Machine learning predicts histologic type and grade of canine gliomas based on MRI texture analysis.

Conventional MRI features of canine gliomas subtypes and grades significantly overlap. Texture analysis (TA) quantifies image texture based on spatial arrangement of pixel intensities. Machine learning (ML) models based on MRI-TA demonstrate high accuracy in predicting brain tumor types and grades in human medicine. The aim of this retrospective, diagnostic accuracy study was to investigate the accuracy of ML-based MRI-TA in predicting canine gliomas histologic types and grades. Dogs with histopathological diagnosis of intracranial glioma and available brain MRI were included. Tumors were manually segmented across their entire volume in enhancing part, non-enhancing part, and peri-tumoral vasogenic edema in T2-weighted (T2w), T1-weighted (T1w), FLAIR, and T1w postcontrast sequences. Texture features were extracted and fed into three ML classifiers. Classifiers' performance was assessed using a leave-one-out cross-validation approach. Multiclass and binary models were built to predict histologic types (oligodendroglioma vs. astrocytoma vs. oligoastrocytoma) and grades (high vs. low), respectively. Thirty-eight dogs with a total of 40 masses were included. Machine learning classifiers had an average accuracy of 77% for discriminating tumor types and of 75.6% for predicting high-grade gliomas. The support vector machine classifier had an accuracy of up to 94% for predicting tumor types and up to 87% for predicting high-grade gliomas. The most discriminative texture features of tumor types and grades appeared related to the peri-tumoral edema in T1w images and to the non-enhancing part of the tumor in T2w images, respectively. In conclusion, ML-based MRI-TA has the potential to discriminate intracranial canine gliomas types and grades.

CT findings in five dogs with surgically confirmed colonic torsion.

Colonic torsion is a life-threatening condition that results in colonic ischemia, necrosis, perforation, sepsis, and eventual death. The aim of this multicenter, retrospective case series study was to describe the CT findings in dogs with surgically confirmed colonic torsion. Medical records were searched for dogs with surgically confirmed colonic torsion following abdominal CT. Five dogs met the inclusion criteria. Three had a history of chronic intermittent diarrhea prior to presentation. Two dogs presented with acute vomiting, diarrhea, and abdominal pain and one dog presented with acute vomiting and lethargy. Computed tomographic findings in all dogs with surgically confirmed colonic torsion include: "whirl sign," displacement and distension of the cecum and colon, focal narrowing of the colon, and distension of the mesenteric vasculature in all dogs (5/5); streaky peritoneal fat and peritoneal effusion (4/5), pneumatosis coli (2/5), small intestinal distension (2/5), portal vein thrombosis (1/5), and reduced colonic wall contrast enhancement (1/5). In all dogs (5/5), the torsion site was the descending colon and demonstrated an anticlockwise rotation. At surgery, three of the five dogs had a partial colonic torsion with hyperemia at the site of obstruction and two of the five dogs had a complete torsion with marked necrosis of the colonic wall. Displacement of the colon and cecum, segmental distension and focal narrowing of the colon, the presence of a "whirl sign" and distension of the mesenteric vasculature are CT findings highly suggestive of colonic torsion.

Cholangiocarcinoma and hepatic myelolipoma incarcerated in a peritoneopericardial diaphragmatic hernia with pulmonary metastasis and carcinomatosis in a cat.

CASE SUMMARY: A 14-year-old female neutered Persian-cross cat was presented with a 1 week history of anorexia and lethargy. On physical examination, marked tachypnoea and dyspnoea were evident. Radiographs of the thorax revealed a globoid-shaped cardiac silhouette with heterogeneous opacity consistent with a peritoneopericardial diaphragmatic hernia (PPDH), pulmonary nodules compatible with metastasis, seven sternal segments and a small liver in the cranial abdomen with loss of serosal detail. On echocardiography, there was no evidence of cardiac tamponade. Triple-phase CT angiography demonstrated a mixed soft tissue-, mineral- and fat-attenuated liver mass arising from the left hepatic lobes that showed a pronounced heterogeneous contrast-enhancement pattern within the pericardial sac, which was producing a marked mass effect on the adjacent structures. Additionally, there was an increase in attenuation of the mesenteric fat and peritoneal effusion. The pulmonary nodules were confirmed. Imaging findings were compatible with a malignant hepatic neoplasia incarcerated in a PPDH, lung metastasis and carcinomatosis. Owing to the poor prognosis, the cat was humanely euthanased. Histopathological diagnosis was cholangiocellular carcinoma and hepatic myelolipoma, pulmonary metastasis and carcinomatosis. RELEVANCE AND NOVEL INFORMATION: Hepatic cholangiocarcinoma incarcerated in a PPDH with pulmonary metastasis and carcinomatosis has not been previously described. Suspicion of a hepatic neoplasia should be raised in cases of PPDH and pulmonary nodules.