tumor segmentation, spatial image normalization and data augmentation based on color and affine transformations. The preprocessed cases are passed to a carefully trained 2-D convolutional neural network. Accuracy above 74% was obtained, with the high-grade tumor recall above 74%. The results are encouraging considering the limited size and high heterogeneity of the data set. The proposed methodology can be useful for other problems involving classification of small and highly heterogeneous data sets.

Machine Learning Assisted Citation Screening for Systematic Reviews.

Evidence-based practice is highly dependent upon up-to-date systematic reviews (SR) for decision making. However, conducting and updating systematic reviews, especially the citation screening for identification of relevant studies, requires much human work and is therefore expensive. Automating citation screening using machine learning (ML) based approaches can reduce cost and labor. Machine learning has been applied to automate citation screening but not for the SRs with very narrow research questions. This paper reports the results and observations for an ongoing research that aims to automate citation screening for SRs with narrow research questions using machine learning. The research also sheds light on the problem of class imbalance and class overlap on the performance of ML classifiers when applied to SRs with narrow research questions.

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.