RESUMEN
BACKGROUND: Accurate delineations of regions of interest (ROIs) on multi-parametric magnetic resonance imaging (mpMRI) are crucial for development of automated, machine learning-based prostate cancer (PCa) detection and segmentation models. However, manual ROI delineations are labor-intensive and susceptible to inter-reader variability. Histopathology images from radical prostatectomy (RP) represent the "gold standard" in terms of the delineation of disease extents, for example, PCa, prostatitis, and benign prostatic hyperplasia (BPH). Co-registering digitized histopathology images onto pre-operative mpMRI enables automated mapping of the ground truth disease extents onto mpMRI, thus enabling the development of machine learning tools for PCa detection and risk stratification. Still, MRI-histopathology co-registration is challenging due to various artifacts and large deformation between in vivo MRI and ex vivo whole-mount histopathology images (WMHs). Furthermore, the artifacts on WMHs, such as tissue loss, may introduce unrealistic deformation during co-registration. PURPOSE: This study presents a new registration pipeline, MSERgSDM, a multi-scale feature-based registration (MSERg) with a statistical deformation (SDM) constraint, which aims to improve accuracy of MRI-histopathology co-registration. METHODS: In this study, we collected 85 pairs of MRI and WMHs from 48 patients across three cohorts. Cohort 1 (D1), comprised of a unique set of 3D printed mold data from six patients, facilitated the generation of ground truth deformations between ex vivo WMHs and in vivo MRI. The other two clinically acquired cohorts (D2 and D3) included 42 patients. Affine and nonrigid registrations were employed to minimize the deformation between ex vivo WMH and ex vivo T2-weighted MRI (T2WI) in D1. Subsequently, ground truth deformation between in vivo T2WI and ex vivo WMH was approximated as the deformation between in vivo T2WI and ex vivo T2WI. In D2 and D3, the prostate anatomical annotations, for example, tumor and urethra, were made by a pathologist and a radiologist in collaboration. These annotations included ROI boundary contours and landmark points. Before applying the registration, manual corrections were made for flipping and rotation of WMHs. MSERgSDM comprises two main components: (1) multi-scale representation construction, and (2) SDM construction. For the SDM construction, we collected N = 200 reasonable deformation fields generated using MSERg, verified through visual inspection. Three additional methods, including intensity-based registration, ProsRegNet, and MSERg, were also employed for comparison against MSERgSDM. RESULTS: Our results suggest that MSERgSDM performed comparably to the ground truth (p > 0.05). Additionally, MSERgSDM (ROI Dice ratio = 0.61, landmark distance = 3.26 mm) exhibited significant improvement over MSERg (ROI Dice ratio = 0.59, landmark distance = 3.69 mm) and ProsRegNet (ROI Dice ratio = 0.56, landmark distance = 4.00 mm) in local alignment. CONCLUSIONS: This study presents a novel registration method, MSERgSDM, for mapping ex vivo WMH onto in vivo prostate MRI. Our preliminary results demonstrate that MSERgSDM can serve as a valuable tool to map ground truth disease annotations from histopathology images onto MRI, thereby assisting in the development of machine learning models for PCa detection on MRI.
Asunto(s)
Próstata , Neoplasias de la Próstata , Masculino , Humanos , Próstata/diagnóstico por imagen , Próstata/cirugía , Próstata/patología , Imagen por Resonancia Magnética/métodos , Neoplasias de la Próstata/diagnóstico por imagen , Neoplasias de la Próstata/cirugía , Prostatectomía , PelvisRESUMEN
Background Intraprostatic inflammation is frequently observed in the prostate and linked to prostatic diseases, including prostatitis, benign prostatic hyperplasia (BPH), and cancer. The etiology of prostate diseases is unclear. Periodontal diseases are associated with an increased risk of prostate diseases. In men, chronic prostatitis and moderate/severe periodontitis have significantly elevated serum prostate-specific antigen (PSA) levels. Treatment of periodontal disease reduced PSA levels in men. The presence of periodontal pathogens deoxyribonucleic acid (DNA) was identified in the prostate fluid of prostatitis patients. These pathogenic bacteria might have the potential to trigger prostatitis progressing to prostatic adenocarcinoma. The mechanism(s) explaining the etiology of association between periodontal disease and prostate cancer remains unclear. However, the presence of periodontal pathogens has not been analyzed in the prostate gland. Objective To identify and compare the presence of specific periodontal pathogens in the areas of BPH, inflammation, and cancer of the prostate glands diagnosed with malignancy. Materials and methods Whole-mount radical prostatectomy sections from men (n=30) were identified for BPH, inflammation, and cancer areas and marked for tissue procurement. The tissues were subjected to DNA isolation and analysis of microbial DNA and total bacterial load for the following pathogens, including Porphyromonas gingivalis strain ATCC 33277, Prevotella intermedia strain B422, Treponema denticola strain 35405, Fusobacterium nucleatum subsp. fusiform strain, Tannerella forsythia strain ATCC 43037, and Campylobacterâââââââ rectus strain ATCC 33238performed real-time PCR. The universal bacterial primer pairs were used to detect genomic DNA (gDNA) from the total bacteria present in the samples. All species-specific primers were designed to target the variable regions of the 16S ribosomal RNA (rRNA). Data were analyzed using the 2-ΔΔCT method, statistically validated using unpaired t-test and ANOVA test. Results A total of 90 samples of prostate tissue specimens were analyzed for periodontal pathogens; only one pathogen (F. nucleatum subsp. fusiform strain ATCC 51190) showed a significant difference compared to the expression of S. epidermidis (internal control). In particular, F. nucleatum expression was 9, 11.9, and 10.3-fold higher in BPH, inflammation, and cancer, respectively, at p-value <0.05. Moreover, the bacterial load abundance/expression was almost similar in BPH (46.8-fold), inflammation (40.9 fold), and cancer (41.5 fold) higher. There was no significant difference in bacterial load (folder change) among the three areas of BPH, inflammation, and cancer (p-valve>0.05). Similarly, there was no significant difference between F. nucleatum (folder change) among the three areas (p-valve>0.05). Conclusion Fusobacterium nucleatum is identified in the prostates that harbor cancer, chronic inflammation, and BPH.