Convolutional Neural Networks for the Evaluation of Chronic and Inflammatory Lesions in Kidney Transplant Biopsies.

In kidney transplant biopsies, both inflammation and chronic changes are important features that predict long-term graft survival. Quantitative scoring of these features is important for transplant diagnostics and kidney research. However, visual scoring is poorly reproducible and labor intensive. The goal of this study was to investigate the potential of convolutional neural networks (CNNs) to quantify inflammation and chronic features in kidney transplant biopsies. A structure segmentation CNN and a lymphocyte detection CNN were applied on 125 whole-slide image pairs of periodic acid-Schiff- and CD3-stained slides. The CNN results were used to quantify healthy and sclerotic glomeruli, interstitial fibrosis, tubular atrophy, and inflammation within both nonatrophic and atrophic tubuli, and in areas of interstitial fibrosis. The computed tissue features showed high correlation with Banff lesion scores of five pathologists (A.A., A.Dend., J.H.B., J.K., and T.N.). Analyses on a small subset showed a moderate correlation toward higher CD3+ cell density within scarred regions and higher CD3+ cell count inside atrophic tubuli correlated with long-term change of estimated glomerular filtration rate. The presented CNNs are valid tools to yield objective quantitative information on glomeruli number, fibrotic tissue, and inflammation within scarred and non-scarred kidney parenchyma in a reproducible manner. CNNs have the potential to improve kidney transplant diagnostics and will benefit the community as a novel method to generate surrogate end points for large-scale clinical studies.

Consensus based recommendations for the diagnosis of serous tubal intraepithelial carcinoma: an international Delphi study.

AIM: Reliably diagnosing or safely excluding serous tubal intraepithelial carcinoma (STIC), a precursor lesion of tubo-ovarian high-grade serous carcinoma (HGSC), is crucial for individual patient care, for better understanding the oncogenesis of HGSC, and for safely investigating novel strategies to prevent tubo-ovarian carcinoma. To optimize STIC diagnosis and increase its reproducibility, we set up a three-round Delphi study. METHODS AND RESULTS: In round 1, an international expert panel of 34 gynecologic pathologists, from 11 countries, was assembled to provide input regarding STIC diagnosis, which was used to develop a set of statements. In round 2, the panel rated their level of agreement with those statements on a 9-point Likert scale. In round 3, statements without previous consensus were rated again by the panel while anonymously disclosing the responses of the other panel members. Finally, each expert was asked to approve or disapprove the complete set of consensus statements. The panel indicated their level of agreement with 64 statements. A total of 27 statements (42%) reached consensus after three rounds. These statements reflect the entire diagnostic work-up for pathologists, regarding processing and macroscopy (three statements); microscopy (eight statements); immunohistochemistry (nine statements); interpretation and reporting (four statements); and miscellaneous (three statements). The final set of consensus statements was approved by 85%. CONCLUSION: This study provides an overview of current clinical practice regarding STIC diagnosis amongst expert gynecopathologists. The experts' consensus statements form the basis for a set of recommendations, which may help towards more consistent STIC diagnosis.

A whole-slide imaging based workflow reduces the reading time of pathologists.

Even though entirely digitized microscopic tissue sections (whole slide images, WSIs) are increasingly being used in histopathology diagnostics, little data is still available on the effect of this technique on pathologists' reading time. This study aimed to compare the time required to perform the microscopic assessment by pathologists between a conventional workflow (an optical microscope) and digitized WSIs. WSI was used in primary diagnostics at the Laboratory for Pathology Eastern Netherlands for several years (LabPON, Hengelo, The Netherlands). Cases were read either in a traditional workflow, with the pathologist recording the time required for diagnostics and reporting, or entirely digitally. Reading times were extracted from image management system log files, and the digitized workflow was fully integrated into the laboratory information system. The digital workflow saved time in the majority of case categories, with prostate biopsies saving the most (68% time gain). Taking into account case distribution, the digital workflow produced an average gain of 12.3%. Using WSI instead of conventional microscopy significantly reduces pathologists' reading times. Pathologists must work in a fully integrated environment to fully reap the benefits of a digital workflow.

Quantitative assessment of inflammatory infiltrates in kidney transplant biopsies using multiplex tyramide signal amplification and deep learning.

Delayed graft function (DGF) is a strong risk factor for development of interstitial fibrosis and tubular atrophy (IFTA) in kidney transplants. Quantitative assessment of inflammatory infiltrates in kidney biopsies of DGF patients can reveal predictive markers for IFTA development. In this study, we combined multiplex tyramide signal amplification (mTSA) and convolutional neural networks (CNNs) to assess the inflammatory microenvironment in kidney biopsies of DGF patients (n = 22) taken at 6 weeks post-transplantation. Patients were stratified for IFTA development (<10% versus ≥10%) from 6 weeks to 6 months post-transplantation, based on histopathological assessment by three kidney pathologists. One mTSA panel was developed for visualization of capillaries, T- and B-lymphocytes and macrophages and a second mTSA panel for T-helper cell and macrophage subsets. The slides were multi spectrally imaged and custom-made python scripts enabled conversion to artificial brightfield whole-slide images (WSI). We used an existing CNN for the detection of lymphocytes with cytoplasmatic staining patterns in immunohistochemistry and developed two new CNNs for the detection of macrophages and nuclear-stained lymphocytes. F1-scores were 0.77 (nuclear-stained lymphocytes), 0.81 (cytoplasmatic-stained lymphocytes), and 0.82 (macrophages) on a test set of artificial brightfield WSI. The CNNs were used to detect inflammatory cells, after which we assessed the peritubular capillary extent, cell density, cell ratios, and cell distance in the two patient groups. In this cohort, distance of macrophages to other immune cells and peritubular capillary extent did not vary significantly at 6 weeks post-transplantation between patient groups. CD163+ cell density was higher in patients with ≥10% IFTA development 6 months post-transplantation (p < 0.05). CD3+CD8-/CD3+CD8+ ratios were higher in patients with <10% IFTA development (p < 0.05). We observed a high correlation between CD163+ and CD4+GATA3+ cell density (R = 0.74, p < 0.001). Our study demonstrates that CNNs can be used to leverage reliable, quantitative results from mTSA-stained, multi spectrally imaged slides of kidney transplant biopsies.

Deep Learning-Based Histopathologic Assessment of Kidney Tissue.

BACKGROUND: The development of deep neural networks is facilitating more advanced digital analysis of histopathologic images. We trained a convolutional neural network for multiclass segmentation of digitized kidney tissue sections stained with periodic acid-Schiff (PAS). METHODS: We trained the network using multiclass annotations from 40 whole-slide images of stained kidney transplant biopsies and applied it to four independent data sets. We assessed multiclass segmentation performance by calculating Dice coefficients for ten tissue classes on ten transplant biopsies from the Radboud University Medical Center in Nijmegen, The Netherlands, and on ten transplant biopsies from an external center for validation. We also fully segmented 15 nephrectomy samples and calculated the network's glomerular detection rates and compared network-based measures with visually scored histologic components (Banff classification) in 82 kidney transplant biopsies. RESULTS: The weighted mean Dice coefficients of all classes were 0.80 and 0.84 in ten kidney transplant biopsies from the Radboud center and the external center, respectively. The best segmented class was "glomeruli" in both data sets (Dice coefficients, 0.95 and 0.94, respectively), followed by "tubuli combined" and "interstitium." The network detected 92.7% of all glomeruli in nephrectomy samples, with 10.4% false positives. In whole transplant biopsies, the mean intraclass correlation coefficient for glomerular counting performed by pathologists versus the network was 0.94. We found significant correlations between visually scored histologic components and network-based measures. CONCLUSIONS: This study presents the first convolutional neural network for multiclass segmentation of PAS-stained nephrectomy samples and transplant biopsies. Our network may have utility for quantitative studies involving kidney histopathology across centers and provide opportunities for deep learning applications in routine diagnostics.

Histological subtypes in triple negative breast cancer are associated with specific information on survival.

Much research has focused on finding novel prognostic biomarkers for triple negative breast cancer (TNBC), whereas only scattered information about the relation between histopathological features and survival in TNBC is available. This study aims to explore the prognostic value of histological subtypes in TNBC. A multicenter retrospective TNBC cohort was established from five Dutch hospitals. All non-neoadjuvantly treated, stage I-III patients with estrogen receptor, progesterone receptor and human epidermal growth factor receptor 2 negative breast cancer diagnosed between 2006 and 2014 were included. Clinical and follow-up data (overall survival; OS, relapse free survival; RFS) were retrieved and a central histopathological review was performed. Of 597 patients included (median follow up 62.8 months, median age at diagnosis 56.0 years), 19.4% developed a recurrence. The most prevalent histological subtypes were carcinoma of no special type (NST) (88.4%), metaplastic carcinoma (4.4%) and lobular carcinoma (3.4%). Collectively, tumors of special type were associated with a worse RFS and OS compared to carcinoma NST (RFS HR 1.89; 95% CI 1.18-3.03; p = 0.008; OS HR 1.94; 95% CI 1.28-2.92; p = 0.002). Substantial differences in survival, however, were present between the different histological subtypes. In the presented TNBC cohort, special histological subtype was in general associated with less favorable survival. However, within the group of tumors of special type there were differences in survival between the different subtypes. Accurate histological examination can provide specific prognostic information that may potentially enable more personalized treatment and surveillance regimes for TNBC patients.

Deep learning assisted mitotic counting for breast cancer.

As part of routine histological grading, for every invasive breast cancer the mitotic count is assessed by counting mitoses in the (visually selected) region with the highest proliferative activity. Because this procedure is prone to subjectivity, the present study compares visual mitotic counting with deep learning based automated mitotic counting and fully automated hotspot selection. Two cohorts were used in this study. Cohort A comprised 90 prospectively included tumors which were selected based on the mitotic frequency scores given during routine glass slide diagnostics. This pathologist additionally assessed the mitotic count in these tumors in whole slide images (WSI) within a preselected hotspot. A second observer performed the same procedures on this cohort. The preselected hotspot was generated by a convolutional neural network (CNN) trained to detect all mitotic figures in digitized hematoxylin and eosin (H&E) sections. The second cohort comprised a multicenter, retrospective TNBC cohort (n = 298), of which the mitotic count was assessed by three independent observers on glass slides. The same CNN was applied on this cohort and the absolute number of mitotic figures in the hotspot was compared to the averaged mitotic count of the observers. Baseline interobserver agreement for glass slide assessment in cohort A was good (kappa 0.689; 95% CI 0.580-0.799). Using the CNN generated hotspot in WSI, the agreement score increased to 0.814 (95% CI 0.719-0.909). Automated counting by the CNN in comparison with observers counting in the predefined hotspot region yielded an average kappa of 0.724. We conclude that manual mitotic counting is not affected by assessment modality (glass slides, WSI) and that counting mitotic figures in WSI is feasible. Using a predefined hotspot area considerably improves reproducibility. Also, fully automated assessment of mitotic score appears to be feasible without introducing additional bias or variability.

Using deep convolutional neural networks to identify and classify tumor-associated stroma in diagnostic breast biopsies.

The breast stromal microenvironment is a pivotal factor in breast cancer development, growth and metastases. Although pathologists often detect morphologic changes in stroma by light microscopy, visual classification of such changes is subjective and non-quantitative, limiting its diagnostic utility. To gain insights into stromal changes associated with breast cancer, we applied automated machine learning techniques to digital images of 2387 hematoxylin and eosin stained tissue sections of benign and malignant image-guided breast biopsies performed to investigate mammographic abnormalities among 882 patients, ages 40-65 years, that were enrolled in the Breast Radiology Evaluation and Study of Tissues (BREAST) Stamp Project. Using deep convolutional neural networks, we trained an algorithm to discriminate between stroma surrounding invasive cancer and stroma from benign biopsies. In test sets (928 whole-slide images from 330 patients), this algorithm could distinguish biopsies diagnosed as invasive cancer from benign biopsies solely based on the stromal characteristics (area under the receiver operator characteristics curve = 0.962). Furthermore, without being trained specifically using ductal carcinoma in situ as an outcome, the algorithm detected tumor-associated stroma in greater amounts and at larger distances from grade 3 versus grade 1 ductal carcinoma in situ. Collectively, these results suggest that algorithms based on deep convolutional neural networks that evaluate only stroma may prove useful to classify breast biopsies and aid in understanding and evaluating the biology of breast lesions.

A New Fiji-Based Algorithm That Systematically Quantifies Nine Synaptic Parameters Provides Insights into Drosophila NMJ Morphometry.

The morphology of synapses is of central interest in neuroscience because of the intimate relation with synaptic efficacy. Two decades of gene manipulation studies in different animal models have revealed a repertoire of molecules that contribute to synapse development. However, since such studies often assessed only one, or at best a few, morphological features at a given synapse, it remained unaddressed how different structural aspects relate to one another. Furthermore, such focused and sometimes only qualitative approaches likely left many of the more subtle players unnoticed. Here, we present the image analysis algorithm 'Drosophila_NMJ_Morphometrics', available as a Fiji-compatible macro, for quantitative, accurate and objective synapse morphometry of the Drosophila larval neuromuscular junction (NMJ), a well-established glutamatergic model synapse. We developed this methodology for semi-automated multiparametric analyses of NMJ terminals immunolabeled for the commonly used markers Dlg1 and Brp and showed that it also works for Hrp, Csp and Syt. We demonstrate that gender, genetic background and identity of abdominal body segment consistently and significantly contribute to variability in our data, suggesting that controlling for these parameters is important to minimize variability in quantitative analyses. Correlation and principal component analyses (PCA) were performed to investigate which morphometric parameters are inter-dependent and which ones are regulated rather independently. Based on nine acquired parameters, we identified five morphometric groups: NMJ size, geometry, muscle size, number of NMJ islands and number of active zones. Based on our finding that the parameters of the first two principal components hardly correlated with each other, we suggest that different molecular processes underlie these two morphometric groups. Our study sets the stage for systems morphometry approaches at the well-studied Drosophila NMJ.

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer.

Importance: Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Objective: Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting. Design, Setting, and Participants: Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Exposures: Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. Main Outcomes and Measures: The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. Results: The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC). Conclusions and Relevance: In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

Contribution of Histopathologic Tissue Composition to Quantitative MR Spectroscopy and Diffusion-weighted Imaging of the Prostate.

PURPOSE: To determine associations of metabolite levels derived from magnetic resonance (MR) spectroscopic imaging (ie, hydrogen 1 [(1)H] MR spectroscopic imaging) and apparent diffusion coefficients (ADCs) from diffusion-weighted imaging with prostate tissue composition assessed by digital image analysis of histologic sections. MATERIALS AND METHODS: Institutional ethical review board approved this retrospective study and waived informed consent. Fifty-seven prostate cancer patients underwent an MR examination followed by prostatectomy. One hematoxylin and eosin-stained section of the resected prostate per patient was digitized and computationally segmented into nuclei, lumen, and combination of epithelial cytoplasm and stroma. On each stained section, regions of interest (ROIs) were chosen and matched to the corresponding ADC map and (1)H MR spectroscopic imaging voxels. ADC and two metabolite ratios (citrate [Cit], spermine [Spm], and creatine [Cr] to choline [Cho] and Cho to Cr plus Spm) were correlated with percentage areas of nuclei, lumen, and cytoplasm and stroma for peripheral zone (PZ), transition zone (TZ), and tumor tissue in both zones of the prostate by using a linear mixed-effect model and Spearman correlation coefficient (ρ). RESULTS: ADC and (Cit + Spm + Cr)/Cho ratio showed positive correlation with percentage area of lumen (ρ = 0.43 and 0.50, respectively) and negative correlation with percentage area of nuclei (ρ = -0.29 and -0.26, respectively). The Cho/(Cr + Spm) ratio showed negative association with percentage area of lumen (ρ = -0.40) and positive association with area of nuclei (ρ = 0.26). Percentage areas of lumen and nuclei, (Cit + Spm + Cr)/Cho ratio, and ADC were significantly different (P < .001) between benign PZ (23.7 and 7.7, 8.83, and 1.58 × 10(-3) mm(2)/sec, respectively) and tumor PZ tissue (11.4 and 12.5, 5.13, and 1.20 × 10(-3) mm(2)/sec, respectively). These parameters were also significantly different between benign TZ (20.0 and 8.2, 6.50, and 1.26 × 10(-3) mm(2)/sec, respectively) and tumor TZ tissue (9.8 and 11.2, 4.36, and 1.03 × 10(-3) mm(2)/sec, respectively). CONCLUSION: The observed correlation of (Cit + Spm + Cr)/Cho ratio and ADC of the prostate with its tissue composition indicates that components of this composition, such as percentage luminal area, contribute to the value of these MR parameters.

Liver parenchyma at the site of hypodense parafissural pseudolesion contains increased collagen.

PURPOSE: To identify a histological substrate explaining the hypodense pseudolesion in the liver at the right side of the falciform ligament and the correlation with CT radiodensity. MATERIALS AND METHODS: Tissue specimens were obtained from the right (pseudolesion) and left (control) side of the falciform ligament at the level of the left portal vein, in deceased adults during autopsy. Radiodensity was measured at the same locations at CT. Digital image analysis determined the amount of collagen and fat in histological sections, and the number of portal triads and central veins were counted. Glycogen content was visually assessed by the area percentage of the histological section. RESULTS: Specimens from 17 patients showed a 39% increase in collagen for the site of the pseudolesion compared to the contralateral side (p = 0.08). No significant differences were found for the amount of fat, glycogen, portal triads, or central veins. In one patient a pseudolesion was visible on CT, and this contained 52% more collagen than the control side. CONCLUSION: The pseudolesion at the right parafissural side in the liver contains more collagen compared to the control left side, while there is no difference in fat or glycogen content or number of portal and hepatic veins. Collagen may be the cause of the pseudolesion.

Correlation between dynamic contrast-enhanced MRI and quantitative histopathologic microvascular parameters in organ-confined prostate cancer.

OBJECTIVES: To correlate pharmacokinetic parameters of 3-T dynamic contrast-enhanced (DCE-)MRI with histopathologic microvascular and lymphatic parameters in organ-confined prostate cancer. METHODS: In 18 patients with unilateral peripheral zone (pT2a) tumours who underwent DCE-MRI prior to radical prostatectomy (RP), the following pharmacokinetic parameters were assessed: permeability surface area volume transfer constant (K (trans)), extravascular extracellular volume (Ve) and rate constant (K ep). In the RP sections blood and lymph vessels were visualised immunohistochemically and automatically examined and analysed. Parameters assessed included microvessel density (MVD), area (MVA) and perimeter (MVP) as well as lymph vessel density (LVD), area (LVA) and perimeter (LVP). RESULTS: A negative correlation was found between age and K (trans) and K ep for tumour (r = -0.60, p = 0.009; r = -0.67, p = 0.002) and normal (r = -0.54, p = 0.021; r = -0.46, p = 0.055) tissue. No correlation existed between absolute values of microvascular parameters from histopathology and DCE-MRI. In contrast, the ratio between tumour and normal tissue (correcting for individual microvascularity variations) significantly correlated between K ep and MVD (r = 0.61, p = 0.007) and MVP (r = 0.54, p = 0.022). The lymphovascular parameters showed only a correlation between LVA and K ep (r = -0.66, p = 0.003). CONCLUSIONS: Significant correlations between DCE-MRI and histopathologic parameters were found when correcting for interpatient variations in microvascularity. KEY POINTS: • Normal prostate tissue shows strong heterogeneity in microvascularity. • Peripheral zone prostate cancer shows increased and less heterogeneous microvascularity. • Normal and tumour tissue shows considerable variation in microvascularity between patients. • DCE-MRI should take into account the interprostatic heterogeneity of microvasculature between patients.

Microvascularity in transition zone prostate tumors resembles normal prostatic tissue.

BACKGROUND: The objective of this study was comparison of characteristics of the microvasculature in transition zone tumor (TZT) and benign nodular hyperplasia (BPH) with normal prostatic transition zone (NTZ), applying accurate and objective quantification based on digital image analysis. Results of this study may increase understanding of prostate dynamic contrast enhanced (DCE) MRI analysis. METHODS: Radical prostatectomy specimens of 28 patients containing TZT ranging from pT2-pT4 were used. In 11 patients a concomitant peripheral zone tumor (PZT) was present. Microvessels were visualized by CD31 immunohistochemistry. Specimens were scanned using a computer-controlled microscope with automatic recognition of microvessels. Pseudocolor maps were produced displaying microvessel density, perimeter, and area of an entire prostate transection. Mean, 75th percentile (p75) and coefficient of variation (CV) were calculated automatically in manually indicated areas of the tumor and corresponding contralateral normal tissue, and BPH. RESULTS: Large variability was seen in TZT microvascular parameters, indicating presence of patients having both hypo and hypervascularized tumors compared to NTZ. In contrast, areas of BPH showed a more consistent increase in vascular parameters, with decreased CV. Analysis of PZT confirmed results of our previous study, with mean and p75 of all vascular parameters being significantly increased and a decrease in CV. No correlation was found for clinicopathological parameters and microvascular parameters. CONCLUSION: Microvasculature of transition zone tumor showed increased heterogeneity compared to BPH and peripheral zone tumors, possibly explaining the difficulty of TZT detection on DCE-MRI.

The evaluation of colon biopsies using virtual microscopy is reliable.

AIMS: Virtual microscopy offers major advantages for pathology practice, separating slide evaluation from slide production. The aim of this study was to investigate the reliability of using whole slide images as compared with routine glass slides for diagnostic purposes. METHODS AND RESULTS: Colon biopsies (n = 295) were assessed using both glass slides and whole slide images by four pathologists and two residents. Two pathologists scored the digital images of biopsies in a primary diagnostic setting. For each case, the consensus diagnosis was defined as the majority diagnosis on the study's glass slides. All diagnoses were grouped into seven main diagnostic categories, and further divided into subgroups. The overall concordance rates were 89.6% for whole slide images and 91.6% for light microscopy. The concordance rates of the subgroups 'adenoma' and 'adenocarcinoma' between whole slide images and conventional microscopy showed only small variability. The intraobserver (whole slide images versus glass slide) agreement, including subgroups, was substantial, with a mean κ-value of 0.78, and was higher than the interobserver agreement for glass slides (interobserver κ-value of 0.69). CONCLUSIONS: This study shows good diagnostic accuracy and reproducibility for virtual microscopy, indicating that this technology can reliably be used for pathological evaluation of colon biopsies in a primary clinical setting.

Pathologists' first opinions on barriers and facilitators of computational pathology adoption in oncological pathology: an international study.

Computational pathology (CPath) algorithms detect, segment or classify cancer in whole slide images, approaching or even exceeding the accuracy of pathologists. Challenges have to be overcome before these algorithms can be used in practice. We therefore aim to explore international perspectives on the future role of CPath in oncological pathology by focusing on opinions and first experiences regarding barriers and facilitators. We conducted an international explorative eSurvey and semi-structured interviews with pathologists utilizing an implementation framework to classify potential influencing factors. The eSurvey results showed remarkable variation in opinions regarding attitude, understandability and validation of CPath. Interview results showed that barriers focused on the quality of available evidence, while most facilitators concerned strengths of CPath. A lack of consensus was present for multiple factors, such as the determination of sufficient validation using CPath, the preferred function of CPath within the digital workflow and the timing of CPath introduction in pathology education. The diversity in opinions illustrates variety in influencing factors in CPath adoption. A next step would be to quantitatively determine important factors for adoption and initiate validation studies. Both should include clear case descriptions and be conducted among a more homogenous panel of pathologists based on sub specialization.

Deep learning based tumor-stroma ratio scoring in colon cancer correlates with microscopic assessment.

Background: The amount of stroma within the primary tumor is a prognostic parameter for colon cancer patients. This phenomenon can be assessed using the tumor-stroma ratio (TSR), which classifies tumors in stroma-low (≤50% stroma) and stroma-high (>50% stroma). Although the reproducibility for TSR determination is good, improvement might be expected from automation. The aim of this study was to investigate whether the scoring of the TSR in a semi- and fully automated method using deep learning algorithms is feasible. Methods: A series of 75 colon cancer slides were selected from a trial series of the UNITED study. For the standard determination of the TSR, 3 observers scored the histological slides. Next, the slides were digitized, color normalized, and the stroma percentages were scored using semi- and fully automated deep learning algorithms. Correlations were determined using intraclass correlation coefficients (ICCs) and Spearman rank correlations. Results: 37 (49%) cases were classified as stroma-low and 38 (51%) as stroma-high by visual estimation. A high level of concordance between the 3 observers was reached, with ICCs of 0.91, 0.89, and 0.94 (all P < .001). Between visual and semi-automated assessment the ICC was 0.78 (95% CI 0.23-0.91, P-value 0.005), with a Spearman correlation of 0.88 (P < .001). Spearman correlation coefficients above 0.70 (N=3) were observed for visual estimation versus the fully automated scoring procedures. Conclusion: Good correlations were observed between standard visual TSR determination and semi- and fully automated TSR scores. At this point, visual examination has the highest observer agreement, but semi-automated scoring could be helpful to support pathologists.

Automated measurement of MIB-1 positive area as an alternative to counting in follicular lymphoma.

Manual counting of MIB-1 positive cells which has been suggested as an alternative to centroblast counting for the diagnostic grading of follicular lymphoma is a laborious task. In this study, the validity of automated measurement of the MIB-1 positive area is analyzed as an alternative approach. Archival MIB-1 stained tissue sections of 15 follicular lymphomas were assessed manually and automatically by three independent observers. Concordance correlation coefficients and coefficients of variation were calculated to study reproducibility and variability of both methods and to compare result from both methods. A good concordance was observed between the two methods. The reproducibility of the automated method was slightly better than the manual counting of positive nuclei. Measurement of MIB-1 positive surface area may be used as a simple and fast alternative to tedious manual counting of positive nuclei as a potential help in follicular lymphoma grading.

Tubal epithelial lesions in salpingo-oophorectomy specimens of BRCA-mutation carriers and controls.

OBJECTIVE: A precursor lesion for ovarian carcinoma, tubal intraepithelial carcinoma (TIC), has been identified in BRCA-mutation carriers undergoing prophylactic bilateral salpingo-oophorectomy (pBSO). Other lesions were also identified in fallopian tubes, but different terminology, interpretation, and lack of knowledge of normal epithelium, have hampered to unravel their possible role in carcinogenesis. The aim of this study is to classify tubal epithelial lesions in BRCA-mutation carriers and controls to enable comparison of prevalence, area of localization, and possible malignant potential. METHODS: Two hundred twenty-six BRCA1/2-mutation carriers were included; ovaries and fallopian tubes, embedded completely, were reviewed. Controls included 105 women who underwent BSO for non-malignant reasons. Tubal epithelial lesions included the following categories: hyperplasia, minor epithelial atypia, TIC, and invasive carcinoma. RESULTS: Tubal neoplasia was identified in 7.1% (invasive carcinoma, 0.9%; TIC, 6.2%) of BRCA-mutation carriers compared to none in controls (p=0.004, Fisher's exact test). Hyperplasia and minor epithelial atypia were identified in 41.6% BRCA-mutation carriers and compared to 58.1% in controls (p=0.005, Pearson's chi square). Invasive carcinoma and TIC showed preference for the fimbrial ends (p=0.027, Pearson's chi square), while hyperplasia and minor epithelial atypia displayed more variation in localization. CONCLUSIONS: Invasive tubal carcinoma and TIC were limited to BRCA-mutation carriers, whereas hyperplasia and minor epithelial atypia were commonly found in both BRCA-mutation carriers and controls. It is suggested that hyperplasia and minor atypia represent variations of normal tubal epithelium instead of premalignant lesions. Furthermore, total salpingectomy is strongly recommended as most but not all TIC occurred in the fimbriae.

Concurrent endometrial intraepithelial carcinoma (EIC) and serous ovarian cancer: can EIC be seen as the precursor lesion?

OBJECTIVE: The pathogenesis of serous ovarian carcinoma (SOC) is still unknown. Recently, endometrial intraepithelial carcinoma (EIC) was proposed to be the precursor lesion of SOC. This study examines the model of EIC as precursor for SOC. METHODS: Cases of SOC with a noninvasive or superficially invasive serous lesion, a hyperplastic lesion with/without atypia, or EIC in the endometrium were selected for inclusion in this study. Tissue sections from both ovaries, the fallopian tubes, and the uterus were extensively reviewed by an expert gynecopathologist. For both EIC and SOC, immunostaining for p53, Ki-67, estrogen receptor, and progesterone receptor; TP53 mutation analysis; and in situ ploidy analysis were performed. RESULTS: Nine cases of SOC with concurrent EIC in the endometrium were identified. Immunostaining for p53, Ki-67, estrogen receptor, and progesterone receptor revealed almost identical expression patterns and similar intensities in each pair of EIC and coincident SOC. Identical TP53 mutations were found in SOC and coinciding EIC in 33% of the cases, suggesting a clonal origin. DNA ploidy analysis, as a marker for neoplastic progression, demonstrated an increased number of aneuploid nuclei in SOC compared to their corresponding EIC (P = 0.039). In addition, the mean amount of DNA per nucleus in SOC was higher (ie, more aneuploid) compared to EIC (P = 0.039). CONCLUSION: This study provides a first indication of EIC as possible precursor lesion for SOC. This finding could have major clinical implications for future ovarian cancer management and underscores EIC as a possible target for early SOC detection and prevention.