DenseRes-Unet: Segmentation of overlapped/clustered nuclei from multi organ histopathology images

Kiran, Iqra; Raza, Basit; Ijaz, Areesha; Khan, Muazzam A.

doi:10.1016/j.compbiomed.2022.105267

Cited by 54 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Heterogeneous levels of tissue in a single glass slide also affected image quality. It appears that numerous efforts have been invested to overcome such hurdles and it would be worthwhile trying new techniques in subsequent studies 18,19 . To acquire quantitative data for the chromatin pattern, we selected a fixed area (316 pixels) in the nuclei and acquired the ID.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Blastoid and Pleomorphic Mantle Cell Lymphoma Demonstrate Distinct Clinicopathologic and Genetic Features

Khanlari¹,

Mo²,

Kim³

et al. 2023

American Journal of Surgical Pathology

View full text Add to dashboard Cite

The blastoid (B) and pleomorphic (P) variants of mantle cell lymphoma (MCL) are associated with aggressive clinical behavior. In this study, we collected 102 cases of B-MCL and P-MCL from untreated patients. We reviewed clinical data, analyzed morphologic features using an image analysis tool (ImageJ) and we assessed mutational and gene expression profiles. The chromatin pattern of lymphoma cells was assessed quantitatively by the pixel value. Cases of B-MCL showed a greater median pixel value with lower variation compared with P-MCL, indicating a homogeneously euchromatin-rich pattern in B-MCL. In addition, the Feret diameter of the nuclei was significantly smaller (median 6.92 vs. 8.49 µm per nucleus, P<0.001) and had a lesser degree of variation in B-MCL compared with P-MCL, indicating that B-MCL cells have smaller cells with a more monomorphic appearance. B-MCL showed a significantly higher median Ki-67 proliferation rate (60% vs. 40%, P=0.003), and affected patients had poorer overall survival compared with those with P-MCL (median overall survival: 3.1 vs. 8.8 y, respectively, P=0.038). NOTCH1 mutation was significantly more frequent in B-MCL compared with P-MCL (33% and 0%, respectively, P=0.004). Gene expression profiling showed 14 genes overexpressed in B-MCL cases and gene set enrichment assay for the overexpressed genes showed significant enrichment in the cell cycle and mitotic transition pathways. We also report a subset of MCL cases that has blastoid chromatin but a higher degree of pleomorphism in nuclear size and shape, designated here as hybrid MCL. Hybrid MCL cases had a similar Ki-67 proliferation rate, mutation profile, and clinical outcome to B-MCL and distinct from P-MCL. In summary, these data suggest biological differences between B-MCL and P-MCL cases justifying their separate designation when possible.

show abstract

Section: Discussionmentioning

confidence: 99%

“…It appears that numerous efforts have been invested to overcome such hurdles and it would be worthwhile trying new techniques in subsequent studies. 18,19 To acquire quantitative data for the chromatin pattern, we selected a fixed area (316 pixels) in the nuclei and acquired the ID. Of note, the ID is proportional to the area of selection.…”

Section: Discussionmentioning

confidence: 99%

Blastoid and Pleomorphic Mantle Cell Lymphoma Demonstrate Distinct Clinicopathologic and Genetic Features

Khanlari¹,

Mo²,

Kim³

et al. 2023

American Journal of Surgical Pathology

View full text Add to dashboard Cite

show abstract

“…initially introduced the fullly convolutional network to address pixel-level segmentation tasks. Subsequently, the segmentation model represented by U-shaped network 4 has become the mainstream segmentation model in the field of medical image segmentation, and various improved U-shaped networks have been derived based on the U-shaped network segmentation model, such as R2U-Net, 5 Nested-UNet, 6 Attention U-Net, 7 Focus Netv2, 8 and Denseres-UNet 9 . Various attempts have been made subsequently, but none of them can be separated from the classical U-shaped segmentation network.…”

Section: Related Workmentioning

confidence: 99%

PS5-Net: a medical image segmentation network with multiscale resolution

Li,

Liu,

et al. 2024

J. Med. Imag.

View full text Add to dashboard Cite

.PurposeIn recent years, the continuous advancement of convolutional neural networks (CNNs) has led to the widespread integration of deep neural networks as a mainstream approach in clinical diagnostic support. Particularly, the utilization of CNN-based medical image segmentation has delivered favorable outcomes for aiding clinical diagnosis. Within this realm, network architectures based on the U-shaped structure and incorporating skip connections, along with their diverse derivatives, have gained extensive utilization across various medical image segmentation tasks. Nonetheless, two primary challenges persist. First, certain organs or tissues present considerable complexity, substantial morphological variations, and size discrepancies, posing significant challenges for achieving highly accurate segmentation. Second, the predominant focus of current deep neural networks on single-resolution feature extraction limits the effective extraction of feature information from complex medical images, thereby contributing to information loss via continuous pooling operations and contextual information interaction constraints within the U-shaped structure.ApproachWe proposed a five-layer pyramid segmentation network (PS5-Net), a multiscale segmentation network with diverse resolutions that is founded on the U-Net architecture. Initially, this network effectively leverages the distinct features of images at varying resolutions across different dimensions, departing from prior single-resolution feature extraction methods to adapt to intricate and variable segmentation scenarios. Subsequently, to comprehensively integrate feature information from diverse resolutions, a kernel selection module is proposed to assign weights to features across different dimensions, enhancing the fusion of feature information from various resolutions. Within the feature extraction network denoted as PS-UNet, we preserve the classical structure of the traditional U-Net while enhancing it through the incorporation of dilated convolutions.ResultsPS5-Net attains a Dice score of 0.9613 for liver segmentation on the CHLISC dataset and 0.8587 on the ISIC2018 dataset for skin lesion segmentation. Comparative analysis with diverse medical image segmentation methodologies in recent years reveals that PS5-Net has achieved the highest scores and substantial advancements.ConclusionsPS5-Net effectively harnesses the rich semantic information available at different resolutions, facilitating a comprehensive and nuanced understanding of the input medical images. By capitalizing on global contextual connections, the network adeptly captures the intricate interplay of features and dependencies across the entire image, resulting in more accurate and robust segmentation outcomes. The experimental validation of PS5-Net underscores its superior performance in medical image segmentation tasks, offering promising prospects for enhancing diagnostic and analytical processes within clinical settings. These results highlight the potential of PS5-Net to significantly c...

show abstract

“…Our proposed model follows the idea of patch-based WSI analysis method and solves the above two key problems by introducing self-supervised learning [21] and heterogeneous feature fusion mechanism. We use a UNetbased model [22][23][24] for patch feature representation. The network consists of an encoder (f ) and a decoder (h ), and a compact feature vector (v) connects them.…”

Section: Introductionmentioning

confidence: 99%

High-Resolution Histopathological Image Classification Model Based on Fused Heterogeneous Networks with Self-Supervised Feature Representation

Lai

Zhang

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Applying machine learning technology to automatic image analysis and auxiliary diagnosis of whole slide image (WSI) may help to improve the efficiency, objectivity, and consistency of pathological diagnosis. Due to its extremely high resolution, it is still a great challenge to directly process WSI through deep neural networks. In this paper, we propose a novel model for the task of classification of WSIs. The model is composed of two parts. The first part is a self-supervised encoding network with a UNet-like architecture. Each patch from a WSI is encoded as a compressed latent representation. These features are placed according to their corresponding patch’s original location in WSI, forming a feature cube. The second part is a classification network fused by 4 famous network blocks with heterogeneous architectures, with feature cube as input. Our model effectively expresses the feature and preserves location information of each patch. The fused network integrates heterogeneous features generated by different networks which yields robust classification results. The model is evaluated on two public datasets with comparison to baseline models. The evaluation results show the effectiveness of the proposed model.

show abstract

DenseRes-Unet: Segmentation of overlapped/clustered nuclei from multi organ histopathology images

Cited by 54 publications

References 31 publications

Blastoid and Pleomorphic Mantle Cell Lymphoma Demonstrate Distinct Clinicopathologic and Genetic Features

Blastoid and Pleomorphic Mantle Cell Lymphoma Demonstrate Distinct Clinicopathologic and Genetic Features

PS5-Net: a medical image segmentation network with multiscale resolution

High-Resolution Histopathological Image Classification Model Based on Fused Heterogeneous Networks with Self-Supervised Feature Representation

Contact Info

Product

Resources

About