Search

Differential classification of prostate cancer (CaP) grade group (GG) 2 and 3 tumors remains challenging, likely due to the subjective quantification of percentage of Gleason pattern 4 (%GP4). Artificial intelligence assessment of %GP4 may improve its accuracy and reproducibility and provide information for prognosis prediction. To investigate this potential, a convolutional neural network (CNN) model was trained to objectively identify and quantify Gleason pattern (GP) 3 and 4 areas, estimate %GP4, and assess whether CNN-assessed %GP4 is associated with biochemical recurrence (BCR) risk in intermediate risk GG 2 and 3 tumors. The study was conducted in a radical prostatectomy cohort (1999–2012) of African American men from the Henry Ford Health System (Detroit, Michigan). A CNN model that could discriminate four tissue types (stroma, benign glands, GP3 glands, and GP4 glands) was developed using histopathologic images containing GG 1 (n = 45) and 4 (n = 20) tumor foci. The CNN model was applied to GG 2 (n = 153) and 3 (n = 62) for %GP4 estimation, and Cox proportional hazard modeling was used to assess the association of %GP4 and BCR, accounting for other clinicopathologic features including GG. The CNN model achieved an overall accuracy of 86% in distinguishing the four tissue types. Further, CNN-assessed %GP4 was significantly higher in GG 3 compared with GG 2 tumors (p = 7.2*10− 11). %GP4 was associated with an increased risk of BCR (adjusted HR = 1.09 per 10% increase in %GP4, p = 0.010) in GG 2 and 3 tumors. Within GG 2 tumors specifically, %GP4 was more strongly associated with BCR (adjusted HR = 1.12, p = 0.006). Our findings demonstrate the feasibility of CNN-assessed %GP4 estimation, which is associated with BCR risk. This objective approach could be added to the standard pathological assessment for patients with GG 2 and 3 tumors and act as a surrogate for specialist genitourinary pathologist evaluation when such consultation is not available.

Low-grade oncocytic tumour (LOT) of the kidney has recently emerged as a potential novel tumour type. Despite similarity to oncocytoma or eosinophilic chromophobe renal cell carcinoma, it shows diffuse keratin 7 immunohistochemistry (IHC) and negative KIT (CD117), which differs from both. We aimed to identify the molecular characteristics of these tumours. Seventeen tumours (one male, 16 female, nine previously published) fitting the original description of this entity (solid eosinophilic cell morphology, often with areas of tumour cells loosely stretched in oedematous stroma, and the above IHC features) were analysed with a next- generation sequencing panel of 324 cancer- associated genes from formalin-fixed, paraffin- embedded tissue. All tumours harboured at least one alteration in either TSC1 (n = 7, 41%), TSC2 (n = 2, 12%), MTOR (n = 5, 29%) or PIK3CA (n = 4, 24%). Four tumours harboured a second alteration, including two NF2, one each in conjunction with MTOR and TSC2 alterations, one PTEN with TSC1 alteration and one tumour with both MTOR and TSC1 alterations. No other renal cancer-related or recurring gene alterations were identified. In addition to the previously described IHC findings, 16 of 16 were positive for GATA3. Eleven patients with follow-up had no metastases or recurrent tumours. Recurrent tuberous sclerosis/MTOR pathway gene alterations in LOT support its consideration as a distinct morphological, immunohistochemical and genetic entity. PIK3CA is another pathway member that may be altered in these tumours. Further study will be necessary to determine whether tumour behaviour or syndromic associations differ from those of oncocytoma and chromophobe carcinoma, warranting different clinical consideration.