Evaluating Temperature Scaling Calibration Effectiveness for CNNs under Varying Noise Levels in Brain Tumour Detection

• URL: http://arxiv.org/abs/2509.24951v1
• Date: Mon, 29 Sep 2025 15:46:23 GMT
• Title: Evaluating Temperature Scaling Calibration Effectiveness for CNNs under Varying Noise Levels in Brain Tumour Detection
• Authors: Ankur Chanda, Kushan Choudhury, Shubhrodeep Roy, Shubhajit Biswas, Somenath Kuiry,
• Abstract summary: We develop a custom CNN and train it on a merged brain MRI dataset.<n>To simulate real-world uncertainty, five types of image noise are introduced: Gaussian, Poisson, Salt & Pepper, Speckle, and Uniform.<n>Results demonstrate that TS significantly reduces ECE and NLL under all noise conditions without degrading classification accuracy.
• Score: 0.18472148461613158
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Precise confidence estimation in deep learning is vital for high-stakes fields like medical imaging, where overconfident misclassifications can have serious consequences. This work evaluates the effectiveness of Temperature Scaling (TS), a post-hoc calibration technique, in improving the reliability of convolutional neural networks (CNNs) for brain tumor classification. We develop a custom CNN and train it on a merged brain MRI dataset. To simulate real-world uncertainty, five types of image noise are introduced: Gaussian, Poisson, Salt & Pepper, Speckle, and Uniform. Model performance is evaluated using precision, recall, F1-score, accuracy, negative log-likelihood (NLL), and expected calibration error (ECE), both before and after calibration. Results demonstrate that TS significantly reduces ECE and NLL under all noise conditions without degrading classification accuracy. This underscores TS as an effective and computationally efficient approach to enhance decision confidence of medical AI systems, hence making model outputs more reliable in noisy or uncertain settings.

Related papers

• Stochastic Spiking Neuron Based SNN Can be Inherently Bayesian [0.033985395340995594]
  Uncertainty in biological neural systems appears to be beneficial rather than detrimental.<n>In neuromorphic computing systems, device variability often limits performance, including accuracy and efficiency.<n>We propose a spiking neural network framework that unifies the dynamic models of intrinsic deviceity.
  arXiv  Detail & Related papers  (2026-02-03T10:48:14Z)
• A Quad-Step Approach to Uncertainty-Aware Deep Learning for Skin Cancer Classification [13.993637404760355]
  Deep learning models have shown promise in automating skin cancer classification.<n>However, challenges remain due to data scarcity and limited uncertainty awareness.<n>This study presents a comprehensive evaluation of DL-based skin lesion classification on the HAM10000 dataset.
  arXiv  Detail & Related papers  (2025-06-12T02:29:16Z)
• Efficient Brain Tumor Classification with Lightweight CNN Architecture: A Novel Approach [0.0]
  Brain tumor classification using MRI images is critical in medical diagnostics, where early and accurate detection significantly impacts patient outcomes.<n>Recent advancements in deep learning (DL) have shown promise, but many models struggle with balancing accuracy and computational efficiency.<n>We propose a novel model architecture integrating separable convolutions and squeeze and excitation (SE) blocks, designed to enhance feature extraction while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2025-02-01T21:06:42Z)
• Calibrating Language Models with Adaptive Temperature Scaling [58.056023173579625]
  We introduce Adaptive Temperature Scaling (ATS), a post-hoc calibration method that predicts a temperature scaling parameter for each token prediction. ATS improves calibration by over 10-50% across three downstream natural language evaluation benchmarks compared to prior calibration methods.
  arXiv  Detail & Related papers  (2024-09-29T22:54:31Z)
• Distributional Drift Detection in Medical Imaging with Sketching and Fine-Tuned Transformer [2.7552551107566137]
  This paper presents an accurate and sensitive approach to detect distributional drift in CT-scan medical images.<n>We developed a robust baseline library model for real-time anomaly detection, allowing for efficient comparison of incoming images.<n>We fine-tuned a pre-trained Vision Transformer model to extract relevant features, using mammography as a case study.
  arXiv  Detail & Related papers  (2024-08-15T23:46:37Z)
• How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks [1.4502611532302039]
  We show that a simple $p$-norm normalization of the logits, followed by taking the maximum logit as the confidence estimator, can lead to considerable gains in selective classification performance. Our results are shown to be consistent under distribution shift.
  arXiv  Detail & Related papers  (2023-05-24T18:56:55Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration [62.4971588282174]
  We propose a new post-processing calibration method called Neural Clamping. Our empirical results show that Neural Clamping significantly outperforms state-of-the-art post-processing calibration methods.
  arXiv  Detail & Related papers  (2022-09-23T14:18:39Z)
• DOMINO: Domain-aware Model Calibration in Medical Image Segmentation [51.346121016559024]
  Modern deep neural networks are poorly calibrated, compromising trustworthiness and reliability. We propose DOMINO, a domain-aware model calibration method that leverages the semantic confusability and hierarchical similarity between class labels. Our results show that DOMINO-calibrated deep neural networks outperform non-calibrated models and state-of-the-art morphometric methods in head image segmentation.
  arXiv  Detail & Related papers  (2022-09-13T15:31:52Z)
• Sample-dependent Adaptive Temperature Scaling for Improved Calibration [95.7477042886242]
  Post-hoc approach to compensate for neural networks being wrong is to perform temperature scaling. We propose to predict a different temperature value for each input, allowing us to adjust the mismatch between confidence and accuracy. We test our method on the ResNet50 and WideResNet28-10 architectures using the CIFAR10/100 and Tiny-ImageNet datasets.
  arXiv  Detail & Related papers  (2022-07-13T14:13:49Z)
• BSM loss: A superior way in modeling aleatory uncertainty of fine_grained classification [0.0]
  We propose a modified Bootstrapping loss(BS loss) function with Mixup data augmentation strategy. Our experiments indicated that BS loss with Mixup(BSM) model can halve the Expected Error(ECE) compared to standard data augmentation. BSM model is able to perceive the semantic distance of out-of-domain data, demonstrating high potential in real-world clinical practice.
  arXiv  Detail & Related papers  (2022-06-09T13:06:51Z)
• Rectified Meta-Learning from Noisy Labels for Robust Image-based Plant Disease Diagnosis [64.82680813427054]
  Plant diseases serve as one of main threats to food security and crop production. One popular approach is to transform this problem as a leaf image classification task, which can be addressed by the powerful convolutional neural networks (CNNs) We propose a novel framework that incorporates rectified meta-learning module into common CNN paradigm to train a noise-robust deep network without using extra supervision information.
  arXiv  Detail & Related papers  (2020-03-17T09:51:30Z)
• Calibrating Deep Neural Networks using Focal Loss [77.92765139898906]
  Miscalibration is a mismatch between a model's confidence and its correctness. We show that focal loss allows us to learn models that are already very well calibrated. We show that our approach achieves state-of-the-art calibration without compromising on accuracy in almost all cases.
  arXiv  Detail & Related papers  (2020-02-21T17:35:50Z)

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.