The 1000 Mitoses Project: A Consensus-Based International Collaborative Study on Mitotic Figures Classification.

Introduction. The identification of mitotic figures is essential for the diagnosis, grading, and classification of various different tumors. Despite its importance, there is a paucity of literature reporting the consistency in interpreting mitotic figures among pathologists. This study leverages publicly accessible datasets and social media to recruit an international group of pathologists to score an image database of more than 1000 mitotic figures collectively. Materials and Methods. Pathologists were instructed to randomly select a digital slide from The Cancer Genome Atlas (TCGA) datasets and annotate 10-20 mitotic figures within a 2 mm2 area. The first 1010 submitted mitotic figures were used to create an image dataset, with each figure transformed into an individual tile at 40x magnification. The dataset was redistributed to all pathologists to review and determine whether each tile constituted a mitotic figure. Results. Overall pathologists had a median agreement rate of 80.2% (range 42.0%-95.7%). Individual mitotic figure tiles had a median agreement rate of 87.1% and a fair inter-rater agreement across all tiles (kappa = 0.284). Mitotic figures in prometaphase had lower percentage agreement rates compared to other phases of mitosis. Conclusion. This dataset stands as the largest international consensus study for mitotic figures to date and can be utilized as a training set for future studies. The agreement range reflects a spectrum of criteria that pathologists use to decide what constitutes a mitotic figure, which may have potential implications in tumor diagnostics and clinical management.

A needle in the haystack: An unusual case presentation of ganglioneuroblastoma at a tertiary care center in Coastal Karnataka.

Key Clinical Message: This case report highlights the importance of recognizing and accurately diagnosing ganglioneuroblastoma, an uncommon variant of neuroblastic tumors in children. Ganglioneuroblastomas have diverse clinical and morphological presentations, and histopathological examination is paramount in guiding treatment decisions, especially in cases with ambiguous symptoms. Early detection is crucial, as the prognosis varies significantly based on the subtype and the presence of metastatic disease. Clinicians should maintain a high index of suspicion and utilize radiological examinations to promptly identify and treat these tumors. Abstract: Children are frequently affected by neuroblastic tumors, which grow from the sympathoadrenal lineage of the neural crest during its development. However, intermixed ganglioneuroblastomas are far less common within the same tumor spectrum, the diagnosis of which could become challenging amidst an unusual presentation. In our case report, we present a 4-year-old boy who had complaints of fever and difficulty in walking, with a supra-renal mass on ultrasound, which was diagnosed as ganglioneuroblastoma-intermixed type on histopathological examination. This report aims to contribute to the understanding of the diverse clinical and morphological spectrum of ganglioneuroblastomas and the importance of multidisciplinary collaboration and histopathological examination to enhance decision-making in such ambiguous scenarios.

p16 expression in urothelial carcinoma: Experience from a tertiary care center in coastal South India.

Background: Urothelial carcinomas (UC) account for 6 and 2% of all cancers in men and women, respectively. Human papillomavirus (HPV) is one of the causative agents in cancers of the uterine cervix and head and neck. The role of HPV is also being studied in cancers of the urinary bladder, penis, and prostate. As p16-INK4a is a surrogate marker for high-risk HPVE7 oncoprotein, this study aims to highlight the utility of p16 immunohistochemistry (IHC) in the evaluation of HPV-associated UC. Materials and Methods: A retrospective study was conducted on UC of the bladder received in the Pathology department between January 2013 and December 2018. Bladder biopsies from non-neoplastic lesions served as controls. IHC was done for the detection of the p16 antigen. The p16 staining was recorded as positive, when there was strong staining in >50% of tumor nuclei. The p16 positive and negative tumors were compared based on age, gender, tumor size, grade, and muscle invasion. P value <0.05 was considered statistically significant. Results: The expression of p16 was analyzed in 72 UC and compared with 20 non-neoplastic cases, of which 26.4% of the cases showed p16 expression. The p16 expression was absent in the non-neoplastic lesions. While the majority (87.5%) of the low-grade tumors were negative for p16 expression, 43.8% high-grade tumors were positive. Similarly, a larger proportion of invasive carcinomas (38.8%) expressed p16 as compared to non-invasive carcinomas (13.8%). Thus, p16 expression showed a significant association with grade and stage in these malignancies (P < 0.05). Conclusion: The p16 expression was associated with high-grade and muscle-invasive UC. The p16 was absent in all non-neoplastic and precursor lesions. Thus, it can provide essential information not only about HPV association but also on the prognostic implications for the patients.

Primary Ovarian Non-Hodgkin's Lymphoma: An 18-year Retrospective Institutional Study and Review of Literature from India.

BACKGROUND: Primary lymphomas of the female reproductive tract are rare and the ovarian extranodal presentation of non-Hodgkin's lymphoma (NHL) accounts for only 0.5% of all NHLs and 1.5% of all ovarian malignancies. METHODS: We retrospectively reviewed the institutional medical oncology database for newly diagnosed NHL cases between 1999 and 2017. We aimed to study the clinical characteristics, pathology, and outcome of primary ovarian non-Hodgkin's lymphoma (NHL) cases presented to our institution. RESULTS: We identified three patients (3.7% of extranodal NHLs and 0.85% of all NHL patients) with primary ovarian NHL from 350 NHL patient records. They underwent total abdominal hysterectomy and bilateral salpingo-oophorectomy followed by six to eight cycles of (rituximab, adriamycin, cyclophosphamide, vincristine, prednisolone (R-CHOP/CHOP), and they attained complete remission. CONCLUSION: Given the heterogeneity of cancer incidence in India and the absence of state-wise cancer registries, our study argues a pressing need to develop a national representative registry for NHL for accurate incidence, mortality, and survival data. Additionally, fertility preservation is an important issue that must be discussed with women of fertile age and the parents of children.

A novel dataset and efficient deep learning framework for automated grading of renal cell carcinoma from kidney histopathology images.

Trends of kidney cancer cases worldwide are expected to increase persistently and this inspires the modification of the traditional diagnosis system to respond to future challenges. Renal Cell Carcinoma (RCC) is the most common kidney cancer and responsible for 80-85% of all renal tumors. This study proposed a robust and computationally efficient fully automated Renal Cell Carcinoma Grading Network (RCCGNet) from kidney histopathology images. The proposed RCCGNet contains a shared channel residual (SCR) block which allows the network to learn feature maps associated with different versions of the input with two parallel paths. The SCR block shares the information between two different layers and operates the shared data separately by providing beneficial supplements to each other. As a part of this study, we also introduced a new dataset for the grading of RCC with five different grades. We obtained 722 Hematoxylin & Eosin (H &E) stained slides of different patients and associated grades from the Department of Pathology, Kasturba Medical College (KMC), Mangalore, India. We performed comparable experiments which include deep learning models trained from scratch as well as transfer learning techniques using pre-trained weights of the ImageNet. To show the proposed model is generalized and independent of the dataset, we experimented with one additional well-established data called BreakHis dataset for eight class-classification. The experimental result shows that proposed RCCGNet is superior in comparison with the eight most recent classification methods on the proposed dataset as well as BreakHis dataset in terms of prediction accuracy and computational complexity.

Automated Molecular Subtyping of Breast Carcinoma Using Deep Learning Techniques.

OBJECTIVE: Molecular subtyping is an important procedure for prognosis and targeted therapy of breast carcinoma, the most common type of malignancy affecting women. Immunohistochemistry (IHC) analysis is the widely accepted method for molecular subtyping. It involves the assessment of the four molecular biomarkers namely estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and antigen Ki67 using appropriate antibody reagents. Conventionally, these biomarkers are assessed manually by a pathologist, who finally combines individual results to identify the molecular subtype. Molecular subtyping necessitates the status of all the four biomarkers together, and to the best of our knowledge, no such automated method exists. This paper proposes a novel deep learning framework for automatic molecular subtyping of breast cancer from IHC images. METHODS AND PROCEDURES: A modified LadderNet architecture is proposed to segment the immunopositive elements from ER, PR, HER2, and Ki67 biomarker slides. This architecture uses long skip connections to pass encoder feature space from different semantic levels to the decoder layers, allowing concurrent learning with multi-scale features. The entire architecture is an ensemble of multiple fully convolutional neural networks, and learning pathways are chosen adaptively based on input data. The segmentation stage is followed by a post-processing stage to quantify the extent of immunopositive elements to predict the final status for each biomarker. RESULTS: The performance of segmentation models for each IHC biomarker is evaluated qualitatively and quantitatively. Furthermore, the biomarker prediction results are also evaluated. The results obtained by our method are highly in concordance with manual assessment by pathologists. CLINICAL IMPACT: Accurate automated molecular subtyping can speed up this pathology procedure, reduce pathologists' workload and associated costs, and facilitate targeted treatment to obtain better outcomes.

Study of pre-operative neutrophil-lymphocyte ratio in urothelial carcinoma.

OBJECTIVES: Neutrophil-lymphocyte ratio (NLR), as an indicator of heightened systemic inflammatory response, predicts increased disease burden and poor oncological outcomes in urothelial carcinoma (UC). The study was undertaken with an aim to evaluate the association of NLR with clinicopathological variables and survival outcomes. METHODS: A total of 80 patients of UC were enrolled in the current retrospective study. Pre-operative NLR (within one month prior to the procedure), patient age, sex, tumour grade, pathological stage, recurrence free survival (RFS), progression free survival (PFS) and cancer specific survival (CSS) were recorded. We chose a cut-off value of 2.7 for NLR and patients were divide into two groups (NLR <2.7 and ≥2.7). RESULTS: NLR ≥2.7 was significantly associated with advanced tumour stage (p=0.001), but not with tumour grade (p=0.116). Progression (p=0.032) and death rates (p=0.026) were high in patients with NLR ≥2.7. Mean RFS (p=0.03), PFS (p=0.04) and CSS (p=0.04) were reduced in patients with NLR ≥2.7. On univariate analysis, NLR ≥2.7 predicted worse RFS (HR=2.928, p=0.007), PFS (HR=3.180, p=0.006) and CSS (HR=3.109, p=0.016). However, it was not an independent predictor of outcomes on multivariate analysis. CONCLUSIONS: Tumour stage and grade are the only independent predictors of RFS, PFS and CSS. High NLR at a cut-off value of ≥2.7 is associated with advanced pathological stage, but does not have an independent predictive value for RFS, PFS and CSS.

Heat exertion precipitating shock and death in a case of previously undiagnosed sickle-cell disease.

Sickle cell disease (SCD) is an autosomal recessive genetic condition characterized by the presence of a mutated form of haemoglobin (HbS). HbS polymerises into long needle-like fibres under low oxygen conditions, leading to the erythrocytes forming sickle shaped red blood cells. With repeated sickling, the red blood cells become irreversibly sickled and trapped within the circulation, and this leads to vaso-occlusive crisis. The patient, a 25-year-old female, previously undiagnosed with SCD, presented with high grade fever, splenomegaly and succumbed due to heat exertion precipitating sickling crisis, multiorgan failure and shock.

Kikuchi-Fujimoto disease in a tertiary care teaching hospital in Coastal South India: A 8-year retrospective study.

Background: Kikuchi-Fujimoto disease (KFD) is a rare, benign condition of unknown etiology, presenting as cervical lymphadenitis. Lymphadenopathy is usually tender and maybe associated with systemic symptoms. Despite the extensive literature on this disease, it continues to be misdiagnosed owing to its misleading clinical presentation. METHODS: A retrospective hospital-based descriptive cross-sectional study was conducted in tertiary care hospitals from 2011 to 2019. All patients with confirmed KFD diagnosis were included and after ethics committee approval the clinical details and histopathological data was retrieved from the medical records department and analyzed. RESULTS: A total of 67 cases were included. The mean age was 26.9±11.3 years with a female: male ratio of 1.9:1. There were 50 patients with tender cervical lymphadenopathy which was the most common clinical presentation. The mean length and width of palpable lymph nodes were 2.3±1.0 cm and 2.2±0.7 cm respectively. Histology revealed proliferative stage in majority of patients ( n=40, 59.7%). Lymphadenopathy resolved in 83.6% within 2 months. There were 42 patients who had complete recovery with symptomatic treatment within a period of 9 months. CONCLUSIONS: KFD is prevalent in young, female patients of Asian descent and often presents as tender cervical lymphadenopathy. Early diagnosis with excisional lymph node biopsy is crucial to avoid unnecessary investigations and treatment. Treatment is symptomatic unless complicated, where steroid therapy is considered. KFD has an excellent prognosis with almost no risk of fatality.

Spindle cell carcinoma masquerading as a benign polyp of the soft palate.

Spindle cell carcinoma of the head and neck is a rare biphasic neoplasm. The presentation mimics other head-and-neck malignancies and hence the diagnosis hinges upon histopathological confirmation along with positive immunohistochemistry (IHC) markers denoting the presence of both epithelial and mesenchymal components. At present, there are no standard management criteria for these tumors with the options varying from surgery alone to surgery combined with adjuvant radiotherapy. We discuss here the case of a patient presenting with an oropharyngeal mass that had benign clinical features and the final diagnosis of spindle cell carcinoma could only be established after histopathology with IHC typing.

p63-positive prostate carcinoma-A very rare presentation.

Prostate cancer being the world's leading cause of cancer and also the second most common cancer in men is posing challenges in its diagnosis. Immunohistochemistry with markers like high molecular weight cytokeratin, p63 aid in the diagnosis. The absence of p63 and high molecular weight cytokeratin and presence of p504s in the biopsies indicate malignant lesions. Yet, there is a loophole to this too. A rare case of p63-positive prostatic adenocarcinoma in an 87-year-old patient, with immunohistochemistry results showing overexpression of p63 in the nuclei of the malignant glands. This tumor shows high molecular weight cytokeratin negativity, and p504s positivity. Prognosis of this variant of the tumor is mostly favorable. Prompt treatment will halt the progression of this tumor and prevent paraplegia. Radical prostatectomy could be avoided by treatment modalities like androgen blockade and brachytherapy, as morbidity is very high with radical prostatectomy surgery.

Deep structured residual encoder-decoder network with a novel loss function for nuclei segmentation of kidney and breast histopathology images.

To improve the process of diagnosis and treatment of cancer disease, automatic segmentation of haematoxylin and eosin (H & E) stained cell nuclei from histopathology images is the first step in digital pathology. The proposed deep structured residual encoder-decoder network (DSREDN) focuses on two aspects: first, it effectively utilized residual connections throughout the network and provides a wide and deep encoder-decoder path, which results to capture relevant context and more localized features. Second, vanished boundary of detected nuclei is addressed by proposing an efficient loss function that better train our proposed model and reduces the false prediction which is undesirable especially in healthcare applications. The proposed architecture experimented on three different publicly available H&E stained histopathological datasets namely: (I) Kidney (RCC) (II) Triple Negative Breast Cancer (TNBC) (III) MoNuSeg-2018. We have considered F1-score, Aggregated Jaccard Index (AJI), the total number of parameters, and FLOPs (Floating point operations), which are mostly preferred performance measure metrics for comparison of nuclei segmentation. The evaluated score of nuclei segmentation indicated that the proposed architecture achieved a considerable margin over five state-of-the-art deep learning models on three different histopathology datasets. Visual segmentation results show that the proposed DSREDN model accurately segment the nuclear regions than those of the state-of-the-art methods.

Clinical benefit of R-CHOP without splenectomy in stage I primary splenic diffuse large B-cell lymphoma.

Primary splenic diffuse large B-cell lymphoma (PS-DLBCL) is a relatively rare malignancy, and there are no optimal approaches for diagnosis and management. There are less invasive splenic biopsies that effectively obviate diagnostic and elective splenectomies. We report a man in his 50s with 2-day history of pain in the abdomen and who was found to have a splenic mass on PET-CT. A CT-guided core needle splenic biopsy confirmed the diagnosis of PS-DLBCL. He was managed with six cycles of R-CHOP (rituximab, cyclophosphamide, doxorubicin, vincristine, prednisone) alone, without splenectomy. The patient attained complete remission, and he is disease free at 6 years of follow-up.

High-resolution deep transferred ASPPU-Net for nuclei segmentation of histopathology images.

PURPOSE: Increasing cancer disease incidence worldwide has become a major public health issue. Manual histopathological analysis is a common diagnostic method for cancer detection. Due to the complex structure and wide variability in the texture of histopathology images, it has been challenging for pathologists to diagnose manually those images. Automatic segmentation of histopathology images to diagnose cancer disease is a continuous exploration field in recent times. Segmentation and analysis for diagnosis of histopathology images by using an efficient deep learning algorithm are the purpose of the proposed method. METHOD: To improve the segmentation performance, we proposed a deep learning framework that consists of a high-resolution encoder path, an atrous spatial pyramid pooling bottleneck module, and a powerful decoder. Compared to the benchmark segmentation models having a deep and thin path, our network is wide and deep that effectively leverages the strength of residual learning as well as encoder-decoder architecture. RESULTS: We performed careful experimentation and analysis on three publically available datasets namely kidney dataset, Triple Negative Breast Cancer (TNBC) dataset, and MoNuSeg histopathology image dataset. We have used the two most preferred performance metrics called F1 score and aggregated Jaccard index (AJI) to evaluate the performance of the proposed model. The measured values of F1 score and AJI score are (0.9684, 0.9394), (0.8419, 0.7282), and (0.8344, 0.7169) on the kidney dataset, TNBC histopathology dataset, and MoNuSeg dataset, respectively. CONCLUSION: Our proposed method yields better results as compared to benchmark segmentation methods on three histopathology datasets. Visual segmentation results justify the high value of the F1 score and AJI scores which indicated that it is a very good prediction by our proposed model.

Efficient deep learning architecture with dimension-wise pyramid pooling for nuclei segmentation of histopathology images.

Image segmentation remains to be one of the most vital tasks in the area of computer vision and more so in the case of medical image processing. Image segmentation quality is the main metric that is often considered with memory and computation efficiency overlooked, limiting the use of power hungry models for practical use. In this paper, we propose a novel framework (Kidney-SegNet) that combines the effectiveness of an attention based encoder-decoder architecture with atrous spatial pyramid pooling with highly efficient dimension-wise convolutions. The segmentation results of the proposed Kidney-SegNet architecture have been shown to outperform existing state-of-the-art deep learning methods by evaluating them on two publicly available kidney and TNBC breast H&E stained histopathology image datasets. Further, our simulation experiments also reveal that the computational complexity and memory requirement of our proposed architecture is very efficient compared to existing deep learning state-of-the-art methods for the task of nuclei segmentation of H&E stained histopathology images. The source code of our implementation will be available at https://github.com/Aaatresh/Kidney-SegNet.

LiverNet: efficient and robust deep learning model for automatic diagnosis of sub-types of liver hepatocellular carcinoma cancer from H&E stained liver histopathology images.

PURPOSE: Liver cancer is one of the most common types of cancers in Asia with a high mortality rate. A common method for liver cancer diagnosis is the manual examination of histopathology images. Due to its laborious nature, we focus on alternate deep learning methods for automatic diagnosis, providing significant advantages over manual methods. In this paper, we propose a novel deep learning framework to perform multi-class cancer classification of liver hepatocellular carcinoma (HCC) tumor histopathology images which shows improvements in inference speed and classification quality over other competitive methods. METHOD: The BreastNet architecture proposed by Togacar et al. shows great promise in using convolutional block attention modules (CBAM) for effective cancer classification in H&E stained breast histopathology images. As part of our experiments with this framework, we have studied the addition of atrous spatial pyramid pooling (ASPP) blocks to effectively capture multi-scale features in H&E stained liver histopathology data. We classify liver histopathology data into four classes, namely the non-cancerous class, low sub-type liver HCC tumor, medium sub-type liver HCC tumor, and high sub-type liver HCC tumor. To prove the robustness and efficacy of our models, we have shown results for two liver histopathology datasets-a novel KMC dataset and the TCGA dataset. RESULTS: Our proposed architecture outperforms state-of-the-art architectures for multi-class cancer classification of HCC histopathology images, not just in terms of quality of classification, but also in computational efficiency on the novel proposed KMC liver data and the publicly available TCGA-LIHC dataset. We have considered precision, recall, F1-score, intersection over union (IoU), accuracy, number of parameters, and FLOPs as metrics for comparison. The results of our meticulous experiments have shown improved classification performance along with added efficiency. LiverNet has been observed to outperform all other frameworks in all metrics under comparison with an approximate improvement of [Formula: see text] in accuracy and F1-score on the KMC and TCGA-LIHC datasets. CONCLUSION: To the best of our knowledge, our work is among the first to provide concrete proof and demonstrate results for a successful deep learning architecture to handle multi-class HCC histopathology image classification among various sub-types of liver HCC tumor. Our method shows a high accuracy of [Formula: see text] on the proposed KMC liver dataset requiring only 0.5739 million parameters and 1.1934 million floating point operations per second.

NucleiSegNet: Robust deep learning architecture for the nuclei segmentation of liver cancer histopathology images.

The nuclei segmentation of hematoxylin and eosin (H&E) stained histopathology images is an important prerequisite in designing a computer-aided diagnostics (CAD) system for cancer diagnosis and prognosis. Automated nuclei segmentation methods enable the qualitative and quantitative analysis of tens of thousands of nuclei within H&E stained histopathology images. However, a major challenge during nuclei segmentation is the segmentation of variable sized, touching nuclei. To address this challenge, we present NucleiSegNet - a robust deep learning network architecture for the nuclei segmentation of H&E stained liver cancer histopathology images. Our proposed architecture includes three blocks: a robust residual block, a bottleneck block, and an attention decoder block. The robust residual block is a newly proposed block for the efficient extraction of high-level semantic maps. The attention decoder block uses a new attention mechanism for efficient object localization, and it improves the proposed architecture's performance by reducing false positives. When applied to nuclei segmentation tasks, the proposed deep-learning architecture yielded superior results compared to state-of-the-art nuclei segmentation methods. We applied our proposed deep learning architecture for nuclei segmentation to a set of H&E stained histopathology images from two datasets, and our comprehensive results show that our proposed architecture outperforms state-of-the-art methods. As part of this work, we also introduced a new liver dataset (KMC liver dataset) of H&E stained liver cancer histopathology image tiles, containing 80 images with annotated nuclei procured from Kasturba Medical College (KMC), Mangalore, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, India. The proposed model's source code is available at https://github.com/shyamfec/NucleiSegNet.

In pursuit of the primary.

Extraovarian primary peritoneal carcinoma (EOPPC) is a rare tumour of the peritoneum that shares many features with serous ovarian carcinoma because of a common embryological origin. We report a case of EOPPC presenting with a malignant pleural effusion. https://bit.ly/3GMuKgL.

Genetic diversity of Indian Plasmodium vivax isolates based on the analysis of PvMSP3ß polymorphic marker.

BACKGROUND: Malaria is one of the major communicable diseases in India and worldwide. PvMSP3ß is a highly polymorphic gene due to its large insertions and deletions in the central alanine-rich region, which, in turn, makes it a valuable marker for population genetic analysis. Very few studies are available from India about the genetic diversity of Plasmodium vivax based on PvMSP3ß gene, and hence, this study was designed to understand the molecular diversity of the P. vivax malaria parasite. The accumulating epidemiological data provide insights into the circulating genetic variants of P. vivax in India, and ultimately benefits the vaccine development. MATERIALS AND METHODS: A total of 268 samples confirmed to be positive by microscopy, rapid diagnostic test, and quantitative buffy coat test were collected from four different regions of India (Puducherry, Mangaluru, Jodhpur, and Cuttack) in the present study. Polymerase chain reaction (PCR)-based diagnosis was carried out to confirm the P. vivax monoinfection, and only the mono-infected samples were subjected to PvMSP3ß gene amplification and further restriction fragment length polymorphism (RFLP) to determine suballeles. RESULTS: Based on the size of the amplified fragment, the PvMSP3ß gene was apportioned into two major types, namely Type A genotype (1.6-2 Kb) was predominantly present in 148 isolates and Type B (1-1.5 Kb) was observed in 110 isolates. The percentage of mixed infections by PCR was 3.73%. All the PCR products were subjected to RFLP to categorize into suballeles and we detected 39 suballeles (A1-A39) in Type A, and 23 suballeles (B1-B23) in Type B genotype. A high degree of diversity was observed among the isolates collected from Mangaluru region when compared to isolates collected from other regions. CONCLUSION: The present study showed a high degree of genetic diversity of PvMSP3ß gene among the isolates collected from various parts of India. High polymorphism in PvMSP3ß gene makes it a promising marker for epidemiological and vaccine development studies.