Tissue Contamination Challenges the Credibility of Machine Learning Models in Real World Digital Pathology.

Machine learning (ML) models are poised to transform surgical pathology practice. The most successful use attention mechanisms to examine whole slides, identify which areas of tissue are diagnostic, and use them to guide diagnosis. Tissue contaminants, such as floaters, represent unexpected tissue. Although human pathologists are extensively trained to consider and detect tissue contaminants, we examined their impact on ML models. We trained 4 whole-slide models. Three operate in placenta for the following functions: (1) detection of decidual arteriopathy, (2) estimation of gestational age, and (3) classification of macroscopic placental lesions. We also developed a model to detect prostate cancer in needle biopsies. We designed experiments wherein patches of contaminant tissue are randomly sampled from known slides and digitally added to patient slides and measured model performance. We measured the proportion of attention given to contaminants and examined the impact of contaminants in the t-distributed stochastic neighbor embedding feature space. Every model showed performance degradation in response to one or more tissue contaminants. Decidual arteriopathy detection--balanced accuracy decreased from 0.74 to 0.69 ± 0.01 with addition of 1 patch of prostate tissue for every 100 patches of placenta (1% contaminant). Bladder, added at 10% contaminant, raised the mean absolute error in estimating gestational age from 1.626 weeks to 2.371 ± 0.003 weeks. Blood, incorporated into placental sections, induced false-negative diagnoses of intervillous thrombi. Addition of bladder to prostate cancer needle biopsies induced false positives, a selection of high-attention patches, representing 0.033 mm2, and resulted in a 97% false-positive rate when added to needle biopsies. Contaminant patches received attention at or above the rate of the average patch of patient tissue. Tissue contaminants induce errors in modern ML models. The high level of attention given to contaminants indicates a failure to encode biological phenomena. Practitioners should move to quantify and ameliorate this problem.

A population-level digital histologic biomarker for enhanced prognosis of invasive breast cancer.

Breast cancer is a heterogeneous disease with variable survival outcomes. Pathologists grade the microscopic appearance of breast tissue using the Nottingham criteria, which are qualitative and do not account for noncancerous elements within the tumor microenvironment. Here we present the Histomic Prognostic Signature (HiPS), a comprehensive, interpretable scoring of the survival risk incurred by breast tumor microenvironment morphology. HiPS uses deep learning to accurately map cellular and tissue structures to measure epithelial, stromal, immune, and spatial interaction features. It was developed using a population-level cohort from the Cancer Prevention Study-II and validated using data from three independent cohorts, including the Prostate, Lung, Colorectal, and Ovarian Cancer trial, Cancer Prevention Study-3, and The Cancer Genome Atlas. HiPS consistently outperformed pathologists in predicting survival outcomes, independent of tumor-node-metastasis stage and pertinent variables. This was largely driven by stromal and immune features. In conclusion, HiPS is a robustly validated biomarker to support pathologists and improve patient prognosis.

BRAF Exon 15 Mutations in the Evaluation of Well-Differentiated Epithelial Nephroblastic Neoplasms in Children: A Report From the Children's Oncology Group Study AREN03B2.

CONTEXT.­: The distinction between well-differentiated epithelial favorable-histology Wilms tumor (EFHWT) and metanephric adenoma (MA) in children has historically been determined by the required absence of both a fibrous pseudocapsule and mitotic activity in MA. More recently these features have been allowed in adult MA. Mutations in exon 15 of the BRAF gene are reported in up to 88% of MAs but have not been reported in EFHWTs. OBJECTIVE.­: To clarify the pathologic and molecular features used to distinguish between pediatric MA and EFHWT. DESIGN.­: Stage I epithelial tumors classified as EFHWT on central review (36 patients) were identified from the Children's Oncology Group AREN03B2 study. Thirteen tumors had morphologic features overlapping those of MA and 23 lacked such features; 35 of 36 had tissue available for sequencing of BRAF. RESULTS.­: Patients with EFHWTs with MA features (13) were older (mean, 8.4 versus 1.9 years; P < .001), had smaller tumor diameters (mean, 6.0 versus 9.7 cm; P < .001), and had fewer mitoses (mean, 1 versus 48 mitoses per 10 high-power fields; P < .001) than patients with EFHWT lacking MA features (23). All EFHWTs with MA features contained at least a partial fibrous pseudocapsule; 7 of 12 (58%) had BRAF exon 15 mutation. No BRAF exon 15 mutations were identified in 23 EFHWTs lacking MA features. None of the 13 EFHWT patients with MA features have experienced relapse (median follow-up 5.9 years). CONCLUSIONS.­: Pediatric epithelial neoplasms with features of MA that show partial encapsulation and/or modest mitotic activity may be classified as MAs. Although BRAF mutation supports the diagnosis of MA, it is not required for the diagnosis.

Placental pathology reports: A qualitative study in a US university hospital setting on perceived clinical utility and areas for improvement.

OBJECTIVE: To explore how placental pathology is currently used by clinicians and what placental information would be most useful in the immediate hours after delivery. STUDY DESIGN: We used a qualitative study design to conduct in-depth, semi-structured interviews with obstetric and neonatal clinicians who provide delivery or postpartum care at an academic medical center in the US (n = 19). Interviews were transcribed and analyzed using descriptive content analysis. RESULTS: Clinicians valued placental pathology information yet cited multiple barriers that prevent the consistent use of pathology. Four main themes were identified. First, the placenta is sent to pathology for consistent reasons, however, the pathology report is accessed by clinicians inconsistently due to key barriers: difficult to find in the electronic medical record, understand, and get quickly. Second, clinicians value placental pathology for explanatory capability as well as for contributions to current and future care, particularly when there is fetal growth restriction, stillbirth, or antibiotic use. Third, a rapid placental exam (specifically including placental weight, infection, infarction, and overall assessment) would be helpful in providing clinical care. Fourth, placental pathology reports that connect clinically relevant findings (similar to radiology) and that are written with plain, standardized language and that non-pathologists can more readily understand are preferred. CONCLUSION: Placental pathology is important to clinicians that care for mothers and newborns (particularly those that are critically ill) after birth, yet many problems stand in the way of its usefulness. Hospital administrators, perinatal pathologists, and clinicians should work together to improve access to and contents of reports. Support for new methods to provide quick placenta information is warranted.

Tissue contamination challenges the credibility of machine learning models in real world digital pathology.

Machine learning (ML) models are poised to transform surgical pathology practice. The most successful use attention mechanisms to examine whole slides, identify which areas of tissue are diagnostic, and use them to guide diagnosis. Tissue contaminants, such as floaters, represent unexpected tissue. While human pathologists are extensively trained to consider and detect tissue contaminants, we examined their impact on ML models. We trained 4 whole slide models. Three operate in placenta for 1) detection of decidual arteriopathy (DA), 2) estimation of gestational age (GA), and 3) classification of macroscopic placental lesions. We also developed a model to detect prostate cancer in needle biopsies. We designed experiments wherein patches of contaminant tissue are randomly sampled from known slides and digitally added to patient slides and measured model performance. We measured the proportion of attention given to contaminants and examined the impact of contaminants in T-distributed Stochastic Neighbor Embedding (tSNE) feature space. Every model showed performance degradation in response to one or more tissue contaminants. DA detection balanced accuracy decreased from 0.74 to 0.69 +/- 0.01 with addition of 1 patch of prostate tissue for every 100 patches of placenta (1% contaminant). Bladder, added at 10% contaminant raised the mean absolute error in estimating gestation age from 1.626 weeks to 2.371 +/ 0.003 weeks. Blood, incorporated into placental sections, induced false negative diagnoses of intervillous thrombi. Addition of bladder to prostate cancer needle biopsies induced false positives, a selection of high-attention patches, representing 0.033mm2, resulted in a 97% false positive rate when added to needle biopsies. Contaminant patches received attention at or above the rate of the average patch of patient tissue. Tissue contaminants induce errors in modern ML models. The high level of attention given to contaminants indicates a failure to encode biological phenomena. Practitioners should move to quantify and ameliorate this problem.

Machine learning classification of placental villous infarction, perivillous fibrin deposition, and intervillous thrombus.

INTRODUCTION: Placental parenchymal lesions are commonly encountered and carry significant clinical associations. However, they are frequently missed or misclassified by general practice pathologists. Interpretation of pathology slides has emerged as one of the most successful applications of machine learning (ML) in medicine with applications ranging from cancer detection and prognostication to transplant medicine. The goal of this study was to use a whole-slide learning model to identify and classify placental parenchymal lesions including villous infarctions, intervillous thrombi (IVT), and perivillous fibrin deposition (PVFD). METHODS: We generated whole slide images from placental discs examined at our institution with infarct, IVT, PVFD, or no macroscopic lesion. Slides were analyzed as a set of overlapping patches. We extracted feature vectors from each patch using a pretrained convolutional neural network (EfficientNetV2L). We trained a model to assign attention to each vector and used the attentions as weights to produce a pooled feature vector. The pooled vector was classified as normal or 1 of 3 lesions using a fully connected network. Patch attention was plotted to highlight informative areas of the slide. RESULTS: Overall balanced accuracy in a test set of held-out slides was 0.86 with receiver-operator characteristic areas under the curve of 0.917-0.993. Cases of PVFD were frequently miscalled as normal or infarcts, the latter possibly due to the perivillous fibrin found at the periphery of infarctions. We used attention maps to further understand some errors, including one most likely due to poor tissue fixation and processing. DISCUSSION: We used a whole-slide learning paradigm to train models to recognize three of the most common placental parenchymal lesions. We used attention maps to gain insight into model function, which differed from intuitive explanations.

Maternal Antibody Response and Transplacental Transfer Following Severe Acute Respiratory Syndrome Coronavirus 2 Infection or Vaccination in Pregnancy.

BACKGROUND: Pregnant persons are at increased risk of severe coronavirus disease 2019 (COVID-19) and adverse obstetric outcomes. Understanding maternal antibody response, duration, and transplacental transfer after severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and COVID-19 vaccination is important to inform public health recommendations. METHODS: This prospective observational cohort study included 351 pregnant people who had SARS-CoV-2 infection or COVID-19 vaccination during pregnancy. Immunoglobulin (Ig) G and IgM to SARS-CoV-2 S1 receptor binding domain were measured in maternal and cord blood. Antibody levels and transplacental transfer ratios were compared across (1) disease severity for those with SARS-CoV-2 infection and (2) infection versus vaccination. RESULTS: There were 252 individuals with SARS-CoV-2 infection and 99 who received COVID-19 vaccination during pregnancy. Birthing people with more severe SARS-CoV-2 infection had higher maternal and cord blood IgG levels (P = .0001, P = .0001). Median IgG transfer ratio was 0.87-1.2. Maternal and cord blood IgG were higher after vaccination than infection (P = .001, P = .001). Transfer ratio was higher after 90 days in the vaccinated group (P < .001). Modeling showed higher amplitude and half-life of maternal IgG following vaccination (P < .0001). There were no significant differences by fetal sex. CONCLUSIONS: COVID-19 vaccination in pregnancy leads to higher and longer lasting maternal IgG levels, higher cord blood IgG, and higher transfer ratio after 90 days compared with SARS-CoV-2 infection. Greater infection severity leads to higher maternal and cord blood antibodies. Maternal IgG decreases over time following both vaccination and infection, reinforcing the importance of vaccination, even after infection, and vaccine boosters for pregnant patients.

Pathology Education Powered by Virtual and Digital Transformation: Now and the Future.

CONTEXT.­: Myriad forces are changing teaching and learning strategies throughout all stages and types of pathology education. Pathology educators and learners face the challenge of adapting to and adopting new methods and tools. The digital pathology transformation and the associated educational ecosystem are major factors in this setting of change. OBJECTIVE.­: To identify and collect resources, tools, and examples of educational innovations involving digital pathology that are valuable to pathology learners and teachers at each phase of professional development. DATA SOURCES.­: Sources were a literature review and the personal experience of authors and educators. CONCLUSIONS.­: High-quality digital pathology tools and resources have permeated all the major niches within anatomic pathology and are increasingly well applied to clinical pathology for learners at all levels. Coupled with other virtual tools, the training landscape in pathology is highly enriched and much more accessible than in the past. Digital pathology is well suited to the demands of peer-to-peer education, such as in the introduction of new testing, grading, or other standardized practices. We found that digital pathology was well adapted to apply our current understanding of optimal teaching strategies and was effective at the undergraduate, graduate, postgraduate, and peer-to-peer levels. We curated and tabulated many existing resources within some segments of pathology. We identified several best practices for each training or educational stage based on current materials and proposed high-priority areas for potential future development.

Bronchopulmonary dysplasia is associated with polyhydramnios in a scan for novel perinatal risk factors.

BACKGROUND: The pathogenesis of bronchopulmonary dysplasia (BPD) is multifactorial, and there are limited data about prenatal exposures and risk of BPD. STUDY DESIGN: Our study performed parallel analyses using a logistic regression model in a cohort of 4527 infants with data from a curated registry and using a phenome wide association study (PheWAS) based on ICD9/10-based phecodes. We examined 20 prenatal exposures from a neonatal intensive care unit (NICU) curated registry database related to pregnancy and maternal health as well as 94 maternal diagnosis phecodes with a PheWAS analysis. RESULT: In both the curated registry and PheWAS analyses, polyhydramnios was associated with an increased risk of BPD (OR 5.70, 95% CI 2.78-11.44, p = 1.37 × 10-6). CONCLUSION: Our data suggest that polyhydramnios may be a clinical indicator of premature infants at increased risk for bronchopulmonary dysplasia. Combining curated registry data with PheWAS analysis creates a valuable tool to generate hypotheses. IMPACT: Polyhydramnios was significantly associated with bronchopulmonary dysplasia in both a curated registry and by ICD coding analysis with a phenome wide association study (PheWAS). Preterm polyhydramnios may be a clinical indicator of infants at increased risk for developing bronchopulmonary dysplasia after preterm birth. Combining curated registry with PheWAS analysis creates a valuable tool to generate hypotheses about perinatal risk factors and morbidities associated with preterm birth.

Placental Pathology After SARS-CoV-2 Infection in the Pre-Variant of Concern, Alpha / Gamma, Delta, or Omicron Eras.

Objectives. The goal of this study is to describe placental pathology after infection with SARS-CoV-2 before the predominance of variants of concern (pre-VOC) and during eras of predominant transmission of the Alpha & Gamma (co-circulating), Delta, and Omicron variants. Methods. We used county-level variant data to establish population-level variant proportions, SARS-CoV-2 PCR to identify cases, and IgG serology to exclude latent infections from controls and histopathologic examination to identify placental pathology. Results. We report findings in 870 placentas from pregnancies complicated by SARS-CoV-2 including 90 with infection in the Alpha/Gamma era, 60 from the Delta era and 56 from the Omicron era. Features of maternal vascular malperfusion (MVM), including decidual arteriopathy, were significantly more frequent after SARS-CoV-2 infection. The risk of these findings varied over time, with the highest rates in the Delta era. Increased COVID-19 severity and the presence of comorbidities strengthened these associations. Conclusion. MVM is a feature of SARS-CoV-2 infection in pregnancy. Lesion frequency changed with the predominant circulating virus and should be considered with new variants.

Medication history-wide association studies for pharmacovigilance of pregnant patients.

Background: Systematic exclusion of pregnant people from interventional clinical trials has created a public health emergency for millions of patients through a dearth of robust safety data for common drugs. Methods: We harnessed an enterprise collection of 2.8 M electronic health records (EHRs) from routine care, leveraging data linkages between mothers and their babies to detect drug safety signals in this population at full scale. Our mixed-methods signal detection approach stimulates new hypotheses for post-marketing surveillance agnostically of both drugs and diseases-by identifying 1,054 drugs historically prescribed to pregnant patients; developing a quantitative, medication history-wide association study; and integrating a qualitative evidence synthesis platform using expert clinician review for integration of biomedical specificity-to test the effects of maternal exposure to diverse drugs on the incidence of neurodevelopmental defects in their children. Results: We replicated known teratogenic risks and existing knowledge on drug structure-related teratogenicity; we also highlight 5 common drug classes for which we believe this work warrants updated assessment of their safety. Conclusion: Here, we present roots of an agile framework to guide enhanced medication regulations, as well as the ontological and analytical limitations that currently restrict the integration of real-world data into drug safety management during pregnancy. This research is not a replacement for inclusion of pregnant people in prospective clinical studies, but it presents a tractable team science approach to evaluating the utility of EHRs for new regulatory review programs-towards improving the delicate equipoise of accuracy and ethics in assessing drug safety in pregnancy.

Low-level SARS-CoV-2 viremia coincident with COVID placentitis and stillbirth.

SARS-CoV-2 infection in pregnancy and COVID placentitis are associated with an increased risk of stillbirth. We sought to investigate the presence of maternal viremia in people with SARS-CoV-2 infection during pregnancy who had histologic placentitis versus those without placentitis. SARS-CoV-2 qRT-PCR was performed on plasma from 6 patients with COVID placentitis and 12 matched controls without placentitis. SARS-CoV-2 infection occurred between 4/2020-1/2021; the latency between SARS-CoV-2 diagnosis and delivery was 0-76 days. Two placentitis cases demonstrated viremia (1 stillbirth and 1 well infant), while 12/12 controls were negative. Future research may consider viremia as a possible marker of COVID placentitis.

Maternal vs Fetal Origin of Placental Intervillous Thrombi.

OBJECTIVES: To determine maternal vs fetal origin for blood in placental intervillous thrombi (IVTs). METHODS: We used comparative analysis of microsatellites (short tandem repeats [STRs]), sex chromosome fluorescence in situ hybridization (FISH), and immunohistochemistry (IHC) for fetal (ɑ-fetoprotein [AFP]) and maternal (immunoglobulin M [IgM]) serum proteins to distinguish the origin of IVTs. Using an informatics approach, we tested the association between IVTs and fetomaternal hemorrhage (FMH). RESULTS: In 9 of 10 cases, the preponderance of evidence showed that the thrombus was mostly or entirely maternal in origin. In 1 case, the thrombus was of mixed origins. STR testing was prone to contamination by entrapped fetal villi. FISH was useful but limited only to cases with male fetuses. IgM showed stronger staining than AFP in 9 cases, supporting maternal origin. By informatics, we found no association between IVTs and FMH. CONCLUSIONS: Evidence supports a maternal origin for blood in IVTs. IHC for IgM and AFP may be clinically useful in determining maternal vs fetal contribution to IVTs.

Laboratory analysis of symptomatic and asymptomatic pregnant patients with SARS-CoV-2 infection.

BACKGROUND: Inflammatory biomarkers have been used to portend disease severity in nonpregnant individuals with SARS-CoV-2 infection. However, currently, limited data are available, and with mixed results, to elucidate which inflammatory biomarkers may be most associated with clinical phenotype in pregnant patients. OBJECTIVE: We aimed to compare laboratory findings among pregnant patients with SARS-CoV-2 infection by symptom status and disease severity. STUDY DESIGN: We retrospectively evaluated pregnant patients with positive SARS-CoV-2 infection, confirmed through polymerase chain reaction testing, at an urban academic US hospital between March 2020 and October 2020, performed for reported symptoms or universal screening on admission. In our hospital, all patients with SARS-CoV-2 infection were recommended to have baseline laboratory testing, including leukocyte, neutrophil, and lymphocyte counts; aspartate aminotransferase and alanine aminotransferase; high-sensitivity C-reactive protein; procalcitonin; lactate dehydrogenase; D-dimer; and ferritin. We performed multivariable logistic regression to evaluate peak laboratory abnormalities significantly associated with symptomatic SARS-CoV-2 infection and disease severity with gestational age at diagnosis, maternal age, and obesity as covariates. The sensitivity and specificity of laboratory abnormalities were calculated to identify symptomatic vs asymptomatic infection and severe to critical disease vs mild to moderate disease. RESULTS: We identified 175 pregnant patients with SARS-CoV-2 infection, of whom 100 (57%) were symptomatic; 17 (17%) of those who were symptomatic had a severe to critical disease. Laboratory data were available for 128 patients, of whom 67 (52%) were symptomatic. Compared with asymptomatic individuals, symptomatic individuals were more likely to exhibit elevated high-sensitivity C-reactive protein levels after adjusting for gestational age (adjusted odds ratio, 5.67; 95% confidence interval, 1.42-22.52; sensitivity, 81%; specificity, 43%). In symptomatic individuals, transaminitis (adjusted odds ratio, 5.67; 95% confidence interval, 1.27-25.43), elevated procalcitonin levels (adjusted odds ratio, 16.60; 95% confidence interval, 2.61-105.46), and elevated lactate dehydrogenase levels (adjusted odds ratio, 17.55; 95% confidence interval, 2.51-122.78) were independently associated with severe to critical disease rather than mild to moderate disease after adjusting for maternal age and obesity. For differentiating disease severity, sensitivity rates for transaminitis, procalcitonin elevation, and lactate dehydrogenase elevation were 47%, 87%, and 53%, respectively, whereas the specificity rates were 89%, 63%, and 90%, respectively. CONCLUSION: Inflammatory biomarkers in pregnant patients with SARS-CoV-2 infection exhibited vast heterogeneity, poor discriminative ability, and thereby limited clinical utility. Larger registry studies should evaluate which inflammatory biomarkers may be most useful for risk stratification and prognostication of pregnant patients with SARS-CoV-2 infection, taking into account the physiology of pregnancy.

Chorioamnionitis and Risk for Maternal and Neonatal Sepsis: A Systematic Review and Meta-analysis.

OBJECTIVE: To estimate the risk of maternal and neonatal sepsis associated with chorioamnionitis. DATA SOURCES: PubMed, BIOSIS, and ClinicalTrials.gov databases were systematically searched for full-text articles in English from inception until May 11, 2020. METHODS OF STUDY SELECTION: We screened 1,251 studies. Randomized controlled trials, case-control, or cohort studies quantifying a relationship between chorioamnionitis and sepsis in mothers (postpartum) or neonates born at greater than 22 weeks of gestation were eligible. Studies were grouped for meta-analyses according to exposures of histologic or clinical chorioamnionitis and outcomes of maternal or neonatal sepsis. TABULATION, INTEGRATION, AND RESULTS: One hundred three studies were included, and 55 met criteria for meta-analysis (39 studies of preterm neonates, 10 studies of general populations of preterm and term neonates, and six studies of late preterm and term neonates). Study details and quantitative data were abstracted. Random-effects models were used to generate pooled odds ratios (ORs); most studies only reported unadjusted results. Histologic chorioamnionitis was associated with confirmed and any early-onset neonatal sepsis (unadjusted pooled ORs 4.42 [95% CI 2.68-7.29] and 5.88 [95% CI 3.68-9.41], respectively). Clinical chorioamnionitis was also associated with confirmed and any early-onset neonatal sepsis (unadjusted pooled ORs 6.82 [95% CI 4.93-9.45] and 3.90 [95% CI 2.74-5.55], respectively). Additionally, histologic and clinical chorioamnionitis were each associated with higher odds of late-onset sepsis in preterm neonates. Confirmed sepsis incidence was 7% (early-onset) and 22% (late-onset) for histologic and 6% (early-onset) and 26% (late-onset) for clinical chorioamnionitis-exposed neonates. Three studies evaluated chorioamnionitis and maternal sepsis and were inconclusive. CONCLUSION: Both histologic and clinical chorioamnionitis were associated with early- and late-onset sepsis in neonates. Overall, our findings support current guidelines for preventative neonatal care. There was insufficient evidence to determine the association between chorioamnionitis and maternal sepsis. SYSTEMATIC REVIEW REGISTRATION: PROSPERO, CRD42020156812.

GestAltNet: aggregation and attention to improve deep learning of gestational age from placental whole-slide images.

The placenta is the first organ to form and performs the functions of the lung, gut, kidney, and endocrine systems. Abnormalities in the placenta cause or reflect most abnormalities in gestation and can have life-long consequences for the mother and infant. Placental villi undergo a complex but reproducible sequence of maturation across the third-trimester. Abnormalities of villous maturation are a feature of gestational diabetes and preeclampsia, among others, but there is significant interobserver variability in their diagnosis. Machine learning has emerged as a powerful tool for research in pathology. To capture the volume of data and manage heterogeneity within the placenta, we developed GestaltNet, which emulates human attention to high-yield areas and aggregation across regions. We used this network to estimate the gestational age (GA) of scanned placental slides and compared it to a baseline model lacking the attention and aggregation functions. In the test set, GestaltNet showed a higher r2 (0.9444 vs. 0.9220) than the baseline model. The mean absolute error (MAE) between the estimated and actual GA was also better in the GestaltNet (1.0847 weeks vs. 1.4505 weeks). On whole-slide images, we found the attention sub-network discriminates areas of terminal villi from other placental structures. Using this behavior, we estimated GA for 36 whole slides not previously seen by the model. In this task, similar to that faced by human pathologists, the model showed an r2 of 0.8859 with an MAE of 1.3671 weeks. We show that villous maturation is machine-recognizable. Machine-estimated GA could be useful when GA is unknown or to study abnormalities of villous maturation, including those in gestational diabetes or preeclampsia. GestaltNet points toward a future of genuinely whole-slide digital pathology by incorporating human-like behaviors of attention and aggregation.

Multi-region saliency-aware learning for cross-domain placenta image segmentation.

We propose a multi-region saliency-aware learning (MSL) method for cross-domain placenta image segmentation. Unlike most existing image-level transfer learning methods that fail to preserve the semantics of paired regions, our MSL incorporates the attention mechanism and a saliency constraint into the adversarial translation process, which can realize multi-region mappings in the semantic level. Specifically, the built-in attention module serves to detect the most discriminative semantic regions that the generator should focus on. Then we use the attention consistency as another guidance for retaining semantics after translation. Furthermore, we exploit the specially designed saliency-consistent constraint to enforce the semantic consistency by requiring the saliency regions unchanged. We conduct experiments using two real-world placenta datasets we have collected. We examine the efficacy of this approach in (1) segmentation and (2) prediction of the placental diagnoses of fetal and maternal inflammatory response (FIR, MIR). Experimental results show the superiority of the proposed approach over the state of the art.