Deep Multi-Scale U-Net Architecture and Label-Noise Robust Training Strategies for Histopathological Image Segmentation

Kurian, Nikhil Cherian; Lehan, Amit; Verghese, Gregory; Nimish, Dharamshi,; Sundaram, Divya Meena; Li, Mengyuan; Liu, Fangfang; Gillet, Cheryl; Rane, Swapnil; Grigoriadis, Anita; Sethi, Amit

doi:10.1109/bibe55377.2022.00027

Cited by 7 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The blurring might be caused by the resolution of the DWI as relevant information source for the network. Another reason for the blurring might be the applied U-Net architecture, as encoder-decoder architectures are known for their blurry outputs if large variations in shape and scale is present in target regions [20; 21]. Such situation naturally occurs in T2w-FS images where large regions of fibro-glandular-tissue occur among areas speckled with small scale nodular or linear appearing tissue tracks.…”

Section: Discussionmentioning

confidence: 99%

Feasibility to virtually generate T2 fat-saturated breast MRI by convolutional neural networks

Liebert,

Hadler,

Ehring

et al. 2024

Preprint

View full text Add to dashboard Cite

BackgroundBreast magnetic resonance imaging (MRI) protocols often include T2-weighted fat-saturated (T2w-FS) sequences, which are vital for tissue characterization but significantly increase scan time.PurposeThis study aims to evaluate whether a 2D-U-Net neural network can generate virtual T2w-FS images from routine multiparametric breast MRI sequences.Materials and MethodsThis IRB approved, retrospective study included n=914 breast MRI examinations performed between January 2017 and June 2020. The dataset was divided into training (n=665), validation (n=74), and test sets (n=175). The U-Net was trained on T1-weighted (T1w), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) sequences to generate virtual T2w-FS images (VirtuT2). Quantitative metrics and a qualitative multi-reader assessment by two radiologists were used to evaluate the VirtuT2 images.ResultsVirtuT2 images demonstrated high structural similarity (SSIM=0.87) and peak signal-to-noise ratio (PSNR=24.90) compared to original T2w-FS images. High level of the frequency error norm (HFNE=0.87) indicates strong blurring presence in the VirtuT2 images, which was also confirmed in qualitative reading. Radiologists correctly identified VirtuT2 images with 92.3% and 94.2% accuracy, respectively. No significant difference in diagnostic image quality (DIQ) was noted for one reader (p=0.21), while the other reported significantly lower DIQ for VirtuT2 (p<=0.001). Moderate inter-reader agreement was observed for edema detection on T2w-FS images (ƙ=0.43), decreasing to fair on VirtuT2 images (ƙ=0.36).ConclusionThe 2D-U-Net can technically generate virtual T2w-FS images with high similarity to real T2w-FS images, though blurring remains a limitation. Further investigation of other architectures and using larger datasets are needed to improve clinical applicability.Summary StatementVirtual T2-weighted fat-saturated images can be generated from routine breast MRI sequences using convolutional neural networks, showing high structural similarity but with notable blurring, necessitating further refinement for clinical use.Key ResultsImages with T2w-FS characteristics can be virtually generated from T1w and DWI images using deep learningImage blurring occurring in the VirtuT2 image limit clinical use for the current momentFurther investigation of different architectures and with larger datasets are necessary in the future to improve the VirtuT2 performance.

show abstract

Section: Discussionmentioning

confidence: 99%

Feasibility to virtually generate T2 fat-saturated breast MRI by convolutional neural networks

Liebert,

Hadler,

Ehring

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…For the segmentation of GCs and sinuses in LNs, we tested three FCNs based on a U‐Net architecture with symmetrical encoder‐decoder paths: (1) a standard U‐Net architecture with five convolution blocks and skip connections (referred to as U‐Net), (2) a U‐Net model with an attention mechanism that upweights salient features during training (referred to as AttenU‐Net) [21], and (3) a multiscale U‐Net approach that assimilates semantic information from different scales during training using atrous convolutions [22] (referred to as MS U‐Net) (see Supplementary materials and methods and supplementary material, Figure S1). A single LN section was selected from 114 H&E‐stained WSIs from Guy's Hospital (London, UK) and manually annotated for GCs and sinuses by a pathologist (FL).…”

Section: Methodsmentioning

confidence: 99%

Multiscale deep learning framework captures systemic immune features in lymph nodes predictive of triple negative breast cancer outcome in large‐scale studies

Verghese

Liu

et al. 2023

The Journal of Pathology

Self Cite

View full text Add to dashboard Cite

The suggestion that the systemic immune response in lymph nodes (LNs) conveys prognostic value for triple-negative breast cancer (TNBC) patients has not previously been investigated in large cohorts. We used a deep learning (DL) framework to quantify morphological features in haematoxylin and eosin-stained LNs on digitised whole slide images. From 345 breast cancer patients, 5,228 axillary LNs, cancer-free and involved, were assessed. Generalisable multiscale DL frameworks were developed to capture and quantify germinal centres (GCs) and sinuses. Cox regression proportional hazard models tested the association between smuLymphNet-captured GC and sinus quantifications and distant metastasis-free survival (DMFS). smuLymphNet achieved a Dice coefficient of 0.86 and 0.74 for capturing GCs and sinuses, respectively, and was comparable to an interpathologist Dice coefficient of 0.66 (GC) and 0.60 (sinus). smuLymphNet-captured sinuses were increased in LNs harbouring GCs (p < 0.001). smuLymphNet-captured GCs retained clinical relevance in LN-positive TNBC patients whose cancer-free LNs had on average ≥2 GCs, had longer DMFS (hazard ratio [HR] = 0.28, p = 0.02) and extended GCs' prognostic value to LN-negative TNBC patients (HR = 0.14, p = 0.002). Enlarged smuLymphNet-captured sinuses in involved LNs were associated with superior DMFS in LN-positive TNBC patients in a cohort from Guy's Hospital (multivariate HR = 0.39, p = 0.039) and with distant recurrence-free survival in 95 LN-positive TNBC patients of the Dutch-N4plus trial (HR = 0.44, p = 0.024). Heuristic scoring of subcapsular sinuses in LNs of LN-positive Tianjin TNBC patients (n = 85) cross-validated the association of enlarged sinuses with shorter DMFS (involved LNs: HR = 0.33, p = 0.029 and cancer-free LNs: HR = 0.21 p = 0.01). Morphological LN features reflective of cancer-associated responses are robustly quantifiable by smuLymphNet. Our findings further strengthen the value of assessment of LN properties beyond the detection of metastatic deposits for prognostication of TNBC patients.

show abstract

“…In particular, the formation of germinal centres and an expanded sinus surface area in a patient's lymph nodes are associated with longer intervals of disease recurrence [43]. By implementing a multi-scale CNN-based framework, germinal centres and sinuses on digitised H&E-stained axillary lymph node sections were robustly quantified, comparable with inter-pathologist assessments [48,49].…”

Section: Detecting Known Biomarkers With Computational Pathologymentioning

confidence: 99%

Computational pathology in cancer diagnosis, prognosis, and prediction – present day and prospects

Verghese

Lennerz

Ruta

et al. 2023

The Journal of Pathology

Self Cite

View full text Add to dashboard Cite

Computational pathology refers to applying deep learning techniques and algorithms to analyse and interpret histopathology images. Advances in artificial intelligence (AI) have led to an explosion in innovation in computational pathology, ranging from the prospect of automation of routine diagnostic tasks to the discovery of new prognostic and predictive biomarkers from tissue morphology. Despite the promising potential of computational pathology, its integration in clinical settings has been limited by a range of obstacles including operational, technical, regulatory, ethical, financial, and cultural challenges. Here, we focus on the pathologists’ perspective of computational pathology: we map its current translational research landscape, evaluate its clinical utility, and address the more common challenges slowing clinical adoption and implementation. We conclude by describing contemporary approaches to drive forward these techniques. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

show abstract

Deep Multi-Scale U-Net Architecture and Label-Noise Robust Training Strategies for Histopathological Image Segmentation

Cited by 7 publications

References 12 publications

Feasibility to virtually generate T2 fat-saturated breast MRI by convolutional neural networks

Feasibility to virtually generate T2 fat-saturated breast MRI by convolutional neural networks

Multiscale deep learning framework captures systemic immune features in lymph nodes predictive of triple negative breast cancer outcome in large‐scale studies

Computational pathology in cancer diagnosis, prognosis, and prediction – present day and prospects

Contact Info

Product

Resources

About