A robust image segmentation and synthesis pipeline for histopathology.

Significant diagnostic variability between and within observers persists in pathology, despite the fact that digital slide images provide the ability to measure and quantify features much more precisely compared to conventional methods. Automated and accurate segmentation of cancerous cell and tissue regions can streamline the diagnostic process, providing insights into the cancer progression, and helping experts decide on the most effective treatment. Here, we evaluate the performance of the proposed PathoSeg model, with an architecture comprising of a modified HRNet encoder and a UNet++ decoder integrated with a CBAM block to utilize attention mechanism for an improved segmentation capability. We demonstrate that PathoSeg outperforms the current state-of-the-art (SOTA) networks in both quantitative and qualitative assessment of instance and semantic segmentation. Notably, we leverage the use of synthetic data generated by PathopixGAN, which effectively addresses the data imbalance problem commonly encountered in histopathology datasets, further improving the performance of PathoSeg. It utilizes spatially adaptive normalization within a generative and discriminative mechanism to synthesize diverse histopathological environments dictated through semantic information passed through pixel-level annotated Ground Truth semantic masks.Besides, we contribute to the research community by providing an in-house dataset that includes semantically segmented masks for breast carcinoma tubules (BCT), micro/macrovesicular steatosis of the liver (MSL), and prostate carcinoma glands (PCG). In the first part of the dataset, we have a total of 14 whole slide images from 13 patients' liver, with fat cell segmented masks, totaling 951 masks of size 512 × 512 pixels. In the second part, it includes 17 whole slide images from 13 patients with prostate carcinoma gland segmentation masks, amounting to 30,000 masks of size 512 × 512 pixels. In the third part, the dataset contains 51 whole slides from 36 patients, with breast carcinoma tubule masks totaling 30,000 masks of size 512 × 512 pixels. To ensure transparency and encourage further research, we will make this dataset publicly available for non-commercial and academic purposes. To facilitate reproducibility and encourage further research, we will also make our code and pre-trained models publicly available at https://github.com/DeepMIALab/PathoSeg.

Does immunohistochemical staining predict mobilization success in multiple myeloma patients?

BACKGROUND: So many risk factors for mobilization failure have been described so far. We aimed to identify the risk factors and search the possible effects of bone marrow fibrosis (BMF), CD56, c-myc, and cyclinD1 expression on mobilization. METHODS: We evaluated 189 patients with MM who were admitted for stem cell mobilization before autologous stem cell transplantation (ASCT) between 2015 and June 2021. Clinical, laboratory, treatment features, and survival outcomes were compared in patients who were successfully mobilized and who were not. RESULTS: Mobilization failure rate was 11.1 % (21) in our study group. Male gender, mobilization with only G-CSF, history of previous ASCT, lenalidomide exposure, and 2 lines of chemotherapy before stem cell mobilization were observed more commonly in mobilization failure group. There is no relationship between mobilization failure and BMF, CD56, c-myc, and cyclin D1 expression status in patients who received either only G-CSF or G-CSF+ chemotherapy for mobilization. Overall survival (OS) was not different in groups of patients who were successfully mobilized and who were not. Neutrophil engraftment was faster in patients who were transfused > 5 × 106/kg stem cells (p = 0.015). ECOG performance status (p = 0.004), c-myc expression (p = 0.005), lenalidomide therapy before mobilization (p = 0.032), and mobilization with G-CSF+chemotherapy was found to be predictive factors for OS. CONCLUSION: Even though we could not find any predictive value of CD56, c-myc, and cyclin D1 expression on mobilization, c-myc was found to be associated with low OS. Further studies with large and homogenous study population would be more informative.

Oxidative and Antioxidative Biomarker Profiles in Neonatal Hypoxic-Ischemic Encephalopathy: Insights for Pathophysiology and Treatment Strategies.

BACKGROUND Neonatal hypoxic-ischemic encephalopathy (HIE) is a significant cause of perinatal and postnatal morbidity and mortality worldwide. Catalase (CAT) activity detection is used to determine levels of inflammation and oxidative stress. Glutathione (GSH) is the most critical non-enzymatic endogenous antioxidant. Lipid peroxidation levels marked after hypoxia can be detected based on the level of malondialdehyde (MDA). Ischemia-modified albumin (IMA) is considered a biomarker for cardiac ischemia and is known to increase in the liver, brain, and kidney in states of insufficient oxygenation. We aimed to explain the results and relations between the oxidant and antioxidants to detail oxidant-antioxidant balance and cellular mechanisms. MATERIAL AND METHODS Serum levels of IMA and MDA, as an oxidative stress marker, and CAT and GSH, as antioxidant enzymes, were measured in first blood samples of 59 neonates diagnosed with HIE, with pH <7, base excess >12, and APGAR scores. RESULTS Neonates who were ≥37 weeks of gestation and had hypoxia were included. Compared with healthy newborns (n=32), CAT was statistically significantly lower in the hypoxia group (P=0.0001), while MDA serum levels were significantly higher in neonates with hypoxia (P=0.01). There was no difference between hypoxic and healthy neonates in GSH and IMA measurements (P=0.054, P=0.19 respectively). CONCLUSIONS HIE pathophysiology involves oxidative stress and mitochondrial energy production failure. Explaining the pathways between oxidant-antioxidant balance and cell death, which explains the pathophysiology of HIE, is essential to develop treatment strategies that will minimize the effects of oxygen deprivation on other body organs, especially the brain.

Post-transplant lymphoproliferative disorder associated Epstein-Barr virus DNAemia after liver transplantation in children: Experience from single center.

The most prevalent malignancy that complicates both adult and pediatric solid organ transplantation is post-transplant lymphoproliferative disorder (PTLD). This study aimed to analyze the clinical and pathological characteristics, treatments, and outcomes of Epstein-Barr virus (EBV) DNAemia and PTLD in pediatric liver transplant recipients. A retrospective chart review was performed on 112 patients less than 18 years of age who underwent isolated orthotopic liver transplantation (OLT) between 2010 and 2022 at Ege University Children's Hospital. Data gathered for 1-year post-OLT included age at OLT, EBV, immunoglobulin (Ig)M/IgG status of the donor and recipient, indication for OLT, induction regimen, all immunosuppression levels, date and result of EBV polymerase chain reaction testing, rejection episodes documented by liver biopsy, and the development of PTLD. Forty-nine patients (43.75%) developed EBV DNAemia (median interval from surgery: 2 months, min-max: 2-36), of which 43 (87.8%) grafts came from living donors, and 6 (12.2%) came from deceased donors. Nine (18.4%) patients died during follow-up, and eight (16.3%) developed PTLD. Of these 8 patients; five patients developed EBV-related disease, one child developed hemophagocytic lymphohistiocytosis, one developed aplastic anemia, and one child developed B cell lymphoma. When PTLD patients and without-PTLD patients were compared, pediatric intensive care unit hospitalization, abnormal bone marrow biopsy findings, lymphadenopathy, age at diagnosis of EBV DNAemia, EBV viral load, tacrolimus (FK 506) pre-infection, were higher and tacrolimus 1-month levels were lower in patients with PTLD (p < 0.05). In logistic regression analysis, we showed that the age at diagnosis of EBV DNAemia was significantly higher in children with PTLD (p = 0.045; OR: 1.389; 95% CI: 1.007-1.914). PTLD is a rare but severe complication associated with EBV after OLT. This study demonstrated that PTLD is associated with older age, higher tacrolimus blood levels before EBV DNAemia, and higher peak EBV viral load at 1 month of EBV DNAemia.

First Case of FLT3-Tyrosine Kinase Domain Mutant Acute Myeloid Leukemia With Unusual Onset as Isolated Bilateral Testicular Myeloid Sarcoma.

Testicular myeloid sarcoma (TMS) is a challenging pathology often posing diagnostic difficulties due to the poorly differentiated nature of tumor cells at the initial presentation. The delay in diagnosis significantly impacts patient life expectancy, emphasizing the need for prompt identification and treatment initiation. In certain cases, the presence of the Fms-like tyrosine kinase (FLT3) mutation adds complexity to the disease, requiring tailored therapeutic approaches. In this report, we present a unique case of bilateral TMS with FLT3 tyrosine kinase domain (TKD) mutation. The patient exhibited an aggressive clinical course, initially misdiagnosed with orchitis during the initial evaluation. Subsequent reevaluation of the testicular biopsy at a second center led to an accurate diagnosis, highlighting the importance of thorough examination in challenging cases. Given the emerging significance of FLT3 mutations in myeloid sarcomas, comprehensive testing for all FLT3 variants is crucial to determine the appropriate treatment modality. This case underscores the need for increased awareness among healthcare professionals regarding the diagnostic nuances and potential genetic variations associated with TMS. Furthermore, the inclusion of tyrosine kinase inhibitors, such as midostaurin or gilteritinib, especially in the presence of FLT3 mutations, may significantly impact treatment outcomes. This report contributes to the growing body of literature on TMS and highlights the importance of considering FLT3 mutations in the diagnostic and therapeutic decision-making process for improved patient care.

The Association of the Epidermal Growth Factor Receptor (EGFR) Immunoexpression With Prognostic Parameters in Adenocarcinoma Patients Receiving Neoadjuvant Treatment.

The epidermal growth factor receptor (EGFR) expression is considered to play an essential role in the pathogenesis of colorectal adenocarcinoma. This study assessed the expression and predictive/prognostic value of EGFR expression in pre-op biopsy and post-op resection specimens in patients receiving neoadjuvant radiotherapy/neoadjuvant chemoradiotherapy (NRT/NCRT). Thirty-four consecutive patients were included in this study. The association between the prognostic features and EGFR immunohistochemical expression was analyzed in pre- (n=34) and post-treatment (n=22) tissue samples in cases with available tissue blocks. Of 34, 23 (67.6%) were men. The median age was 60.50 ± 10.69 (range, 31-84) years. EGFR expression was detected in 88.2% of biopsy specimens and in 91.2% of surgical specimens. There was only slight agreement between pre-op and post-op EGFR expression scores (kappa value 0.11). There was no significant correlation between pre-op and post-op EGFR expression scores (p>0.05). Although pre-op EGFR positivity and higher pre-op EGFR scores seemed to indicate a worse prognosis, this association between pre-op EGFR expression and overall survival (OS) or disease-specific survival (DSS) did not reach statistical significance (p>0.05). The only case with a post-op EGFR score of three who died of the disease experienced local recurrence and had distant metastasis. In conclusion, EGFR positivity in pre-op biopsy samples seems to be associated with shorter survival, and increased EGFR expression in post-treatment resection specimens predicts aggressive behavior in patients with rectal adenocarcinoma who received NRT/NCRT. However, due to the molecular heterogeneity, EGFR expression status should be evaluated in resection specimens rather than in pre-op biopsy samples for optimal prognosis prediction.

FFPE++: Improving the quality of formalin-fixed paraffin-embedded tissue imaging via contrastive unpaired image-to-image translation.

Formalin-fixation and paraffin-embedding (FFPE) is a technique for preparing and preserving tissue specimens that has been utilized in histopathology since the late 19th century. This process is further complicated by FFPE preparation steps such as fixation, processing, embedding, microtomy, staining, and coverslipping, which often results in artifacts due to the complex histological and cytological characteristics of a tissue specimen. The term "artifacts" includes, but is not limited to, staining inconsistencies, tissue folds, chattering, pen marks, blurring, air bubbles, and contamination. The presence of artifacts may interfere with pathological diagnosis in disease detection, subtyping, grading, and choice of therapy. In this study, we propose FFPE++, an unpaired image-to-image translation method based on contrastive learning with a mixed channel-spatial attention module and self-regularization loss that drastically corrects the aforementioned artifacts in FFPE tissue sections. Turing tests were performed by 10 board-certified pathologists with more than 10 years of experience. These tests which were performed for ovarian carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, and papillary thyroid carcinoma, demonstrate the clear superiority of the proposed method in many clinical aspects compared with standard FFPE images. Based on the qualitative experiments and feedback from the Turing tests, we believe that FFPE++ can contribute to substantial diagnostic and prognostic accuracy in clinical pathology in the future and can also improve the performance of AI tools in digital pathology. The code and dataset are publicly available at https://github.com/DeepMIALab/FFPEPlus.

Insights into the New Molecular Updates in Acute Myeloid Leukemia Pathogenesis.

As our understanding of the biologic basis of acute myeloid leukemia evolves, so do the classification systems used to describe this group of cancers. Early classification systems focused on the morphologic features of blasts and other cell populations; however, the explosion in genomic technologies has led to rapid growth in our understanding of these diseases and thus the refinement of classification systems. Recently, two new systems, the International Consensus Classification system and the 5th edition of the World Health Organization classification of tumors of hematopoietic and lymphoid tissues, were published to incorporate the latest genomic advances in blood cancer. This article reviews the major updates in acute myeloid leukemia in both systems and highlights the biologic insights that have driven these changes.

Clinicopathological characteristics, genetics and prognosis of patients with myeloid sarcoma: a single-center study.

AIM: Myeloid sarcoma (MS) is a rare tumour comprising myeloid blasts occurring at an anatomical site other than the bone marrow. We sought to investigate both paediatric and adult patients with MS diagnosed at our institution and determine possible correlations among their clinicopathological, phenotypic, molecular and prognostic features. METHODS: This study retrospectively evaluated the data of 45 patients diagnosed with MS at Ege University Faculty of Medicine Hospital, Turkey, over a 17-year period. RESULTS: The male-to-female ratio was 1.5:1, and the median age was 39.12 years. The most commonly involved sites were the skin, lymph nodes, soft tissues and bone. Immunohistochemically, CD68-KP1 was the most commonly expressed marker, followed by CD33, myeloperoxidase, CD117, lysozyme, CD68-PGM1 and CD34. Of the patients, 26 (57.7%) presented with de novo MS, 7 (15.5%) had simultaneous acute myeloid leukaemia and 12 (26.8%) had a previous history of haematological disorders. Kaplan-Meier survival analysis revealed that the 2-year and 5-year overall survival (OS) rates were 46.4% and 39.8%, respectively; the median OS duration was 11 months. Increasing age had a negative prognostic relationship with survival (p = 0.04). Chromosomal abnormalities were detected in approximately 6/10 (60%) of paediatric patients and 6/9 (66.7%) of adult patients. t(8;21)(q22;q22) translocation was identified in 20% of paediatric patients. CONCLUSIONS: MS diagnosis is usually challenging; an expanded immunohistochemical panel should be used for an accurate diagnosis. Although MS generally has a poor prognosis, increasing age appears to be associated with a worse outcome.

A deep-learning model for transforming the style of tissue images from cryosectioned to formalin-fixed and paraffin-embedded.

Histological artefacts in cryosectioned tissue can hinder rapid diagnostic assessments during surgery. Formalin-fixed and paraffin-embedded (FFPE) tissue provides higher quality slides, but the process for obtaining them is laborious (typically lasting 12-48 h) and hence unsuitable for intra-operative use. Here we report the development and performance of a deep-learning model that improves the quality of cryosectioned whole-slide images by transforming them into the style of whole-slide FFPE tissue within minutes. The model consists of a generative adversarial network incorporating an attention mechanism that rectifies cryosection artefacts and a self-regularization constraint between the cryosectioned and FFPE images for the preservation of clinically relevant features. Transformed FFPE-style images of gliomas and of non-small-cell lung cancers from a dataset independent from that used to train the model improved the rates of accurate tumour subtyping by pathologists.

Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies.

Endomyocardial biopsy (EMB) screening represents the standard of care for detecting allograft rejections after heart transplant. Manual interpretation of EMBs is affected by substantial interobserver and intraobserver variability, which often leads to inappropriate treatment with immunosuppressive drugs, unnecessary follow-up biopsies and poor transplant outcomes. Here we present a deep learning-based artificial intelligence (AI) system for automated assessment of gigapixel whole-slide images obtained from EMBs, which simultaneously addresses detection, subtyping and grading of allograft rejection. To assess model performance, we curated a large dataset from the United States, as well as independent test cohorts from Turkey and Switzerland, which includes large-scale variability across populations, sample preparations and slide scanning instrumentation. The model detects allograft rejection with an area under the receiver operating characteristic curve (AUC) of 0.962; assesses the cellular and antibody-mediated rejection type with AUCs of 0.958 and 0.874, respectively; detects Quilty B lesions, benign mimics of rejection, with an AUC of 0.939; and differentiates between low-grade and high-grade rejections with an AUC of 0.833. In a human reader study, the AI system showed non-inferior performance to conventional assessment and reduced interobserver variability and assessment time. This robust evaluation of cardiac allograft rejection paves the way for clinical trials to establish the efficacy of AI-assisted EMB assessment and its potential for improving heart transplant outcomes.

Ectopic Adrenal Gland Tissue In The Inguinal Hernia Sac Occuring In An Adult.

Ectopic adrenal tissue is a benign lesion generally determined incidentally during a surgical intervention applied for another reason. This tissue may be present along the path of the testicles and groin discovered during surgery. While the condition has been mainly reported in the pediatric population, it is very rarely reported in adults. The aim of this study was to present an adult patient with ectopic adrenal tissue which was determined incidentally within an indirect inguinal hernia sac.

Retrospective Analysis of Hairy Cell Leukemia Patients Treated with Different Modalities as First Line: Real-Life Experience Over 20 years.

We aimed to analyze the characteristics and response rates of different treatment modalities in hairy cell leukemia patients over 20 diagnosed as hairy cell leukemia (HCL). Clinical data, response rates and survival outcome of the patients who were diagnosed with HCL were retrospectively analyzed. Fifty-two patients with a median age of 50 (28-87) years were enrolled in the study. 38 patients (73%) were male and male to female ratio was 2.7. First line therapy was cladrabine in 36 patients (69.2%). The overall response rate was 97%. CR and PR rates were 86.1% and 11.1%, respectively. Interferon was used in 10(19.2%) patients who were diagnosed before 2000s years. CR and PR rates were 70% and 30%, respectively. Although the CR rates were lower in IFN group, this difference could not be reached statistically significance (p = 0.24). The median follow up was 48 months (12-252). The median OS was not reached and median PFS was 150 months (95% CI, 116-214). The OS at 36 and 48 months were 95.9% and 92.3%, respectively and the PFS at 36 and 48 months were 90.2% and 83.4%, respectively. After the introduction of purine analogues, the fate of the HCL patients have been changed. Cladrabin achieved very high response rates in both young and older patients, in our study. Although relapse still constitutes a problem, another single dose of cladrabine results in good response rates.

Is it possible to diagnose infectious oesophagitis without seeing the causative organism? A histopathological study.

BACKGROUND/AIMS: We investigated the utility of using histological changes to diagnose infectious oesophagitis when causative organisms cannot be seen. MATERIALS AND METHODS: Sixty-seven endoscopic biopsy specimens (51 Candida, 9 herpes simplex virus, 4 tuberculosis, and 3 cytomegalovirus oesophagitis) collected from 2000-2010 that matched the investigative criteria were included in the study. Cases were re-evaluated for histological changes observed in oesophagitis, and the findings were statistically compared using nonparametric tests. RESULTS: Thirty-nine cases occurred in male patients, and 28 occurred in female patients; the mean age of the patients was 51±20.1 years (range, 5-94 years). All cases showed lymphocytic and neutrophilic infiltration; while 27 (40.3%) showed eosinophilic infiltration. The density of lymphocytes and eosinophils were 8.43±6 and 1.07±1.62 per high power field, respectively, and these rates were higher in tuberculosis oesophagitis cases. Lamina propria infiltration was present in herpes simplex virus and Candida oesophagitis. Dense neutrophilic infiltration (>50/high power field) was noted in herpes simplex virus oesophagitis. Candida colonization was observed in 82% of cases with eosinophilic infiltration, and 80% of cases with erosion. Ulceration was present in all tuberculosis oesophagitis cases (p<0.001). Basal cell hyperplasia, papillary elongation, and dilated intercellular spaces were seen in all cases except for 2 Candida oesophagitis cases. Lamina propria fibrosis was especially noted in cytomegalovirus oesophagitis cases. CONCLUSION: It is not possible to distinguish infectious oesophagitis from other subtypes, especially reflux oesophagitis, if the causative organism is not detected. Clinicopathological correlation and control with repeat targeted biopsies are essential for diagnosis.

Prognostic significance of bcl-2, c-myc, survivin and tumor grade in synovial sarcoma.

OBJECTIVE: We aimed to determine the prognostic value of bcl-2, c-myc and survivin in synovial sarcoma cases and to evaluate the relationship between the conventional morphological findings with prognosis. MATERIAL AND METHOD: In this study, we evaluated 81 synovial sarcoma cases referred to our tertiary tumor center during a period of 20 years. We applied bcl-2, c-myc and survivin immunohistochemically and investigated the relationship with prognosis for those 65 cases with follow-up. The relationship between the conventional morphological findings (mitosis, necrosis, grade) with prognosis was also investigated. RESULTS: Five-year disease free survival rate was 44% and ten-year progression free survival rate was 38%, reflecting the aggressive behavior of synovial sarcoma. Tumor grade (according to FNCLCC) was the most significant prognostic input in this study. We obtained a significant difference between grade II (40 cases) and grade III (24 cases) group regarding progression-free survival and overall survival (p < 0.001 and p < 0.001 respectively). Grade II was divided into two groups according to mitotic index and necrosis (grade IIa and IIb) and there was a significant difference between them regarding prognosis (p=0.013 for progression free survival, p=0.003 for overall survival). There was a significant relationship between bcl-2 negative plus focally weak positive cases (9 cases) and focally strong cases (21 cases) and diffuse strong cases (35 cases) (p=0.042 and p=0.016 respectively). There was a significant relation between c-myc negative cases (25 cases) and nuclear positive cases (17 cases) regarding overall survival (p=0.043) and between c-myc negative cases and cytoplasmic positive cases (23 cases) regarding progression free survival (p=0.05). The relation between survivin and prognosis was not significant. CONCLUSION: Tumor grade was the most significant prognostic parameter in this study. The grade IIa group (with less than 10 mitoses in 10 HPF, without necrosis) had a better prognosis than both the grade IIb and III groups. The grade IIb group was closer to grade III regarding the prognosis. Bcl-2 and c-myc (nuclear and/or cytoplasmic) immunohistochemical positivity had prognostic value but this finding has to be confirmed by large series.