Introduction

Pancreatic Ductal Adenocarcinoma (PDAC) is a highly aggressive and lethal malignancy of the pancreas due to limited treatment response and lack of early diagnosis. PDAC accounts for more than 90% of all pancreatic neoplasms and early PDAC may be missed on Computed Tomography (CT) scan due to similar attenuation as healthy pancreas, small size and hidden location.

Aims & Methods

The current study aims at improving detection of PDAC with CT scans using a deep learning model. It uses three different Convolutional Neural Network (CNN) models namely, Visual Geometry Group 19 (VGG19), Residual Neural Network 50 (ResNet-50) and Inception-v3. A compendium of 129,910 abdomen CT images (107 patients) of PDAC patients and 18,942 abdomen CT images (80 patients) of healthy controls were considered from The Cancer Imaging Archive. Additionally, several pre-processing and image augmentation methods were used to prevent overfitting and improve accuracies.

Results

The current model showed high construct validity with markedly lowered computational power. The Inception-v3 model showed the highest accuracy in the detection of PDAC with an accuracy of 97.93%. Specificity of the VGG-19 model was the highest at 98.77 whereas sensitivity was the highest for the Inception-v3 model at 98.75%. Data on the CNN models’ Performance Metrics (accuracy, sensitivity, specificity and area under ROC) ​were all compared.

Conclusion

The deep learning enabled tool accurately detected PDAC on CT scans versus healthy controls. The models were also reasonably sensitive for tumours below 2 cm.

References

1. Ushio J, Kanno A, Ikeda E, et al. Pancreatic Ductal Adenocarcinoma: Epidemiology and Risk Factors. Diagnostics (Basel). 2021;11(3):562. doi:10.3390/diagnostics11030562
2. Qureshi TA, Gaddam S, Wachsman AM, et al. Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images. Cancer Biomark. 2022;33(2):211-217. doi:10.3233/CBM-210273
3. Ahmed HS. BEYOND TRADITIONAL TOOLS: EXPLORING CONVOLUTIONAL NEURAL NETWORKS AS INNOVATIVE PROGNOSTIC MODELS IN PANCREATIC DUCTAL ADENOCARCINOMA. Arq Gastroenterol. 2024;61:e23107. doi:10.1590/S0004-2803.24612023-117

Clinical Case Summary

A 72-year-old man with a 49-year history of ulcerative colitis (UC), characterized as pancolitis and steroid-dependent, underwent routine surveillance colonoscopy. A congested, ulcerated mass was found in the recto-anal region, with no signs of active colitis in the rest of the colon.
From 2000–2012, he was treated with infliximab, discontinued due to secondary failure, followed by azathioprine (2012–2017), which was stopped due to leukopenia. Since then, he has been on vedolizumab. His medical history also includes hypertension and previous tobacco use.
The patient had been in clinical and biochemical remission for the last two years. Given his long-standing UC and the resection of a lateral spreading tumor (LST) via mucosectomy in 2019 showing hyperplastic mucosa with a focus of low-grade dysplasia, he has been under annual endoscopic surveillance.
At the current exam, a large exophytic, ulcerated mass with superficial necrosis and fibrin (Kudo IV) was seen in the recto-anal region, occupying approximately 1/6 of the luminal circumference and bleeding spontaneously.
Histology revealed a poorly differentiated neuroendocrine carcinoma (NEC) with a high proliferative index (Ki-67: 60%). Staging workup, including CT, pelvic MRI, and endoscopic ultrasound, identified a suspicious regional lymph node, that was confirmed by FDG-PET to be metabolically active.
After multidisciplinary discussion, the decision was made to start systemic chemotherapy without delay. If the patient responds, a total proctocolectomy with permanent ileostomy will be considered.
This case is notable for the rarity of recto-anal NECs, especially in UC patients. Their poor prognosis and unclear association with long-term UC or immunosuppressive treatment complicate management and raise important clinical questions.

References

Images that will be uploaded are: endoscopic findings of the colonic mass, histological specimens of the NEC, radiologic findings (PET)

Introduction

Low Phospholipid-Associated Cholelithiasis (LPAC) syndrome is a rare disorder caused by mutations in the ABCB4 phospholipid transporter, found in biliary canaliculi. These mutations lead to a deficiency in phospholipids and the subsequent precipitation of cholesterol crystals within the small intrahepatic bile ducts. LPAC syndrome can be diagnosed following the emergence of biliary symptoms or through familial screening. The objective of our study is to characterize the epidemiological, clinical, and paraclinical data of patients monitored for LPAC syndrome in our institution and to assess therapeutic responses and outcomes.

Aims & Methods

We collected data from all patients diagnosed with LPAC syndrome at our institution. Diagnosis was established based on the presence of at least two of the following criteria: (1) age at onset of biliary symptoms ≤40 years; (2) presence of hyperechoic intrahepatic foci ("comet tails" or micro-spots); (3) recurrence of biliary symptoms post-cholecystectomy.

Results

10 patients were included. The Average age at diagnosis was 33,6 years, with symptoms typically beginning around age 30. The sex ratio was 2/8 (M/F).a family history of biliary lithiasis and cholecystectomy before the age of 40 were found in 70% of cases . None of the female patients had a history of pregnancy-related cholestasis. 70% of the patients had undergone cholecystectomy prior to their LPAC diagnosis, with recurrence of biliary symptoms before age 40 in all these patients. Clinical presentations upon admission included symptomatic gallstone disease in 5 cases, acute cholangitis due to main bile duct stones in 4 cases, and acute lithiasic pancreatitis in 1 case. Hepatobiliary ultrasound was performed in all patients, revealing comet tail signs in 50% of cases, hyperechoic intrahepatic spots in 20% of cases, and intrahepatic stones in 50% of cases. Biochemical tests showed hyperbilirubinemia in 30% of cases, elevated Gamma-GT and alkaline phosphatase in 80% of cases, and hepatocellular damage in 40% of cases. A mutation in the ABCB4 gene was found in 2-patients.8 patients benefit from An Ursodeoxycholic Acid (UDCA) dosage averaging 11mg/kg, experiencing significant clinical and biological improvements.

Conclusion

LPAC syndrome is a rare pathology in our series, predominantly affecting young, non-overweight women with personal and family history of early biliary stones occurrence . Treatment with Ursodeoxycholic Acid (UDCA) controlled symptoms in the majority of cases.