We consider a patch-based learning approach defined in terms of neural networks to estimate spatially adaptive regularisation parameter maps for image denoising with weighted Total Variation and test it to situations when the noise distribution is unknown. As an example, we consider situations where noise could be either Gaussian or Poisson and perform preliminary model selection by a standard binary classification network. Then, we define a patch-based approach where at each image pixel an optimal weighting between TV regularisation and the corresponding data fidelity is learned in a supervised way using reference natural image patches upon optimisation of SSIM and in a sliding window fashion. Extensive numerical results are reported for both noise models, showing significant improvement w.r.t. results obtained by means of optimal scalar regularisation.

Its mortality rate is considered high, with respect to its incidence rate, as this tumor is typically asymptomatic at the early stages for many patients [1, 2]. This leads to a late diagnosis of the tumor, where the curability likelihood is lower. RCC can be categorized into multiple histological subtypes, mainly: Clear Cell Renal Cell Carcinoma (ccRCC) forming 75% of RCCs, Papillary Renal Cell Carcinoma (pRCC) accounting for 10%, and Chromophobe Renal Cell Carcinoma (chRCC) accounting for 5%. Some of the other sutypes include Collecting Duct Renal Cell Carcinoma (cdRCC), Tubulocystic Renal Cell Carcinoma (tRCC), and unclassified [1]. Approximately 10% of renal tumors belong to the benign entities neoplasms, being Oncocytoma (ONCO) the most frequent subtype with an incidence of 3-7% among all RCCs [3, 2]. These subtypes show different cytological signature as well as histological features [2], which ends up in significantly different prognosis. The correct categorization of the tumor subtype is indeed of major importance, as prognosis and treatment approaches depend on it and on the disease stage. For instance, the overall 5-year survival rate significantly differs among the different histological subtypes, being 55-60% for ccRCC, 80-90% for pRCC and 90% for chRCC.