Search

Simple Summary: This study introduces a deep learning model designed to predict the 5-year recurrence risk of lung adenocarcinoma based on histopathology images. Using a dataset of 189 patients with 455 histopathology slides, our model demonstrated superior performance in risk stratification, achieving a hazard ratio of 2.29 (95% CI: 1.69–3.09, p < 0.005). This outperforms several existing deep learning methods, showcasing the potential of deep learning in automatically predicting lung adenocarcinoma recurrence risk. The superior performance of this model underscores the potential for deep learning models to be integrated into clinical workflows for more accurate and automated risk assessment in lung adenocarcinoma. This could lead to more personalized treatment strategies and better patient outcomes. Lung cancer is the leading cause of cancer-related death in the United States. Lung adenocarcinoma (LUAD) is one of the most common subtypes of lung cancer that can be treated with resection. While resection can be curative, there is a significant risk of recurrence, which necessitates close monitoring and additional treatment planning. Traditionally, microscopic evaluation of tumor grading in resected specimens is a standard pathologic practice that informs subsequent therapy and patient management. However, this approach is labor-intensive and subject to inter-observer variability. To address the challenge of accurately predicting recurrence, we propose a deep learning-based model to predict the 5-year recurrence of LUAD in patients following surgical resection. In our model, we introduce an innovative dual-attention architecture that significantly enhances computational efficiency. Our model demonstrates excellent performance in recurrent risk stratification, achieving a hazard ratio of 2.29 (95% CI: 1.69–3.09, p < 0.005), which outperforms several existing deep learning methods. This study contributes to ongoing efforts to use deep learning models for automatically learning histologic patterns from whole slide images (WSIs) and predicting LUAD recurrence risk, thereby improving the accuracy and efficiency of treatment decision making. [ABSTRACT FROM AUTHOR]

Surgical pathology of the head and neck is one of the more challenging areas in all of diagnostic pathology. Its unparalleled diversity and complexity renders it highly vulnerable to diagnostic error compelling unconstrained access to specialized diagnostic expertise. Digital pathology (DP) is a state-of-the-art tool that could facilitate access to specialized expertise, but it is relatively untested in the context of pathology consultations. In a collaboration between Labcorp Dianon and a large academic hospital with subspecialized surgical pathology, DP was implemented to provide the pathology community access to head and neck pathology expertise. From this collaborative experience, glass slides from consecutive consult cases that had been previously diagnosed using DP were reviewed by an expert consultant in a blinded manner following an extended wash-out period. The intraobserver discrepancy rate was recorded. Major discrepancies were defined as those resulting in significant impact on clinical management and/or prognosis, whereas minor discrepancies were those with no impact on care or prognosis. Slides from 57 cases were available for review. The average wash-out period was 19 months. Five discrepancies were recorded (intraobserver concordance rate of 91%). All discrepancies were minor (major discrepancy rate, 0%; minor discrepancy rate, 9%). On appraisal of the discrepant cases, discordant diagnoses were attributed to subjective differences in interpretation rather than objective differences related to the inferiority of DP. DP decreased the median turnaround time by 97% (from 70 h 26 min to 2 h 25 min). DP provides efficient and fast access to expert consultants. The speed of case delivery does not compromise diagnostic precision. Discrepancies are uncommon, minor, and reflect subjective interpretative differences inherent to difficult and ambiguous head and neck cases, and not the inferiority of DP as a diagnostic platform. High concordance can be achieved even for those difficult and complex cases that are concentrated in the consultation practice. This observation carries profound implications regarding universal health care access to specialized diagnostic expertise. [ABSTRACT FROM AUTHOR]

This study aims to investigate the impact of virtual microscopy (VM) and light microscopy (LM) on the satisfaction of second-year medical students and how they affect student performance in different educational settings. The research involved 94 second-year students from Izmir Democracy University's School of Medicine, with criteria requiring enrollment in the 2021–2022 academic year and attendance of at least 80% in histology practical course. A paired two-tailed t-test was used for comparison, with a researcher-designed questionnaire for data collection. Cronbach's alpha was 0.894 for the LM questionnaire, and 0.918 for the VM questionnaire, indicating high level of reliability. LM scored higher in the questionnaire (p = 0.010), but VM showed higher exam averages (p = 0.013). The study found VM more effective in exams, with students showing high satisfaction with LM. VM's accessibility to histological preparations and its impact on learning levels and board exam success rates were noted. The study concludes that while VM is becoming essential in histology education due to its positive impact on exam performance and accessibility, LM remains highly valued by students for its hands-on experience and satisfaction levels. [ABSTRACT FROM AUTHOR]

As a part of modern technological environments, virtual microscopy enriches histological learning, with support from large institutional investments. However, existing literature does not supply empirical evidence of its role in improving pedagogy. Virtual microscopy provides fresh opportunities for investigating user behavior during the histology learning process, through digitized histological slides. This study establishes how students' perceptions and user behavior data can be processed and analyzed using machine learning algorithms. These also provide predictive data called learning analytics that enable predicting students' performance and behavior favorable for academic success. This information can be interpreted and used for validating instructional designs. Data on the perceptions, performances, and user behavior of 552 students enrolled in a histology course were collected from the virtual microscope, Cytomine®. These data were analyzed using an ensemble of machine learning algorithms, the extra‐tree regression method, and predictive statistics. The predictive algorithms identified the most pertinent histological slides and descriptive tags, alongside 10 types of student behavior conducive to academic success. We used these data to validate our instructional design, and align the educational purpose, learning outcomes, and evaluation methods of digitized histological slides on Cytomine®. This model also predicts students' examination scores, with an error margin of <0.5 out of 20 points. The results empirically demonstrate the value of a digital learning environment for both students and teachers of histology. [ABSTRACT FROM AUTHOR]

Context.--In the United States, review of digital whole slide images (WSIs) using specific systems is approved for primary diagnosis but has not been implemented for intraoperative consultation. Objective.--To evaluate the safety of review of WSIs and compare the efficiency of review of WSIs and glass slides (GSs) for intraoperative consultation. Design.--Ninety-one cases previously submitted for frozen section evaluation were randomly selected from 8 different anatomic pathology subspecialties. GSs from these cases were scanned on a Leica Aperio AT2 scanner at X20 magnification (0.25 μm/pixel). The slides were deidentified, and a short relevant clinical history was provided for each slide. Nine board-certified general pathologists who do not routinely establish primary diagnoses using WSIs reviewed the WSIs using Leica Aperio ImageScope viewing software. After a washout period of 2--3 weeks, the pathologists reviewed the corresponding GSs using a light microscope (Olympus BX43). The pathologists recorded the diagnosis and time to reach the diagnosis. Intraobserver concordance, time to diagnosis, and specificity and sensitivity compared to the original diagnosis were evaluated. Results.--The rate of intraobserver concordance between GS results andWSI results was 93.7%. Mean time to diagnosis was 1.25 minutes for GSs and 1.76 minutes for WSIs (P < .001). Specificity was 91% for GSs and 90% for WSIs; sensitivity was 92% for GSs and 92% for WSIs. Conclusions.--Time to diagnosis was longer with WSIs than with GSs, and scanning GSs and uploading the data to whole slide imaging systems takes time. However, review of WSIs appears to be a safe alternative to review of GSs. Use of WSIs allows reporting from a remote site during a public health emergency such as the COVID-19 pandemic and facilitates subspecialty histopathology services. [ABSTRACT FROM AUTHOR]

Introduction. Digital microscopy transformation, the basis for the virtual microscopy applications, is a challenge but also a requirement in modern Medical Education. This paper presents the scope, background, methods, and results of the project "Digital Transformation of Histology and Histopathology by Virtual Microscopy (VM) for an Innovative Medical School Curriculum", VM3.0, funded by the European Union under the Erasmus+ framework (ref.no.2022-1-RO01-KA220-HED-000089017). The project was initiated at Grigore T. Popa University of Medicine and Pharmacy, Iași, Romania, with the support of Euroed Foundation, Iași, and cooperation of University partners from Gdansk (Poland), Plovdiv (Bulgaria), Alicante (Spain), and Patras (Greece) aimed to implement digital histology and histopathology teaching in a common network. Materials and methods. The backbone of the project was the development of a Digital Slide Platform based on the scans of histological slides collected from all the partners of the participating universities and the creation of a simple and fast digital/internet communication tool that could be used to improve histology and histopathology teaching of medical and natural sciences students. The construction of a Virtual Microscopy Library (VML) has been based on the acquisition of whole scans of high-quality histological slides stained by hematoxylin and eosin (H&E) and other classical staining methods and description of various organs' details in English as well as respective languages of the project's partners. The VML can be used for different approches, both for students' instruction in classes as well as for individual students' work and self-testing. Universities from other countries could use the modal structure of the developed VML system on the condition that more slides are provided and the implementation of national language(s) is implemented. Conclusions. The combined efforts of all university partners allowed to establish the dynamic low-cost virtual microscopy educational system. The VM system could help unify the standards of cytology, histology, and histopathology teaching in a quest for the digital transformation of the European educational system. [ABSTRACT FROM AUTHOR]

This study aims to investigate the impact of virtual microscopy (VM) and light microscopy (LM) on the satisfaction of second-year medical students and how they affect student performance in different educational settings. The research involved 94 second-year students from Izmir Democracy University’s School of Medicine, with criteria requiring enrollment in the 2021–2022 academic year and attendance of at least 80% in histology practical course. A paired two-tailed t-test was used for comparison, with a researcher-designed questionnaire for data collection. Cronbach’s alpha was 0.894 for the LM questionnaire, and 0.918 for the VM questionnaire, indicating high level of reliability. LM scored higher in the questionnaire (p = 0.010), but VM showed higher exam averages (p = 0.013). The study found VM more effective in exams, with students showing high satisfaction with LM. VM’s accessibility to histological preparations and its impact on learning levels and board exam success rates were noted. The study concludes that while VM is becoming essential in histology education due to its positive impact on exam performance and accessibility, LM remains highly valued by students for its hands-on experience and satisfaction levels.

Context.--Digital pathology using whole slide images has been recently approved to support primary diagnosis in clinical surgical pathology practices. Here we describe a novel imaging method, fluorescence-imitating bright-field imaging, that can capture the surface of fresh tissue without requiring prior fixation, paraffin embedding, tissue sectioning, or staining. Objective.--To compare the ability of pathologists to evaluate direct-to-digital images with standard pathology preparations. Design.--One hundred surgical pathology samples were obtained. Samples were first digitally imaged, then processed for standard histologic examination on 4-lm hematoxylin-eosin-stained sections and digitally scanned. The resulting digital images from both digital and standard scan sets were viewed by each of 4 reading pathologists. The data set consisted of 100 reference diagnoses and 800 study pathologist reads. Each study read was compared to the reference diagnosis, and also compared to that reader's diagnosis across both modalities. Results.--The overall agreement rate, across 800 reads, was 97.9%. This consisted of 400 digital reads at 97.0% versus reference and 400 standard reads versus reference at 98.8%. Minor discordances (defined as alternative diagnoses without clinical treatment or outcome implications) were 6.1% overall, 7.2% for digital, and 5.0% for standard. Conclusions.--Pathologists can provide accurate diagnoses from fluorescence-imitating brightfield imaging slide-free images. Concordance and discordance rates are similar to published rates for comparisons of whole slide imaging to standard light microscopy of glass slides for primary diagnosis. It may be possible, therefore, to develop a slide-free, nondestructive approach for primary pathology diagnosis. [ABSTRACT FROM AUTHOR]

Objectives: To compare volumetric wear of lithium disilicate against different ceramic (3 mol% yttria‐stabilized (3Y) zirconia, 5 mol% yttria‐stabilized (5Y) zirconia, lithium disilicate, porcelain and enamel antagonists). Materials and Methods: Forty lithium disilicate (e.max CAD) specimens (n = 8/antagonist) were wet sanded to 1200grit SiC and mounted into a UAB wear device. Antagonist spheres (diameter = 4.75 mm) were made from polished 3Y zirconia, 5Y zirconia, lithium disilicate, porcelain and human enamel. A two‐body wear test was performed with 20 N load and 1.5 mm slide for 400,000 cycles at 1 Hz. 33% glycerin was used as a lubricant. Wear facets were measured with optical profilometry. Wear scar areas of antagonists were measured with digital microscopy. Scanning electron microscopy was performed on wear facets and scars. Vicker's microhardness was measured of all antagonist materials. All data were compared with 1‐way ANOVA and Tukey post‐hoc analysis. Results: Significant differences in lithium disilicate volumetric wear (mm3) occurred with various antagonist materials: 0.38 ± 0.01a (3Y zirconia), 0.33 ± 0.01b, (5Y zirconia), 0.16 ± 0.01c (lithium disilicate), 0.11 ± 0.03d, (enamel), and 0.07 ± 0.01e (porcelain). The lithium disilicate antagonist demonstrated a larger wear scar than other materials. Zirconia was the hardest material and enamel the least hard. Conclusions: Zirconia causes significant wear on lithium disilicate and lithium disilicate causes significant wear against itself. Clinical Significance: When selecting a material to oppose an existing lithium disilicate crown, a porcelain or lithium disilicate surface would cause significantly less wear to the existing crown. If an existing zirconia crown exists opposed to a prepared tooth, lithium disilicate may not be an ideal material selection to restore the tooth. [ABSTRACT FROM AUTHOR]

This study, with its potential to significantly impact the field of medical education, is a testament to the active participation and invaluable contributions of a cohort of 59 first-year medical students. These students, the future of medical practice, shared their perspectives on two distinct methods of learning microscopic anatomy— traditional glass slide and microscope-based lessons versus online microscopical anatomy lessons employing the virtual slides in the Histology Guide website. They attended traditional microscopic anatomy lessons using a histology glass slide and a light microscope; the same group attended online lessons using virtual slides. Their feedback was gathered through a comprehensive questionnaire of 27 questions, which assessed effectiveness, convenience, engagement, and overall preference. Our quantitative and qualitative results clearly show that the same students who attended both the in-person and distance microscopic anatomy labs, while appreciating the usefulness and effectiveness of the two types of experiences, significantly prefer the in-person microscopic anatomy labs, judging the latter to be more interactive, due to the possibility of being able to directly use an optical microscope and slides containing histological preparations and the opportunity to work in groups with other students, being able to interact directly with the lecturer in the classroom. The remote experience of the light microscopy lab also allowed them to access it at their preferred times and review the lab several times during their available time. As reflected in the findings, these students’ preferences and perceptions regarding these contrasting educational modalities offer insights crucial for refining anatomy teaching practices in medical education. [ABSTRACT FROM AUTHOR]

In cytopathology education, Virtual Microscopy e-learning modules (VM-eLM) have achieved remarkable results in the improvement and personalization of learning. However, it remains to be determined whether these modules can significantly contribute to improving the accuracy of cytological diagnosis. The aim of this work was to create a VM-eLM for gynecologic cytopathology education designed to improve screening and interpretation skills in two groups of cytologists: experienced and nonexperienced. The module was designed in Moodle with both Whole Slide Images and Static Images taken from Papanicolaou smears that were diagnosed as: negative for intraepithelial lesion, low-grade squamous intraepithelial lesion, high-grade squamous intraepithelial lesion, squamous cell carcinoma, or adenocarcinoma. We assessed the effectiveness of the module using 1) clinical quality indicators to measure skill development and 2) a user survey. After training, participants significantly improved their cytological screening skills, decreasing their false negative diagnosis by 78% in the non-experienced group and eliminating them entirely in the experienced group. Nonexperienced participants also significantly increased their recognition of low-grade squamous intraepithelial lesion and high-grade squamous intraepithelial lesion by 31% and 50%, respectively. Participants positively evaluated the module, highlighting its novelty, the possibility to train remotely, the immediate feedback and the quality of the Whole Slide Images. We designed, implemented and tested a VM-eLM for Gynecologic Cytopathology Education that improved cytological screening skills for both non-experienced and experienced cytologists, also increasing the diagnostic accuracy of preinvasive lesions by less experienced cytologists. The module was positively evaluated by participants, who perceived an improvement in their interpretive skills. [Display omitted] • We designed, implemented, and tested a virtual microscopy E-learning module for cytopathology education. • Participants with different expertise levels reduced their false negative diagnosis. • Non-experienced participants also increased their recognition of preinvasive lesions. • Participants with lower initial performance from both groups particularly enhance their overall performance level. • Participants engage with the module and perceive an improvement in their skills. [ABSTRACT FROM AUTHOR]

Coronavirus disease 2019 (COVID-19) has influenced the dental education in Osaka Dental University. The purpose of this study was to summarize the impact of COVID-19 on student performance and the current more appropriate teaching methods by comparing the changes in various oral pathology exam results before and after COVID-19. The experimental and control groups consisted of second year students in the department of dentistry at our university for the years 2019 (136 people) and 2020 (125 people). The impact of different teaching methods on student performance was compared by calculating the mean scores and percentage of failures on various exams and whether or not class credits were earned between the two years. A t test was used to determine statistical significance. The mean scores on the mini-tests were lower in 2020 than in 2019, while the average score of the intermediate exam and the number of students receiving class credits were higher. The mean scores on the practical and unit exams were not statistically significant between the years, but the failure rate on both exams was higher in 2019 than in 2020. COVID-19 had impacts on student performance. A comparison of the mean scores on the exams revealed that the use of microscopy, oral questions, and online animations contributed to improved performance on different exams. Therefore, to promote students' understanding and retention of memorized knowledge of oral pathology, the use of microscopes will be resumed whenever possible, as well as continuation with oral questions and online animations. [ABSTRACT FROM AUTHOR]

Recent advancements in Digital Pathology (DP) have empowered pathologists to provide more accurate diagnosis through digital means. Whole-slide Imaging (WSI) technology has enabled the digital scanning, representation, and preservation of numerous tissue slides, while Artificial Intelligence (AI), image analysis, and Machine Learning (ML) have enhanced disease diagnosis accuracy. There is a growing acceptance of the transition from traditional glass slide histopathological diagnosis to AI-assisted diagnosis using digital slides, driven by the substantial data accumulation that demands computer-aided analysis. Maximising the potential of AI breakthroughs in DP is critical, offering significant research opportunities across related fields. DP offers significant potential for telepathology, second opinions, and educational purposes. Additionally, it presents substantial research opportunities in image computing due to its vast reservoir of data. Pathologists have discerned characteristics beyond the naked eye’s perception by analysing “sub-visual” images using DP. The flexibility of workflow provided by DP will be the main reason for its widespread adaptation and acceptance. DP also has the potential to be an essential tool to maintain operations of the pathology department in case of public health emergencies, which will streamline, fast-track, and improve patient care. Given the expanding accessibility and prevalence of the internet, it is crucial to develop innovations like DP. This technology catalyses enhancing patient care, opening avenues for further advancements in healthcare delivery. The purpose of present review was to bring to light the great potential that DP encompasses to improve diagnosis and treatment planning, which will ultimately lead to better patient care. However, integrating DP systems necessitates collaboration from various stakeholders beyond the Pathology Department. Despite evident advantages, several challenges must be addressed for the successful implementation and mass acceptance. Therefore, this narrative review aimed to illuminate the substantial potential inherent in DP for enhancing both diagnosis and treatment planning processes, consequently fostering improvements in patient care and also understanding DP, highlighting its challenges and opportunities. It also delves into the role of AI, image analysis, and ML in aiding disease diagnosis and reporting. With social distancing measures in place during the Coronavirus Disease -2019 (COVID-19) pandemic, pathologists were able to remotely access and analyse DP images, further cementing the importance of DP in current scenarios.

Simple Summary: The pathologic diagnosis of primary and secondary liver cancers can often be difficult. Artificial intelligence (AI) presents potential solutions to these difficulties by aiding in the histopathological diagnosis of tumors using digital whole slide images (WSIs). We developed an AI diagnostic assistant using a deep learning model for distinguishing hepatocellular carcinoma, cholangiocarcinoma, and metastatic colorectal cancer using WSIs. Overall, the classifiers were highly accurate, showing significant potential for improving liver cancer diagnosis and advancing precision medicine. However, additional research is required to further refine and validate these promising tools. Diagnosing primary liver cancers, particularly hepatocellular carcinoma (HCC) and cholangiocarcinoma (CC), is a challenging and labor-intensive process, even for experts, and secondary liver cancers further complicate the diagnosis. Artificial intelligence (AI) offers promising solutions to these diagnostic challenges by facilitating the histopathological classification of tumors using digital whole slide images (WSIs). This study aimed to develop a deep learning model for distinguishing HCC, CC, and metastatic colorectal cancer (mCRC) using histopathological images and to discuss its clinical implications. The WSIs from HCC, CC, and mCRC were used to train the classifiers. For normal/tumor classification, the areas under the curve (AUCs) were 0.989, 0.988, and 0.991 for HCC, CC, and mCRC, respectively. Using proper tumor tissues, the HCC/other cancer type classifier was trained to effectively distinguish HCC from CC and mCRC, with a concatenated AUC of 0.998. Subsequently, the CC/mCRC classifier differentiated CC from mCRC with a concatenated AUC of 0.995. However, testing on an external dataset revealed that the HCC/other cancer type classifier underperformed with an AUC of 0.745. After combining the original training datasets with external datasets and retraining, the classification drastically improved, all achieving AUCs of 1.000. Although these results are promising and offer crucial insights into liver cancer, further research is required for model refinement and validation. [ABSTRACT FROM AUTHOR]

Background: After a series of standardized reporting systems in cytopathology, the Sydney system was recently introduced to address the need for reproducibility and standardization in lymph node cytopathology. Since then, the risk of malignancy for the categories of the Sydney system has been explored by several studies, but no studies have yet examined the interobserver reproducibility of the Sydney system. Methods: The authors assessed interobserver reproducibility of the Sydney system on 85 lymph node fine‐needle aspiration cytology cases reviewed by 15 cytopathologists from 12 institutions in eight different countries, resulting in 1275 diagnoses. In total, 186 slides stained with Diff‐Quik, Papanicolaou, and immunocytochemistry were scanned. A subset of the cases included clinical data and results from ultrasound examinations, flow cytometry immunophenotyping, and fluorescence in situ hybridization analysis. The study participants assessed the cases digitally using whole‐slide images. Results: Overall, the authors observed an almost perfect agreement of cytopathologists with the ground truth (median weighted Cohen κ = 0.887; interquartile range, κ = 0.210) and moderate overall interobserver concordance (Fleiss κ = 0.476). There was substantial agreement for the inadequate and malignant categories (κ = 0.794 and κ = 0.729, respectively), moderate agreement for the benign category (κ = 0.490), and very slight agreement for the suspicious (κ = 0.104) and atypical (κ = 0.075) categories. Conclusions: The Sydney system for reporting lymph node cytopathology shows adequate interobserver concordance. Digital microscopy is an adequate means to assess lymph node cytopathology specimens. The Sydney system for reporting lymph node cytopathology exhibits adequate interobserver concordance. Digital microscopy is an adequate means to assess lymph node cytopathology specimens. [ABSTRACT FROM AUTHOR]

Objectives: This study was assessed the biocompatibility of three different root canal sealers (Well-Root St, GuttaFlow Bioseal, and AH-Plus) following implantation in rat subcutaneous tissues, using histopathological immunohistochemical analysis. Methods: Four groups of eighty-four male rats each underwent subcutaneous dorsal implantation of a polyethylene tube, either empty or filled. Tissues were collected, fixed, and processed for histological analysis after 7, 15, and 30 d. Slides were photographed and digitally processed to identify lymphocytes and macrophages using Cluster of differentiation 3 (CD3) and cluster of differentiation 68 (CD68) markers, respectively. P was set at 0.05, when lymphocyte and macrophage infiltration was compared between groups and observation times using one-way analysis of variance (ANOVA). Results: Histopathological analysis of all groups revealed an inflammatory reaction followed by the emergence of a fibrous capsule after 7 days. After 30 days, the thickness of the fibrous capsule and the inflammatory response subsided. CD3 staining for immunohistochemical analysis revealed that the AH-Plus group had the highest mean percentage of lymphocyte infiltration at 7 and 15 days, followed by the Well-Root St, GuttaFlow Bioseal, and Control groups. After 30 days, no discernible difference was observed between the groups in terms of the mean percentage of lymphocyte infiltration. After 7, 15, and 30 days, there was a significant difference in the mean percentage of macrophage infiltration across the groups, as demonstrated by CD68 staining. After 7, 15, and 30 days, the AH-Plus group had the highest mean percentage of macrophage infiltration, followed by the Well-Root St. and GuttaFlow Bioseal groups, while the control group had the lowest mean percentage. Conclusion: All observational periods showed minimal inflammatory reactions to GuttaFlow Bioseal. After subcutaneous tissue implantation in a rat model, the initial inflammatory reactions to Well-Root St and AH-Plus had abated by day 30, and all tested sealers had outstanding biocompatibility. [ABSTRACT FROM AUTHOR]

Federated learning (FL), a relatively new area of research in medical image analysis, enables collaborative learning of a federated deep learning model without sharing the data of participating clients. In this paper, we propose FedDropoutAvg, a new federated learning approach for detection of tumor in images of colon tissue slides. The proposed method leverages the power of dropout, a commonly employed scheme to avoid overfitting in neural networks, in both client selection and federated averaging processes. We examine FedDropoutAvg against other FL benchmark algorithms for two different image classification tasks using a publicly available multi-site histopathology image dataset. We train and test the proposed model on a large dataset consisting of 1.2 million image tiles from 21 different sites. For testing the generalization of all models, we select held-out test sets from sites that were not used during training. We show that the proposed approach outperforms other FL methods and reduces the performance gap (to less than 3% in terms of AUC on independent test sites) between FL and a central deep learning model that requires all data to be shared for centralized training, demonstrating the potential of the proposed FedDropoutAvg model to be more generalizable than other state-of-the-art federated models. To the best of our knowledge, ours is the first study to effectively utilize the dropout strategy in a federated setting for tumor detection in histology images. [ABSTRACT FROM AUTHOR]

Virtual pathology education has shown to enhance the students' learning experience. At the Radboud University, an E‐learning platform—called the "PathoDiscovery"—was developed and first used in a course about neoplasm development amongst first year (bio)medical sciences students. The PathoDiscovery incorporates high‐power microscopic images, histological annotations, interactive questions and pre‐programmed feedback.The objective of our study was to develop and evaluate the PathoDiscovery within the "Neoplasm" course focusing on student perceptions of usability and utility. For this study the online feedback on the PathoDiscovery that was obtained anonymously from (bio)medical students over two consecutive academic years was analyzed. The responses of the first year were used to make improvements. After the second year, the feedback of the two academic years was compared. The rating of the E‐learning increased from 6.8 (n = 285) to 7.4 (n = 247) after implementation of feedback obtained in the first year. The students judged the structure as logical (90%). The content was considered easy or just right (57%), matched the learning objectives (76%), and contributed to knowledge development (78%). We conclude that the first experiences with the PathoDiscovery are positive for both students and lecturers; it is an example of a dynamic online learning tool that is easily adaptable and is well suited for a blended learning approach. [ABSTRACT FROM AUTHOR]

Introduction: In low- and middle-income countries (LMICs), surgical care can be limited by access to pathology services. In Uganda, the pathologist-to-population ratio is less than 1 to 1 million people. The Kyabirwa Surgical Center in Jinja, Uganda, created a telepathology service in collaboration with an academic institution in New York City. This study demonstrated the feasibility and considerations of implementing a telepathology model to supplement the critical pathology needs of a low-income country. Methods: This was a retrospective, single-center study of an ambulatory surgery center with pathology capability using virtual microscopy. The remote pathologist (also known as a telepathologist) controlled the microscope and reviewed histology images transmitted across the network in real time. In addition, this study collected demographics, clinical histories, the surgeon's preliminary diagnoses, and the pathology reports from the center's electronic medical record. Results: Nikon's NIS Element Software was used as a dynamic, robotic microscopy model with a video conferencing platform for communication. An underground fiber optic cable established Internet connectivity. After a two-hour tutorial session, the lab technician and pathologist were able to proficiently use the software. The remote pathologist read (1) pathology slides with inconclusive reports from external pathology labs, and (2) tissues labeled by the surgeon as suspicious for malignancy, which belonged to patients who lacked financial means for pathology services. Between April 2021 and July 2022, tissue samples of 110 patients were examined by a telepathologist. The most common malignancies on histology were squamous cell carcinoma of the esophagus, ductal carcinoma of the breast, and colorectal adenocarcinoma. Conclusion: With the increasing availability of video conference platforms and network connections, telepathology is an emerging field that can be used by surgeons in LMICs to improve access to pathology services, confirming histological diagnosis of malignancies to ensure appropriate treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: The detection of thyroid nodules is increasing worldwide. Fine needle aspiration biopsy (FNA) is used to differentiate benign and malignant nodules and to address patient management; about 30% of patients receive indeterminate or inadequate cytological report. This clinical problem needs an innovative approach, overcoming the limits of traditional cytological diagnostics. Fluorescence laser confocal microscopes (FCM) is a new optical technique for allowing immediate digital imaging of fresh unfixed tissues, and it recently obtained attention for real-time assessment of sample adequacy and diagnostic evaluation for small biopsies and cytological samples. Herein we tested FCM technology for evaluating FNA thyroid samples at the procedure time and to assess the concordance between FCM evaluations, paired conventional cytology, and final histology of removed thyroid gland. We also analyzed the integrity of nucleic acids after FCM evaluation to assure viability for molecular assessment. Our results demonstrated that FCM might improve timely and accurate patient management. Thyroid cytological examination, a key tool in preoperative thyroid nodule evaluation, is specific and accurate; some drawbacks are due to inadequate or indeterminate cytological reports and there is a need for an innovative approach overcoming the limits of traditional cytological diagnostics. Fluorescence laser confocal microscopes (FCM) is a new optical technique for allowing immediate digital imaging of fresh unfixed tissues and real-time assessment of sample adequacy and diagnostic evaluation for small biopsies and cytological samples. Currently, there are no data about the use of FCMs in the field of thyroid nodular pathology. The aims of this study were to test FCM technology for evaluating the adequacy of FNA samples at the time of the procedure and to assess the level of concordance between FCM cytological evaluations, paired conventional cytology, and final surgical histology. The secondary aim was to define the integrity of nucleic acids after FCM evaluation through NGS molecular analysis. Sample adequacy was correctly stated. Comparing FCM evaluation with the final histology, all cases resulting in malignant or suspicious for malignancy at FCM, were confirmed to be carcinomas (PPV 100%). In conclusion, we describe a successful application of FCM in thyroid preoperative cytological evaluation, with advantages in immediate adequacy assessment and diagnostic information, while preserving cellular specimens for permanent morphology and molecular analysis, thus improving timely and accurate patient management. [ABSTRACT FROM AUTHOR]

Background: Developing efficient bonding techniques for orthodontic brackets and all-ceramic materials continues to pose a clinical difficulty. This study aimed to evaluate the shear bond strengths (SBS) of metal and ceramic brackets to various all-ceramic CAD-CAM materials, such as lithium disilicate CAD (LDS-CAD), polymer-infiltrated ceramic (PIC), zirconia-reinforced lithium silicate glass ceramic (ZLS), and 5YTZP zirconia after different surface treatments and thermal cycling. Materials and methods: The samples were divided into two groups to be bonded with ceramic and metal lower incisor brackets. Each group was subdivided into a control group devoid of any surface treatment, 10% HF acid (HFA) etching, ceramic etch & prime (MEP), Al2O3 air abrasion, and medium grit diamond bur roughening. After surface treatment, brackets were bonded with composite resin cement, thermal cycled, and tested for shear bond strength. The failed surfaces were evaluated with a digital microscope to analyse the type of failure. The data were statistically analysed using a one-way ANOVA and Tukey HSD tests at p < 0.05. Results: The highest mean bond strengths were found with HFA etching in LDS-CAD (13.17 ± 0.26 MPa) and ZLS (12.85 0.52 MPa). Diamond bur recorded the lowest mean bond strength roughening across all the ceramic groups. There were significant differences in mean shear bond values per surface treatment (p < 0.001) and ceramic materials. Conclusion: Among the surface treatment protocols evaluated, HFA etching and MEP surface treatment resulted in enhanced bond strength of both ceramic and metal brackets to CAD-CAM all ceramic materials. [ABSTRACT FROM AUTHOR]

Cervical cancer is still a public health scourge in the developing countries due to the lack of organized screening programs. Though liquid-based cytology methods improved the performance of cervical cytology, the interpretation still suffers from subjectivity. Artificial intelligence (AI) algorithms have offered objectivity leading to better sensitivity and specificity of cervical cancer screening. Whole slide imaging (WSI) that converts a glass slide to a virtual slide provides a new perspective to the application of AI, especially for cervical cytology. In the recent years, there have been a few studies employing various AI algorithms on WSI images of conventional or LBC smears and demonstrating differing sensitivity/specificity or accuracy at detection of abnormalities in cervical smears. Considering the interest in AI-based screening modalities, this well-timed review intends to summarize the progress in this field while highlighting the research gaps and providing future research directions. [ABSTRACT FROM AUTHOR]

This article proposes using microscopy for nature-inspired design in the early stage of "fuzzy front end" radical innovation and sustainable design technology, where it would have a high positive or sustainable impact. To give a taste of what is possible, a live virtual Nature Experience Radical Design (NERD) Jam was created. Instead of starting with a problem, designers, biologists, engineers, microscopists, and curious people were invited to begin with the solution. By observing and empathizing with nature, both in its element and under a microscope, microscopy reveals unique structural adaptations and possible unknown strategies and mechanisms when exploring nature as a series of successful devices in particular environmental contexts. By looking at nature on multiple scales, one can discover unique models to design sustainable solutions for multiple human challenges. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to determine anatomical landmarks for accurate and safe middle turn cochleostomy on cadaveric temporal bones. Methods: In 17 cadaveric wet adult temporal bones, cortical mastoidectomy was performed, followed by extended posterior tympanotomy through which a middle turn opening was created anterior to the stapes footplate. Micro-measurements of various lengths were taken from the cochleostomy to normal middle-ear anatomical landmarks using a digital microscope. Results: The mean length from the middle turn cochleostomy to the processus cochleariformis was 1.8 ± 0.3 mm and to the tympanic segment of the facial nerve was 2.2 ± 0.3 mm. The mean shortest length from the oval window to the osseous spiral lamina was 2.4 ± 0.3 mm and to the internal carotid artery was 5.0 ± 0.6 mm. The mean shortest length from the round window to the internal carotid artery was 4.3 ± 0.6 mm. Conclusion: A middle turn cochleostomy can be safely drilled by using the measured lengths in difficult cases. [ABSTRACT FROM AUTHOR]

The article stresses the need to expand proficiency testing (PT) to cover telepathology across institutions. It suggests the addition of a PT program for telepathology given the fact that the College of American Pathologists' educational program does not assess the accuracy of the diagnoses or assessments of biomarker analyses made from digital slides. It also discusses the incorporation of digital telepathology into clinical decision-making for rapid on-site specimen evaluation.

Simple Summary: Renal cell carcinoma causes over 179,000 deaths per year worldwide, and the Fuhrman grading (FG) system is crucial for diagnosing this deadly cancer. However, visual histopathological assessment is influenced by inter-observer variability and irreproducibility. In this study, we trained a deep learning model named SSL-CLAM using whole slide histopathology images to objectively diagnose the FG status of patients with clear cell renal cell carcinoma (ccRCC). We demonstrated that the SSL-CLAM model successfully diagnosed five FG states of ccRCC (Grade-0, 1, 2, 3, and 4) and validated the results in two independent cohorts. The attention heatmap of the SSL-CLAM model visualized high attention regions, and we found that cell nuclear size, contour, and cellular pleomorphism were critical morphologies that align with the existing FG criteria. In summary, a human–machine collaborative diagnostic model may assist pathologists in making diagnostic decisions, and further prospective clinical trials are needed to confirm its efficacy. (1) Background: The Fuhrman grading (FG) system is widely used in the management of clear cell renal cell carcinoma (ccRCC). However, it is affected by observer variability and irreproducibility in clinical practice. We aimed to use a deep learning multi-class model called SSL-CLAM to assist in diagnosing the FG status of ccRCC patients using digitized whole slide images (WSIs). (2) Methods: We recruited 504 eligible ccRCC patients from The Cancer Genome Atlas (TCGA) cohort and obtained 708 hematoxylin and eosin-stained WSIs for the development and internal validation of the SSL-CLAM model. Additionally, we obtained 445 WSIs from 188 ccRCC eligible patients in the Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohort as an independent external validation set. A human–machine fusion approach was used to validate the added value of the SSL-CLAM model for pathologists. (3) Results: The SSL-CLAM model successfully diagnosed the five FG statuses (Grade-0, 1, 2, 3, and 4) of ccRCC, and achieved AUCs of 0.917 and 0.887 on the internal and external validation sets, respectively, outperforming a junior pathologist. For the normal/tumor classification (Grade-0, Grade-1/2/3/4) task, the SSL-CLAM model yielded AUCs close to 1 on both the internal and external validation sets. The SSL-CLAM model achieved a better performance for the two-tiered FG (Grade-0, Grade-1/2, and Grade-3/4) task, with AUCs of 0.936 and 0.915 on the internal and external validation sets, respectively. The human–machine diagnostic performance was superior to that of the SSL-CLAM model, showing promising prospects. In addition, the high-attention regions of the SSL-CLAM model showed that with an increasing FG status, the cell nuclei in the tumor region become larger, with irregular contours and increased cellular pleomorphism. (4) Conclusions: Our findings support the feasibility of using deep learning and human–machine fusion methods for FG classification on WSIs from ccRCC patients, which may assist pathologists in making diagnostic decisions. [ABSTRACT FROM AUTHOR]

The tissue sample analysis based on the visualization of the entire tissue sample represents an important methodology in clinical diagnostics, research, and education. This process that enables visualization of the entire tissue sample is named whole slide imaging. For clinical purposes, professional and very expensive scanners are used for tissue sample digitization and the creation of whole slide images. In education, it is possible to use whole slide images that do not necessarily follow strict medical standards and regulations. Therefore, the important research task is to propose a methodology for the manual creation of whole slide images and its adequate use in medical education. In this paper, the use of manually created whole slide images in histology classes education was analyzed. In the experimental part of this research, the methodology of manual creation and usage of whole slide images (WSI) in histology education is presented in more detail. The subjective assessment of the user's satisfaction with WSI usage in education was also performed. It was shown that the whole slide images were evaluated very positively in the histological analysis and education process. Using WSI can significantly improve histology teaching, especially when distance education principles are implemented. Therefore, in crises like the pandemic situation COVID-19 WSI usage becomes a very important educational tool for teaching microscope-related topics. The results of this research showed that the use of whole slide images in histology classes is in line with the process of digital transformation in education. [ABSTRACT FROM AUTHOR]

Whole slide imaging is a promising tool for cytology. In the present study, we assessed the performance of and user experience with virtual microscopy (VM) to determine its feasibility and usage in an educational setting. From January 1 through August 31, 2022, 46 Papanicolaou slides, of which 22 (48%) were abnormal, 23 (50%) were negative, and 1 (2%) was unsatisfactory, were reviewed by the students using both VM and light microscopy (LM) platforms. In addition to assessing VM's overall performance, the SurePath imaged slides' accuracy was reviewed as a potential alternative to ThinPrep because of its cloud storage advantage. Finally, the students' weekly feedback logs were analyzed to gain insights for improving the digital screening experience. The overall diagnostic concordance difference was significant between the 2 screening platforms (Z = 5.38; P < 0.001), favoring LM (86% correct diagnosis) over VM (70% correct diagnosis). The overall sensitivity of VM and LM was 54.0% and 89.6%, respectively. VM also had an overall higher specificity (91.8%) compared with LM (81.3%). LM performed better than whole slide imaging for the correct identification of an organism when one was present, with 77.6% sensitivity compared with 58.9% for the digital platform. The rate of agreement for the SurePath imaged slides with the reference diagnosis was 74.3% compared with 65.7% for the ThinPrep slides. Finally, 4 themes were discerned from reviewing the user logs, with issues about image quality and the lack of fine focus functionality most frequently mentioned, followed by themes associated with a higher learning curve and novelty associated with the digital screening. Although the VM results were poorer than the LM results in our validation, its use in an educational setting is promising considering the continued technological improvements and the renewed focus on improving the digital user experience. • Our findings revealed that there is a significant difference in diagnostic performance (Z = 5.38, P < 0.001) for students when using virtual microscopy platform, relative to light microscopy, in favor of the physical glass slides and microscopes. • SurePath imaged slides' accuracy was also reviewed as a potential alternative for its cloud storage advantage and found to be just as good, if not better, than the ThinPrep imaged slides (74.3% accuracy in SP compared to 65.7% in TP). • Themes were discerned from the students' digital slide review logs, to gain insights on the end-user experience using the virtual platform, which can be built upon to improve the future virtual screening experience. • The top three most frequently reported themes from the end-users when screening in virtual platforms were image quality (cited 21 times), lack of ability to fine-focus (cited 12 times), and high learning curve (cited 12 times) [ABSTRACT FROM AUTHOR]

With anatomical education becoming a global endeavor, free online resources offered via the Internet or other electronic venues are of increasing importance for teaching and learning communities worldwide. Students and instructors from developing countries, often limited in access to modern instructional resources by infrastructural and financial constraints, are frequent users of such online learning tools. During the recent Covid‐19 pandemic when all academic institutions were forced to quickly switch to a non‐contact mode of teaching, free online instructional resources were often essential for continuing the educational mission. However, there are a number of obstacles and issues that need to be considered when creating and offering such learning resources. These include the type, quality, and completeness of the content, their educational purpose, access to technical and financial resources, copyright and ethical issues, and more. Educators, who plan to generate and maintain free online resources, should also be aware that such projects usually require a considerable long‐term time commitment. In this article, these issues are discussed using the Michigan Histology website as an example. The discussion also addresses how e‐learning resources like the Michigan Histology website supported online learning during the recent Covid‐19 pandemic. [ABSTRACT FROM AUTHOR]

Objective: This study was carried out to analyze the perception and performance of dental students regarding the use of conventional microscopic slides and virtual slides about teaching and learning. Material and methods: Eighty undergraduate dental students who had studied the subject of oral pathology as a compulsory subject at Watim Dental College were invited to participate in the study. Students not willing to take part in the study were excluded. The questionnaires were duly filled and the test was taken by the students using either virtual slides or glass slides. The data was collected and analyzed using SPSS 20. Results: A total of eighty undergraduate students participated in the study. The results showed that dental students had a higher acceptance rate (all P-value<0.001) for cases taught via virtual microscopy and they outperformed in cases shown on virtual slides (p<0.01). Conclusion: In this study, the students preferred teaching oral histopathology via virtual slides over conventional glass slides and it also contributed more to their learning. [ABSTRACT FROM AUTHOR]

Digital whole slide images are Food and Drug Administration approved for clinical diagnostic use in pathology; however, integration is nascent. Trainees from 9 pathology training programs completed an online survey to ascertain attitudes toward and experiences with whole slide images for pathological interpretations. Respondents (n = 76) reported attending 63 unique medical schools (45 United States, 18 international). While 63% reported medical school exposure to whole slide images, most reported ≤ 5 hours. Those who began training more recently were more likely to report at least some exposure to digital whole slide image training in medical school compared to those who began training earlier: 75% of respondents beginning training in 2017 or 2018 reported exposure to whole slide images compared to 54% for trainees beginning earlier. Trainees exposed to whole slide images in medical school were more likely to agree they were comfortable using whole slide images for interpretation compared to those not exposed (29% vs 12%; P = .06). Most trainees agreed that accurate diagnoses can be made using whole slide images for primary diagnosis (92%; 95% CI: 86-98) and that whole slide images are useful for obtaining second opinions (93%; 95% CI: 88-99). Trainees reporting whole slide image experience during training, compared to those with no experience, were more likely to agree they would use whole slide images in 5 years for primary diagnosis (64% vs 50%; P = .3) and second opinions (86% vs 76%; P = .4). In conclusion, although exposure to whole slide images in medical school has increased, overall exposure is limited. Positive attitudes toward future whole slide image diagnostic use were associated with exposure to this technology during medical training. Curricular integration may promote adoption.

Vascular anomalies grouped into vascular tumors (hemangioma) (HI) and vascular malformation (VM) are benign vascular lesions that are difficult to distinguish from one another clinically and often confused with each other at histopathology. This confusing terminology leads to improper diagnosis, illogical treatment, and misdirected research. This study aimed to study GLUT 1, S-100, and nerve bundle to differentiate hemangioma and vascular malformation. Thirty two cases of vascular lesions (26 vascular malformations and 6 hemangiomas) were taken into the study. For histological evaluation and immunohistochemistry (IHC), samples of vascular lesions were collected in formalin. All the hematoxylin and eosin-stained slides were evaluated under light microscope for histology and nerve bundles. Immunohistochemical staining was performed by streptavidin–biotin method for GLUT 1 and S-100. GLUT 1 was positive in all 6 cases of hemangiomas (100%) and only in 1 case of vascular malformation. Nerve bundle was present in 24 cases of vascular malformation (92.3%) out of 26 cases but not in any cases of hemangioma and S-100 was found positive in all vascular malformation cases (100%) but not in hemangioma. So GLUT 1 expression, S-100, and presence of nerve bundle in vascular lesions can help to differentiate hemangioma and vascular malformation. [ABSTRACT FROM AUTHOR]

Background: The usage of whole-slide images has recently been gaining a foothold in medical education, training, and diagnosis. Objectives: The first objective of the current study was to compare academic performance on virtual microscopy (VM) and light microscopy (LM) for learning pathology, anatomy, and histology in medical and dental students during the COVID-19 period. The second objective was to gather insight into various applications and usage of such technology for medical education. Materials and methods: Using the keywords "virtual microscopy" or "light microscopy" or "digital microscopy" and "medical" and "dental" students, databases (PubMed, Embase, Scopus, Cochrane, CINAHL, and Google Scholar) were searched. Hand searching and snowballing were also employed for article searching. After extracting the relevant data based on inclusion and execution criteria, the qualitative data were used for the systematic review and quantitative data were used for meta-analysis. The Newcastle Ottawa Scale (NOS) scale was used to assess the quality of the included studies. Additionally, we registered our systematic review protocol in the prospective register of systematic reviews (PROSPERO) with registration number CRD42020205583. Results: A total of 39 studies met the criteria to be included in the systematic review. Overall, results indicated a preference for this technology and better academic scores. Qualitative analyses reported improved academic scores, ease of use, and enhanced collaboration amongst students as the top advantages, whereas technical issues were a disadvantage. The performance comparison of virtual versus light microscopy meta-analysis included 19 studies. Most (10/39) studies were from medical universities in the USA. VM was mainly used for teaching pathology courses (25/39) at medical schools (30/39). Dental schools (10/39) have also reported using VM for teaching microscopy. The COVID-19 pandemic was responsible for the transition to VM use in 17/39 studies. The pooled effect size of 19 studies significantly demonstrated higher exam performance (SMD: 1.36 [95% CI: 0.75, 1.96], p < 0.001) among the students who used VM for their learning. Students in the VM group demonstrated significantly higher exam performance than LM in pathology (SMD: 0.85 [95% CI: 0.26, 1.44], p < 0.01) and histopathology (SMD: 1.25 [95% CI: 0.71, 1.78], p < 0.001). For histology (SMD: 1.67 [95% CI: −0.05, 3.40], p = 0.06), the result was insignificant. The overall analysis of 15 studies assessing exam performance showed significantly higher performance for both medical (SMD: 1.42 [95% CI: 0.59, 2.25], p < 0.001) and dental students (SMD: 0.58 [95% CI: 0.58, 0.79], p < 0.001). Conclusions: The results of qualitative and quantitative analyses show that VM technology and digitization of glass slides enhance the teaching and learning of microscopic aspects of disease. Additionally, the COVID-19 global health crisis has produced many challenges to overcome from a macroscopic to microscopic scale, for which modern virtual technology is the solution. Therefore, medical educators worldwide should incorporate newer teaching technologies in the curriculum for the success of the coming generation of health-care professionals. [ABSTRACT FROM AUTHOR]

The article draws on the VM project, Digital Transformation of Histology and Histopathology by Virtual Microscopy (VM) for an Innovative Medical School Curriculum, funded by the European Union under the Erasmus+ framework. The project has as its focus VM, which has come to be regarded as a modern tool boasting increased quality and utility in microscopy education in European medical schools. We aim therefore at digitally transforming microscopy teaching and learning in order to achieve a cost-effective implementation and successful use of virtual microscopy technology towards the improvement of the histology and histopathology curriculum. The paper looks into the project's objectives and results, among which standard E.U. curricula for histology and histopathology, a virtual slide library, a training guide on advanced VM teaching in microscopy, and an open online course on VM. As an add-on, we also introduce the parallel text reading approach and its beneficial effects on the quality of foreign language learning by medical students. In view of the transferability potential of its deliverables and its relevant methodology, we are confident that the VM project contributes to the overall modernization of the educational system. [ABSTRACT FROM AUTHOR]

Virtual microscopy podcasts (VMPs) are narrative recordings of digital histology images. This study evaluated the outcomes of integrating the VMPs into teaching histology to osteopathic medical students. The hypothesis was that incorporating virtual microscopy podcasts as supplementary histology resources to the curriculum would have a positive impact on student performance and satisfaction. Sixty‐one podcasts of dynamic microscopic images were created using screen recordings of the digital slides. The VMPs were integrated as supplementary histology resources in multiple courses during the first and second years of the medical curriculum for three classes, a total of 477 osteopathic medical students. A voluntary and anonymous survey was obtained from the students using a questionnaire that included two open‐ended questions. The overall performance of the three classes on the histology content of the preclinical course examinations was compared to historical controls of the previous two classes that did not have access to the VMPs. Most students indicated that the podcasts enabled more efficient study time and improved their confidence in the histology content on examinations. The findings indicated a positive association between podcast viewing and efficient study time utilization and class performance. The class average scores of the three consecutive cohorts that used the VMPs progressively increased by 7.69%, 14.88%, and 14.91% compared to the controls. A summary of students' feedback and academic performance supported that integration of the VMPs into Histology teaching improved the learning experience. The findings align with previous studies on the effectiveness of multimedia‐based teaching in histology laboratory modules. [ABSTRACT FROM AUTHOR]

Simple Summary: For the effective treatment of lung cancer patients, correct tumor subtyping is of utmost importance, but it is often challenging in clinical routine. Using artificial intelligence and combining information from digital microscopy and matrix-assisted laser desorption/ionization mass spectrometry imaging data have the potential to support the pathologist's decision-making process. We present a classification algorithm to distinguish between adenocarcinoma and squamous cell carcinoma of the lung based on the automatic detection of tumor areas in whole tissue sections and the determination of the tumor subtype with high accuracy. Artificial intelligence (AI) has shown potential for facilitating the detection and classification of tumors. In patients with non-small cell lung cancer, distinguishing between the most common subtypes, adenocarcinoma (ADC) and squamous cell carcinoma (SqCC), is crucial for the development of an effective treatment plan. This task, however, may still present challenges in clinical routine. We propose a two-modality, AI-based classification algorithm to detect and subtype tumor areas, which combines information from matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) data and digital microscopy whole slide images (WSIs) of lung tissue sections. The method consists of first detecting areas with high tumor cell content by performing a segmentation of the hematoxylin and eosin-stained (H&E-stained) WSIs, and subsequently classifying the tumor areas based on the corresponding MALDI MSI data. We trained the algorithm on six tissue microarrays (TMAs) with tumor samples from N = 232 patients and used 14 additional whole sections for validation and model selection. Classification accuracy was evaluated on a test dataset with another 16 whole sections. The algorithm accurately detected and classified tumor areas, yielding a test accuracy of 94.7% on spectrum level, and correctly classified 15 of 16 test sections. When an additional quality control criterion was introduced, a 100% test accuracy was achieved on sections that passed the quality control (14 of 16). The presented method provides a step further towards the inclusion of AI and MALDI MSI data into clinical routine and has the potential to reduce the pathologist's work load. A careful analysis of the results revealed specific challenges to be considered when training neural networks on data from lung cancer tissue. [ABSTRACT FROM AUTHOR]

* Context.--Breast carcinoma grade, as determined by the Nottingham Grading System (NGS), is an important criterion for determining prognosis. The NGS is based on 3 parameters: tubule formation (TF), nuclear pleomorphism (NP), and mitotic count (MC). The advent of digital pathology and artificial intelligence (AI) have increased interest in virtual microscopy using digital whole slide imaging (WSI) more broadly. Objective.--To compare concordance in breast carcinoma grading between AI and a multi-institutional group of breast pathologists using digital WSI. Design.--We have developed an automated NGS framework using deep learning. Six pathologists and AI independently reviewed a digitally scanned slide from 137 invasive carcinomas and assigned a grade based on scoring of the TF, NP, and MC. Results.--Interobserver agreement for the pathologists and AI for overall grade was moderate (κ = 0.471). Agreement was good (κ = 0.681), moderate (κ = 0.442), and fair (κ = 0.368) for grades 1, 3, and 2, respectively. Observer pair concordance for AI and individual pathologists ranged from fair to good (j = 0.313-0.606). Perfect agreement was observed in 25 cases (27.4%). Interobserver agreement for the individual components was best for TF (κ = 0.471 each) followed by NP (κ = 0.342) and was worst for MC (κ = 0.233). There were no observed differences in concordance amongst pathologists alone versus pathologists + AI. Conclusions.--Ours is the first study comparing concordance in breast carcinoma grading between a multi-institutional group of pathologists using virtual microscopy to a newly developed WSI AI methodology. Using explainable methods, AI demonstrated similar concordance to pathologists alone. [ABSTRACT FROM AUTHOR]

Simple Summary: In this study, we trained deep learning models to classify TUR-P WSIs into prostate adenocarcinoma and benign (non-neoplastic) lesions using transfer and weakly supervised learning. Overall, the model achieved good classification performance in classifying whole-slide images, demonstrating the potential benefit of future deployments in a practical TUR-P histopathological diagnostic workflow system. The transurethral resection of the prostate (TUR-P) is an option for benign prostatic diseases, especially nodular hyperplasia patients who have moderate to severe urinary problems that have not responded to medication. Importantly, incidental prostate cancer is diagnosed at the time of TUR-P for benign prostatic disease. TUR-P specimens contain a large number of fragmented prostate tissues; this makes them time consuming to examine for pathologists as they have to check each fragment one by one. In this study, we trained deep learning models to classify TUR-P WSIs into prostate adenocarcinoma and benign (non-neoplastic) lesions using transfer and weakly supervised learning. We evaluated the models on TUR-P, needle biopsy, and The Cancer Genome Atlas (TCGA) public dataset test sets, achieving an ROC-AUC up to 0.984 in TUR-P test sets for adenocarcinoma. The results demonstrate the promising potential of deployment in a practical TUR-P histopathological diagnostic workflow system to improve the efficiency of pathologists. [ABSTRACT FROM AUTHOR]

Context.--: Wide adoption of digital pathology requires efficient visualization and navigation in Web-based digital slide viewers, which is poorly defined. Objective.--: To define and quantify relevant performance metrics for efficient visualization of cases and slides in digital slide viewers. Design.--: With a universal slide viewer used in clinical routine diagnostics, we evaluated the impact of slide caching, compression type, tile, and block size of whole slide images generated from Philips, Leica, and 3DHistech scanners on streaming performance on case, slide, and field of view levels. Results.--: Two hundred thirty-nine pathologists routinely reviewed 60 080 whole slide images over 3 months. The median time to open a case's slides from the laboratory information system was less than 4 seconds, the time to change to a slide within the case was less than 1 second, and the time to render the adjacent field of view when navigating the slide was less than one-quarter of a second. A whole slide image's block size and a viewer tile size of 1024 pixels showed best performance to display a field of view and was preferrable over smaller tiles due to fewer mosaic effects. For Philips, fastest median slide streaming pace was 238 ms per field of view and for 3DHistech, 125 ms. For Leica, the fastest pace of 108 ms per field of view was established with block serving without decompression. Conclusions.--: This is the first study to systematically assess user-centric slide visualization performance metrics for digital viewers, including time to open a case, time to change a slide, and time to change a field of view. These metrics help to improve the viewer's configuration, leading to an efficient visualization baseline that is widely accepted among pathologists using routine digital pathology. [ABSTRACT FROM AUTHOR]

The number of melanoma diagnoses has increased dramatically over the past three decades, outpacing almost all other cancers. Nearly 1 in 4 skin biopsies is of melanocytic lesions, highlighting the clinical and public health importance of correct diagnosis. Deep learning image analysis methods may improve and complement current diagnostic and prognostic capabilities. The histologic evaluation of melanocytic lesions, including melanoma and its precursors, involves determining whether the melanocytic population involves the epidermis, dermis, or both. Semantic segmentation of clinically important structures in skin biopsies is a crucial step towards an accurate diagnosis. While training a segmentation model requires ground-truth labels, annotation of large images is a labor-intensive task. This issue becomes especially pronounced in a medical image dataset in which expert annotation is the gold standard. In this paper, we propose a two-stage segmentation pipeline using coarse and sparse annotations on a small region of the whole slide image as the training set. Segmentation results on whole slide images show promising performance for the proposed pipeline. [ABSTRACT FROM AUTHOR]