Radiomics in pancreatic cancer for oncologist: Present and future

Radiogenomic analysis for predicting lymph node metastasis and molecular annotation of radiomic features in pancreatic cancer

BACKGROUND

To provide a preoperative prediction model for lymph node metastasis in pancreatic cancer patients and provide molecular information of key radiomic features.

METHODS

Two cohorts comprising 151 and 54 pancreatic cancer patients were included in the analysis. Radiomic features from the tumor region of interests were extracted by using PyRadiomics software. We used a framework that incorporated 10 machine learning algorithms and generated 77 combinations to construct radiomics-based models for lymph node metastasis prediction. Weighted gene coexpression network analysis (WGCNA) was subsequently performed to determine the relationships between gene expression levels and radiomic features. Molecular pathways enrichment analysis was performed to uncover the underlying molecular features.

RESULTS

Patients in the in-house cohort (mean age, 61.3 years ± 9.6 [SD]; 91 men [60%]) were separated into training (n = 105, 70%) and validation (n = 46, 30%) cohorts. A total of 1,239 features were extracted and subjected to machine learning algorithms. The 77 radiomic models showed moderate performance for predicting lymph node metastasis, and the combination of the StepGBM and Enet algorithms had the best performance in the training (AUC = 0.84, 95% CI = 0.77-0.91) and validation (AUC = 0.85, 95% CI = 0.73-0.98) cohorts. We determined that 15 features were core variables for lymph node metastasis. Proliferation-related processes may respond to the main molecular alterations underlying these features.

CONCLUSIONS

Machine learning-based radiomics could predict the status of lymph node metastasis in pancreatic cancer, which is associated with proliferation-related alterations.

CT‑based radiomics analysis of consolidation characteristics in differentiating pulmonary disease of non‑tuberculous mycobacterium from pulmonary tuberculosis

Global incidence rate of non-tuberculous mycobacteria (NTM) pulmonary disease has been increasing rapidly. In some countries and regions, its incidence rate is higher than that of tuberculosis. It is easily confused with tuberculosis. The topic of this study is to identify two diseases using CT radioomics. The aim in the present study was to investigate the value of CT-based radiomics to analyze consolidation features in differentiation of non-tuberculous mycobacteria (NTM) from pulmonary tuberculosis (TB). A total of 156 patients (75 with NTM pulmonary disease and 81 with TB) exhibiting consolidation characteristics in Shandong Public Health Clinical Center were retrospectively analyzed. Subsequently, 305 regions of interest of CT consolidation were outlined. Using a random number generated via a computer, 70 and 30% of consolidations were allocated to the training and the validation cohort, respectively. By means of variance threshold, when investigating the effective radiomics features, SelectKBest and the least absolute shrinkage and selection operator regression method were employed for feature selection and combined to calculate the radiomics score. K-nearest neighbor (KNN), support vector machine (SVM) and logistic regression (LR) were used to analyze effective radiomics features. A total of 18 patients with NTM pulmonary disease and 18 with TB possessing consolidation characteristics in Jinan Infectious Disease Hospital were collected for external validation of the model. A total of three methods was used in the selection of 52 optimal features. For KNN, the area under the curve (AUC; sensitivity, specificity) for the training and validation cohorts were 0.98 (0.93, 0.94) and 0.90 (0.88, 083), respectively; for SVM, AUC was 0.99 (0.96, 0.96) and 0.92 (0.86, 0.85) and for LR, AUC was 0.99 (0.97, 0.97) and 0.89 (0.88, 0.85). In the external validation cohort, AUC values of models were all >0.84 and LR classifier exhibited the most significant precision, recall and F1 score (0.87, 0.94 and 0.88, respectively). LR classifier possessed the best performance in differentiating diseases. Therefore, CT-based radiomics analysis of consolidation features may distinguish NTM pulmonary disease from TB.

Complete Primary Pathological Response Following Neoadjuvant Treatment and Radical Resection for Pancreatic Ductal Adenocarcinoma

INTRODUCTION

Neoadjuvant treatment (NAT) for borderline (BD) or locally advanced (LA) primary pancreatic cancer (PDAC) is now a widely adopted approach. We present a case series of patients who have achieved a complete pathological response of the primary tumour on final histology following neoadjuvant chemotherapy +/- chemoradiation and radical surgery.

METHODS

Patients who underwent radical pancreatic resection following neoadjuvant treatment between March 2006 and March 2023 at a single institution were identified by retrospective case note review of a prospectively maintained database.

RESULTS

Ten patients were identified to have a complete primary pathological response (ypT0) on postoperative histology. Before treatment, five patients were considered BD and five were LA according to National Comprehensive Cancer Network guidelines. All patients underwent staging Computed Tomography (CT) and nine underwent 18Fluorodeoxyglucose Positron Emission Tomography (18FDG-PET/CT) imaging, with a mean maximum standardized uptake value (SUVmax) of the primary lesion at 6.14 ± 1.98 units. All patients received neoadjuvant chemotherapy, and eight received further chemoradiotherapy prior to resection. Mean pre- and post-neoadjuvant treatment serum Ca19-9 was 148.0 ± 146.3 IU/L and 18.0 ± 18.7 IU/L, respectively (p = 0.01). The mean duration of NAT was 5.6 ± 1.7 months. The mean time from completion of NAT to surgery was 13.1 ± 8.3 weeks. The mean lymph node yield was 21.1 ± 10.4 nodes, with one patient found to have 1 lymph node involved. All resections were reported to be R0. The mean length of stay was 11.8 ± 6.2 days. At the time of analysis, one death was reported at 35 months postoperatively. Two cases of recurrence were reported at 16 months (surgical bed) and 33 months (pulmonary). All other patients remain alive and under active surveillance. The current overall survival is 26.6 ± 20.7 months and counting.

CONCLUSIONS

Complete primary pathological response is uncommon but possible following neoadjuvant treatment in patients with PDAC. Further work to identify the common denominator within this unique cohort may lead to advances in the therapeutic approach and offer hope for patients diagnosed with borderline or locally advanced pancreatic ductal adenocarcinoma.

Lycorine inhibits pancreatic cancer cell growth and neovascularization by inducing Notch1 degradation and downregulating key vasculogenic genes

Pancreatic cancer is highly metastatic and lethal with an increasing incidence globally and a 5-year survival rate of only 8%. One of the factors contributing to the high mortality is the lack of effective drugs in the clinical setting. We speculated that effective compounds against pancreatic cancer exist in natural herbs and explored active small molecules among traditional Chinese medicinal herbs. The small molecule lycorine (MW: 323.77) derived from the herb Lycoris radiata inhibited pancreatic cancer cell growth with an IC50 value of 1 μM in a concentration-dependent manner. Lycorine markedly reduced pancreatic cancer cell viability, migration, invasion, neovascularization, and gemcitabine resistance. Additionally, lycorine effectively suppressed tumor growth in mouse xenograft models without obvious toxicity. Pharmacological studies revealed that the levels and half-life of Notch1 oncoprotein in the pancreatic cancer cells Panc-1 and Patu8988 were notably reduced. Moreover, the expression of the key vasculogenic genes Semaphorin 4D (Sema4D) and angiopoietin-2 (Ang-2) were also significantly inhibited by lycorine. Mechanistically, lycorine strongly triggered the degradation of Notch1 oncoprotein through the ubiquitin-proteasome system. In conclusion, lycorine effectively inhibits pancreatic cancer cell growth, migration, invasion, neovascularization, and gemcitabine resistance by inducing degradation of Notch1 oncoprotein and downregulating the key vasculogenic genes Sema4D and Ang-2. Our findings provide a new therapeutic candidate and treatment strategy against pancreatic cancer.

Predictive factors for survival in borderline resectable and locally advanced pancreatic cancer: are these really two different entities?

BACKGROUND

The treatment of borderline resectable (BR) and locally advanced (LA) pancreatic ductal adenocarcinoma (PDAC) has evolved with a wider application of neoadjuvant chemotherapy (NACHT). The aim of this study was to identify predictive factors for survival in BR and LA PDAC.

METHODS

Clinicopathologic data of patients with BR and LA PDAC who underwent surgical exploration between January 2011 and June 2021 were retrospectively collected. Survival from the date of surgery was estimated using the Kaplan-Meier method. Simple and multiple Cox proportional hazards models were fitted to identify factors associated with survival. Surgical resection was analyzed in combination with the involvement of lymph nodes as this last was only known after a formal resection.

RESULTS

Ninety patients were surgically explored (BR: 45, LA: 45), of which 51 (57%) were resected (BR: 31, LA: 20). NACHT was administered to 43 patients with FOLFIRINOX being the most frequent regimen applied (33/43, 77%). Major complications (Clavien-Dindo grade III and IV) occurred in 7.8% of patients and 90-day mortality rate was 3.3%. The median overall survival since surgery was 16 months (95% CI 12-20) in the group which underwent surgical resection and 10 months (95% CI 7-13) in the group with an unresectable tumor (p=0.001). Cox proportional hazards models showed significantly lower mortality hazard for surgical resection compared to no surgical resection, even after adjusting for National Comprehensive Cancer Network  (NCCN) classification and administration of NACHT [surgical resection with involved lymph nodes vs no surgical resection (cHR 0.49; 95% CI 0.29-0.82; p=0.007)]. There was no significant difference in survival between patients with BR and LA disease (cHR= 1.01; 95% CI 0.63-1.62; p=0.98).

CONCLUSIONS

Surgical resection is the only predictor of survival in patients with BR and LA PDAC, regardless of their initial classification as BR or LA. Our results suggest that surgery should not be denied to patients with LA PDAC a priori. Prospective studies including patients from the moment of diagnosis are required to identify biologic and molecular markers which may allow a better selection of patients who will benefit from surgery.

Replacing secretin-enhanced MRCP with MRI radiomics model based on a fully automated pancreas segmentation for assessing pancreatic exocrine function in chronic pancreatitis

OBJECTIVES

To develop and validate a radiomics nomogram based on a fully automated pancreas segmentation to assess pancreatic exocrine function. Furthermore, we aimed to compare the performance of the radiomics nomogram with the pancreatic flow output rate (PFR) and conclude on the replacement of secretin-enhanced magnetic resonance cholangiopancreatography (S-MRCP) by the radiomics nomogram for pancreatic exocrine function assessment.

METHODS

All participants underwent S-MRCP between April 2011 and December 2014 in this retrospective study. PFR was quantified using S-MRCP. Participants were divided into normal and pancreatic exocrine insufficiency (PEI) groups using the cut-off of 200 µg/L of fecal elastase-1. Two prediction models were developed including the clinical and non-enhanced T1-weighted imaging radiomics model. A multivariate logistic regression analysis was conducted to develop the prediction models. The models' performances were determined based on their discrimination, calibration, and clinical utility.

RESULTS

A total of 159 participants (mean age [Formula: see text] standard deviation, 45 years [Formula: see text] 14;119 men) included 85 normal and 74 PEI. All the participants were divided into a training set comprising 119 consecutive patients and an independent validation set comprising 40 consecutive patients. The radiomics score was an independent risk factor for PEI (odds ratio = 11.69; p < 0.001). In the validation set, the radiomics nomogram exhibited the highest performance (AUC, 0.92) in PEI prediction, whereas the clinical nomogram and PFR had AUCs of 0.79 and 0.78, respectively.

CONCLUSION

The radiomics nomogram accurately predicted pancreatic exocrine function and outperformed pancreatic flow output rate on S-MRCP in patients with chronic pancreatitis.

KEY POINTS

• The clinical nomogram exhibited moderate performance in diagnosing pancreatic exocrine insufficiency. • The radiomics score was an independent risk factor for pancreatic exocrine insufficiency, and every point rise in the rad-score was associated with an 11.69-fold increase in pancreatic exocrine insufficiency risk. • The radiomics nomogram accurately predicted pancreatic exocrine function and outperformed the clinical model and pancreatic flow output rate quantified by secretin-enhanced magnetic resonance cholangiopancreatography on MRI in patients with chronic pancreatitis.

Prognostic Predicting Model of Pancreatic Body Tail Carcinoma Using Clinical and CT Radiomic Data

Objective: To collect the clinical, pathological, and computed tomography (CT) data of 143 accepted surgical cases of pancreatic body tail cancer (PBTC) and to model and predict its prognosis. Methods: The clinical, pathological, and CT data of 143 PBTC patients who underwent surgical resection or endoscopic ultrasound biopsy and were pathologically diagnosed in Xiangyang No.1 People's Hospital Hospital from December 2012 to December 2022 were retrospectively analyzed. The Kaplan-Meier method was adopted to make survival curves based on the 1 to 5 years' follow-up data, and then the log-rank was employed to analyze the survival. According to the median survival of 6 months, the PBTC patients were divided into a group with a good prognosis (survival time ≥ 6 months) and a group with a poor prognosis (survival time < 6 months), and further the training set and test set were set at a ratio of 7/3. Then logistic regression was conducted to find independent risk factors, establish predictive models, and further the models were validated. Results: The Kaplan-Meier analysis showed that age, diabetes, tumor, node, and metastasis stage, CT enhancement mode, peripancreatic lymph node swelling, nerve invasion, surgery in a top hospital, tumor size, carbohydrate antigen 19-9, carcinoembryonic antigen, Radscore 1/2/3 were the influencing factors of PBTC recurrence. The overall average survival was 7.4 months in this study. The multivariate logistic analysis confirmed that nerve invasion, surgery in top hospital, dilation of the main pancreatic duct, and Radscore 2 were independent factors affecting the mortality of PBTC (P < .05). In the test set, the combined model achieved the best predictive performance [AUC 0.944, 95% CI (0.826-0.991)], significantly superior to the clinicopathological model [AUC 0.770, 95% CI (0.615-0.886), P = .0145], and the CT radiomics model [AUC 0.883, 95% CI (0.746-0.961), P = .1311], with a good clinical net benefit confirmed by decision curve. The same results were subsequently validated on the test set. Conclusion: The diagnosis and treatment of PBTC are challenging, and survival is poor. Nevertheless, the combined model benefits the clinical management and prognosis of PBTC.

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.