Introduction

Endoscopic ultrasound (EUS) is the gold standard for evaluating pancreatic lesions, allowing for real-time imaging and biopsy sampling. Nevertheless, the differentiation between solid pancreatic lesions — such as pancreatic ductal adenocarcinoma (PDAC) and pancreatic neuroendocrine tumors (PNETs) — as well as cystic lesions is often troublesome. Specifically, identifying intraductal papillary mucinous neoplasms (IPMNs) with varying degrees of dysplasia is crucial for guiding clinical management. However, the diagnostic accuracy of current methods remains suboptimal. This multicenter study aimed to develop and validate convolutional neural networks (CNNs) to characterize solid and cystic pancreatic lesions and stratify IPMNs into high-grade dysplasia/carcinoma (HGD/C) and low-grade dysplasia (LGD).

Aims & Methods

This multicenter study included EUS images from 12 centers in Spain, Brazil, the United Kingdom and the United States of America. Solid lesion differentiation (PDAC vs. PNET) was achieved using a CNN trained on 49034 images from 95 patients (n=69 for PDAC and n=26 for PNET), with diagnoses confirmed via EUS-guided fine-needle biopsy or surgical specimen analysis. A second CNN was trained on 79395 images from 82 patients (n=64 for mucinous cystic lesions and n=18 for non-mucinous cystic lesions). Finally, a third model used the subset of IPMNs (n=51046 frames, 30 patients) to distinguish between HGD/C (n=5 patients) and LGD (n=25 patients). Histological confirmation was used as the gold standard. Performance metrics included sensitivity, specificity, accuracy, and area under the precision-recall curve (AUC-PR). To comprehensively determine the model's performance, we evaluated multiple thresholds for the confidence score and the IoU, between 0.45 and 0.55 with a step of 0.02 ([0.45, 0.47, 0.50, 0.52, 0.55]). The datasets were split into training (70%), validation (20%), and testing (10%) subsets.

Results

For solid lesions, the model differentiated PDAC from PNETs with an accuracy of 91.8%, with sensitivities of 96.2% and 97.8%, respectively. The AUC-PR was 0.982 for PDAC and 0.977 for PNET. Regarding cystic lesions the model detected mucinous cystic lesions with a sensitivity of 97.5%, an overall accuracy of 89.7% and an AUC-PR of 0.977. When the subset of IPMNs was specifically analyzed, the model distinguished IPMNs with HGD/C from those with LGD with a sensitivity of 97.5%, specificity of 94.3%, and an overall accuracy of 89.8%. The AUC was 0.988.

Conclusion

This is the first multicenter, transatlantic AI study aiming to provide a holistic approach to both solid and cystic pancreatic lesions, focusing on those with a significantly higher malignant potential. Our models achieved high accuracy in identifying and differentiating these conditions. Furthermore, to our knowledge this is the first integrative model to include the ability to stratify IPMNs into LGD and HGD/C, which has significant clinical implications, potentially reducing unnecessary surgeries and ensuring timely intervention for high-risk patients. The inclusion of data from diverse regions reduces demographic bias and enhances model generalizability. Real-time implementation of these solutions could significantly improve decision-making in EUS and optimize patient outcomes.

Introduction

Irritable bowel syndrome (IBS), which affects between 5 and 10% of the population according to the Rome III or IV diagnostic criteria, manifests as chronic abdominal pain associated with altered bowel transit. Moderate or severe IBS significantly impair the quality of life of patients, who are often dissatisfied with conventional treatments. In search of more effective solutions, many are turning to complementary and alternative approaches, such as hypnotherapy, whose effectiveness is well-established. Among these approaches, osteopathy, adopted by nearly 40% of patients in France, attracts growing interest. Single-centre studies with small sample sizes (30 to 40 patients) have reported promising but miscellaneous results, suggesting an improvement in symptoms and an effect on rectal sensitivity (1), or a transient effect on the severity of IBS (2).

Aims & Methods

Our study aims to evaluate the efficacy of visceral osteopathy on the severity of IBS symptoms in a French multicentre study. The trial, conducted as part of the 2015 National Hospital Clinical Research Program (PHRCN-PHRC-15-294), included adult patients suffering from IBS according to Rome III criteria and with moderate or severe IBS (IBS-SSS of 175 to 500 points at baseline). Patients were randomised into two groups: one with visceral osteopathy (three sessions performed over one month, two weeks apart) and one with placebo manipulation performed by the same osteopaths. Clinical characteristics (age, gender, BMI, IBS subtype according to bowel movements), anxiety (Spielberger State-Trait Anxiety Inventory, STAI-1 and STAI-2) and depression (Beck Depression Inventory or BDI II) levels, quality of life (IBS-QOL, ranging from 0 to 100, with 100 corresponding to the best quality of life), and IBS severity (IBS-SSS) were recorded. The primary objective of the study was the improvement in the IBS-SSS severity score at 2 months (1 month after the end of osteopathy). The effects on anxiety and depression levels as well as on quality of life were secondary objectives. The number of subjects to be included was calculated at 210 patients.

Results

Six centres included a total of 156 patients* (78 per group): mean age of 46 (± 15) years, 73% of women, 60% with IBS-C, 17% with IBS-D, 15% with IBS-M, and 8% with IBS-U. The mean IBS-SSS severity score was 336 (± 66) points (27.1% moderate severity and 72.9% severe with IBS-SSS > 300), with no difference between the two groups. Before inclusion, 61% of patients felt that osteopathy would be effective for their condition. At 2 months, the absolute decrease in the severity score (primary endpoint) was similar in both groups (52.4 ± 97.6 vs. 48.6 ± 98.9 points, p-value = 0.975), suggesting a placebo effect, as were the state-trait anxiety levels and quality of life (secondary endpoints).
* The monitoring committee terminated the study after a futility analysis on the first 156 patients because the study message could not be changed by including additional patients out of a planned total of 210.

Conclusion

In this first randomised multicentre study, visceral osteopathy was no more effective than a placebo manipulation in improving the severity of IBS, psychological comorbidities, or quality of life.

References

(1) Attali et al. Treatment of refractory irritable bowel syndrome with visceral osteopathy: Short-term and long-term results of a randomized trial. Journal of Digestive Diseases 2013; 14; 654–661. doi: 10.1111/1751-2980.12098
(2) Florance et al. Osteopathy improves the severity of irritable bowel syndrome: a pilot randomized sham-controlled study. European Journal of Gastroenterology & Hepatology 2012 ; 24 (8) : p 944-949. DOI: 10.1097/MEG.0b013e3283543eb7

Disclosure

Nothing to disclose