Evaluation of Multi-Scale Multiple Instance Learning to Improve Thyroid
Cancer Classification
- URL: http://arxiv.org/abs/2204.10942v1
- Date: Fri, 22 Apr 2022 21:48:56 GMT
- Title: Evaluation of Multi-Scale Multiple Instance Learning to Improve Thyroid
Cancer Classification
- Authors: Maximilian E. Tschuchnig, Philipp Grubm\"uller, Lea M. Stangassinger,
Christina Kreutzer, S\'ebastien Couillard-Despr\'es, Gertie J. Oostingh,
Anton Hittmair, Michael Gadermayr
- Abstract summary: Thyroid cancer is the fifth most common malignancy diagnosed in women.
differentiation of cancer sub-types is important for treatment and current, automatic computer-aided differentiation of cancer types is crucial.
Patch based multiple instance learning approaches, combined with aggregations such as bag-of-words, is a common approach.
This work's contribution is to extend a patch based state-of-the-art method by generating and combining feature vectors of three different patch resolutions.
- Score: 0.3518016233072556
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Thyroid cancer is currently the fifth most common malignancy diagnosed in
women. Since differentiation of cancer sub-types is important for treatment and
current, manual methods are time consuming and subjective, automatic
computer-aided differentiation of cancer types is crucial. Manual
differentiation of thyroid cancer is based on tissue sections, analysed by
pathologists using histological features. Due to the enormous size of gigapixel
whole slide images, holistic classification using deep learning methods is not
feasible. Patch based multiple instance learning approaches, combined with
aggregations such as bag-of-words, is a common approach. This work's
contribution is to extend a patch based state-of-the-art method by generating
and combining feature vectors of three different patch resolutions and
analysing three distinct ways of combining them. The results showed
improvements in one of the three multi-scale approaches, while the others led
to decreased scores. This provides motivation for analysis and discussion of
the individual approaches.
Related papers
- Adaptive Deep Learning for Multiclass Breast Cancer Classification via Misprediction Risk Analysis [0.8028869343053783]
Early detection is crucial for improving patient outcomes.
Computer-aided diagnostic approaches have significantly enhanced breast cancer detection.
However, these methods face challenges in multiclass classification, leading to frequent mispredictions.
arXiv Detail & Related papers (2025-03-17T03:25:28Z) - Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification [50.899861205016265]
We propose a new framework PaGMIL to mitigate catastrophic forgetting in breast cancer WSI classification.
Our framework introduces two key components into the common MIL model architecture.
We evaluate the continual learning performance of PaGMIL across several public breast cancer datasets.
arXiv Detail & Related papers (2025-03-08T04:51:58Z) - DIOR-ViT: Differential Ordinal Learning Vision Transformer for Cancer Classification in Pathology Images [4.2832657904981435]
We introduce a differential ordinal learning problem in which we define and learn the degree of difference in the categorical class labels between pairs of samples.
We demonstrate that the adoption of differential ordinal learning can improve the accuracy and reliability of cancer grading.
The proposed approach should be applicable to other diseases and problems as they involve ordinal relationship among class labels.
arXiv Detail & Related papers (2024-07-10T12:42:27Z) - A transductive few-shot learning approach for classification of digital
histopathological slides from liver cancer [0.0]
This paper presents a new approach for classifying 2D histopathology patches using few-shot learning.
By applying a sliding window technique to histopathology slides, we illustrate the practical benefits of transductive learning.
arXiv Detail & Related papers (2023-11-29T15:44:00Z) - Stain-invariant self supervised learning for histopathology image
analysis [74.98663573628743]
We present a self-supervised algorithm for several classification tasks within hematoxylin and eosin stained images of breast cancer.
Our method achieves the state-of-the-art performance on several publicly available breast cancer datasets.
arXiv Detail & Related papers (2022-11-14T18:16:36Z) - 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) - Breast Cancer Classification Based on Histopathological Images Using a
Deep Learning Capsule Network [0.0]
This study aims to classify different types of breast cancer using histological images (HIs)
We present an enhanced capsule network that extracts multi-scale features using the Res2Net block and four additional convolutional layers.
As a result, the new method outperforms the old ones since it automatically learns the best possible features.
arXiv Detail & Related papers (2022-08-01T03:45:36Z) - Metastatic Cancer Outcome Prediction with Injective Multiple Instance
Pooling [1.0965065178451103]
We process two public datasets to set up a benchmark cohort of 341 patient in total for studying outcome prediction of metastatic cancer.
We propose two injective multiple instance pooling functions that are better suited to outcome prediction.
Our results show that multiple instance learning with injective pooling functions can achieve state-of-the-art performance in the non-small-cell lung cancer CT and head and neck CT outcome prediction benchmarking tasks.
arXiv Detail & Related papers (2022-03-09T16:58:03Z) - EMT-NET: Efficient multitask network for computer-aided diagnosis of
breast cancer [58.720142291102135]
We propose an efficient and light-weighted learning architecture to classify and segment breast tumors simultaneously.
We incorporate a segmentation task into a tumor classification network, which makes the backbone network learn representations focused on tumor regions.
The accuracy, sensitivity, and specificity of tumor classification is 88.6%, 94.1%, and 85.3%, respectively.
arXiv Detail & Related papers (2022-01-13T05:24:40Z) - Triplet Contrastive Learning for Brain Tumor Classification [99.07846518148494]
We present a novel approach of directly learning deep embeddings for brain tumor types, which can be used for downstream tasks such as classification.
We evaluate our method on an extensive brain tumor dataset which consists of 27 different tumor classes, out of which 13 are defined as rare.
arXiv Detail & Related papers (2021-08-08T11:26:34Z) - Weakly supervised multiple instance learning histopathological tumor
segmentation [51.085268272912415]
We propose a weakly supervised framework for whole slide imaging segmentation.
We exploit a multiple instance learning scheme for training models.
The proposed framework has been evaluated on multi-locations and multi-centric public data from The Cancer Genome Atlas and the PatchCamelyon dataset.
arXiv Detail & Related papers (2020-04-10T13:12:47Z) - Stan: Small tumor-aware network for breast ultrasound image segmentation [68.8204255655161]
We propose a novel deep learning architecture called Small Tumor-Aware Network (STAN) to improve the performance of segmenting tumors with different size.
The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors.
arXiv Detail & Related papers (2020-02-03T22:25:01Z)
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.