A comparative analysis of RNA-Seq and NanoString technologies in deciphering viral infection response in upper airway lung organoids.

In this study, we delved into the comparative analysis of gene expression data across RNA-Seq and NanoString platforms. While RNA-Seq covered 19,671 genes and NanoString targeted 773 genes associated with immune responses to viruses, our primary focus was on the 754 genes found in both platforms. Our experiment involved 16 different infection conditions, with samples derived from 3D airway organ-tissue equivalents subjected to three virus types, influenza A virus (IAV), human metapneumovirus (MPV), and parainfluenza virus 3 (PIV3). Post-infection measurements, after UV (inactive virus) and Non-UV (active virus) treatments, were recorded at 24-h and 72-h intervals. Including untreated and Mock-infected OTEs as control groups enabled differentiating changes induced by the virus from those arising due to procedural elements. Through a series of methodological approaches (including Spearman correlation, Distance correlation, Bland-Altman analysis, Generalized Linear Models Huber regression, the Magnitude-Altitude Score (MAS) algorithm and Gene Ontology analysis) the study meticulously contrasted RNA-Seq and NanoString datasets. The Magnitude-Altitude Score algorithm, which integrates both the amplitude of gene expression changes (magnitude) and their statistical relevance (altitude), offers a comprehensive tool for prioritizing genes based on their differential expression profiles in specific viral infection conditions. We observed a strong congruence between the platforms, especially in identifying key antiviral defense genes. Both platforms consistently highlighted genes including ISG15, MX1, RSAD2, and members of the OAS family (OAS1, OAS2, OAS3). The IFIT proteins (IFIT1, IFIT2, IFIT3) were emphasized for their crucial role in counteracting viral replication by both platforms. Additionally, CXCL10 and CXCL11 were pinpointed, shedding light on the organ tissue equivalent's innate immune response to viral infections. While both platforms provided invaluable insights into the genetic landscape of organoids under viral infection, the NanoString platform often presented a more detailed picture in situations where RNA-Seq signals were more subtle. The combined data from both platforms emphasize their joint value in advancing our understanding of viral impacts on lung organoids.

B cells in perivascular and peribronchiolar granuloma-associated lymphoid tissue and B-cell signatures identify asymptomatic Mycobacterium tuberculosis lung infection in Diversity Outbred mice.

Because most humans resist Mycobacterium tuberculosis infection, there is a paucity of lung samples to study. To address this gap, we infected Diversity Outbred mice with M. tuberculosis and studied the lungs of mice in different disease states. After a low-dose aerosol infection, progressors succumbed to acute, inflammatory lung disease within 60 days, while controllers maintained asymptomatic infection for at least 60 days, and then developed chronic pulmonary tuberculosis (TB) lasting months to more than 1 year. Here, we identified features of asymptomatic M. tuberculosis infection by applying computational and statistical approaches to multimodal data sets. Cytokines and anti-M. tuberculosis cell wall antibodies discriminated progressors vs controllers with chronic pulmonary TB but could not classify mice with asymptomatic infection. However, a novel deep-learning neural network trained on lung granuloma images was able to accurately classify asymptomatically infected lungs vs acute pulmonary TB in progressors vs chronic pulmonary TB in controllers, and discrimination was based on perivascular and peribronchiolar lymphocytes. Because the discriminatory lesion was rich in lymphocytes and CD4 T cell-mediated immunity is required for resistance, we expected CD4 T-cell genes would be elevated in asymptomatic infection. However, the significantly different, highly expressed genes were from B-cell pathways (e.g., Bank1, Cd19, Cd79, Fcmr, Ms4a1, Pax5, and H2-Ob), and CD20+ B cells were enriched in the perivascular and peribronchiolar regions of mice with asymptomatic M. tuberculosis infection. Together, these results indicate that genetically controlled B-cell responses are important for establishing asymptomatic M. tuberculosis lung infection.

Predicting response to neoadjuvant chemotherapy for colorectal liver metastasis using deep learning on prechemotherapy cross-sectional imaging.

BACKGROUND AND OBJECTIVES: Deep learning models (DLMs) are applied across domains of health sciences to generate meaningful predictions. DLMs make use of neural networks to generate predictions from discrete data inputs. This study employs DLM on prechemotherapy cross-sectional imaging to predict patients' response to neoadjuvant chemotherapy. METHODS: Adult patients with colorectal liver metastasis who underwent surgery after neoadjuvant chemotherapy were included. A DLM was trained on computed tomography images using attention-based multiple-instance learning. A logistic regression model incorporating clinical parameters of the Fong clinical risk score was used for comparison. Both model performances were benchmarked against the Response Evaluation Criteria in Solid Tumors criteria. A receiver operating curve was created and resulting area under the curve (AUC) was determined. RESULTS: Ninety-five patients were included, with 33,619 images available for study inclusion. Ninety-five percent of patients underwent 5-fluorouracil-based chemotherapy with oxaliplatin and/or irinotecan. Sixty percent of the patients were categorized as chemotherapy responders (30% reduction in tumor diameter). The DLM had an AUC of 0.77. The AUC for the clinical model was 0.41. CONCLUSIONS: Image-based DLM for prediction of response to neoadjuvant chemotherapy in patients with colorectal cancer liver metastases was superior to a clinical-based model. These results demonstrate potential to identify nonresponders to chemotherapy and guide select patients toward earlier curative resection.

Association of CT-Derived Skeletal Muscle and Adipose Tissue Metrics with Frailty in Older Adults.

RATIONALE AND OBJECTIVES: Tools are needed for frailty screening of older adults. Opportunistic analysis of body composition could play a role. We aim to determine whether computed tomography (CT)-derived measurements of muscle and adipose tissue are associated with frailty. MATERIALS AND METHODS: Outpatients aged ≥ 55 years consecutively imaged with contrast-enhanced abdominopelvic CT over a 3-month interval were included. Frailty was determined from the electronic health record using a previously validated electronic frailty index (eFI). CT images at the level of the L3 vertebra were automatically segmented to derive muscle metrics (skeletal muscle area [SMA], skeletal muscle density [SMD], intermuscular adipose tissue [IMAT]) and adipose tissue metrics (visceral adipose tissue [VAT], subcutaneous adipose tissue [SAT]). Distributions of demographic and CT-derived variables were compared between sexes. Sex-specific associations of muscle and adipose tissue metrics with eFI were characterized by linear regressions adjusted for age, race, ethnicity, duration between imaging and eFI measurements, and imaging parameters. RESULTS: The cohort comprised 886 patients (449 women, 437 men, mean age 67.9 years), of whom 382 (43%) met the criteria for pre-frailty (ie, 0.10 < eFI ≤ 0.21) and 138 (16%) for frailty (eFI > 0.21). In men, 1 standard deviation changes in SMD (ß = -0.01, 95% confidence interval [CI], -0.02 to -0.001, P = .02) and VAT area (ß = 0.008, 95% CI, 0.0005-0.02, P = .04), but not SMA, IMAT, or SAT, were associated with higher frailty. In women, none of the CT-derived muscle or adipose tissue metrics were associated with frailty. CONCLUSION: We observed a positive association between frailty and CT-derived biomarkers of myosteatosis and visceral adiposity in a sex-dependent manner.

Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images.

Multiple instance learning (MIL) models have achieved remarkable success in analyzing whole slide images (WSIs) for disease classification problems. However, with regard to giga-pixel WSI classification problems, current MIL models are often incapable of differentiating a WSI with extremely small tumor lesions. This minute tumor-to-normal area ratio in a MIL bag inhibits the attention mechanism from properly weighting the areas corresponding to minor tumor lesions. To overcome this challenge, we propose salient instance inference MIL (SiiMIL), a weakly-supervised MIL model for WSI classification. We introduce a novel representation learning for histopathology images to identify representative normal keys. These keys facilitate the selection of salient instances within WSIs, forming bags with high tumor-to-normal ratios. Finally, an attention mechanism is employed for slide-level classification based on formed bags. Our results show that salient instance inference can improve the tumor-to-normal area ratio in the tumor WSIs. As a result, SiiMIL achieves 0.9225 AUC and 0.7551 recall on the Camelyon16 dataset, which outperforms the existing MIL models. In addition, SiiMIL can generate tumor-sensitive attention heatmaps that is more interpretable to pathologists than the widely used attention-based MIL method. Our experiments imply that SiiMIL can accurately identify tumor instances, which could only take up less than 1% of a WSI, so that the ratio of tumor to normal instances within a bag can increase by two to four times.

The correlation between rheological properties and extrusion-based printability in bioink artifact quantification.

Bioinks for cell-based bioprinting face availability limitations. Furthermore, the bioink development process needs comprehensive printability assessment methods and a thorough understanding of rheological factors' influence on printing outcomes. To bridge this gap, our study aimed to investigate the relationship between rheological properties and printing outcomes. We developed a specialized bioink artifact specifically designed to improve the quantification of printability assessment. This bioink artifact adhered to established criteria from extrusion-based bioprinting approaches. Seven hydrogel-based bioinks were selected and tested using the bioink artifact and rheological measurement. Rheological analysis revealed that the high-performing bioinks exhibited notable characteristics such as high storage modulus, low tan(δ), high shear-thinning capabilities, high yield stress, and fast, near-complete recovery abilities. Although rheological data alone cannot fully explain printing outcomes, certain metrics like storage modulus and tan(δ) correlated well (R2 > 0.9) with specific printing outcomes, such as gap-spanning capability and turn accuracy. This study provides a comprehensive examination of bioink shape fidelity across a wide range of bioinks, rheological measures, and printing outcomes. The results highlight the importance of considering the holistic view of bioink's rheological properties and directly measuring printing outcomes. These findings underscore the need to enhance bioink availability and establish standardized methods for assessing printability.

Machine learning-based analytics of the impact of the Covid-19 pandemic on alcohol consumption habit changes among United States healthcare workers.

The COVID-19 pandemic is a global health concern that has spread around the globe. Machine Learning is promising in the fight against the COVID-19 pandemic. Machine learning and artificial intelligence have been employed by various healthcare providers, scientists, and clinicians in medical industries in the fight against COVID-19 disease. In this paper, we discuss the impact of the Covid-19 pandemic on alcohol consumption habit changes among healthcare workers in the United States during the first wave of the Covid-19 pandemic. We utilize multiple supervised and unsupervised machine learning methods and models such as decision trees, logistic regression, support vector machines, multilayer perceptron, XGBoost, CatBoost, LightGBM, AdaBoost, Chi-Squared Test, mutual information, KModes clustering and the synthetic minority oversampling technique on a mental health survey data obtained from the University of Michigan Inter-University Consortium for Political and Social Research to investigate the links between COVID-19-related deleterious effects and changes in alcohol consumption habits among healthcare workers. Through the interpretation of the supervised and unsupervised methods, we have concluded that healthcare workers whose children stayed home during the first wave in the US consumed more alcohol. We also found that the work schedule changes due to the Covid-19 pandemic led to a change in alcohol use habits. Changes in food consumption, age, gender, geographical characteristics, changes in sleep habits, the amount of news consumption, and screen time are also important predictors of an increase in alcohol use among healthcare workers in the United States.

BCR-Net: A deep learning framework to predict breast cancer recurrence from histopathology images.

Breast cancer is the most common malignancy in women, with over 40,000 deaths annually in the United States alone. Clinicians often rely on the breast cancer recurrence score, Oncotype DX (ODX), for risk stratification of breast cancer patients, by using ODX as a guide for personalized therapy. However, ODX and similar gene assays are expensive, time-consuming, and tissue destructive. Therefore, developing an AI-based ODX prediction model that identifies patients who will benefit from chemotherapy in the same way that ODX does would give a low-cost alternative to the genomic test. To overcome this problem, we developed a deep learning framework, Breast Cancer Recurrence Network (BCR-Net), which automatically predicts ODX recurrence risk from histopathology slides. Our proposed framework has two steps. First, it intelligently samples discriminative features from whole-slide histopathology images of breast cancer patients. Then, it automatically weights all features through a multiple instance learning model to predict the recurrence score at the slide level. On a dataset of H&E and Ki67 breast cancer resection whole slides images (WSIs) from 99 anonymized patients, the proposed framework achieved an overall AUC of 0.775 (68.9% and 71.1% accuracies for low and high risk) on H&E WSIs and overall AUC of 0.811 (80.8% and 79.2% accuracies for low and high risk) on Ki67 WSIs of breast cancer patients. Our findings provide strong evidence for automatically risk-stratify patients with a high degree of confidence. Our experiments reveal that the BCR-Net outperforms the state-of-the-art WSI classification models. Moreover, BCR-Net is highly efficient with low computational needs, making it practical to deploy in limited computational settings.

Machine Learning Models for Predicting the Outcomes of Surgical Treatment of Colorectal Liver Metastases.

BACKGROUND: Surgical intervention remains the cornerstone of a multidisciplinary approach in the treatment of colorectal liver metastases (CLM). Nevertheless, patient outcomes vary greatly. While predictive tools can assist decision-making and patient counseling, decades of efforts have yet to result in generating a universally adopted tool in clinical practice. STUDY DESIGN: An international collaborative database of CLM patients who underwent surgical therapy between 2000 and 2018 was used to select 1,004 operations for this study. Two different machine learning methods were applied to construct 2 predictive models for recurrence and death, using 128 clinicopathologic variables: gradient-boosted trees (GBTs) and logistic regression with bootstrapping (LRB) in a leave-one-out cross-validation. RESULTS: Median survival after resection was 47.2 months, and disease-free survival was 19.0 months, with a median follow-up of 32.0 months in the cohort. Both models had good predictive power, with GBT demonstrating a superior performance in predicting overall survival (area under the receiver operating curve [AUC] 0.773, 95% CI 0.743 to 0.801 vs LRB: AUC 0.648, 95% CI 0.614 to 0.682) and recurrence (AUC 0.635, 95% CI 0.599 to 0.669 vs LRB: AUC 0.570, 95% CI 0.535 to 0.601). Similarly, better performances were observed predicting 3- and 5-year survival, as well as 3- and 5-year recurrence, with GBT methods generating higher AUCs. CONCLUSIONS: Machine learning provides powerful tools to create predictive models of survival and recurrence after surgery for CLM. The effectiveness of both machine learning models varies, but on most occasions, GBT outperforms LRB. Prospective validation of these models lays the groundwork to adopt them in clinical practice.

CXCL1: A new diagnostic biomarker for human tuberculosis discovered using Diversity Outbred mice.

More humans have died of tuberculosis (TB) than any other infectious disease and millions still die each year. Experts advocate for blood-based, serum protein biomarkers to help diagnose TB, which afflicts millions of people in high-burden countries. However, the protein biomarker pipeline is small. Here, we used the Diversity Outbred (DO) mouse population to address this gap, identifying five protein biomarker candidates. One protein biomarker, serum CXCL1, met the World Health Organization's Targeted Product Profile for a triage test to diagnose active TB from latent M.tb infection (LTBI), non-TB lung disease, and normal sera in HIV-negative, adults from South Africa and Vietnam. To find the biomarker candidates, we quantified seven immune cytokines and four inflammatory proteins corresponding to highly expressed genes unique to progressor DO mice. Next, we applied statistical and machine learning methods to the data, i.e., 11 proteins in lungs from 453 infected and 29 non-infected mice. After searching all combinations of five algorithms and 239 protein subsets, validating, and testing the findings on independent data, two combinations accurately diagnosed progressor DO mice: Logistic Regression using MMP8; and Gradient Tree Boosting using a panel of 4: CXCL1, CXCL2, TNF, IL-10. Of those five protein biomarker candidates, two (MMP8 and CXCL1) were crucial for classifying DO mice; were above the limit of detection in most human serum samples; and had not been widely assessed for diagnostic performance in humans before. In patient sera, CXCL1 exceeded the triage diagnostic test criteria (>90% sensitivity; >70% specificity), while MMP8 did not. Using Area Under the Curve analyses, CXCL1 averaged 94.5% sensitivity and 88.8% specificity for active pulmonary TB (ATB) vs LTBI; 90.9% sensitivity and 71.4% specificity for ATB vs non-TB; and 100.0% sensitivity and 98.4% specificity for ATB vs normal sera. Our findings overall show that the DO mouse population can discover diagnostic-quality, serum protein biomarkers of human TB.

Digital Otoscopy Videos Versus Composite Images: A Reader Study to Compare the Accuracy of ENT Physicians.

OBJECTIVES/HYPOTHESIS: With the increasing emphasis on developing effective telemedicine approaches in Otolaryngology, this study explored whether a single composite image stitched from a digital otoscopy video provides acceptable diagnostic information to make an accurate diagnosis, as compared with that provided by the full video. STUDY DESIGN: Diagnostic survey analysis. METHODS: Five Ear, Nose, and Throat (ENT) physicians reviewed the same set of 78 digital otoscope eardrum videos from four eardrum conditions: normal, effusion, retraction, and tympanosclerosis, along with the composite images generated by a SelectStitch method that selectively uses video frames with computer-assisted selection, as well as a Stitch method that incorporates all the video frames. Participants provided a diagnosis for each item along with a rating of diagnostic confidence. Diagnostic accuracy for each pathology of SelectStitch was compared with accuracy when reviewing the entire video clip and when reviewing the Stitch image. RESULTS: There were no significant differences in diagnostic accuracy for physicians reviewing SelectStitch images and full video clips, but both provided better diagnostic accuracy than Stitch images. The inter-reader agreement was moderate. CONCLUSIONS: Equal to using full video clips, composite images of eardrums generated by SelectStitch provided sufficient information for ENTs to make the correct diagnoses for most pathologies. These findings suggest that use of a composite eardrum image may be sufficient for telemedicine approaches to ear diagnosis, eliminating the need for storage and transmission of large video files, along with future applications for improved documentation in electronic medical record systems, patient/family counseling, and clinical training. LEVEL OF EVIDENCE: 3 Laryngoscope, 131:E1668-E1676, 2021.

The Influence of Printing Parameters and Cell Density on Bioink Printing Outcomes.

Bioink printability persists as a limiting factor toward many bioprinting applications. Printing parameter selection is largely user-dependent, and the effect of cell density on printability has not been thoroughly investigated. Recently, methods have been developed to give greater insight into printing outcomes. This study aims to further advance those methods and apply them to study the effect of printing parameters (feedrate and flowrate) and cell density on printability. Two printed structures, a crosshatch and five-layer tube, were established as printing standards and utilized to determine the printing outcomes. Acellular bioinks were printed using a testing matrix of feedrates of 37.5, 75, 150, 300, and 600 mm/min and flowrates of 21, 42, 84, 168, and 336 mm3/min. Structures were also printed with cell densities of 5, 10, 20, and 40 × 106 cell/mL at 150 mm/min and 84 mm3/min. Only speed ratios (defined as flowrate divided by feedrate) from 0.07 to 2.24 mm2 were suitable for analysis. Increasing speed ratio dramatically increased the height, width, and wall thickness of tubular structures, but did not influence radial accuracy. For crosshatch structures, the area of pores and the frequency of broken filaments were decreased without impacting pore shape (Pr). Within speed ratios, feedrate and flowrate had negligible, inconsistent effects. Cell density did not affect any printing outcomes despite slight rheological changes. Printing outcomes were dominated by the speed ratio, with feedrate, flowrate, and cell density having little impact on printing outcomes when controlling for speed ratio within the ranges tested. The relevance of these results to other bioinks and printing conditions requires continued investigation by the bioprinting community, as well as highlight speed ratio as a key variable to report and suggest that rheology is a more sensitive measure than printing outcomes.

Semantic segmentation to identify bladder layers from H&E Images.

BACKGROUND: Identification of bladder layers is a necessary prerequisite to bladder cancer diagnosis and prognosis. We present a method of multi-class image segmentation, which recognizes urothelium, lamina propria, muscularis propria, and muscularis mucosa layers as well as regions of red blood cells, cauterized tissue, and inflamed tissue from images of hematoxylin and eosin stained slides of bladder biopsies. METHODS: Segmentation is carried out using a U-Net architecture. The number of layers was either, eight, ten, or twelve and combined with a weight initializers of He uniform, He normal, Glorot uniform, and Glorot normal. The most optimal of these parameters was found by through a seven-fold training, validation, and testing of a dataset of 39 whole slide images of T1 bladder biopsies. RESULTS: The most optimal model was a twelve layer U-net using He normal initializer. Initial visual evaluation by an experienced pathologist on an independent set of 15 slides segmented by our method yielded an average score of 8.93 ± 0.6 out of 10 for segmentation accuracy. It took only 23 min for the pathologist to review 15 slides (1.53 min/slide) with the computer annotations. To assess the generalizability of the proposed model, we acquired an additional independent set of 53 whole slide images and segmented them using our method. Visual examination by a different experienced pathologist yielded an average score of 8.87 ± 0.63 out of 10 for segmentation accuracy. CONCLUSIONS: Our preliminary findings suggest that predictions of our model can minimize the time needed by pathologists to annotate slides. Moreover, the method has the potential to identify the bladder layers accurately. Further development can assist the pathologist with the diagnosis of T1 bladder cancer.

OtoMatch: Content-based eardrum image retrieval using deep learning.

Acute infections of the middle ear are the most commonly treated childhood diseases. Because complications affect children's language learning and cognitive processes, it is essential to diagnose these diseases in a timely and accurate manner. The prevailing literature suggests that it is difficult to accurately diagnose these infections, even for experienced ear, nose, and throat (ENT) physicians. Advanced care practitioners (e.g., nurse practitioners, physician assistants) serve as first-line providers in many primary care settings and may benefit from additional guidance to appropriately determine the diagnosis and treatment of ear diseases. For this purpose, we designed a content-based image retrieval (CBIR) system (called OtoMatch) for normal, middle ear effusion, and tympanostomy tube conditions, operating on eardrum images captured with a digital otoscope. We present a method that enables the conversion of any convolutional neural network (trained for classification) into an image retrieval model. As a proof of concept, we converted a pre-trained deep learning model into an image retrieval system. We accomplished this by changing the fully connected layers into lookup tables. A database of 454 labeled eardrum images (179 normal, 179 effusion, and 96 tube cases) was used to train and test the system. On a 10-fold cross validation, the proposed method resulted in an average accuracy of 80.58% (SD 5.37%), and maximum F1 score of 0.90 while retrieving the most similar image from the database. These are promising results for the first study to demonstrate the feasibility of developing a CBIR system for eardrum images using the newly proposed methodology.

Ros-NET: A deep convolutional neural network for automatic identification of rosacea lesions.

BACKGROUND: Rosacea is one of the most common cutaneous disorder characterized primarily by facial flushing, erythema, papules, pustules, telangiectases, and nasal swelling. Diagnosis of rosacea is principally done by a physical examination and a consistent patient history. However, qualitative human assessment is often subjective and suffers from a relatively high intra- and inter-observer variability in evaluating patient outcomes. MATERIALS AND METHODS: To overcome these problems, we propose a quantitative and reproducible computer-aided diagnosis system, Ros-NET, which integrates information from different image scales and resolutions in order to identify rosacea lesions. This involves adaption of Inception-ResNet-v2 and ResNet-101 to extract rosacea features from facial images. Additionally, we propose to refine the detection results by means of facial-landmarks-based zones (ie, anthropometric landmarks) as regions of interest (ROI), which focus on typical areas of rosacea occurrence on a face. RESULTS: Using a leave-one-patient-out cross-validation scheme, the weighted average Dice coefficients, in percentages, across all patients (N = 41) with 256 × 256 image patches are 89.8 ± 2.6% and 87.8 ± 2.4% with Inception-ResNet-v2 and ResNet-101, respectively. CONCLUSION: The findings from this study support that pre-trained networks trained via transfer learning can be beneficial in identifying rosacea lesions. Our future work will involve expanding the work to a larger database of cases with varying degrees of disease characteristics.

Digital pathology and artificial intelligence.

In modern clinical practice, digital pathology has a crucial role and is increasingly a technological requirement in the scientific laboratory environment. The advent of whole-slide imaging, availability of faster networks, and cheaper storage solutions has made it easier for pathologists to manage digital slide images and share them for clinical use. In parallel, unprecedented advances in machine learning have enabled the synergy of artificial intelligence and digital pathology, which offers image-based diagnosis possibilities that were once limited only to radiology and cardiology. Integration of digital slides into the pathology workflow, advanced algorithms, and computer-aided diagnostic techniques extend the frontiers of the pathologist's view beyond a microscopic slide and enable true utilisation and integration of knowledge that is beyond human limits and boundaries, and we believe there is clear potential for artificial intelligence breakthroughs in the pathology setting. In this Review, we discuss advancements in digital slide-based image diagnosis for cancer along with some challenges and opportunities for artificial intelligence in digital pathology.

Relationship between the Ki67 index and its area based approximation in breast cancer.

BACKGROUND: The Ki67 Index has been extensively studied as a prognostic biomarker in breast cancer. However, its clinical adoption is largely hampered by the lack of a standardized method to assess Ki67 that limits inter-laboratory reproducibility. It is important to standardize the computation of the Ki67 Index before it can be effectively used in clincial practice. METHOD: In this study, we develop a systematic approach towards standardization of the Ki67 Index. We first create the ground truth consisting of tumor positive and tumor negative nuclei by registering adjacent breast tissue sections stained with Ki67 and H&E. The registration is followed by segmentation of positive and negative nuclei within tumor regions from Ki67 images. The true Ki67 Index is then approximated with a linear model of the area of positive to the total area of tumor nuclei. RESULTS: When tested on 75 images of Ki67 stained breast cancer biopsies, the proposed method resulted in an average root mean square error of 3.34. In comparison, an expert pathologist resulted in an average root mean square error of 9.98 and an existing automated approach produced an average root mean square error of 5.64. CONCLUSIONS: We show that it is possible to approximate the true Ki67 Index accurately without detecting individual nuclei and also statically demonstrate the weaknesses of commonly adopted approaches that use both tumor and non-tumor regions together while compensating for the latter with higher order approximations.

Nuclear IHC enumeration: A digital phantom to evaluate the performance of automated algorithms in digital pathology.

Automatic and accurate detection of positive and negative nuclei from images of immunostained tissue biopsies is critical to the success of digital pathology. The evaluation of most nuclei detection algorithms relies on manually generated ground truth prepared by pathologists, which is unfortunately time-consuming and suffers from inter-pathologist variability. In this work, we developed a digital immunohistochemistry (IHC) phantom that can be used for evaluating computer algorithms for enumeration of IHC positive cells. Our phantom development consists of two main steps, 1) extraction of the individual as well as nuclei clumps of both positive and negative nuclei from real WSI images, and 2) systematic placement of the extracted nuclei clumps on an image canvas. The resulting images are visually similar to the original tissue images. We created a set of 42 images with different concentrations of positive and negative nuclei. These images were evaluated by four board certified pathologists in the task of estimating the ratio of positive to total number of nuclei. The resulting concordance correlation coefficients (CCC) between the pathologist and the true ratio range from 0.86 to 0.95 (point estimates). The same ratio was also computed by an automated computer algorithm, which yielded a CCC value of 0.99. Reading the phantom data with known ground truth, the human readers show substantial variability and lower average performance than the computer algorithm in terms of CCC. This shows the limitation of using a human reader panel to establish a reference standard for the evaluation of computer algorithms, thereby highlighting the usefulness of the phantom developed in this work. Using our phantom images, we further developed a function that can approximate the true ratio from the area of the positive and negative nuclei, hence avoiding the need to detect individual nuclei. The predicted ratios of 10 held-out images using the function (trained on 32 images) are within ±2.68% of the true ratio. Moreover, we also report the evaluation of a computerized image analysis method on the synthetic tissue dataset.

Optimized generation of high-resolution phantom images using cGAN: Application to quantification of Ki67 breast cancer images.

In pathology, Immunohistochemical staining (IHC) of tissue sections is regularly used to diagnose and grade malignant tumors. Typically, IHC stain interpretation is rendered by a trained pathologist using a manual method, which consists of counting each positively- and negatively-stained cell under a microscope. The manual enumeration suffers from poor reproducibility even in the hands of expert pathologists. To facilitate this process, we propose a novel method to create artificial datasets with the known ground truth which allows us to analyze the recall, precision, accuracy, and intra- and inter-observer variability in a systematic manner, enabling us to compare different computer analysis approaches. Our method employs a conditional Generative Adversarial Network that uses a database of Ki67 stained tissues of breast cancer patients to generate synthetic digital slides. Our experiments show that synthetic images are indistinguishable from real images. Six readers (three pathologists and three image analysts) tried to differentiate 15 real from 15 synthetic images and the probability that the average reader would be able to correctly classify an image as synthetic or real more than 50% of the time was only 44.7%.