Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology

Diagnosis of Hirschsprung disease by analyzing acetylcholinesterase staining using artificial intelligence

OBJECTIVES

Classical Hirschsprung disease (HD) is defined by the absence of ganglion cells in the rectosigmoid colon. The diagnosis is made from rectal biopsy, which reveals the aganglionosis and the presence of cholinergic hyperinnervation. However, depending on the method of rectal biopsy, the quality of the specimens and the related diagnostic accuracy varies substantially. To facilitate and objectify the diagnosis of HD, we investigated whether software-based identification of cholinergic hyperinnervation in digitalized histopathology slides is suitable for distinguishing healthy individuals from affected individuals.

METHODS

N = 190 samples of 112 patients who underwent open surgical rectal biopsy at our pediatric surgery center between 2009 and 2019 were included in this study. Acetylcholinesterase (AChE) stained slides of these samples were collected and digitalized via slide scanning and analyzed using two digital imaging software programs (HALO, QuPath). The AChE-positive staining area in the mucosal layers of the intestinal wall was determined. In the next step machine learning was employed to identify patterns of cholinergic hyperinnervation.

RESULTS

The area of AChE-positive staining was greater in HD patients compared to healthy individuals (p < 0.0001). Artificial intelligence-based assessment of parasympathetic hyperinnervation identified Hirschsprung disease with a high precision (area under the curve [AUC] 0.96). The accuracy of the prediction model increased when nonrectal samples were excluded (AUC 0.993).

CONCLUSIONS

Software-assisted machine-learning analysis of AChE staining is suitable to improve the diagnostic accuracy of Hirschsprung disease.

Molecular and clinical epidemiology of carbapenem resistant Acinetobacter baumannii, Pseudomonas aeruginosa and Enterobacterales in Fiji: a multicentre prospective observational study

Background

Carbapenem resistant organisms (CROs) such as Acinetobacter baumannii (CRAb), Pseudomonas aeruginosa (CRPa), Escherichia coli (CREc), and Klebsiella pneumoniae (CRKp) have been identified by the World Health Organization (WHO) as global priority pathogens. The dissemination of these pathogens and clonal outbreaks within healthcare facilities are of serious concern, particularly in regions with limited resources. In Fiji, where healthcare services are primarily provided by public hospitals, understanding the extent and nature of this problem is essential for the development of effective patient management, prevention interventions and control strategies.

Methods

CROs isolated from 211 (77.3%) non-sterile (urinary catheters, urine, sputum, wound swab, and endotracheal tube) and 62 (22.7%) normally sterile (blood, cerebrospinal fluid, intravascular catheter, and aspirates) body sites of 272 patients treated at the three major hospitals in Fiji, the Colonial War Memorial Hospital (CWMH), Lautoka Hospital (LTKH), and Labasa Hospital (LBSH), and outer peripheral health centres around Fiji, were analysed. Clinical and demographic patient data such as age, sex, admission diagnosis, admission and discharge dates, patient outcomes, date of death, start and end date of meropenem and colistin treatment were reviewed. These CRO isolates comprised A. baumannii, P. aeruginosa, E. coli, and K. pneumoniae, that were prospectively collected at the microbiology laboratory of CWMH and LBSH from January 2020 through August 2021 and at the LTKH from January 2020 to December 2021. In addition, 10 retrospectively stored CRPa isolates collected from patients at the CWMH from January through December 2019, were also included in the study. All isolates were characterised using mass spectrometry, antimicrobial susceptibility testing, and whole genome sequencing. Phylogenetic relationships among the CROs were assessed through core genome single nucleotide polymorphism (SNP) analysis. The CRAb isolates were also compared to the CRAb isolates from CWMH isolated in 2016/2017 and 2019, along with CRAb isolates obtained from Fijian patients admitted to New Zealand hospitals in 2020 and 2021 from our retrospective study.

Findings

Of 272 patients, 140 (51.5%) were male, the median (range) age of patients was 45 (<1-89) years, 161 (59.2%) were I-Taukei, 104 (38.2%) Fijians of Indian descent, and 7 (2.6%) were from other ethnic backgrounds. 234 (86.0%) of these 272 patients, had their first positive CRO sample collected ≥72 h following admission and the remaining 38 (14.0%) were isolated within 72 h following admission. Of the 273 CROs, 146 (53.5%) were collected at the CWMH, 66 (24.2%) LTKH, and 61 (22.3%) LBSH, while 62 (22.7%) were isolated from normally sterile sites and 211 (77.3%) from sites that are not sterile. Of 273 isolates, 131 (48.0%) were CRAb, 90 (33.0%) CRPa, 46 (16.8%) CREc, and 6 (2.2%) CRKp. Of 131 CRAb, 108 (82.4%) were ST2, with three distinct clones, all encoding bla OXA-23 and bla OXA - 66, while clone 3 also encoded bla NDM-1; bla OXA-23 was associated with two copies of ISAba1 insertion element, forming the composite transposon Tn2006. The first two CRAb ST2 clones were genetically linked to those isolated at CMWH 2016 through 2019, while the third was genetically linked to isolates from Fijian patients admitted to New Zealand hospitals in 2020 and 2021. Of CRPa, 65 (72.2%) were ST773 and carried β-lactamase genes bla NDM-1, bla OXA-50, and bla OXA-395. Of 10 retrospective CRPa isolates, all belonged to CRPa ST773 and carried bla NDM-1, bla OXA-50, and bla OXA-395. Of 46 CREc, 44 (95.7%) were ST410 and encoded bla NDM-7 on an IncX3 plasmid. Of 6 CRKp, 4 (66.7%) were ST16 and carried bla NDM-5 on an IncX3 plasmid. Other sequence types of CRPa (ST9, ST357, ST654, ST664), CRAb (ST25, ST374, ST499), CREc (ST167), and CRKp (ST45, ST336) were also detected. Of those receiving meropenem treatment in the prospective study, 30 (57.7%) received it inappropriately. Of 272 patients, 65 (23.9%) died within the 30 days after first positive CRO isolation.

Interpretation

We identified nosocomial transmission of distinct clones of CRAb ST2, CRPa ST773, CREc ST410, and CRKp ST16 within and between the three major hospitals in Fiji. Moreover, community onset infections associated with CRPa, CREc, and CRAb were also detected. Of note, cross-border transmission of CRAb ST2 clone 3 strain between Fiji and New Zealand was also detected. These clones encoded an array of carbapenem resistance genes associated with mobile genetic elements, including plasmids, transposons, and integrative and conjugative elements, signifying their potential for increased mobility, further acquisition of resistance genes, and spread. Inappropriate use of meropenem was common. Of note, the majority of patients who died had acquired CRO during their hospital stay. These findings highlight the need for stringent IPC strategies focusing on catheter and ventilator management, meticulous wound care, rigorous sepsis control, consistent hand hygiene, effective use of disinfectants, and thorough sanitisation of both hospital environments and medical equipment in the three major hospitals in Fiji. Additionally, diligent surveillance of AMR and robust antimicrobial stewardship are crucial for effectively managing nosocomial infections.

Funding

This project was funded by the Otago Medical School Foundations Trust (Dean's Bequest Fund) and a Fiji National University seed grant. The funders of the study had no role in the study design, data collection, data analysis, data interpretation, or writing of the report.

Unified mRNA Subcellular Localization Predictor based on machine learning techniques

BACKGROUND

The mRNA subcellular localization bears substantial impact in the regulation of gene expression, cellular migration, and adaptation. However, the methods employed for experimental determination of this localization are arduous, time-intensive, and come with a high cost.

METHODS

In this research article, we tackle the essential challenge of predicting the subcellular location of messenger RNAs (mRNAs) through Unified mRNA Subcellular Localization Predictor (UMSLP), a machine learning (ML) based approach. We embrace an in silico strategy that incorporate four distinct feature sets: kmer, pseudo k-tuple nucleotide composition, nucleotide physicochemical attributes, and the 3D sequence depiction achieved via Z-curve transformation for predicting subcellular localization in benchmark dataset across five distinct subcellular locales, encompassing nucleus, cytoplasm, extracellular region (ExR), mitochondria, and endoplasmic reticulum (ER).

RESULTS

The proposed ML model UMSLP attains cutting-edge outcomes in predicting mRNA subcellular localization. On independent testing dataset, UMSLP ahcieved over 87% precision, 94% specificity, and 94% accuracy. Compared to other existing tools, UMSLP outperformed mRNALocator, mRNALoc, and SubLocEP by 11%, 21%, and 32%, respectively on average prediction accuracy for all five locales. SHapley Additive exPlanations analysis highlights the dominance of k-mer features in predicting cytoplasm, nucleus, ER, and ExR localizations, while Z-curve based features play pivotal roles in mitochondria subcellular localization detection.

AVAILABILITY

We have shared datasets, code, Docker API for users in GitHub at: https://github.com/smusleh/UMSLP .

Binary semantic segmentation for detection of prostate adenocarcinoma using an ensemble with attention and residual U-Net architectures

An accurate determination of the Gleason Score (GS) or Gleason Pattern (GP) is crucial in the diagnosis of prostate cancer (PCa) because it is one of the criterion used to guide treatment decisions for prognostic-risk groups. However, the manually designation of GP by a pathologist using a microscope is prone to error and subject to significant inter-observer variability. Deep learning has been used to automatically differentiate GP on digitized slides, aiding pathologists and reducing inter-observer variability, especially in the early GP of cancer. This article presents a binary semantic segmentation for the GP of prostate adenocarcinoma. The segmentation separates benign and malignant tissues, with the malignant class consisting of adenocarcinoma GP3 and GP4 tissues annotated from 50 unique digitized whole slide images (WSIs) of prostate needle core biopsy specimens stained with hematoxylin and eosin. The pyramidal digitized WSIs were extracted into image patches with a size of 256 × 256 pixels at a magnification of 20×. An ensemble approach is proposed combining U-Net-based architectures, including traditional U-Net, attention-based U-Net, and residual attention-based U-Net. This work initially considers a PCa tissue analysis using a combination of attention gate units with residual convolution units. The performance evaluation revealed a mean Intersection-over-Union of 0.79 for the two classes, 0.88 for the benign class, and 0.70 for the malignant class. The proposed method was then used to produce pixel-level segmentation maps of PCa adenocarcinoma tissue slides in the testing set. We developed a screening tool to discriminate between benign and malignant prostate tissue in digitized images of needle biopsy samples using an AI approach. We aimed to identify malignant adenocarcinoma tissues from our own collected, annotated, and organized dataset. Our approach returned the performance which was accepted by the pathologists.

A large-scale dataset of patient summaries for retrieval-based clinical decision support systems

Retrieval-based Clinical Decision Support (ReCDS) can aid clinical workflow by providing relevant literature and similar patients for a given patient. However, the development of ReCDS systems has been severely obstructed by the lack of diverse patient collections and publicly available large-scale patient-level annotation datasets. In this paper, we collect a novel dataset of patient summaries and relations called PMC-Patients to benchmark two ReCDS tasks: Patient-to-Article Retrieval (ReCDS-PAR) and Patient-to-Patient Retrieval (ReCDS-PPR). Specifically, we extract patient summaries from PubMed Central articles using simple heuristics and utilize the PubMed citation graph to define patient-article relevance and patient-patient similarity. PMC-Patients contains 167k patient summaries with 3.1 M patient-article relevance annotations and 293k patient-patient similarity annotations, which is the largest-scale resource for ReCDS and also one of the largest patient collections. Human evaluation and analysis show that PMC-Patients is a diverse dataset with high-quality annotations. We also implement and evaluate several ReCDS systems on the PMC-Patients benchmarks to show its challenges and conduct several case studies to show the clinical utility of PMC-Patients.

Deep learning approach for accurate prostate cancer identification and stratification using combined immunostaining of cytokeratin, p63, and racemase

BACKGROUND

Prostate cancer (PCa) is the most frequently diagnosed cancer in men worldwide, affecting around 1.4 million individuals. Current PCa diagnosis relies on histological analysis of prostate biopsy samples, an activity that is both time-consuming and prone to observer bias. Previous studies have demonstrated that immunostaining of cytokeratin, p63, and racemase can significantly improve the sensitivity and the specificity of PCa detection compared to traditional H&E staining.

METHODS

This study introduces a novel approach that combines diagnosis-specific immunohistochemical (IHC) staining and deep learning techniques to provide reliable stratification of prostate glands. Our approach leverages a customized segmentation network, called K-PPM, that incorporates adaptive kernels and multiscale feature integration to enhance the functional information of IHC. To address the high class-imbalance problem in the dataset, we propose a weighted adaptive patch-extraction and specific-class kernel update.

RESULTS

Our system achieved noteworthy results, with a mean Dice Score Coefficient of 90.36% and a mean absolute error of 1.64 % in specific-class gland quantification on whole slides. These findings demonstrate the potential of our system as a valuable support tool for pathologists, reducing workload and decreasing diagnostic inter-observer variability.

CONCLUSIONS

Our study presents innovative approaches that have broad applicability to other digital pathology areas beyond PCa diagnosis. As a fully automated system, this model can serve as a framework for improving the histological and IHC diagnosis of other types of cancer.