Prediction of Early Distant Recurrence in Upfront Resectable Pancreatic Adenocarcinoma: A Multidisciplinary, Machine Learning-Based Approach

Prediction of overall survival in patients with locally advanced pancreatic cancer using longitudinal diffusion-weighted MRI

Background and purpose

Biomarkers for prediction of outcome in patients with pancreatic cancer are wanted in order to personalize the treatment. This study investigated the value of longitudinal diffusion-weighted magnetic resonance imaging (DWI) for prediction of overall survival (OS) in patients with locally advanced pancreatic cancer (LAPC) treated with stereotactic body radiotherapy (SBRT).

Materials and methods

The study included 45 patients with LAPC who received 5 fractions of 10 Gy on a 1.5T MRI-Linac. DWI was acquired prior to irradiation at each fraction. The analysis included baseline values and time-trends of the apparent diffusion coefficient (ADC) and DWI parameters obtained using a decomposition method. A multivariable Cox proportional hazards model for OS was made using best-subset selection, using cross-validation based on Bootstrap.

Results

The median OS from the first day of SBRT was 15.5 months (95% CI: 13.2-20.6), and the median potential follow-up time was 19.8 months. The best-performing multivariable model for OS included two decomposition-based DWI parameters: one baseline and one time-trend parameter. The C-Harrell index describing the model's discriminating power was 0.754. High baseline ADC values were associated with reduced OS, whereas no association between the ADC time-trend and OS was observed.

Conclusion

Decomposition-based DWI parameters indicated value in the prediction of OS in LAPC. A DWI time-trend parameter was included in the best-performing model, indicating a potential benefit of acquiring longitudinal DWI during the SBRT course. These findings support both baseline and longitudinal DWI as candidate prognostic biomarkers, which may become tools for personalization of the treatment of patients with LAPC.

Preoperative MRI radiomic analysis for predicting local tumor progression in colorectal liver metastases before microwave ablation

PURPOSE

Radiomics may aid in predicting prognosis in patients with colorectal liver metastases (CLM). Consistent data is available on CT, yet limited data is available on MRI. This study assesses the capability of MRI-derived radiomic features (RFs) to predict local tumor progression-free survival (LTPFS) in patients with CLMs treated with microwave ablation (MWA).

METHODS

All CLM patients with pre-operative Gadoxetic acid-MRI treated with MWA in a single institution between September 2015 and February 2022 were evaluated. Pre-procedural information was retrieved retrospectively. Two observers manually segmented CLMs on T2 and T1-Hepatobiliary phase (T1-HBP) scans. After inter-observer variability testing, 148/182 RFs showed robustness on T1-HBP, and 141/182 on T2 (ICC > 0.7).Cox multivariate analysis was run to establish clinical (CLIN-mod), radiomic (RAD-T1, RAD-T2), and combined (COMB-T1, COMB-T2) models for LTPFS prediction.

RESULTS

Seventy-six CLMs (43 patients) were assessed. Median follow-up was 14 months. LTP occurred in 19 lesions (25%).CLIN-mod was composed of minimal ablation margins (MAMs), intra-segment progression and primary tumor grade and exhibited moderately high discriminatory power in predicting LTPFS (AUC = 0.89, p = 0.0001). Both RAD-T1 and RAD-T2 were able to predict LTPFS: (RAD-T1: AUC = 0.83, p = 0.0003; RAD-T2: AUC = 0.79, p = 0.001). Combined models yielded the strongest performance (COMB-T1: AUC = 0.98, p = 0.0001; COMB-T2: AUC = 0.95, p = 0.0003). Both combined models included MAMs and tumor regression grade; COMB-T1 also featured 10th percentile of signal intensity, while tumor flatness was present in COMB-T2.

CONCLUSION

MRI-based radiomic evaluation of CLMs is feasible and potentially useful for LTP prediction. Combined models outperformed clinical or radiomic models alone for LTPFS prediction.

Delta Radiomic Features Predict Resection Margin Status and Overall Survival in Neoadjuvant-Treated Pancreatic Cancer Patients

BACKGROUND

Neoadjuvant therapy (NAT) emerged as the standard of care for patients with pancreatic ductal adenocarcinoma (PDAC) who undergo surgery; however, surgery is morbid, and tools to predict resection margin status (RMS) and prognosis in the preoperative setting are needed. Radiomic models, specifically delta radiomic features (DRFs), may provide insight into treatment dynamics to improve preoperative predictions.

METHODS

We retrospectively collected clinical, pathological, and surgical data (patients with resectable, borderline, locally advanced, and metastatic disease), and pre/post-NAT contrast-enhanced computed tomography (CT) scans from PDAC patients at the University of Texas Southwestern Medical Center (UTSW; discovery) and Humanitas Hospital (validation cohort). Gross tumor volume was contoured from CT scans, and 257 radiomics features were extracted. DRFs were calculated by direct subtraction of pre/post-NAT radiomic features. Cox proportional models and binary prediction models, including/excluding clinical variables, were constructed to predict overall survival (OS), disease-free survival (DFS), and RMS.

RESULTS

The discovery and validation cohorts comprised 58 and 31 patients, respectively. Both cohorts had similar clinical characteristics, apart from differences in NAT (FOLFIRINOX vs. gemcitabine/nab-paclitaxel; p < 0.05) and type of surgery resections (pancreatoduodenectomy, distal or total pancreatectomy; p < 0.05). The model that combined clinical variables (pre-NAT carbohydrate antigen (CA) 19-9, the change in CA19-9 after NAT (∆CA19-9), and resectability status) and DRFs outperformed the clinical feature-based models and other radiomics feature-based models in predicting OS (UTSW: 0.73; Humanitas: 0.66), DFS (UTSW: 0.75; Humanitas: 0.64), and RMS (UTSW 0.73; Humanitas: 0.69).

CONCLUSIONS

Our externally validated, predictive/prognostic delta-radiomics models, which incorporate clinical variables, show promise in predicting the risk of predicting RMS in NAT-treated PDAC patients and their OS or DFS.

Comparing Performances of Predictive Models of Toxicity after Radiotherapy for Breast Cancer Using Different Machine Learning Approaches

PURPOSE

Different ML models were compared to predict toxicity in RT on a large cohort (n = 1314).

METHODS

The endpoint was RTOG G2/G3 acute toxicity, resulting in 204/1314 patients with the event. The dataset, including 25 clinical, anatomical, and dosimetric features, was split into 984 for training and 330 for internal tests. The dataset was standardized; features with a high p-value at univariate LR and with Spearman ρ>0.8 were excluded; synthesized data of the minority were generated to compensate for class imbalance. Twelve ML methods were considered. Model optimization and sequential backward selection were run to choose the best models with a parsimonious feature number. Finally, feature importance was derived for every model.

RESULTS

The model's performance was compared on a training-test dataset over different metrics: the best performance model was LightGBM. Logistic regression with three variables (LR3) selected via bootstrapping showed performances similar to the best-performing models. The AUC of test data is slightly above 0.65 for the best models (highest value: 0.662 with LightGBM).

CONCLUSIONS

No model performed the best for all metrics: more complex ML models had better performances; however, models with just three features showed performances comparable to the best models using many (n = 13-19) features.

Uncovering the clinicopathological features of early recurrence after surgical resection of pancreatic cancer

To identify risk factors and biomarker for early recurrence in patients diagnosed with pancreatic cancer who undergo curative resection. Early recurrence after curative resection of pancreatic cancer is an obstacle to long-term survival. We retrospectively reviewed 162 patients diagnosed with pancreatic cancer who underwent curative resection. Early recurrence was defined as recurrence within 12 months of surgery. We selected S100A2 as a biomarker and investigated its expression using immunohistochemistry. Of the total, 79.6% (n = 129) of patients received adjuvant chemotherapy after surgery and 117 (72.2%) experienced recurrence, of which 73 (45.1%) experience early recurrence. In multivariate analysis, age < 60 years, presence of lymph node metastasis, and no adjuvant chemotherapy were significantly associated with early recurrence (all P < 0.05). The proportion of patients with high S100A2 expression (H-score > 5) was significantly lower in the early recurrence group (41.5% vs. 63.3%, P = 0.020). The cumulative incidence rate of early recurrence was higher in patients with an S100A2 H-score < 5 (41.5% vs. 63.3%, P = 0.012). The median overall survival of patients with higher S100A2 expression was longer than those with lower S100A2 expression (median 30.1 months vs. 24.2 months, P = 0.003). High-risk factors for early recurrence after surgery for pancreatic cancer include young age, lymph node metastasis, and no adjuvant therapy. Neoadjuvant treatment or intensive adjuvant therapy after surgery may improve the prognosis of patients with high-risk signatures. In patients who receive adjuvant therapy, high S100A2 expression is a good predictor.

Machine Learning of Histopathological Images Predicts Recurrences of Resected Pancreatic Ductal Adenocarcinoma With Adjuvant Treatment

OBJECTIVES

Pancreatic ductal adenocarcinoma is an intractable disease with frequent recurrence after resection and adjuvant therapy. The present study aimed to clarify whether artificial intelligence-assisted analysis of histopathological images can predict recurrence in patients with pancreatic ductal adenocarcinoma who underwent resection and adjuvant chemotherapy with tegafur/5-chloro-2,4-dihydroxypyridine/potassium oxonate.

MATERIALS AND METHODS

Eighty-nine patients were enrolled in the study. Machine-learning algorithms were applied to 10-billion-scale pixel data of whole-slide histopathological images to generate key features using multiple deep autoencoders. Areas under the curve were calculated from receiver operating characteristic curves using a support vector machine with key features alone and by combining with clinical data (age and carbohydrate antigen 19-9 and carcinoembryonic antigen levels) for predicting recurrence. Supervised learning with pathological annotations was conducted to determine the significant features for predicting recurrence.

RESULTS

Areas under the curves obtained were 0.73 (95% confidence interval, 0.59-0.87) by the histopathological data analysis and 0.84 (95% confidence interval, 0.73-0.94) by the combinatorial analysis of histopathological data and clinical data. Supervised learning model demonstrated that poor tumor differentiation was significantly associated with recurrence.

CONCLUSIONS

Results indicate that machine learning with the integration of artificial intelligence-driven evaluation of histopathological images and conventional clinical data provides relevant prognostic information for patients with pancreatic ductal adenocarcinoma.

Preoperative prediction of early recurrence in resectable pancreatic cancer integrating clinical, radiologic, and CT radiomics features

OBJECTIVES

To use clinical, radiographic, and CT radiomics features to develop and validate a preoperative prediction model for the early recurrence of pancreatic cancer.

METHODS

We retrospectively analyzed 190 patients (150 and 40 in the development and test cohort from different centers) with pancreatic cancer who underwent pancreatectomy between January 2018 and June 2021. Radiomics, clinical-radiologic (CR), and clinical-radiologic-radiomics (CRR) models were developed for the prediction of recurrence within 12 months after surgery. Performance was evaluated using the area under the curve (AUC), Brier score, sensitivity, and specificity.

RESULTS

Early recurrence occurred in 36.7% and 42.5% of the development and test cohorts, respectively (P = 0.62). The features for the CR model included carbohydrate antigen 19-9 > 500 U/mL (odds ratio [OR], 3.60; P = 0.01), abutment to the portal and/or superior mesenteric vein (OR, 2.54; P = 0.054), and adjacent organ invasion (OR, 2.91; P = 0.03). The CRR model demonstrated significantly higher AUCs than the radiomics model in the internal (0.77 vs. 0.73; P = 0.048) and external (0.83 vs. 0.69; P = 0.038) validations. Although we found no significant difference between AUCs of the CR and CRR models (0.83 vs. 0.76; P = 0.17), CRR models showed more balanced sensitivity and specificity (0.65 and 0.87) than CR model (0.41 and 0.91) in the test cohort.

CONCLUSIONS

The CRR model outperformed the radiomics and CR models in predicting the early recurrence of pancreatic cancer, providing valuable information for risk stratification and treatment guidance.

Pancreatic Ductal Adenocarcinoma: Update of CT-Based Radiomics Applications in the Pre-Surgical Prediction of the Risk of Post-Operative Fistula, Resectability Status and Prognosis

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) is the seventh leading cause of cancer-related deaths worldwide. Surgical resection is the main driver to improving survival in resectable tumors, while neoadjuvant treatment based on chemotherapy (and radiotherapy) is the best option-treatment for a non-primally resectable disease. CT-based imaging has a central role in detecting, staging, and managing PDAC. As several authors have proposed radiomics for risk stratification in patients undergoing surgery for PADC, in this narrative review, we have explored the actual fields of interest of radiomics tools in PDAC built on pre-surgical imaging and clinical variables, to obtain more objective and reliable predictors.

METHODS

The PubMed database was searched for papers published in the English language no earlier than January 2018.

RESULTS

We found 301 studies, and 11 satisfied our research criteria. Of those included, four were on resectability status prediction, three on preoperative pancreatic fistula (POPF) prediction, and four on survival prediction. Most of the studies were retrospective.

CONCLUSIONS

It is possible to conclude that many performing models have been developed to get predictive information in pre-surgical evaluation. However, all the studies were retrospective, lacking further external validation in prospective and multicentric cohorts. Furthermore, the radiomics models and the expression of results should be standardized and automatized to be applicable in clinical practice.

Prediction of postoperative recurrence in resectable pancreatic body/tail adenocarcinoma: a novel risk stratification approach using a CT-based nomogram

OBJECTIVES

To identify prognostic CT features that predict recurrence in patients with resectable pancreatic body/tail adenocarcinoma (PBTA) and construct a CT-based nomogram for preoperative risk stratification.

METHODS

A total of 258 patients with resectable PBTA who underwent upfront surgery were retrospectively enrolled (development cohort, n = 172; validation cohort, n = 86), and their clinical and CT features were analyzed. Stepwise Cox proportional hazard analysis was performed to identify prognostic features and construct a predictive nomogram for recurrence-free survival (RFS). The prognostic performance of the CT-based nomogram was validated and compared to the 8th American Joint Committee on Cancer (AJCC) pathological staging system.

RESULTS

In the development cohort, the following five CT features for predicting recurrence were identified to construct the nomogram: tumor density in the venous phase, tumor necrosis, adjacent organ invasion, splenic vein invasion, and superior mesenteric vein/portal vein abutment. In the validation cohort, the CT-based nomogram showed a concordance index of 0.65 (95% confidence interval: 0.58-0.73), which was higher than the 8th AJCC staging system. The area under the curves of the nomogram for predicting recurrence at 0.5, 1, and 2 years were 0.66, 0.71, and 0.72, respectively. Patients were categorized into high- and low-risk groups with 1-year recurrence probabilities of 0.73 and 0.43, respectively.

CONCLUSIONS

The proposed nomogram provided accurate recurrence risk stratification for patients with resectable PBTA in a preoperative setting and may be used to facilitate clinical decision-making.

CLINICAL RELEVANCE STATEMENT

The proposed CT-based nomogram, based on easily available CT features, may serve as an effective and convenient tool for stratifying further the recurrence risk of patients with pancreatic body/tail adenocarcinoma.

KEY POINTS

• The CT-based nomogram, incorporating five commonly used CT features, successfully preoperatively stratified patients with resectable PBTA into distinct prognosis groups. • Tumor density in the venous phase, tumor necrosis, splenic vein invasion, adjacent organ invasion, and superior mesenteric vein/portal vein abutment were associated with RFS in patients with resectable PBTA. • The CT-based nomogram exhibited better predictive performance for recurrence than the 8th AJCC staging system.

Machine learning in pancreas surgery, what is new? literature review

Background

Machine learning (ML) is an inquiry domain that aims to establish methodologies that leverage information to enhance performance of various applications. In the healthcare domain, the ML concept has gained prominence over the years. As a result, the adoption of ML algorithms has become expansive. The aim of this scoping review is to evaluate the application of ML in pancreatic surgery.

Methods

We integrated the preferred reporting items for systematic reviews and meta-analyses for scoping reviews. Articles that contained relevant data specializing in ML in pancreas surgery were included.

Results

A search of the following four databases PubMed, Cochrane, EMBASE, and IEEE and files adopted from Google and Google Scholar was 21. The main features of included studies revolved around the year of publication, the country, and the type of article. Additionally, all the included articles were published within January 2019 to May 2022.

Conclusion

The integration of ML in pancreas surgery has gained much attention in previous years. The outcomes derived from this study indicate an extensive literature gap on the topic despite efforts by various researchers. Hence, future studies exploring how pancreas surgeons can apply different learning algorithms to perform essential practices may ultimately improve patient outcomes.

Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients

PURPOSE

To explore the variation of the discriminative power of CT (Computed Tomography) radiomic features (RF) against image discretization/interpolation in predicting early distant relapses (EDR) after upfront surgery.

MATERIALS AND METHODS

Data of 144 patients with pre-surgical high contrast CT were processed consistently with IBSI (Image Biomarker Standardization Initiative) guidelines. Image interpolation/discretization parameters were intentionally changed, including cubic voxel size (0.21-27 mm³) and binning (32-128 grey levels) in a 15 parameter's sets. After excluding RF with poor inter-observer delineation agreement (ICC < 0.80) and not negligible inter-scanner variability, the variation of 80 RF against discretization/interpolation was first quantified. Then, their ability in classifying patients with early distant relapses (EDR, < 10 months, previously assessed at the first quartile value of time-to-relapse) was investigated in terms of AUC (Area Under Curve) variation for those RF significantly associated to EDR.

RESULTS

Despite RF variability against discretization/interpolation parameters was large and only 30/80 RF showed %COV < 20 (%COV = 100*STDEV/MEAN), AUC changes were relatively limited: for 30 RF significantly associated with EDR (AUC values around 0.60-0.70), the mean values of SD of AUC variability and AUC range were 0.02 and 0.05 respectively. AUC ranges were between 0.00 and 0.11, with values ≤ 0.05 in 16/30 RF. These variations were further reduced when excluding the extreme values of 32 and 128 for grey levels (Average AUC range 0.04, with values between 0.00 and 0.08).

CONCLUSIONS

The discriminative power of CT RF in the prediction of EDR after upfront surgery for pancreatic cancer is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

Ex‐vivo investigation of radiofrequency ablation in pancreatic adenocarcinoma after neoadjuvant chemotherapy

Objective

Endoscopic ultrasound (US)‐guided radiofrequency ablation (RFA) has been investigated for pancreatic ductal adenocarcinoma (PDAC) but studies are limited and heterogeneous. Computed tomography (CT) scan features may predict RFA response after chemotherapy but their role is unexplored. The primary aim was to investigate the efficacy of ex‐vivo application of a dedicated RFA system at three power on surgically resected PDAC in patients who underwent neoadjuvant chemotherapy. The secondary aim was to explore the association between pre‐treatment CT‐based quantitative features and RFA response.

Methods

Fifteen ex‐vivo PDAC samples were treated by RFA under US control at three power groups (10, 30, and 50 W). Short axis necrosis diameter was measured by two expert blinded pathologists as the primary outcome. Two radiologists independently reviewed preoperative CT images.

Results

Eighty percent of specimens showed coagulative necrosis consisting of few millimeters: 5.7 ± 3.9 mm at 10 W, 3.7 ± 2.2 mm at 30 W, and 3.5 ± 2.4 mm at 50 W (p = 0.3), without a significant correlation between power setting and mean necrosis short axis (rho = –0.28; p = 0.30). Good agreement was seen between pathologists (k = 0.76; 95% confidence interval 0.55–0.98). Logistic regression analysis did not show associations between CT features and RFA response.

Conclusions

RFA causes histologically evident damage with coagulative necrosis of a few millimeters in 80% of ex‐vivo PDAC samples after chemotherapy and no clinical or pre‐operative CT features can predict efficacy. Power settings do not correlate with the histological ablation area. These results are of relevance when employing RFA in vivo and planning clinical trials on its role in PDAC patients.

Prediction of the characteristics of aggressiveness of pancreatic neuroendocrine neoplasms (PanNENs) based on CT radiomic features

OBJECTIVES

To predict tumor grade (G1 vs. G2/3), presence of distant metastasis (M+), metastatic lymph nodes (N+), and microvascular invasion (VI) of pancreatic neuroendocrine neoplasms (PanNEN) based on preoperative CT radiomic features (RFs), by applying a machine learning approach aimed to limit overfit.

METHODS

This retrospective study included 101 patients who underwent surgery for PanNEN; the entire population was split into training (n = 70) and validation cohort (n = 31). Based on a previously validated methodology, after tumor segmentation on contrast-enhanced CT, RFs were extracted from unenhanced CT images. In addition, conventional radiological and clinical features were combined with RFs into multivariate logistic regression models using minimum redundancy and a bootstrap-based machine learning approach. For each endpoint, models were trained and validated including only RFs (RF_model), and both (radiomic and clinicoradiological) features (COMB_model).

RESULTS

Twenty-five patients had G2/G3 tumor, 37 N+, and 14 M+ and 38 were shown to have VI. From a total of 182 RFs initially extracted, few independent radiomic and clinicoradiological features were identified. For M+ and G, the resulting models showed moderate to high performances: areas under the curve (AUC) for training/validation cohorts were 0.85/0.77 (RF_model) and 0.81/0.81 (COMB_model) for M+ and 0.67/0.72 and 0.68/0.70 for G. Concerning N+ and VI, only the COMB_model could be built, with poorer performance for N+ (AUC = 0.72/0.61) compared to VI (0.82/0.75). For all endpoints, the negative predictive value was good (≥ 0.75).

CONCLUSIONS

Combining few radiomic and clinicoradiological features resulted in presurgical prediction of histological characteristics of PanNENs. Despite the limited risk of overfit, external validations are warranted.

KEY POINTS

• Histology is the only tool currently available allowing characterization of PanNEN biological characteristics important for prognostic assessment; significant limitations to this approach exist. • Based upon preoperative contrast-enhanced CT images, a machine learning approach optimized to favor models' generalizability was successfully applied to train predictive models for tumor grading (G1 vs. G2/3), microvascular invasion, metastatic lymph nodes, and distant metastatic spread. • Moderate to high discriminative models (AUC: 0.67-0.85) based on few parameters (≤ 3) showing high negative predictive value (0.75-0.98) were generated and then successfully validated.

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.

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.

Development and Validation of a Preoperative Nomogram for Predicting Benign and Malignant Gallbladder Polypoid Lesions

Purpose

The purpose of this study was to develop and validate a preoperative nomogram of differentiating benign and malignant gallbladder polypoid lesions (GPs) combining clinical and radiomics features.

Methods

The clinical and imaging data of 195 GPs patients which were confirmed by pathology from April 2014 to May 2021 were reviewed. All patients were randomly divided into the training and testing cohorts. Radiomics features based on 3 sequences of contrast-enhanced computed tomography were extracted by the Pyradiomics package in python, and the nomogram further combined with clinical parameters was established by multiple logistic regression. The performance of the nomogram was evaluated by discrimination and calibration.

Results

Among 195 GPs patients, 132 patients were pathologically benign, and 63 patients were malignant. To differentiate benign and malignant GPs, the combined model achieved an area under the curve (AUC) of 0.950 as compared to the radiomics model and clinical model with AUC of 0.929 and 0.925 in the training cohort, respectively. Further validation showed that the combined model contributes to better sensitivity and specificity in the training and testing cohorts by the same cutoff value, although the clinical model had an AUC of 0.943, which was higher than 0.942 of the combined model in the testing cohort.

Conclusion

This study develops a nomogram based on the clinical and radiomics features for the highly effective differentiation and prediction of benign and malignant GPs before surgery.

The role of artificial intelligence in pancreatic surgery: a systematic review

Artificial intelligence (AI), including machine learning (ML), is being slowly incorporated in medical practice, to provide a more precise and personalized approach. Pancreatic surgery is an evolving field, which offers the only curative option for patients with pancreatic cancer. Increasing amounts of data are available in medicine: AI and ML can help incorporate large amounts of information in clinical practice. We conducted a systematic review, based on PRISMA criteria, of studies that explored the use of AI or ML algorithms in pancreatic surgery. To our knowledge, this is the first systematic review on this topic. Twenty-five eligible studies were included in this review; 12 studies with implications in the preoperative diagnosis, while 13 studies had implications in patient evolution. Preoperative diagnosis, such as predicting the malignancy of IPMNs, differential diagnosis between pancreatic cystic lesions, classification of different pancreatic tumours, and establishment of the correct management for each of these lesions, can be facilitated through different AI or ML algorithms. Postoperative evolution can also be predicted, and some studies reported prediction models for complications, including postoperative pancreatic fistula, while other studies have analysed the implications for prognosis evaluation (from predicting a textbook outcome, the risk of metastasis or relapse, or the mortality rate and survival). One study discussed the possibility of predicting an intraoperative complication-massive intraoperative bleeding. Artificial intelligence and machine learning models have promising applications in pancreatic surgery, in the preoperative period (high-accuracy diagnosis) and postoperative setting (prognosis evaluation and complication prediction), and the intraoperative applications have been less explored.