Diagnosis of soil-transmitted helminth infections with digital mobile microscopy and artificial intelligence in a resource-limited setting.

BACKGROUND: Infections caused by soil-transmitted helminths (STHs) are the most prevalent neglected tropical diseases and result in a major disease burden in low- and middle-income countries, especially in school-aged children. Improved diagnostic methods, especially for light intensity infections, are needed for efficient, control and elimination of STHs as a public health problem, as well as STH management. Image-based artificial intelligence (AI) has shown promise for STH detection in digitized stool samples. However, the diagnostic accuracy of AI-based analysis of entire microscope slides, so called whole-slide images (WSI), has previously not been evaluated on a sample-level in primary healthcare settings in STH endemic countries. METHODOLOGY/PRINCIPAL FINDINGS: Stool samples (n = 1,335) were collected during 2020 from children attending primary schools in Kwale County, Kenya, prepared according to the Kato-Katz method at a local primary healthcare laboratory and digitized with a portable whole-slide microscopy scanner and uploaded via mobile networks to a cloud environment. The digital samples of adequate quality (n = 1,180) were split into a training (n = 388) and test set (n = 792) and a deep-learning system (DLS) developed for detection of STHs. The DLS findings were compared with expert manual microscopy and additional visual assessment of the digital samples in slides with discordant results between the methods. Manual microscopy detected 15 (1.9%) Ascaris lumbricoides, 172 (21.7%) Tricuris trichiura and 140 (17.7%) hookworm (Ancylostoma duodenale or Necator americanus) infections in the test set. Importantly, more than 90% of all STH positive cases represented light intensity infections. With manual microscopy as the reference standard, the sensitivity of the DLS as the index test for detection of A. lumbricoides, T. trichiura and hookworm was 80%, 92% and 76%, respectively. The corresponding specificity was 98%, 90% and 95%. Notably, in 79 samples (10%) classified as negative by manual microscopy for a specific species, STH eggs were detected by the DLS and confirmed correct by visual inspection of the digital samples. CONCLUSIONS/SIGNIFICANCE: Analysis of digitally scanned stool samples with the DLS provided high diagnostic accuracy for detection of STHs. Importantly, a substantial number of light intensity infections were missed by manual microscopy but detected by the DLS. Thus, analysis of WSIs with image-based AI may provide a future tool for improved detection of STHs in a primary healthcare setting, which in turn could facilitate monitoring and evaluation of control programs.

External validation of a deep learning-based algorithm for detection of tall cells in papillary thyroid carcinoma: A multicenter study.

The tall cell subtype (TC-PTC) is an aggressive subtype of papillary thyroid carcinoma (PTC). The TC-PTC is defined as a PTC comprising at least 30% epithelial cells that are three times as tall as they are wide. In practice, this definition is difficult to adhere to, resulting in high inter-observer variability. In this multicenter study, we validated a previously trained deep learning (DL)-based algorithm for detection of tall cells on 160 externally collected hematoxylin and eosin (HE)-stained PTC whole-slide images. In a test set of 360 manual annotations of regions of interest from 18 separate tissue sections in the external dataset, the DL-based algorithm detected TCs with a sensitivity of 90.6% and a specificity of 88.5%. The DL algorithm detected non-TC areas with a sensitivity of 81.6% and a specificity of 92.9%. In the validation datasets, 20% and 30% TC thresholds correlated with a significantly shorter relapse-free survival. In conclusion, the DL algorithm detected TCs in unseen, external scanned HE tissue slides with high sensitivity and specificity without any retraining.

Development and evaluation of deep learning algorithms for assessment of acute burns and the need for surgery.

Assessment of burn extent and depth are critical and require very specialized diagnosis. Automated image-based algorithms could assist in performing wound detection and classification. We aimed to develop two deep-learning algorithms that respectively identify burns, and classify whether they require surgery. An additional aim assessed the performances in different Fitzpatrick skin types. Annotated burn (n = 1105) and background (n = 536) images were collected. Using a commercially available platform for deep learning algorithms, two models were trained and validated on 70% of the images and tested on the remaining 30%. Accuracy was measured for each image using the percentage of wound area correctly identified and F1 scores for the wound identifier; and area under the receiver operating characteristic (AUC) curve, sensitivity, and specificity for the wound classifier. The wound identifier algorithm detected an average of 87.2% of the wound areas accurately in the test set. For the wound classifier algorithm, the AUC was 0.885. The wound identifier algorithm was more accurate in patients with darker skin types; the wound classifier was more accurate in patients with lighter skin types. To conclude, image-based algorithms can support the assessment of acute burns with relatively good accuracy although larger and different datasets are needed.

High relative amount of nodular calcification in femoral plaques is associated with milder lower extremity arterial disease.

BACKGROUND: Clinical implications of different types of vascular calcification are poorly understood. The two most abundant forms of calcification, nodular and sheet calcification, have not been quantitatively analyzed in relation to the clinical presentation of lower extremity arterial disease (LEAD). METHODS: The study analyzed 51 femoral artery plaques collected during femoral endarterectomy, characterized by the presence of > 90% stenosis. Comprehensive clinical data was obtained from patient records, including magnetic resonance angiography (MRA) images, toe pressure and ankle brachial index measurements and laboratory values. The plaques were longitudinally sectioned, stained with Hematoxylin and Eosin and digitized in a deep learning platform for quantification of the relative area of nodular and sheet calcification to the plaque section area. A deep learning artificial intelligence algorithm was designed and independently validated to reliably quantify nodular calcification and sheet calcification. Vessel measurements and quantity of each calcification category was compared to the risk factors and clinical presentation. RESULTS: On average, > 90% stenosed vessels contained 22.4 ± 12.3% of nodular and 14.5 ± 11.8% of sheet calcification. Nodular calcification area proportion in lesions with > 90% stenosis is associated with reduced risk of critically low toe pressure (< 30 mmHg) (OR = 0.910, 95% CI = 0.835-0.992, p < 0.05), severely lowered ankle brachial index (< 0.4) (OR = 0.912, 95% CI = 0.84-0.986, p < 0.05), and semi-urgent operation (OR = 0.882, 95% CI = 0.797-0.976, p < 0.05). Sheet calcification did not show any significant association. CONCLUSIONS: Large amount of nodular calcification is associated with less severe LEAD. Patients with nodular calcification may have better flow reserves despite local obstruction.

A deep learning-based algorithm for tall cell detection in papillary thyroid carcinoma.

INTRODUCTION: According to the World Health Organization, the tall cell variant (TCV) is an aggressive subtype of papillary thyroid carcinoma (PTC) comprising at least 30% epithelial cells two to three times as tall as they are wide. In practice, applying this definition is difficult causing substantial interobserver variability. We aimed to train a deep learning algorithm to detect and quantify the proportion of tall cells (TCs) in PTC. METHODS: We trained the deep learning algorithm using supervised learning, testing it on an independent dataset, and further validating it on an independent set of 90 PTC samples from patients treated at the Hospital District of Helsinki and Uusimaa between 2003 and 2013. We compared the algorithm-based TC percentage to the independent scoring by a human investigator and how those scorings associated with disease outcomes. Additionally, we assessed the TC score in 71 local and distant tumor relapse samples from patients with aggressive disease. RESULTS: In the test set, the deep learning algorithm detected TCs with a sensitivity of 93.7% and a specificity of 94.5%, whereas the sensitivity fell to 90.9% and specificity to 94.1% for non-TC areas. In the validation set, the deep learning algorithm TC scores correlated with a diminished relapse-free survival using cutoff points of 10% (p = 0.044), 20% (p < 0.01), and 30% (p = 0.036). The visually assessed TC score did not statistically significantly predict survival at any of the analyzed cutoff points. We observed no statistically significant difference in the TC score between primary tumors and relapse tumors determined by the deep learning algorithm or visually. CONCLUSIONS: We present a novel deep learning-based algorithm to detect tall cells, showing that a high deep learning-based TC score represents a statistically significant predictor of less favorable relapse-free survival in PTC.

Mental health in individuals with self-reported psychiatric symptoms during the COVID-19 pandemic: Baseline data from a swedish longitudinal cohort study.

Objective: Individuals with psychiatric disorders may be both vulnerable and sensitive to rapid societal changes that have occurred during the COVID-19 pandemic. To fully understand these impacts, repeated measurements of these individuals are warranted. The current longitudinal study set out to perform monthly assessment of individuals with common psychiatric disorders using established questionnaires with a possibility for them to self- rate their symptoms, over time. Methods: Recruitment of individuals who identified themselves as struggling with mental health problems, living in Sweden between July 2020 and June 2021 using an online survey. The individuals answered questions on demographics, psychiatric history, current psychiatric symptoms (e.g., Patient Health Questionnaire, PHQ-9; General Anxiety Disorder, GAD-7), somatic health, health-care contacts and any changes therein during the pandemic. Monthly, longitudinal assessments are still ongoing (consenting participants provide data for 1 year), and here we present descriptive statistics from the baseline measurement. All measurements from baseline (>400 items), and follow-ups are presented in detail. Results: A total of 6.095 participants (average age 35 years) submitted complete baseline data. Marital status (43% single) and number of years of education (48% highest degree being high school) were evenly distributed in this population. The most common lifetime psychiatric disorder in the sample was depressive disorder (80.5%) and generalized anxiety disorder (45.9%), with a substantial proportion having severe symptoms of depression. (30.5%) and anxiety (37.1%). Lifetime suicidal ideation (75.0%) and non-suicidal self-harm (57.7%) were prevalent in the group and 14.5% reported drug use during the pandemic. Allergies (36.8%) were the most common somatic condition, followed by irritable bowel syndrome (18.7%). For those having experienced a traumatic event, 39% showed symptoms during the pandemic indicating PTSD. Regarding contact with mental health services during the pandemic, 22% had established a new contact, and 20% reported to have increased their psychiatric medication compared to before the pandemic. Conclusion: Baseline data collected during the pandemic from individuals in Sweden with pre-existing psychiatric disorders demonstrate that this sample represents a population suitable for an investigation on the long-term impact of the pandemic, as intended by the longitudinal investigation that is ongoing. Follow-up questionnaires over a 12-month period are being collected and will indicate how the health and well-being of this population was impacted during the changes and uncertainties that have been characteristic of the past 2 years.

A proof-of-concept study on mortality prediction with machine learning algorithms using burn intensive care data.

INTRODUCTION: Burn injuries are a common traumatic injury. Large burns have high mortality requiring intensive care and accurate mortality predictions. To assess if machine learning (ML) could improve predictions, ML algorithms were tested and compared with the original and revised Baux score. METHODS: Admission data and mortality outcomes were collected from patients at Uppsala University Hospital Burn Centre from 2002 to 2019. Prognostic variables were selected, ML algorithms trained and predictions assessed by analysis of the area under the receiver operating characteristic curve (AUC). Comparison was made with Baux scores using DeLong test. RESULTS: A total of 17 prognostic variables were selected from 92 patients. AUCs in leave-one-out cross-validation for a decision tree model, an extreme boosting model, a random forest model, a support-vector machine (SVM) model and a generalised linear regression model (GLM) were 0.83 (95% confidence interval [CI] = 0.72-0.94), 0.92 (95% CI = 0.84-1), 0.92 (95% CI = 0.84-1), 0.92 (95% CI = 0.84-1) and 0.84 (95% CI = 0.74-0.94), respectively. AUCs for the Baux score and revised Baux score were 0.85 (95% CI = 0.75-0.95) and 0.84 (95% CI = 0.74-0.94). No significant differences were observed when comparing ML algorithms with Baux score and revised Baux score. Secondary variable selection was made to analyse model performance. CONCLUSION: This proof-of-concept study showed initial credibility in using ML algorithms to predict mortality in burn patients. The sample size was small and future studies are needed with larger sample sizes, further variable selections and prospective testing of the algorithms. LAY SUMMARY: Burn injuries are one of the most common traumatic injuries especially in countries with limited prevention and healthcare resources. To treat a patient with large burns who has been admitted to an intensive care unit, it is often necessary to assess the risk of a fatal outcome. Physicians traditionally use simplified scores to calculate risks. One commonly used score, the Baux score, uses age of the patient and the size of the burn to predict the risk of death. Adding the factor of inhalation injury, the score is then called the revised Baux score. However, there are a number of additional causes that can influence the risk of fatal outcomes that Baux scores do not take into account. Machine learning is a method of data modelling where the system learns to predict outcomes based on previous cases and is a branch of artificial intelligence. In this study we evaluated several machine learning methods for outcome prediction in patients admitted for burn injury. We gathered data on 93 patients at admission to the intensive care unit and our experiments show that machine learning methods can reach an accuracy comparable with Baux scores in calculating the risk of fatal outcomes. This study represents a proof of principle and future studies on larger patient series are required to verify our results as well as to evaluate the methods on patients in real-life situations.

Outcome and Biomarker Supervised Deep Learning for Survival Prediction in Two Multicenter Breast Cancer Series.

BACKGROUND: Prediction of clinical outcomes for individual cancer patients is an important step in the disease diagnosis and subsequently guides the treatment and patient counseling. In this work, we develop and evaluate a joint outcome and biomarker supervised (estrogen receptor expression and ERBB2 expression and gene amplification) multitask deep learning model for prediction of outcome in breast cancer patients in two nation-wide multicenter studies in Finland (the FinProg and FinHer studies). Our approach combines deep learning with expert knowledge to provide more accurate, robust, and integrated prediction of breast cancer outcomes. MATERIALS AND METHODS: Using deep learning, we trained convolutional neural networks (CNNs) with digitized tissue microarray (TMA) samples of primary hematoxylin-eosin-stained breast cancer specimens from 693 patients in the FinProg series as input and breast cancer-specific survival as the endpoint. The trained algorithms were tested on 354 TMA patient samples in the same series. An independent set of whole-slide (WS) tumor samples from 674 patients in another multicenter study (FinHer) was used to validate and verify the generalization of the outcome prediction based on CNN models by Cox survival regression and concordance index (c-index). Visual cancer tissue characterization, i.e., number of mitoses, tubules, nuclear pleomorphism, tumor-infiltrating lymphocytes, and necrosis was performed on TMA samples in the FinProg test set by a pathologist and combined with deep learning-based outcome prediction in a multitask algorithm. RESULTS: The multitask algorithm achieved a hazard ratio (HR) of 2.0 (95% confidence interval [CI] 1.30-3.00), P < 0.001, c-index of 0.59 on the 354 test set of FinProg patients, and an HR of 1.7 (95% CI 1.2-2.6), P = 0.003, c-index 0.57 on the WS tumor samples from 674 patients in the independent FinHer series. The multitask CNN remained a statistically independent predictor of survival in both test sets when adjusted for histological grade, tumor size, and axillary lymph node status in a multivariate Cox analyses. An improved accuracy (c-index 0.66) was achieved when deep learning was combined with the tissue characteristics assessed visually by a pathologist. CONCLUSIONS: A multitask deep learning algorithm supervised by both patient outcome and biomarker status learned features in basic tissue morphology predictive of survival in a nationwide, multicenter series of patients with breast cancer. The algorithms generalized to another independent multicenter patient series and whole-slide breast cancer samples and provide prognostic information complementary to that of a comprehensive series of established prognostic factors.

Using 360-degree videos for virtual reality exposure in CBT for panic disorder with agoraphobia: a feasibility study.

BACKGROUND: Cognitive behavioural therapy (CBT) is an effective treatment for panic disorder with agoraphobia (PDA). However, implementation of some of the procedures involved, particularly in vivo exposure, can be time consuming and taxing for routine health care services. CBT with exposure taking place in virtual reality (VR-CBT) is a more time-efficient option and has shown promising results in the treatment of PDA. However, VR-CBT requires expensive equipment and appropriate virtual environments, which historically has been costly and cumbersome to produce. Thus, access to VR-CBT has been sparse in regular care environments. AIMS: The aim of this study was to investigate whether VR-CBT using filmed virtual environments produced with a low-cost 360-degree film camera can be a feasible and acceptable treatment for PDA when implemented in a primary care context. METHOD: This was an open feasibility trial with a within-group design, with assessments conducted at pre-test, post-test, and 6-month follow-up. Participants (n = 12) received a 10-12 week treatment programme of VR-CBT and PDA-related symptoms were assessed by the primary outcome measure The Mobility Inventory for Agoraphobia (MIA) and the Panic-Disorder Severity Scale-Self Rated (PDSS-SR). RESULTS: The results showed that treatment satisfaction was high and participants were significantly improved on PDA-related measures at post-treatment and at 6-month follow-up with large effect sizes (Cohen's d range = 1.46-2.82). All 12 participants completed the treatment. CONCLUSIONS: These findings suggest that VR-CBT with 360-degree video virtual environments delivered to primary care patients with PDA is feasible, acceptable, and potentially efficacious.

Isolation and worry in relation to gambling and onset of gambling among psychiatry patients during the COVID-19 pandemic: A mediation study.

When the COVID-19 pandemic started spreading globally, there was a fear that addictive behaviors would increase due to changes in everyday life caused by restrictions due to COVID-19. Studies were carried out to explore if this was true for gambling, typically revealing no overall increase in gambling behavior, although individuals who had previous experience with gambling problems were more likely to increase gambling during the pandemic. However, these studies only included individuals with previous gambling problems. It remains unknown whether other vulnerable groups, such as individuals with common mental disorders increased their gambling. This study aimed to explore the level of gambling problems among individuals with a history of mental disorders, namely, (i) pre-pandemic gamblers and (ii) pandemic-onset gamblers. Furthermore, we explored if worry and isolation mediate gambling and problem gambling. The data were analyzed using descriptive statistics and a structural equation model to investigate mediation. The results showed a high prevalence of at-risk and problem gambling in both groups. The pre-pandemic gamblers had a high level of at-risk and problem gambling. Furthermore, the individuals that started to gamble during the pandemic had an even higher degree of at-risk and problem gambling. The mediation showed that the onset of gambling was linked with the worry of COVID-infection and that worry predicted the level of gambling problems. This study highlights that vulnerability factors, isolation, and worry can be triggers for individuals with common mental disorders to engage in gambling as well as the importance of screening this population for gambling problems.

Artificial intelligence in cancer research, diagnosis and therapy.

STANDFIRST: Artificial intelligence and machine learning techniques are breaking into biomedical research and health care, which importantly includes cancer research and oncology, where the potential applications are vast. These include detection and diagnosis of cancer, subtype classification, optimization of cancer treatment and identification of new therapeutic targets in drug discovery. While big data used to train machine learning models may already exist, leveraging this opportunity to realize the full promise of artificial intelligence in both the cancer research space and the clinical space will first require significant obstacles to be surmounted. In this Viewpoint article, we asked four experts for their opinions on how we can begin to implement artificial intelligence while ensuring standards are maintained so as transform cancer diagnosis and the prognosis and treatment of patients with cancer and to drive biological discovery.

HLA-G expression correlates with histological grade but not with prognosis in colorectal carcinoma.

Trophoblast-specific expression of HLA-G induces immune tolerance for the developing fetus. Pathological HLA-G expression later in life might contribute to immune escape of various cancers. We studied the still controversial role of HLA-G in colorectal carcinoma (CRC) using the MEM-G/1 antibody and a tissue microarray series of CRC tumors (n = 317). HLA-G expression appeared in 20% of the tumors and showed high intratumoral heterogeneity. HLA-G positivity was associated with better differentiation (p = 0.002) and non-mucinous histology (p = 0.008). However, HLA-G expression alone showed no prognostic value: 5-years disease-specific survival among patients with HLA-G expression was 68.9% (95% CI: 62.7%-75.0%) compared to 74.8% (95% CI: 63.2%-86.3%) among those without expression. These results support a modulatory role of HLA-G in CRC.

Point-of-Care Digital Cytology With Artificial Intelligence for Cervical Cancer Screening in a Resource-Limited Setting.

Importance: Cervical cancer is highly preventable but remains a common and deadly cancer in areas without screening programs. The creation of a diagnostic system to digitize Papanicolaou test samples and analyze them using a cloud-based deep learning system (DLS) may provide needed cervical cancer screening to resource-limited areas. Objective: To determine whether artificial intelligence-supported digital microscopy diagnostics can be implemented in a resource-limited setting and used for analysis of Papanicolaou tests. Design, Setting, and Participants: In this diagnostic study, cervical smears from 740 HIV-positive women aged between 18 and 64 years were collected between September 1, 2018, and September 30, 2019. The smears were digitized with a portable slide scanner, uploaded to a cloud server using mobile networks, and used to train and validate a DLS for the detection of atypical cervical cells. This single-center study was conducted at a local health care center in rural Kenya. Exposures: Detection of squamous cell atypia in the digital samples by analysis with the DLS. Main Outcomes and Measures: The accuracy of the DLS in the detection of low- and high-grade squamous intraepithelial lesions in Papanicolaou test whole-slide images. Results: Papanicolaou test results from 740 HIV-positive women (mean [SD] age, 41.8 [10.3] years) were collected. The DLS was trained using 350 whole-slide images and validated on 361 whole-slide images (average size, 100 387 × 47 560 pixels). For detection of cervical cellular atypia, sensitivities were 95.7% (95% CI, 85.5%-99.5%) and 100% (95% CI, 82.4%-100%), and specificities were 84.7% (95% CI, 80.2%-88.5%) and 78.4% (95% CI, 73.6%-82.4%), compared with the pathologist assessment of digital and physical slides, respectively. Areas under the receiver operating characteristic curve were 0.94 and 0.96, respectively. Negative predictive values were high (99%-100%), and accuracy was high, particularly for the detection of high-grade lesions. Interrater agreement was substantial compared with the pathologist assessment of digital slides (κ = 0.72) and fair compared with the assessment of glass slides (κ = 0.36). No samples that were classified as high grade by manual sample analysis had false-negative assessments by the DLS. Conclusions and Relevance: In this study, digital microscopy with artificial intelligence was implemented at a rural clinic and used to detect atypical cervical smears with a high sensitivity compared with visual sample analysis.

Deep learning identifies morphological features in breast cancer predictive of cancer ERBB2 status and trastuzumab treatment efficacy.

The treatment of patients with ERBB2 (HER2)-positive breast cancer with anti-ERBB2 therapy is based on the detection of ERBB2 gene amplification or protein overexpression. Machine learning (ML) algorithms can predict the amplification of ERBB2 based on tumor morphological features, but it is not known whether ML-derived features can predict survival and efficacy of anti-ERBB2 treatment. In this study, we trained a deep learning model with digital images of hematoxylin-eosin (H&E)-stained formalin-fixed primary breast tumor tissue sections, weakly supervised by ERBB2 gene amplification status. The gene amplification was determined by chromogenic in situ hybridization (CISH). The training data comprised digitized tissue microarray (TMA) samples from 1,047 patients. The correlation between the deep learning-predicted ERBB2 status, which we call H&E-ERBB2 score, and distant disease-free survival (DDFS) was investigated on a fully independent test set, which included whole-slide tumor images from 712 patients with trastuzumab treatment status available. The area under the receiver operating characteristic curve (AUC) in predicting gene amplification in the test sets was 0.70 (95% CI, 0.63-0.77) on 354 TMA samples and 0.67 (95% CI, 0.62-0.71) on 712 whole-slide images. Among patients with ERBB2-positive cancer treated with trastuzumab, those with a higher than the median morphology-based H&E-ERBB2 score derived from machine learning had more favorable DDFS than those with a lower score (hazard ratio [HR] 0.37; 95% CI, 0.15-0.93; P = 0.034). A high H&E-ERBB2 score was associated with unfavorable survival in patients with ERBB2-negative cancer as determined by CISH. ERBB2-associated morphology correlated with the efficacy of adjuvant anti-ERBB2 treatment and can contribute to treatment-predictive information in breast cancer.

Antibody Supervised Training of a Deep Learning Based Algorithm for Leukocyte Segmentation in Papillary Thyroid Carcinoma.

The quantity of leukocytes in papillary thyroid carcinoma (PTC) potentially have prognostic and treatment predictive value. Here, we propose a novel method for training a convolutional neural network (CNN) algorithm for segmenting leukocytes in PTCs. Tissue samples from two retrospective PTC cohort were obtained and representative tissue slides from twelve patients were stained with hematoxylin and eosin (HE) and digitized. Then, the HE slides were destained and restained immunohistochemically (IHC) with antibodies to the pan-leukocyte anti CD45 antigen and scanned again. The two stain-pairs of all representative tissue slides were registered, and image tiles of regions of interests were exported. The image tiles were processed and the 3,3'-diaminobenzidine (DAB) stained areas representing anti CD45 expression were turned into binary masks. These binary masks were applied as annotations on the HE image tiles and used in the training of a CNN algorithm. Ten whole slide images (WSIs) were used for training using a five-fold cross-validation and the remaining two slides were used as an independent test set for the trained model. For visual evaluation, the algorithm was run on all twelve WSIs, and in total 238,144 tiles sized 500 × 500 pixels were analyzed. The trained CNN algorithm had an intersection over union of 0.82 for detection of leukocytes in the HE image tiles when comparing the prediction masks to the ground truth anti CD45 mask. We conclude that this method for generating antibody supervised annotations using the destain-restain IHC guided annotations resulted in high accuracy segmentations of leukocytes in HE tissue images.

Osteoid Metaplasia in Femoral Artery Plaques Is Associated With the Clinical Severity of Lower Extremity Artery Disease in Men.

Lamellar metaplastic bone, osteoid metaplasia (OM), is found in atherosclerotic plaques, especially in the femoral arteries. In the carotid arteries, OM has been documented to be associated with plaque stability. This study investigated the clinical impact of OM load in femoral artery plaques of patients with lower extremity artery disease (LEAD) by using a deep learning-based image analysis algorithm. Plaques from 90 patients undergoing endarterectomy of the common femoral artery were collected and analyzed. After decalcification and fixation, 4-µm-thick longitudinal sections were stained with hematoxylin and eosin, digitized, and uploaded as whole-slide images on a cloud-based platform. A deep learning-based image analysis algorithm was trained to analyze the area percentage of OM in whole-slide images. Clinical data were extracted from electronic patient records, and the association with OM was analyzed. Fifty-one (56.7%) sections had OM. Females with diabetes had a higher area percentage of OM than females without diabetes. In male patients, the area percentage of OM inversely correlated with toe pressure and was significantly associated with severe symptoms of LEAD including rest pain, ulcer, or gangrene. According to our results, OM is a typical feature of femoral artery plaques and can be quantified using a deep learning-based image analysis method. The association of OM load with clinical features of LEAD appears to differ between male and female patients, highlighting the need for a gender-specific approach in the study of the mechanisms of atherosclerotic disease. In addition, the role of plaque characteristics in the treatment of atherosclerotic lesions warrants further consideration in the future.

Machine-learning-driven biomarker discovery for the discrimination between allergic and irritant contact dermatitis.

Contact dermatitis tremendously impacts the quality of life of suffering patients. Currently, diagnostic regimes rely on allergy testing, exposure specification, and follow-up visits; however, distinguishing the clinical phenotype of irritant and allergic contact dermatitis remains challenging. Employing integrative transcriptomic analysis and machine-learning approaches, we aimed to decipher disease-related signature genes to find suitable sets of biomarkers. A total of 89 positive patch-test reaction biopsies against four contact allergens and two irritants were analyzed via microarray. Coexpression network analysis and Random Forest classification were used to discover potential biomarkers and selected biomarker models were validated in an independent patient group. Differential gene-expression analysis identified major gene-expression changes depending on the stimulus. Random Forest classification identified CD47, BATF, FASLG, RGS16, SYNPO, SELE, PTPN7, WARS, PRC1, EXO1, RRM2, PBK, RAD54L, KIFC1, SPC25, PKMYT, HISTH1A, TPX2, DLGAP5, TPX2, CH25H, and IL37 as potential biomarkers to distinguish allergic and irritant contact dermatitis in human skin. Validation experiments and prediction performances on external testing datasets demonstrated potential applicability of the identified biomarker models in the clinic. Capitalizing on this knowledge, novel diagnostic tools can be developed to guide clinical diagnosis of contact allergies.

A novel deep learning-based point-of-care diagnostic method for detecting Plasmodium falciparum with fluorescence digital microscopy.

BACKGROUND: Malaria remains a major global health problem with a need for improved field-usable diagnostic tests. We have developed a portable, low-cost digital microscope scanner, capable of both brightfield and fluorescence imaging. Here, we used the instrument to digitize blood smears, and applied deep learning (DL) algorithms to detect Plasmodium falciparum parasites. METHODS: Thin blood smears (n = 125) were collected from patients with microscopy-confirmed P. falciparum infections in rural Tanzania, prior to and after initiation of artemisinin-based combination therapy. The samples were stained using the 4',6-diamidino-2-phenylindole fluorogen and digitized using the prototype microscope scanner. Two DL algorithms were trained to detect malaria parasites in the samples, and results compared to the visual assessment of both the digitized samples, and the Giemsa-stained thick smears. RESULTS: Detection of P. falciparum parasites in the digitized thin blood smears was possible both by visual assessment and by DL-based analysis with a strong correlation in results (r = 0.99, p < 0.01). A moderately strong correlation was observed between the DL-based thin smear analysis and the visual thick smear-analysis (r = 0.74, p < 0.01). Low levels of parasites were detected by DL-based analysis on day three following treatment initiation, but a small number of fluorescent signals were detected also in microscopy-negative samples. CONCLUSION: Quantification of P. falciparum parasites in DAPI-stained thin smears is feasible using DL-supported, point-of-care digital microscopy, with a high correlation to visual assessment of samples. Fluorescent signals from artefacts in samples with low infection levels represented the main challenge for the digital analysis, thus highlighting the importance of minimizing sample contaminations. The proposed method could support malaria diagnostics and monitoring of treatment response through automated quantification of parasitaemia and is likely to be applicable also for diagnostics of other Plasmodium species and other infectious diseases.