Classification of H. pylori Infection from Histopathological Images Using Deep Learning.

Helicobacter pylori (H. pylori) is a widespread pathogenic bacterium, impacting over 4 billion individuals globally. It is primarily linked to gastric diseases, including gastritis, peptic ulcers, and cancer. The current histopathological method for diagnosing H. pylori involves labour-intensive examination of endoscopic biopsies by trained pathologists. However, this process can be time-consuming and may occasionally result in the oversight of small bacterial quantities. Our study explored the potential of five pre-trained models for binary classification of 204 histopathological images, distinguishing between H. pylori-positive and H. pylori-negative cases. These models include EfficientNet-b0, DenseNet-201, ResNet-101, MobileNet-v2, and Xception. To evaluate the models' performance, we conducted a five-fold cross-validation, ensuring the models' reliability across different subsets of the dataset. After extensive evaluation and comparison of the models, ResNet101 emerged as the most promising. It achieved an average accuracy of 0.920, with impressive scores for sensitivity, specificity, positive predictive value, negative predictive value, F1 score, Matthews's correlation coefficient, and Cohen's kappa coefficient. Our study achieved these robust results using a smaller dataset compared to previous studies, highlighting the efficacy of deep learning models even with limited data. These findings underscore the potential of deep learning models, particularly ResNet101, to support pathologists in achieving precise and dependable diagnostic procedures for H. pylori. This is particularly valuable in scenarios where swift and accurate diagnoses are essential.

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.

COVID-19 Disease in a Kidney Transplant Recipient With Diffuse Intrarenal Hemorrhage.

Presentation of COVID-19 in renal transplant recipients is similar to that shown in the nonimmunocompromised population; almost all recipients who have this disease present with symptoms of the respiratory system. Acute kidney injury has been found prevalent in transplant recipients with COVID-19. In those with severe COVID-19 disease who transfer to an intensive care unit prevalence of acute kidney injury is more than 50%. The pathophysiological mechanisms of kidney involvement and the type of involvement are unclear. Here, we present a 71-year-old kidney transplant recipient who was admitted to our hospital with pulmonary and renal involvement. A kidney allograft biopsy demonstrated diffuse intrarenal hemorrhage, capillary congestion, and severe acute tubular injury. COVID-19 RNA was detected by real-time polymerase chain reaction from lysed allograft tissues, but no findings of acute or chronic cellular or antibody-mediated rejection were detected. This case indicates that COVID-19 may involve the allograft by causing hemorrhage within the renal parenchymal via direct or indirect pathways.

Incidence, Histopathological Features and Differential Diagnosis of Cutaneous Graft Versus Host Disease in Allogeneic Bone Marrow Transplantation.

OBJECTIVES: Hematopoietic stem cell transplantation by allogeneic bone marrow transplantation is a method used in the treatment of various genetic, immunological disorders, hematologic and solid organ malignancies. Graft versus Host Disease is one of the major and fatal complications of allogeneic bone marrow transplantation. It is a systemic disease affecting five main areas: skin, gastrointestinal tract, liver, lung and hematopoietic system. Diagnosis of cutaneous Graft versus Host Disease is made by the correlation between clinical and histopathological findings of the patient. The present study aims to investigate the incidence of cutaneous graft versus Host Disease in allogeneic bone marrow transplantation patients in our center, to discuss the histopathological features and differential diagnosis of cutaneous graft versus Host Disease in the light of the literature. METHODS: The pathology slides of allogeneic bone marrow transplantation patients who were diagnosed as graft versus Host Disease in our pathology department between January 2015 and January 2019 were re-evaluated. Epidermal and dermal histomorphological findings of the disease were classified; the patients' clinical and demographic information was obtained from the files. The incidence of cutaneous Graft versusHost Disease was calculated. RESULTS: In our center, between January 2015 and January 2019, 273 pediatric and 100 adult patients underwent allogeneic and 181 autologous bone marrow transplantation. Twenty-three patients who underwent allogeneic bone marrow transplantation had cutaneous Graft versus Host Disease whereas and 21 patients had gastrointestinal Graft versus Host Disease. The incidence of cutaneous and gastrointestinal Graft versus Host Disease was 16.1% whereas the incidence of cutaneous Graft versus Host Disease was 8.42%. The most common clinical differential diagnosis of cutaneous Graft versus Host Disease was drug reaction (74%). The most common epidermal histomorphologic finding in our cases was keratinocyte necrosis (87%). In our cases, the most common epidermal histomorphologic finding was keratinocyte necrosis (87%). This was followed by vacuolar degeneration in basal keratinocytes (63%), acanthosis and spongiosis (61%), respectively. The most common finding in the dermis was pigment incontinence (59%). Of the patients with Graft versus Host Disease, 56% had transplantation from unrelated donors, whereas 44% of them had transplantation from their relatives. CONCLUSION: Cutaneous Graft versus Host Disease is a common complication of allogeneic hematopoietic stem cell transplantation. It is associated with high mortality rates and has a significant negative impact on the patient's quality of life. Dermatological early recognition of the disease; histopathological evaluation and verification with differential diagnosis plays a key role in preventing patient morbidity and mortality.

Evaluation of the effect of topical and systemic ozone application in periodontitis: an experimental study in rats.

OBJECTIVE: The goal of the present study was to determine the effect of systemic and topical ozone application on alveolar bone loss (ABL) by evaluating the effect of Hypoxia-inducible factor -1 alpha (HIF-1-α) and receptor activator of NF-kB ligand (RANKL)-positive cells on histopathological and immunohistochemical changes in a rat periodontitis model. METHODOLOGY: Thirty male Wistar rats were divided into three groups: 1) Group C (control group); 2) Group SO (systemic ozone group) and 3) Group TO (topical ozone group). Experimental periodontitis was induced with a 3/0 silk suture placed at the mandibular left first molars of rats, and the suture was removed 14 days later. Ozone gas was injected intraperitoneally (0.7 mg/kg) in SO group. Topical ozone application protocol was performed using an ozone generator at 80% concentration (4th grade) 90- degree probe for the duration of 30 s. Both ozone applications were carried out for two weeks at intervals of two days. Histomorphometric and immunohistochemical analysis were performed. RESULTS: ABL was significantly lower in Group SO compared to Group C (p: 0.0052). HIF-1α- positive cells were significantly lower in Group TO than in Group C (p: 0.0043). RANKL-positive cells were significantly lower in Group SO and in Group TO compared to the control group (p: 0.0033, p: 0.0075, respectively). CONCLUSION: Both ozone applications decreased RANKL-positive cell counts, TO application decreased HIF-1-α positive cells counts, and SO application was found to be more effective in reducing ABL compared to control group.

Evaluation of the effect of topical and systemic ozone application in periodontitis: an experimental study in rats

Abstract Objective: The goal of the present study was to determine the effect of systemic and topical ozone application on alveolar bone loss (ABL) by evaluating the effect of Hypoxia-inducible factor −1 alpha (HIF-1-α) and receptor activator of NF-kB ligand (RANKL)-positive cells on histopathological and immunohistochemical changes in a rat periodontitis model. Methodology: Thirty male Wistar rats were divided into three groups: 1) Group C (control group); 2) Group SO (systemic ozone group) and 3) Group TO (topical ozone group). Experimental periodontitis was induced with a 3/0 silk suture placed at the mandibular left first molars of rats, and the suture was removed 14 days later. Ozone gas was injected intraperitoneally (0.7 mg/kg) in SO group. Topical ozone application protocol was performed using an ozone generator at 80% concentration (4th grade) 90- degree probe for the duration of 30 s. Both ozone applications were carried out for two weeks at intervals of two days. Histomorphometric and immunohistochemical analysis were performed. Results: ABL was significantly lower in Group SO compared to Group C (p: 0.0052). HIF-1α- positive cells were significantly lower in Group TO than in Group C (p: 0.0043). RANKL-positive cells were significantly lower in Group SO and in Group TO compared to the control group (p: 0.0033, p: 0.0075, respectively). Conclusion: Both ozone applications decreased RANKL-positive cell counts, TO application decreased HIF-1-α positive cells counts, and SO application was found to be more effective in reducing ABL compared to control group.

Cervical spine giant cell bone tumor: a case report.

BACKGROUND: Giant cell tumors (GCTs) of the bone are locally aggressive primary bone tumors with a benign character. Spinal involvement is rare and they are quite rare in the cervical spine. CASE PRESENTATION: A 31-year-old male patient presented with neck pain. Cervical CT revealed a lytic lesion extending posteriorly and causing the collapse of the C4 vertebra corpus. The patient underwent excision of the tumor extending from the anterior to the posterior with a single-stage anterior intervention followed by the placement of an anterior cage and plate-screw system for fusion. The pathology was reported as GCT. CONCLUSIONS: The posteriorly located lesion was widely curetted through an anterior approach in a single session.

Telecytology: Is it possible with smartphone images?

INTRODUCTION: This study aimed to discuss smartphone usage in telecytology and determine intraobserver concordance between microscopic cytopathological diagnoses and diagnoses derived via static smartphone images. METHODS: The study was conducted with 172 cytologic material. A pathologist captured static images of the cytology slides from the ocular lens of a microscope using a smartphone. The images were transferred via WhatsApp® to a cytopathologist working in another center who made all the microscopic cytopathological diagnoses 5-27 months ago. The cytopathologist diagnosed images on a smartphone without knowledge of their previous microscopic diagnoses. The Kappa agreement between microscopic cytopathological diagnoses and smartphone image diagnoses was determined. RESULTS: The average image capturing, transfer, and remote cytopathological diagnostic time for one case was 6.20 minutes. The percentage of cases whose microscopic and smartphone image diagnoses were concordant was 84.30%, and the percentage of those whose diagnoses were discordant was 15.69%. The highest Kappa agreement was observed in endoscopic ultrasound-guided fine needle aspiration (1.000), and the lowest agreement was observed in urine cytology (0.665). Patient management changed with smart phone image diagnoses at 11.04%. CONCLUSIONS: This study showed that easy, fast, and high-quality image capturing and transfer is possible from cytology slides using smartphones. The intraobserver Kappa agreement between the microscopic cytopathological diagnoses and remote smartphone image diagnoses was high. It was found that remote diagnosis due to difficulties in telecytology might change patient management. The developments in the smartphone camera technology and transfer software make them efficient telepathology and telecytology tools.