Morphologic features of prostate cancer-encased native vessels: An image analysis study.

BACKGROUND: Vasculature plays a crucial role in the progression of prostate cancer (PC). Changes to the prostatic native vessels have not been studied since 2000 when Garcia et al. demonstrated marked media hypercellularity and increased artery thickness in prostatic native arteries within PC. We aim to further evaluate and characterize prostatic native vessels with a more accurate method with the use of virtual slides and digital analysis. DESIGN: Pathologist-annotated whole-mount digital slides from 96 entirely submitted prostatectomies were annotated for PC (color-coded by Gleason) using Omero platform. A subset of 44 cases met criteria for further analysis of media thickness, cellularity, and wall thickness to lumen ratio. Cases were included based on containing ≥5 native arteries (≥100 µm diameter) encased on at least 3 sides by PC, with vessels (≥100 µm diameter) designated as controls if they were ≥ 1000 µm away from PC. Annotated vessels were segmented and processed using Matlab 2023b. Mean media thickness (corrected for oblique sections), media: lumen ratio (based on numbers of pixels), and media cellularity (nuclei count) were studied by analysis with SPSS by linear mixed model with nested random effects for subject and slide to account for repeated measures. RESULTS: Vessels encased by PC showed greater media thickness (p=0.02), cellularity (p=0.02) and wall thickness/lumen ratio (p= <0.001) compared to vessels away from PC. These values showed an increasing trend according to stage in cellularity (p=0.14), media thickness (p=0.12) and wall thickness/ lumen ratio (p= 0.33) with higher stage (pT3). A Gleason group comparison showed a borderline-significant gradewise trend when analyzing wall thickness/lumen ratio (p=0.06). Grade 5 emerged as significantly different (p=0.02) from grades 3 or 4 non-cribriform. CONCLUSIONS: Similar to the 2000 study, increased media thickness and hypercellularity of vessels encased by PC were evident compared to controls. Borderline grade-dependent increased vessel cellularity changes were seen, suggesting a possible role in PC progression; the predictive value of these changes for outcome is uncertain. Whether the etiology of changes reflects locally increased intravascular pressure of vessels within tumor should be investigated.

NuInsSeg: A fully annotated dataset for nuclei instance segmentation in H&E-stained histological images.

In computational pathology, automatic nuclei instance segmentation plays an essential role in whole slide image analysis. While many computerized approaches have been proposed for this task, supervised deep learning (DL) methods have shown superior segmentation performances compared to classical machine learning and image processing techniques. However, these models need fully annotated datasets for training which is challenging to acquire, especially in the medical domain. In this work, we release one of the biggest fully manually annotated datasets of nuclei in Hematoxylin and Eosin (H&E)-stained histological images, called NuInsSeg. This dataset contains 665 image patches with more than 30,000 manually segmented nuclei from 31 human and mouse organs. Moreover, for the first time, we provide additional ambiguous area masks for the entire dataset. These vague areas represent the parts of the images where precise and deterministic manual annotations are impossible, even for human experts. The dataset and detailed step-by-step instructions to generate related segmentation masks are publicly available on the respective repositories.

Conjunctival leiomyosarcoma: A clinico-pathological study with in deep molecular characterization.

BACKGROUND: Primary and metastatic leiomyosarcomas (LMS) involving the orbital region are well known to occur however, the conjunctiva represents an extremely rare site of occurrence. METHODS: A 97-year-old male was referred to the Ocular Oncology Unit due to a rapidly growing painful mass (16×12×20 mm) in the nasal conjunctiva of his left eye. Wide excision followed by radiotherapy was performed. RESULTS: Based on the microscopic features (hypercellular neoplasm composed of spindle cells with cigar shaped and blunt ended nuclei with brightly eosinophilic fibrillary cytoplasm) and immunohistochemical findings (positive staining for Vimentin, Desmin, Caldesmon, and SMA and negative staining for AE1/AE3, EMA, CD117, S100, MelanA, SOX10, HMB45, TLE1, CD99, EMA and AE1 / AE3) the final diagnosis of grade 2 leyomiosarcoma was rendered. Moreover, 'in deep' DNA sequencing (>500 genes analysis) revealed a neoplasm with high TMB: 64 muts/Mb and numerous VUS and several pathogenic/oncogenic molecular alterations, including CNV loss or gain in > 10 genes. At the last follow-up visit, residual disease was observed in the superior fornix, at the nasal limbus and the cornea. At the time of writing, after a follow-up of 2 month the patients is still alive without evidence of metastatic disease. CONCLUSION: An uncommon molecular finding observed in our case was the presence of TSC1 gene mutation usually associated with soft tissue and gynecological PEComas. Our finding may harbor important therapeutic implications since the inactivation of the tumor suppressor genes TSC1 and TSC2 lead to upregulation of mTOR signaling, providing the rationale for target therapy with mTOR inhibitors. Additional studies on larger series are needed to validate our findings.

HoLy-Net: Segmentation of histological images of diffuse large B-cell lymphoma.

Over the last years, there has been large progress in automated segmentation and classification methods in histological whole slide images (WSIs) stained with hematoxylin and eosin (H&E). Current state-of-the-art (SOTA) techniques are based on diverse datasets of H&E-stained WSIs of different types of predominantly solid cancer. However, there is a scarcity of methods and datasets enabling segmentation of tumors of the lymphatic system (lymphomas). Here, we propose a solution for segmentation of diffuse large B-cell lymphoma (DLBCL), the most common non-Hodgkin's lymphoma. Our method applies to both H&E-stained slides and to a broad range of markers stained with immunohistochemistry (IHC). While IHC staining is an important tool in cancer diagnosis and treatment decisions, there are few automated segmentation and classification methods for IHC-stained WSIs. To address the challenges of nuclei segmentation in H&E- and IHC-stained DLBCL images, we propose HoLy-Net - a HoVer-Net-based deep learning model for lymphoma segmentation. We train two different models, one for segmenting H&E- and one for IHC-stained images and compare the test results with the SOTA methods as well as with the original version of HoVer-Net. Subsequently, we segment patient WSIs and perform single cell-level analysis of different cell types to identify patient-specific tumor characteristics such as high level of immune infiltration. Our method outperforms general-purpose segmentation methods for H&E staining in lymphoma WSIs (with an F1 score of 0.899) and is also a unique automated method for IHC slide segmentation (with an F1 score of 0.913). With our solution, we provide a new dataset we denote LyNSeC (lymphoma nuclear segmentation and classification) containing 73,931 annotated cell nuclei from H&E and 87,316 from IHC slides. Our method and dataset open up new avenues for quantitative, large-scale studies of morphology and microenvironment of lymphomas overlooked by the current automated segmentation methods.

Aggressive renal cell carcinoma with biphasic papillary and solid clear cell features harboring IDH2 (R172M) mutation.

Renal cell carcinoma (RCC) is fundamentally a metabolic disease, and RCC associated with mutation of the Krebs cycle enzyme genes include fumarate hydratase-deficient and succinate dehydrogenase-deficient RCC. Most recently, the mutation of isocitrate dehydrogenase 2 (IDH2) has been suggested as the third Krebs cycle enzyme alteration to be associated with oncometabolite-induced RCC tumorigenesis. Herein, we report the second case of RCC harboring an IDH2 (R127M) mutation identified by targeted next-generation sequencing and further confirmed by reverse transcription polymerase chain reaction and Sanger sequencing. This tumor demonstrated a distinctive biphasic morphology, characterized by mixture of a clear cells solid component and an eosinophilic papillary component. These two components were intermingled and formed variably sized nodular or nested structures. Unfavorable histologic features, including infiltration into the perirenal and renal sinus adipose tissues, high nuclei grade, rhabdoid tumor cells, and focal tumor necrosis, were observed. The patient had local lymph nodes metastases at diagnosis and developed brain metastases 3 months after the surgery. This peculiar case provides further insights into RCCs harboring IDH2 mutations.

Blasts with folded nuclei: A histopathologic finding in myeloid leukemia cutis with NPM1 and FLT3 mutations.

Leukemia cutis is a term used to describe cutaneous manifestations of leukemic infiltration of the skin and portends a poor prognosis. Cutaneous involvement by hematopoietic/lymphoid tumors can occur before, concurrently, or after the initial diagnosis. Early involvement of dermatologists and timely biopsies play a crucial role in achieving a prompt diagnosis. Prior reports of acute myeloid leukemia have revealed a strong association between the cup-like nuclear morphology observed in bone marrow specimens and concurrent mutations of NPM1 and FLT3-ITD. In cutaneous tissue sections of leukemia cutis, folded or indented nuclei may represent the "cup-like" counterpart previously described in bone marrow specimens. Recognizing this morphological feature could aid in identifying this molecular subtype of leukemia cutis. In this study, we present a case of leukemia cutis in a 63-year-old female with AML and NPM1 and FLT3-ITD mutations, demonstrating scattered indented/folded nuclei.

Nuclei detection in breast histopathology images with iterative correction.

This work presents a deep network architecture to improve nuclei detection performance and achieve the high localization accuracy of nuclei in breast cancer histopathology images. The proposed model consists of two parts, generating nuclear candidate module and refining nuclear localization module. We first design a novel patch learning method to obtain high-quality nuclear candidates, where in addition to categories, location representations are also added to the patch information to implement the multi-task learning process of nuclear classification and localization; meanwhile, the deep supervision mechanism is introduced to obtain the coherent contributions from each scale layer. In order to refine nuclear localization, we propose an iterative correction strategy to make the prediction progressively closer to the ground truth, which significantly improves the accuracy of nuclear localization and facilitates neighbor size selection in the nonmaximum suppression step. Experimental results demonstrate the superior performance of our method for nuclei detection on the H&E stained histopathological image dataset as compared to previous state-of-the-art methods, especially in multiple cluttered nuclei detection, can achieve better results than existing techniques.

Digital analyses of nuclear features can help discriminate among non-invasive follicular thyroid neoplasm with papillary-like nuclear features, papillary thyroid carcinoma follicular subtype, and follicular carcinoma in cytological specimens.

BACKGROUND: As it stands, the diagnosis of non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) is primarily based on histological analysis. We hypothesised that computerised analysis of nuclear images of cytological specimens could be used to differentiate NIFTP from papillary thyroid carcinoma follicular subtype (PTCFS) and follicular carcinoma (FC), influencing patient management. METHODS: We employed a retrospective analytical observational study based on nuclear morphometric variables of cytological material from thyroid nodules classified as PTCFS, NIFTP, or FC. Five cases of each entity were analysed. Cytological slides were photographed, and 1170 cells for each entity were analysed digitally. The captured images were evaluated (blindly) using the ImageJ software package. The morphometric evaluation included area, perimeter, width, height, and circularity. Numerical variables were expressed as mean, median, minimum, and maximum (min; max) values. Kruskal-Wallis and Dunn's tests were used with a 5% significance level. RESULTS: Regarding nuclear analysis, all variables differed among the three groups (p < 0.001). Given the interdependence among the variables, these data indicated that nuclear size was greatest in the NIFTP group, followed by FC and PTCFS. DISCUSSION/CONCLUSION: Our analysis of the digital images, with a focus on nuclear parameters, found significantly difference among cytological specimens from cases of NIFTP, PTCFS and FC. Thus, this tool has the potential to provide additional information that may help in the diagnosis of NIFTP, even during the preoperative period. Additional studies are needed to create protocols, evaluate the applicability of nuclear morphological and morphometric parameters-focusing on digital pathology-and create algorithms and tools to assist cytopathologists with their diagnostic routines.

CoNIC Challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting.

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge's improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.

Discrimination of early HCC using single cell nucleus image and visualization of feature distribution in whole slide images.

Among hepatocellular carcinoma (HCC), early HCC such as well-differentiated hepatocellular carcinoma is more difficult to distinguish from non-cancer than other cancers. In particular, very well-differentiated hepatocellular carcinoma is even more difficult to distinguish, and it is difficult for pathologists to distinguish between cancer and non-cancer from a single nucleus image. If a function to distinguish cancer with a single cell nucleus image is realized, it may be possible to find new features related to nuclei that are useful for differentiating early HCC. The function will also be very helpful in needle biopsy where the area that can be observed is limited.In this study, we investigated the potential to discriminate cancer/non-cancer from an image of a single hepatocyte nucleus using CNN. The results indicated that discrimination was achievable with a correct rate of around 70%.The probability of cancer/non-cancer was visualized on WSI. The visualization results indicated a difference between cancerous and non-cancerous areas in 71% of the cases, which will help pathologists distinguish region of interest. Grouping sections with similar features also proved useful in improving accuracy and visualization results.

Cell migration in dense microenvironments.

The nucleus has been viewed as a passenger during cell migration that functions merely to protect the genome. However, increasing evidence shows that the nucleus is an active organelle, constantly sensing the surrounding environment and translating extracellular mechanical inputs into intracellular signaling. The nuclear envelope has a large membrane reservoir which serves as a buffer for mechanical inputs as it unfolds without increasing its tension. In contrast, when cells cope with mechanical strain, such as migration through solid tumors or dense interstitial spaces, the nuclear envelope folds stretch, increasing nuclear envelope tension and sometimes causing rupture. Different degrees of nuclear envelope tension regulate cellular behaviors and functions, especially in cells that move and grow within dense matrices. The crosstalk between extracellular mechanical inputs and the cell nucleus is a critical component in the modulation of cell function of cells that navigate within packed microenvironments. Moreover, there is a link between regimes of nuclear envelope unfolding and different cellular behaviors, from orchestrated signaling cascades to cellular perturbations and damage.

Le noyau a longtemps été considéré comme un passager lors de la migration cellulaire, servant simplement à protéger le génome. Cependant, de plus en plus de preuves montrent que le noyau est un organite actif, qui sonde le milieu environnant et traduit les entrées mécaniques extracellulaires en signalisation intracellulaire. L'enveloppe nucléaire possède un grand réservoir membranaire qui sert de tampon face aux entrées mécaniques en se dépliant sans augmenter sa tension. En revanche, lorsque les cellules font face à des contraintes mécaniques, telles que la migration au travers de tumeurs solides ou despaces interstitiels denses, les plis de l'enveloppe nucléaire s'étirent, augmentant sa tension et provoquant parfois sa rupture. Différents degrés de tension de l'enveloppe nucléaire régulent les comportements et les fonctions cellulaires, en particulier des cellules qui se déplacent et se développent dans des matrices denses. La signalisation croisée entre les entrées mécaniques extracellulaires et le noyau cellulaire sont des composants essentiels dans la modulation de la fonction des cellules qui naviguent dans des microenvironnements encombrés. De plus, il existe un lien entre les régimes de déploiement de l'enveloppe nucléaire et les différents comportements cellulaires, allant des cascades de signalisation jusquaux perturbations et dommages cellulaires.

Cytologic atypia of benign inflammatory versus neoplastic cutaneous squamous lesions.

BACKGROUND: Cytologic atypia encompasses several features of abnormal cellular morphology. We sought to quantify these features in benign and premalignant/malignant squamous cell lesions to better characterize criteria for malignancy. METHODS: We conducted a rater-blinded observational study in which histopathology slides were evaluated under light microscopy, and the presence and relative quantity of 24 distinct cytological features were recorded, along with respective diagnoses. Each slide was evaluated, and the ratings were recorded and analyzed. RESULTS: The most helpful findings, whose presence in high numbers indicates an increased likelihood that the tissue sample is premalignant/malignant, were: (1) pleomorphic parakeratosis; (2) pleomorphic nuclei in the epithelium; (3) irregular nuclei; (4) thick refractile nuclear envelope; (5) presence of nuclear hyperchromasia (dark gray); (6) peripheral nucleoli; and (7) nucleolar stems. Higher values of round or oval nuclear shape and vesicular nuclei increase the likelihood that the tissue sample is benign. CONCLUSIONS: Certain nuclear features have a higher association with premalignancy/malignancy and may guide histologic evaluation of a given lesion. These findings can be used in combination with architectural features and clinical history to add to a complete diagnostic picture.

Early Alzheimer's disease pathology in human cortex involves transient cell states.

Cellular perturbations underlying Alzheimer's disease (AD) are primarily studied in human postmortem samples and model organisms. Here, we generated a single-nucleus atlas from a rare cohort of cortical biopsies from living individuals with varying degrees of AD pathology. We next performed a systematic cross-disease and cross-species integrative analysis to identify a set of cell states that are specific to early AD pathology. These changes-which we refer to as the early cortical amyloid response-were prominent in neurons, wherein we identified a transitional hyperactive state preceding the loss of excitatory neurons, which we confirmed by acute slice physiology on independent biopsy specimens. Microglia overexpressing neuroinflammatory-related processes also expanded as AD pathology increased. Finally, both oligodendrocytes and pyramidal neurons upregulated genes associated with ß-amyloid production and processing during this early hyperactive phase. Our integrative analysis provides an organizing framework for targeting circuit dysfunction, neuroinflammation, and amyloid production early in AD pathogenesis.

True Oncocytic Acinic Cell Carcinoma: A Case Image.

A 67-year-old female with a history of chronic lymphocytic leukemia/small lymphocytic lymphoma (CLL/SLL) presented with right sided otalgia and a 2-3 cm firm, tender right posterior parotid mass. Fine needle aspiration biopsy (FNAB) established a diagnosis of acinic cell carcinoma (AciCC). Further workup demonstrated lung nodules which were confirmed by FNAB to represent metastatic AciCC. A right radical parotidectomy with sacrifice of the facial nerve, segmental mandibulectomy, and selective neck dissection (levels II-IV) was performed. Microscopically, the tumor displayed an infiltrative border with a solid multinodular growth pattern and fibrosclerotic septation. The tumor was composed mainly of uniform cells with abundant eosinophilic granular cytoplasm with round nuclei with prominent nucleoli. Nuclei were fairly monomorphic, mitotic counts were 3-4 per 2mm2 and there was no necrosis despite the aggressive growth pattern. An anti-mitochondrial immunohistochemical stain showed strong reactivity in the tumor cells, with an internal positive control of adjacent striated ducts. An immunohistochemical stain for NR4A3 demonstrated strong nuclear reactivity in the tumor cells. Electron microscopy highlighted the tumor cells with numerous mitochondria and distinctive electron dense intramitochondrial inclusions. Concurrent CLL/SLL was identified on histologic examination of the lymph nodes, but they were free of AciCC. After eight weeks of follow-up, she tolerated the surgery well and is currently receiving radiation therapy to the parotid and neck. In this illustrative case, we justify the oncocytic designation of AciCC by morphology, immunohistochemistry, and electron microscopy.

CNSeg: A dataset for cervical nuclear segmentation.

BACKGROUND AND OBJECTIVE: Nuclear segmentation in cervical cell images is a crucial technique for automatic cytopathology diagnosis. Experimental evaluation of nuclear segmentation methods with datasets is helpful in promoting the advancement of nuclear segmentation techniques. However, public datasets are not enough for a reasonable and comprehensive evaluation because of insufficient quantity, single data source, and low segmentation difficulty. METHODS: Therefore, we provide the largest dataset for cervical nuclear segmentation (CNSeg). It contains 124,000 annotated nuclei collected from 1,530 patients under different conditions. The image styles in this dataset cover most practical application scenarios, including microbial infection, cytopathic heterogeneity, overlapping nuclei, etc. To evaluate the performance of segmentation methods from different aspects, we divided the CNSeg dataset into three subsets, namely the patch segmentation dataset (PatchSeg) with nuclei images collected under complex conditions, the cluster segmentation dataset (ClusterSeg) with cluster nuclei, and the domain segmentation dataset (DomainSeg) with data from different domains. Furthermore, we propose a post-processing method that processes overlapping nuclei single ones. RESULTS AND CONCLUSION: Experiments show that our dataset can comprehensively evaluate cervical nuclear segmentation methods from different aspects. We provide guidelines for other researchers to use the dataset. https://github.com/jingzhaohlj/AL-Net.

Esophageal carcinoma with SMARCA4 mutation: Unique diagnostic challenges.

Esophageal carcinoma with SMARCA4 deficiency or dysfunction is a recently recognized entity. This study describes the clinicopathologic features of four cases of esophageal carcinoma with SMARCA4 mutation, three with deep deletion and one with missense mutation. Patients include 3 males and 1 female, with an age range of 45-68 years old. Histologically, the neoplasms showed frequent mitotic activity, large nucleus and prominent nucleoli. Glandular differentiation was variable from not identifiable to approximately 20% in the biopsy material. Percentage of rhabdoid morphology was also variable from not identifiable to 20% of the biopsy material. For these cases, one case was diagnosed SMARCA4 deficient esophageal carcinoma based on the biopsy of a retroperitoneal lymph node showing loss of BRG1 by immunostain, and next generation sequencing confirmed deep deletion of SMARCA4. The other three cases had diagnosis of undifferentiated carcinoma or poorly differentiated carcinoma, and the SMARCA4 deep deletion or mutation was discovered by next generation sequencing. Molecular analysis showed TP53 mutation in all the three cases with SMARCA4 deep deletion. Two of the patients deceased 72 and 78 days after diagnosis, and the other two patients showed limited or no treatment response to chemotherapy. In conclusion, esophageal carcinoma with SMARCA4 mutation may pose significant diagnostic challenge for surgical pathologists due to its variable morphology and immunoprofile, and accurate classification of this entity requires recognition of the spectrum of morphology and utilization of BRG1 immunostain and next generating sequencing.

Discriminant Analysis Using Gabor Filter Sets for Lobular Endocervical Glandular Hyperplasia: Numerical Interpretation of Nuclear Atypia by Gabor Filter Features.

INTRODUCTION: Lobular endocervical glandular hyperplasia (LEGH) is a benign lesion; however, it is considered to be the origin of gastric-type adenocarcinoma in the uterine cervix, and early diagnosis is important. At Shinshu University Hospital, screening of LEGH cells is based on the difference in color tone of cytoplasmic mucin on Papanicolaou staining and detection of gastric mucin using HIK1083-labeled latex agglutination assay. However, it is sometimes difficult to distinguish LEGH cells with subtle nuclear atypia from endocervical (EC) cells. METHODS: We calculated the Gabor filter features (mean signal value, standard deviation, skewness, kurtosis) from the nuclei of cytological specimens in EC cells (37 cases) and LEGH cells (33 cases) using microscopic images, and we performed statistical analysis and discriminant analysis by linear support vector machine (LSVM) using these features. A Gabor filter is a linear filter defined as a mathematical representation of the mammalian visual system. Gabor filters with three wavelengths and eight angles were used for analysis. RESULTS: Gabor filter features in EC cells were higher than in LEGH cells, demonstrating that the gradient of LEGH cell nuclei was milder than that of EC cell nuclei. The accuracy calculated using all Gabor filters was 91.0% and the accuracy of four Gabor filters (λ = 2/3π and θ = 0°, 45°, 90°, 135°) was 88.9%. High accuracy with low computation costs was achieved by reducing the number of features used for LSVM. CONCLUSION: The application of a Gabor filter with convolutional processing resulted in the edges of LEGH cells being slightly rough and thick, whereas those of EC cells were fine and thin. Thus, it is thought that the frequency of abrupt gradients of pixels was higher in EC cells than in LEGH cells, and the gradient of chromatin distribution in LEGH cell nuclei was milder than that in EC cell nuclei. It was possible to evaluate nuclear findings of EC and LEGH cells objectively by quantifying morphological features of nuclei using Gabor filters. It was possible to differentiate EC cells from LEGH cells using LSVM using Gabor filter features.

Physical Training Chronically Stimulates the Motor Neuron Cell Nucleus in the Ts65Dn Mouse, a Model of Down Syndrome.

Down syndrome (DS) is a genetically-based disease based on the trisomy of chromosome 21 (Hsa21). DS is characterized by intellectual disability in association with several pathological traits among which early aging and altered motor coordination are prominent. Physical training or passive exercise were found to be useful in counteracting motor impairment in DS subjects. In this study we used the Ts65Dn mouse, a widely accepted animal model of DS, to investigate the ultrastructural architecture of the medullary motor neuron cell nucleus taken as marker of the cell functional state. Using transmission electron microscopy, ultrastructural morphometry, and immunocytochemistry we carried out a detailed investigation of possible trisomy-related alteration(s) of nuclear constituents, which are known to vary their amount and distribution as a function of nuclear activity, as well as the effect of adapted physical training upon them. Results demonstrated that trisomy per se affects nuclear constituents to a limited extent; however, adapted physical training is able to chronically stimulate pre-mRNA transcription and processing activity in motor neuron nuclei of trisomic mice, although to a lesser extent than in their euploid mates. These findings are a step towards understanding the mechanisms underlying the positive effect of physical activity in DS.

Panoptic quality should be avoided as a metric for assessing cell nuclei segmentation and classification in digital pathology.

Panoptic Quality (PQ), designed for the task of "Panoptic Segmentation" (PS), has been used in several digital pathology challenges and publications on cell nucleus instance segmentation and classification (ISC) since its introduction in 2019. Its purpose is to encompass the detection and the segmentation aspects of the task in a single measure, so that algorithms can be ranked according to their overall performance. A careful analysis of the properties of the metric, its application to ISC and the characteristics of nucleus ISC datasets, shows that is not suitable for this purpose and should be avoided. Through a theoretical analysis we demonstrate that PS and ISC, despite their similarities, have some fundamental differences that make PQ unsuitable. We also show that the use of the Intersection over Union as a matching rule and as a segmentation quality measure within PQ is not adapted for such small objects as nuclei. We illustrate these findings with examples taken from the NuCLS and MoNuSAC datasets. The code for replicating our results is available on GitHub ( https://github.com/adfoucart/panoptic-quality-suppl ).

Multi CNN based automatic detection of mitotic nuclei in breast histopathological images.

In breast cancer diagnosis, the number of mitotic cells in a specific area is an important measure. It indicates how far the tumour has spread, which has consequences for forecasting the aggressiveness of cancer. Mitosis counting is a time-consuming and challenging technique that a pathologist does manually by examining Hematoxylin and Eosin (H&E) stained biopsy slices under a microscope. Due to limited datasets and the resemblance between mitotic and non-mitotic cells, detecting mitosis in H&E stained slices is difficult. By assisting in the screening, identifying, and labelling of mitotic cells, computer-aided mitosis detection technologies make the entire procedure much easier. For computer-aided detection approaches of smaller datasets, pre-trained convolutional neural networks are extensively employed. The usefulness of a multi CNN framework with three pre-trained CNNs is investigated in this research for mitosis detection. Features were collected from histopathology data and identified using VGG16, ResNet50, and DenseNet201 pre-trained networks. The proposed framework utilises all training folders of the MITOS dataset provided for the MITOS-ATYPIA contest 2014 and all the 73 folders of the TUPAC16 dataset. Each pre-trained Convolutional Neural Network model, such as VGG16, ResNet50 and DenseNet201, provides an accuracy of 83.22%, 73.67%, and 81.75%, respectively. Different combinations of these pre-trained CNNs constitute a multi CNN framework. Performance measures of multi CNN consisting of 3 pre-trained CNNs with Linear SVM give 93.81% precision and 92.41% F1-score compared to multi CNN combinations with other classifiers such as Adaboost and Random Forest.