Comparing two artificial intelligence software packages for normative brain volumetry in memory clinic imaging.

PURPOSE: To compare two artificial intelligence software packages performing normative brain volumetry and explore whether they could differently impact dementia diagnostics in a clinical context. METHODS: Sixty patients (20 Alzheimer's disease, 20 frontotemporal dementia, 20 mild cognitive impairment) and 20 controls were included retrospectively. One MRI per subject was processed by software packages from two proprietary manufacturers, producing two quantitative reports per subject. Two neuroradiologists assigned forced-choice diagnoses using only the normative volumetry data in these reports. They classified the volumetric profile as "normal," or "abnormal", and if "abnormal," they specified the most likely dementia subtype. Differences between the packages' clinical impact were assessed by comparing (1) agreement between diagnoses based on software output; (2) diagnostic accuracy, sensitivity, and specificity; and (3) diagnostic confidence. Quantitative outputs were also compared to provide context to any diagnostic differences. RESULTS: Diagnostic agreement between packages was moderate, for distinguishing normal and abnormal volumetry (K = .41-.43) and for specific diagnoses (K = .36-.38). However, each package yielded high inter-observer agreement when distinguishing normal and abnormal profiles (K = .73-.82). Accuracy, sensitivity, and specificity were not different between packages. Diagnostic confidence was different between packages for one rater. Whole brain intracranial volume output differed between software packages (10.73%, p < .001), and normative regional data interpreted for diagnosis correlated weakly to moderately (rs = .12-.80). CONCLUSION: Different artificial intelligence software packages for quantitative normative assessment of brain MRI can produce distinct effects at the level of clinical interpretation. Clinics should not assume that different packages are interchangeable, thus recommending internal evaluation of packages before adoption.

A rare case of small bowel leiomyosarcoma presenting with acute gastro-intestinal bleeding.

A 62-year-old Turkish female was admitted to our hospital with acute, progressive melena. Gastroscopy and colonoscopy could not reveal the cause of the melena. Subsequent CT angiography demonstrated a large, exophytic mass in the ileocecal junction as a source of the haemorrhage, leading to urgent laparotomy and resection. Histopathology revealed a low grade leiomyosarcoma (LMS) and confirmatory immunological staining. Primary LMS of the small bowel is an extremely rare gastrointestinal (GI) malignancy. Presentation with acute GI bleeding is even more exceptional, since LMS is a mainly intramural, exophytic tumour of the bowel wall. Immunohistochemistry plays a crucial role in differentiating LMS from GI stromal tumour. The work up of occult small bowel neoplasms currently consists of MRI enterography or enteroclysis and wireless capsule endoscopy. Treatment is surgical resection. This case highlights the non-specific imaging features of ileal LMS and highlights the management of acute GI bleed.

Clinical evaluation vs magnetic resonance imaging of the skier's thumb: A prospective cohort of 30 patients.

INTRODUCTION: A skiers thumb, or a partial or complete rupture of the ulnar collateral ligament (UCL) is a clinical diagnosis. Swelling, pain, natural left-right difference and inexperience of a young physician can cause difficulty to correctly diagnose this injury. However, our theory is that any physician, given the correct instructions, should be able to diagnose this injury solely on clinical findings, without the necessity of additional imaging. MATERIAL AND METHODS: In a large Dutch teaching hospital, physicians (residents with working experience of 6months-3years) working at the ER received instructions for physical examination. Patients >18 years, with an injury <1 week old, suspected of a true skier's thumb had an MRI reported by two independent radiologists to confirm the diagnosis. RESULTS: Thirty patients were included. Seven patients had no fixed endpoint (23%), all had a complete ligamentous rupture of the UCL on MRI, of which three patients had a Stener lesion. Fifteen patients (50%) met with the criteria >35° laxity in extension of MCP/ >20° laxity in 30° flexion of the MCP. Of these, thirteen patients (81%) had a complete rupture (nine Stener lesions (56%)). One patient had a partial injury and one patient had no UCL-injury. Eight patients (27%) had inconclusive results during physical examination. Of these, two had a complete rupture (40%, 1 Stener). Three patients had a partial rupture and three patients had an intact UCL. CONCLUSION: A skier's thumb can be diagnosed by any resident when correctly instructed. Additional imaging when diagnosing a skier's thumb should be reserved in cases when physical examination remains inconclusive.

Nasal paraganglioma: differential diagnosis from a radiologic and pathologic perspective.

A 33-year-old Asian male presented with spontaneous nosebleeds and olfactory sense problems for the past several years. CT scan and MRI demonstrated a large soft tissue mass in the nasal cavity and paranasal sinus with avid and homogeneous contrast enhancement, focal osseous destruction and a non-enhancing cyst at the intracranial tumour-brain margin. After complete endonasal resection, histopathological examination revealed a paraganglioma. This case highlights the non-specific imaging features of a rare paraganglioma of the anterior skull base and the differential diagnosis from both radiological and pathological perspective.

Extremely elevated CA-125 in benign ovarian disease due to stretch of the peritoneum.

Serum concentrations of CA-125 are rarely elevated beyond 1000 U/ml in benign conditions of the ovary in postmenopausal women. In this report, the authors present an unusual case of a 78-year-old woman with an extremely elevated CA-125 concentration of 2897 U/ml without the presence of a malignancy, ascites or pleural effusion. Imaging revealed a large intra-abdominal cystic mass with irregular solid deviations on CT scan, most likely arising from an ovary. Exploratory laparotomy was performed with suspicion of ovarian cancer but histopathological analysis revealed benign serous cystic adenofibroma. This case report highlights the diagnostic challenge of extremely increased levels of CA-125 in postmenopausal women. A possible explanation for this CA-125 elevation could be the mechanical stretch of the peritoneum.

Periprostatic fat correlates with tumour aggressiveness in prostate cancer patients.

STUDY TYPE: Prognostic (case series). LEVEL OF EVIDENCE: 4. What's known on the subject? and What does the study add? Nowadays more and more publications have been published about the topic prostate cancer aggressiveness and obesity with mixed results. However, most of the publications used the BMI as a marker for obesity, while the most metabolic active fat is the visceral fat. To learn more about these relations we measured and used the visceral fat in our paper. OBJECTIVE: To examine if the periprostatic fat measured on computed tomography (CT) correlates with advanced disease we examined patients who received radiotherapy for localized prostate cancer. Several USA reports found a positive association between obesity and prostate cancer aggressiveness. However, in recent European studies these conclusions were not confirmed. Studies concerning this issue have basically relied on body mass index (BMI), as a marker of general obesity. Visceral fat, however, is the most metabolically active and best measured on CT. PATIENTS AND METHODS: In 932 patients, who were treated with external radiotherapy (N=311) or brachytherapy (N=621) for their T1-3N0M0 prostate cancer, different fat measurements (periprostatic fat, subcutaneous fat thickness) were performed on a CT. Associations between the different fat measurements and risk of having high-risk (according to Ash et al., PSA>20 or Gleason score≥8 or T3) disease was measured. RESULTS: The median age (IQR) was 67.0 years (62.0-71.0) and median BMI (IQR) was 25.8 (24.2-28.3). Logistic regression analyses, adjusted for age, revealed a significant association between periprostatic fat density (PFD) and risk of having a high risk disease. (Odds ratio [95% CI] 1.06 [1.04-1.08], P<0.001) CONCLUSION: Patients with a higher PFD had more often aggressive prostate cancer.