Artificial intelligence: a critical review of current applications in pancreatic imaging

Assessing radiologists' and radiographers' perceptions on artificial intelligence integration: opportunities and challenges

OBJECTIVES

The objective of this study was to evaluate radiologists' and radiographers' opinions and perspectives on artificial intelligence (AI) and its integration into the radiology department. Additionally, we investigated the most common challenges and barriers that radiologists and radiographers face when learning about AI.

METHODS

A nationwide, online descriptive cross-sectional survey was distributed to radiologists and radiographers working in hospitals and medical centres from May 29, 2023 to July 30, 2023. The questionnaire examined the participants' opinions, feelings, and predictions regarding AI and its applications in the radiology department. Descriptive statistics were used to report the participants' demographics and responses. Five-points Likert-scale data were reported using divergent stacked bar graphs to highlight any central tendencies.

RESULTS

Responses were collected from 258 participants, revealing a positive attitude towards implementing AI. Both radiologists and radiographers predicted breast imaging would be the subspecialty most impacted by the AI revolution. MRI, mammography, and CT were identified as the primary modalities with significant importance in the field of AI application. The major barrier encountered by radiologists and radiographers when learning about AI was the lack of mentorship, guidance, and support from experts.

CONCLUSION

Participants demonstrated a positive attitude towards learning about AI and implementing it in the radiology practice. However, radiologists and radiographers encounter several barriers when learning about AI, such as the absence of experienced professionals support and direction.

ADVANCES IN KNOWLEDGE

Radiologists and radiographers reported several barriers to AI learning, with the most significant being the lack of mentorship and guidance from experts, followed by the lack of funding and investment in new technologies.

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

PURPOSE

This multicenter retrospective study aims to identify reliable clinical and radiomic features to build machine learning models that predict progression-free survival (PFS) and overall survival (OS) in pancreatic ductal adenocarcinoma (PDAC) patients.

METHODS

Between 2010 and 2020 pre-treatment contrast-enhanced CT scans of 287 pathology-confirmed PDAC patients from two sites of the Hopital Universitaire de Bruxelles (HUB) and from 47 hospitals within the HUB network were retrospectively analysed. Demographic, clinical, and survival data were also collected. Gross tumour volume (GTV) and non-tumoral pancreas (RPV) were semi-manually segmented and radiomics features were extracted. Patients from two HUB sites comprised the training dataset, while those from the remaining 47 hospitals of the HUB network constituted the testing dataset. A three-step method was used for feature selection. Based on the GradientBoostingSurvivalAnalysis classifier, different machine learning models were trained and tested to predict OS and PFS. Model performances were assessed using the C-index and Kaplan-Meier curves. SHAP analysis was applied to allow for post hoc interpretability.

RESULTS

A total of 107 radiomics features were extracted from each of the GTV and RPV. Fourteen subgroups of features were selected: clinical, GTV, RPV, clinical & GTV, clinical & GTV & RPV, GTV-volume and RPV-volume both for OS and PFS. Subsequently, 14 Gradient Boosting Survival Analysis models were trained and tested. In the testing dataset, the clinical & GTV model demonstrated the highest performance for OS (C-index: 0.72) among all other models, while for PFS, the clinical model exhibited a superior performance (C-index: 0.70).

CONCLUSIONS

An integrated approach, combining clinical and radiomics features, excels in predicting OS, whereas clinical features demonstrate strong performance in PFS prediction.

CT and MRI of abdominal cancers: current trends and perspectives in the era of radiomics and artificial intelligence

Abdominal cancers continue to pose daily challenges to clinicians, radiologists and researchers. These challenges are faced at each stage of abdominal cancer management, including early detection, accurate characterization, precise assessment of tumor spread, preoperative planning when surgery is anticipated, prediction of tumor aggressiveness, response to therapy, and detection of recurrence. Technical advances in medical imaging, often in combination with imaging biomarkers, show great promise in addressing such challenges. Information extracted from imaging datasets owing to the application of radiomics can be used to further improve the diagnostic capabilities of imaging. However, the analysis of the huge amount of data provided by these advances is a difficult task in daily practice. Artificial intelligence has the potential to help radiologists in all these challenges. Notably, the applications of AI in the field of abdominal cancers are expanding and now include diverse approaches for cancer detection, diagnosis and classification, genomics and detection of genetic alterations, analysis of tumor microenvironment, identification of predictive biomarkers and follow-up. However, AI currently has some limitations that need further refinement for implementation in the clinical setting. This review article sums up recent advances in imaging of abdominal cancers in the field of image/data acquisition, tumor detection, tumor characterization, prognosis, and treatment response evaluation.

Pancreatic Adenocarcinoma: Imaging Modalities and the Role of Artificial Intelligence in Analyzing CT and MRI Images

Pancreatic ductal adenocarcinoma (PDAC) stands out as the predominant malignant neoplasm affecting the pancreas, characterized by a poor prognosis, in most cases patients being diagnosed in a nonresectable stage. Image-based artificial intelligence (AI) models implemented in tumor detection, segmentation, and classification could improve diagnosis with better treatment options and increased survival. This review included papers published in the last five years and describes the current trends in AI algorithms used in PDAC. We analyzed the applications of AI in the detection of PDAC, segmentation of the lesion, and classification algorithms used in differential diagnosis, prognosis, and histopathological and genomic prediction. The results show a lack of multi-institutional collaboration and stresses the need for bigger datasets in order for AI models to be implemented in a clinically relevant manner.

Preliminary assessment of automated radiology report generation with generative pre-trained transformers: comparing results to radiologist-generated reports

PURPOSE

In this preliminary study, we aimed to evaluate the potential of the generative pre-trained transformer (GPT) series for generating radiology reports from concise imaging findings and compare its performance with radiologist-generated reports.

METHODS

This retrospective study involved 28 patients who underwent computed tomography (CT) scans and had a diagnosed disease with typical imaging findings. Radiology reports were generated using GPT-2, GPT-3.5, and GPT-4 based on the patient's age, gender, disease site, and imaging findings. We calculated the top-1, top-5 accuracy, and mean average precision (MAP) of differential diagnoses for GPT-2, GPT-3.5, GPT-4, and radiologists. Two board-certified radiologists evaluated the grammar and readability, image findings, impression, differential diagnosis, and overall quality of all reports using a 4-point scale.

RESULTS

Top-1 and Top-5 accuracies for the different diagnoses were highest for radiologists, followed by GPT-4, GPT-3.5, and GPT-2, in that order (Top-1: 1.00, 0.54, 0.54, and 0.21, respectively; Top-5: 1.00, 0.96, 0.89, and 0.54, respectively). There were no significant differences in qualitative scores about grammar and readability, image findings, and overall quality between radiologists and GPT-3.5 or GPT-4 (p > 0.05). However, qualitative scores of the GPT series in impression and differential diagnosis scores were significantly lower than those of radiologists (p < 0.05).

CONCLUSIONS

Our preliminary study suggests that GPT-3.5 and GPT-4 have the possibility to generate radiology reports with high readability and reasonable image findings from very short keywords; however, concerns persist regarding the accuracy of impressions and differential diagnoses, thereby requiring verification by radiologists.

Improvement of image quality in diffusion-weighted imaging with model-based deep learning reconstruction for evaluations of the head and neck

OBJECTIVES

To investigate the utility of deep learning (DL)-based image reconstruction using a model-based approach in head and neck diffusion-weighted imaging (DWI).

MATERIALS AND METHODS

We retrospectively analyzed the cases of 41 patients who underwent head/neck DWI. The DWI in 25 patients demonstrated an untreated lesion. We performed qualitative and quantitative assessments in the DWI analyses with both deep learning (DL)- and conventional parallel imaging (PI)-based reconstructions. For the qualitative assessment, we visually evaluated the overall image quality, soft tissue conspicuity, degree of artifact(s), and lesion conspicuity based on a five-point system. In the quantitative assessment, we measured the signal-to-noise ratio (SNR) of the bilateral parotid glands, submandibular gland, the posterior muscle, and the lesion. We then calculated the contrast-to-noise ratio (CNR) between the lesion and the adjacent muscle.

RESULTS

Significant differences were observed in the qualitative analysis between the DWI with PI-based and DL-based reconstructions for all of the evaluation items (p < 0.001). In the quantitative analysis, significant differences in the SNR and CNR between the DWI with PI-based and DL-based reconstructions were observed for all of the evaluation items (p = 0.002 ~ p < 0.001).

DISCUSSION

DL-based image reconstruction with the model-based technique effectively provided sufficient image quality in head/neck DWI.

Enhancing pancreatic cancer classification through dynamic weighted ensemble: a game theory approach

The significant research carried out on medical healthcare networks is giving computing innovations lots of space to produce the most recent innovations. Pancreatic cancer, which ranks among of the most common tumors that are thought to be fatal and unsuspected since it is positioned in the region of the abdomen beyond the stomach and can't be adequately treated once diagnosed. In radiological imaging, such as MRI and CT, computer-aided diagnosis (CAD), quantitative evaluations, and automated pancreatic cancer classification approaches are routinely provided. This study provides a dynamic weighted ensemble framework for pancreatic cancer classification inspired by game theory. Grey Level Co-occurrence Matrix (GLCM) is utilized for feature extraction, together with Gaussian kernel-based fuzzy rough sets theory (GKFRST) for feature reduction and the Random Forest (RF) classifier for categorization. The ResNet50 and VGG16 are used in the transfer learning (TL) paradigm. The combination of the outcomes from the TL paradigm and the RF classifier paradigm is suggested using an innovative ensemble classifier that relies on the game theory method. When compared with the current models, the ensemble technique considerably increases the pancreatic cancer classification accuracy and yields exceptional performance. The study improves the categorization of pancreatic cancer by using game theory, a mathematical paradigm that simulates strategic interactions. Because game theory has been not frequently used in the discipline of cancer categorization, this research is distinctive in its methodology.

A preoperative computed tomography radiomics model to predict disease-free survival in patients with pancreatic neuroendocrine tumors

IMPORTANCE

Imaging has demonstrated capabilities in the diagnosis of pancreatic neuroendocrine tumors (pNETs), but its utility for prognostic prediction has not been elucidated yet.

OBJECTIVE

The aim of this study was to build a radiomics model using preoperative computed tomography (CT) data that may help predict recurrence-free survival (RFS) or OS in patients with pNET.

DESIGN

We performed a retrospective observational study in a cohort of French patients with pNETs.

PARTICIPANTS

Patients with surgically resected pNET and available CT examinations were included.

INTERVENTIONS

Radiomics features of preoperative CT data were extracted using 3D-Slicer® software with manual segmentation. Discriminant features were selected with penalized regression using least absolute shrinkage and selection operator method with training on the tumor Ki67 rate (≤2 or >2). Selected features were used to build a radiomics index ranging from 0 to 1.

OUTCOME AND MEASURE

A receiving operator curve was built to select an optimal cutoff value of the radiomics index to predict patient RFS and OS. Recurrence-free survival and OS were assessed using Kaplan-Meier analysis.

RESULTS

Thirty-seven patients (median age, 61 years; 20 men) with 37 pNETs (grade 1, 21/37 [57%]; grade 2, 12/37 [32%]; grade 3, 4/37 [11%]) were included. Patients with a radiomics index >0.4 had a shorter median RFS (36 months; range: 1-133) than those with a radiomics index ≤0.4 (84 months; range: 9-148; P = .013). No associations were found between the radiomics index and OS (P = .86).

Examining the effectiveness of a deep learning-based computer-aided breast cancer detection system for breast ultrasound

PURPOSE

This study aimed to evaluate the clinical usefulness of a deep learning-based computer-aided detection (CADe) system for breast ultrasound.

METHODS

The set of 88 training images was expanded to 14,000 positive images and 50,000 negative images. The CADe system was trained to detect lesions in real- time using deep learning with an improved model of YOLOv3-tiny. Eighteen readers evaluated 52 test image sets with and without CADe. Jackknife alternative free-response receiver operating characteristic analysis was used to estimate the effectiveness of this system in improving lesion detection.

RESULT

The area under the curve (AUC) for image sets was 0.7726 with CADe and 0.6304 without CADe, with a 0.1422 difference, indicating that with CADe was significantly higher than that without CADe (p < 0.0001). The sensitivity per case was higher with CADe (95.4%) than without CADe (83.7%). The specificity of suspected breast cancer cases with CADe (86.6%) was higher than that without CADe (65.7%). The number of false positives per case (FPC) was lower with CADe (0.22) than without CADe (0.43).

CONCLUSION

The use of a deep learning-based CADe system for breast ultrasound by readers significantly improved their reading ability. This system is expected to contribute to highly accurate breast cancer screening and diagnosis.

Current State of Artificial Intelligence in Clinical Applications for Head and Neck MR Imaging

Due primarily to the excellent soft tissue contrast depictions provided by MRI, the widespread application of head and neck MRI in clinical practice serves to assess various diseases. Artificial intelligence (AI)-based methodologies, particularly deep learning analyses using convolutional neural networks, have recently gained global recognition and have been extensively investigated in clinical research for their applicability across a range of categories within medical imaging, including head and neck MRI. Analytical approaches using AI have shown potential for addressing the clinical limitations associated with head and neck MRI. In this review, we focus primarily on the technical advancements in deep-learning-based methodologies and their clinical utility within the field of head and neck MRI, encompassing aspects such as image acquisition and reconstruction, lesion segmentation, disease classification and diagnosis, and prognostic prediction for patients presenting with head and neck diseases. We then discuss the limitations of current deep-learning-based approaches and offer insights regarding future challenges in this field.

New trend in artificial intelligence-based assistive technology for thoracic imaging

Although there is no solid agreement for artificial intelligence (AI), it refers to a computer system with intelligence similar to that of humans. Deep learning appeared in 2006, and more than 10 years have passed since the third AI boom was triggered by improvements in computing power, algorithm development, and the use of big data. In recent years, the application and development of AI technology in the medical field have intensified internationally. There is no doubt that AI will be used in clinical practice to assist in diagnostic imaging in the future. In qualitative diagnosis, it is desirable to develop an explainable AI that at least represents the basis of the diagnostic process. However, it must be kept in mind that AI is a physician-assistant system, and the final decision should be made by the physician while understanding the limitations of AI. The aim of this article is to review the application of AI technology in diagnostic imaging from PubMed database while particularly focusing on diagnostic imaging in thorax such as lesion detection and qualitative diagnosis in order to help radiologists and clinicians to become more familiar with AI in thorax.

Optimized Atlas-Based Auto-Segmentation of Bony Structures from Whole-Body Computed Tomography

PURPOSE

To develop and test a method for fully automated segmentation of bony structures from whole-body computed tomography (CT) and evaluate its performance compared with manual segmentation.

METHODS AND MATERIALS

We developed a workflow for automatic whole-body bone segmentation using atlas-based segmentation (ABS) method with a postprocessing module (ABSPP) in MIM MAESTRO software. Fifty-two CT scans comprised the training set to build the atlas library, and 29 CT scans comprised the test set. To validate the workflow, we compared Dice similarity coefficient (DSC), mean distance to agreement, and relative volume errors between ABSPP and ABS with no postprocessing (ABSNPP) with manual segmentation as the reference (gold standard).

RESULTS

The ABSPP method resulted in significantly improved segmentation accuracy (DSC range, 0.85-0.98) compared with the ABSNPP method (DSC range, 0.55-0.87; P < .001). Mean distance to agreement results also indicated high agreement between ABSPP and manual reference delineations (range, 0.11-1.56 mm), which was significantly improved compared with ABSNPP (range, 1.00-2.34 mm) for the majority of tested bony structures. Relative volume errors were also significantly lower for ABSPP compared with ABSNPP for most bony structures.

CONCLUSIONS

We developed a fully automated MIM workflow for bony structure segmentation from whole-body CT, which exhibited high accuracy compared with manual delineation. The integrated postprocessing module significantly improved workflow performance.

A primer on artificial intelligence in pancreatic imaging

Artificial Intelligence (AI) is set to transform medical imaging by leveraging the vast data contained in medical images. Deep learning and radiomics are the two main AI methods currently being applied within radiology. Deep learning uses a layered set of self-correcting algorithms to develop a mathematical model that best fits the data. Radiomics converts imaging data into mineable features such as signal intensity, shape, texture, and higher-order features. Both methods have the potential to improve disease detection, characterization, and prognostication. This article reviews the current status of artificial intelligence in pancreatic imaging and critically appraises the quality of existing evidence using the radiomics quality score.

Clinical applications of artificial intelligence in liver imaging

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.

Endocrine Tumor Classification via Machine-Learning-Based Elastography: A Systematic Scoping Review

Elastography complements traditional medical imaging modalities by mapping tissue stiffness to identify tumors in the endocrine system, and machine learning models can further improve diagnostic accuracy and reliability. Our objective in this review was to summarize the applications and performance of machine-learning-based elastography on the classification of endocrine tumors. Two authors independently searched electronic databases, including PubMed, Scopus, Web of Science, IEEEXpress, CINAHL, and EMBASE. Eleven (n = 11) articles were eligible for the review, of which eight (n = 8) focused on thyroid tumors and three (n = 3) considered pancreatic tumors. In all thyroid studies, the researchers used shear-wave ultrasound elastography, whereas the pancreas researchers applied strain elastography with endoscopy. Traditional machine learning approaches or the deep feature extractors were used to extract the predetermined features, followed by classifiers. The applied deep learning approaches included the convolutional neural network (CNN) and multilayer perceptron (MLP). Some researchers considered the mixed or sequential training of B-mode and elastographic ultrasound data or fusing data from different image segmentation techniques in machine learning models. All reviewed methods achieved an accuracy of ≥80%, but only three were ≥90% accurate. The most accurate thyroid classification (94.70%) was achieved by applying sequential training CNN; the most accurate pancreas classification (98.26%) was achieved using a CNN-long short-term memory (LSTM) model integrating elastography with B-mode and Doppler images.

Early Diagnosis of Pancreatic Cancer: Clinical Premonitions, Timely Precursor Detection and Increased Curative-Intent Surgery

BACKGROUND

The overall poor prognosis in pancreatic cancer is related to late clinical detection. Early diagnosis remains a considerable challenge in pancreatic cancer. Unfortunately, the onset of clinical symptoms in patients usually indicate advanced disease or presence of metastasis.

ANALYSIS AND RESULTS

Currently, there are no designated diagnostic or screening tests for pancreatic cancer in clinical use. Thus, identifying risk groups, preclinical risk factors or surveillance strategies to facilitate early detection is a target for ongoing research. Hereditary genetic syndromes are a obvious, but small group at risk, and warrants close surveillance as suggested by society guidelines. Screening for pancreatic cancer in asymptomatic individuals is currently associated with the risk of false positive tests and, thus, risk of harms that outweigh benefits. The promise of cancer biomarkers and use of 'omics' technology (genomic, transcriptomics, metabolomics etc.) has yet to see a clinical breakthrough. Several proposed biomarker studies for early cancer detection lack external validation or, when externally validated, have shown considerably lower accuracy than in the original data. Biopsies or tissues are often taken at the time of diagnosis in research studies, hence invalidating the value of a time-dependent lag of the biomarker to detect a pre-clinical, asymptomatic yet operable cancer. New technologies will be essential for early diagnosis, with emerging data from image-based radiomics approaches, artificial intelligence and machine learning suggesting avenues for improved detection.

CONCLUSIONS

Early detection may come from analytics of various body fluids (eg 'liquid biopsies' from blood or urine). In this review we present some the technological platforms that are explored for their ability to detect pancreatic cancer, some of which may eventually change the prospects and outcomes of patients with pancreatic cancer.

Artificial intelligence in musculoskeletal oncology imaging: A critical review of current applications

Artificial intelligence (AI) is increasingly being studied in musculoskeletal oncology imaging. AI has been applied to both primary and secondary bone tumors and assessed for various predictive tasks that include detection, segmentation, classification, and prognosis. Still, in the field of clinical research, further efforts are needed to improve AI reproducibility and reach an acceptable level of evidence in musculoskeletal oncology. This review describes the basic principles of the most common AI techniques, including machine learning, deep learning and radiomics. Then, recent developments and current results of AI in the field of musculoskeletal oncology are presented. Finally, limitations and future perspectives of AI in this field are discussed.

Artificial intelligence in adrenal imaging: A critical review of current applications

In the elective field of adrenal imaging, artificial intelligence (AI) can be used for adrenal lesion detection, characterization, hypersecreting syndrome management and patient follow-up. Although a perfect AI tool that includes all required steps from detection to analysis does not exist yet, multiple AI algorithms have been developed and tested with encouraging results. However, AI in this setting is still at an early stage. In this regard, most published studies about AI in adrenal gland imaging report preliminary results that do not have yet daily applications in clinical practice. In this review, recent developments and current results of AI in the field of adrenal imaging are presented. Limitations and future perspectives of AI are discussed.

Acute Pancreatitis Severity Prediction: It Is Time to Use Artificial Intelligence

The clinical course of acute pancreatitis (AP) can be variable depending on the severity of the disease, and it is crucial to predict the probability of organ failure to initiate early adequate treatment and management. Therefore, possible high-risk patients should be admitted to a high-dependence unit. For risk assessment, we have three options: (1) There are univariate biochemical markers for predicting severe AP. One of their main characteristics is that the absence or excess of these factors affects the outcome of AP in a dose-dependent manner. Unfortunately, all of these parameters have low accuracy; therefore, they cannot be used in clinical settings. (2) Score systems have been developed to prognosticate severity by using 4-25 factors. They usually require multiple parameters that are not measured on a daily basis, and they often require more than 24 h for completion, resulting in the loss of valuable time. However, these scores can foresee specific organ failure or severity, but they only use dichotomous parameters, resulting in information loss. Therefore, their use in clinical settings is limited. (3) Artificial intelligence can detect the complex nonlinear relationships between multiple biochemical parameters and disease outcomes. We have recently developed the very first easy-to-use tool, EASY-APP, which uses multiple continuous variables that are available at the time of admission. The web-based application does not require all of the parameters for prediction, allowing early and easy use on admission. In the future, prognostic scores should be developed with the help of artificial intelligence to avoid information loss and to provide a more individualized risk assessment.

Proposal to Improve the Image Quality of Short-Acquisition Time-Dedicated Breast Positron Emission Tomography Using the Pix2pix Generative Adversarial Network

This study aimed to evaluate the ability of the pix2pix generative adversarial network (GAN) to improve the image quality of low-count dedicated breast positron emission tomography (dbPET). Pairs of full- and low-count dbPET images were collected from 49 breasts. An image synthesis model was constructed using pix2pix GAN for each acquisition time with training (3776 pairs from 16 breasts) and validation data (1652 pairs from 7 breasts). Test data included dbPET images synthesized by our model from 26 breasts with short acquisition times. Two breast radiologists visually compared the overall image quality of the original and synthesized images derived from the short-acquisition time data (scores of 1−5). Further quantitative evaluation was performed using a peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In the visual evaluation, both readers revealed an average score of >3 for all images. The quantitative evaluation revealed significantly higher SSIM (p < 0.01) and PSNR (p < 0.01) for 26 s synthetic images and higher PSNR for 52 s images (p < 0.01) than for the original images. Our model improved the quality of low-count time dbPET synthetic images, with a more significant effect on images with lower counts.

Machine learning model identifies aggressive acute pancreatitis within 48 h of admission: a large retrospective study

BACKGROUND

Acute pancreatitis (AP) with critical illness is linked to increased morbidity and mortality. Current risk scores to identify high-risk AP patients have certain limitations.

OBJECTIVE

To develop and validate a machine learning tool within 48 h after admission for predicting which patients with AP will develop critical illness based on ubiquitously available clinical, laboratory, and radiologic variables.

METHODS

5460 AP patients were enrolled. Clinical, laboratory, and imaging variables were collected within 48 h after hospital admission. Least Absolute Shrinkage Selection Operator with bootstrap method was employed to select the most informative variables. Five different machine learning models were constructed to predictive likelihood of critical illness, and the optimal model (APCU) was selected. External cohort was used to validate APCU. APCU and other risk scores were compared using multivariate analysis. Models were evaluated by area under the curve (AUC). The decision curve analysis was employed to evaluate the standardized net benefit.

RESULTS

Xgboost was constructed and selected as APCU, involving age, comorbid disease, mental status, pulmonary infiltrates, procalcitonin (PCT), neutrophil percentage (Neu%), ALT/AST, ratio of albumin and globulin, cholinesterase, Urea, Glu, AST and serum total cholesterol. The APCU performed excellently in discriminating AP risk in internal cohort (AUC = 0.95) and external cohort (AUC = 0.873). The APCU was significant for biliogenic AP (OR = 4.25 [2.08-8.72], P < 0.001), alcoholic AP (OR = 3.60 [1.67-7.72], P = 0.001), hyperlipidemic AP (OR = 2.63 [1.28-5.37], P = 0.008) and tumor AP (OR = 4.57 [2.14-9.72], P < 0.001). APCU yielded the highest clinical net benefit, comparatively.

CONCLUSION

Machine learning tool based on ubiquitously available clinical variables accurately predicts the development of AP, optimizing the management of AP.

Artificial Intelligence for the Prediction and Early Diagnosis of Pancreatic Cancer: Scoping Review (Preprint).. [DOI: 10.2196/preprints.44248] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Pancreatic cancer is the 12th most common cancer worldwide, with an overall survival rate of 4.9%. Early diagnosis of pancreatic cancer is essential for timely treatment and survival. Artificial intelligence (AI) provides advanced models and algorithms for better diagnosis of pancreatic cancer.

OBJECTIVE

This study aims to explore AI models used for the prediction and early diagnosis of pancreatic cancers as reported in the literature.

METHODS

A scoping review was conducted and reported in line with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. PubMed, Google Scholar, Science Direct, BioRXiv, and MedRxiv were explored to identify relevant articles. Study selection and data extraction were independently conducted by 2 reviewers. Data extracted from the included studies were synthesized narratively.

RESULTS

Of the 1185 publications, 30 studies were included in the scoping review. The included articles reported the use of AI for 6 different purposes. Of these included articles, AI techniques were mostly used for the diagnosis of pancreatic cancer (14/30, 47%). Radiological images (14/30, 47%) were the most frequently used data in the included articles. Most of the included articles used data sets with a size of &lt;1000 samples (11/30, 37%). Deep learning models were the most prominent branch of AI used for pancreatic cancer diagnosis in the studies, and the convolutional neural network was the most used algorithm (18/30, 60%). Six validation approaches were used in the included studies, of which the most frequently used approaches were k-fold cross-validation (10/30, 33%) and external validation (10/30, 33%). A higher level of accuracy (99%) was found in studies that used support vector machine, decision trees, and k-means clustering algorithms.

CONCLUSIONS

This review presents an overview of studies based on AI models and algorithms used to predict and diagnose pancreatic cancer patients. AI is expected to play a vital role in advancing pancreatic cancer prediction and diagnosis. Further research is required to provide data that support clinical decisions in health care.

Artificial Intelligence-Driven Diagnosis of Pancreatic Cancer

Pancreatic cancer is among the most challenging forms of cancer to treat, owing to its late diagnosis and aggressive nature that reduces the survival rate drastically. Pancreatic cancer diagnosis has been primarily based on imaging, but the current state-of-the-art imaging provides a poor prognosis, thus limiting clinicians' treatment options. The advancement of a cancer diagnosis has been enhanced through the integration of artificial intelligence and imaging modalities to make better clinical decisions. In this review, we examine how AI models can improve the diagnosis of pancreatic cancer using different imaging modalities along with a discussion on the emerging trends in an AI-driven diagnosis, based on cytopathology and serological markers. Ethical concerns regarding the use of these tools have also been discussed.

Imaging of Pancreatic Ductal Adenocarcinoma: An Update on Recent Advances

Pancreatic ductal carcinoma (PDAC) is one of the leading causes of cancer-related death worldwide. Computed tomography (CT) remains the primary imaging modality for diagnosis of PDAC. However, CT has limitations for early pancreatic tumor detection and tumor characterization so that it is currently challenged by magnetic resonance imaging. More recently, a particular attention has been given to radiomics for the characterization of pancreatic lesions using extraction and analysis of quantitative imaging features. In addition, radiomics has currently many applications that are developed in conjunction with artificial intelligence (AI) with the aim of better characterizing pancreatic lesions and providing a more precise assessment of tumor burden. This review article sums up recent advances in imaging of PDAC in the field of image/data acquisition, tumor detection, tumor characterization, treatment response evaluation, and preoperative planning. In addition, current applications of radiomics and AI in the field of PDAC are discussed.

Pancreatic cancer, radiomics and artificial intelligence

Patients with pancreatic ductal adenocarcinoma (PDAC) are generally classified into four categories based on contrast-enhanced CT at diagnosis: resectable, borderline resectable, unresectable, and metastatic disease. In the initial grading and staging of PDAC, structured radiological templates are useful but limited, as there is a need to define the aggressiveness and microscopic disease stage of these tumours to ensure adequate treatment allocation. Quantitative imaging analysis allows radiomics and dynamic imaging features to provide information of clinical outcomes, and to construct clinical models based on radiomics signatures or imaging phenotypes. These quantitative features may be used as prognostic and predictive biomarkers in clinical decision-making, enabling personalised management of advanced PDAC. Deep learning and convolutional neural networks also provide high level bioinformatics tools that can help define features associated with a given aspect of PDAC biology and aggressiveness, paving the way to define outcomes based on these features. Thus, the prediction of tumour phenotype, treatment response and patient prognosis may be feasible by using such comprehensive and integrated radiomics models. Despite these promising results, quantitative imaging is not ready for clinical implementation in PDAC. Limitations include the instability of metrics and lack of external validation. Large properly annotated datasets, including relevant semantic features (demographics, blood markers, genomics), image harmonisation, robust radiomics analysis, clinically significant tasks as outputs, comparisons with gold-standards (such as TNM or pretreatment classifications) and fully independent validation cohorts, will be required for the development of trustworthy radiomics and artificial intelligence solutions to predict PDAC aggressiveness in a clinical setting.

Artificial intelligence for the detection of pancreatic lesions

PURPOSE

Pancreatic cancer is one of the most lethal neoplasms among common cancers worldwide, and PCLs are well-known precursors of this type of cancer. Artificial intelligence (AI) could help to improve and speed up the detection and classification of pancreatic lesions. The aim of this review is to summarize the articles addressing the diagnostic yield of artificial intelligence applied to medical imaging (computed tomography [CT] and/or magnetic resonance [MR]) for the detection of pancreatic cancer and pancreatic cystic lesions.

METHODS

We performed a comprehensive literature search using PubMed, EMBASE, and Scopus (from January 2010 to April 2021) to identify full articles evaluating the diagnostic accuracy of AI-based methods processing CT or MR images to detect pancreatic ductal adenocarcinoma (PDAC) or pancreatic cystic lesions (PCLs).

RESULTS

We found 20 studies meeting our inclusion criteria. Most of the AI-based systems used were convolutional neural networks. Ten studies addressed the use of AI to detect PDAC, eight studies aimed to detect and classify PCLs, and 4 aimed to predict the presence of high-grade dysplasia or cancer.

CONCLUSION

AI techniques have shown to be a promising tool which is expected to be helpful for most radiologists' tasks. However, methodologic concerns must be addressed, and prospective clinical studies should be carried out before implementation in clinical practice.

Research trends of artificial intelligence in pancreatic cancer: a bibliometric analysis

Purpose

We evaluated the related research on artificial intelligence (AI) in pancreatic cancer (PC) through bibliometrics analysis and explored the research hotspots and current status from 1997 to 2021.

Methods

Publications related to AI in PC were retrieved from the Web of Science Core Collection (WoSCC) during 1997-2021. Bibliometrix package of R software 4.0.3 and VOSviewer were used to bibliometrics analysis.

Results

A total of 587 publications in this field were retrieved from WoSCC database. After 2018, the number of publications grew rapidly. The United States and Johns Hopkins University were the most influential country and institution, respectively. A total of 2805 keywords were investigated, 81 of which appeared more than 10 times. Co-occurrence analysis categorized these keywords into five types of clusters: (1) AI in biology of PC, (2) AI in pathology and radiology of PC, (3) AI in the therapy of PC, (4) AI in risk assessment of PC and (5) AI in endoscopic ultrasonography (EUS) of PC. Trend topics and thematic maps show that keywords " diagnosis ", “survival”, “classification”, and “management” are the research hotspots in this field.

Conclusion

The research related to AI in pancreatic cancer is still in the initial stage. Currently, AI is widely studied in biology, diagnosis, treatment, risk assessment, and EUS of pancreatic cancer. This bibliometrics study provided an insight into AI in PC research and helped researchers identify new research orientations.

Radiomics in pancreatic cancer for oncologist: Present and future

Radiomics is changing the world of medicine and more specifically the world of oncology. Early diagnosis and treatment improve the prognosis of patients with cancer. After treatment, the evaluation of the response will determine future treatments. In oncology, every change in treatment means a loss of therapeutic options and this is key in pancreatic cancer. Radiomics has been developed in oncology in the early diagnosis and differential diagnosis of benign and malignant lesions, in the evaluation of response, in the prediction of possible side effects, marking the risk of recurrence, survival and prognosis of the disease. Some studies have validated its use to differentiate normal tissues from tumor tissues with high sensitivity and specificity, and to differentiate cystic lesions and pancreatic neuroendocrine tumor grades with texture parameters. In addition, these parameters have been related to survival in patients with pancreatic cancer and to response to radiotherapy and chemotherapy. This review aimed to establish the current status of the use of radiomics in pancreatic cancer and future perspectives.

Three-dimensional conditional generative adversarial network-based virtual thin-slice technique for the morphological evaluation of the spine

Virtual thin-slice (VTS) technique is a generative adversarial network-based algorithm that can generate virtual 1-mm-thick CT images from images of 3–10-mm thickness. We evaluated the performance of VTS technique for assessment of the spine. VTS was applied to 4-mm-thick CT images of 73 patients, and the visibility of intervertebral spaces was evaluated on the 4-mm-thick and VTS images. The heights of vertebrae measured on sagittal images reconstructed from the 4-mm-thick images and VTS images were compared with those measured on images reconstructed from 1-mm-thick images. Diagnostic performance for the detection of compression fractures was also compared. The intervertebral spaces were significantly more visible on the VTS images than on the 4-mm-thick images (P < 0.001). The absolute value of the measured difference in mean vertebral height between the VTS and 1-mm-thick images was smaller than that between the 4-mm-thick and 1-mm-thick images (P < 0.01–0.54). The diagnostic performance of the VTS images for detecting compression fracture was significantly lower than that of the 4-mm-thick images for one reader (P = 0.02). VTS technique enabled the identification of each vertebral body, and enabled accurate measurement of vertebral height. However, this technique is not suitable for diagnosing compression fractures.

EASY-APP: An artificial intelligence model and application for early and easy prediction of severity in acute pancreatitis

Background

Acute pancreatitis (AP) is a potentially severe or even fatal inflammation of the pancreas. Early identification of patients at high risk for developing a severe course of the disease is crucial for preventing organ failure and death. Most of the former predictive scores require many parameters or at least 24 h to predict the severity; therefore, the early therapeutic window is often missed.

Methods

The early achievable severity index (EASY) is a multicentre, multinational, prospective and observational study (ISRCTN10525246). The predictions were made using machine learning models. We used the scikit‐learn, xgboost and catboost Python packages for modelling. We evaluated our models using fourfold cross‐validation, and the receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC), and accuracy metrics were calculated on the union of the test sets of the cross‐validation. The most critical factors and their contribution to the prediction were identified using a modern tool of explainable artificial intelligence called SHapley Additive exPlanations (SHAP).

Results

The prediction model was based on an international cohort of 1184 patients and a validation cohort of 3543 patients. The best performing model was an XGBoost classifier with an average AUC score of 0.81 ± 0.033 and an accuracy of 89.1%, and the model improved with experience. The six most influential features were the respiratory rate, body temperature, abdominal muscular reflex, gender, age and glucose level. Using the XGBoost machine learning algorithm for prediction, the SHAP values for the explanation and the bootstrapping method to estimate confidence, we developed a free and easy‐to‐use web application in the Streamlit Python‐based framework (http://easy‐app.org/).

Conclusions

The EASY prediction score is a practical tool for identifying patients at high risk for severe AP within hours of hospital admission. The web application is available for clinicians and contributes to the improvement of the model.

Role of artificial intelligence in early detection and screening for pancreatic adenocarcinoma

Pancreatic adenocarcinoma remains to be one of the deadliest malignancies in the world despite treatment advancement over the past few decades. Its low survival rates and poor prognosis can be attributed to ambiguity in recommendations for screening and late symptom onset, contributing to its late presentation. In the recent years, artificial intelligence (AI) as emerged as a field to aid in the process of clinical decision making. Considerable efforts have been made in the realm of AI to screen for and predict future development of pancreatic ductal adenocarcinoma. This review discusses the use of AI in early detection and screening for pancreatic adenocarcinoma, and factors which may limit its use in a clinical setting.

Adrenal Mass Characterization in the Era of Quantitative Imaging: State of the Art

Simple Summary

Non-invasive characterization of adrenal lesions requires a rigorous approach. Although CT is the cornerstone of adrenal lesion characterization, a multimodality multiparametric imaging approach helps improve confidence in adrenal lesion characterization.

Abstract

Detection and characterization of adrenal lesions have evolved during the past two decades. Although the role of imaging in adrenal lesions associated with hormonal secretion is usually straightforward, characterization of non-functioning adrenal lesions may be challenging to confidently identify those that need to be resected. Although many adrenal lesions can be readily diagnosed when they display typical imaging features, the diagnosis may be challenging for atypical lesions. Computed tomography (CT) remains the cornerstone of adrenal imaging, but other morphological or functional modalities can be used in combination to reach a diagnosis and avoid useless biopsy or surgery. Early- and delayed-phase contrast-enhanced CT images are essential for diagnosing lipid-poor adenoma. Ongoing studies are evaluating the capabilities of dual-energy CT to provide valid virtual non-contrast attenuation and iodine density measurements from contrast-enhanced examinations. Adrenal lesions with attenuation values between 10 and 30 Hounsfield units (HU) on unenhanced CT can be characterized by MRI when iodinated contrast material injection cannot be performed. ¹⁸F-FDG PET/CT helps differentiate between atypical benign and malignant adrenal lesions, with the adrenal-to-liver maximum standardized uptake value ratio being the most discriminative variable. Recent studies evaluating the capabilities of radiomics and artificial intelligence have shown encouraging results.

Accuracy of a CT density threshold enhancement in distinguishing pancreas parenchymal necrosis in cases of acute pancreatitis in the first week

PURPOSE

The purpose of this study was to identify attenuation threshold value on computed tomography (CT) that allowed discriminating between interstitial edematous pancreatitis (IEP) and necrotizing pancreatitis (NP) in patients with acute pancreatitis during the first week of the disease and evaluate interobserver reproducibility for the diagnosis of acute pancreatitis category.

MATERIALS AND METHODS

Patients with acute pancreatitis who underwent CT examination of the abdomen between March 2015 and December 2019 were retrospectively included. Actual diagnosis of IEP or NP was based on final clinical report, follow-up evaluation, and complications. Six regions of interest were manually placed in the pancreatic gland and peripancreatic fat, and differences in CT attenuation values before contrast injection and during the portal venous phase of enhancement were computed. Performance in the diagnosis of AP category was evaluated using receiver operating characteristic analysis. Interobserver agreement was estimated by the intraclass correlation coefficient (ICC) and Bland Altman analysis was used to estimate reproducibility between pairs of observers.

RESULTS

Sixty-six patients with NP (46 men, 20 women; mean age, 55 ± 17 [SD] years; age range: 20-89 years) and 70 patients with IEP (39 men, 31 women; mean age, 54 ± 18 [SD] years; age range: 21-87 years) were included. An enhancement value less than 30 Hounsfield units (HU) in the pancreatic gland during the portal phase compared to non-contrast phase, yielded 90.9% sensitivity (60/66; 95% CI: 81.3-96.6), 94.3% specificity (66/70; 95% CI: 86.0-98.4) and an area under curve of 0.958 (95% CI: 0.919-0.996) for the diagnosis of NP versus IEP. Interobserver reproducibility for pancreas enhancement was good using Bland Altman plot and ICC was excellent for pancreatic gland analysis (ICC 0.978; 95% CI: 0.961-0.988) but poor or moderate (ICC ≤0.634) regarding peripancreatic fat necrosis.

CONCLUSION

By using a pancreas enhancement threshold value of 30 HU, CT is accurate and reproducible for the diagnosis of NP during the first week of the disease.

Radiomics in breast MRI: current progress toward clinical application in the era of artificial intelligence

Breast magnetic resonance imaging (MRI) is the most sensitive imaging modality for breast cancer diagnosis and is widely used clinically. Dynamic contrast-enhanced MRI is the basis for breast MRI, but ultrafast images, T2-weighted images, and diffusion-weighted images are also taken to improve the characteristics of the lesion. Such multiparametric MRI with numerous morphological and functional data poses new challenges to radiologists, and thus, new tools for reliable, reproducible, and high-volume quantitative assessments are warranted. In this context, radiomics, which is an emerging field of research involving the conversion of digital medical images into mineable data for clinical decision-making and outcome prediction, has been gaining ground in oncology. Recent development in artificial intelligence has promoted radiomics studies in various fields including breast cancer treatment and numerous studies have been conducted. However, radiomics has shown a translational gap in clinical practice, and many issues remain to be solved. In this review, we will outline the steps of radiomics workflow and investigate clinical application of radiomics focusing on breast MRI based on published literature, as well as current discussion about limitations and challenges in radiomics.