Cancer Grade Research Articles

Deep learning-assisted survival prognosis in renal cancer: A CT scan-based personalized approach

This paper presents a deep learning (DL) approach for predicting survival probabilities of renal cancer patients based solely on preoperative CT imaging. The proposed approach consists of two networks: a classifier- and a survival- network. The classifier attempts to extract features from 3D CT scans to predict the ISUP grade of Renal cell carcinoma (RCC) tumors, as defined by the International Society of Urological Pathology (ISUP). Our classifier is a 3D convolutional neural network to avoid losing crucial information on the interconnection of slides in 3D images. We employ multiple procedures, including image augmentation, preprocessing, and concatenation, to improve the performance of the classifier. Given the strong correlation between ISUP grading and renal cancer prognosis in the clinical context, we use the ISUP grading features extracted by the classifier as the input to the survival network. By leveraging this clinical association and the classifier network, we are able to model our survival analysis using a simple DL-based network. We adopt a discrete LogisticHazard-based loss to extract intrinsic survival characteristics of RCC tumors from CT images. This allows us to build a completely parametric survival model that varies with patients' tumor characteristics and predicts non-proportional survival probability curves for different patients. Our results demonstrated that the proposed method could predict the future course of renal cancer with reasonable accuracy from the CT scans. The proposed method obtained an average concordance index of 0.72, an integrated Brier score of 0.15, and an area under the curve value of 0.71 on the test cohorts.

SwinCNN: An Integrated Swin Transformer and CNN for Improved Breast Cancer Grade Classification

SwinCNN: An Integrated Swin Transformer and CNN for Improved Breast Cancer Grade Classification

Using multi-label ensemble CNN classifiers to mitigate labelling inconsistencies in patch-level Gleason grading.

This paper presents a novel approach to enhance the accuracy of patch-level Gleason grading in prostate histopathology images, a critical task in the diagnosis and prognosis of prostate cancer. This study shows that the Gleason grading accuracy can be improved by addressing the prevalent issue of label inconsistencies in the SICAPv2 prostate dataset, which employs a majority voting scheme for patch-level labels. We propose a multi-label ensemble deep-learning classifier that effectively mitigates these inconsistencies and yields more accurate results than the state-of-the-art works. Specifically, our approach leverages the strengths of three different one-vs-all deep learning models in an ensemble to learn diverse features from the histopathology images to individually indicate the presence of one or more Gleason grades (G3, G4, and G5) in each patch. These deep learning models have been trained using transfer learning to fine-tune a variant of the ResNet18 CNN classifier chosen after an extensive ablation study. Experimental results demonstrate that our multi-label ensemble classifier significantly outperforms traditional single-label classifiers reported in the literature by at least 14% and 4% on accuracy and f1-score metrics respectively. These results underscore the potential of our proposed machine learning approach to improve the accuracy and consistency of prostate cancer grading.

Prognostic significance of the PI-RADS score in men with prostate cancer undergoing radical prostatectomy.

MRI-targeted biopsy (T-Bx) for which Prostate Imaging Reporting and Data System (PI-RADS) assessment categories are useful has been shown to more accurately detect clinically significant prostate cancer. However, the prognostic significance of the PI-RADS in prostate cancer patients needs further investigation. In the present study, we compared radical prostatectomy findings and postoperative oncologic outcomes in men with prostate cancer initially undergoing T-Bx for PI-RADS 3 vs. 4 vs. 5 lesions. We assessed consecutive patients undergoing T-Bx with concurrent systematic biopsy (S-Bx), followed by radical prostatectomy. Within our Surgical Pathology database, we identified a total of 207 men where prostatic adenocarcinoma was detected on either S-Bx or T-Bx, or both. Prostate cancer was detected on S-Bx only (n = 32; 15%), T-Bx only (n = 39; 19%), or both S-Bx and T-Bx (n = 136; 66%). These patients had PI-RADS 3 (n = 42; 20%), 4 (n = 86; 42%), or 5 (n = 79; 38%) lesions, while T-Bx detected cancer in 31 (74%) of PI-RADS 3 cases, 72 (84%) of PI-RADS 4 cases, and 72 (91%) of PI-RADS 5 cases. There were no significant differences in any of the clinicopathologic features examined, including tumor grade on biopsy or prostatectomy and pT or pN stage, among the PI-RADS 3 vs. 4 vs. 5 groups, except a significantly higher rate of positive margin and significantly larger tumor volume in PI-RADS 5 cases than in PI-RADS 3 cases. Univariate and multivariable analyses revealed significantly higher risks of biochemical recurrence after prostatectomy in patients with PI-RADS 5 lesion than in those with PI-RADS 3 or 4 lesion. Additionally, compared with respective controls, detection of any grade cancer (P = 0.046) or Grade Group 2 or higher cancer (P = 0.005) on T-Bx was associated with a significantly higher risk of recurrence in patients with PI-RADS 5 lesion, but not in those with PI-RADS 3 or 4 lesion. PI-RADS 5 lesions were thus found to independently predict a significantly poorer postoperative prognosis. Moreover, the failure of detection of any grade cancer or clinically significant cancer on T-Bx of PI-RADS 5 lesion may particularly indicate favorable outcomes in radical prostatectomy cases.

High-risk and Oligometastatic Prostate Cancer: Current Treatment Paradigms

Summary Over the past decade or so with the treatment of high risk and oligometastatic disease has undergone a paradigm shift. Improvements in surgical techniques especially the robot assisted surgeries and better radiation techniques have ensured a good quality of life with maintained oncological outcomes. Further to it development and better understanding the disease biology have ensured good outcomes even in high grade cancers. This comprehensive overview delves into the management of high-risk prostate cancer and oligometastatic prostate cancer, addressing their definitions, diagnostic workup, and treatment modalities. Essentially managing high-risk and oligometastatic prostate cancer requires a multidisciplinary approach, integrating surgery, radiation, and systemic therapies.

Targeted biopsy added to systematic biopsy improves cancer detection in prostate cancer screening.

Magnetic resonance imaging (MRI)/ultrasound targeted biopsy has frequently been used together with a 12-core systematic biopsy for prostate cancer screening in the past few years. However, the efficacy of targeted biopsy compared to systematic biopsy, as well as its clinical-histologic correlation, has been assessed by a limited number of studies and is further investigated in this study. We collected 960 cases with both targeted and systematic prostate biopsies from 04/2019 to 04/2022 (Table 1). We compared cancer detection rates between targeted and systematic prostate biopsies in different grade groups. Correlations with the size of prostate lesions, prostate-specific antigen (PSA) level, and Prostate Imaging-Reporting and Data System (PI-RADS) scale were also analyzed for each of these biopsy methods. Among the 960 men who underwent targeted biopsy with systematic biopsy, prostatic adenocarcinoma was diagnosed in 652 (67.9%) cases. 489 (50.9%) cases were diagnosed by targeted biopsy and 576 (60.0%) cases were diagnosed by systematic biopsy. In the 384 cases diagnosed negative by systematic biopsy, targeted biopsy identified cancer in 76 (8%) cases. Systematic biopsy was able to detect 163 cancer cases that were missed by targeted biopsy. Systematic biopsy detected more grade group 1 cancers compared to targeted biopsy. However, for higher grade cancers, the differences between the cancer detection rates of targeted biopsy and systematic biopsy became negligible. Targeted biopsy upgraded the grade group categorized by systematic biopsy in several cases (3.8%, 7.0%, 2.6%, 1.1% and 0.9% in Grade Groups 1, 2, 3, 4, and 5 respectively). Targeted biopsy was more likely to detect cancer in larger lesions (13.17 mm VS 11.41 mm, P=0.0056) and for higher PI-RADS scales (4.19 VS 3.68, P<0.0001). The cancers detected by targeted biopsy also had higher PSA levels (10.38 ng/ml VS 6.39 ng/ml, P=0.0026). Targeted biopsy with systematic biopsy improved cancer detection rate compared to systematic biopsy alone. Targeted biopsy is not more sensitive for grade groups 1, 4, or 5 cancers but is as sensitive as systematic biopsy for detecting grade group 2 and 3 cancers. Targeted biopsy is more effective at detecting cancers when patients have larger lesions, higher PI-RADS scales, and higher PSA levels.

Reduction in Nuclear Size by DHRS7 in Prostate Cancer Cells and by Estradiol Propionate in DHRS7-Depleted Cells.

Increased nuclear size correlates with lower survival rates and higher grades for prostate cancer. The short-chain dehydrogenase/reductase (SDR) family member DHRS7 was suggested as a biomarker for use in prostate cancer grading because it is largely lost in higher-grade tumors. Here, we found that reduction in DHRS7 from the LNCaP prostate cancer cell line with normally high levels of DHRS7 increases nuclear size, potentially explaining the nuclear size increase observed in higher-grade prostate tumors where it is lost. An exogenous expression of DHRS7 in the PC3 prostate cancer cell line with normally low DHRS7 levels correspondingly decreases nuclear size. We separately tested 80 compounds from the Microsource Spectrum library for their ability to restore normal smaller nuclear size to PC3 cells, finding that estradiol propionate had the same effect as the re-expression of DHRS7 in PC3 cells. However, the drug had no effect on LNCaP cells or PC3 cells re-expressing DHRS7. We speculate that separately reported beneficial effects of estrogens in androgen-independent prostate cancer may only occur with the loss of DHRS7/ increased nuclear size, and thus propose DHRS7 levels and nuclear size as potential biomarkers for the likely effectiveness of estrogen-based treatments.

A bibliometric analysis of using machine learning and artificial intelligence in prostate cancer detection

Prostate cancer stands as one of the most prevalent cancers globally among men, exhibiting substantial geographical variations in both incidence and mortality. While developed countries bear a higher incidence, developing countries grapple with elevated mortality rates. The heightened mortality in the latter is attributed to variations in practices that impede early diagnosis. In this context, the integration of artificial intelligence (AI) and machine learning (ML) has become increasingly common to improve the diagnostic accuracy of prostate cancer. This review delves into the existing literature to scrutinize the utilization of AI and ML in the diagnosis of prostate cancer. To compile relevant literature, comprehensive searches were conducted on research databases, including SCOPUS, Web of Science, and Google Scholar, to identify articles related to AI or ML (AI/ML) in the diagnosis and management of prostate cancer. Using a screening criterion, 293 reviewed research papers were identified. The two most consistent themes were predictive modeling and the application of AI/ML tools for cancer grading and radiomics. AI and ML enhance diagnostic accuracy by reducing inter-individual variation in Gleason&amp;rsquo;s scoring and complimenting the interpretation of multiparametric magnetic resonance imaging (mpMRI). A few publications reported the use of AI/ML tools that combine histopathology with MRI signals. The literature surveyed indicates a compelling potential for AI and ML to improve diagnostic accuracy in prostate cancer. Emerging literature suggests the use of a combination of demographic features, clinical data, serological markers, pathological grading and radiological factors, and genomic data to propose an accurate, non-invasive diagnosis of clinically significant prostate cancer.

Prostate cancer grade using self-supervised learning and novel feature aggregator based on weakly-labeled gbit-pixel pathology images

Prostate cancer grade using self-supervised learning and novel feature aggregator based on weakly-labeled gbit-pixel pathology images

Diagnostic value of 18F-PSMA-1007 PET/CT for predicting the pathological grade of prostate cancer

ABSTRACT This study was designed to evaluate the diagnostic efficacy of relevant parameters of 18F-prostate-specific membrane antigen (PSMA)-1007 PET/CT in predicting the pathological grade of primary prostate cancer. Briefly, a prospective analysis was performed on 53 patients diagnosed with prostate cancer by systematic puncture biopsy, followed by 18F-PSMA-1007 PET/CT examination prior to treatment within 10 d. The patients were grouped in accordance with the Gleason grading system revised by the International Association of Urology Pathology (ISUP). They were divided into high-grade group (ISUP 4–5 group) and low-grade group (ISUP 1–3 group). The differences in maximum standardized uptake value (SUVmax), tumor-to-background ratio (TBR), intraprostatic PSMA-derived tumor volume (iPSMA-TV), and intraprostatic total lesion PSMA (iTL-PSMA) between the high- and low-grade group were statistically significant (p < .001). No significant difference was found for mean standardized uptake value (SUVmean) between the high- and low-grade groups (Z = −1.131, p = .258). Besides, binary multivariate logistic regression analysis showed that only iPSMA-TV and iTL-PSMA were independent predictors of the pathological grading, for which the odds ratios were 18.821 [95% confidence interval (CI): 2.040–173.614, p = .010] and 0.758 (95% CI: 0.613–0.938, p = .011), respectively. The area under the ROC of this regression model was 0.983 (95% CI: 0.958–1.00, p < .001). Only iTL-PSMA was a significant parameter for distinguishing ISUP-4 and ISUP-5 groups (Z = −2.043, p = .041). In a nutshell, 18F-PSMA-1007 PET/CT has good application value in predicting the histopathological grade of primary prostate cancer. Three-dimensional volume metabolism parameters iPSMA-TV and iTL-PSMA were found to be independent predictors for pathological grade.

Identification of MicroRNAs Associated with Histological Grade in Early-Stage Invasive Breast Cancer.

This study aimed to identify microRNAs associated with histological grade using comprehensive microRNA analysis data obtained by next-generation sequencing from early-stage invasive breast cancer. RNA-seq data from normal breast and breast cancer samples were compared to identify candidate microRNAs with differential expression using bioinformatics. A total of 108 microRNAs were significantly differentially expressed in normal breast and breast cancer tissues. Using clinicopathological information and microRNA sequencing data of 430 patients with breast cancer from The Cancer Genome Atlas (TCGA), the differences in candidate microRNAs between low- and high-grade tumors were identified. Comparing the expression of the 108 microRNAs between low- and high-grade cases, 25 and 18 microRNAs were significantly upregulated and downregulated, respectively, in high-grade cases. Clustering analysis of the TCGA cohort using these 43 microRNAs identified two groups strongly predictive of histological grade. miR-3677 is a microRNA upregulated in high-grade breast cancer. The outcome analysis revealed that patients with high miR-3677 expression had significantly worse prognosis than those with low miR-3677 expression. This study shows that microRNAs are associated with histological grade in early-stage invasive breast cancer. These findings contribute to the elucidation of a new mechanism of breast cancer growth regulated by specific microRNAs.

Value of altered methylation patterns of genes RANBP3, LCP2 and GRAP2 in cfDNA in breast cancer diagnosis.

The purpose of this study was to investigate the potential of plasma cfDNA methylation patterns in reflecting tumour methylation changes, focusing on three candidate sites, cg02469161, cg11528914, and cg20131654. These sites were selected for verification, with a particular emphasis on their association with breast cancer. We conducted a comprehensive analysis of 850k whole-methylation sequencing data to identify potential markers for breast cancer detection. Subsequently, we investigated the methylation status of the genes Ran-binding protein 3 (RANBP3), Lymphocyte cytoplasmic protein 2 (LCP2), and GRB2 related adaptor protein 2 (GRAP2), situated at the specified sites, using cancer and canceradjacent tissues from 17 breast cancer patients. We also examined the methylation patterns in different molecular subtypes and pathological grades of breast cancer. Additionally, we compared the methylation levels of these genes in plasma cfDNA to their performance in tissues. Our analysis revealed that RANBP3, LCP2, and GRAP2 genes exhibited significant methylation differences between cancer and cancer-adjacent tissues. In breast cancer, these genes displayed diagnostic efficiencies of 91.0%, 90.6%, and 92.2%, respectively. Notably, RANBP3 showed a tendency towards lower methylation in HR+ breast cancer, and LCP2 methylation was correlated with tumour malignancy. Importantly, the methylation levels of these three genes in plasma cfDNA closely mirrored their tissue counterparts, with diagnostic efficiencies of 83.3%, 83.9%, and 77.6% for RANBP3, LCP2, and GRAP2, respectively. Our findings propose that the genes RANBP3, LCP2, and GRAP2, located at the identified methylation sites, hold significant potential as molecular markers in blood for the supplementary diagnosis of breast cancer. This study lays the groundwork for a more in-depth investigation into the changes in gene methylation patterns in circulating free DNA (cfDNA) for the early detection not only of breast cancer but also for various other types of cancer.

Prognostic Value of Tumor Volume, Tumor Volume Reduction Rate and Magnetic Resonance Tumor Regression Grade in Rectal Cancer.

Background and Objectives: Rectal cancer poses significant treatment challenges, especially in advanced stages. Radiologic assessment, particularly with MRI, is critical for surgeons and oncologists to understand tumor dynamics and tailor treatment strategies to improve patient outcomes. The purpose of this study was to correlate MRI-based tumor volumetric and tumor regression grade analysis in patients with advanced rectal cancer, assessing the impact of preoperative chemotherapy (CT) alone or chemoradiotherapy (CRT) on surgical technique choices. Materials and Methods: Between 2015 and 2022, a prospective study was enrolled, including a cohort of 89 patients diagnosed with rectal cancer at stage II or III. The participants were divided into two distinct therapy groups, ensuring an equal distribution with a ratio of 1:1. The initial group was treated with the contemporary preoperative chemotherapy protocol FOLFOX4. In contrast, the alternative group received conventional preoperative chemoradiotherapy. Before surgery, each patient underwent a rectal MRI scan at 1.5 T, including T2-weighted and diffusion-weighted imaging (DWI) sequences. Results: The CT group showed a 36.52% tumor volume reduction rate (TVRR), and the CRT group showed 54.87%, with varying magnetic resonance and pathological tumor regression grades (mrTRG and pTRG). Analysis revealed a significant interaction between mrTRG and tumor volumetrics (volume and VRR) in both groups, especially CRT, underscoring the complexity of tumor response. Both treatment groups had similar initial tumor volumes, with CRT displaying a higher TVRR, particularly in higher pathological TRG (3/4) cases. This interaction and the strong correlation between mrTRG and pTRG suggest mrTRG's role as a non-invasive predictor for treatment response, highlighting the need for personalized treatment plans. Conclusions: Rectal tumor volume, volume reduction rate, and mrTRG are not just abstract measures; they are concrete indicators that have a direct and practical impact on surgical decision-making, planning, and prognosis, ultimately influencing the quality of care and life expectancy of patients with rectal cancer.

The accuracy of core needle biopsy in determining histological type and Scarf-Bloom-Richardson grade in invasive breast cancer

Core needle biopsy provides information not only on the histological diagnosis but also about tumor grade and different prognosis factors for breast cancer. This study was designed to determine the accuracy of percutaneous core needle biopsy (CNB) through comparative analysis of histological diagnosis and SBR tumor grade of invasive breast cancer between CNB and surgical excision specimen (SES). This was a retrospective cross-sectional study from January 2023 to July 2023. All patients with invasive breast cancer diagnosed by CNB and confirmed by surgical excision specimen (SES) examination were included in the study. Patients who received neoadjuvant chemotherapy were excluded. One twenty-three patients were assessed. All patients were female. The median age was 45 years (37 – 54). Invasive ductal carcinoma (IDC) was the major histological type of breast cancer (95.1%) followed by invasive lobular carcinoma (ILC) (4.9%). SBR grade 2 tumors accounted for 78.1% of cases. The majority of patients presented with locally advanced stage breast cancer (65.9%) or a metastatic disease (31.7%). Concordance for histological type was substantial (k= 0.79; p&amp;#60;0,001) whereas it was moderate (k= 0.45; p&amp;#60;0,001) for Scarf-Bloom-Richardson grade. Histological type on CNB correlates almost perfectly with that of the surgical excisional specimen in case of breast cancer. Nevertheless, the agreement of tumor grade between CNB and SES remains moderate, with a significant underestimation and overestimation rates.

Prospective evaluation of MR-TRG (Tumor Regression Grade) in esophageal cancer after neo-adjuvant therapy: Preliminary results

PurposeTo develop MRI-based criteria to assess tumor response to neoadjuvant therapies (NAT) of esophageal cancers (EC) and to evaluate its diagnostic performance in predicting the pathological Tumor Regression Grade (pTRG). MethodFrom 2018 to 2022, patients with newly diagnosed locally advanced EC underwent MRI examinations for initial staging and restaging after NAT. Magnetic Resonance TRG (MR-TRG), equivalent to the Mandard and Becker classifications, were developed and independently assessed by two radiologists, blinded to pTRG, using T2W and DW-MR Images. All patients underwent surgery and benefited from a blinded pTRG evaluation by two pathologists. The agreement between readers and between MR-TRG and pTRG were assessed with Cohen’s Kappa. The correlation of MR-TRG and pTRG was determined using Spearman’s correlation. Results28 patients were included. Interrater agreement was substantial between radiologists, improved when grouping grade 1 and 2 (κ = 0.78 rose to 0,84 for Mandard and 0.68 to 0,78 for Becker score). Agreement between pTRG and MR-TRG was moderate with a percentaged agreement (p) = 87.5 %, kappa (κ) = 0.54 and p = 83.3 %, κ = 0.49 for Mandard and Becker, respectively. Agreement was improved to substantial when grouping grades 1–2 for Mandard and 1a-1b for Becker with p = 89.3 %, κ = 0.65 and p = 85.2 %, κ = 0.65 respectively. Sensitivity and specificity of MR-TRG in predicting pTRG were 88.2 % and 72.7 % for Mandard system (scores 1–2 versus 3–5), and 83.3 % and 80 % for Becker system (scores 1a-1b versus 2–3). ConclusionA substantial agreement between MR-TRG and pTRG was achieved when grouping grade 1–2. Hence, MR-TRG could be used as a surrogate of complete and near-complete pTRG.

Whole-lesion iodine map histogram analysis versus single-slice spectral CT parameters for determining novel International Association for the Study of Lung Cancer grade of invasive non-mucinous pulmonary adenocarcinomas

PurposeThe purpose of this study was to evaluate and compare the performances of whole-lesion iodine map histogram analysis to those of single-slice spectral computed tomography (CT) parameters in discriminating between low-to-moderate grade invasive non-mucinous pulmonary adenocarcinoma (INMA) and high-grade INMA according to the novel International Association for the Study of Lung Cancer grading system of INMA. Materials and methodsSixty-one patients with INMA (34 with low-to-moderate grade [i.e., grade I and grade II] and 27 with high grade [i.e., grade III]) were evaluated with spectral CT. There were 28 men and 33 women, with a mean age of 56.4 ± 10.5 (standard deviation) years (range: 29–78 years). The whole-lesion iodine map histogram parameters (mean, standard deviation, variance, skewness, kurtosis, entropy, and 1st, 10th, 25th, 50th, 75th, 90th, and 99th percentile) were measured for each INMA. In other sessions, by placing regions of interest at representative levels of the tumor and normalizing them, spectral CT parameters (iodine concentration and normalized iodine concentration) were obtained. Discriminating capabilities of spectral CT and histogram parameters were assessed and compared using area under the ROC curve (AUC) and logistic regression models. ResultsThe 1st, 10th, and 25th percentiles of the iodine map histogram analysis, and iodine concentration and normalized iodine concentration of single-slice spectral CT parameters were significantly different between high-grade and low-to-moderate grade INMAs (P < 0.001 to P = 0.002). The 1st percentile of histogram parameters (AUC, 0.84; 95% confidence interval [CI]: 0.73–0.92) and iodine concentration (AUC, 0.78; 95% CI: 0.66–0.88) from single-slice spectral CT parameters had the best performance for discriminating between high-grade and low-to-moderate grade INMAs. At ROC curve analysis no significant differences in AUC were found between histogram parameters (AUC = 0.86; 95% CI: 0.74–0.93) and spectral CT parameters (AUC = 0.81; 95% CI: 0.74–0.93) (P = 0.60). ConclusionBoth whole-lesion iodine map histogram analysis and single-slice spectral CT parameters help discriminate between low-to-moderate grade and high-grade INMAs according to the novel International Association for the Study of Lung Cancer grading system, with no differences in diagnostic performances.

Metalloproteinase 9 immunostaining profile is positively correlated with tumor grade, extraprostatic extension and biochemical recurrence in prostate cancer

Metastasis is the main problem in the treatment of prostate cancer (PCa), and for it to occur, proteolytic enzymes must remodel the extracellular matrix (ECM) surrounding the tumor. The most important group of enzymes with this action include the matrix metalloproteinases (MMPs), which act on various substrates cleaving ECM components. The present study aimed to evaluate the protein immunostaining profiles of matrix metalloproteinase 2 (MMP-2) and 9 (MMP-9) in PCa Brazilian patients using the indirect immunohistochemical methodology. The tissue samples (n = 178), 60 from malignant tumor, 58 from adjacent non-tumor, and 60 from ECM, were evaluated according to the immunostaining intensity. The malignant tumor cytoplasmic MMP-2 immunostaining was more intense than in ECM (p = 0.001), but it did not correlate with any clinical-pathological parameter. The MMP-9 staining was similar in tumor cytoplasm, adjacent non-tumor cytoplasm and ECM, but showed significant positive correlations with ISUP grade (p = 0.044; Tau=0.249), extraprostatic extension (p = 0.025; Tau=0.309), and biochemical recurrence (p = 0.048; Tau=0.306). A significant positive correlation was also observed between MMP-2 and MMP-9 in all cell compartments analyzed. Although further research is warranted to elucidate the precise mechanisms underlying these observations, our findings suggest MMP-9 as a promising candidate marker for tissue invasion that could be used in predicting the progression and prognosis of PCa.

Multi-cell type and multi-level graph aggregation network for cancer grading in pathology images.

In pathology, cancer grading is crucial for patient management and treatment. Recent deep learning methods, based upon convolutional neural networks (CNNs), have shown great potential for automated and accurate cancer diagnosis. However, these do not explicitly utilize tissue/cellular composition, and thus difficult to incorporate the existing knowledge of cancer pathology. In this study, we propose a multi-cell type and multi-level graph aggregation network (MMGA-Net) for cancer grading. Given a pathology image, MMGA-Net constructs multiple cell graphs at multiple levels to represent intra- and inter-cell type relationships and to incorporate global and local cell-to-cell interactions. In addition, it extracts tissue contextual information using a CNN. Then, the tissue and cellular information are fused to predict a cancer grade. The experimental results on two types of cancer datasets demonstrate the effectiveness of MMGA-Net, outperforming other competing models. The results also suggest that the information fusion of multiple cell types and multiple levels via graphs is critical for improved pathology image analysis.

Assessment of HER1 (rs11543848) and HER2 (rs1136201) polymorphism and their association with colorectal cancer susceptibility in Khyber Pakhtunkhwa, Pakistan.

Colorectal cancer (CRC) is a widespread malignancy characterized by uncontrolled growth in the colon or rectum and remains a leading cause of cancer-related mortality globally. Various genes polymorphisms have been linked with the risk of CRC, but our study aimed to investigate the association between HER1 (rs11543848) and HER2 (rs1136201) polymorphisms with the risk of CRC in the Khyber Pakhtunkhwa (KPK) population of Pakistan. The association of the selected polymorphisms (rs11543848 and rs1136201) with CRC risk has been investigated in various ethnic groups, but their impact remains unexplored in Pakistan, particularly within the KPK population, highlighting the need of the study in this region. In this study 120 CRC patients and 120 healthy controls were enrolled. The DNA was extracted from the blood by salting-out method and genotyping was done using ARMS-PCR. Our investigations provided convincing evidence of a strong association between HER1 (rs11543848) and the risk of CRC. Both the genotypes heterozygous GA (OR = 2.07, CI = 1.18 to 3.64, P = 0.01) and homozygous AA (OR = 6.22, CI = 2.56 to 15.08, P = 0.0001) showed higher risk and significant association with the CRC risk. Similarly, heterozygous genotype AG of HER2 (rs1136201) was significantly associated (OR = 3.16, 95% CI = 1.78 to 5.58, P = 0.0001) while mutant genotype GG showed higher risk but non-significant association (OR = 3.23, 95% CI = 0.84 to 12.43, P = 0.08) with CRC patients. HER1 (rs11543848) demonstrated a significant association (P = 0.003) with the age at diagnosis in CRC patients, while HER2 (rs1136201) showed a non-significant association (P = 0.434). Both the SNPs were non-significantly associated with gender (P = 0.793 and 0.117), metastasis (P = 0.582 and 0.129), location of the tumor (P = 0.555 and 0.993), tumor grade (P = 0.290 and 0.920), tumor size (P = 0.535 and 0.289) and stages of cancer (P = 0.892 and 0.352). In conclusion, both the polymorphisms rs11543848 and rs1136201 displayed susceptibility with CRC in the KPK population. However, further investigations are recommended while using whole exome sequencing on a larger sample size for more precise results.

Added-value of 3D amide proton transfer MRI in assessing prognostic factors of cervical cancer: a comparative study with multiple model diffusion-weighted imaging.

Amide proton transfer (APT) imaging has been gradually applied to cervical cancer, yet the relationships between APT and multiple model diffusion-weighted imaging (DWI) have yet to be investigated. This study attempted to evaluate the added value of 3-dimensional (3D) APT imaging to multiple model DWI for assessing prognostic factors of cervical cancer. This prospective diagnostic study was conducted in The First Affiliated Hospital of Zhengzhou University. A total of 88 consecutive patients with cervical cancer underwent APT imaging and DWI with 11 b-values (0-2,000 s/mm2). The apparent diffusion coefficient (ADC), pure molecular diffusion (D), perfusion fraction (f), pseudo-diffusion (D*), mean kurtosis (MK), and mean diffusivity (MD) were calculated based on mono-exponential, bi-exponential, and kurtosis models. The mean, minimum, and maximum values of APT signal intensity (APT SI) and DWI-derived metrics were compared based on tumor stages, subtypes, grades, and lymphovascular space invasion status by Student's t-test or Mann-Whitney U test. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance of the parameters. APT SImax, APT SImin, MKmean, and MKmax showed significant differences between adenocarcinoma (AC) and squamous cell carcinoma (SCC) (all P<0.05). APT SImean, APT SImax, and MKmax were higher and ADCmin, Dmean, Dmin, and MDmin were lower in the high-grade tumor than in low-grade tumor (all P<0.05). For distinguishing lymphovascular space invasion, only MKmean showed significant difference (P=0.010). APT SImax [odds ratio (OR) =2.347, P=0.029], APT SImin (OR =0.352; P=0.024), and MKmean (OR =6.523; P=0.001) were the independent predictors for tumor subtype, and APT SImax (OR =2.885; P=0.044), MDmin (OR =0.155, P=0.012) were the independent predictors for histological grade of cervical cancer. When APT SImin and APT SImax was combined with MKmean and MKmax, the diagnostic performance was significantly improved for differentiating AC and AC [area under the curve (AUC): 0.908, sensitivity: 87.5%; specificity: 83.3%; P<0.001]. The combination of APT SImean, APT SImax, ADCmin, MKmax, and MDmin demonstrated the highest diagnostic performance for predicting tumor grade (AUC: 0.903, sensitivity: 78.6%; specificity: 88.9%; P<0.001). Addition of APT to DWI may improve the ability to noninvasively predict poor prognostic factors of cervical cancer.