Interobserver reproducibility of perineural invasion of prostatic adenocarcinoma in needle biopsies

Perineural invasion detection in pancreatic ductal adenocarcinoma using artificial intelligence

Perineural invasion (PNI) refers to the presence of cancer cells around or within nerves, raising the risk of residual tumor. Linked to worse prognosis in pancreatic ductal adenocarcinoma (PDAC), PNI is also being explored as a therapeutic target. The purpose of this work was to build a PNI detection algorithm to enhance accuracy and efficiency in identifying PNI in PDAC specimens. Training used 260 manually segmented nerve and tumor HD images from 6 scanned PDAC cases; Analytical performance analysis used 168 additional images; clinical analysis used 59 PDAC cases. The algorithm pinpointed key areas of tumor-nerve proximity for pathologist confirmation. Analytical performance reached sensitivity of 88% and 54%, and specificity of 78% and 85% for the detection of nerve and tumor, respectively. Incorporating tumor-nerve distance in clinical evaluation raised PNI detection from 52 to 81% of all cases. Interestingly, pathologist analysis required an average of only 24 s per case. This time-efficient tool accurately identifies PNI in PDAC, even with a small training cohort, by imitating pathologist thought processes.

Diagnostic concordance between traditional and digital workflows. A study on 1427 prostate biopsies

Objective

To evaluate intra-observer diagnostic reproducibility using traditional slides (TS) versus whole slide images (WSI).

Methods

TS and WSI of 1427 prostatic biopsies (107 consecutive patients) were evaluated by a single pathologist. Agreement between readings was evaluated with Gwet's Agreement coefficient (AC) and Landis and Koch benchmark scale.

Results

The positive/negative agreement between the readings was almost perfect (AC1= 0.962; 95% CI[0.949,0.974]), with method independent distribution of discrepancies. Among positive biopsies, 212 had identical Gleason score (GS) on TS and WSI and discordant GS in 69 cases (AC2 = 0.932; 95% CI[0.907, 0.956]). Concordant negative and positive patient classification was observed in 39 and 64 cases, respectively; two cases were assigned to the positive group on TS and 2 on WSI configuring an almost perfect agreement (AC1=0.929; 95% C1[0.860, 0.998]). ISUP Grade group (ISUP GG) agreement was evaluated in the 60 concordantly positive cases: in 45 cases it was identical on TS and WSI; in 10 biopsies the discrepancy implied a modification of the assigned ISUP GG of ≤ 1 class and in 5 the discrepancy implied a modification of 2 classes. Gwet's agreement coefficient was (95% CI [0.834, 0.962]), i.e.: almost perfect agreement.

Conclusions

Our data show almost perfect agreement between digital and traditional diagnostic activity in a routine setting, confirming that digital pathology can be safely introduced into routine workflows.

Clinical Significance of Perineural Invasion by Prostate Cancer Detected on Needle Core Biopsy

OBJECTIVES

The clinical impact of the laterality of perineural invasion (PNI) by prostate cancer remains poorly understood. We herein compared radical prostatectomy (RP) findings and long-term oncologic outcomes in patients with prostate cancer with PNI in two prostate biopsy (PBx) sites.

METHODS

We retrospectively assessed 170 consecutive patients undergoing systematic sextant PBx where PNI had been detected in two of six PBx sites, followed by RP.

RESULTS

PNI occurred unilaterally in 140 (82.4%) cases and bilaterally in 30 (17.6%) cases. Compared with unilateral PNI, bilateral PNI was significantly associated with a higher number of cancer-positive sites and longer total tumor length on PBx. However, there were no significant differences in RP findings, including tumor grade/stage and tumor volume, between unilateral and bilateral PNI cohorts. Kaplan-Meier analysis revealed that patients with bilateral PNI had a significantly higher risk of disease progression after RP than those with unilateral PNI (P = .038). In multivariate analysis, bilateral PNI (vs unilateral PNI) showed significance for progression (hazard ratio, 2.281; P = .023).

CONCLUSIONS

In PBx specimens exhibiting PNI in two sextant sites, bilateral PNI was found to be associated with poorer prognosis as an independent predictor but not worse histopathologic features in RP specimens compared with unilateral PNI.

The Role of Perineural Invasion in Prostate Cancer and Its Prognostic Significance

Simple Summary

Prostate cancer is one of the most frequently diagnosed cancers in men worldwide. Perineural invasion (PNI), the movement of cancer cells along nerves, is a commonly observed approach to tumor spread and is important in both research and clinical practice of prostate cancer. However, despite many studies reporting on molecules and pathways involved in PNI, understanding its clinical relevance remains insufficient. In this review, we aim to summarize the current knowledge of mechanisms and prognostic significance of PNI in prostate cancer, which may provide new perspectives for future studies and improved treatment.

Abstract

Perineural invasion (PNI) is a common indication of tumor metastasis that can be detected in multiple malignancies, including prostate cancer. In the development of PNI, tumor cells closely interact with the nerve components in the tumor microenvironment and create the perineural niche, which provides a supportive surrounding for their survival and invasion and benefits the nerve cells. Various transcription factors, cytokines, chemokines, and their related signaling pathways have been reported to be important in the progress of PNI. Nevertheless, the current understanding of the molecular mechanism of PNI is still very limited. Clinically, PNI is commonly associated with adverse clinicopathological parameters and poor outcomes for prostate cancer patients. However, whether PNI could act as an independent prognostic predictor remains controversial among studies due to inconsistent research aim and endpoint, sample type, statistical methods, and, most importantly, the definition and inclusion criteria. In this review, we provide a summary and comparison of the prognostic significance of PNI in prostate cancer based on existing literature and propose that a more standardized description of PNI would be helpful for a better understanding of its clinical relevance.

Detection of perineural invasion in prostate needle biopsies with deep neural networks

The presence of perineural invasion (PNI) by carcinoma in prostate biopsies has been shown to be associated with poor prognosis. The assessment and quantification of PNI are, however, labor intensive. To aid pathologists in this task, we developed an artificial intelligence (AI) algorithm based on deep neural networks. We collected, digitized, and pixel-wise annotated the PNI findings in each of the approximately 80,000 biopsy cores from the 7406 men who underwent biopsy in a screening trial between 2012 and 2014. In total, 485 biopsy cores showed PNI. We also digitized more than 10% (n = 8318) of the PNI negative biopsy cores. Digitized biopsies from a random selection of 80% of the men were used to build the AI algorithm, while 20% were used to evaluate its performance. For detecting PNI in prostate biopsy cores, the AI had an estimated area under the receiver operating characteristics curve of 0.98 (95% CI 0.97-0.99) based on 106 PNI positive cores and 1652 PNI negative cores in the independent test set. For a pre-specified operating point, this translates to sensitivity of 0.87 and specificity of 0.97. The corresponding positive and negative predictive values were 0.67 and 0.99, respectively. The concordance of the AI with pathologists, measured by mean pairwise Cohen's kappa (0.74), was comparable to inter-pathologist concordance (0.68 to 0.75). The proposed algorithm detects PNI in prostate biopsies with acceptable performance. This could aid pathologists by reducing the number of biopsies that need to be assessed for PNI and by highlighting regions of diagnostic interest.

Nerve density in cancer: Less is better

The density of nerves in cancer is emerging as a relevant clinical parameter for patient survival. Nerves in the tumor microenvironment have been associated with poor survival and recurrence, particularly if involved in perineural invasion. However, usually only a few nerves inside a tumor are affected by perineural invasion, while most nerves are not. Mechanistic studies have shown nerve-secreted factors promote tumor growth and invasion thereby making tumors more aggressive. Therefore, the overall number of nerves in the tumor microenvironment should be more representative of the nerve-tumor biological interaction than perineural invasion. This review summarizes the available clinical information about nerve density as a measure of clinical outcome in cancer and explores the mechanisms underlying nerve density in cancer, specifically, neurogenesis, axonogenesis, and neurotropism.