Pancreatic Serous Cystic Neoplasms and Mucinous Cystic Neoplasms: Differential Diagnosis by Combining Imaging Features and Enhanced CT Texture Analysis

Machine Learning Methods Based on CT Features Differentiate G1/G2 From G3 Pancreatic Neuroendocrine Tumors

RATIONALE AND OBJECTIVES

To identify CT features for distinguishing grade 1 (G1)/grade 2 (G2) from grade 3 (G3) pancreatic neuroendocrine tumors (PNETs) using different machine learning (ML) methods.

MATERIALS AND METHODS

A total of 147 patients with 155 lesions confirmed by pathology were retrospectively included. Clinical-demographic and radiological CT features was collected. The entire cohort was separated into training and validation groups at a 7:3 ratio. Least absolute shrinkage and selection operator (LASSO) algorithm and principal component analysis (PCA) were used to select features. Three ML methods, namely logistic regression (LR), support vector machine (SVM), and K-nearest neighbor (KNN) were used to build a differential model. Receiver operating characteristic (ROC) curves and precision-recall curves for each ML method were generated. The area under the curve (AUC), accuracy rate, sensitivity, and specificity were calculated.

RESULTS

G3 PNETs were more likely to present with invasive behaviors and lower enhancement than G1/G2 PNETs. The LR classifier yielded the highest AUC of 0.964 (95% confidence interval [CI]: 0.930, 0.972), with 95.4% accuracy rate, 95.7% sensitivity, and 92.9% specificity, followed by SVM (AUC: 0.957) and KNN (AUC: 0.893) in the training group. In the validation group, the SVM classier reached the highest AUC of 0.952 (95% CI: 0.860, 0.981), with 91.5% accuracy rate, 97.3% sensitivity, and 70% specificity, followed by LR (AUC: 0.949) and KNN (AUC: 0.923).

CONCLUSIONS

The LR and SVM classifiers had the best performance in the training group and validation group, respectively. ML method could be helpful in differentiating between G1/G2 and G3 PNETs.

Clinical and CT Quantitative Features for Predicting Liver Metastases in Patients with Pancreatic Neuroendocrine Tumors: A Study with Prospective/External Validation

RATIONALE AND OBJECTIVES

We aimed to evaluate clinical characteristics and quantitative CT imaging features for the prediction of liver metastases (LMs) in patients with pancreatic neuroendocrine tumors (PNETs).

METHODS

Patients diagnosed with pathologically confirmed PNETs were included, 133 patients were in the training group, 22 patients in the prospective internal validation group, and 28 patients in the external validation group. Clinical information and quantitative features were collected. The independent variables for predicting LMs were confirmed through the implementation of univariate and multivariate logistic analyses. The diagnostic performance was evaluated by conducting receiver operating characteristic curves for predicting LMs in the training and validation groups.

RESULTS

PNETs with LMs demonstrated significantly larger diameter and lower arterial/portal tumor-parenchymal enhancement ratio, arterial/portal absolute enhancement value (AAE/PAE value) (p < 0.05). After multivariate analyses, A high level of tumor marker (odds ratio (OR): 5.32; 95% CI, 1.54-18.35), maximum diameter larger than 24.6 mm (OR: 7.46; 95% CI, 1.70-32.72), and AAE value ≤ 51 HU (OR: 4.99; 95% CI, 0.93-26.95) were independent positive predictors of LMs in patients with PNETs, with area under curve (AUC) of 0.852 (95%CI, 0.781-0.907). The AUCs for prospective internal and external validation groups were 0.883 (95% CI, 0.686-0.977) and 0.789 (95% CI, 0.602-0.916), respectively.

CONCLUSION

Tumor marker, maximum diameter and absolute enhancement value in arterial phase were independent predictors with good predictive performance for the prediction of LMs in patients with PNETs. Combining clinical and quantitative features may facilitate the attainment of good predictive precision in predicting LMs.

Radiomics advances in the evaluation of pancreatic cystic neoplasms

With the development of medical imaging, the detection rate of pancreatic cystic neoplasms (PCNs) has increased greatly. Serous cystic neoplasm, solid pseudopapillary neoplasm, intraductal papillary mucinous neoplasm and mucinous cystic neoplasm are the main subtypes of PCN, and their treatment options vary greatly due to the different biological behaviours of the tumours. Different from conventional qualitative imaging evaluation, radiomics is a promising noninvasive approach for the diagnosis, classification, and risk stratification of diseases involving high-throughput extraction of medical image features. We present a review of radiomics in the diagnosis of serous cystic neoplasm and mucinous cystic neoplasm, risk classification of intraductal papillary mucinous neoplasm and prediction of solid pseudopapillary neoplasm invasiveness compared to conventional imaging diagnosis. Radiomics is a promising tool in the field of medical imaging, providing a noninvasive, high-performance model for preoperative diagnosis and risk stratification of PCNs and improving prospects regarding management of these diseases. Further studies are warranted to investigate MRI image radiomics in connection with PCNs to improve the diagnosis and treatment strategies in the management of PCN patients.

Role of artificial intelligence in the characterization of indeterminate pancreatic head mass and its usefulness in preoperative diagnosis

Artificial intelligence (AI) has been used in various fields of day-to-day life and its role in medicine is immense. Understanding of oncology has been improved with the introduction of AI which helps in diagnosis, treatment planning, management, prognosis, and follow-up. It also helps to identify high-risk groups who can be subjected to timely screening for early detection of malignant conditions. It is more important in pancreatic cancer as it is one of the major causes of cancer-related deaths worldwide and there are no specific early features (clinical and radiological) for diagnosis. With improvement in imaging modalities (computed tomography, magnetic resonance imaging, endoscopic ultrasound), most often clinicians were being challenged with lesions that were difficult to diagnose with human competence. AI has been used in various other branches of medicine to differentiate such indeterminate lesions including the thyroid gland, breast, lungs, liver, adrenal gland, kidney, etc. In the case of pancreatic cancer, the role of AI has been explored and is still ongoing. This review article will focus on how AI can be used to diagnose pancreatic cancer early or differentiate it from benign pancreatic lesions, therefore, management can be planned at an earlier stage.

Differentiation Between Phyllodes Tumors and Fibroadenomas of Breast Using Mammography-based Machine Learning Methods: A Preliminary Study

OBJECTIVE

To investigate the diagnostic performance of a mammography-based radiomics model for distinguishing phyllodes tumors (PTs) from fibroadenomas (FAs) of the breast.

MATERIALS AND METHODS

A total of 156 patients were retrospectively included (75 with PTs, 81 with FAs) and divided into training and validation groups at a ratio of 7:3. Radiomics features were extracted from craniocaudal and mediolateral oblique images. The least absolute shrinkage and selection operator (LASSO) algorithm and principal component analysis (PCA) were performed to select features. Three machine learning classifiers, including logistic regression (LR), K-nearest neighbor classifier (KNN) and support vector machine (SVM), were implemented in the radiomics model, imaging model and combined model. Receiver operating characteristic curves, area under the curve (AUC), sensitivity and specificity were computed.

RESULTS

Among 1084 features, the LASSO algorithm selected 17 features, and PCA further selected 6 features. Three machine learning classifiers yielded the same AUC of 0.935 in the validation group for the radiomics model. In the imaging model, KNN yielded the highest accuracy rate of 89.4% and AUC of 0.947 in the validation set. For the combined model, the SVM classifier reached the highest AUC of 0.918 with an accuracy rate of 86.2%, sensitivity of 83.9%, and specificity of 89.4% in the training group. In the validation group, LR yielded the highest AUC of 0.973. The combined model had a relatively higher AUC than the radiomics model or imaging model, especially in the validation group.

CONCLUSIONS

Mammography-based radiomics features demonstrate good diagnostic performance for discriminating PTs from FAs.

Pancreatic Cystic Lesions: Next Generation of Radiologic Assessment

Pancreatic cystic lesions are frequently identified on cross-sectional imaging. As many of these are presumed branch-duct intraductal papillary mucinous neoplasms, these lesions generate much anxiety for the patients and clinicians, often necessitating long-term follow-up imaging and even unnecessary surgical resections. However, the incidence of pancreatic cancer is overall low for patients with incidental pancreatic cystic lesions. Radiomics and deep learning are advanced tools of imaging analysis that have attracted much attention in addressing this unmet need, however, current publications on this topic show limited success and large-scale research is needed.

Mammography-based radiomics analysis and imaging features for predicting the malignant risk of phyllodes tumours of the breast

AIM

To determine whether the mammography (MG)-based radiomics analysis and MG/ultrasound (US) imaging features could predict the malignant risk of phyllodes tumours (PTs) of the breast.

MATERIALS AND METHODS

Seventy-five patients with PTs were included retrospectively (39 with benign PTs, 36 with borderline/malignant PTs) and divided into thetraining (n=52) and validation groups (n=23). The clinical information, MG and US imaging characteristics, and histogram features were extracted from craniocaudal (CC) and mediolateral oblique (MLO) images. The lesion region of interest (ROI) and perilesional ROI were delineated. Multivariate logistic regression analysis was performed to determine the malignant factors of PTs. Receiver operating characteristic (ROC) curves were generated, and the area under the curve (AUC), sensitivity, and specificity were calculated.

RESULTS

There was no significant difference found in the clinical or MG/US features between benign and borderline/malignant PTs. In the lesion ROI, variance in the CC view and mean and variance in the MLO view were independent predictors. The AUC was 0.942, sensitivity and specificity were 96.3% and 92%, respectively, in the training group. In the validation group, the AUC was 0.879, the sensitivity was 91.7%, and the specificity was 81.8%. In the perilesional ROI, the AUCs were 0.904 and 0.939, sensitivities were 88.9% and 91.7%, and the specificities were 92% and 90.9% in the training and validation groups, respectively.

CONCLUSIONS

MG-based radiomic features could predict the risk of malignancy of patients with PTs and may be used as a potential tool to differentiate benign and borderline/malignant PTs.

Integrating CT-based radiomic model with clinical features improves long-term prognostication in high-risk prostate cancer

Objective

High-risk prostate cancer (PCa) is often treated by prostate-only radiotherapy (PORT) owing to its favourable toxicity profile compared to whole-pelvic radiotherapy. Unfortunately, more than 50% patients still developed disease progression following PORT. Conventional clinical factors may be unable to identify at-risk subgroups in the era of precision medicine. In this study, we aimed to investigate the prognostic value of pre-treatment planning computed tomography (pCT)-based radiomic features and clinical attributes to predict 5-year progression-free survival (PFS) in high-risk PCa patients following PORT.

Materials and methods

A total of 176 biopsy-confirmed PCa patients who were treated at the Hong Kong Princess Margaret Hospital were retrospectively screened for eligibility. Clinical data and pCT of one hundred eligible high-risk PCa patients were analysed. Radiomic features were extracted from the gross-tumour-volume (GTV) with and without applying Laplacian-of-Gaussian (LoG) filter. The entire patient cohort was temporally stratified into a training and an independent validation cohort in a ratio of 3:1. Radiomics (R), clinical (C) and radiomic-clinical (RC) combined models were developed by Ridge regression through 5-fold cross-validation with 100 iterations on the training cohort. A model score was calculated for each model based on the included features. Model classification performance on 5-year PFS was evaluated in the independent validation cohort by average area-under-curve (AUC) of receiver-operating-characteristics (ROC) curve and precision-recall curve (PRC). Delong's test was used for model comparison.

Results

The RC combined model which contains 6 predictive features (tumour flatness, root-mean-square on fine LoG-filtered image, prostate-specific antigen serum concentration, Gleason score, Roach score and GTV volume) was the best-performing model (AUC = 0.797, 95%CI = 0.768-0.826), which significantly outperformed the R-model (AUC = 0.795, 95%CI = 0.774-0.816) and C-model (AUC = 0.625, 95%CI = 0.585-0.665) in the independent validation cohort. Besides, only the RC model score significantly classified patients in both cohorts into progression and progression-free groups regarding their 5-year PFS (p< 0.05).

Conclusion

Combining pCT-based radiomic and clinical attributes provided superior prognostication value regarding 5-year PFS in high-risk PCa patients following PORT. A large multi-centre study will potentially aid clinicians in implementing personalised treatment for this vulnerable subgroup in the future.

CT classification model of pancreatic serous cystic neoplasm and mucinous cystic neoplasm based on deep transfer learning

BACKGROUND

Pancreatic cancer is a highly lethal disease. The preoperative distinction between pancreatic serous cystic neoplasm (SCN) and mucinous cystic neoplasm (MCN) remains a clinical challenge.

OBJECTIVE

The goal of this study is to provide clinicians with supportive advice and avoid overtreatment by constructing a convolutional neural network (CNN) classifier to automatically identify pancreatic cancer using computed tomography (CT) images.

METHODS

We construct a CNN model using a dataset of 6,173 CT images obtained from 107 pathologically confirmed pancreatic cancer patients at Shanghai Changhai Hospital from January 2017 to February 2022. We divide CT slices into three categories namely, SCN, MCN, and no tumor, to train the DenseNet201-based CNN model with multi-head spatial attention mechanism (MSAM-DenseNet201). The attention module enhances the network's attention to local features and effectively improves the network performance. The trained model is applied to process all CT image slices and finally realize the two categories classification of MCN and SCN patients through a joint voting strategy.

RESULTS

Using a 10-fold cross validation method, this new MSAM-DenseNet201 model achieves a classification accuracy of 92.52%, a precision of 92.16%, a sensitivity of 92.16%, and a specificity of 92.86%, respectively.

CONCLUSIONS

This study demonstrates the feasibility of using a deep learning network or classification model to help diagnose MCN and SCN cases. This, the new method has great potential for developing new computer-aided diagnosis systems and applying in future clinical practice.

Artificial intelligence in pancreatic cancer

Pancreatic cancer is the deadliest disease, with a five-year overall survival rate of just 11%. The pancreatic cancer patients diagnosed with early screening have a median overall survival of nearly ten years, compared with 1.5 years for those not diagnosed with early screening. Therefore, early diagnosis and early treatment of pancreatic cancer are particularly critical. However, as a rare disease, the general screening cost of pancreatic cancer is high, the accuracy of existing tumor markers is not enough, and the efficacy of treatment methods is not exact. In terms of early diagnosis, artificial intelligence technology can quickly locate high-risk groups through medical images, pathological examination, biomarkers, and other aspects, then screening pancreatic cancer lesions early. At the same time, the artificial intelligence algorithm can also be used to predict the survival time, recurrence risk, metastasis, and therapy response which could affect the prognosis. In addition, artificial intelligence is widely used in pancreatic cancer health records, estimating medical imaging parameters, developing computer-aided diagnosis systems, etc. Advances in AI applications for pancreatic cancer will require a concerted effort among clinicians, basic scientists, statisticians, and engineers. Although it has some limitations, it will play an essential role in overcoming pancreatic cancer in the foreseeable future due to its mighty computing power.

Quantitative analysis of enhanced CT in differentiating well-differentiated pancreatic neuroendocrine tumors and poorly differentiated neuroendocrine carcinomas

OBJECTIVE

To identify quantitative CT features for distinguishing well-differentiated pancreatic neuroendocrine tumors (PNETs) from poorly differentiated pancreatic neuroendocrine carcinomas (PNECs).

MATERIALS AND METHODS

Seventeen patients with PNECs and 131 patients with PNETs confirmed by biopsy or surgery were retrospectively included. General demographic (sex, age) and CT quantitative parameters (arterial/portal absolute enhancement, arterial/portal relative enhancement ratio, arterial/portal enhancement ratio) were collected. Univariate and multivariate logistic regression analyses were performed to confirm independent variables for differentiating PNECs from PNETs. Receiver operating characteristic (ROC) curves for each quantitative parameter were generated to determine their diagnostic ability.

RESULTS

PNECs had a much lower mean arterial/portal absolute enhancement value (19.5 ± 11.0 vs. 78.8 ± 47.2; 28.1 ± 15.8 vs. 77.0 ± 39.4), arterial/portal relative enhancement ratio (0.57 ± 0.36 vs. 2.03 ± 1.31; 0.80 ± 0.52 vs. 1.99 ± 1.13), and arterial/portal enhancement ratio (0.62 ± 0.27 vs. 1.22 ± 0.49; 0.74 ± 0.19 vs. 1.21 ± 0.36) than PNETs (all p < 0.001). After multivariable analysis, arterial absolute enhancement (odds ratio [OR]: 0.96, 95% confidence interval [CI]: 0.93, 0.99) and portal absolute enhancement (OR: 0.96, 95% CI: 0.92, 0.99) were independent factors for differentiating PNECs from PNETs. For each quantitative parameter, arterial lesion enhancement yielded the highest diagnostic performance, with an area under the curve (AUC) of 0.922 (95% CI: 0.867-0.960), followed by portal absolute enhancement.

CONCLUSIONS

Arterial/portal absolute enhancements were independent predictors with good diagnostic accuracy for differentiating between PNETs and PNECs. Quantitative parameters of enhanced CT can distinguish PNECs from PNETs.

KEY POINTS

• PNECs were hypovascular and had a much lower enhanced CT attenuation in both arterial and portal phases than well-differentiated PNETs. • Quantitative parameters derived from enhanced CT can be used to distinguish PNECs from PNETs. • Arterial absolute enhancement and portal absolute enhancement were independent predictive factors for differentiating between PNETs and PNECs.

Quantitative MRI of Pancreatic Cystic Lesions: A New Diagnostic Approach

The commonly used magnetic resonance (MRI) criteria can be insufficient for discriminating mucinous from non-mucinous pancreatic cystic lesions (PCLs). The histological differences between PCLs’ fluid composition may be reflected in MRI images, but cannot be assessed by visual evaluation alone. We investigate whether additional MRI quantitative parameters such as signal intensity measurements (SIMs) and radiomics texture analysis (TA) can aid the differentiation between mucinous and non-mucinous PCLs. Fifty-nine PCLs (mucinous, n = 24; non-mucinous, n = 35) are retrospectively included. The SIMs were performed by two radiologists on T2 and diffusion-weighted images (T2WI and DWI) and apparent diffusion coefficient (ADC) maps. A total of 550 radiomic features were extracted from the T2WI and ADC maps of every lesion. The SIMs and TA features were compared between entities using univariate, receiver-operating, and multivariate analysis. The SIM analysis showed no statistically significant differences between the two groups (p = 0.69, 0.21–0.43, and 0.98 for T2, DWI, and ADC, respectively). Mucinous and non-mucinous PLCs were successfully discriminated by both T2-based (83.2–100% sensitivity and 69.3–96.2% specificity) and ADC-based (40–85% sensitivity and 60–96.67% specificity) radiomic features. SIMs cannot reliably discriminate between PCLs. Radiomics have the potential to augment the common MRI diagnosis of PLCs by providing quantitative and reproducible imaging features, but validation is required by further studies.