Data Science in Radiology: A Path Forward

Prognostic and Predictive Value of Systemic Inflammatory Markers in Epithelial Ovarian Cancer

Background and Objectives: Epithelial ovarian cancer (EOC) remains a significant global health challenge. While traditional prognostic factors are well established, emerging biomarkers continue to gain attention. Materials and Methods: This retrospective study evaluated the impact of systemic inflammatory markers on progression-free survival (PFS) and overall survival (OS) in 154 EOC patients. Pre-treatment neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), and systemic inflammatory index (SII) were calculated and categorized into low and high groups. Univariate and multivariate analyses were conducted to identify independent prognostic factors, while logistic regression analysis was used to determine predictors of platinum resistance. Results: In the univariate analysis, elevated NLR and PLR were associated with poorer PFS and OS. However, these markers did not maintain statistical significance in the multivariate analysis. Although SII demonstrated a trend toward worse outcomes, it did not reach statistical significance. Histopathological type, PLR, and surgical approach were identified as independent predictors of platinum resistance. Conclusions: Our findings indicate that systemic inflammatory markers may hold prognostic value in EOC; however, further validation through larger prospective studies is necessary.

Applying oversampling before cross-validation will lead to high bias in radiomics

Class imbalance is often unavoidable for radiomic data collected from clinical routine. It can create problems during classifier training since the majority class could dominate the minority class. Consequently, resampling methods like oversampling or undersampling are applied to the data to class-balance the data. However, the resampling must not be applied upfront to all data because it would lead to data leakage and, therefore, to erroneous results. This study aims to measure the extent of this bias. Five-fold cross-validation with 30 repeats was performed using a set of 15 radiomic datasets to train predictive models. The training involved two scenarios: first, the models were trained correctly by applying the resampling methods during the cross-validation. Second, the models were trained incorrectly by performing the resampling on all the data before cross-validation. The bias was defined empirically as the difference between the best-performing models in both scenarios in terms of area under the receiver operating characteristic curve (AUC), sensitivity, specificity, balanced accuracy, and the Brier score. In addition, a simulation study was performed on a randomly generated dataset for verification. The results demonstrated that incorrectly applying the oversampling methods to all data resulted in a large positive bias (up to 0.34 in AUC, 0.33 in sensitivity, 0.31 in specificity, and 0.37 in balanced accuracy). The bias depended on the data balance, and approximately an increase of 0.10 in the AUC was observed for each increase in imbalance. The models also showed a bias in calibration measured using the Brier score, which differed by up to -0.18 between the correctly and incorrectly trained models. The undersampling methods were not affected significantly by bias. These results emphasize that any resampling method should be applied correctly only to the training data to avoid data leakage and, subsequently, biased model performance and calibration.

'Is your accuser me, or is it the software?' Ambiguity and contested expertise in probabilistic DNA profiling

What happens when an algorithm is added to the work of an expert group? This study explores how algorithms pose a practical problem for experts. We study the introduction of a Probabilistic DNA Profiling (PDP) software into a forensics lab through interviews and court admissibility hearings. While meant to support experts' decision-making, in practice it has destabilized their authority. They respond to this destabilization by producing alternating and often conflicting accounts of the agency and significance of the software. The algorithm gets constructed alternately either as merely a tool or as indispensable statistical backing; the analysts' authority as either independent of the algorithm or reliant upon it to resolve conflict and create a final decision; and forensic expertise as resting either with the analysts or with the software. These tensions reflect the forensic 'culture of anticipation', specifically the experts' anticipation of ongoing litigation that destabilizes their control over the deployment and interpretation of expertise in the courtroom. The software highlights tensions between the analysts' supposed impartiality and their role in the courtroom, exposing legal and narrative implications of the changing nature of expertise and technology in the criminal legal system.

Trends and Hotspots in Global Radiomics Research: A Bibliometric Analysis

Objectives: The purpose of this research is to summarize the structure of radiomics-based knowledge and to explore potential trends and priorities by using bibliometric analysis. Methods: Select radiomics-related publications from 2012 to October 2022 from the Science Core Collection Web site. Use VOSviewer (version 1.6.18), CiteSpace (version 6.1.3), Tableau (version 2022), Microsoft Excel and Rstudio's free online platforms (http://bibliometric.com) for co-writing, co-citing, and co-occurrence analysis of countries, institutions, authors, references, and keywords in the field. The visual analysis is also carried out on it. Results: The study included 6428 articles. Since 2012, there has been an increase in research papers based on radiomics. Judging by publications, China has made the largest contribution in this area. We identify the most productive institutions and authors as Fudan University and Tianjie. The top three magazines with the most publications are《FRONTIERS IN ONCOLOGY》, 《EUROPEAN RADIOLOGY》, and 《CANCERS》. According to the results of reference and keyword analysis, "deep learning, nomogram, ultrasound, f-18-fdg, machine learning, covid-19, radiogenomics" has been determined as the main research direction in the future. Conclusion: Radiomics is in a phase of vigorous development with broad prospects. Cross-border cooperation between countries and institutions should be strengthened in the future. It can be predicted that the development of deep learning-based models and multimodal fusion models will be the focus of future research. Advances in knowledge: This study explores the current state of research and hot spots in the field of radiomics from multiple perspectives, comprehensively, and objectively reflecting the evolving trends in imaging-related research and providing a reference for future research.

Use of a Convolutional Neural Network to Predict the Malignant Potential of Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Images: Visualization of the Focus of the Prediction Model

OBJECTIVE

We established a deep convolutional neural network (CNN) model based on ultrasound images (US-CNN) for predicting the malignant potential of gastrointestinal stromal tumors (GISTs).

METHODS

A total of 980 ultrasound images from 245 pathology-confirmed GIST patients after surgical operation were retrospectively collected and divided into a low (very-low-risk, low-risk) and a high (medium-risk, high-risk) malignant potential group. Eight pre-trained CNN models were used to extract the features. The CNN model with the highest accuracy in the test set was selected. The model's performance was evaluated by calculating accuracy, sensitivity, specificity, positive-predictive value (PPV), negative-predictive value (NPV) and the F1 score. Three radiologists with different experience levels also predicted the malignant potential of GISTs in the same test set. US-CNN and human assessments were compared. Subsequently, gradient-weighted class activation diagrams (Grad-CAMs) were used to visualize the model's final classification decisions.

RESULTS

Among the eight transfer learning-based CNNs, ResNet18 performed best. The accuracy, sensitivity, specificity, PPV, NPV and F1 score were 0.88, 0.86, 0.89, 0.82, 0.92 and 0.90, respectively, which were significantly better than those achieved by radiologists (resident doctor: 0.66, 0.55, 0.79, 0.74, 0.62 and 0.69; attending doctor: 0.68, 0.59, 0.78, 0.70, 0.69 and 0.73; professor: 0.69, 0.63, 0.72, 0.51, 0.80 and 0.76). Model interpretation with Grad-CAMs revealed that the activated areas mainly focused on cystic necrosis and margins.

CONCLUSION

The US-CNN model predicts GIST malignant potential well, which can assist in clinical treatment decision-making.

Deep learning PET/CT-based radiomics integrates clinical data: A feasibility study to distinguish between tuberculosis nodules and lung cancer

BACKGROUND

Radiomic diagnosis models generally consider only a single dimension of information, leading to limitations in their diagnostic accuracy and reliability. The integration of multiple dimensions of information into the deep learning model have the potential to improve its diagnostic capabilities. The purpose of study was to evaluate the performance of deep learning model in distinguishing tuberculosis (TB) nodules and lung cancer (LC) based on deep learning features, radiomic features, and clinical information.

METHODS

Positron emission tomography (PET) and computed tomography (CT) image data from 97 patients with LC and 77 patients with TB nodules were collected. One hundred radiomic features were extracted from both PET and CT imaging using the pyradiomics platform, and 2048 deep learning features were obtained through a residual neural network approach. Four models included traditional machine learning model with radiomic features as input (traditional radiomics), a deep learning model with separate input of image features (deep convolutional neural networks [DCNN]), a deep learning model with two inputs of radiomic features and deep learning features (radiomics-DCNN) and a deep learning model with inputs of radiomic features and deep learning features and clinical information (integrated model). The models were evaluated using area under the curve (AUC), sensitivity, accuracy, specificity, and F1-score metrics.

RESULTS

The results of the classification of TB nodules and LC showed that the integrated model achieved an AUC of 0.84 (0.82-0.88), sensitivity of 0.85 (0.80-0.88), and specificity of 0.84 (0.83-0.87), performing better than the other models.

CONCLUSION

The integrated model was found to be the best classification model in the diagnosis of TB nodules and solid LC.

Predicting prognosis of nasopharyngeal carcinoma based on deep learning: peritumoral region should be valued

BACKGROUND

The purpose of this study was to explore whether incorporating the peritumoral region to train deep neural networks could improve the performance of the models for predicting the prognosis of NPC.

METHODS

A total of 381 NPC patients who were divided into high- and low-risk groups according to progression-free survival were retrospectively included. Deeplab v3 and U-Net were trained to build segmentation models for the automatic segmentation of the tumor and suspicious lymph nodes. Five datasets were constructed by expanding 5, 10, 20, 40, and 60 pixels outward from the edge of the automatically segmented region. Inception-Resnet-V2, ECA-ResNet50t, EfficientNet-B3, and EfficientNet-B0 were trained with the original, segmented, and the five new constructed datasets to establish the classification models. The receiver operating characteristic curve was used to evaluate the performance of each model.

RESULTS

The Dice coefficients of Deeplab v3 and U-Net were 0.741(95%CI:0.722-0.760) and 0.737(95%CI:0.720-0.754), respectively. The average areas under the curve (aAUCs) of deep learning models for classification trained with the original and segmented images and with images expanded by 5, 10, 20, 40, and 60 pixels were 0.717 ± 0.043, 0.739 ± 0.016, 0.760 ± 0.010, 0.768 ± 0.018, 0.802 ± 0.013, 0.782 ± 0.039, and 0.753 ± 0.014, respectively. The models trained with the images expanded by 20 pixels obtained the best performance.

CONCLUSIONS

The peritumoral region NPC contains information related to prognosis, and the incorporation of this region could improve the performance of deep learning models for prognosis prediction.

The Use of Artificial Intelligence (AI) in the Radiology Field: What Is the State of Doctor-Patient Communication in Cancer Diagnosis?

BACKGROUND

In the past decade, interest in applying Artificial Intelligence (AI) in radiology to improve diagnostic procedures increased. AI has potential benefits spanning all steps of the imaging chain, from the prescription of diagnostic tests to the communication of test reports. The use of AI in the field of radiology also poses challenges in doctor-patient communication at the time of the diagnosis. This systematic review focuses on the patient role and the interpersonal skills between patients and physicians when AI is implemented in cancer diagnosis communication.

METHODS

A systematic search was conducted on PubMed, Embase, Medline, Scopus, and PsycNet from 1990 to 2021. The search terms were: ("artificial intelligence" or "intelligence machine") and "communication" "radiology" and "oncology diagnosis". The PRISMA guidelines were followed.

RESULTS

517 records were identified, and 5 papers met the inclusion criteria and were analyzed. Most of the articles emphasized the success of the technological support of AI in radiology at the expense of patient trust in AI and patient-centered communication in cancer disease. Practical implications and future guidelines were discussed according to the results.

CONCLUSIONS

AI has proven to be beneficial in helping clinicians with diagnosis. Future research may improve patients' trust through adequate information about the advantageous use of AI and an increase in medical compliance with adequate training on doctor-patient diagnosis communication.

Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning

Background

We evaluated the role of radiomics applied to contrast-enhanced computed tomography (CT) in the detection of lymph node (LN) metastases in patients with known lung cancer compared to ¹⁸F-fluorodeoxyglucose positron emission tomography (PET)/CT as a reference.

Methods

This retrospective analysis included 381 patients with 1,799 lymph nodes (450 malignant, 1,349 negative). The data set was divided into a training and validation set. A radiomics analysis with 4 filters and 6 algorithms resulting in 24 different radiomics signatures and a bootstrap algorithm (Bagging) with 30 bootstrap iterations was performed. A decision curve analysis was applied to generate a net benefit to compare the radiomics signature to two expert radiologists as one-by-one and as a prescreening tool in combination with the respective radiologist and only the radiologists.

Results

All 24 modeling methods showed good and reliable discrimination for malignant/benign LNs (area under the curve 0.75−0.87). The decision curve analysis showed a net benefit for the least absolute shrinkage and selection operator (LASSO) classifier for the entire probability range and outperformed the expert radiologists except for the high probability range. Using the radiomics signature as a prescreening tool for the radiologists did not improve net benefit.

Conclusions

Radiomics showed good discrimination power irrespective of the modeling technique in detecting LN metastases in patients with known lung cancer. The LASSO classifier was a suitable diagnostic tool and even outperformed the expert radiologists, except for high probabilities. Radiomics failed to improve clinical benefit as a prescreening tool.

Supplementary Information

The online version contains supplementary material available at 10.1186/s41747-022-00296-8.

Ultrasound-based radiomics for predicting different pathological subtypes of epithelial ovarian cancer before surgery

Objective

To evaluate the value of ultrasound-based radiomics in the preoperative prediction of type I and type II epithelial ovarian cancer.

Methods

A total of 154 patients with epithelial ovarian cancer were enrolled retrospectively. There were 102 unilateral lesions and 52 bilateral lesions among a total of 206 lesions. The data for the 206 lesions were randomly divided into a training set (53 type I + 71 type II) and a test set (36 type I + 46 type II) by random sampling. ITK-SNAP software was used to manually outline the boundary of the tumor, that is, the region of interest, and 4976 features were extracted. The quantitative expression values of the radiomics features were normalized by the Z-score method, and the 7 features with the most differences were screened by using the Lasso regression tenfold cross-validation method. The radiomics model was established by logistic regression. The training set was used to construct the model, and the test set was used to evaluate the predictive efficiency of the model. On the basis of multifactor logistic regression analysis, combined with the radiomics score of each patient, a comprehensive prediction model was established, the nomogram was drawn, and the prediction effect was evaluated by analyzing the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve.

Results

The AUCs of the training set and test set in the radiomics model and comprehensive model were 0.817 and 0.731 and 0.982 and 0.886, respectively. The calibration curve showed that the two models were in good agreement. The clinical decision curve showed that both methods had good clinical practicability.

Conclusion

The radiomics model based on ultrasound images has a good predictive effect for the preoperative differential diagnosis of type I and type II epithelial ovarian cancer. The comprehensive model has higher prediction efficiency.

Stakeholders' perspectives on the future of artificial intelligence in radiology: a scoping review

OBJECTIVES

Artificial intelligence (AI) has the potential to impact clinical practice and healthcare delivery. AI is of particular significance in radiology due to its use in automatic analysis of image characteristics. This scoping review examines stakeholder perspectives on AI use in radiology, the benefits, risks, and challenges to its integration.

METHODS

A search was conducted from 1960 to November 2019 in EMBASE, PubMed/MEDLINE, Web of Science, Cochrane Library, CINAHL, and grey literature. Publications reflecting stakeholder attitudes toward AI were included with no restrictions.

RESULTS

Commentaries (n = 32), surveys (n = 13), presentation abstracts (n = 8), narrative reviews (n = 8), and a social media study (n = 1) were included from 62 eligible publications. These represent the views of radiologists, surgeons, medical students, patients, computer scientists, and the general public. Seven themes were identified (predicted impact, potential replacement, trust in AI, knowledge of AI, education, economic considerations, and medicolegal implications). Stakeholders anticipate a significant impact on radiology, though replacement of radiologists is unlikely in the near future. Knowledge of AI is limited for non-computer scientists and further education is desired. Many expressed the need for collaboration between radiologists and AI specialists to successfully improve patient care.

CONCLUSIONS

Stakeholder views generally suggest that AI can improve the practice of radiology and consider the replacement of radiologists unlikely. Most stakeholders identified the need for education and training on AI, as well as collaborative efforts to improve AI implementation. Further research is needed to gain perspectives from non-Western countries, non-radiologist stakeholders, on economic considerations, and medicolegal implications.

KEY POINTS

Stakeholders generally expressed that AI alone cannot be used to replace radiologists. The scope of practice is expected to shift with AI use affecting areas from image interpretation to patient care. Patients and the general public do not know how to address potential errors made by AI systems while radiologists believe that they should be "in-the-loop" in terms of responsibility. Ethical accountability strategies must be developed across governance levels. Students, residents, and radiologists believe that there is a lack in AI education during medical school and residency. The radiology community should work with IT specialists to ensure that AI technology benefits their work and centres patients.

Sources of variation in multicenter rectal MRI data and their effect on radiomics feature reproducibility

OBJECTIVES

To investigate sources of variation in a multicenter rectal cancer MRI dataset focusing on hardware and image acquisition, segmentation methodology, and radiomics feature extraction software.

METHODS

T2W and DWI/ADC MRIs from 649 rectal cancer patients were retrospectively acquired in 9 centers. Fifty-two imaging features (14 first-order/6 shape/32 higher-order) were extracted from each scan using whole-volume (expert/non-expert) and single-slice segmentations using two different software packages (PyRadiomics/CapTk). Influence of hardware, acquisition, and patient-intrinsic factors (age/gender/cTN-stage) on ADC was assessed using linear regression. Feature reproducibility was assessed between segmentation methods and software packages using the intraclass correlation coefficient.

RESULTS

Image features differed significantly (p < 0.001) between centers with more substantial variations in ADC compared to T2W-MRI. In total, 64.3% of the variation in mean ADC was explained by differences in hardware and acquisition, compared to 0.4% by patient-intrinsic factors. Feature reproducibility between expert and non-expert segmentations was good to excellent (median ICC 0.89-0.90). Reproducibility for single-slice versus whole-volume segmentations was substantially poorer (median ICC 0.40-0.58). Between software packages, reproducibility was good to excellent (median ICC 0.99) for most features (first-order/shape/GLCM/GLRLM) but poor for higher-order (GLSZM/NGTDM) features (median ICC 0.00-0.41).

CONCLUSIONS

Significant variations are present in multicenter MRI data, particularly related to differences in hardware and acquisition, which will likely negatively influence subsequent analysis if not corrected for. Segmentation variations had a minor impact when using whole volume segmentations. Between software packages, higher-order features were less reproducible and caution is warranted when implementing these in prediction models.

KEY POINTS

• Features derived from T2W-MRI and in particular ADC differ significantly between centers when performing multicenter data analysis. • Variations in ADC are mainly (> 60%) caused by hardware and image acquisition differences and less so (< 1%) by patient- or tumor-intrinsic variations. • Features derived using different image segmentations (expert/non-expert) were reproducible, provided that whole-volume segmentations were used. When using different feature extraction software packages with similar settings, higher-order features were less reproducible.

AI-RADS: An Artificial Intelligence Curriculum for Residents

Rationale and Objectives

Artificial intelligence (AI) has rapidly emerged as a field poised to affect nearly every aspect of medicine, especially radiology. A PubMed search for the terms “artificial intelligence radiology” demonstrates an exponential increase in publications on this topic in recent years. Despite these impending changes, medical education designed for future radiologists have only recently begun. We present our institution's efforts to address this problem as a model for a successful introductory curriculum into artificial intelligence in radiology titled AI-RADS.

Materials and Methods

The course was based on a sequence of foundational algorithms in AI; these algorithms were presented as logical extensions of each other and were introduced as familiar examples (spam filters, movie recommendations, etc.). Since most trainees enter residency without computational backgrounds, secondary lessons, such as pixel mathematics, were integrated in this progression. Didactic sessions were reinforced with a concurrent journal club highlighting the algorithm discussed in the previous lecture. To circumvent often intimidating technical descriptions, study guides for these papers were produced. Questionnaires were administered before and after each lecture to assess confidence in the material. Surveys were also submitted at each journal club assessing learner preparedness and appropriateness of the article.

Results

The course received a 9.8/10 rating from residents for overall satisfaction. With the exception of the final lecture, there were significant increases in learner confidence in reading journal articles on AI after each lecture. Residents demonstrated significant increases in perceived understanding of foundational concepts in artificial intelligence across all mastery questions for every lecture.

Conclusion

The success of our institution's pilot AI-RADS course demonstrates a workable model of including AI in resident education.

A Comprehensive Review on Radiomics and Deep Learning for Nasopharyngeal Carcinoma Imaging

Nasopharyngeal carcinoma (NPC) is one of the most common malignant tumours of the head and neck, and improving the efficiency of its diagnosis and treatment strategies is an important goal. With the development of the combination of artificial intelligence (AI) technology and medical imaging in recent years, an increasing number of studies have been conducted on image analysis of NPC using AI tools, especially radiomics and artificial neural network methods. In this review, we present a comprehensive overview of NPC imaging research based on radiomics and deep learning. These studies depict a promising prospect for the diagnosis and treatment of NPC. The deficiencies of the current studies and the potential of radiomics and deep learning for NPC imaging are discussed. We conclude that future research should establish a large-scale labelled dataset of NPC images and that studies focused on screening for NPC using AI are necessary.

Machine-Learning-Derived Nomogram Based on 3D Radiomic Features and Clinical Factors Predicts Progression-Free Survival in Lung Adenocarcinoma

BACKGROUND

To establish a machine-learning-derived nomogram based on radiomic features and clinical factors to predict post-surgical 2-year progression-free survival (PFS) in patients with lung adenocarcinoma.

METHODS

Patients with >2 years post-surgical prognosis results of lung adenocarcinoma were included in Hospital-1 for model training (n = 100) and internal validation (n = 50), and in Hospital-2 for external testing (n = 50). A total of 1,672 radiomic features were extracted from 3D segmented CT images. The Rad-score was established using random survival forest by accumulating and weighting the top-20 imaging features contributive to PFS. A nomogram for predicting PFS was established, which comprised the Rad-score and clinical factors highly relevant to PFS.

RESULTS

In the training, internal validation, and external test groups, 69/100 (69%), 37/50 (74%) and 36/50 (72%) patients were progression-free at two years, respectively. According to the Rad-score, the integral of area under the curve (iAUC) for discriminating high and low risk of progression was 0.92 (95%CI: 0.77-1.0), 0.70 (0.41-0.98) and 0.90 (0.65-1.0), respectively. The C-index of Rad-score was 0.781 and 0.860 in the training and external test groups, higher than 0.707 and 0.606 for TNM stage, respectively. The nomogram integrating Rad-score and clinical factors (lung nodule type, cM stage and histological type) achieved a C-index of 0.845 and 0.837 to predict 2-year PFS, respectively, significantly higher than by only radiomic features (all p < 0.01).

CONCLUSION

The nomogram comprising CT-derived radiomic features and risk factors showed a high performance in predicting post-surgical 2-year PFS of patients with lung adenocarcinoma, which may help personalize the treatment decisions.

A review of AI and Data Science support for cancer management

INTRODUCTION

Thanks to improvement of care, cancer has become a chronic condition. But due to the toxicity of treatment, the importance of supporting the quality of life (QoL) of cancer patients increases. Monitoring and managing QoL relies on data collected by the patient in his/her home environment, its integration, and its analysis, which supports personalization of cancer management recommendations. We review the state-of-the-art of computerized systems that employ AI and Data Science methods to monitor the health status and provide support to cancer patients managed at home.

OBJECTIVE

Our main objective is to analyze the literature to identify open research challenges that a novel decision support system for cancer patients and clinicians will need to address, point to potential solutions, and provide a list of established best-practices to adopt.

METHODS

We designed a review study, in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, analyzing studies retrieved from PubMed related to monitoring cancer patients in their home environments via sensors and self-reporting: what data is collected, what are the techniques used to collect data, semantically integrate it, infer the patient's state from it and deliver coaching/behavior change interventions.

RESULTS

Starting from an initial corpus of 819 unique articles, a total of 180 papers were considered in the full-text analysis and 109 were finally included in the review. Our findings are organized and presented in four main sub-topics consisting of data collection, data integration, predictive modeling and patient coaching.

CONCLUSION

Development of modern decision support systems for cancer needs to utilize best practices like the use of validated electronic questionnaires for quality-of-life assessment, adoption of appropriate information modeling standards supplemented by terminologies/ontologies, adherence to FAIR data principles, external validation, stratification of patients in subgroups for better predictive modeling, and adoption of formal behavior change theories. Open research challenges include supporting emotional and social dimensions of well-being, including PROs in predictive modeling, and providing better customization of behavioral interventions for the specific population of cancer patients.

Development of a Malignancy Potential Binary Prediction Model Based on Deep Learning for the Mitotic Count of Local Primary Gastrointestinal Stromal Tumors

Objective

The mitotic count of gastrointestinal stromal tumors (GIST) is closely associated with the risk of planting and metastasis. The purpose of this study was to develop a predictive model for the mitotic index of local primary GIST, based on deep learning algorithm.

Materials and Methods

Abdominal contrast-enhanced CT images of 148 pathologically confirmed GIST cases were retrospectively collected for the development of a deep learning classification algorithm. The areas of GIST masses on the CT images were retrospectively labelled by an experienced radiologist. The postoperative pathological mitotic count was considered as the gold standard (high mitotic count, > 5/50 high-power fields [HPFs]; low mitotic count, ≤ 5/50 HPFs). A binary classification model was trained on the basis of the VGG16 convolutional neural network, using the CT images with the training set (n = 108), validation set (n = 20), and the test set (n = 20). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both, the image level and the patient level. The receiver operating characteristic curves were generated on the basis of the model prediction results and the area under curves (AUCs) were calculated. The risk categories of the tumors were predicted according to the Armed Forces Institute of Pathology criteria.

Results

At the image level, the classification prediction results of the mitotic counts in the test cohort were as follows: sensitivity 85.7% (95% confidence interval [CI]: 0.834–0.877), specificity 67.5% (95% CI: 0.636–0.712), PPV 82.1% (95% CI: 0.797–0.843), NPV 73.0% (95% CI: 0.691–0.766), and AUC 0.771 (95% CI: 0.750–0.791). At the patient level, the classification prediction results in the test cohort were as follows: sensitivity 90.0% (95% CI: 0.541–0.995), specificity 70.0% (95% CI: 0.354–0.919), PPV 75.0% (95% CI: 0.428–0.933), NPV 87.5% (95% CI: 0.467–0.993), and AUC 0.800 (95% CI: 0.563–0.943).

Conclusion

We developed and preliminarily verified the GIST mitotic count binary prediction model, based on the VGG convolutional neural network. The model displayed a good predictive performance.

Radiomics and Bladder Cancer: Current Status

PURPOSE: To systematically review the current literature and discuss the applications and limitations of radiomics and machine-learning augmented radiomics in the management of bladder cancer. METHODS: Pubmed ®, Scopus ®, and Web of Science ® databases were searched systematically for all full-text English-language articles assessing the impact of Artificial Intelligence OR Radiomics OR Machine Learning AND Bladder Cancer AND (staging OR grading OR prognosis) published up to January 2020. RESULTS: Of the 686 articles that were identified, 13 studies met the criteria for quantitative analysis. Staging, Grading and Tumor Classification, Prognosis, and Therapy Response were discussed in 7, 3, 2 and 7 studies, respectively. Data on cost of implementation were not reported. CT and MRI were the most common imaging approaches. CONCLUSION: Radiomics shows potential in bladder cancer detection, staging, grading, and response to therapy, thereby supporting the physician in personalizing patient management. Extension and validation of this promising technology in large multisite prospective trials is warranted to pave the way for its clinical translation.

An analysis of key indicators of reproducibility in radiology

BACKGROUND

Given the central role of radiology in patient care, it is important that radiological research is grounded in reproducible science. It is unclear whether there is a lack of reproducibility or transparency in radiologic research.

PURPOSE

To analyze published radiology literature for the presence or lack of key indicators of reproducibility.

METHODS

This cross-sectional retrospective study was performed by conducting a search of the National Library of Medicine (NLM) for publications contained within journals in the field of radiology. Our inclusion criteria were being MEDLINE indexed, written in English, and published from January 1, 2014, to December 31, 2018. We randomly sampled 300 publications for this study. A pilot-tested Google form was used to record information from the publications regarding indicators of reproducibility. Following peer-review, we extracted data from an additional 200 publications in an attempt to reproduce our initial results. The additional 200 publications were selected from the list of initially randomized publications.

RESULTS

Our initial search returned 295,543 records, from which 300 were randomly selected for analysis. Of these 300 records, 294 met inclusion criteria and 6 did not. Among the empirical publications, 5.6% (11/195, [3.0-8.3]) contained a data availability statement, 0.51% (1/195) provided clear documented raw data, 12.0% (23/191, [8.4-15.7]) provided a materials availability statement, 0% provided analysis scripts, 4.1% (8/195, [1.9-6.3]) provided a pre-registration statement, 2.1% (4/195, [0.4-3.7]) provided a protocol statement, and 3.6% (7/195, [1.5-5.7]) were pre-registered. The validation study of the 5 key indicators of reproducibility-availability of data, materials, protocols, analysis scripts, and pre-registration-resulted in 2 indicators (availability of protocols and analysis scripts) being reproduced, as they fell within the 95% confidence intervals for the proportions from the original sample. However, materials' availability and pre-registration proportions from the validation sample were lower than what was found in the original sample.

CONCLUSION

Our findings demonstrate key indicators of reproducibility are missing in the field of radiology. Thus, the ability to reproduce studies contained in radiology publications may be problematic and may have potential clinical implications.

A Shallow Convolutional Neural Network Predicts Prognosis of Lung Cancer Patients in Multi-Institutional CT-Image Data

Lung cancer is the most common fatal malignancy in adults worldwide, and non-small cell lung cancer (NSCLC) accounts for 85% of lung cancer diagnoses. Computed tomography (CT) is routinely used in clinical practice to determine lung cancer treatment and assess prognosis. Here, we developed LungNet, a shallow convolutional neural network for predicting outcomes of NSCLC patients. We trained and evaluated LungNet on four independent cohorts of NSCLC patients from four medical centers: Stanford Hospital (n = 129), H. Lee Moffitt Cancer Center and Research Institute (n = 185), MAASTRO Clinic (n = 311) and Charité - Universitätsmedizin (n=84). We show that outcomes from LungNet are predictive of overall survival in all four independent survival cohorts as measured by concordance indices of 0.62, 0.62, 0.62 and 0.58 on cohorts 1, 2, 3, and 4, respectively. Further, the survival model can be used, via transfer learning, for classifying benign vs malignant nodules on the Lung Image Database Consortium (n = 1010), with improved performance (AUC=0.85) versus training from scratch (AUC=0.82). LungNet can be used as a noninvasive predictor for prognosis in NSCLC patients and can facilitate interpretation of CT images for lung cancer stratification and prognostication.

A review of original articles published in the emerging field of radiomics

PURPOSE

To determine the characteristics of and trends in research in the emerging field of radiomics through bibliometric and hotspot analyses of relevant original articles published between 2013 and 2018.

METHODS

We evaluated 553 original articles concerning radiomics, published in a total of 61 peer-reviewed journals between 2013 and 2018. The following information was retrieved for each article: radiological subspecialty, imaging technique(s), machine learning technique(s), sample size, study setting and design, statistical result(s), study purpose, software used for feature calculation, funding declarations, author number, first author's affiliation, study origin, and journal name. Qualitative and quantitative analyses were performed for the manually extracted data for identification and visualization of the trends in radiomics research.

RESULTS

The annual growth rate in the number of published papers was 177.82% (p < 0.001). The characteristics and trends of research hotspots in the field of radiomics were clarified and visualized in this study. It was found that the field of radiomics is at a more mature stage for lung, breast, and prostate cancers than for other sites. Radiomics studies primarily focused on radiological characterization (215) and monitoring (182). Logistic regression and LASSO were the two most commonly used techniques for feature selection. Non-clinical researchers without a medical background dominated radiomics studies (70.52%), the vast majority of which only highlighted positive results (97.80%) while downplaying negative findings.

CONCLUSIONS

The reporting of quantifiable knowledge about the characteristics and trajectories of radiomics can inform researchers about the gaps in the field of radiomics and guide its future direction.

Preoperative diagnosis of malignant pulmonary nodules in lung cancer screening with a radiomics nomogram

Background

Lung cancer is the most commonly diagnosed cancer worldwide. Its survival rate can be significantly improved by early screening. Biomarkers based on radiomics features have been found to provide important physiological information on tumors and considered as having the potential to be used in the early screening of lung cancer. In this study, we aim to establish a radiomics model and develop a tool to improve the discrimination between benign and malignant pulmonary nodules.

Methods

A retrospective study was conducted on 875 patients with benign or malignant pulmonary nodules who underwent computed tomography (CT) examinations between June 2013 and June 2018. We assigned 612 patients to a training cohort and 263 patients to a validation cohort. Radiomics features were extracted from the CT images of each patient. Least absolute shrinkage and selection operator (LASSO) was used for radiomics feature selection and radiomics score calculation. Multivariate logistic regression analysis was used to develop a classification model and radiomics nomogram. Radiomics score and clinical variables were used to distinguish benign and malignant pulmonary nodules in logistic model. The performance of the radiomics nomogram was evaluated by the area under the curve (AUC), calibration curve and Hosmer‐Lemeshow test in both the training and validation cohorts.

Results

A radiomics score was built and consisted of 20 features selected by LASSO from 1288 radiomics features in the training cohort. The multivariate logistic model and radiomics nomogram were constructed using the radiomics score and patients’ age. Good discrimination of benign and malignant pulmonary nodules was obtained from the training cohort (AUC, 0.836; 95% confidence interval [CI]: 0.793‐0.879) and validation cohort (AUC, 0.809; 95% CI: 0.745‐0.872). The Hosmer‐Lemeshow test also showed good performance for the logistic regression model in the training cohort (P = 0.765) and validation cohort (P = 0.064). Good alignment with the calibration curve indicated the good performance of the nomogram.

Conclusions

The established radiomics nomogram is a noninvasive preoperative prediction tool for malignant pulmonary nodule diagnosis. Validation revealed that this nomogram exhibited excellent discrimination and calibration capacities, suggesting its clinical utility in the early screening of lung cancer.

[A primer on radiomics]

CLINICAL ISSUE

The reproducible and exhaustive extraction of information from radiological images is a central task in the practice of radiology. Dynamic developments in the fields of artificial intelligence (AI) and machine learning are introducing new methods for this task. Radiomics is one such method and offers new opportunities and challenges for the future of radiology.

METHODOLOGICAL INNOVATIONS

Radiomics describes the quantitative evaluation, interpretation, and clinical assessment of imaging markers in radiological data. Components of a radiomics analysis are data acquisition, data preprocessing, data management, segmentation of regions of interest, computation and selection of imaging markers, as well as the development of a radiomics model used for diagnosis and prognosis. This article explains these components and aims at providing an introduction to the field of radiomics while highlighting existing limitations.

MATERIALS AND METHODS

This article is based on a selective literature search with the PubMed search engine.

ASSESSMENT

Even though radiomics applications have yet to arrive in routine clinical practice, the quantification of radiological data in terms of radiomics is underway and will increase in the future. This holds the potential for lasting change in the discipline of radiology. Through the successful extraction and interpretation of all the information encoded in radiological images the next step in the direction of a more personalized, future-oriented form of medicine can be taken.

Proceedings of the fourth international molecular pathological epidemiology (MPE) meeting

An important premise of epidemiology is that individuals with the same disease share similar underlying etiologies and clinical outcomes. In the past few decades, our knowledge of disease pathogenesis has improved, and disease classification systems have evolved to the point where no complex disease processes are considered homogenous. As a result, pathology and epidemiology have been integrated into the single, unified field of molecular pathological epidemiology (MPE). Advancing integrative molecular and population-level health sciences and addressing the unique research challenges specific to the field of MPE necessitates assembling experts in diverse fields, including epidemiology, pathology, biostatistics, computational biology, bioinformatics, genomics, immunology, and nutritional and environmental sciences. Integrating these seemingly divergent fields can lead to a greater understanding of pathogenic processes. The International MPE Meeting Series fosters discussion that addresses the specific research questions and challenges in this emerging field. The purpose of the meeting series is to: discuss novel methods to integrate pathology and epidemiology; discuss studies that provide pathogenic insights into population impact; and educate next-generation scientists. Herein, we share the proceedings of the Fourth International MPE Meeting, held in Boston, MA, USA, on 30 May-1 June, 2018. Major themes of this meeting included 'integrated genetic and molecular pathologic epidemiology', 'immunology-MPE', and 'novel disease phenotyping'. The key priority areas for future research identified by meeting attendees included integration of tumor immunology and cancer disparities into epidemiologic studies, further collaboration between computational and population-level scientists to gain new insight on exposure-disease associations, and future pooling projects of studies with comparable data.

Integrating molecular nuclear imaging in clinical research to improve anticancer therapy

Effective patient selection before or early during treatment is important to increasing the therapeutic benefits of anticancer treatments. This selection process is often predicated on biomarkers, predominantly biospecimen biomarkers derived from blood or tumour tissue; however, such biomarkers provide limited information about the true extent of disease or about the characteristics of different, potentially heterogeneous tumours present in an individual patient. Molecular imaging can also produce quantitative outputs; such imaging biomarkers can help to fill these knowledge gaps by providing complementary information on tumour characteristics, including heterogeneity and the microenvironment, as well as on pharmacokinetic parameters, drug-target engagement and responses to treatment. This integrative approach could therefore streamline biomarker and drug development, although a range of issues need to be overcome in order to enable a broader use of molecular imaging in clinical trials. In this Perspective article, we outline the multistage process of developing novel molecular imaging biomarkers. We discuss the challenges that have restricted the use of molecular imaging in clinical oncology research to date and outline future opportunities in this area.

Radiogenomics in renal cell carcinoma

Radiogenomics, a field of radiology investigating the association between the imaging features of a disease and its gene expression pattern, has expanded considerably in the last few years. Recent advances in whole-genome sequencing of clear cell renal cell carcinoma (ccRCC) and the identification of mutations with prognostic significance have led to increased interest in the relationship between imaging and genomic data. ccRCC is particularly suitable for radiogenomic analysis as the relative paucity of mutated genes allows for more straightforward genomic-imaging associations. The ultimate aim of radiogenomics of ccRCC is to retrieve additional data for accurate diagnosis, prognostic stratification, and optimization of therapy. In this review article, we will present the state-of-the-art of radiogenomics of ccRCC, and after briefly reviewing updates in genomics, we will discuss imaging-genomic associations for diagnosis and staging, prognosis, and for assessment of optimal therapy in ccRCC.

The Big Picture on the "AI Turn" for Digital Health: The Internet of Things and Cyber-Physical Systems

This article offers an analysis of the ways in which digital health innovations are being coproduced by mainstreaming of artificial intelligence (AI), the Internet of Things (IoT), and cyber-physical systems (CPS) in health care. CPS blurs the boundaries between the physical and virtual worlds, and creates a dynamic digital map of all things in existence that can be analyzed in ways that are much more sophisticated than a bar code scanning system. Examples of CPS include self-driving cars, wearables for digital monitoring of heart arrhythmias, industrial AI-powered robots in smart factories and health robots delivering home care services to disabled persons and rural communities. Another interesting prospect of digital health powered by AI, IoT, and CPS is remote phenotypic data capture and characterization of pharmaceutical outcomes in clinical trials in ways that are user centric and meaningful to patients. For rural or remote communities with limited access to medical product information, the IoT could bring about pharmacy and health services innovation. There are unprecedented societal challenges at intersections of digital health with AI, IoT, and CPS as well. For example, the physical and virtual worlds markedly differ in speed, scale, and temporalities, as do our physical self and digital footprints. Our efforts to map and develop effective solutions to societal corollaries of AI, IoT, and CPS need to bear in mind such asymmetries between the physical and virtual worlds. A societal issue such as privacy may emerge in different forms and intensities in the physical and virtual contexts. Digital data are highly fluid and can rapidly move across spaces and places, whereas the physical data and humans are much slower and exist in different scales than our digital footprints. It is therefore timely for the system sciences and integrative biology communities to critically engage with digital health and the related technologies, such as AI, IoT, and CPS.

Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging

PURPOSE

Tumors are continuously evolving biological systems, and medical imaging is uniquely positioned to monitor changes throughout treatment. Although qualitatively tracking lesions over space and time may be trivial, the development of clinically relevant, automated radiomics methods that incorporate serial imaging data is far more challenging. In this study, we evaluated deep learning networks for predicting clinical outcomes through analyzing time series CT images of patients with locally advanced non-small cell lung cancer (NSCLC).Experimental Design: Dataset A consists of 179 patients with stage III NSCLC treated with definitive chemoradiation, with pretreatment and posttreatment CT images at 1, 3, and 6 months follow-up (581 scans). Models were developed using transfer learning of convolutional neural networks (CNN) with recurrent neural networks (RNN), using single seed-point tumor localization. Pathologic response validation was performed on dataset B, comprising 89 patients with NSCLC treated with chemoradiation and surgery (178 scans).

RESULTS

Deep learning models using time series scans were significantly predictive of survival and cancer-specific outcomes (progression, distant metastases, and local-regional recurrence). Model performance was enhanced with each additional follow-up scan into the CNN model (e.g., 2-year overall survival: AUC = 0.74, P < 0.05). The models stratified patients into low and high mortality risk groups, which were significantly associated with overall survival [HR = 6.16; 95% confidence interval (CI), 2.17-17.44; P < 0.001]. The model also significantly predicted pathologic response in dataset B (P = 0.016).

CONCLUSIONS

We demonstrate that deep learning can integrate imaging scans at multiple timepoints to improve clinical outcome predictions. AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic given their low cost and minimal requirements for human input.

Radiomics in Kidney Cancer: MR Imaging

Renal tumors encompass a heterogeneous disease spectrum, which confounds patient management and treatment. Percutaneous biopsy is limited by an inability to sample every part of the tumor. Radiomics may provide detail beyond what can be achieved from human interpretation. Understanding what new technologies offer will allow radiologists to play a greater role in caring for patients with renal cell carcinoma. In this article, we review the use of radiomics in renal cell carcinoma, in both the pretreatment assessment of renal masses and posttreatment evaluation of renal cell carcinoma, with special emphasis on the use of multiparametric MR imaging datasets.

Developed and validated a prognostic nomogram for recurrence-free survival after complete surgical resection of local primary gastrointestinal stromal tumors based on deep learning

This study aimed to develop and validate a prognostic nomogram for recurrence-free survival (RFS) after surgery in the absence of adjuvant therapy to guide the selection for adjuvant imatinib therapy based on Residual Neural Network (ResNet). The ResNet model was developed based on contrast-enhanced computed tomography (CE-CT) in a training cohort consisted of 80 patients pathologically diagnosed gastrointestinal sromal tumors (GISTs) and validated in internal and external validation cohort respectively. Independent clinicopathologic factors were integrated with the ResNet model to construct the individualized nomogram. The performance of the nomogram was evaluated in regard to discrimination, calibration, and clinical usefulness. The ResNet model was significantly associated with RFS. Integrable predictors in the individualized ResNet nomogram included the tumor site, size, and mitotic count. Compared with modified NIH, AFIP, and clinicopathologic nomogram, both ResNet nomogram and ResNet model showed a better discrimination capability with AUCs of 0·947(95%CI, 0·910-0·984) for 3-year-RFS, 0·918(0·852-0·984) for 5-year-RFS, and AUCs of 0·912 (0·851-0·973) for 3-year-RFS, 0·887(0·816-0·960) for 5-year-RFS, respectively. Calibration curve shows the good calibration of the nomogram in terms of the agreement between the estimated and the observed 3- and 5- year outcomes. Decision curve analysis showed that the ResNet nomogram had a higher overall net benefit. In conclusion, we presented a deep learning-based prognostic nomogram to predict RFS after resection of localized primary GISTs with excellent performance and could be a potential tool to select patients for adjuvant imatinib therapy.

Abbreviated MRI Protocols in Breast Cancer Diagnostics

Oncologic imaging focused on the detection of breast cancer is of increasing importance, with over 1.7 million new cases detected each year worldwide. MRI of the breast has been described to be one of the most sensitive imaging modalities in breast cancer detection; however, clinical use is limited due to high costs. In the past, the objective and clinical routine of oncologic imaging was to provide one extended imaging protocol covering all potential needs and clinical implications regardless of the specific clinical indication or question. Future protocols might be more focused according to a "keep it short and simple" approach, with a reduction of patient magnet time and a limited number of images to review. Rather than replacing conventional full-diagnostic breast MRI protocols, these approaches aim at introducing a new thinking in oncologic imaging using a diversification of available imaging approaches targeted to the dedicated clinical needs of the individual patient. Here we review current approaches on using abbreviated protocols that aim to increase the clinical availability and use of breast MRI for improved early detection of breast cancer. Level of Evidence: 2 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;49:647-658.

Data Analysis Strategies in Medical Imaging

Radiographic imaging continues to be one of the most effective and clinically useful tools within oncology. Sophistication of artificial intelligence has allowed for detailed quantification of radiographic characteristics of tissues using predefined engineered algorithms or deep learning methods. Precedents in radiology as well as a wealth of research studies hint at the clinical relevance of these characteristics. However, critical challenges are associated with the analysis of medical imaging data. Although some of these challenges are specific to the imaging field, many others like reproducibility and batch effects are generic and have already been addressed in other quantitative fields such as genomics. Here, we identify these pitfalls and provide recommendations for analysis strategies of medical imaging data, including data normalization, development of robust models, and rigorous statistical analyses. Adhering to these recommendations will not only improve analysis quality but also enhance precision medicine by allowing better integration of imaging data with other biomedical data sources. Clin Cancer Res; 24(15); 3492-9. ©2018 AACR.