Development of a Radiomics-Based Model to Predict Graft Fibrosis in Liver Transplant Recipients: A Pilot Study.

Liver Transplantation is complicated by recurrent fibrosis in 40% of recipients. We evaluated the ability of clinical and radiomic features to flag patients at risk of developing future graft fibrosis. CT scans of 254 patients at 3-6 months post-liver transplant were retrospectively analyzed. Volumetric radiomic features were extracted from the portal phase using an Artificial Intelligence-based tool (PyRadiomics). The primary endpoint was clinically significant (≥F2) graft fibrosis. A 10-fold cross-validated LASSO model using clinical and radiomic features was developed. In total, 75 patients (29.5%) developed ≥F2 fibrosis by a median of 19 (4.3-121.8) months. The maximum liver attenuation at the venous phase (a radiomic feature reflecting venous perfusion), primary etiology, donor/recipient age, recurrence of disease, brain-dead donor, tacrolimus use at 3 months, and APRI score at 3 months were predictive of ≥F2 fibrosis. The combination of radiomics and the clinical features increased the AUC to 0.811 from 0.793 for the clinical-only model (p = 0.008) and from 0.664 for the radiomics-only model (p < 0.001) to predict future ≥F2 fibrosis. This pilot study exploring the role of radiomics demonstrates that the addition of radiomic features in a clinical model increased the model's performance. Further studies are required to investigate the generalizability of this experimental tool.

Gastrosplenic Fistula Secondary to Simultaneous Gastric and Splenic Diffuse Large B-Cell Lymphoma.

Gastrosplenic fistula is a rare complication arising mainly secondary to involvement of the stomach or spleen by lymphoma. A delayed diagnosis is associated with high morbidity and mortality. We present a case of gastrosplenic fistula secondary to gastric and splenic involvement by diffuse large B-cell lymphoma with relevant imaging findings. The patient was successfully treated with surgical resection.

Risk of gallbladder cancer in patients with primary sclerosing cholangitis and radiographically detected gallbladder polyps.

BACKGROUND & AIMS: Primary sclerosing cholangitis (PSC) is associated with an increased risk of gallbladder cancer (GBC). Gallbladder polyps potentially harbour malignancy and thus international guidelines recommend prophylactic cholecystectomy for gallbladder polyps of any size in patients with PSC. To best inform patient care we sought to quantify the malignant risk of gallbladder polyps in patients with PSC. METHODS: A retrospective cohort study of patients followed in secondary and tertiary care settings in two large PSC clinics in North America was performed. RESULTS: In total, 453 patients were included with a median (IQR) follow-up time of 7.7 (4.1-12) years. A gallbladder polyp was radiographically detected in 16% (n = 71) with median size (range) of 4 (2-18) mm. In this group, post-cholecystectomy histology (n = 17) reported benign or no polyp in 77% (n = 13), dysplasia in 5.9% (n = 1) and malignancy in 18% (n = 3). The GBC rate was 8.8 (95% CI 1.8-25.7) per 1000 person-years in patients with a radiographically detected gallbladder polyp. GBC was associated with polyps >10 mm, interval growth or mass-like lesions on pre-operative imaging. In patients who did not have cholecystectomy (n = 50), the polyp was only transiently seen in 80% (n = 40), remained stable or decreased in size in 10% (n = 5) and increased in size in 6% (n = 3). The majority of gallbladder polyps did not show significant growth over time (0.041 mm/year [95% CI -0.017 to 0.249]). CONCLUSIONS: Most gallbladder polyps in patients with PSC are benign. Short-term surveillance imaging may be considered prior to recommending immediate cholecystectomy in patients with PSC without high-risk imaging features.

Extramural venous invasion in rectal cancer: overview of imaging, histopathology, and clinical implications.

OBJECTIVE: Extramural venous invasion (EMVI) is an independent prognostic factor for prediction of overall unfavorable outcomes in rectal cancer. While EMVI has traditionally been detected in postoperative pathologic specimens, MRI can provide this important piece of information preoperatively. This article reviews the methods of EMVI detection and their clinical implications for treatment and outcomes of rectal cancer. CONCLUSION: EMVI has fundamental implications for rectal cancer prognosis and long-term outcomes. Since MRI has the advantage of preoperative detection of EMVI, it has been suggested that MRI-detected EMVI be incorporated for preoperative chemoradiotherapy (CRT) treatment stratification of rectal cancer for better patient triage and outcomes.