The Effect of the Loss on Generalization: Empirical Study on Synthetic Lung Nodule Data

• URL: http://arxiv.org/abs/2108.04815v1
• Date: Tue, 10 Aug 2021 17:58:01 GMT
• Title: The Effect of the Loss on Generalization: Empirical Study on Synthetic Lung Nodule Data
• Authors: Vasileios Baltatzis, Loic Le Folgoc, Sam Ellis, Octavio E. Martinez Manzanera, Kyriaki-Margarita Bintsi, Arjun Nair, Sujal Desai, Ben Glocker, Julia A. Schnabel
• Abstract summary: We show that different loss functions lead to different features being learned and consequently affect the generalization ability of the classifier on unseen data. This study provides some important insights into the design of deep learning solutions for medical imaging tasks.
• Score: 13.376247652484274
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional Neural Networks (CNNs) are widely used for image classification in a variety of fields, including medical imaging. While most studies deploy cross-entropy as the loss function in such tasks, a growing number of approaches have turned to a family of contrastive learning-based losses. Even though performance metrics such as accuracy, sensitivity and specificity are regularly used for the evaluation of CNN classifiers, the features that these classifiers actually learn are rarely identified and their effect on the classification performance on out-of-distribution test samples is insufficiently explored. In this paper, motivated by the real-world task of lung nodule classification, we investigate the features that a CNN learns when trained and tested on different distributions of a synthetic dataset with controlled modes of variation. We show that different loss functions lead to different features being learned and consequently affect the generalization ability of the classifier on unseen data. This study provides some important insights into the design of deep learning solutions for medical imaging tasks.

Related papers

• Multi-task Explainable Skin Lesion Classification [54.76511683427566]
  We propose a few-shot-based approach for skin lesions that generalizes well with few labelled data. The proposed approach comprises a fusion of a segmentation network that acts as an attention module and classification network.
  arXiv  Detail & Related papers  (2023-10-11T05:49:47Z)
• Data Augmentation using Feature Generation for Volumetric Medical Images [0.08594140167290097]
  Medical image classification is one of the most critical problems in the image recognition area. One of the major challenges in this field is the scarcity of labelled training data. Deep Learning models, in particular, show promising results on image segmentation and classification problems.
  arXiv  Detail & Related papers  (2022-09-28T13:46:24Z)
• LifeLonger: A Benchmark for Continual Disease Classification [59.13735398630546]
  We introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection. Task and class incremental learning of diseases address the issue of classifying new samples without re-training the models from scratch. Cross-domain incremental learning addresses the issue of dealing with datasets originating from different institutions while retaining the previously obtained knowledge.
  arXiv  Detail & Related papers  (2022-04-12T12:25:05Z)
• Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models [50.537859423741644]
  Training a model on an imbalanced dataset can introduce unique challenges to the learning problem. We look deeper into the internal units of neural networks to observe how handling data imbalance affects the learned features.
  arXiv  Detail & Related papers  (2022-04-04T09:38:38Z)
• Skin lesion segmentation and classification using deep learning and handcrafted features [0.0]
  We form a new type of image features, called hybrid features, which has stronger discrimination ability than single method features. Our model achieves an 92.3% balanced multiclass accuracy, which is 6.8% better than the typical single method architecture for deep learning.
  arXiv  Detail & Related papers  (2021-12-20T02:45:42Z)
• Multi-loss ensemble deep learning for chest X-ray classification [0.8594140167290096]
  Class imbalance is common in medical image classification tasks, where the number of abnormal samples is fewer than the number of normal samples. We propose novel loss functions to train a DL model and analyze its performance in a multiclass classification setting.
  arXiv  Detail & Related papers  (2021-09-29T14:14:04Z)
• Medulloblastoma Tumor Classification using Deep Transfer Learning with Multi-Scale EfficientNets [63.62764375279861]
  We propose an end-to-end MB tumor classification and explore transfer learning with various input sizes and matching network dimensions. Using a data set with 161 cases, we demonstrate that pre-trained EfficientNets with larger input resolutions lead to significant performance improvements.
  arXiv  Detail & Related papers  (2021-09-10T13:07:11Z)
• Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition [65.77962788209103]
  We propose class subset learning by dividing the long-tailed data into multiple class subsets according to prior knowledge. It enforces the model to focus on learning the subset-specific knowledge. The proposed framework proved to be effective for the long-tailed retinal diseases recognition task.
  arXiv  Detail & Related papers  (2021-04-22T13:39:33Z)
• Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction [55.94378672172967]
  We focus on few-shot disease subtype prediction problem, identifying subgroups of similar patients. We introduce meta learning techniques to develop a new model, which can extract the common experience or knowledge from interrelated clinical tasks. Our new model is built upon a carefully designed meta-learner, called Prototypical Network, that is a simple yet effective meta learning machine for few-shot image classification.
  arXiv  Detail & Related papers  (2020-09-02T02:50:30Z)
• Contraction Mapping of Feature Norms for Classifier Learning on the Data with Different Quality [5.47982638565422]
  We propose a contraction mapping function to compress the range of feature norms of training images according to their quality. Experiments on various classification applications, including handwritten digit recognition, lung nodule classification, face verification and face recognition, demonstrate that the proposed approach is promising.
  arXiv  Detail & Related papers  (2020-07-27T09:53:55Z)

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.