Imaging in pleural Mesothelioma: A review of the 16th International Conference of the International Mesothelioma Interest Group.

Imaging continues to gain a greater role in the assessment and clinical management of patients with mesothelioma. This communication summarizes the oral presentations from the imaging session at the 2023 International Conference of the International Mesothelioma Interest Group (iMig), which was held in Lille, France from June 26 to 28, 2023. Topics at this session included an overview of best practices for clinical imaging of mesothelioma as reported by an iMig consensus panel, emerging imaging techniques for surgical planning, radiologic assessment of malignant pleural effusion, a radiomics-based transfer learning model to predict patient response to treatment, automated assessment of early contrast enhancement, and tumor thickness for response assessment in peritoneal mesothelioma.

AI and machine learning in medical imaging: key points from development to translation.

Innovation in medical imaging artificial intelligence (AI)/machine learning (ML) demands extensive data collection, algorithmic advancements, and rigorous performance assessments encompassing aspects such as generalizability, uncertainty, bias, fairness, trustworthiness, and interpretability. Achieving widespread integration of AI/ML algorithms into diverse clinical tasks will demand a steadfast commitment to overcoming issues in model design, development, and performance assessment. The complexities of AI/ML clinical translation present substantial challenges, requiring engagement with relevant stakeholders, assessment of cost-effectiveness for user and patient benefit, timely dissemination of information relevant to robust functioning throughout the AI/ML lifecycle, consideration of regulatory compliance, and feedback loops for real-world performance evidence. This commentary addresses several hurdles for the development and adoption of AI/ML technologies in medical imaging. Comprehensive attention to these underlying and often subtle factors is critical not only for tackling the challenges but also for exploring novel opportunities for the advancement of AI in radiology.

Implementation of a high-resolution, high-contrast magnetic resonance imaging protocol with extended delayed phases for peritoneal mesothelioma.

Background: Imaging of peritoneal malignancies using conventional cross-sectional imaging is challenging, but accurate assessment of peritoneal disease burden could guide better selection for definitive surgery. Here we demonstrate feasibility of high-resolution, high-contrast magnetic resonance imaging (MRI) of peritoneal mesothelioma and explore optimal timing for delayed post-contrast imaging. Methods: Prospective data from inpatients with malignant peritoneal mesothelioma (MPM), imaged with a novel MRI protocol, were analyzed. The new sequences augmenting the clinical protocol were (I) pre-contrast coronal high-resolution T2-weighted single-shot fast spin echo (COR hr T2w SSH FSE) of abdomen and pelvis; and (II) post-contrast coronal high-resolution three-dimensional (3D) T1-weighted modified Dixon (COR hr T1w mDIXON) of abdomen, acquired at five delay times, up to 20 min after administration of a double dose of contrast agent. Quantitative analysis of contrast enhancement was performed using linear regression applied to normalized signal in lesion regions of interest (ROIs). Qualitative analysis was performed by three blinded radiologists. Results: MRI exams from 14 participants (age: mean ± standard deviation, 60±12 years; 71% male) were analyzed. The rate of lesion contrast enhancement was strongly correlated with tumor grade (cumulative nuclear score) (r=-0.65, P<0.02), with 'early' delayed phase (12 min post-contrast) and 'late' delayed phase (19 min post-contrast) performing better for higher grade and lower grade tumors, respectively, in agreement with qualitative scoring of image contrast. Conclusions: High-resolution, high-contrast MRI with extended post-contrast imaging is a viable modality for imaging peritoneal mesothelioma. Multiple, extended (up to 20 min post-contrast) delayed phases are necessary for optimal imaging of peritoneal mesothelioma, depending on the grade of disease.

Artificial intelligence in medicine: mitigating risks and maximizing benefits via quality assurance, quality control, and acceptance testing.

The adoption of artificial intelligence (AI) tools in medicine poses challenges to existing clinical workflows. This commentary discusses the necessity of context-specific quality assurance (QA), emphasizing the need for robust QA measures with quality control (QC) procedures that encompass (1) acceptance testing (AT) before clinical use, (2) continuous QC monitoring, and (3) adequate user training. The discussion also covers essential components of AT and QA, illustrated with real-world examples. We also highlight what we see as the shared responsibility of manufacturers or vendors, regulators, healthcare systems, medical physicists, and clinicians to enact appropriate testing and oversight to ensure a safe and equitable transformation of medicine through AI.

Convolutional Neural Networks for Segmentation of Malignant Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance).

Malignant pleural mesothelioma (MPM) is the most common form of malignant mesothelioma, with exposure to asbestos being the primary cause of the disease. To assess response to treatment, tumor measurements are acquired and evaluated based on a patient's longitudinal computed tomography (CT) scans. Tumor volume, however, is the more accurate metric for assessing tumor burden and response. Automated segmentation methods using deep learning can be employed to acquire volume, which otherwise is a tedious task performed manually. The deep learning-based tumor volume and contours can then be compared with a standard reference to assess the robustness of the automated segmentations. The purpose of this study was to evaluate the impact of probability map threshold on MPM tumor delineations generated using a convolutional neural network (CNN). Eighty-eight CT scans from 21 MPM patients were segmented by a VGG16/U-Net CNN. A radiologist modified the contours generated at a 0.5 probability threshold. Percent difference of tumor volume and overlap using the Dice Similarity Coefficient (DSC) were compared between the standard reference provided by the radiologist and CNN outputs for thresholds ranging from 0.001 to 0.9. CNN annotations consistently yielded smaller tumor volumes than radiologist contours. Reducing the probability threshold from 0.5 to 0.1 decreased the absolute percent volume difference, on average, from 43.96% to 24.18%. Median and mean DSC ranged from 0.58 to 0.60, with a peak at a threshold of 0.5; no distinct threshold was found for percent volume difference. The CNN exhibited deficiencies with specific disease presentations, such as severe pleural effusion or disease in the pleural fissure. No single output threshold in the CNN probability maps was optimal for both tumor volume and DSC. This study emphasized the importance of considering both figures of merit when evaluating deep learning-based tumor segmentations across probability thresholds. This work underscores the need to simultaneously assess tumor volume and spatial overlap when evaluating CNN performance. While automated segmentations may yield comparable tumor volumes to that of the reference standard, the spatial region delineated by the CNN at a specific threshold is equally important.

Magnetic resonance imaging preprocessing and radiomic features for classification of autosomal dominant polycystic kidney disease genotype.

Purpose: Our study aims to investigate the impact of preprocessing on magnetic resonance imaging (MRI) radiomic features extracted from the noncystic kidney parenchyma of patients with autosomal dominant polycystic kidney disease (ADPKD) in the task of classifying PKD1 versus PKD2 genotypes, which differ with regard to cyst burden and disease outcome. Approach: The effect of preprocessing on radiomic features was investigated using a single T2-weighted fat saturated (T2W-FS) MRI scan from PKD1 and PKD2 subjects (29 kidneys in total) from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease study. Radiomic feature reproducibility using the intraclass correlation coefficient (ICC) was computed across MRI normalizations (z-score, reference-tissue, and original image), gray-level discretization, and upsampling and downsampling pixel schemes. A second dataset for genotype classification from 136 subjects T2W-FS MRI images previously enrolled in the HALT Progression of Polycystic Kidney Disease study was matched for age, gender, and Mayo imaging classification class. Genotype classification was performed using a logistic regression classifier and radiomic features extracted from (1) the noncystic kidney parenchyma and (2) the entire kidney. The area under the receiver operating characteristic curve (AUC) was used to evaluate the classification performance across preprocessing methods. Results: Radiomic features extracted from the noncystic kidney parenchyma were sensitive to preprocessing parameters, with varying reproducibility depending on the parameter. The percentage of features with good-to-excellent ICC scores ranged from 14% to 58%. AUC values ranged between 0.47 to 0.68 and 0.56 to 0.73 for the noncystic kidney parenchyma and entire kidney, respectively. Conclusions: Reproducibility of radiomic features extracted from the noncystic kidney parenchyma was dependent on the preprocessing parameters used, and the effect on genotype classification was sensitive to preprocessing parameters. The results suggest that texture features may be indicative of genotype expression in ADPKD.

AI in medical imaging grand challenges: translation from competition to research benefit and patient care.

Artificial intelligence (AI), in one form or another, has been a part of medical imaging for decades. The recent evolution of AI into approaches such as deep learning has dramatically accelerated the application of AI across a wide range of radiologic settings. Despite the promises of AI, developers and users of AI technology must be fully aware of its potential biases and pitfalls, and this knowledge must be incorporated throughout the AI system development pipeline that involves training, validation, and testing. Grand challenges offer an opportunity to advance the development of AI methods for targeted applications and provide a mechanism for both directing and facilitating the development of AI systems. In the process, a grand challenge centralizes (with the challenge organizers) the burden of providing a valid benchmark test set to assess performance and generalizability of participants' models and the collection and curation of image metadata, clinical/demographic information, and the required reference standard. The most relevant grand challenges are those designed to maximize the open-science nature of the competition, with code and trained models deposited for future public access. The ultimate goal of AI grand challenges is to foster the translation of AI systems from competition to research benefit and patient care. Rather than reference the many medical imaging grand challenges that have been organized by groups such as MICCAI, RSNA, AAPM, and grand-challenge.org, this review assesses the role of grand challenges in promoting AI technologies for research advancement and for eventual clinical implementation, including their promises and limitations.

Germline Variants Incidentally Detected via Tumor-Only Genomic Profiling of Patients With Mesothelioma.

Importance: Patients with mesothelioma often have next-generation sequencing (NGS) of their tumor performed; tumor-only NGS may incidentally identify germline pathogenic or likely pathogenic (P/LP) variants despite not being designed for this purpose. It is unknown how frequently patients with mesothelioma have germline P/LP variants incidentally detected via tumor-only NGS. Objective: To determine the prevalence of incidental germline P/LP variants detected via tumor-only NGS of mesothelioma. Design, Setting, and Participants: A series of 161 unrelated patients with mesothelioma from a high-volume mesothelioma program had tumor-only and germline NGS performed during April 2016 to October 2021. Follow-up ranged from 18 months to 7 years. Tumor and germline assays were compared to determine which P/LP variants identified via tumor-only NGS were of germline origin. Data were analyzed from January to March 2023. Main Outcomes and Measures: The proportion of patients with mesothelioma who had P/LP germline variants incidentally detected via tumor-only NGS. Results: Of 161 patients with mesothelioma, 105 were male (65%), the mean (SD) age was 64.7 (11.2) years, and 156 patients (97%) self-identified as non-Hispanic White. Most (126 patients [78%]) had at least 1 potentially incidental P/LP germline variant. The positive predictive value of a potentially incidental germline P/LP variant on tumor-only NGS was 20%. Overall, 26 patients (16%) carried a P/LP germline variant. Germline P/LP variants were identified in ATM, ATR, BAP1, CHEK2, DDX41, FANCM, HAX1, MRE11A, MSH6, MUTYH, NF1, SAMD9L, and TMEM127. Conclusions and Relevance: In this case series of 161 patients with mesothelioma, 16% had confirmed germline P/LP variants. Given the implications of a hereditary cancer syndrome diagnosis for preventive care and familial counseling, clinical approaches for addressing incidental P/LP germline variants in tumor-only NGS are needed. Tumor-only sequencing should not replace dedicated germline testing. Universal germline testing is likely needed for patients with mesothelioma.

A Competition, Benchmark, Code, and Data for Using Artificial Intelligence to Detect Lesions in Digital Breast Tomosynthesis.

Importance: An accurate and robust artificial intelligence (AI) algorithm for detecting cancer in digital breast tomosynthesis (DBT) could significantly improve detection accuracy and reduce health care costs worldwide. Objectives: To make training and evaluation data for the development of AI algorithms for DBT analysis available, to develop well-defined benchmarks, and to create publicly available code for existing methods. Design, Setting, and Participants: This diagnostic study is based on a multi-institutional international grand challenge in which research teams developed algorithms to detect lesions in DBT. A data set of 22 032 reconstructed DBT volumes was made available to research teams. Phase 1, in which teams were provided 700 scans from the training set, 120 from the validation set, and 180 from the test set, took place from December 2020 to January 2021, and phase 2, in which teams were given the full data set, took place from May to July 2021. Main Outcomes and Measures: The overall performance was evaluated by mean sensitivity for biopsied lesions using only DBT volumes with biopsied lesions; ties were broken by including all DBT volumes. Results: A total of 8 teams participated in the challenge. The team with the highest mean sensitivity for biopsied lesions was the NYU B-Team, with 0.957 (95% CI, 0.924-0.984), and the second-place team, ZeDuS, had a mean sensitivity of 0.926 (95% CI, 0.881-0.964). When the results were aggregated, the mean sensitivity for all submitted algorithms was 0.879; for only those who participated in phase 2, it was 0.926. Conclusions and Relevance: In this diagnostic study, an international competition produced algorithms with high sensitivity for using AI to detect lesions on DBT images. A standardized performance benchmark for the detection task using publicly available clinical imaging data was released, with detailed descriptions and analyses of submitted algorithms accompanied by a public release of their predictions and code for selected methods. These resources will serve as a foundation for future research on computer-assisted diagnosis methods for DBT, significantly lowering the barrier of entry for new researchers.

Considerations for Imaging of Malignant Pleural Mesothelioma: A Consensus Statement from the International Mesothelioma Interest Group.

Malignant pleural mesothelioma (MPM) is an aggressive primary malignancy of the pleura that presents unique radiologic challenges with regard to accurate and reproducible assessment of disease extent at staging and follow-up imaging. By optimizing and harmonizing technical approaches to imaging MPM, the best quality imaging can be achieved for individual patient care, clinical trials, and imaging research. This consensus statement represents agreement on harmonized, standard practices for routine multimodality imaging of MPM, including radiography, computed tomography, 18F-2-deoxy-D-glucose positron emission tomography, and magnetic resonance imaging, by an international panel of experts in the field of pleural imaging assembled by the International Mesothelioma Interest Group. In addition, modality-specific technical considerations and future directions are discussed. A bulleted summary of all technical recommendations is provided.

AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging.

Rapid advances in artificial intelligence (AI) and machine learning, and specifically in deep learning (DL) techniques, have enabled broad application of these methods in health care. The promise of the DL approach has spurred further interest in computer-aided diagnosis (CAD) development and applications using both "traditional" machine learning methods and newer DL-based methods. We use the term CAD-AI to refer to this expanded clinical decision support environment that uses traditional and DL-based AI methods. Numerous studies have been published to date on the development of machine learning tools for computer-aided, or AI-assisted, clinical tasks. However, most of these machine learning models are not ready for clinical deployment. It is of paramount importance to ensure that a clinical decision support tool undergoes proper training and rigorous validation of its generalizability and robustness before adoption for patient care in the clinic. To address these important issues, the American Association of Physicists in Medicine (AAPM) Computer-Aided Image Analysis Subcommittee (CADSC) is charged, in part, to develop recommendations on practices and standards for the development and performance assessment of computer-aided decision support systems. The committee has previously published two opinion papers on the evaluation of CAD systems and issues associated with user training and quality assurance of these systems in the clinic. With machine learning techniques continuing to evolve and CAD applications expanding to new stages of the patient care process, the current task group report considers the broader issues common to the development of most, if not all, CAD-AI applications and their translation from the bench to the clinic. The goal is to bring attention to the proper training and validation of machine learning algorithms that may improve their generalizability and reliability and accelerate the adoption of CAD-AI systems for clinical decision support.

Assessment of a deep learning model for COVID-19 classification on chest radiographs: a comparison across image acquisition techniques and clinical factors.

Purpose: The purpose is to assess the performance of a pre-trained deep learning model in the task of classifying between coronavirus disease (COVID)-positive and COVID-negative patients from chest radiographs (CXRs) while considering various image acquisition parameters, clinical factors, and patient demographics. Methods: Standard and soft-tissue CXRs of 9860 patients comprised the "original dataset," consisting of training and test sets and were used to train a DenseNet-121 architecture model to classify COVID-19 using three classification algorithms: standard, soft tissue, and a combination of both types of images via feature fusion. A larger more-current test set of 5893 patients (the "current test set") was used to assess the performance of the pretrained model. The current test set contained a larger span of dates, incorporated different variants of the virus and included different immunization statuses. Model performance between the original and current test sets was evaluated using area under the receiver operating characteristic curve (ROC AUC) [95% CI]. Results: The model achieved AUC values of 0.67 [0.65, 0.70] for cropped standard images, 0.65 [0.63, 0.67] for cropped soft-tissue images, and 0.67 [0.65, 0.69] for both types of cropped images. These were all significantly lower than the performance of the model on the original test set. Investigations regarding matching the acquisition dates between the test sets (i.e., controlling for virus variants), immunization status, disease severity, and age and sex distributions did not fully explain the discrepancy in performance. Conclusions: Several relevant factors were considered to determine whether differences existed in the test sets, including time period of image acquisition, vaccination status, and disease severity. The lower performance on the current test set may have occurred due to model overfitting and a lack of generalizability.

The role of imaging in diagnosis and management of malignant peritoneal mesothelioma: a systematic review.

PURPOSE: Imaging of the peritoneum and related pathology is a challenge. Among peritoneal diseases, malignant peritoneal mesothelioma (MPeM) is an uncommon tumor with poor prognosis. To date, there are no specific guidelines or imaging protocols dedicated for the peritoneum and MPeM. The objective of this study was to analyze the literature describing imaging modalities used for MPeM to determine their relative clinical efficacy and review commonly reported imaging features of MPeM to promote standardized reporting. METHODS: We performed a systematic review of original research articles discussing imaging modalities in MPeM from 1999 to 2020. Effectiveness measures and common findings were compared across imaging modalities. RESULTS: Among 582 studies analyzed, the most-used imaging modality was CT (54.3%). In the differentiation of MPeM from peritoneal carcinomatosis, one study found CT had a diagnostic sensitivity of 53%, specificity of 100%, and accuracy of 68%. Two studies found fluorodeoxyglucose positron emission tomography (FDG-PET) had sensitivity of 86-92%, specificity of 83-89%, and accuracy of 87-89%. Another study found magnetic resonance imaging (MRI) was the best predictor of the peritoneal carcinomatosis index. Characteristics shown to best differentiate MPeM from other diseases included ascites, peritoneal thickening, mesenteric thickening, pleural plaques, maximum tumor dimension, and number of masses. CONCLUSION: Most published MPeM imaging studies utilized CT. PET/CT or MRI appear promising, and future studies should compare effectiveness of these modalities. MPeM imaging reports should highlight ascites, number of and maximum tumor dimension, peritoneal/mesenteric thickening, and associated pleural plaques, allowing for better aggregation of MPeM imaging data across studies.

Imaging in pleural mesothelioma: A review of the 15th International Conference of the International Mesothelioma Interest Group.

Imaging of mesothelioma plays a role in all aspects of patient management, including disease detection, staging, evaluation of treatment options, response assessment, pre-surgical evaluation, and surveillance. Imaging in this disease impacts a wide range of disciplines throughout the healthcare enterprise. Researchers and clinician-scientists are developing state-of-the-art techniques to extract more of the information contained within these medical images and to utilize it for more sophisticated tasks; moreover, image-acquisition technology is advancing the inherent capabilities of these images. This paper summarizes the imaging-based topics presented orally at the 2021 International Conference of the International Mesothelioma Interest Group (iMig), which was held virtually from May 7-9, 2021. These topics include an update on the mesothelioma staging system, novel molecular targets to guide therapy in mesothelioma, special considerations and potential pitfalls in imaging mesothelioma in the immunotherapy setting, tumor measurement strategies and their correlation with patient survival, tumor volume measurement in MRI and CT, CT-based texture analysis for differentiation of histologic subtype, diffusion-weighted MRI for the assessment of biphasic mesothelioma, and the prognostic significance of skeletal muscle loss with chemotherapy.

Anatomic Point-Based Lung Region with Zone Identification for Radiologist Annotation and Machine Learning for Chest Radiographs.

Our objective is to investigate the reliability and usefulness of anatomic point-based lung zone segmentation on chest radiographs (CXRs) as a reference standard framework and to evaluate the accuracy of automated point placement. Two hundred frontal CXRs were presented to two radiologists who identified five anatomic points: two at the lung apices, one at the top of the aortic arch, and two at the costophrenic angles. Of these 1000 anatomic points, 161 (16.1%) were obscured (mostly by pleural effusions). Observer variations were investigated. Eight anatomic zones then were automatically generated from the manually placed anatomic points, and a prototype algorithm was developed using the point-based lung zone segmentation to detect cardiomegaly and levels of diaphragm and pleural effusions. A trained U-Net neural network was used to automatically place these five points within 379 CXRs of an independent database. Intra- and inter-observer variation in mean distance between corresponding anatomic points was larger for obscured points (8.7 mm and 20 mm, respectively) than for visible points (4.3 mm and 7.6 mm, respectively). The computer algorithm using the point-based lung zone segmentation could diagnostically measure the cardiothoracic ratio and diaphragm position or pleural effusion. The mean distance between corresponding points placed by the radiologist and by the neural network was 6.2 mm. The network identified 95% of the radiologist-indicated points with only 3% of network-identified points being false-positives. In conclusion, a reliable anatomic point-based lung segmentation method for CXRs has been developed with expected utility for establishing reference standards for machine learning applications.

Radiomics-based assessment of idiopathic pulmonary fibrosis is associated with genetic mutations and patient survival.

Purpose: The purpose of our study was to combine differences in radiomic features extracted from lung regions in the computed tomography (CT) scans of patients diagnosed with idiopathic pulmonary fibrosis (IPF) to identify associations with genetic variations and patient survival. Approach: A database of CT scans and genomic data from 169 patients diagnosed with IPF was collected retrospectively. Six region-of-interest pairs (three per lung, positioned posteriorly, anteriorly, and laterally) were placed in each of three axial CT sections for each patient. Thirty-one features were used in logistic regression to classify patients' genetic mutation status; classification performance was evaluated through the area under the receiver operating characteristic (ROC) curve [average area under the ROC curve (AUC)]. Kaplan-Meier (KM) survival curve models quantified the ability of each feature to differentiate between survival curves based on feature-specific thresholds. Results: Nine first-order texture features and one fractal feature were correlated with TOLLIP-1 (rs4963062) mutations (AUC: 0.54 to 0.74), and five Laws' filter features were correlated with TOLLIP-2 (rs5743905) mutations (AUC: 0.53 to 0.70). None of the features analyzed were found to be correlated with MUC5B mutations. First-order and fractal features demonstrated the greatest discrimination between KM curves. Conclusions: A radiomics approach for the correlation of patient genetic mutations with image texture features has potential as a biomarker. These features also may serve as prognostic indicators using a survival curve modeling approach in which the combination of radiomic features and genetic mutations provides an enhanced understanding of the interaction between imaging phenotype and patient genotype on the progression and treatment of IPF.