CNN-based survival model for pancreatic ductal adenocarcinoma in medical imaging

Machine learning models for classifying non-specific neck pain using craniocervical posture and movement

OBJECTIVE

Physical therapists and clinicians commonly confirm craniocervical posture (CCP), cervical retraction, and craniocervical flexion as screening tests because they contribute to non-specific neck pain (NSNP). We compared the predictive performance of statistical machine learning (ML) models for classifying individuals with and without NSNP using datasets containing CCP and cervical kinematics during pro- and retraction (CKdPR).

DESIGN

Exploratory, cross-sectional design.

SETTING AND PARTICIPANTS

In total, 773 public service office workers (PSOWs) were screened for eligibility (NSNP, 441; without NSNP, 332).

METHODS

We set up five datasets (CCP, cervical kinematics during the protraction, cervical kinematics during the retraction, CKdPR and combination of the CCP and CKdPR). Four ML algorithms-random forest, logistic regression, Extreme Gradient boosting, and support vector machine-were trained.

MAIN OUTCOME MEASURES

Model performance were assessed using area under the curve (AUC), accuracy, precision, recall and F1-score. To interpret the predictions, we used Feature permutation importance and SHapley Additive explanation values.

RESULTS

The random forest model in the CKdPR dataset classified PSOWs with and without NSNP and achieved the best AUC among the five datasets using the test data (AUC, 0.892 [good]; F1, 0.832). The random forest model in the CCP dataset had the worst AUC among the five datasets using the test data [AUC, 0.738 (fair); F1, 0.715].

CONCLUSION

ML performance was higher for the CKdPR dataset than for the CCP dataset, suggesting that ML algorithms are more suitable than classical statistical methods for developing robust models for classifying PSOWs with and without NSNP.

Automatic Head and Neck Tumor segmentation and outcome prediction relying on FDG-PET/CT images: Findings from the second edition of the HECKTOR challenge

By focusing on metabolic and morphological tissue properties respectively, FluoroDeoxyGlucose (FDG)-Positron Emission Tomography (PET) and Computed Tomography (CT) modalities include complementary and synergistic information for cancerous lesion delineation and characterization (e.g. for outcome prediction), in addition to usual clinical variables. This is especially true in Head and Neck Cancer (HNC). The goal of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge was to develop and compare modern image analysis methods to best extract and leverage this information automatically. We present here the post-analysis of HECKTOR 2nd edition, at the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2021. The scope of the challenge was substantially expanded compared to the first edition, by providing a larger population (adding patients from a new clinical center) and proposing an additional task to the challengers, namely the prediction of Progression-Free Survival (PFS). To this end, the participants were given access to a training set of 224 cases from 5 different centers, each with a pre-treatment FDG-PET/CT scan and clinical variables. Their methods were subsequently evaluated on a held-out test set of 101 cases from two centers. For the segmentation task (Task 1), the ranking was based on a Borda counting of their ranks according to two metrics: mean Dice Similarity Coefficient (DSC) and median Hausdorff Distance at 95th percentile (HD95). For the PFS prediction task, challengers could use the tumor contours provided by experts (Task 3) or rely on their own (Task 2). The ranking was obtained according to the Concordance index (C-index) calculated on the predicted risk scores. A total of 103 teams registered for the challenge, for a total of 448 submissions and 29 papers. The best method in the segmentation task obtained an average DSC of 0.759, and the best predictions of PFS obtained a C-index of 0.717 (without relying on the provided contours) and 0.698 (using the expert contours). An interesting finding was that best PFS predictions were reached by relying on DL approaches (with or without explicit tumor segmentation, 4 out of the 5 best ranked) compared to standard radiomics methods using handcrafted features extracted from delineated tumors, and by exploiting alternative tumor contours (automated and/or larger volumes encompassing surrounding tissues) rather than relying on the expert contours. This second edition of the challenge confirmed the promising performance of fully automated primary tumor delineation in PET/CT images of HNC patients, although there is still a margin for improvement in some difficult cases. For the first time, the prediction of outcome was also addressed and the best methods reached relatively good performance (C-index above 0.7). Both results constitute another step forward toward large-scale outcome prediction studies in HNC.

AI-enabled routine H&E image based prognostic marker for early-stage luminal breast cancer

Breast cancer (BC) grade is a well-established subjective prognostic indicator of tumour aggressiveness. Tumour heterogeneity and subjective assessment result in high degree of variability among observers in BC grading. Here we propose an objective Haematoxylin & Eosin (H&E) image-based prognostic marker for early-stage luminal/Her2-negative BReAst CancEr that we term as the BRACE marker. The proposed BRACE marker is derived from AI based assessment of heterogeneity in BC at a detailed level using the power of deep learning. The prognostic ability of the marker is validated in two well-annotated cohorts (Cohort-A/Nottingham: n = 2122 and Cohort-B/Coventry: n = 311) on early-stage luminal/HER2-negative BC patients treated with endocrine therapy and with long-term follow-up. The BRACE marker is able to stratify patients for both distant metastasis free survival (p = 0.001, C-index: 0.73) and BC specific survival (p < 0.0001, C-index: 0.84) showing comparable prediction accuracy to Nottingham Prognostic Index and Magee scores, which are both derived from manual histopathological assessment, to identify luminal BC patients that may be likely to benefit from adjuvant chemotherapy.

An Automated Prognostic Model for Pancreatic Ductal Adenocarcinoma

Pancreatic ductal adenocarcinoma (PDAC) constitutes a leading cause of cancer-related mortality despite advances in detection and treatment methods. While computed tomography (CT) serves as the current gold standard for initial evaluation of PDAC, its prognostic value remains limited, as it relies on diagnostic stage parameters encompassing tumor size, lymph node involvement, and metastasis. Radiomics have recently shown promise in predicting postoperative survival of PDAC patients; however, they rely on manual pancreas and tumor delineation by clinicians. In this study, we collected a dataset of pre-operative CT scans from a cohort of 40 PDAC patients to evaluate a fully automated pipeline for survival prediction. Employing nnU-Net trained on an external dataset, we generated automated pancreas and tumor segmentations. Subsequently, we extracted 854 radiomic features from each segmentation, which we narrowed down to 29 via feature selection. We then combined these features with the Tumor, Node, Metastasis (TNM) system staging parameters, as well as the patient's age. We trained a random survival forest model to perform an overall survival prediction over time, as well as a random forest classifier for the binary classification of two-year survival, using repeated cross-validation for evaluation. Our results exhibited promise, with a mean C-index of 0.731 for survival modeling and a mean accuracy of 0.76 in two-year survival prediction, providing evidence of the feasibility and potential efficacy of a fully automated pipeline for PDAC prognostication. By eliminating the labor-intensive manual segmentation process, our streamlined pipeline demonstrates an efficient and accurate prognostication process, laying the foundation for future research endeavors.

Bounding box-based 3D AI model for user-guided volumetric segmentation of pancreatic ductal adenocarcinoma on standard-of-care CTs

OBJECTIVES

To develop a bounding-box-based 3D convolutional neural network (CNN) for user-guided volumetric pancreas ductal adenocarcinoma (PDA) segmentation.

METHODS

Reference segmentations were obtained on CTs (2006-2020) of treatment-naïve PDA. Images were algorithmically cropped using a tumor-centered bounding box for training a 3D nnUNet-based-CNN. Three radiologists independently segmented tumors on test subset, which were combined with reference segmentations using STAPLE to derive composite segmentations. Generalizability was evaluated on Cancer Imaging Archive (TCIA) (n = 41) and Medical Segmentation Decathlon (MSD) (n = 152) datasets.

RESULTS

Total 1151 patients [667 males; age:65.3 ± 10.2 years; T1:34, T2:477, T3:237, T4:403; mean (range) tumor diameter:4.34 (1.1-12.6)-cm] were randomly divided between training/validation (n = 921) and test subsets (n = 230; 75% from other institutions). Model had a high DSC (mean ± SD) against reference segmentations (0.84 ± 0.06), which was comparable to its DSC against composite segmentations (0.84 ± 0.11, p = 0.52). Model-predicted versus reference tumor volumes were comparable (mean ± SD) (29.1 ± 42.2-cc versus 27.1 ± 32.9-cc, p = 0.69, CCC = 0.93). Inter-reader variability was high (mean DSC 0.69 ± 0.16), especially for smaller and isodense tumors. Conversely, model's high performance was comparable between tumor stages, volumes and densities (p > 0.05). Model was resilient to different tumor locations, status of pancreatic/biliary ducts, pancreatic atrophy, CT vendors and slice thicknesses, as well as to the epicenter and dimensions of the bounding-box (p > 0.05). Performance was generalizable on MSD (DSC:0.82 ± 0.06) and TCIA datasets (DSC:0.84 ± 0.08).

CONCLUSION

A computationally efficient bounding box-based AI model developed on a large and diverse dataset shows high accuracy, generalizability, and robustness to clinically encountered variations for user-guided volumetric PDA segmentation including for small and isodense tumors.

CLINICAL RELEVANCE

AI-driven bounding box-based user-guided PDA segmentation offers a discovery tool for image-based multi-omics models for applications such as risk-stratification, treatment response assessment, and prognostication, which are urgently needed to customize treatment strategies to the unique biological profile of each patient's tumor.

Development and Validation of a Nomogram for Preoperative Prediction of Early Recurrence after Upfront Surgery in Pancreatic Ductal Adenocarcinoma by Integrating Deep Learning and Radiological Variables

Around 80% of pancreatic ductal adenocarcinoma (PDAC) patients experience recurrence after curative resection. We aimed to develop a deep-learning model based on preoperative CT images to predict early recurrence (recurrence within 12 months) in PDAC patients. The retrospective study included 435 patients with PDAC from two independent centers. A modified 3D-ResNet18 network was used for a deep learning model construction. A nomogram was constructed by incorporating deep learning model outputs and independent preoperative radiological predictors. The deep learning model provided the area under the receiver operating curve (AUC) values of 0.836, 0.736, and 0.720 in the development, internal, and external validation datasets for early recurrence prediction, respectively. Multivariate logistic analysis revealed that higher deep learning model outputs (odds ratio [OR]: 1.675; 95% CI: 1.467, 1.950; p < 0.001), cN1/2 stage (OR: 1.964; 95% CI: 1.036, 3.774; p = 0.040), and arterial involvement (OR: 2.207; 95% CI: 1.043, 4.873; p = 0.043) were independent risk factors associated with early recurrence and were used to build an integrated nomogram. The nomogram yielded AUC values of 0.855, 0.752, and 0.741 in the development, internal, and external validation datasets. In conclusion, the proposed nomogram may help predict early recurrence in PDAC patients.

Siamese Delta Network with Multimodality Fusion for Systemic Treatment Response Prediction in Pancreatic Cancer

Systemic treatment is a main way for pancreas cancer patients that are ineligible for surgery. A subgroup of patients showed good response to systemic treatment and the rest received limited benefits. CT images provide a non-invasive way to assess the treatment response. Alternative non-image methods include radiology analysis, tumor marker analysis and combination analysis. To combine the image and non-image data, we propose the Siamese Delta Network with Multimodality Fusion (SDN-MF) to predict systemic treatment response in an end-to-end way. First, a Siamese Delta Network (SDN) is designed to process pre-treatment and pre-surgery CT images and get the image feature changes to predict response. Then, patients' characteristics from EMR and alternative analysis results forms non-image data, which is incorporated into SDN with a multimodality fusion (MF) module. The proposed SDN-MF is evaluated on a private dataset and achieves average AUC value of 0.883 with five cross-validation. Comparison among image-only, non-image-only, and fusion models verifies the superior of multimodality model in predicting systemic treatment response of pancreas cancer patients.

Deep multimodal graph-based network for survival prediction from highly multiplexed images and patient variables

The spatial architecture of the tumour microenvironment and phenotypic heterogeneity of tumour cells have been shown to be associated with cancer prognosis and clinical outcomes, including survival. Recent advances in highly multiplexed imaging, including imaging mass cytometry (IMC), capture spatially resolved, high-dimensional maps that quantify dozens of disease-relevant biomarkers at single-cell resolution, that contain potential to inform patient-specific prognosis. Existing automated methods for predicting survival, on the other hand, typically do not leverage spatial phenotype information captured at the single-cell level. Furthermore, there is no end-to-end method designed to leverage the rich information in whole IMC images and all marker channels, and aggregate this information with clinical data in a complementary manner to predict survival with enhanced accuracy. To that end, we present a deep multimodal graph-based network (DMGN) with two modules: (1) a multimodal graph-based module that considers relationships between spatial phenotype information in all image regions and all clinical variables adaptively, and (2) a clinical embedding module that automatically generates embeddings specialised for each clinical variable to enhance multimodal aggregation. We demonstrate that our modules are consistently effective at improving survival prediction performance using two public breast cancer datasets, and that our new approach can outperform state-of-the-art methods in survival prediction.

Role of Machine Learning in Precision Oncology: Applications in Gastrointestinal Cancers

Gastrointestinal (GI) cancers, consisting of a wide spectrum of pathologies, have become a prominent health issue globally. Despite medical imaging playing a crucial role in the clinical workflow of cancers, standard evaluation of different imaging modalities may provide limited information. Accurate tumor detection, characterization, and monitoring remain a challenge. Progress in quantitative imaging analysis techniques resulted in "radiomics", a promising methodical tool that helps to personalize diagnosis and treatment optimization. Radiomics, a sub-field of computer vision analysis, is a bourgeoning area of interest, especially in this era of precision medicine. In the field of oncology, radiomics has been described as a tool to aid in the diagnosis, classification, and categorization of malignancies and to predict outcomes using various endpoints. In addition, machine learning is a technique for analyzing and predicting by learning from sample data, finding patterns in it, and applying it to new data. Machine learning has been increasingly applied in this field, where it is being studied in image diagnosis. This review assesses the current landscape of radiomics and methodological processes in GI cancers (including gastric, colorectal, liver, pancreatic, neuroendocrine, GI stromal, and rectal cancers). We explain in a stepwise fashion the process from data acquisition and curation to segmentation and feature extraction. Furthermore, the applications of radiomics for diagnosis, staging, assessment of tumor prognosis and treatment response according to different GI cancer types are explored. Finally, we discussed the existing challenges and limitations of radiomics in abdominal cancers and investigate future opportunities.

Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview

Gastrointestinal (GI) cancers are the major cause of cancer-related mortality globally. Medical imaging is an important auxiliary means for the diagnosis, assessment and prognostic prediction of GI cancers. Radiomics is an emerging and effective technology to decipher the encoded information within medical images, and traditional machine learning is the most commonly used tool. Recent advances in deep learning technology have further promoted the development of radiomics. In the field of GI cancer, although there are several surveys on radiomics, there is no specific review on the application of deep-learning-based radiomics (DLR). In this review, a search was conducted on Web of Science, PubMed, and Google Scholar with an emphasis on the application of DLR for GI cancers, including esophageal, gastric, liver, pancreatic, and colorectal cancers. Besides, the challenges and recommendations based on the findings of the review are comprehensively analyzed to advance DLR.

Quantitative Radiomic Features From Computed Tomography Can Predict Pancreatic Cancer up to 36 Months Before Diagnosis

INTRODUCTION

Pancreatic cancer is the third leading cause of cancer deaths among men and women in the United States. We aimed to detect early changes on computed tomography (CT) images associated with pancreatic ductal adenocarcinoma (PDAC) based on quantitative imaging features (QIFs) for patients with and without chronic pancreatitis (CP).

METHODS

Adults 18 years and older diagnosed with PDAC in 2008-2018 were identified. Their CT scans 3 months-3 years before the diagnosis date were matched to up to 2 scans of controls. The pancreas was automatically segmented using a previously developed algorithm. One hundred eleven QIFs were extracted. The data set was randomly split for training/validation. Neighborhood and principal component analyses were applied to select the most important features. A conditional support vector machine was used to develop prediction algorithms separately for patients with and without CP. The computer labels were compared with manually reviewed CT images 2-3 years before the index date in 19 cases and 19 controls.

RESULTS

Two hundred twenty-seven of 554 scans of non-CP cancer cases/controls and 70 of 140 scans of CP cancer cases/controls were included (average age 71 and 68 years, 51% and 44% females for non-CP patients and patients with CP, respectively). The QIF-based algorithms varied based on CP status. For non-CP patients, accuracy measures were 94%-95% and area under the curve (AUC) measures were 0.98-0.99. Sensitivity, specificity, positive predictive value, and negative predictive value were in the ranges of 88%-91%, 96%-98%, 91%-95%, and 94%-96%, respectively. QIFs on CT examinations within 2-3 years before the index date also had very high predictive accuracy (accuracy 95%-98%; AUC 0.99-1.00). The QIF-based algorithm outperformed manual rereview of images for determination of PDAC risk. For patients with CP, the algorithms predicted PDAC perfectly (accuracy 100% and AUC 1.00).

DISCUSSION

QIFs can accurately predict PDAC for both non-CP patients and patients with CP on CT imaging and represent promising biomarkers for early detection of pancreatic cancer.

Machine learning for image analysis in the cervical spine: Systematic review of the available models and methods

•Neural network approaches show the most potential for automated image analysis of thecervical spine.•Fully automatic convolutional neural network (CNN) models are promising Deep Learning methods for segmentation.•In cervical spine analysis, the biomechanical features are most often studied using finiteelement models.•The application of artificial neural networks and support vector machine models looks promising for classification purposes.•This article provides an overview of the methods for research on computer aided imaging diagnostics of the cervical spine.

Preoperative data-based deep learning model for predicting postoperative survival in pancreatic cancer patients

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) has a poor prognosis even after curative resection. A deep learning-based stratification of postoperative survival in the preoperative setting may aid the treatment decisions for improving prognosis. This study was aimed to develop a deep learning model based on preoperative data for predicting postoperative survival.

METHODS

The patients who underwent surgery for PDAC between January 2014 and May 2015. Clinical data-based machine learning models and computed tomography (CT) data-based deep learning models were developed separately, and ensemble learning was utilized to combine two models. The primary outcomes were the prediction of 2-year overall survival (OS) and 1-year recurrence-free survival (RFS). The model's performance was measured by area under the receiver operating curve (AUC) and was compared with that of American Joint Committee on Cancer (AJCC) 8th stage.

RESULTS

The median OS and RFS were 23 and 10 months in training dataset (n = 229), and 22 and 11 months in test dataset (n = 53), respectively. The AUC of the ensemble model for predicting 2-year OS and 1-year RFS in the test dataset was 0.76 and 0.74, respectively. The performance of the ensemble model was comparable to that of the AJCC in predicting 2-year OS (AUC, 0.67; P = 0.35) and superior to the AJCC in predicting 1-year RFS (AUC, 0.54; P = 0.049).

CONCLUSION

and relevance: Our ensemble model based on routine preoperative variables showed good performance for predicting prognosis for PDAC patients after surgery.

Multimodal survival prediction in advanced pancreatic cancer using machine learning

Background

Existing risk scores appear insufficient to assess the individual survival risk of patients with advanced pancreatic ductal adenocarcinoma (PDAC) and do not take advantage of the variety of parameters that are collected during clinical care.

Methods

In this retrospective study, we built a random survival forest model from clinical data of 203 patients with advanced PDAC. The parameters were assessed before initiation of systemic treatment and included age, CA19-9, C-reactive protein, metastatic status, neutrophil-to-lymphocyte ratio and total serum protein level. Separate models including imaging and molecular parameters were built for subgroups.

Results

Over the entire cohort, a model based on clinical parameters achieved a c-index of 0.71. Our approach outperformed the American Joint Committee on Cancer (AJCC) staging system and the modified Glasgow Prognostic Score (mGPS) in the identification of high- and low-risk subgroups. Inclusion of the KRAS p.G12D mutational status could further improve the prediction, whereas radiomics data of the primary tumor only showed little benefit. In an external validation cohort of PDAC patients with liver metastases, our model achieved a c-index of 0.67 (mGPS: 0.59).

Conclusions

The combination of multimodal data and machine-learning algorithms holds potential for personalized prognostication in advanced PDAC already at diagnosis.

•

We developed a machine-learning-based prediction model that outperforms the AJCC staging system and mGPS.

•

Applying our model to an external validation cohort demonstrates generalizability.

•

Explainable machine learning enables to understand the decision making of our model and identifies relevant parameters.

•

Combining clinical, imaging and genetic data holds potential for personalized prognostication in advanced PDAC.

Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging

Simple Summary

Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest cancers worldwide, associated with a 98% loss of life expectancy and a 30% increase in disability-adjusted life years. Image-based artificial intelligence (AI) can help improve outcomes for PDAC given that current clinical guidelines are non-uniform and lack evidence-based consensus. However, research on image-based AI for PDAC is too scattered and lacking in sufficient quality to be incorporated into clinical workflows. In this review, an international, multi-disciplinary team of the world’s leading experts in pancreatic cancer breaks down the patient pathway and pinpoints the current clinical touchpoints in each stage. The available PDAC imaging AI literature addressing each pathway stage is then rigorously analyzed, and current performance and pitfalls are identified in a comprehensive overview. Finally, the future research agenda for clinically relevant, image-driven AI in PDAC is proposed.

Abstract

Pancreatic ductal adenocarcinoma (PDAC), estimated to become the second leading cause of cancer deaths in western societies by 2030, was flagged as a neglected cancer by the European Commission and the United States Congress. Due to lack of investment in research and development, combined with a complex and aggressive tumour biology, PDAC overall survival has not significantly improved the past decades. Cross-sectional imaging and histopathology play a crucial role throughout the patient pathway. However, current clinical guidelines for diagnostic workup, patient stratification, treatment response assessment, and follow-up are non-uniform and lack evidence-based consensus. Artificial Intelligence (AI) can leverage multimodal data to improve patient outcomes, but PDAC AI research is too scattered and lacking in quality to be incorporated into clinical workflows. This review describes the patient pathway and derives touchpoints for image-based AI research in collaboration with a multi-disciplinary, multi-institutional expert panel. The literature exploring AI to address these touchpoints is thoroughly retrieved and analysed to identify the existing trends and knowledge gaps. The results show absence of multi-institutional, well-curated datasets, an essential building block for robust AI applications. Furthermore, most research is unimodal, does not use state-of-the-art AI techniques, and lacks reliable ground truth. Based on this, the future research agenda for clinically relevant, image-driven AI in PDAC is proposed.

A deep convolutional neural network to predict the curve progression of adolescent idiopathic scoliosis: a pilot study

Background

Adolescent idiopathic scoliosis (AIS) is a three-dimensional spinal deformity that predominantly occurs in girls. While skeletal growth and maturation influence the development of AIS, accurate prediction of curve progression remains difficult because the prognosis for deformity differs among individuals. The purpose of this study is to develop a new diagnostic platform using a deep convolutional neural network (DCNN) that can predict the risk of scoliosis progression in patients with AIS.

Methods

Fifty-eight patients with AIS (49 females and 9 males; mean age: 12.5 ± 1.4 years) and a Cobb angle between 10 and 25 degrees (mean angle: 18.7 ± 4.5) were divided into two groups: those whose Cobb angle increased by more than 10 degrees within two years (progression group, 28 patients) and those whose Cobb angle changed by less than 5 degrees (non-progression group, 30 patients). The X-ray images of three regions of interest (ROIs) (lung [ROI1], abdomen [ROI2], and total spine [ROI3]), were used as the source data for learning and prediction. Five spine surgeons also predicted the progression of scoliosis by reading the X-rays in a blinded manner.

Results

The prediction performance of the DCNN for AIS curve progression showed an accuracy of 69% and an area under the receiver-operating characteristic curve of 0.70 using ROI3 images, whereas the diagnostic performance of the spine surgeons showed inferior at 47%. Transfer learning with a pretrained DCNN contributed to improved prediction accuracy.

Conclusion

Our developed method to predict the risk of scoliosis progression in AIS by using a DCNN could be a valuable tool in decision-making for therapeutic interventions for AIS.

DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients With Advanced Nasopharyngeal Carcinoma Using Pretreatment PET/CT

Nasopharyngeal Carcinoma (NPC) is a malignant epithelial cancer arising from the nasopharynx. Survival prediction is a major concern for NPC patients, as it provides early prognostic information to plan treatments. Recently, deep survival models based on deep learning have demonstrated the potential to outperform traditional radiomics-based survival prediction models. Deep survival models usually use image patches covering the whole target regions (e.g., nasopharynx for NPC) or containing only segmented tumor regions as the input. However, the models using the whole target regions will also include non-relevant background information, while the models using segmented tumor regions will disregard potentially prognostic information existing out of primary tumors (e.g., local lymph node metastasis and adjacent tissue invasion). In this study, we propose a 3D end-to-end Deep Multi-Task Survival model (DeepMTS) for joint survival prediction and tumor segmentation in advanced NPC from pretreatment PET/CT. Our novelty is the introduction of a hard-sharing segmentation backbone to guide the extraction of local features related to the primary tumors, which reduces the interference from non-relevant background information. In addition, we also introduce a cascaded survival network to capture the prognostic information existing out of primary tumors and further leverage the global tumor information (e.g., tumor size, shape, and locations) derived from the segmentation backbone. Our experiments with two clinical datasets demonstrate that our DeepMTS can consistently outperform traditional radiomics-based survival prediction models and existing deep survival models.

Imaging-based Machine-learning Models to Predict Clinical Outcomes and Identify Biomarkers in Pancreatic Cancer: A Scoping Review

OBJECTIVE

To perform a scoping review of imaging-based machine-learning models to predict clinical outcomes and identify biomarkers in patients with PDAC.

SUMMARY OF BACKGROUND DATA

Patients with PDAC could benefit from better selection for systemic and surgical therapy. Imaging-based machine-learning models may improve treatment selection.

METHODS

A scoping review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-analyses-scoping review guidelines in the PubMed and Embase databases (inception-October 2020). The review protocol was prospectively registered (open science framework registration: m4cyx). Included were studies on imaging-based machine-learning models for predicting clinical outcomes and identifying biomarkers for PDAC. The primary outcome was model performance. An area under the curve (AUC) of ≥0.75, or a P-value of ≤0.05, was considered adequate model performance. Methodological study quality was assessed using the modified radiomics quality score.

RESULTS

After screening 1619 studies, 25 studies with 2305 patients fulfilled the eligibility criteria. All but 1 study was published in 2019 and 2020. Overall, 23/25 studies created models using radiomics features, 1 study quantified vascular invasion on computed tomography, and one used histopathological data. Nine models predicted clinical outcomes with AUC measures of 0.78-0.95, and C-indices of 0.65-0.76. Seventeen models identified biomarkers with AUC measures of 0.68-0.95. Adequate model performance was reported in 23/25 studies. The methodological quality of the included studies was suboptimal, with a median modified radiomics quality score score of 7/36.

CONCLUSIONS

The use of imaging-based machine-learning models to predict clinical outcomes and identify biomarkers in patients with PDAC is increasingly rapidly. Although these models mostly have good performance scores, their methodological quality should be improved.

Deep-Learning-Based Survival Prediction of Patients in Coronary Care Units

Background

A survival prediction model based on deep learning has higher accuracy than the CPH model in predicting the survival of CCU patients, and it also has a better discrimination ability. We collected information on patients with various diseases in coronary care units (CCUs) from the Medical Information Mart for Intensive Care III (MIMIC-III) database. The purpose of this study was to use this information to construct a neural-network model based on deep learning to predict the survival probabilities of patients with conditions that are common in CCUs.

Method

We collected information on patients in the United States with five common diseases in CCUs from 2001 to 2012. We randomly divided the patients into a training cohort and a testing cohort at a ratio of 7 : 3 and applied a survival prediction method based on deep learning to predict their survival probability. We compared our model with the Cox proportional-hazards regression (CPH) model and used the concordance indexes (C-indexes), receiver operating characteristic (ROC) curve, and calibration plots to evaluate the predictive performance of the model.

Results

The 3,388 CCU patients included in the study were randomly divided into 2,371 in the training cohort and 1,017 in the testing cohort. The stepwise regression results showed that the important factors affecting patient survival were the type of disease, age, race, anion gap, glucose, neutrophils, white blood cells, potassium, creatine kinase, and blood urea nitrogen (P < 0.05). We used the training cohort to construct a deep-learning model, for which the C-index was 0.833, or about 5% higher than that for the CPH model (0.786). The C-index of the deep-learning model for the test cohort was 0.822, which was also higher than that for the CPH model (0.782). The areas under the ROC curve for the 28-day, 90-day, and 1-year survival probabilities were 0.875, 0.865, and 0.874, respectively, in the deep-learning model, respectively, and 0.830, 0.843, and 0.806 in the CPH model. These values indicate that the survival analysis model based on deep learning is better than the traditional CPH model in predicting the survival of CCU patients.

Conclusion

A survival prediction model based on deep learning has higher accuracy than the CPH model in predicting the survival of CCU patients, and it also has a better discrimination ability.

The impact of radiomics in diagnosis and staging of pancreatic cancer

INTRODUCTION

Pancreatic cancer (PC) is one of the most aggressive tumours, and better risk stratification among patients is required to provide tailored treatment. The meaning of radiomics and texture analysis as predictive techniques are not already systematically assessed. The aim of this study is to assess the role of radiomics in PC.

METHODS

A PubMed/MEDLINE and Embase systematic review was conducted to assess the role of radiomics in PC. The search strategy was 'radiomics [All Fields] AND ("pancreas" [MeSH Terms] OR "pancreas" [All Fields] OR "pancreatic" [All Fields])' and only original articles referred to PC in humans in the English language were considered.

RESULTS

A total of 123 studies and 183 studies were obtained using the mentioned search strategy on PubMed and Embase, respectively. After the complete selection process, a total of 56 papers were considered eligible for the analysis of the results. Radiomics methods were applied in PC for assessment technical feasibility and reproducibility aspects analysis, risk stratification, biologic or genomic status prediction and treatment response prediction.

DISCUSSION

Radiomics seems to be a promising approach to evaluate PC from diagnosis to treatment response prediction. Further and larger studies are required to confirm the role and allowed to include radiomics parameter in a comprehensive decision support system.

CovH2SD: A COVID-19 detection approach based on Harris Hawks Optimization and stacked deep learning

Starting from Wuhan in China at the end of 2019, coronavirus disease (COVID-19) has propagated fast all over the world, affecting the lives of billions of people and increasing the mortality rate worldwide in few months. The golden treatment against the invasive spread of COVID-19 is done by identifying and isolating the infected patients, and as a result, fast diagnosis of COVID-19 is a critical issue. The common laboratory test for confirming the infection of COVID-19 is Reverse Transcription Polymerase Chain Reaction (RT-PCR). However, these tests suffer from some problems in time, accuracy, and availability. Chest images have proven to be a powerful tool in the early detection of COVID-19. In the current study, a hybrid learning and optimization approach named CovH2SD is proposed for the COVID-19 detection from the Chest Computed Tomography (CT) images. CovH2SD uses deep learning and pre-trained models to extract the features from the CT images and learn from them. It uses Harris Hawks Optimization (HHO) algorithm to optimize the hyperparameters. Transfer learning is applied using nine pre-trained convolutional neural networks (i.e. ResNet50, ResNet101, VGG16, VGG19, Xception, MobileNetV1, MobileNetV2, DenseNet121, and DenseNet169). Fast Classification Stage (FCS) and Compact Stacking Stage (CSS) are suggested to stack the best models into a single one. Nine experiments are applied and results are reported based on the Loss, Accuracy, Precision, Recall, F1-Score, and Area Under Curve (AUC) performance metrics. The comparison between combinations is applied using the Weighted Sum Method (WSM). Six experiments report a WSM value above 96.5%. The top WSM and accuracy reported values are 99.31% and 99.33% respectively which are higher than the eleven compared state-of-the-art studies.

Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients

Glioblastoma is an aggressive brain tumor with a low survival rate. Understanding tumor behavior by predicting prognosis outcomes is a crucial factor in deciding a proper treatment plan. In this paper, an automatic overall survival time prediction system (OST) for glioblastoma patients is developed on the basis of radiomic features and machine learning (ML). This system is designed to predict prognosis outcomes by classifying a glioblastoma patient into one of three survival groups: short-term, mid-term, and long-term. To develop the prediction system, a medical dataset based on imaging information from magnetic resonance imaging (MRI) and non-imaging information is used. A novel radiomic feature extraction method is proposed and developed on the basis of volumetric and location information of brain tumor subregions extracted from MRI scans. This method is based on calculating the volumetric features from two brain sub-volumes obtained from the whole brain volume in MRI images using brain sectional planes (sagittal, coronal, and horizontal). Many experiments are conducted on the basis of various ML methods and combinations of feature extraction methods to develop the best OST system. In addition, the feature fusions of both radiomic and non-imaging features are examined to improve the accuracy of the prediction system. The best performance was achieved by the neural network and feature fusions.

Recent advances in artificial intelligence for pancreatic ductal adenocarcinoma

Pancreatic ductal adenocarcinoma (PDAC) remains the most lethal type of cancer. The 5-year survival rate for patients with early-stage diagnosis can be as high as 20%, suggesting that early diagnosis plays a pivotal role in the prognostic improvement of PDAC cases. In the medical field, the broad availability of biomedical data has led to the advent of the "big data" era. To overcome this deadly disease, how to fully exploit big data is a new challenge in the era of precision medicine. Artificial intelligence (AI) is the ability of a machine to learn and display intelligence to solve problems. AI can help to transform big data into clinically actionable insights more efficiently, reduce inevitable errors to improve diagnostic accuracy, and make real-time predictions. AI-based omics analyses will become the next alterative approach to overcome this poor-prognostic disease by discovering biomarkers for early detection, providing molecular/genomic subtyping, offering treatment guidance, and predicting recurrence and survival. Advances in AI may therefore improve PDAC survival outcomes in the near future. The present review mainly focuses on recent advances of AI in PDAC for clinicians. We believe that breakthroughs will soon emerge to fight this deadly disease using AI-navigated precision medicine.

Pre-operative radiomics model for prognostication in resectable pancreatic adenocarcinoma with external validation

OBJECTIVES

In resectable pancreatic ductal adenocarcinoma (PDAC), few pre-operative prognostic biomarkers are available. Radiomics has demonstrated potential but lacks external validation. We aimed to develop and externally validate a pre-operative clinical-radiomic prognostic model.

METHODS

Retrospective international, multi-center study in resectable PDAC. The training cohort included 352 patients (pre-operative CTs from five Canadian hospitals). Cox models incorporated (a) pre-operative clinical variables (clinical), (b) clinical plus CT-radiomics, and (c) post-operative TNM model, which served as the reference. Outcomes were overall (OS)/disease-free survival (DFS). Models were assessed in the validation cohort from Ireland (n = 215, CTs from 34 hospitals), using C-statistic, calibration, and decision curve analyses.

RESULTS

The radiomic signature was predictive of OS/DFS in the validation cohort, with adjusted hazard ratios (HR) 2.87 (95% CI: 1.40-5.87, p < 0.001)/5.28 (95% CI 2.35-11.86, p < 0.001), respectively, along with age 1.02 (1.01-1.04, p = 0.01)/1.02 (1.00-1.04, p = 0.03). In the validation cohort, median OS was 22.9/37 months (p = 0.0092) and DFS 14.2/29.8 (p = 0.0023) for high-/low-risk groups and calibration was moderate (mean absolute errors 7%/13% for OS at 3/5 years). The clinical-radiomic model discrimination (C = 0.545, 95%: 0.543-0.546) was higher than the clinical model alone (C = 0.497, 95% CI 0.496-0.499, p < 0.001) or TNM (C = 0.525, 95% CI: 0.524-0.526, p < 0.001). Despite superior net benefit compared to the clinical model, the clinical-radiomic model was not clinically useful for most threshold probabilities.

CONCLUSION

A multi-institutional pre-operative clinical-radiomic model for resectable PDAC prognostication demonstrated superior net benefit compared to a clinical model but limited clinical utility at external validation. This reflects inherent limitations of radiomics for PDAC prognostication, when deployed in real-world settings.

KEY POINTS

• At external validation, a pre-operative clinical-radiomics prognostic model for pancreatic ductal adenocarcinoma (PDAC) outperformed pre-operative clinical variables alone or pathological TNM staging. • Discrimination and clinical utility of the clinical-radiomic model for treatment decisions remained low, likely due to heterogeneity of CT acquisition parameters. • Despite small improvements, prognosis in PDAC using state-of-the-art radiomics methodology remains challenging, mostly owing to its low discriminative ability. Future research should focus on standardization of CT protocols and acquisition parameters.

Artificial intelligence in gastroenterology: A state-of-the-art review

The development of artificial intelligence (AI) has increased dramatically in the last 20 years, with clinical applications progressively being explored for most of the medical specialties. The field of gastroenterology and hepatology, substantially reliant on vast amounts of imaging studies, is not an exception. The clinical applications of AI systems in this field include the identification of premalignant or malignant lesions (e.g., identification of dysplasia or esophageal adenocarcinoma in Barrett’s esophagus, pancreatic malignancies), detection of lesions (e.g., polyp identification and classification, small-bowel bleeding lesion on capsule endoscopy, pancreatic cystic lesions), development of objective scoring systems for risk stratification, predicting disease prognosis or treatment response [e.g., determining survival in patients post-resection of hepatocellular carcinoma), determining which patients with inflammatory bowel disease (IBD) will benefit from biologic therapy], or evaluation of metrics such as bowel preparation score or quality of endoscopic examination. The objective of this comprehensive review is to analyze the available AI-related studies pertaining to the entirety of the gastrointestinal tract, including the upper, middle and lower tracts; IBD; the hepatobiliary system; and the pancreas, discussing the findings and clinical applications, as well as outlining the current limitations and future directions in this field.

Machine Learning: Applications and Advanced Progresses of Radiomics in Endocrine Neoplasms

Endocrine neoplasms remain a great threat to human health. It is extremely important to make a clear diagnosis and timely treatment of endocrine tumors. Machine learning includes radiomics, which has long been utilized in clinical cancer research. Radiomics refers to the extraction of valuable information by analyzing a large amount of standard data with high-throughput medical images mainly including computed tomography, positron emission tomography, magnetic resonance imaging, and ultrasound. With the quantitative imaging analysis and model building, radiomics can reflect specific underlying characteristics of a disease that otherwise could not be evaluated visually. More and more promising results of radiomics in oncological practice have been seen in recent years. Radiomics may have the potential to supplement traditional imaging analysis and assist in providing precision medicine for patients. Radiomics had developed rapidly in endocrine neoplasms practice in the past decade. In this review, we would introduce the general workflow of radiomics and summarize the applications and developments of radiomics in endocrine neoplasms in recent years. The limitations of current radiomic research studies and future development directions would also be discussed.

Deep Learning for Adjacent Segment Disease at Preoperative MRI for Cervical Radiculopathy

Background Patients who undergo surgery for cervical radiculopathy are at risk for developing adjacent segment disease (ASD). Identifying patients who will develop ASD remains challenging for clinicians. Purpose To develop and validate a deep learning algorithm capable of predicting ASD by using only preoperative cervical MRI in patients undergoing single-level anterior cervical diskectomy and fusion (ACDF). Materials and Methods In this Health Insurance Portability and Accountability Act-compliant study, retrospective chart review was performed for 1244 patients undergoing single-level ACDF in two tertiary care centers. After application of inclusion and exclusion criteria, 344 patients were included, of whom 60% (n = 208) were used for training and 40% for validation (n = 43) and testing (n = 93). A deep learning-based prediction model with 48 convolutional layers was designed and trained by using preoperative T2-sagittal cervical MRI. To validate model performance, a neuroradiologist and neurosurgeon independently provided ASD predictions for the test set. Validation metrics included accuracy, areas under the curve, and F1 scores. The difference in proportion of wrongful predictions between the model and clinician was statistically tested by using the McNemar test. Results A total of 344 patients (median age, 48 years; interquartile range, 41-58 years; 182 women) were evaluated. The model predicted ASD on the 93 test images with an accuracy of 88 of 93 (95%; 95% CI: 90, 99), sensitivity of 12 of 15 (80%; 95% CI: 60, 100), and specificity of 76 of 78 (97%; 95% CI: 94, 100). The neuroradiologist and neurosurgeon provided predictions with lower accuracy (54 of 93; 58%; 95% CI: 48, 68), sensitivity (nine of 15; 60%; 95% CI: 35, 85), and specificity (45 of 78; 58%; 95% CI: 56, 77) compared with the algorithm. The McNemar test on the contingency table demonstrated that the proportion of wrongful predictions was significantly lower by the model (test statistic, 2.000; P < .001). Conclusion A deep learning algorithm that used only preoperative cervical T2-weighted MRI outperformed clinical experts at predicting adjacent segment disease in patients undergoing surgery for cervical radiculopathy. © RSNA, 2021 An earlier incorrect version appeared online. This article was corrected on September 22, 2021.

Modeling Texture in Deep 3D CNN for Survival Analysis

Radiomics has shown remarkable potential for predicting the survival outcome for various types of cancers such as pancreatic ductal adenocarcinoma (PDAC). However, to date, there has been limited research using convolutional neural networks (CNN) with radiomic methods for this task, due to their requirement for large training sets. To overcome this issue, we propose a new type of radiomic descriptor modeling the distribution of learned features with a Gaussian mixture model (GMM). These parametric features (GMM-CNN) are computed from gross tumor volumes of PDAC patients defined semi-automatically in pre-operative computed tomography (CT) scans. We use the proposed GMM-CNN features as input to a robust classifier based on random forests (RF) to predict the survival outcome of patients with PDAC. Our experiments assess the advantage of GMM-CNN compared to employing the same 3D CNN model directly, standard radiomic (i.e., histogram, texture and shape), conditional entropy (CENT) based on 3DCNN, and clinical features (i.e., serum carbohydrate antigen 19-9 and chemotherapy neoadjuvant). Using the RF model (100 samples for training; 59 samples for validation), GMM-CNN features provided the highest area under the ROC curve (AUC) of 72.0% (p =  6.4×10^-5) compared to 64.0% (p = 0.01) for the 3D CNN model output, 66.8% (p = 0.01) for standard radiomic features, 64.2% (p = 0.003) for CENT, and 57.6% (p = 0.3) for clinical variables. Our results suggest that the proposed GMM-CNN features used with a RF classifier can significantly improve the capacity to prognosticate PDAC patients prior to surgery via routinely-acquired imaging data.

External Validation of the VOCAL-Penn Cirrhosis Surgical Risk Score in 2 Large, Independent Health Systems

Cirrhosis poses an increased risk of postoperative mortality, yet it remains challenging to accurately risk stratify patients in clinical practice. The VOCAL-Penn cirrhosis surgical risk score was recently developed and internally validated in the national Veterans Affairs health system; however, to date this score has not been evaluated in independent cohorts. The goal of this study was to compare the predictive performance of the VOCAL-Penn to the Mayo risk, Model for End-Stage Liver Disease (MELD), and MELD-sodium (MELD-Na) scores in 2 large health systems. We performed a retrospective cohort study of patients with cirrhosis undergoing surgical procedures of interest at the Beth Israel Deaconess Medical Center or University of Pennsylvania Health System from January 1, 2008, to October 1, 2015. The outcomes of interest were 30-day and 90-day postoperative mortality. Concordance statistics (C-statistics), calibration curves, Brier scores, and the index of prediction accuracy (IPA) were compared for each predictive model. A total of 855 surgical procedures were identified. The VOCAL-Penn score had the numerically highest C-statistic for 90-day postoperative mortality (eg, 0.82 versus 0.79 Mayo versus 0.78 MELD-Na versus 0.79 MELD), although differences were not statistically significant. Calibrations were excellent for the VOCAL-Penn, MELD, and MELD-Na; however, the Mayo score consistently overestimated risk. The VOCAL-Penn had the lowest Brier score and highest IPA at both time points, suggesting superior overall predictive model performance. In subgroup analyses of patients with higher MELD scores, the VOCAL-Penn had significantly higher C-statistics compared with the MELD and MELD-Na. The VOCAL-Penn score (www.vocalpennscore.com) has excellent discrimination and calibration for postoperative mortality among diverse patients with cirrhosis. Overall performance is superior to the Mayo, MELD, and MELD-Na scores. In contrast to the MELD/MELD-Na, the VOCAL-Penn retains excellent discrimination among patients with higher MELD scores.

Artificial intelligence for pancreatic cancer detection: Recent development and future direction

Artificial intelligence (AI) has been increasingly utilized in medical applications, especially in the field of gastroenterology. AI can assist gastroenterologists in imaging-based testing and prediction of clinical diagnosis, for examples, detecting polyps during colonoscopy, identifying small bowel lesions using capsule endoscopy images, and predicting liver diseases based on clinical parameters. With its high mortality rate, pancreatic cancer can highly benefit from AI since the early detection of small lesion is difficult with conventional imaging techniques and current biomarkers. Endoscopic ultrasound (EUS) is a main diagnostic tool with high sensitivity for pancreatic adenocarcinoma and pancreatic cystic lesion. The standard tumor markers have not been effective for diagnosis. There have been recent research studies in AI application in EUS and novel biomarkers to early detect and differentiate malignant pancreatic lesions. The findings are impressive compared to the available traditional methods. Herein, we aim to explore the utility of AI in EUS and novel serum and cyst fluid biomarkers for pancreatic cancer detection.

Distant metastasis time to event analysis with CNNs in independent head and neck cancer cohorts

Deep learning models based on medical images play an increasingly important role for cancer outcome prediction. The standard approach involves usage of convolutional neural networks (CNNs) to automatically extract relevant features from the patient’s image and perform a binary classification of the occurrence of a given clinical endpoint. In this work, a 2D-CNN and a 3D-CNN for the binary classification of distant metastasis (DM) occurrence in head and neck cancer patients were extended to perform time-to-event analysis. The newly built CNNs incorporate censoring information and output DM-free probability curves as a function of time for every patient. In total, 1037 patients were used to build and assess the performance of the time-to-event model. Training and validation was based on 294 patients also used in a previous benchmark classification study while for testing 743 patients from three independent cohorts were used. The best network could reproduce the good results from 3-fold cross validation [Harrell’s concordance indices (HCIs) of 0.78, 0.74 and 0.80] in two out of three testing cohorts (HCIs of 0.88, 0.67 and 0.77). Additionally, the capability of the models for patient stratification into high and low-risk groups was investigated, the CNNs being able to significantly stratify all three testing cohorts. Results suggest that image-based deep learning models show good reliability for DM time-to-event analysis and could be used for treatment personalisation.

Prediction and interpretation of cancer survival using graph convolution neural networks

The survival rate of cancer has increased significantly during the past two decades for breast, prostate, testicular, and colon cancer, while the brain and pancreatic cancers have a much lower median survival rate that has not improved much over the last forty years. This has imposed the challenge of finding gene markers for early cancer detection and treatment strategies. Different methods including regression-based Cox-PH, artificial neural networks, and recently deep learning algorithms have been proposed to predict the survival rate for cancers. We established in this work a novel graph convolution neural network (GCNN) approach called Surv_GCNN to predict the survival rate for 13 different cancer types using the TCGA dataset. For each cancer type, 6 Surv_GCNN models with graphs generated by correlation analysis, GeneMania database, and correlation + GeneMania were trained with and without clinical data to predict the risk score (RS). The performance of the 6 Surv_GCNN models was compared with two other existing models, Cox-PH and Cox-nnet. The results showed that Cox-PH has the worst performance among 8 tested models across the 13 cancer types while Surv_GCNN models with clinical data reported the best overall performance, outperforming other competing models in 7 out of 13 cancer types including BLCA, BRCA, COAD, LUSC, SARC, STAD, and UCEC. A novel network-based interpretation of Surv_GCNN was also proposed to identify potential gene markers for breast cancer. The signatures learned by the nodes in the hidden layer of Surv_GCNN were identified and were linked to potential gene markers by network modularization. The identified gene markers for breast cancer have been compared to a total of 213 gene markers from three widely cited lists for breast cancer survival analysis. About 57% of gene markers obtained by Surv_GCNN with correlation + GeneMania graph either overlap or directly interact with the 213 genes, confirming the effectiveness of the identified markers by Surv_GCNN.

Improving prognostic performance in resectable pancreatic ductal adenocarcinoma using radiomics and deep learning features fusion in CT images

As an analytic pipeline for quantitative imaging feature extraction and analysis, radiomics has grown rapidly in the past decade. On the other hand, recent advances in deep learning and transfer learning have shown significant potential in the quantitative medical imaging field, raising the research question of whether deep transfer learning features have predictive information in addition to radiomics features. In this study, using CT images from Pancreatic Ductal Adenocarcinoma (PDAC) patients recruited in two independent hospitals, we discovered most transfer learning features have weak linear relationships with radiomics features, suggesting a potential complementary relationship between these two feature sets. We also tested the prognostic performance for overall survival using four feature fusion and reduction methods for combining radiomics and transfer learning features and compared the results with our proposed risk score-based feature fusion method. It was shown that the risk score-based feature fusion method significantly improves the prognosis performance for predicting overall survival in PDAC patients compared to other traditional feature reduction methods used in previous radiomics studies (40% increase in area under ROC curve (AUC) yielding AUC of 0.84).

Artificial intelligence for the management of pancreatic diseases

Novel artificial intelligence techniques are emerging in all fields of healthcare, including gastroenterology. The aim of this review is to give an overview of artificial intelligence applications in the management of pancreatic diseases. We performed a systematic literature search in PubMed and Medline up to May 2020 to identify relevant articles. Our results showed that the development of machine-learning based applications is rapidly evolving in the management of pancreatic diseases, guiding precision medicine in clinical, endoscopic and radiologic settings. Before implementation into clinical practice, further research should focus on the external validation of novel techniques, clarifying the accuracy and robustness of these models.

Multiparametric Modelling of Survival in Pancreatic Ductal Adenocarcinoma Using Clinical, Histomorphological, Genetic and Image-Derived Parameters

Rationale: Pancreatic ductal adenocarcinoma (PDAC) remains a tumor entity of exceptionally poor prognosis, and several biomarkers are under current investigation for the prediction of patient prognosis. Many studies focus on promoting newly developed imaging biomarkers without a rigorous comparison to other established parameters. To assess the true value and leverage the potential of all efforts in this field, a multi-parametric evaluation of the available biomarkers for PDAC survival prediction is warranted. Here we present a multiparametric analysis to assess the predictive value of established parameters and the added contribution of newly developed imaging features such as biomarkers for overall PDAC patient survival. Methods: 103 patients with resectable PDAC were retrospectively enrolled. Clinical and histopathological data (age, sex, chemotherapy regimens, tumor size, lymph node status, grading and resection status), morpho-molecular and genetic data (tumor morphology, molecular subtype, tp53, kras, smad4 and p16 genetics), image-derived features and the combination of all parameters were tested for their prognostic strength based on the concordance index (CI) of multivariate Cox proportional hazards survival modelling after unsupervised machine learning preprocessing. Results: The average CIs of the out-of-sample data were: 0.63 for the clinical and histopathological features, 0.53 for the morpho-molecular and genetic features, 0.65 for the imaging features and 0.65 for the combined model including all parameters. Conclusions: Imaging-derived features represent an independent survival predictor in PDAC and enable the multiparametric, machine learning-assisted modelling of postoperative overall survival with a high performance compared to clinical and morpho-molecular/genetic parameters. We propose that future studies systematically include imaging-derived features to benchmark their additive value when evaluating biomarker-based model performance.

PGNet: Pipeline Guidance for Human Key-Point Detection

Human key-point detection is a challenging research field in computer vision. Convolutional neural models limit the number of parameters and mine the local structure, and have made great progress in significant target detection and key-point detection. However, the features extracted by shallow layers mainly contain a lack of semantic information, while the features extracted by deep layers contain rich semantic information but a lack of spatial information that results in information imbalance and feature extraction imbalance. With the complexity of the network structure and the increasing amount of computation, the balance between the time of communication and the time of calculation highlights the importance. Based on the improvement of hardware equipment, network operation time is greatly improved by optimizing the network structure and data operation methods. However, as the network structure becomes deeper and deeper, the communication consumption between networks also increases, and network computing capacity is optimized. In addition, communication overhead is also the focus of recent attention. We propose a novel network structure PGNet, which contains three parts: pipeline guidance strategy (PGS); Cross-Distance-IoU Loss (CIoU); and Cascaded Fusion Feature Model (CFFM).