Comparison of quantitative parameters and radiomic features as inputs into machine learning models to predict the Gleason score of prostate cancer lesions.

INTRODUCTION: The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification. METHODS: 20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (KTRANS), efflux rate constant (Kep), and extracellular volume ratio (Ve) from mpMR images, and SUVmean and SUVmax from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM). RESULTS: SUVmax yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input. CONCLUSIONS: ML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy.

Ureteral pseudodiverticulosis and urothelial cell carcinoma: rethinking the association.

PURPOSE: To compare frequency of new and recurrent urothelial cell carcinoma (UCC) among patients with and without pseudodiverticulosis on imaging. METHODS: This retrospective case-control study compared all 113 sequential patients with ureteral pseudodiverticulosis on radiographic urography between 1/1/2002 and 12/31/2012. Six patients were lost to follow-up. 107 patients without pseudodiverticulosis were matched by imaging modality, clinical indication, and tumor grade. Known UCC and primary outcome of new or recurrent UCC were determined through pathology on cystoscopy or clinical follow-up. RESULTS: Nearly half of patients with pseudodiverticulosis had known UCC at the time of imaging (49/107, 46%). Mean cystoscopy follow-up was 7.0 and 4.6 years for pseudodiverticulosis cases with and without known UCC, respectively, and 7.5 and 7.3 years for controls, respectively. Mean clinic follow-up was 7.5 and 6.0 years for pseudodiverticulosis cases with and without known UCC, respectively, and 6.4 and 7.6 years for controls, respectively. Among patients with known UCC at the time of imaging, similar rates of recurrent UCC were demonstrated on follow-up among patients with pseudodiverticulosis (6/49, 12%) and without (7/49, 14%). Among patients with no known history of UCC at the time of imaging, no patients with pseudodiverticulosis developed UCC on follow-up and 5% (3/58) of patients without pseudodiverticulosis developed UCC. CONCLUSION: Although half of patients with ureteral pseudodiverticulosis have a known diagnosis of UCC, the presence of pseudodiverticulosis did not signify an increased likelihood of developing new or recurrent UCC over the follow-up period.

Surveillance Neck Sonography After Thyroidectomy for Papillary Thyroid Carcinoma: Pitfalls in the Diagnosis of Locally Recurrent and Metastatic Disease.

A sonographic examination of the neck performed 6 to 12 months after thyroid surgery in patients with differentiated thyroid cancer is strongly recommended by the American Thyroid Association and considered mandatory by the European Thyroid Association for locoregional surveillance. The aim of this article is to review the normal anatomic changes expected after thyroid surgery and the pathologic mimics of thyroid carcinoma recurrence in post-thyroidectomy patients as they appear on neck sonography. We hope to offer some pearls to increase diagnostic confidence in this setting.

Pancreatic gout and the role of multimodality imaging in its management.

Uric acid deposition in the pancreas is very rare and neither an endoscopic ultrasound (EUS) nor a contrast-enhanced CT image of this condition has ever been published. We describe a case of asymptomatic pancreatic gout that was detected incidentally on CT. Imaging features mimicked pancreatic neoplasm, warranting further evaluation with EUS-guided fine-needle aspiration. Samples revealed debris encrusted with monosodium urate crystals. Follow-up CT showed complete resolution with urate-lowering therapy. We aim to augment current knowledge on the imaging of pancreatic gout and discuss its management.