Clinical Case Summary

The introduction and increasingly wide use of immune checkpoint inhibitors in the treatment of malignant diseases has been revolutionary in the last decade. However, as these inhibitors alter immunity through T-cell modulation, immune-related adverse events(irAEs) driven by the very same immunologic mechanisms responsible for the therapeutic effects might occur.
Herein, we present a case of a 42 year-old woman with locally advanced melanoma who developed a number of concomitant irAEs: pancreatitis, colitis, hepatitis, thyroiditis but the most rare and the most severe of them was immune checkpoint inhibitor- related gastritis. This patient presented with diarrhea, nausea, vomiting, weight loss, and reduced oral intake for two weeks. She had previously been treated with 16 doses of nivolumab, then switched to combination of nivolumab/ipilimumab due to progression of the melanoma.
Diagnosis was confirmed with oesophagogastroduodenoscopy (OGDS), computed tomography(CT) scan and biopsy. The patient was treated with proton pump inhibitor combined with methylprednisolon for 2 weeks without improvement, after which Mycofenolate mofetil was added again without improvement of symptoms. Considering the severity of the irAEs, immunotherapy was discontinued definitively.
We started salvage therapy with Infliximab in a dose of 5mg/kg - two applications at week 0 and week 2 with minor improvement confirmed with a second OGDS. Local radiotherapy was initiated. Despite the multidisciplinary approach the patient's condition continued to worsen and head CT scan noted brain metastasis. The patient died shortly afterwards.

References

endoscopic images, computed tomography images, histological images

Disclosure

no conflict of interest

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

Introduction: Since the covid-19 pandemic, there has been a significant resurgence of tuberculosis in endemic countries. As a result, extremely rare localizations of tuberculosis have appeared. Stomach involvement is rarely seen in gastrointestinal tuberculosis. The clinical presentation can be either alarming symptoms (anorexia, weight loss...), or a complication (digestive hemorrhage, perforation). In front of the weight loss and the alteration of the general state, the diagnosis is often directed towards a neoplastic pathology, which represents a diagnostic challenge.

Clinical case: We received in our institution a 77-year-old woman, referred from the emergency room for hematemesis with epigastric pain. She had experienced important weight loss during the last month. The clinical examination was unremarkable, and blood tests was normal, despite an hemoglobin of 8,7 g/dl. An upper endoscopy was performed, which showed the existence of 3 ulcerations localized on the greater curvature of the stomach, the largest measuring 4 centimeters. Biopsies of the ulceration borders were performed. Histology revealed the presence of an epithelio-giganto-cellular granuloma with caseous necrosis.
The final diagnosis was gastric tuberculosis. We started an antituberculosis therapy, with a proton pump inhibitor, with significant improvement within one month.

Conclusion: In conclusion, gastric tuberculosis, even if it is a rare entity, should be considered when gastric signs are associated with signs of tuberculosis impregnation, especially in endemic countries. The endoscopic signs are not specific, only histology can establish a reassuring diagnosis. Our patient was successfully treated by Antitubercular drug despite the severity of his bleeding.

References

Endoscopic images showing tow small gastric ulcers and a large gastric ulcer of the greater curve of the stomach
Histological image showing epithelio-giganto-cellular granuloma with caseous necrosis

Introduction

Although circulating tumor DNA (ctDNA) has shown promising results in monitoring response/relapse in pancreatic cancer patients, the limited availability of sensitive, cost-effective, and efficient molecular technologies for their detection has restricted its use. Here, we present a fast single-step methodology utilizing the amplification-refractory mutation system (ARMS) coupled with high-resolution melting analysis (HRMA) as a new method to evaluate KRAS mutations in tumor samples and ctDNA.

Aims & Methods

This is a prospective bicentric cohort study including pancreatic ductal adenocarcinoma cancer patients with tumor samples and liquid biopsies collected at diagnosis. Codon-12 KRAS mutations were tested by Sanger-Sequencing (SS) and G12D, G12V, G12R, G12C mutations were tested by ARMS/HRMA. The frequency of KRAS mutations by both techniques was evaluated. Progression-free survival and overall survival were also calculated.

Results

41 patients, 61% male, with median-age at diagnosis of 69 (IQR 62-76) years-old, 40% with metastatic disease at diagnosis were included. SS detected KRAS mutations in 23 (56%) tumor samples (G12D=12, G12V=7, G12R=2, G12C=2) and ARMS/HRMA in 33 (81%) (G12D=18, G12V=9, G12R=2, G12C=1, G12V/G12D=2, G12D/G12C=1), with a moderate concordance in mutation detection (kappa=0.48, p<0.001). Regarding liquid biopsies, no mutations were detected with SS technique, but ARMS/HRMA detected KRAS mutations in 7 patients (G12D=4, G12V=2, G12V/G12D=1), all of which were in agreement with mutations found in primary tumor. In non-operated patients, those with KRAS mutations detected in liquid biopsies showed a trend towards lower OS compared to patients with wildtype tumors (2 vs 10 months, HR 3.143, p=0.133).

Conclusion

The ARMS/HRMA method is a more effective means of detecting KRAS mutations in both PDAC tumor samples and liquid biopsies compared to SS, although its accuracy in liquid biopsies can be optimized. It might become a cost-effective tool to assess response to medical or surgical therapy as well as to detect early relapse. Further studies are required to validate these findings.