ABSTRACT
PURPOSE: Prostate-specific membrane antigen (PSMA) is increasingly used to image prostate cancer in clinical practice. We sought to develop and test a humanised PSMA minibody IAB2M conjugated to the fluorophore IRDye 800CW-NHS ester in men undergoing robot-assisted laparoscopic radical prostatectomy (RARP) to image prostate cancer cells during surgery. METHODS: The minibody was evaluated pre-clinically using PSMA positive/negative xenograft models, following which 23 men undergoing RARP between 2018 and 2020 received between 2.5 mg and 20 mg of IR800-IAB2M intravenously, at intervals between 24 h and 17 days prior to surgery. At every step of the procedure, the prostate, pelvic lymph node chains and extra-prostatic surrounding tissue were imaged with a dual Near-infrared (NIR) and white light optical platform for fluorescence in vivo and ex vivo. Histopathological evaluation of intraoperative and postoperative microscopic fluorescence imaging was undertaken for verification. RESULTS: Twenty-three patients were evaluated to optimise both the dose of the reagent and the interval between injection and surgery and secure the best possible specificity of fluorescence images. Six cases are presented in detail as exemplars. Overall sensitivity and specificity in detecting non-lymph-node extra-prostatic cancer tissue were 100% and 65%, and 64% and 64% respectively for lymph node positivity. There were no side-effects associated with administration of the reagent. CONCLUSION: Intraoperative imaging of prostate cancer tissue is feasible and safe using IR800-IAB2M. Further evaluation is underway to assess the benefit of using the technique in improving completion of surgical excision during RARP. REGISTRATION: ISCRCTN10046036: https://www.isrctn.com/ISRCTN10046036 .
Subject(s)
Antigens, Surface , Glutamate Carboxypeptidase II , Optical Imaging , Prostatectomy , Prostatic Neoplasms , Male , Humans , Prostatectomy/methods , Prostatic Neoplasms/surgery , Prostatic Neoplasms/diagnostic imaging , Glutamate Carboxypeptidase II/metabolism , Antigens, Surface/metabolism , Optical Imaging/methods , Intraoperative Period , Middle Aged , Animals , Aged , Surgery, Computer-Assisted/methods , MiceABSTRACT
Digital pathology continues to gain momentum, with the promise of artificial intelligence to aid diagnosis and for assessment of features which may impact prognosis and clinical management. Successful adoption of these technologies depends upon the quality of digitised whole-slide images (WSI); however, current quality control largely depends upon manual assessment, which is inefficient and subjective. We previously developed PathProfiler, an automated image quality assessment tool, and in this feasibility study we investigate its potential for incorporation into a diagnostic clinical pathology setting in real-time. A total of 1254 genitourinary WSI were analysed by PathProfiler. PathProfiler was developed and trained on prostate tissue and, of the prostate biopsy WSI, representing 46% of the WSI analysed, 4.5% were flagged as potentially being of suboptimal quality for diagnosis. All had concordant subjective issues, mainly focus-related, 54% severe enough to warrant remedial action which resulted in improved image quality. PathProfiler was less reliable in assessment of non-prostate surgical resection-type cases, on which it had not been trained. PathProfiler shows potential for incorporation into a digitised clinical pathology workflow, with opportunity for image quality improvement. Whilst its reliability in the current form appears greatest for assessment of prostate specimens, other specimen types, particularly biopsies, also showed benefit.
ABSTRACT
Human tissue, which is inherently three-dimensional (3D), is traditionally examined through standard-of-care histopathology as limited two-dimensional (2D) cross-sections that can insufficiently represent the tissue due to sampling bias. To holistically characterize histomorphology, 3D imaging modalities have been developed, but clinical translation is hampered by complex manual evaluation and lack of computational platforms to distill clinical insights from large, high-resolution datasets. We present TriPath, a deep-learning platform for processing tissue volumes and efficiently predicting clinical outcomes based on 3D morphological features. Recurrence risk-stratification models were trained on prostate cancer specimens imaged with open-top light-sheet microscopy or microcomputed tomography. By comprehensively capturing 3D morphologies, 3D volume-based prognostication achieves superior performance to traditional 2D slice-based approaches, including clinical/histopathological baselines from six certified genitourinary pathologists. Incorporating greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, further emphasizing the value of capturing larger extents of heterogeneous morphology.
Subject(s)
Imaging, Three-Dimensional , Prostatic Neoplasms , Supervised Machine Learning , Humans , Male , Deep Learning , Imaging, Three-Dimensional/methods , Prognosis , Prostatic Neoplasms/pathology , Prostatic Neoplasms/diagnostic imaging , X-Ray Microtomography/methodsABSTRACT
Cancer remains one of the leading causes of mortality worldwide, leading to increased interest in utilizing immunotherapy strategies for better cancer treatments. In the past decade, CD103+ T cells have been associated with better clinical prognosis in patients with cancer. However, the specific immune mechanisms contributing toward CD103-mediated protective immunity remain unclear. Here, we show an unexpected and transient CD61 expression, which is paired with CD103 at the synaptic microclusters of T cells. CD61 colocalization with the T cell antigen receptor further modulates downstream T cell antigen receptor signaling, improving antitumor cytotoxicity and promoting physiological control of tumor growth. Clinically, the presence of CD61+ tumor-infiltrating T lymphocytes is associated with improved clinical outcomes, mediated through enhanced effector functions and phenotype with limited evidence of cellular exhaustion. In conclusion, this study identified an unconventional and transient CD61 expression and pairing with CD103 on human immune cells, which potentiates a new target for immune-based cellular therapies.
Subject(s)
Antigens, CD , Apyrase , Integrin alpha Chains , Receptors, Antigen, T-Cell , Signal Transduction , Animals , Humans , Mice , Antigens, CD/metabolism , Antigens, CD/immunology , Cell Line, Tumor , Cytotoxicity, Immunologic , Integrin alpha Chains/metabolism , Lymphocytes, Tumor-Infiltrating/immunology , Lymphocytes, Tumor-Infiltrating/metabolism , Neoplasms/immunology , Neoplasms/therapy , Receptors, Antigen, T-Cell/metabolism , Receptors, Antigen, T-Cell/immunology , Signal Transduction/immunology , T-Lymphocytes, Cytotoxic/immunologyABSTRACT
BACKGROUND: It is important to identify molecular features that improve prostate cancer (PCa) risk stratification before radical treatment with curative intent. Molecular analysis of historical diagnostic formalin-fixed paraffin-embedded (FFPE) prostate biopsies from cohorts with post-radiotherapy (RT) long-term clinical follow-up has been limited. Utilizing parallel sequencing modalities, we performed a proof-of-principle sequencing analysis of historical diagnostic FFPE prostate biopsies. We compared patients with (i) stable PCa (sPCa) postprimary or salvage RT, (ii) progressing PCa (pPCa) post-RT, and (iii) de novo metastatic PCa (mPCa). METHODS: A cohort of 19 patients with diagnostic prostate biopsies (n = 6 sPCa, n = 5 pPCa, n = 8 mPCa) and mean 4 years 10 months follow-up (diagnosed 2009-2016) underwent nucleic acid extraction from demarcated malignancy. Samples underwent 3'RNA sequencing (3'RNAseq) (n = 19), nanoString analysis (n = 12), and Illumina 850k methylation (n = 8) sequencing. Bioinformatic analysis was performed to coherently identify differentially expressed genes and methylated genomic regions (MGRs). RESULTS: Eighteen of 19 samples provided useable 3'RNAseq data. Principal component analysis (PCA) demonstrated similar expression profiles between pPCa and mPCa cases, versus sPCa. Coherently differentially methylated probes between these groups identified ~600 differentially MGRs. The top 50 genes with increased expression in pPCa patients were associated with reduced progression-free survival post-RT (p < 0.0001) in an external cohort. CONCLUSIONS: 3'RNAseq, nanoString and 850k-methylation analyses are each achievable from historical FFPE diagnostic pretreatment prostate biopsies, unlocking the potential to utilize large cohorts of historic clinical samples. Profiling similarities between individuals with pPCa and mPCa suggests biological similarities and historical radiological staging limitations, which warrant further investigation.
Subject(s)
Disease Progression , Prostatic Neoplasms , Humans , Male , Prostatic Neoplasms/genetics , Prostatic Neoplasms/pathology , Prostatic Neoplasms/radiotherapy , Aged , Middle Aged , Biopsy , Genomics , Prostate/pathology , Neoplasm Metastasis , Cohort StudiesABSTRACT
BACKGROUND: Extension of prostate cancer beyond the primary site by local invasion or nodal metastasis is associated with poor prognosis. Despite significant research on tumour evolution in prostate cancer metastasis, the emergence and evolution of cancer clones at this early stage of expansion and spread are poorly understood. We aimed to delineate the routes of evolution and cancer spread within the prostate and to seminal vesicles and lymph nodes, linking these to histological features that are used in diagnostic risk stratification. METHODS: We performed whole-genome sequencing on 42 prostate cancer samples from the prostate, seminal vesicles and lymph nodes of five treatment-naive patients with locally advanced disease. We spatially mapped the clonal composition of cancer across the prostate and the routes of spread of cancer cells within the prostate and to seminal vesicles and lymph nodes in each individual by analysing a total of > 19,000 copy number corrected single nucleotide variants. RESULTS: In each patient, we identified sample locations corresponding to the earliest part of the malignancy. In patient 10, we mapped the spread of cancer from the apex of the prostate to the seminal vesicles and identified specific genomic changes associated with the transformation of adenocarcinoma to amphicrine morphology during this spread. Furthermore, we show that the lymph node metastases in this patient arose from specific cancer clones found at the base of the prostate and the seminal vesicles. In patient 15, we observed increased mutational burden, altered mutational signatures and histological changes associated with whole genome duplication. In all patients in whom histological heterogeneity was observed (4/5), we found that the distinct morphologies were located on separate branches of their respective evolutionary trees. CONCLUSIONS: Our results link histological transformation with specific genomic alterations and phylogenetic branching. These findings have implications for diagnosis and risk stratification, in addition to providing a rationale for further studies to characterise the genetic changes causally linked to morphological transformation. Our study demonstrates the value of integrating multi-region sequencing with histopathological data to understand tumour evolution and identify mechanisms of prostate cancer spread.
Subject(s)
Prostatic Neoplasms , Male , Humans , Phylogeny , Prostatic Neoplasms/genetics , Prostatic Neoplasms/pathology , Prostate/pathology , Lymphatic Metastasis/pathology , Seminal Vesicles/pathologyABSTRACT
In recent years, technological advances in tissue preparation, high-throughput volumetric microscopy, and computational infrastructure have enabled rapid developments in nondestructive 3D pathology, in which high-resolution histologic datasets are obtained from thick tissue specimens, such as whole biopsies, without the need for physical sectioning onto glass slides. While 3D pathology generates massive datasets that are attractive for automated computational analysis, there is also a desire to use 3D pathology to improve the visual assessment of tissue histology. In this perspective, we discuss and provide examples of potential advantages of 3D pathology for the visual assessment of clinical specimens and the challenges of dealing with large 3D datasets (of individual or multiple specimens) that pathologists have not been trained to interpret. We discuss the need for artificial intelligence triaging algorithms and explainable analysis methods to assist pathologists or other domain experts in the interpretation of these novel, often complex, large datasets.
Subject(s)
Artificial Intelligence , Microscopy , Humans , Microscopy/methods , BiopsyABSTRACT
Genetic signatures have added a molecular dimension to prognostics and therapeutic decision-making. However, tumour heterogeneity in prostate cancer and current sampling methods could confound accurate assessment. Based on previously published spatial transcriptomic data from multifocal prostate cancer, we created virtual biopsy models that mimic conventional biopsy placement and core size. We then analysed the gene expression of different prognostic signatures (OncotypeDx®, Decipher®, Prostadiag®) using a step-wise approach with increasing resolution from pseudo-bulk analysis of the whole biopsy, to differentiation by tissue subtype (benign, stroma, tumour), followed by distinct tumour grade and finally clonal resolution. The gene expression profile of virtual tumour biopsies revealed clear differences between grade groups and tumour clones, compared to a benign control, which were not reflected in bulk analyses. This suggests that bulk analyses of whole biopsies or tumour-only areas, as used in clinical practice, may provide an inaccurate assessment of gene profiles. The type of tissue, the grade of the tumour and the clonal composition all influence the gene expression in a biopsy. Clinical decision making based on biopsy genomics should be made with caution while we await more precise targeting and cost-effective spatial analyses.
Subject(s)
Prostate , Prostatic Neoplasms , Male , Humans , Prostate/pathology , Transcriptome , Biopsy , Prostatic Neoplasms/genetics , Prostatic Neoplasms/pathology , GenomicsABSTRACT
Prostate cancer is typically of acinar adenocarcinoma type but can occasionally present as neuroendocrine and/or ductal type carcinoma. These are associated with clinically aggressive disease, and the former often arises on a background of androgen deprivation therapy, although it can also arise de novo. Two prostate cancer cases were sequenced by exome capture from archival tissue. Case 1 was de novo small cell neuroendocrine carcinoma and ductal adenocarcinoma with three longitudinal samples over 5 years. Case 2 was a single time point after the development of treatment-related neuroendocrine prostate carcinoma. Case 1 showed whole genome doubling in all samples and focal amplification of AR in all samples except the first time point. Phylogenetic analysis revealed a common ancestry for ductal and small cell carcinoma. Case 2 showed 13q loss (involving RB1) in both adenocarcinoma and small cell carcinoma regions, and 3p gain, 4p loss, and 17p loss (involving TP53) in the latter. By using highly curated samples, we demonstrate for the first time that small-cell neuroendocrine and ductal prostatic carcinoma can have a common ancestry. We highlight whole genome doubling in a patient with prostate cancer relapse, reinforcing its poor prognostic nature.
Subject(s)
Carcinoma, Acinar Cell , Carcinoma, Ductal , Carcinoma, Small Cell , Lung Neoplasms , Prostatic Neoplasms , Small Cell Lung Carcinoma , Male , Humans , Prostatic Neoplasms/genetics , Androgen Antagonists , Phylogeny , Carcinoma, Ductal/genetics , Evolution, MolecularABSTRACT
AIM: we describe our experience of validating departmental pathologists for digital pathology reporting, based on the UK Royal College of Pathologists (RCPath) "Best Practice Recommendations for Implementing Digital Pathology (DP)," at a large academic teaching hospital that scans 100% of its surgical workload. We focus on Stage 2 of validation (prospective experience) prior to full validation sign-off. METHODS AND RESULTS: twenty histopathologists completed Stage 1 of the validation process and subsequently completed Stage 2 validation, prospectively reporting a total of 3777 cases covering eight specialities. All cases were initially viewed on digital whole slide images (WSI) with relevant parameters checked on glass slides, and discordances were reconciled before the case was signed out. Pathologists kept an electronic log of the cases, the preferred reporting modality used, and their experiences. At the end of each validation, a summary was compiled and reviewed with a mentor. This was submitted to the DP Steering Group who assessed the scope of cases and experience before sign-off for full validation. A total of 1.3% (49/3777) of the cases had a discordance between WSI and glass slides. A total of 61% (30/49) of the discordances were categorised as a minor error in a supplementary parameter without clinical impact. The most common reasons for diagnostic discordances across specialities included identification and grading of dysplasia, assessment of tumour invasion, identification of small prognostic or diagnostic objects, interpretation of immunohistochemistry/special stains, and mitotic count assessment. Pathologists showed similar mean diagnostic confidences (on Likert scale from 0 to 7) with a mean of 6.8 on digital and 6.9 on glass slide reporting. CONCLUSION: we describe one of the first real-world experiences of a department-wide effort to implement, validate, and roll out digital pathology reporting by applying the RCPath Recommendations for Implementing DP. We have shown a very low rate of discordance between WSI and glass slides.
ABSTRACT
Although T lymphocytes have been considered the major players in the tumour microenvironment to induce tumour regression and contribute to anti-tumour immunity, much less is known about the role of tumour-infiltrating B lymphocytes (TIL-Bs) in solid malignancies, particularly in breast cancer, which has been regarded as heterogeneous and much less immunogenic compared to other common tumours like melanoma, colorectal cancer and non-small cell lung cancer. Such paucity of research could translate to limited opportunities for this most common type of cancer in the UK to join the immunotherapy efforts in this era of precision medicine. Here, we provide a systematic literature review assessing the clinical significance of TIL-Bs in breast cancer. Articles published between January 2000 and April 2022 were retrieved via an electronic search of two databases (PubMed and Embase) and screened against pre-specified eligibility criteria. The majority of studies reported favourable prognostic and predictive roles of TIL-Bs, indicating that they could have a profound impact on the clinical outcome of breast cancer. Further studies are, however, needed to better define the functional role of B cell subpopulations and to discover ways to harness this intrinsic mechanism in the fight against breast cancer.
ABSTRACT
OBJECTIVES: Primary objectives: to determine whether local anaesthetic transperineal prostate (LATP) biopsy improves the detection of clinically significant prostate cancer (csPCa), defined as International Society of Urological Pathology (ISUP) Grade Group ≥2 disease (i.e., any Gleason pattern 4 disease), compared to transrectal ultrasound-guided (TRUS) prostate biopsy, in biopsy-naïve men undergoing biopsy based on suspicion of csPCa. SECONDARY OBJECTIVES: to compare (i) infection rates, (ii) health-related quality of life, (iii) patient-reported procedure tolerability, (iv) patient-reported biopsy-related complications (including bleeding, bruising, pain, loss of erectile function), (v) number of subsequent prostate biopsy procedures required, (vi) cost-effectiveness, (vii) other histological parameters, and (viii) burden and rate of detection of clinically insignificant PCa (ISUP Grade Group 1 disease) in men undergoing these two types of prostate biopsy. PATIENTS AND METHODS: The TRANSLATE trial is a UK-wide, multicentre, randomised clinical trial that meets the criteria for level-one evidence in diagnostic test evaluation. TRANSLATE is investigating whether LATP biopsy leads to a higher rate of detection of csPCa compared to TRUS prostate biopsy. Both biopsies are being performed with an average of 12 systematic cores in six sectors (depending on prostate size), plus three to five target cores per multiparametric/bi-parametric magnetic resonance imaging lesion. LATP biopsy is performed using an ultrasound probe-mounted needle-guidance device (either the 'Precision-Point' or BK UA1232 system). TRUS biopsy is performed according to each hospital's standard practice. The study is 90% powered to detect a 10% difference (LATP biopsy hypothesised at 55% detection rate for csPCa vs 45% for TRUS biopsy). A total of 1042 biopsy-naïve men referred with suspected PCa need to be recruited. CONCLUSIONS: This trial will provide robust prospective data to determine the diagnostic ability of LATP biopsy vs TRUS biopsy in the primary diagnostic setting.
Subject(s)
Prostate , Prostatic Neoplasms , Male , Humans , Prostate/pathology , Prospective Studies , Quality of Life , Prostatic Neoplasms/diagnosis , Prostatic Neoplasms/pathology , Biopsy/adverse effects , Image-Guided Biopsy/adverse effects , Image-Guided Biopsy/methods , Magnetic Resonance Imaging/methods , Randomized Controlled Trials as Topic , Multicenter Studies as TopicABSTRACT
AIMS: With increasing utility of digital pathology (DP), it is important to consider the experiences of histopathologists in training, particularly in view of the varied access to DP across a training region and the consequent need to remain competent in reporting on glass slides (GS), which is also relevant for the Fellowship of the Royal College of Pathologists part 2 examination. Understanding the impact of DP on training is limited but could aid development of guidance to support the transition. We sought to investigate the perceptions of histopathologists in training around the introduction of DP for clinical diagnosis within a training region, and the potential training benefits and challenges. METHODS: An anonymous online survey was circulated to 24 histopathologists in training within a UK training region, including a hospital which has been fully digitised since summer 2020. RESULTS: 19 of 24 histopathologists in training responded (79%). The results indicate that DP offers many benefits to training, including ease of access to cases to enhance individual learning and teaching in general. Utilisation of DP for diagnosis appears variable; almost half of the (10 of 19) respondents with DP experience using it only for ancillary purposes such as measurements, reporting varying levels of confidence in using DP clinically. For those yet to undergo the transition, there was a perceived anxiety regarding digital reporting despite experience with DP in other contexts. CONCLUSIONS: The survey evidences the need for provision of training and support for histopathologists in training during the transition to DP, and for consideration of their need to maintain competence and confidence with GS reporting.
Subject(s)
Pathologists , Pathology, Clinical , Humans , Pathology, Clinical/methods , Image Interpretation, Computer-Assisted/methods , Surveys and Questionnaires , United KingdomABSTRACT
Multiplexed immunofluorescence provides an un-precedented opportunity for studying specific cell-to-cell and cell microenvironment interactions. We employ graph neural networks to combine features obtained from tissue morphology with measurements of protein expression to profile the tumour microenvironment associated with different tumour stages. Our framework presents a new approach to analysing and processing these complex multi-dimensional datasets that overcomes some of the key challenges in analysing these data and opens up the opportunity to abstract biologically meaningful interactions.
Subject(s)
Cell Communication , Neural Networks, Computer , Staining and Labeling , Tumor MicroenvironmentABSTRACT
Digital pathology (DP) offers potential for time efficiency gains over an analog workflow however, to date, evidence supporting this claim is relatively lacking. Studies available concentrate on specific workflow points such as diagnostic reporting time, rather than overall efficiencies in slide logistics that might be expected. This is in part a result of the complexity and variation in analog working, and the challenge therefore in capturing this. We have utilized RFID technology to conduct a novel study capturing the movement of diagnostic cases within the analog pathway in a large teaching hospital setting, thus providing benchmark data for potential efficiency gains with DP. This technology overcomes the need to manually record data items and has facilitated the capture of both the physical journey of a case and the time associated with relevant components of the analog pathway predicted to be redundant in the digital setting. RFID tracking of 1,173 surgical pathology cases and over 30 staff in an analog cellular pathology workflow illustrates the complexity of the physical movement of slides within the department, which impacts on case traceability within the system. Detailed analysis of over 400 case journeys highlights redundant periods created by batching of slides at workflow points, including potentially 2-3 h for a case to become available for reporting after release from the lab, and variable lag-times prior to collection for reporting, and provides an illustration of patterns of lab and pathologist working within the analog setting. This study supports the challenge in evidencing efficiency gains to be anticipated with DP in the context of the variation and complexity of the analog pathway, but also evidences the efficiency gains that may be expected through a greater understanding of patterns of working and movement of cases. Such data may benefit other departments building a business case for DP.
ABSTRACT
PURPOSE OF REVIEW: Germ-cell tumours of the testis affect predominantly younger males aged between 15 and 40âyears, with nearly 74,500 new cases estimated globally in 2020. Their rarity and the complex morphology, mean that, in nonexpert hands, there is a significant risk of misdiagnosis of both type and staging of these neoplasms. RECENT FINDINGS: There have been significant changes in the 2016 WHO classification of Testicular tumours that need to be understood by both pathologists and clinicians for streamlining management. Standardised structured reporting guidelines and discussion at the multidisciplinary-team meetings lead to subsequently better health outcomes and patient safety. SUMMARY: Therefore, communication with high-quality reports and understanding of clinicians of what constitutes an adequate report, is the key to ensure proper management of these patients. We attempt to discuss the key updates and pathological features that influence management and need to be communicated with clarity and precision.
Subject(s)
Neoplasms, Germ Cell and Embryonal , Testicular Neoplasms , Adolescent , Adult , Humans , Male , Neoplasms, Germ Cell and Embryonal/diagnosis , Neoplasms, Germ Cell and Embryonal/therapy , Testicular Neoplasms/diagnosis , Testicular Neoplasms/pathology , Testicular Neoplasms/therapy , Young AdultABSTRACT
There has been particular interest in the deployment of digital pathology (DP) and artificial intelligence (AI) in the diagnosis of prostate cancer, but little is known about the views of the public on their use. Prostate Cancer UK supporters were invited to an online survey which included quantitative and qualitative questions exploring views on the use of DP and AI in histopathological assessment. A total of 1276 responses to the survey were analysed (response rate 12.5%). Most respondents were supportive of DP (87%, 1113/1276) and of testing AI in clinical practice as a diagnostic adjunct (83%, 1058/1276). Respondents saw DP as potentially increasing workflow efficiency, facilitating research, education/training and fostering clinical discussions between clinician and patient. Some respondents raised concerns regarding data security, reliability and the need for human oversight. Among those who were unsure about AI, information was requested regarding its performance and others wanted to defer the decision to use it to an expert. Although most are in favour of its use, some are unsure, and their concerns could be addressed with more information or better communication. A small minority (<1%) are not in favour of the testing of the use of AI in histopathology for reasons which are not easily addressed.
ABSTRACT
Due to COVID-19 outbreaks, most school pupils have had to be home-schooled for long periods of time. Two editions of a web-based competition "Beat the Pathologists" for school age participants in the UK ran to fill up pupils' spare time after home-schooling and evaluate their ability on contributing to AI annotation. The two editions asked the participants to annotate different types of cells on Ki67 stained breast cancer images. The Main competition was at four levels with different level of complexity. We obtained annotations of four kinds of cells entered by school pupils and ground truth from expert pathologists. In this paper, we analyse school pupils' performance on differentiating different kinds of cells and compare their performance with two neural networks (AlexNet and VGG16). It was observed that children tend to get very good performance in tumour cell annotation with the best F1 measure 0.81 which is a metrics taking both false positives and false negatives into account. Low accuracy was achieved with F1 score 0.75 on positive non-tumour cells and 0.59 on negative non-tumour cells. Superior performance on non-tumour cell detection was achieved by neural networks. VGG16 with training from scratch achieved an F1 score over 0.70 in all cell categories and 0.92 in tumour cell detection. We conclude that non-experts like school pupils have the potential to contribute to large-scale labelling for AI algorithm development if sufficient training activities are organised. We hope that competitions like this can promote public interest in pathology and encourage participation by more non-experts for annotation.
Subject(s)
COVID-19 , Neoplasms , COVID-19/epidemiology , Child , Data Collection , Humans , Schools , StudentsABSTRACT
Research using whole slide images (WSIs) of histopathology slides has increased exponentially over recent years. Glass slides from retrospective cohorts, some with patient follow-up data are digitised for the development and validation of artificial intelligence (AI) tools. Such resources, therefore, become very important, with the need to ensure that their quality is of the standard necessary for downstream AI development. However, manual quality control of large cohorts of WSIs by visual assessment is unfeasible, and whilst quality control AI algorithms exist, these focus on bespoke aspects of image quality, e.g. focus, or use traditional machine-learning methods, which are unable to classify the range of potential image artefacts that should be considered. In this study, we have trained and validated a multi-task deep neural network to automate the process of quality control of a large retrospective cohort of prostate cases from which glass slides have been scanned several years after production, to determine both the usability of the images at the diagnostic level (considered in this study to be the minimal standard for research) and the common image artefacts present. Using a two-layer approach, quality overlays of WSIs were generated from a quality assessment (QA) undertaken at patch-level at [Formula: see text] magnification. From these quality overlays the slide-level quality scores were predicted and then compared to those generated by three specialist urological pathologists, with a Pearson correlation of 0.89 for overall 'usability' (at a diagnostic level), and 0.87 and 0.82 for focus and H&E staining quality scores respectively. To demonstrate its wider potential utility, we subsequently applied our QA pipeline to the TCGA prostate cancer cohort and to a colorectal cancer cohort, for comparison. Our model, designated as PathProfiler, indicates comparable predicted usability of images from the cohorts assessed (86-90% of WSIs predicted to be usable), and perhaps more significantly is able to predict WSIs that could benefit from an intervention such as re-scanning or re-staining for quality improvement. We have shown in this study that AI can be used to automate the process of quality control of large retrospective WSI cohorts to maximise their utility for research.