Leveraging weak complementary labels to improve semantic segmentation of hepatocellular carcinoma and cholangiocarcinoma in H&E-stained slides

• URL: http://arxiv.org/abs/2302.01813v1
• Date: Fri, 3 Feb 2023 15:35:54 GMT
• Title: Leveraging weak complementary labels to improve semantic segmentation of hepatocellular carcinoma and cholangiocarcinoma in H&E-stained slides
• Abstract summary: We present a deep learning segmentation approach to classify and quantify the two most prevalent primary liver cancers - carcinoma and intrahepatic cholangiocarcinoma. We propose to leverage such weak information from patient diagnoses by deriving complementary labels that indicate to which class a sample cannot belong.
• Score: 3.418658036508099
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present a deep learning segmentation approach to classify and quantify the two most prevalent primary liver cancers - hepatocellular carcinoma and intrahepatic cholangiocarcinoma - from hematoxylin and eosin (H&E) stained whole slide images. While semantic segmentation of medical images typically requires costly pixel-level annotations by domain experts, there often exists additional information which is routinely obtained in clinical diagnostics but rarely utilized for model training. We propose to leverage such weak information from patient diagnoses by deriving complementary labels that indicate to which class a sample cannot belong to. To integrate these labels, we formulate a complementary loss for segmentation. Motivated by the medical application, we demonstrate for general segmentation tasks that including additional patches with solely weak complementary labels during model training can significantly improve the predictive performance and robustness of a model. On the task of diagnostic differentiation between hepatocellular carcinoma and intrahepatic cholangiocarcinoma, we achieve a balanced accuracy of 0.91 (CI 95%: 0.86 - 0.95) at case level for 165 hold-out patients. Furthermore, we also show that leveraging complementary labels improves the robustness of segmentation and increases performance at case level.

Related papers

• Semantic Segmentation-Driven Image-Level Diagnosis of Liver Cancers in Hematoxylin and Eosin Histopathology Images [2.4629531282150876]
  We propose a semantic segmentation-based framework for image-level diagnosis.<n>Image-level predictions are obtained by assigning the class of the dominant pixel-level label in the segmentation output.<n>Five-fold cross-validation yielded balanced accuracy of 0.975 (HCC), 0.950 (CCA), and 1.000 (CMA)
  arXiv  Detail & Related papers  (2026-07-03T12:12:56Z)
• A Unified Framework for the Detection and Classification of Fatty Pancreas in Ultrasound Images [0.0]
  Non-alcoholic fatty pancreas disease (NAFPD) is an underdiagnosed condition associated with metabolic syndrome, insulin resistance, and increased risk of pancreatic cancer.<n>We propose an end-to-end framework for automatically classifying normal versus fatty pancreas from abdominal ultrasound images.
  arXiv  Detail & Related papers  (2026-05-08T09:13:30Z)
• A Digital Pathology Resource for Liver Cancer Quantification with Datasets, Benchmarks, and Tools [17.811013755898365]
  We release HepatoBench, a patch-level image database for liver cancer with annotations for seven key tissue categories.<n>Based on HepatoBench, we train and open-source a deep learning classification model as a tissue recognition tool.<n>We build HepatoQuant, an end-to-end, disease-specific regional quantification tool for liver cancer.
  arXiv  Detail & Related papers  (2026-04-22T14:13:09Z)
• Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT [68.09387763135236]
  We introduce a weakly supervised method trained solely on vertebra-level healthy/malignant labels, without any lesion masks.<n>We achieve strong blastic/lytic performance despite no mask supervision.
  arXiv  Detail & Related papers  (2025-12-07T14:03:28Z)
• Transformer Classification of Breast Lesions: The BreastDCEDL_AMBL Benchmark Dataset and 0.92 AUC Baseline [1.9336815376402718]
  This study introduces a transformer-based framework for automated classification of breast lesions in dynamic contrast-enhanced MRI.<n>We implemented a SegFormer architecture that achieved an AUC of 0.92 for lesion-level classification, with 100% sensitivity and 67% specificity at the patient level.<n>Public release of the dataset, models, and evaluation protocols provides the first standardized benchmark for DCE-MRI lesion classification.
  arXiv  Detail & Related papers  (2025-09-30T15:58:02Z)
• LGE-Guided Cross-Modality Contrastive Learning for Gadolinium-Free Cardiomyopathy Screening in Cine CMR [51.11296719862485]
  We propose a Contrastive Learning and Cross-Modal alignment framework for gadolinium-free cardiomyopathy screening using cine CMR sequences.<n>By aligning the latent spaces of cine CMR and Late Gadolinium Enhancement (LGE) sequences, our model encodes fibrosis-specific pathology into cine CMR embeddings.
  arXiv  Detail & Related papers  (2025-08-23T07:21:23Z)
• Prostate Cancer Classification Using Multimodal Feature Fusion and Explainable AI [2.656041527404895]
  We propose an explainable AI system combining BERT (for textual clinical notes) and Random Forest (for numerical lab data)<n>Our work demonstrates that a simple yet interpretable BERT+RF pipeline delivers clinically significant improvements.
  arXiv  Detail & Related papers  (2025-07-28T11:07:17Z)
• MyGO: Make your Goals Obvious, Avoiding Semantic Confusion in Prostate Cancer Lesion Region Segmentation [14.346163388200148]
  We propose a novel Pixel Anchor Module, which guides the model to discover a sparse set of feature anchors.<n>This mechanism enhances the model's nonlinear representation capacity and improves segmentation accuracy within lesion regions.<n>Our method achieves state-of-the-art performance on the PI-CAI dataset, demonstrating 69.73% IoU and 74.32% Dice scores.
  arXiv  Detail & Related papers  (2025-07-23T07:10:07Z)
• SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours [2.5229190642019286]
  Fully-supervised machine learning models aim to automate localisation tasks.<n>They require a large number of costly and often subjective 3D voxel-level labels for training.<n>We propose a novel weakly-supervised machine learning framework called SPARS.<n>It uses object-level binary cancer presence labels to localise cancerous regions on CT scans.
  arXiv  Detail & Related papers  (2025-05-25T06:14:41Z)
• Multi-Stage Segmentation and Cascade Classification Methods for Improving Cardiac MRI Analysis [15.236546465767026]
  We introduce a novel deep learning-based approach to segmentation and classification of cardiac magnetic resonance images. The method improved segmentation accuracy, achieving a Dice coefficient of 0.974 for the left ventricle and 0.947 for the right ventricle. For classification, a cascade of deep learning classifiers was employed to distinguish heart conditions, including hypertrophic cardiomyopathy, myocardial infarction, and dilated cardiomyopathy.
  arXiv  Detail & Related papers  (2024-12-12T15:53:14Z)
• A Holistic Weakly Supervised Approach for Liver Tumor Segmentation with Clinical Knowledge-Informed Label Smoothing [17.798774864007505]
  Liver cancer is a leading cause of mortality worldwide. Deep learning has shown promise for automated liver segmentation. We present a novel holistic weakly supervised framework to address these challenges.
  arXiv  Detail & Related papers  (2024-10-13T20:52:25Z)
• Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports [68.39938936308023]
  We propose a novel text-guided learning method to achieve highly accurate cancer detection results. Our approach can leverage clinical knowledge by large-scale pre-trained VLM to enhance generalization ability.
  arXiv  Detail & Related papers  (2024-05-23T07:03:38Z)
• Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning [10.50491279664907]
  The diagnosis of primary liver cancers (PLCs) can be challenging, especially on biopsies and for combined-cholangiocarcinoma (cHCC-CCA) We automatically classified PLCs on routine-stained biopsies using a weakly supervised learning method. Weak tumour/non-tumour annotations served as labels for training a Resnet18 neural network, and the network's last convolutional layer was used to extract new tumour tile features.
  arXiv  Detail & Related papers  (2024-04-07T15:03:46Z)
• CAMEL2: Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio [6.1718120147795466]
  Histopathology image analysis plays a crucial role in cancer diagnosis. weakly supervised learning methods, which only require coarse-grained labels at the image level, can significantly reduce labelling efforts. We present CAMEL2, which achieves comparable results to those of fully supervised baselines in pixel-level segmentation.
  arXiv  Detail & Related papers  (2023-10-09T04:17:21Z)
• Two-Stage Hybrid Supervision Framework for Fast, Low-resource, and Accurate Organ and Pan-cancer Segmentation in Abdomen CT [12.506232623163665]
  We propose a hybrid supervised framework, StMt, that integrates self-training and mean teacher for the segmentation of abdominal organs and tumors. Experiments on the validation set of FLARE2023 demonstrate that our method achieves excellent segmentation performance.
  arXiv  Detail & Related papers  (2023-09-11T12:12:25Z)
• Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies [62.840338941861134]
  We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset. We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis. This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
  arXiv  Detail & Related papers  (2023-02-16T17:06:23Z)
• Clinical Contrastive Learning for Biomarker Detection [15.510581400494207]
  We exploit the relationship between clinical and biomarker data to improve performance for biomarker classification. This is accomplished by leveraging the larger amount of clinical data as pseudo-labels for our data without biomarker labels. Our method is shown to outperform state of the art self-supervised methods by as much as 5% in terms of accuracy on individual biomarker detection.
  arXiv  Detail & Related papers  (2022-11-09T18:29:56Z)
• A Pathologist-Informed Workflow for Classification of Prostate Glands in Histopathology [62.997667081978825]
  Pathologists diagnose and grade prostate cancer by examining tissue from needle biopsies on glass slides. Cancer's severity and risk of metastasis are determined by the Gleason grade, a score based on the organization and morphology of prostate cancer glands. This paper proposes an automated workflow that follows pathologists' textitmodus operandi, isolating and classifying multi-scale patches of individual glands.
  arXiv  Detail & Related papers  (2022-09-27T14:08:19Z)
• WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma [51.50991881342181]
  This challenge includes 10,091 patch-level annotations and over 130 million labeled pixels. First place team achieved mIoU of 0.8413 (tumor: 0.8389, stroma: 0.7931, normal: 0.8919)
  arXiv  Detail & Related papers  (2022-04-13T15:27:05Z)
• Lymphocyte Classification in Hyperspectral Images of Ovarian Cancer Tissue Biopsy Samples [94.37521840642141]
  We present a machine learning pipeline to segment white blood cell pixels in hyperspectral images of biopsy cores. These cells are clinically important for diagnosis, but some prior work has struggled to incorporate them due to difficulty obtaining precise pixel labels.
  arXiv  Detail & Related papers  (2022-03-23T00:58:27Z)
• Label-Assemble: Leveraging Multiple Datasets with Partial Labels [68.46767639240564]
  "Label-Assemble" aims to unleash the full potential of partial labels from an assembly of public datasets. We discovered that learning from negative examples facilitates both computer-aided disease diagnosis and detection.
  arXiv  Detail & Related papers  (2021-09-25T02:48:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.