Stimulated Raman Histology Interpretation by Artificial Intelligence Provides Near-Real-Time Pathologic Feedback for Unprocessed Prostate Biopsies.

PURPOSE: Stimulated Raman histology is an innovative technology that generates real-time, high-resolution microscopic images of unprocessed tissue, significantly reducing prostate biopsy interpretation time. This study aims to evaluate the ability for an artificial intelligence convolutional neural network to interpretate prostate biopsy histologic images created with stimulated Raman histology. MATERIALS AND METHODS: Unprocessed, unlabeled prostate biopsies were prospectively imaged using a stimulated Raman histology microscope. Following stimulated Raman histology creation, the cores underwent standard pathological processing and interpretation by at least 2 genitourinary pathologists to establish a ground truth assessment. A network, trained on 303 prostate biopsies from 100 participants, was used to measure the accuracy, sensitivity, and specificity of detecting prostate cancer on stimulated Raman histology relative to conventional pathology. The performance of the artificial intelligence was evaluated on an independent 113-biopsy test set. RESULTS: Prostate biopsy images obtained through stimulated Raman histology can be generated within a time frame of 2 to 2.75 minutes. The artificial intelligence system achieved a rapid classification of prostate biopsies with cancer, with a potential identification time of approximately 1 minute. The artificial intelligence demonstrated an impressive accuracy of 96.5% in detecting prostate cancer. Moreover, the artificial intelligence exhibited a sensitivity of 96.3% and a specificity of 96.6%. CONCLUSIONS: Stimulated Raman histology generates microscopic images capable of accurately identifying prostate cancer in real time, without the need for sectioning or tissue processing. These images can be interpreted by artificial intelligence, providing physicians with near-real-time pathological feedback during the diagnosis or treatment of prostate cancer.

DHX15 promotes prostate cancer progression by stimulating Siah2-mediated ubiquitination of androgen receptor.

Androgen receptor (AR) activation is critical for prostate cancer (PCa) development and progression, including castration resistance. The nuclear export signal of AR (NESAR) has an important role in AR intracellular trafficking and proteasome-dependent degradation. Here, we identified the RNA helicase DHX15 as a novel AR co-activator using a yeast mutagenesis screen and revealed that DHX15 regulates AR activity by modulating E3 ligase Siah2-mediated AR ubiquitination independent of its ATPase activity. DHX15 and Siah2 form a complex with AR, through NESAR. DHX15 stabilized Siah2 and enhanced its E3 ubiquitin-ligase activity, resulting in AR activation. Importantly, DHX15 was upregulated in PCa specimens and its expression was correlated with Gleason scores and prostate-specific antigen recurrence. Furthermore, DHX15 immunostaining correlated with Siah2. Finally, DHX15 knockdown inhibited the growth of C4-2 prostate tumor xenografts in mice. Collectively, our data argue that DHX15 enhances AR transcriptional activity and contributes to PCa progression through Siah2.

Preliminary experience with a novel method of three-dimensional co-registration of prostate cancer digital histology and in vivo multiparametric MRI.

AIM: To assess a novel method of three-dimensional (3D) co-registration of prostate cancer digital histology and in-vivo multiparametric magnetic resonance imaging (mpMRI) image sets for clinical usefulness. MATERIAL AND METHODS: A software platform was developed to achieve 3D co-registration. This software was prospectively applied to three patients who underwent radical prostatectomy. Data comprised in-vivo mpMRI [T2-weighted, dynamic contrast-enhanced weighted images (DCE); apparent diffusion coefficient (ADC)], ex-vivo T2-weighted imaging, 3D-rebuilt pathological specimen, and digital histology. Internal landmarks from zonal anatomy served as reference points for assessing co-registration accuracy and precision. RESULTS: Applying a method of deformable transformation based on 22 internal landmarks, a 1.6 mm accuracy was reached to align T2-weighted images and the 3D-rebuilt pathological specimen, an improvement over rigid transformation of 32% (p = 0.003). The 22 zonal anatomy landmarks were more accurately mapped using deformable transformation than rigid transformation (p = 0.0008). An automatic method based on mutual information, enabled automation of the process and to include perfusion and diffusion MRI images. Evaluation of co-registration accuracy using the volume overlap index (Dice index) met clinically relevant requirements, ranging from 0.81-0.96 for sequences tested. Ex-vivo images of the specimen did not significantly improve co-registration accuracy. CONCLUSION: This preliminary analysis suggests that deformable transformation based on zonal anatomy landmarks is accurate in the co-registration of mpMRI and histology. Including diffusion and perfusion sequences in the same 3D space as histology is essential further clinical information. The ability to localize cancer in 3D space may improve targeting for image-guided biopsy, focal therapy, and disease quantification in surveillance protocols.

Inverse expression of uroplakins and inducible nitric oxide synthase in the urothelium of patients with bladder outlet obstruction.

OBJECTIVE: To assess the expression and distribution of uroplakins, protein subunits of the asymmetric unit membrane (AUM), and inducible nitric-oxide synthase (iNOS) in the urinary bladder urothelium of patients with bladder outlet obstruction (BOO) caused by benign prostatic hyperplasia (BPH). PATIENTS AND METHODS: Urinary bladder urothelium samples from 15 men (mean age 69 years) with BOO secondary to BPH were processed for light and electron immunocytochemistry. Uroplakins and iNOS were detected, and areas of apical surface covered with AUM were compared with those of iNOS-positive urothelial cells. RESULTS: Areas of superficial urothelial cells with no AUM were found in all obstructed bladder samples. The immuno-electron microscopy showed that the uroplakin-positive cells had the characteristic appearance of terminally differentiated umbrella cells, whereas cells from the uroplakin-negative regions were undifferentiated, typically showing microvilli on their apical surface. iNOS was not detected in areas with continuous AUM staining, but was readily detected in the uroplakin-negative areas. There was an inverse correlation between the intensity of uroplakin and iNOS staining. CONCLUSIONS: In patients with BOO associated with BPH, some superficial urothelial cells lacked the AUM, suggesting focal compromise of the blood-urine permeability barrier. In such relatively undifferentiated urothelial zones there was an accompanying increase in the expression of iNOS, which marks perturbed urothelial differentiation and may modulate bladder response to the outlet obstruction.

Organization of uroplakin subunits: transmembrane topology, pair formation and plaque composition.

The apical surfaces of urothelial cells are almost entirely covered with plaques consisting of crystalline, hexagonal arrays of 16 nm uroplakin particles. Although all four uroplakins, when SDS-denatured, can be digested by chymotrypsin, most uroplakin domains in native urothelial plaques are resistant to the enzyme, suggesting a tightly packed structure. The only exception is the C-terminal, cytoplasmic tail of UPIII (UPIII) which is highly susceptible to proteolysis, suggesting a loose configuration. When uroplakins are solubilized with 2% octylglucoside and fractionated with ion exchangers, UPIa and UPII were bound as a complex by a cation exchanger, whereas UPIb and UPIII were bound by an anion exchanger. This result is consistent with the fact that UPIa and UPIb are cross-linked to UPII and UPIII, respectively, and suggests that the four uroplakins form two pairs consisting of UPIa/II and UPIb/III. Immunogold labelling using a new mouse monoclonal antibody, AU1, revealed that UPIII is present in all urothelial plaques, indicating that the two uroplakin pairs are not segregated into two different types of urothelial plaque and that all plaques must have a similar uroplakin composition. Taken together, these results indicate that uroplakins form a tightly packed structure, that the four uroplakins interact specifically forming two pairs, and that both uroplakin pairs are required for normal urothelial plaque formation.

Urothelial function reconsidered: a role in urinary protein secretion.

Mammalian bladder epithelium functions as an effective permeability barrier. We demonstrate here that this epithelium can also function as a secretory tissue directly involved in modifying urinary protein composition. Our data indicate that normal bovine urothelium synthesizes, as its major differentiation products, two well-known proteases: tissue-type plasminogen activator and urokinase, as well as a serine protease inhibitor, PP5. Moreover, we demonstrate that the urothelium secretes these proteins in a polarized fashion into the urine via a cAMP- and calcium-regulated pathway. Urinary plasminogen activators of ruminants are therefore urothelium derived rather then kidney derived as in some other species; this heterogeneity may have evolved in response to different physiological or dietary factors. In conjunction with our recent finding that transgenic mouse urothelium can secrete ectopically expressed human growth hormone into the urine, our data establish that normal mammalian urothelium can function not only as a permeability barrier but also as a secretor of urinary proteins that can play physiological or pathological roles in the urinary tract.

Ablation of uroplakin III gene results in small urothelial plaques, urothelial leakage, and vesicoureteral reflux.

Urothelium synthesizes a group of integral membrane proteins called uroplakins, which form two-dimensional crystals (urothelial plaques) covering >90% of the apical urothelial surface. We show that the ablation of the mouse uroplakin III (UPIII) gene leads to overexpression, defective glycosylation, and abnormal targeting of uroplakin Ib, the presumed partner of UPIII. The UPIII-depleted urothelium features small plaques, becomes leaky, and has enlarged ureteral orifices resulting in the back flow of urine, hydronephrosis, and altered renal function indicators. Thus, UPIII is an integral subunit of the urothelial plaque and contributes to the permeability barrier function of the urothelium, and UPIII deficiency can lead to global anomalies in the urinary tract. The ablation of a single urothelial-specific gene can therefore cause primary vesicoureteral reflux (VUR), a hereditary disease affecting approximately 1% of pregnancies and representing a leading cause of renal failure in infants. The fact that VUR caused by UPIII deletion seems distinct from that caused by the deletion of angiotensin receptor II gene suggests the existence of VUR subtypes. Mutations in multiple gene, including some that are urothelial specific, may therefore cause different subtypes of primary reflux. Studies of VUR in animal models caused by well-defined genetic defects should lead to improved molecular classification, prenatal diagnosis, and therapy of this important hereditary problem.

[Pathological basis for elevation of serum prostate specific antigen].

67 patients with serum prostate specific antigen (PSA) over 4ng/ml were investigated pathologically. All the patients had prostatic lesions: prostate cancer (24) and benign prostatic lesions (43). The serum PSA was conspicuously higher in the carcinoma group than in the benign group (P < 0.01). When 10ng/ml was used as the low limit to detect prostate cancer, the sensitivity and specificity were 83.3% and 74.4% respectively. We suggest that the range of serum PSA from 4.0 to 10.0ng/ml should be considered dangerous in detecting prostate cancer. The epithelium-blood barrier lesion and epithelial hyperplasia of the prostate might be the pathological basis for the elevation of serum PSA.