Senior Pathologist Research Articles

The Swin-Transformer network based on focal loss is used to identify images of pathological subtypes of lung adenocarcinoma with high similarity and class imbalance.

The classification of primary lung adenocarcinoma is complex and varied. Different subtypes of lung adenocarcinoma have different treatment methods and different prognosis. In this study, we collected 11 datasets comprising subtypes of lung cancer and proposed FL-STNet model to provide the assistance for improving clinical problems of pathologic classification in primary adenocarcinoma of lung. Samples were collected from 360 patients diagnosed with lung adenocarcinoma and other subtypes of lung diseases. In addition, an auxiliary diagnosis algorithm based on Swin-Transformer, which used Focal Loss for function in training, was developed. Meanwhile, the diagnostic accuracy of the Swin-Transformer was compared to pathologists. The Swin-Transformer captures not only information in the overall tissue structure but also the local tissue details in the images of lung cancer pathology. Furthermore, training FL-STNet with the Focal Loss function can further balance the difference in the amount of data between different subtypes, improving recognition accuracy. The average classification accuracy, F1, and AUC of the proposed FL-STNet reached 85.71%, 86.57%, and 0.9903. The average accuracy of the FL-STNet was higher by 17% and 34%, respectively, than in the senior pathologist and junior pathologist group. The first deep learning based on an 11-category classifier was developed for classifying lung adenocarcinoma subtypes based on WSI histopathology. Aiming at the deficiencies of the current CNN and Vit, FL-STNet model is proposed in this study by introducing Focal Loss and combining the advantages of Swin-Transformer model.

Synoptic Reporting in Clinical Placental Pathology: A Preliminary Investigation Into Report Findings and Interobserver Agreement.

Placental pathology is key for investigating adverse pregnancy outcomes, however, lack of standardization in reporting has limited clinical utility. We evaluated a novel placental pathology synoptic report, comparing its robustness to narrative reports, and assessed interobserver agreement. 100 singleton placentas were included. Histology slides were examined by 2 senior perinatal pathologists and 2 pathology residents using a synoptic report (32 lesions). Historical narrative reports were compared to synoptic reports. Kappa scores were calculated for interobserver agreement between senior, resident, and senior vs resident pathologists. Synoptic reporting detected 169 (51.4%) lesion instances initially not included in historical reports. Amongst senior pathologists, 64% of all lesions examined demonstrated fair-to-excellent agreement (Kappa ≥0.41), with only 26% of Kappas ≥0.41 amongst those examined by resident pathologists. Well-characterized lesions (e.g., chorioamnionitis) demonstrated higher agreement, with lower agreement for uncommon lesions and those previously shown to have poor consensus. Synoptic reporting is one proposed method to address issues in placenta pathology reporting. The synoptic report generally identifies more lesions compared to the narrative report, however clinical significance remains unclear. Interobserver agreement is likely related to differential in experience. Further efforts to improve overall standardization of placenta pathology reporting are needed.

Deep learning-based classification and spatial prognosis risk score on whole-slide images of lung adenocarcinoma.

Classification of histological patterns in lung adenocarcinoma (LUAD) is critical for clinical decision-making, especially in the early stage. However, the inter- and intraobserver subjectivity of pathologists make the quantification of histological patterns varied and inconsistent. Moreover, the spatial information of histological patterns is not evident to the naked eye of pathologists. We establish the LUAD-subtype deep learning model (LSDLM) with optimal ResNet34 followed by a four-layer Neural Network classifier, based on 40 000 well-annotated path-level tiles. The LSDLM shows robust performance for the identification of histopathological subtypes on the whole-slide level, with an area under the curve (AUC) value of 0.93, 0.96 and 0.85 across one internal and two external validation data sets. The LSDLM is capable of accurately distinguishing different LUAD subtypes through confusion matrices, albeit with a bias for high-risk subtypes. It possesses mixed histology pattern recognition on a par with senior pathologists. Combining the LSDLM-based risk score with the spatial K score (K-RS) shows great capacity for stratifying patients. Furthermore, we found the corresponding gene-level signature (AI-SRSS) to be an independent risk factor correlated with prognosis. Leveraging state-of-the-art deep learning models, the LSDLM shows capacity to assist pathologists in classifying histological patterns and prognosis stratification of LUAD patients.

Artificial intelligence-based model for lymph node metastases detection on whole slide images in bladder cancer: a retrospective, multicentre, diagnostic study.

Accurate lymph node staging is important for the diagnosis and treatment of patients with bladder cancer. We aimed to develop a lymph node metastases diagnostic model (LNMDM) on whole slide images and to assess the clinical effect of an artificial intelligence-assisted (AI) workflow. In this retrospective, multicentre, diagnostic study in China, we included consecutive patients with bladder cancer who had radical cystectomy and pelvic lymph node dissection, and from whom whole slide images of lymph node sections were available, for model development. We excluded patients with non-bladder cancer and concurrent surgery, or low-quality images. Patients from two hospitals (Sun Yat-sen Memorial Hospital of Sun Yat-sen University and Zhujiang Hospital of Southern Medical University, Guangzhou, Guangdong, China) were assigned before a cutoff date to a training set and after the date to internal validation sets for each hospital. Patients from three other hospitals (the Third Affiliated Hospital of Sun Yat-sen University, Nanfang Hospital of Southern Medical University, and the Third Affiliated Hospital of Southern Medical University, Guangzhou, Guangdong, China) were included as external validation sets. A validation subset of challenging cases from the five validation sets was used to compare performance between the LNMDM and pathologists, and two other datasets (breast cancer from the CAMELYON16 dataset and prostate cancer from the Sun Yat-sen Memorial Hospital of Sun Yat-sen University) were collected for a multi-cancer test. The primary endpoint was diagnostic sensitivity in the four prespecified groups (ie, the five validation sets, a single-lymph-node test set, the multi-cancer test set, and the subset for a performance comparison between the LNMDM and pathologists). Between Jan 1, 2013 and Dec 31, 2021, 1012 patients with bladder cancer had radical cystectomy and pelvic lymph node dissection and were included (8177 images and 20 954 lymph nodes). We excluded 14 patients (165 images) with concurrent non-bladder cancer and also excluded 21 low-quality images. We included 998 patients and 7991 images (881 [88%] men; 117 [12%] women; median age 64 years [IQR 56-72]; ethnicity data not available; 268 [27%] with lymph node metastases) to develop the LNMDM. The area under the curve (AUC) for accurate diagnosis of the LNMDM ranged from 0·978 (95% CI 0·960-0·996) to 0·998 (0·996-1·000) in the five validation sets. Performance comparisons between the LNMDM and pathologists showed that the diagnostic sensitivity of the model (0·983 [95% CI 0·941-0·998]) substantially exceeded that of both junior pathologists (0·906 [0·871-0·934]) and senior pathologists (0·947 [0·919-0·968]), and that AI assistance improved sensitivity for both junior (from 0·906 without AI to 0·953 with AI) and senior (from 0·947 to 0·986) pathologists. In the multi-cancer test, the LNMDM maintained an AUC of 0·943 (95% CI 0·918-0·969) in breast cancer images and 0·922 (0·884-0·960) in prostate cancer images. In 13 patients, the LNMDM detected tumour micrometastases that had been missed by pathologists who had previously classified these patients' results as negative. Receiver operating characteristic curves showed that the LNMDM would enable pathologists to exclude 80-92% of negative slides while maintaining 100% sensitivity in clinical application. We developed an AI-based diagnostic model that did well in detecting lymph node metastases, particularly micrometastases. The LNMDM showed substantial potential for clinical applications in improving the accuracy and efficiency of pathologists' work. National Natural Science Foundation of China, the Science and Technology Planning Project of Guangdong Province, the National Key Research and Development Programme of China, and the Guangdong Provincial Clinical Research Centre for Urological Diseases.

A nomogram based on LI-RADS features, clinical indicators and quantitative contrast-enhanced MRI parameters for predicting glypican-3 expression in hepatocellular carcinoma.

Noninvasively assessing the tumor biology and microenvironment before treatment is greatly important, and glypican-3 (GPC-3) is a new-generation immunotherapy target for hepatocellular carcinoma (HCC). This study investigated the application value of a nomogram based on LI-RADS features, quantitative contrast-enhanced MRI parameters and clinical indicators in the noninvasive preoperative prediction of GPC-3 expression in HCC. We retrospectively reviewed 127 patients with pathologically confirmed solitary HCC who underwent Gd-EOB-DTPA MRI examinations and related laboratory tests. Quantitative contrast-enhanced MRI parameters and clinical indicators were collected by an abdominal radiologist, and LI-RADS features were independently assessed and recorded by three trained intermediate- and senior-level radiologists. The pathological and immunohistochemical results of HCC were determined by two senior pathologists. All patients were divided into a training cohort (88 cases) and validation cohort (39 cases). Univariate analysis and multivariate logistic regression were performed to identify independent predictors of GPC-3 expression in HCC, and a nomogram model was established in the training cohort. The performance of the nomogram was assessed by the area under the receiver operating characteristic curve (AUC) and the calibration curve in the training cohort and validation cohort, respectively. Blood products in mass, nodule-in-nodule architecture, mosaic architecture, contrast enhancement ratio (CER), transition phase lesion-liver parenchyma signal ratio (TP-LNR), and serum ferritin (Fer) were independent predictors of GPC-3 expression, with odds ratios (ORs) of 5.437, 10.682, 5.477, 11.788, 0.028, and 1.005, respectively. Nomogram based on LI-RADS features (blood products in mass, nodule-in-nodule architecture and mosaic architecture), quantitative contrast-enhanced MRI parameters (CER and TP-LNR) and clinical indicators (Fer) for predicting GPC-3 expression in HCC was established successfully. The nomogram showed good discrimination (AUC of 0.925 in the training cohort and 0.908 in the validation cohort) and favorable calibration. The diagnostic sensitivity and specificity were 76.9% and 92.3% in the training cohort, 76.8% and 93.8% in the validation cohort respectively. The nomogram constructed from LI-RADS features, quantitative contrast-enhanced MRI parameters and clinical indicators has high application value, can accurately predict GPC-3 expression in HCC and may help noninvasively identify potential patients for GPC-3 immunotherapy.

Combined Merkel Cell Carcinoma with Nodal Presentation: Report of a Case Diagnosed with Excisional but Not Incisional Biopsy and Literature Review.

Merkel cell carcinoma (MCC) is a rare primary neuroendocrine carcinoma (NEC) of the skin. As compared to pure MCCs, combined MCCs are aggressive and exhibit a higher probability of metastasis. A correct diagnosis might be missed, especially when the biopsy sample is too small or too superficial. We report a 79-year-old Taiwanese male who presented with lymphadenopathy suspicious for lymphoma. A nodal biopsy showed metastatic NEC. A skin tumor in the lower back was identified, and an incisional biopsy showed only squamous cell carcinoma (SCC). A subsequent excisional biopsy was performed based on the advice of the senior pathologist because of the presence of metastatic nodal NEC. Finally, a diagnosis of combined MCC and SCC was confirmed. Our literature review identified 13 cases of combined MCC with nodal metastasis as initial presentations, all with an aggressive clinical course. Both the MCC and non-MCC components could be present in the metastatic nodes. Metastases of pure MCC cells were observed in three combined MCCs in sun-protected areas, probably pointing to a distinct pathogenesis. Excision or punch biopsy to include the deep dermal NEC component is recommended as timely diagnosis is mandatory for appropriate management of patients with this rare skin cancer.

A Deep Neural Network–Based Decision Support Tool for the Detection of Lymph Node Metastases in Colorectal Cancer Specimens

The identification of lymph node metastases in colorectal cancer (CRC) specimens is crucial for the planning of postoperative treatment and can be a time-consuming task for pathologists. In this study, we developed a deep neural network (DNN) algorithm for the detection of metastatic CRC in digitized histologic sections of lymph nodes and evaluated its performance as a diagnostic support tool. First, the DNN algorithm was trained using pixel-level annotations of cancerous areas on 758 whole slide images (360 with cancerous areas). The algorithm’s performance was evaluated on 74 whole slide images (43 with cancerous areas). Second, the algorithm was evaluated as a decision support tool on 288 whole slide images covering 1517 lymph node sections, randomized in 16 batches. Two senior pathologists (C.K. and C.O.) assessed each batch with and without the help of the algorithm in a 2 × 2 crossover design, with a washout period of 1 month in between. The time needed for the evaluation of each node section was recorded. The DNN algorithm achieved a median pixel-level accuracy of 0.952 on slides with cancerous areas and 0.996 on slides with benign samples. N+ disease (metastases, micrometastases, or tumor deposits) was present in 103 of the 1517 sections. The algorithm highlighted cancerous areas in 102 of these sections, with a sensitivity of 0.990. Assisted by the algorithm, the median time needed for evaluation was significantly shortened for both pathologists (median time for pathologist 1, 26 vs 14 seconds; P < .001; 95% CI, 11.0-12.0; median time for pathologist 2, 25 vs 23 seconds; P < .001; 95% CI, 2.0-4.0). Our DNN showed high accuracy for detecting metastatic CRC in digitized histologic sections of lymph nodes. This decision support tool has the potential to improve the diagnostic workflow by shortening the time needed for the evaluation of lymph nodes in CRC specimens without impairing diagnostic accuracy.

The Role of Artificial Intelligence in Accurate Interpretation of HER2 Immunohistochemical Scores 0 and 1+ in Breast Cancer

The new human epidermal growth factor receptor (HER)2-targeting antibody-drug conjugate offers the opportunity to treat patients with HER2-low breast cancer. Distinguishing HER2 immunohistochemical (IHC) scores of 0 and 1+ is not only critical but also challenging owing to HER2 heterogeneity and variability of observers. In this study, we aimed to increase the interpretation accuracy and consistency of HER2 IHC 0 and 1+ evaluation through assistance from an artificial intelligence (AI) algorithm. In addition, we examined the value of our AI algorithm in evaluating HER2 IHC scores in tumors with heterogeneity. AI-assisted interpretation consisted of AI algorithms and an augmenting reality module with a microscope. Fifteen pathologists (5 junior, 5 midlevel, and 5 senior) participated in this multi-institutional 2-round ring study that included 246 infiltrating duct carcinoma cases that were not otherwise specified. In round 1, pathologists analyzed 246 HER2 IHC slides by microscope without AI assistance. After a 2-week washout period, the pathologists read the same slides with AI algorithm assistance and rendered the definitive results by adjusting to the AI algorithm. The accuracy of interpretation accuracy with AI assistance (0.93 vs 0.80), thereby the evaluation precision of HER2 0 and the recall of HER2 1+. In addition, the AI algorithm improved the total consistency (intraclass correlation coefficient = 0.542-0.812), especially in HER2 1+ cases. In cases with heterogeneity, accuracy improved significantly (0.68 to 0.89) and to a similar level as in cases without heterogeneity (accuracy, 0.97). Both accuracy and consistency improved more for junior pathologists than those for the midlevel and senior pathologists. To the best of our knowledge, this is the first study to show that the accuracy and consistency of HER2 IHC 0 and 1+ evaluation and the accuracy of HER2 IHC evaluation in breast cancers with heterogeneity can be significantly improved using AI-assisted interpretation.

Pathology Job Search and Interview: Perspectives on the United States Experience.

Pathology training is focused on the attainment of clinical, diagnostic, and administrative skills. Preparation for employment search and the interview process are often neglected. Given that a near majority of pathology trainees in the United States are graduates of foreign medical schools, training in the job search and interview process according to local customs, norms, and expectations has greater salience for individuals new to the United States. To offer perspectives on 2 components of the job search process: (1) finding a suitable job opening in academic and private practice settings and (2) preparing for an interview. We have provided a set of common interview questions and suggested preparatory methodology. The differences in the process and expectations in academic settings and private practice operations are highlighted. Engaging in the job search process early and networking are emphasized. We have also suggested approaches for pathology teachers and mentors in guiding trainees in a job search and preparation for an interview. The information and opinions expressed in this communication are based on the personal experiences of 4 senior pathologists in academic and private practice settings. Start networking early. Leverage contacts with teachers, attending pathologists, senior residents, and people at national meetings to locate appropriate job opportunities. Seek assistance from attending pathologists in preparing a curriculum vitae and cover letter. Prepare for the questions that may come up in an interview. A dress rehearsal for an interview is strongly recommended.

An Obituary-Brigadier Chiragh Hassan Breathes his Last

An eminent senior Pathologist, Brigadier Chiragh Hassan, died in Lahore on 20th October 2022. He wasborn in the Hoshiarpur District and migrated to Lyallpur in 1947.He graduated from King Edward Medical College,Lahore in 1961; had a span of government service, firstas House Physician in Mayo Hospital and later asRegistrar till September 1965. He volunteered for thearmed services in the 1965 war, where he continued toserve till his retirement as Brigadier from CombinedMilitary Hospital, Lahore Pakistan. He did his FCPS in1978 and proceeded to on-the-job training in Tumor Pathology in a specialist unit in London for about a year.He spent a considerable part of his service at Pakistan Naval Ship, Shifa Hospital and did an excellent job in upgrading its laboratory.Dr Chiragh was a keen tennis player. He was very hospitable and loved by his friends and family alike. After retirement, he was an honorary consultantin a Lahore laboratory run by a Non-GovernmentOrganizations (NGO) in Lahore Cantt, Pakistan. The profession will be the loser with the departureof Brigadier Dr Chiragh.May Allah bless the soul!

Expression Levels of Glutathione S-Transferase and Cytochrome P450 Isoenzymes in Nasal Polyp Tissue.

Nasal polyps are benign sinonasal masses composed of eosinophils and extracellular edema. Pathogenesis of the polyp formation is unclear but several studies strongly suggest a correlation with infection, inflammation and allergy conditions. Our aim is to investigate the potential link between allergy and nasal polyp in tissue level. Nasal polyp group included 60 patients whose diagnosis was confirmed with biopsy and the control group included 38 healthy patients. Tissue sample of the control group was taken from inferior turbinate mucosa under local anesthesia and nasal polyp tissue was collected from functional endoscopic sinus surgery. The glutathione S-transferase (GST) and cytochrome P450 (CYP) isoenzyme expressions of the tissue samples were investigated under light microscopy and graded by a senior pathologist. GSTP1 protein expression was significantly higher in tissue samples from nasal polyp group compared to that of control group (p < 0.05). However, CYP1A1, GSTM1 and GSTA1 isoenzymes were not different between the two groups (p > 0.05). We have found that GSTP1 isoenzyme was elevated in nasal polyp tissue compared to the control. The increase in protein expression of GSTP1 might have occured as a tissue response to the increased oxidative stress thus suggesting a role of GSTP1 in polyp formation.

Using Silva pattern system to predict prognosis and plan treatment of invasive endocervical adenocarcinoma: a single-center retrospective analysis

BackgroundThis study evaluated the prognostic value of the Silva pattern system for invasive endocervical adenocarcinoma (EAC) by analysing its association with clinical and pathological features to provide more appropriate clinical management.MethodsA retrospective analysis including 63 patients with pathological diagnosis of invasive EAC was performed from March 2011 to December 2016 at our hospital. All pathological slides were reviewed by three senior pathologists, and cases were stratified into patterns A, B, or C by consensus according to the Silva pattern system criteria. Clinicopathological characteristics and follow-up of the three Silva subgroups were analysed.ResultsSilva A, B, and C EAC patients were compared based on tumour size, clinical stage, lymphovascular invasion (LVI), and depth of invasion (DOI). The differences were found to be statistically significant (p < 0.01). There was no statistically significant difference in the proportion of lymph node metastasis among the three groups (p > 0.05) or in the recurrence and mortality rates of patients with Silva A, B, and C EAC (p > 0.05). Single factor analysis showed that tumour size, clinical stage, lymph node metastasis, LVI, and DOI were related to postoperative recurrence, whereas age, Silva classification, and postoperative recurrence were not correlated.ConclusionThe Silva classification system can predict lymph node status and prognosis of invasive EAC, but it cannot be used as an independent indicator. Individualized treatment plans should be adopted for patients with EAC.

Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification.

Ki67 is a protein associated with tumor proliferation and metastasis in breast cancer and acts as an essential prognostic factor. Clinical work requires recognizing tumor regions on Ki67-stained whole-slide images (WSIs) before quantitation. Deep learning has the potential to provide assistance but largely relies on massive annotations and consumes a huge amount of time and energy. Hence, a novel tumor region recognition approach is proposed for more precise Ki67 quantification. An unsupervised domain adaptive method is proposed, which combines adversarial and self-training. The model trained on labeled hematoxylin and eosin (H&E) data and unlabeled Ki67 data can recognize tumor regions in Ki67 WSIs. Based on the UDA method, a Ki67 automated assisted quantification system is developed, which contains foreground segmentation, tumor region recognition, cell counting, and WSI-level score calculation. The proposed UDA method achieves high performance in tumor region recognition and Ki67 quantification. The AUC reached 0.9915, 0.9352, and 0.9689 on the validation set and internal and external test sets, respectively, substantially exceeding baseline (0.9334, 0.9167, 0.9408) and rivaling the fully supervised method (0.9950, 0.9284, 0.9652). The evaluation of automated quantification on 148 WSIs illustrated statistical agreement with pathological reports. The model trained by the proposed method is capable of accurately recognizing Ki67 tumor regions. The proposed UDA method can be readily extended to other types of immunohistochemical staining images. The results of automated assisted quantification are accurate and interpretable to provide assistance to both junior and senior pathologists in their interpretation.

A study on the diagnosis of the Helicobacter pylori coccoid form with artificial intelligence technology.

Helicobacter pylori (H. pylori) is an important pathogenic microorganism that causes gastric cancer, peptic ulcers and dyspepsia, and infects more than half of the world's population. Eradicating H. pylori is the most effective means to prevent and treat these diseases. H. pylori coccoid form (HPCF) causes refractory H. pylori infection and should be given more attention in infection management. However, manual HPCF recognition on slides is time-consuming and labor-intensive and depends on experienced pathologists; thus, HPCF diagnosis is rarely performed and often overlooked. Therefore, simple HPCF diagnostic methods need to be developed. We manually labeled 4,547 images from anonymized paraffin-embedded samples in the China Center for H. pylori Molecular Medicine (CCHpMM, Shanghai), followed by training and optimizing the Faster R-CNN and YOLO v5 models to identify HPCF. Mean average precision (mAP) was applied to evaluate and select the model. The artificial intelligence (AI) model interpretation results were compared with those of the pathologists with senior, intermediate, and junior experience levels, using the mean absolute error (MAE) of the coccoid rate as an evaluation metric. For the HPCF detection task, the YOLO v5 model was superior to the Faster R-CNN model (0.688 vs. 0.568, mean average precision, mAP); the optimized YOLO v5 model had a better performance (0.803 mAP). The MAE of the optimized YOLO v5 model (3.25 MAE) was superior to that of junior pathologists (4.14 MAE, p < 0.05), no worse than intermediate pathologists (3.40 MAE, p > 0.05), and equivalent to a senior pathologist (3.07 MAE, p > 0.05). HPCF identification using AI has the advantage of high accuracy and efficiency with the potential to assist or replace pathologists in clinical practice for HPCF identification.

Two-step artificial intelligence system for endoscopic gastric biopsy improves the diagnostic accuracy of pathologists.

BackgroundEndoscopic biopsy is the pivotal procedure for the diagnosis of gastric cancer. In this study, we applied whole-slide images (WSIs) of endoscopic gastric biopsy specimens to develop an endoscopic gastric biopsy assistant system (EGBAS).MethodsThe EGBAS was trained using 2373 WSIs expertly annotated and internally validated on 245 WSIs. A large-scale, multicenter test dataset of 2003 WSIs was used to externally evaluate EGBAS. Eight pathologists were compared with the EGBAS using a man-machine comparison test dataset. The fully manual performance of the pathologists was also compared with semi-manual performance using EGBAS assistance.ResultsThe average area under the curve of the EGBAS was 0·979 (0·958-0·990). For the diagnosis of all four categories, the overall accuracy of EGBAS was 86·95%, which was significantly higher than pathologists (P< 0·05). The EGBAS achieved a higher κ score (0·880, very good κ) than junior and senior pathologists (0·641 ± 0·088 and 0·729 ± 0·056). With EGBAS assistance, the overall accuracy (four-tier classification) of the pathologists increased from 66·49 ± 7·73% to 73·83 ± 5·73% (P< 0·05). The length of time for pathologists to manually complete the dataset was 461·44 ± 117·96 minutes; this time was reduced to 305·71 ± 82·43 minutes with EGBAS assistance (P = 0·00).ConclusionsThe EGBAS is a promising system for improving the diagnosis ability and reducing the workload of pathologists.

S2.1d Incidence of mixed fungal infections in post-COVID-19 outbreak of Mucormycosis

S2.1 Update on Mucormycosis, September 21, 2022, 3:00 PM - 4:30 PM IntroductionPost-COVID-19 rhino orbital mucormycosis has emerged as an important life-threatening complication adding to mortality. Fungal infections are a major health challenge, especially in the immunocompromised.Mucormycosis is a severe, frequently fatal fungal infection that has a unique predisposition to infect patients with diabetes. The most probable reasons for the emergence of these cases could be the extensive use of steroids in the management of coronavirus disease 2019 (COVID-19) patients and extensive dysregulated immune response due to severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection. A prompt diagnosis is vital for the effective management of invasive rhino-orbital fungal infections due to their propensity for angioinvasion and destructive spread with brain involvement.Materials and MethodsA total of 150 surgical pathology specimens received with a clinical suspicion of invasive fungal infection during the post-COVID-19 outbreak of mucormycosis were retrieved from the archives of the Department of histopathology. The cases were reviewed for the presence of Aspergillus fruiting bodies by senior pathologists and microbiologists on a multi-headed microscope. The morphological features of the fruiting bodies were noted and correlated with the fungal KOH and culture. The tissue reaction pattern, presence of oxalate crystals, and morphology of the fungal hyphae were also noted in each case showing Aspergillus fruiting bodies.ResultsA total of 8 out of 150 cases (5.3%) showed the presence of Aspergillus fruiting bodies. The histopathological diagnosis given in these 8 cases were—Aspergillus (1), combined Aspergillus and Mucorales (7). Two types of fungal hyphae were noted in all seven cases of combined infection. Granulomatous tissue reaction was noted in two out of seven cases of combined infection. Calcium oxalate crystals were noted in the single case of Aspergillosis and were absent in all cases of mixed infection.ConclusionTo conclude Aspergillus fruiting bodies are found in a small but significant number of cases of post-COVID-19 Rhino-Orbital invasive mold infections so while reporting the surgical specimens with clinical suspicion of post-COVID-19 mucormycosis one should be aware of the possibility of mixed fungal infections and look for Aspergillus fruiting bodies as a tell-tale sign of mixed Mucorales and Aspergillus infection. However, their presence does not estimate the true incidence of mixed fungal infections for which immunohistochemistry and polymerase chain reaction are needed.

A retrospective study of PD-L1 immunohistochemistry for hepatocellular carcinoma

Programmed cell death ligand 1 (PD-L1) expression plays an important role in selecting hepatocellular carcinoma (HCC) patients who will benefit from anti-programmed cell death 1 (PD-1)/PD-L1 monotherapy and directing those with lower levels to alternative treatments. In total, 156 HCC tumors were stained with three PD-L1 immunohistochemistry assays (SP142, 28-8, and E1L3N). Two junior pathologists and one senior pathologist evaluated the pathological slides and recorded the percentages of tumor and immune cells stained at any intensity. Analytical comparisons demonstrated that the anti-PD-L1 assay SP142 is a significantly stronger reagent that stains a higher percent of both tumor and immune cells, while 28-8 and E1L3N behave similarly to each other. The correlation coefficients of the three assays ranged from 0.77 to 0.92 for tumor cells and from 0.66 to 0.75 for immune cells. Next, 1% and 5% tumor cell staining cutoffs were designated using various combinations of assays and cutoffs. Across all three reagents, 14 samples showed concordance above the 5% threshold, eight showed concordance within the 1% to 5% interval, and 93 showed concordance below the 1% threshold. The remaining 41 samples showed a combination of discordant results across all three reagents. High PD-L1 expression in tumor and immune cells tended to not be recurrent. The anti-PD-L1 assays 28-8 and E1L3N were closely aligned with regards to staining tumor and immune cells, whereas SP142 showed higher percentages of staining for both cell types. All three assays indicated greater variability in immune cell staining than in tumor cells.

556 Case Report: Diagnosis of Bilateral PASH (Pseudoangiomatous Stromal Hyperplasia) in an 11-Year-Old Female

Abstract PASH (Pseudoangiomatous stromal hyperplasia) is a rare pathological finding, defined as a benign mesenchymal proliferative lesion of the breast, presenting more frequently in premenopausal women. Although benign, differentiation from low grade Angiosarcoma due to their histological similarities. Management guidelines for PASH remain primitive due to the rarity in diagnosis and reporting of such cases. We present a very interesting case of an 11-year-old female assessed for her rapidly enlarging breasts. Initial management entailed right breast reduction Mammoplasty due to the presumed diagnosis of Macromastia. Histopathological assessment of the specimen initially reported the presence of Fibroadenoma. However, re-assessment by a senior Pathologist subsequently diagnosed the lesion as Pseudoangiomatous Stromal Hyperplasia (PASH). Further MRI imaging of both breasts revealed multiple, large, bilateral lesions. All identified bilateral breast lesions were excised, with a cumulative weight of 1.6 Kg, combined with WISE pattern reduction of the right breast overlying skin was carried out in due course. There has been no previous reporting of PASH in an 11-year-old female, which itself is a rare condition. Further studies on PASH are recommended to reduce the risk unnecessary surgical management of such cases due to misdiagnosis.

Deep learning-based fully automated differential diagnosis of eyelid basal cell and sebaceous carcinoma using whole slide images.

BackgroundThe differential diagnosis of eyelid basal cell carcinoma (BCC) and sebaceous carcinoma (SC) is highly dependent on pathologist’s experience. Herein, we proposed a fully automated differential diagnostic method, which used deep learning (DL) to accurately classify eyelid BCC and SC based on whole slide images (WSIs).MethodsWe used 116 haematoxylin and eosin (H&E)-stained sections from 116 eyelid BCC patients and 180 H&E-stained sections from 129 eyelid SC patients treated at the Shanghai Ninth People’s Hospital from 2017 to 2019. The method comprises two stages: patch prediction by the DenseNet-161 architecture-based DL model and WSI differentiation by an average-probability strategy-based integration module, and its differential performance was assessed by the carcinoma differentiation accuracy and F1 score. We compared the classification performance of the method with that of three pathologists, two junior and one senior. To validate the auxiliary value of the method, we compared the pathologists’ BCC and SC classification with and without the assistance of our proposed method.ResultsOur proposed method achieved an accuracy of 0.983, significantly higher than that of the three pathologists (0.644 and 0.729 for the two junior pathologists and 0.831 for the senior pathologist). With the method’s assistance, the pathologists’ accuracy increased significantly (P<0.05), by 28.8% and 15.2%, respectively, for the two junior pathologists and by 11.8% for the senior pathologist.ConclusionsOur proposed method accurately classifies eyelid BCC and SC and effectively improves the diagnostic accuracy of pathologists. It may therefore facilitate the development of appropriate and timely therapeutic plans.

Digital image analysis provides robust tissue microenvironment-based prognosticators in patients with stage I-IV colorectal cancer

In patients with colorectal cancer (CRC), a promising marker is tumor-stroma ratio (TSR). Quantification issues highlight the importance of precise assessment that might be solved by artificial intelligence-based digital image analysis systems. Some alternatives have been offered so far, although these platforms are either proprietary developments or require additional programming skills. Our aim was to validate a user-friendly, commercially available software running in everyday computational environment to improve TSR assessment and also to compare the prognostic value of assessing TSR in 3 distinct regions of interests, like hotspot, invasive front, and whole tumor. Furthermore, we compared the prognostic power of TSR with the newly suggested carcinoma percentage (CP) and carcinoma-stroma percentage (CSP). Slides of 185 patients with stage I-IV CRC with clinical follow-up data were scanned and evaluated by a senior pathologist. A machine learning-based digital pathology software was trained to recognize tumoral and stromal compartments. The aforementioned parameters were evaluated in the hotspot, invasive front, and whole tumor area, both visually and by machine learning. Patients were classified based on TSR, CP, and CSP values. On multivariate analysis,TSR-hotspot was found to be an independent prognostic factor of overall survival (hazard ratio for TSR-hotspotsoftware: 2.005 [95% confidence interval (CI): 1.146-3.507], P=.011, for TSR-hotspotvisual: 1.781 [CI: 1.060-2.992], P=.029). Also, TSR was an independent predictor for distant metastasis and local relapse in most settings. Generally, software performance was comparable to visual evaluation and delivered reliable prognostication in more settings also with CP and CSP values. This study presents that software-assisted evaluation is a robust prognosticator. Our approach used a less sophisticated and thus easily accessible software without the aid of a convolutional neural network; however, it was still effective enough to deliver reliable prognostic information.