2-Step-Scores with optional nephropathology for the prediction of adverse outcomes for brain-dead donor kidneys in Eurotransplant.

BACKGROUND AND HYPOTHESIS: The decision for acceptance or discard of the increasingly rare and marginal brain-dead donor kidneys in Eurotransplant (ET) countries has to be made without solid evidence. Thus, we developed and validated flexible clinicopathological scores called 2-Step Scores for the prognosis of delayed graft function (DGF) and one-year death-censored transplant loss (1y-tl) reflecting the current practice of six ET countries including Croatia and Belgium. METHODS: The training set was n=620 for DGF and n=711 for 1y-tl, with validation sets n=158 and n=162. In step 1, stepwise logistic regression models including only clinical predictors were used to estimate the risks. In step 2, risk estimates were updated for statistically relevant intermediate risk percentiles with nephropathology. RESULTS: Step 1 revealed an increased risk of DGF with increased cold ischaemia time, donor and recipient BMI, dialysis vintage, number of HLA-DR mismatches or recipient CMV IgG positivity. On the training and validation set, c-statistics were 0.672 and 0.704, respectively. At a range between 18% and 36%, accuracy of DGF-prognostication improved with nephropathology including number of glomeruli and Banff cv (updated overall c statistics of 0.696 and 0.701, respectively).Risk of 1y-tl increased in recipients with cold ischaemia time, sum of HLA-A. -B, -DR mismatches and donor age. On training and validation sets, c-statistics were 0.700 and 0.769, respectively. Accuracy of 1y-tl prediction improved (c-statistics = 0.706 and 0.765) with Banff ct. Overall, calibration was good on the training, but moderate on the validation set; discrimination was at least as good as established scores when applied to the validation set. CONCLUSION: Our flexible 2-Step Scores with optional inclusion of time-consuming and often unavailable nephropathology should yield good results for clinical practice in ET, and may be superior to established scores. Our scores are adaptable to donation after cardiac death and perfusion pump use.

Digital Pathology Applications for PD-L1 Scoring in Head and Neck Squamous Cell Carcinoma: A Challenging Series.

The assessment of programmed death-ligand 1 (PD-L1) combined positive scoring (CPS) in head and neck squamous cell carcinoma (HNSCC) is challenged by pre-analytical and inter-observer variabilities. An educational program to compare the diagnostic performances between local pathologists and a board of pathologists on 11 challenging cases from different Italian pathology centers stained with PD-L1 immunohistochemistry on a digital pathology platform is reported. A laboratory-developed test (LDT) using both 22C3 (Dako) and SP263 (Ventana) clones on Dako or Ventana platforms was compared with the companion diagnostic (CDx) Dako 22C3 pharm Dx assay. A computational approach was performed to assess possible correlations between stain features and pathologists' visual assessments. Technical discordances were noted in five cases (LDT vs. CDx, 45%), due to an abnormal nuclear/cytoplasmic diaminobenzidine (DAB) stain in LDT (n = 2, 18%) and due to variation in terms of intensity, dirty background, and DAB droplets (n = 3, 27%). Interpretative discordances were noted in six cases (LDT vs. CDx, 54%). CPS remained unchanged, increased, or decreased from LDT to CDx in three (27%) cases, two (18%) cases, and one (9%) case, respectively, around relevant cutoffs (1 and 20, k = 0.63). Differences noted in DAB intensity/distribution using computational pathology partly explained the LDT vs. CDx differences in two cases (18%). Digital pathology may help in PD-L1 scoring, serving as a second opinion consultation platform in challenging cases. Computational and artificial intelligence tools will improve clinical decision-making and patient outcomes.

TROP-2, NECTIN-4 and predictive biomarkers in sarcomatoid and rhabdoid bladder urothelial carcinoma.

Introduction: The surface protein TROP-2/TACSTD2 and the cell adhesion protein NECTIN-4/NECTIN4 are responsible for the efficacy of anticancer therapies based on antibody-drug conjugates (ADC) targeting intracellular microtubules. In contrast with common histologic subtypes of bladder urothelial carcinoma (BUC), little is known of TROP-2 and NECTIN-4 expression in sarcomatoid and rhabdoid BUC. Aims: In this study, we aimed to analyze TROP-2 and NECTIN-4 expression and additional predictive biomarkers by immunohistochemistry and fluorescence in situ hybridization (FISH) on 35 undifferentiated BUC (28 sarcomatoid and 7 rhabdoid). Wide genomic investigation was also performed on 411 BUC cases of the PanCancer Atlas, focusing on genes related to the microtubule pathways. Results: Seven of 35 (20%) undifferentiated BUC showed expression of TROP-2. NECTIN-4 was expressed in 10 cases (29%). Seven cases (20%) co-expressed TROP-2 and NECTIN-4. HER-2 FISH was amplified in 5 cases (14%) while HER-2 immunoexpression was observed in 14 cases (40%). PD-L1 scored positive for combined proportion score (CPS) in 66% of cases and for tumor proportion score (TPS) in 51% of cases. Pan-NTRK1-2/3 was elevated in 9 cases (26%) and FGFR-2/3 was broken in 7 of 35 cases (20%). Of 28 sarcomatoid BUC, 9 (32%) were negative for all (TROP-2, NECTIN-4, PD-L1, HER-2, FGFR and pan-NTRK) biomarkers and 3 (11%) expressed all five biomarkers. Among cases with rhabdoid dedifferentiation, 1 of 7 (14%) showed activation of all biomarkers, whereas 2 of 7 (28%) showed none. The mRNA analysis identified microtubule-related genes and pathways suitable for combined ADC treatments in BUC. Conclusion: Sarcomatoid and rhabdoid BUC do harbor positive expression of the ADC targets TROP-2 or NECTIN-4 in a relatively modest subset of cases, whereas the majority do not. Different combinations of other positive biomarkers may help the choice of medical therapies. Overall, these findings have important clinical implications for targeted therapy for BUC.

Benchmarking digital displays (monitors) for histological diagnoses: the nephropathology use case.

AIM: The digital transformation of the pathology laboratory is being continuously sustained by the introduction of innovative technologies promoting whole slide image (WSI)-based primary diagnosis. Here, we proposed a real-life benchmark of a pathology-dedicated medical monitor for the primary diagnosis of renal biopsies, evaluating the concordance between the 'traditional' microscope and commercial monitors using WSI from different scanners. METHODS: The College of American Pathologists WSI validation guidelines were used on 60 consecutive renal biopsies from three scanners (Aperio, 3DHISTECH and Hamamatsu) using pathology-dedicated medical grade (MG), professional grade (PG) and consumer-off-the-shelf (COTS) monitors, comparing results with the microscope diagnosis after a 2-week washout period. RESULTS: MG monitor was faster (1090 vs 1159 vs 1181 min, delta of 6-8%, p<0.01), with slightly better performances on the detection of concurrent diseases compared with COTS (κ=1 vs 0.96, 95% CI=0.87 to 1), but equal concordance to the commercial monitors on main diagnosis (κ=1). Minor discrepancies were noted on specific scores/classifications, with MG and PG monitors closer to the reference report (r=0.98, 95% CI=0.83 to 1 vs 0.98, 95% CI=0.83 to 1 vs 0.91, 95% CI=0.76 to 1, κ=0.93, 95% CI=077 to 1 vs 0.93, 95% CI=0.77 to 1 vs 0.86, 95% CI=0.64 to 1, κ=1 vs 0.50, 95% CI=0 to 1 vs 0.50, 95% CI=0 to 1, for IgA, antineutrophilic cytoplasmic antibody and lupus nephritis, respectively). Streamlined Pipeline for Amyloid detection through congo red fluorescence Digital Analysis detected amyloidosis on both monitors (4 of 30, 13% cases), allowing detection of minimal interstitial deposits with slight overestimation of the Amyloid Score (average 6 vs 7). CONCLUSIONS: The digital transformation needs careful assessment of the hardware component to support a smart and safe diagnostic process. Choosing the display for WSI is critical in the process and requires adequate planning.

Comparing deep learning and pathologist quantification of cell-level PD-L1 expression in non-small cell lung cancer whole-slide images.

Programmed death-ligand 1 (PD-L1) expression is currently used in the clinic to assess eligibility for immune-checkpoint inhibitors via the tumor proportion score (TPS), but its efficacy is limited by high interobserver variability. Multiple papers have presented systems for the automatic quantification of TPS, but none report on the task of determining cell-level PD-L1 expression and often reserve their evaluation to a single PD-L1 monoclonal antibody or clinical center. In this paper, we report on a deep learning algorithm for detecting PD-L1 negative and positive tumor cells at a cellular level and evaluate it on a cell-level reference standard established by six readers on a multi-centric, multi PD-L1 assay dataset. This reference standard also provides for the first time a benchmark for computer vision algorithms. In addition, in line with other papers, we also evaluate our algorithm at slide-level by measuring the agreement between the algorithm and six pathologists on TPS quantification. We find a moderately low interobserver agreement at cell-level level (mean reader-reader F1 score = 0.68) which our algorithm sits slightly under (mean reader-AI F1 score = 0.55), especially for cases from the clinical center not included in the training set. Despite this, we find good AI-pathologist agreement on quantifying TPS compared to the interobserver agreement (mean reader-reader Cohen's kappa = 0.54, 95% CI 0.26-0.81, mean reader-AI kappa = 0.49, 95% CI 0.27-0.72). In conclusion, our deep learning algorithm demonstrates promise in detecting PD-L1 expression at a cellular level and exhibits favorable agreement with pathologists in quantifying the tumor proportion score (TPS). We publicly release our models for use via the Grand-Challenge platform.

Donors risk assessment in transplantation: From the guidelines to their real-world application.

Transplantation of an organ from a donor carries an unavoidable risk of tumor transmission. The need to extend the donor pool increases the use of organs from donors with malignancies and potential disease transmission is a constant tension influencing donor suitability decisions. Current classification systems for the assessment of donor malignancy transmission risk have evolved from reports of potential transmission events in recipients to national donation and transplant surveillance agencies. Although the risk of malignancy transmission is very low in the general transplant setting it must constantly be balanced with the transplant benefits. Guidelines are mainly based on large registries and sparse case reports of transmission, so they cannot cover all the possible situations. For this reason, in 2004 in Italy, the National Transplant Center gave rise to the Second Opinion Service, charged by the Ministry of Health, by structuring expertise in diagnostic oncology and risk transmission and making it available to the Italian Transplant Centers. In this paper the registry of the Italian Oncological Second Opinion was reviewed, from 2016 to 2018, to detail the most frequent and problematic neoplastic topics addressed, those are separately reported and discussed. Furthermore, a review of the most recent strategies and risk stratification is provided, according to the most recent literature evidence and to the European Guidelines.

Artificial intelligence-based algorithms for the diagnosis of prostate cancer: A systematic review.

OBJECTIVES: The high incidence of prostate cancer causes prostatic samples to significantly affect pathology laboratories workflow and turnaround times (TATs). Whole-slide imaging (WSI) and artificial intelligence (AI) have both gained approval for primary diagnosis in prostate pathology, providing physicians with novel tools for their daily routine. METHODS: A systematic review according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines was carried out in electronic databases to gather the available evidence on the application of AI-based algorithms to prostate cancer. RESULTS: Of 6290 articles, 80 were included, mostly (59%) dealing with biopsy specimens. Glass slides were digitized to WSI in most studies (89%), roughly two-thirds of which (66%) exploited convolutional neural networks for computational analysis. The algorithms achieved good to excellent results about cancer detection and grading, along with significantly reduced TATs. Furthermore, several studies showed a relevant correlation between AI-identified histologic features and prognostic predictive variables such as biochemical recurrence, extraprostatic extension, perineural invasion, and disease-free survival. CONCLUSIONS: The published evidence suggests that AI can be reliably used for prostate cancer detection and grading, assisting pathologists in the time-consuming screening of slides. Further technologic improvement would help widening AI's adoption in prostate pathology, as well as expanding its prognostic predictive potential.

The Puzzle of Preimplantation Kidney Biopsy Decision-Making Process: The Pathologist Perspective.

Kidney transplantation is the best treatment for end-stage renal disease since it offers the greatest survival benefit compared to dialysis. The gap between the number of renal transplants performed and the number of patients awaiting renal transplants leads to a steadily increasing pressure on the scientific community. Kidney preimplantation biopsy is used as a component of the evaluation of organ quality before acceptance for transplantation. However, the reliability and predictive value of biopsy data are controversial. Most of the previously proposed predictive models were not associated with graft survival, but what has to be reaffirmed is that histologic examination of kidney tissue can provide an objective window on the state of the organ that cannot be deduced from clinical records and renal functional studies. The balance of evidence indicates that reliable decisions about donor suitability must be made based on the overall picture. This work discusses recent trends that can reduce diagnostic timing and variability among players in the decision-making process that lead to kidney transplants, from the pathologist's perspective.

Perspective of a Pathologist on Benchmark Strategies for Artificial Intelligence Development in Organ Transplantation.

Transplant pathology of donors is a highly specialized field comprising both the evaluation of organ donor biopsy for the oncological risk transmission and to guide the organ allocation. Timing is critical in transplant procurement since organs must be recovered as soon as possible to ensure the best possible outcome for the recipient. To all this is added the fact that the evaluation of a donor causes difficulties in many cases and the impact of these assessments is paramount, considering the possible recovery of organs that would have been erroneously discarded or, conversely, the possibly correct discarding of donors with unacceptable risk profiles. In transplant pathology histology is still the gold standard for diagnosis dictating the subsequent decisions and course of clinical care. Digital pathology has played an important role in accelerating healthcare progression and nowadays artificial intelligence powered computational pathology can effectively improve diagnostic needs, supporting the quality and safety of the process. Mapping the shape of the journey would suggest a progressive approach from supervised to semi/unsupervised models, which would involve training these models directly for clinical endpoints. In machine learning, this generally delivers better performance, compensating for a potential lack in interpretability. With planning and enough confidence in the performance of learning-based methods from digital pathology and artificial intelligence, there is great potential to augment the diagnostic quality and correlation with clinical endpoints. This may improve the donor pool and vastly reduce diagnostic and prognostic errors that are known but currently are unavoidable in transplant donor pathology.

Pre-Implantation Kidney Biopsies in Extended Criteria Donors: From On Call to Expert Pathologist, from Conventional Microscope to Digital Pathology.

The number of patients awaiting a kidney transplant is constantly rising but lack of organs leads kidneys from extended criteria donors (ECD) to be used to increase the donor pool. Pre-transplant biopsies are routinely evaluated through the Karpinski-Remuzzi score but consensus on its correlation with graft survival is controversial. This study aims to test a new diagnostic model relying on digital pathology to evaluate pre-transplant biopsies and to correlate it with graft outcomes. Pre-transplant biopsies from 78 ECD utilized as single kidney transplantation were scanned, converted to whole-slide images (WSIs), and reassessed by two expert nephropathologists using the Remuzzi-Karpinski score. The correlation between graft survival at 36 months median follow-up and parameters assigned by either WSI or glass slide score (GSL) by on-call pathologists was evaluated, as well as the agreement between the GSL and the WSIs score. No relation was found between the GSL assessed by on-call pathologists and graft survival (P = 0.413). Conversely, the WSI score assigned by the two nephropathologists strongly correlated with graft loss probability, as confirmed by the ROC curves analysis (DeLong test P = 0.046). Digital pathology allows to share expertise in the transplant urgent setting, ensuring higher accuracy and favoring standardization of the process. Its employment may significantly increase the predictive capability of the pre-transplant biopsy evaluation for ECD, improving the quality of allocation and patient safety.

From Hype To Reality: A Narrative Review on the Promising Role of Artificial Intelligence in Larynx Cancer Detection and Transoral Microsurgery.

Early larynx cancer detection plays a crucial role in improving treatment outcomes and recent studies have shown promising results in using artificial intelligence for larynx cancer detection. Artificial intelligence also has the potential to enhance transoral larynx microsurgery. This narrative review summarizes the current evidence regarding its use in larynx cancer detection and potential applications in transoral larynx microsurgery. The utilization of artificial intelligence in larynx cancer detection with white light endoscopy and narrow-band imaging helps improve diagnostic accuracy and efficiency. It can also potentially enhance transoral larynx microsurgery by aiding surgeons in real-time decision-making and minimizing the risk of complications. However, further prospective studies are warranted to validate the findings, and additional research is necessary to optimize the integration of artificial intelligence in our clinical practice.

Harnessing the Power of Artificial Intelligence: Revolutionizing Free Flaps Monitoring in Head and Neck Tumor Treatment.

Treating head and neck tumors has undergone significant advancements, focusing on improving the patient's quality of life after treatment. Reconstructive surgical techniques with free flaps have been vital in restoring anatomy, function, and aesthetics, reducing morbidity from locoregional treatments. Monitoring free flaps is crucial to detect and address any vascular compromise that may lead to flap failure. Various monitoring techniques have been employed in free flap monitoring. However, standardizing them presents a challenge due to the need for more consensus among surgeons and variability in techniques, costs, and training requirements. Artificial intelligence (AI) shows promise in standardizing monitoring practices and reducing the operator-dependent variability. AI techniques have been explored to improve monitoring and early detection of complications in free flap surgeries, and they have shown high accuracy in analyzing images and predicting flap outcomes. Despite the potential benefits, implementing AI in free flap monitoring remains challenging. Standardization of input data, interpretation, cost, training, and accounting for patient and flap variability are crucial considerations. Further research, including multicenter studies, validation, and collaboration amongst clinicians, researchers, and AI experts is needed to overcome these challenges.

Cutting-edge technology and automation in the pathology laboratory.

One of the goals of pathology is to standardize laboratory practices to increase the precision and effectiveness of diagnostic testing, which will ultimately enhance patient care and results. Standardization is crucial in the domains of tissue processing, analysis, and reporting. To enhance diagnostic testing, innovative technologies are also being created and put into use. Furthermore, although problems like algorithm training and data privacy issues still need to be resolved, digital pathology and artificial intelligence are emerging in a structured manner. Overall, for the field of pathology to advance and for patient care to be improved, standard laboratory practices and innovative technologies must be adopted. In this paper, we describe the state-of-the-art of automation in pathology laboratories in order to lead technological progress and evolution. By anticipating laboratory needs and demands, the aim is to inspire innovation tools and processes as positively transformative support for operators, organizations, and patients.

ABO-Incompatible Orthotopic Liver Transplant as a Rescue Strategy for Fulminant Hepatic Failure in a Recipient With Breast Cancer: Highlights on Transplant Management.

Pretransplant malignancy unrelated to hepatocellular carcinoma is a challenging condition in liver transplantation. Standard of care requires the completion of treatments and a disease-free period before the transplant. However, in the setting of a fulminant hepatic failure, these steps cannot be achieved. A 46-year-old woman with a recent diagnosis of stage 2 breast cancer presented to our center with a fulminant hepatic failure of unknown origin. Because of the rapid worsening of her clinical status, she was listed as eligible for transplant after a multidisciplinary evaluation. Because of a shortage of available donors, a deceased donor ABO-incompatible liver transplant with a synchronous mastectomy and first-level axillary lymphadenectomy was performed. To prevent antibody-mediated rejection, a triple immunosuppression therapy and a postoperative therapeutic plasmapheresis were performed. The patient remains without cancer recurrence at 18 months of follow-up. Recent studies have shown that cancer recurrence in recipients with pretransplant malignancy is considerably lower than suggested in previously published studies. However,this data is not sufficient to establish evidence-based guidelines on the indications and timing of transplant. In selected cases, the presence of a pretransplant malignancy does notrepresent a contraindication for a rescue liver transplant. Further studies are needed to stratify the risk and to help clinicians to choose the best strategy in an urgent context such as this.

Digital pathology world tour.

Objective: Digital pathology (DP) is currently in the spotlight and is rapidly gaining ground, even though the history of this field spans decades. Despite great technological progress, the adoption of DP for routine clinical diagnostic use remains limited. Methods: A systematic search was conducted in the electronic databases Pubmed-MEDLINE and Embase. Inclusion criteria were all published studies that encompassed any application of DP. Results: Of 4888 articles retrieved, 4041 were included. Relevant articles were categorized as "diagnostic" (147/4041, 4%) where DP was utilized for routine diagnostic workflow and "non-diagnostic" (3894/4041, 96%) for all other applications. The "non-diagnostic" articles were further categorized according to DP application including "artificial intelligence" (33%), "education" (5%), "narrative" (17%) for reviews and editorials, and "technical" (45%) for pure research publications. Conclusion: This manuscript provided temporal and geographical insight into the global adoption of DP by analyzing the published scientific literature.

Performance and limitations of a supervised deep learning approach for the histopathological Oxford Classification of glomeruli with IgA nephropathy.

BACKGROUND AND OBJECTIVE: The Oxford Classification for IgA nephropathy is the most successful example of an evidence-based nephropathology classification system. The aim of our study was to replicate the glomerular components of Oxford scoring with an end-to-end deep learning pipeline that involves automatic glomerular segmentation followed by classification for mesangial hypercellularity (M), endocapillary hypercellularity (E), segmental sclerosis (S) and active crescents (C). METHODS: A total number of 1056 periodic acid-Schiff (PAS) whole slide images (WSIs), coming from 386 kidney biopsies, were annotated. Several detection models for glomeruli, based on the Mask R-CNN architecture, were trained on 587 WSIs, validated on 161 WSIs, and tested on 127 WSIs. For the development of segmentation models, 20,529 glomeruli were annotated, of which 16,571 as training and 3958 as validation set. The test set of the segmentation module comprised of 2948 glomeruli. For the Oxford classification, 6206 expert-annotated glomeruli from 308 PAS WSIs were labelled for M, E, S, C and split into a training set of 4298 glomeruli from 207 WSIs, and a test set of 1908 glomeruli. We chose the best-performing models to construct an end-to-end pipeline, which we named MESCnn (MESC classification by neural network), for the glomerular Oxford classification of WSIs. RESULTS: Instance segmentation yielded excellent results with an AP50 ranging between 78.2-80.1 % (79.4 ± 0.7 %) on the validation and 75.1-77.7 % (76.5 ± 0.9 %) on the test set. The aggregated Jaccard Index was between 73.4-75.9 % (75.0 ± 0.8 %) on the validation and 69.1-73.4 % (72.2 ± 1.4 %) on the test set. At granular glomerular level, Oxford Classification was best replicated for M with EfficientNetV2-L with a mean ROC-AUC of 90.2 % and a mean precision/recall area under the curve (PR-AUC) of 81.8 %, best for E with MobileNetV2 (ROC-AUC 94.7 %) and ResNet50 (PR-AUC 75.8 %), best for S with EfficientNetV2-M (mean ROC-AUC 92.7 %, mean PR-AUC 87.7 %), best for C with EfficientNetV2-L (ROC-AUC 92.3 %) and EfficientNetV2-S (PR-AUC 54.7 %). At biopsy-level, correlation between expert and deep learning labels fulfilled the demands of the Oxford Classification. CONCLUSION: We designed an end-to-end pipeline for glomerular Oxford Classification on both a granular glomerular and an entire biopsy level. Both the glomerular segmentation and the classification modules are freely available for further development to the renal medicine community.

Time for a full digital approach in nephropathology: a systematic review of current artificial intelligence applications and future directions.

INTRODUCTION: Artificial intelligence (AI) integration in nephropathology has been growing rapidly in recent years, facing several challenges including the wide range of histological techniques used, the low occurrence of certain diseases, and the need for data sharing. This narrative review retraces the history of AI in nephropathology and provides insights into potential future developments. METHODS: Electronic searches in PubMed-MEDLINE and Embase were made to extract pertinent articles from the literature. Works about automated image analysis or the application of an AI algorithm on non-neoplastic kidney histological samples were included and analyzed to extract information such as publication year, AI task, and learning type. Prepublication servers and reviews were not included. RESULTS: Seventy-six (76) original research articles were selected. Most of the studies were conducted in the United States in the last 7 years. To date, research has been mainly conducted on relatively easy tasks, like single-stain glomerular segmentation. However, there is a trend towards developing more complex tasks such as glomerular multi-stain classification. CONCLUSION: Deep learning has been used to identify patterns in complex histopathology data and looks promising for the comprehensive assessment of renal biopsy, through the use of multiple stains and virtual staining techniques. Hybrid and collaborative learning approaches have also been explored to utilize large amounts of unlabeled data. A diverse team of experts, including nephropathologists, computer scientists, and clinicians, is crucial for the development of AI systems for nephropathology. Collaborative efforts among multidisciplinary experts result in clinically relevant and effective AI tools.