Quantifying uncertainty in lung cancer segmentation with foundation models applied to mixed-domain datasets

• URL: http://arxiv.org/abs/2403.13113v2
• Date: Wed, 4 Sep 2024 17:29:04 GMT
• Title: Quantifying uncertainty in lung cancer segmentation with foundation models applied to mixed-domain datasets
• Authors: Aneesh Rangnekar, Nishant Nadkarni, Jue Jiang, Harini Veeraraghavan,
• Abstract summary: Medical image foundation models have shown the ability to segment organs and tumors with minimal fine-tuning. These models are typically evaluated on task-specific in-distribution (ID) datasets. We introduced a comprehensive set of computationally fast metrics to evaluate the performance of multiple foundation models trained with self-supervised learning (SSL) SMIT produced a highest F1-score (LRAD: 0.60, 5Rater: 0.64) and lowest entropy (LRAD: 0.06, 5Rater: 0.12), indicating higher tumor detection rate and confident segmentations.
• Score: 6.712251433139412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Medical image foundation models have shown the ability to segment organs and tumors with minimal fine-tuning. These models are typically evaluated on task-specific in-distribution (ID) datasets. However, reliable performance on ID dataset does not guarantee robust generalization on out-of-distribution (OOD) datasets. Importantly, once deployed for clinical use, it is impractical to have `ground truth' delineations to assess ongoing performance drifts, especially when images fall into OOD category due to different imaging protocols. Hence, we introduced a comprehensive set of computationally fast metrics to evaluate the performance of multiple foundation models (Swin UNETR, SimMIM, iBOT, SMIT) trained with self-supervised learning (SSL). SSL pretraining was selected as this approach is applicable for large, diverse, and unlabeled image sets. All models were fine-tuned on identical datasets for lung tumor segmentation from computed tomography (CT) scans. SimMIM, iBOT, and SMIT used identical architecture, pretraining, and fine-tuning datasets to assess performance variations with the choice of pretext tasks used in SSL. Evaluation was performed on two public lung cancer datasets (LRAD: n = 140, 5Rater: n = 21) with different image acquisitions and tumor stage compared to training data (n = 317 public resource with stage III-IV lung cancers) and a public non-cancer dataset containing volumetric CT scans of patients with pulmonary embolism (n = 120). All models produced similarly accurate tumor segmentation on the lung cancer testing datasets. SMIT produced a highest F1-score (LRAD: 0.60, 5Rater: 0.64) and lowest entropy (LRAD: 0.06, 5Rater: 0.12), indicating higher tumor detection rate and confident segmentations. In the OOD dataset, SMIT misdetected least number of tumors, indicated by median volume occupancy of 5.67 cc compared to second best method SimMIM of 9.97 cc.

Related papers

• Towards a Benchmark for Colorectal Cancer Segmentation in Endorectal Ultrasound Videos: Dataset and Model Development [59.74920439478643]
  In this paper, we collect and annotated the first benchmark dataset that covers diverse ERUS scenarios. Our ERUS-10K dataset comprises 77 videos and 10,000 high-resolution annotated frames. We introduce a benchmark model for colorectal cancer segmentation, named the Adaptive Sparse-context TRansformer (ASTR)
  arXiv  Detail & Related papers  (2024-08-19T15:04:42Z)
• TotalSegmentator MRI: Sequence-Independent Segmentation of 59 Anatomical Structures in MR images [62.53931644063323]
  In this study we extended the capabilities of TotalSegmentator to MR images. We trained an nnU-Net segmentation algorithm on this dataset and calculated similarity coefficients (Dice) to evaluate the model's performance. The model significantly outperformed two other publicly available segmentation models (Dice score 0.824 versus 0.762; p0.001 and 0.762 versus 0.542; p)
  arXiv  Detail & Related papers  (2024-05-29T20:15:54Z)
• MRSegmentator: Robust Multi-Modality Segmentation of 40 Classes in MRI and CT Sequences [4.000329151950926]
  The model was trained on 1,200 manually annotated MRI scans from the UK Biobank, 221 in-house MRI scans and 1228 CT scans. It showcased high accuracy in segmenting well-defined organs, achieving Dice Similarity Coefficient (DSC) scores of 0.97 for the right and left lungs, and 0.95 for the heart. It also demonstrated robustness in organs like the liver (DSC: 0.96) and kidneys (DSC: 0.95 left, 0.95 right), which present more variability.
  arXiv  Detail & Related papers  (2024-05-10T13:15:42Z)
• High-Fidelity Image Synthesis from Pulmonary Nodule Lesion Maps using Semantic Diffusion Model [10.412300404240751]
  Lung cancer has been one of the leading causes of cancer-related deaths worldwide for years. Deep learning, computer-assisted diagnosis (CAD) models based on learning algorithms can accelerate the screening process. However, developing robust and accurate models often requires large-scale and diverse medical datasets with high-quality annotations.
  arXiv  Detail & Related papers  (2023-05-02T01:04:22Z)
• Mediastinal Lymph Node Detection and Segmentation Using Deep Learning [1.7188280334580195]
  In clinical practice, computed tomography (CT) and positron emission tomography (PET) imaging detect abnormal lymph nodes (LNs) Deep convolutional neural networks frequently segment items in medical photographs. A well-established deep learning technique UNet was modified using bilinear and total generalized variation (TGV) based up strategy to segment and detect mediastinal lymph nodes. The modified UNet maintains texture discontinuities, selects noisy areas, searches appropriate balance points through backpropagation, and recreates image resolution.
  arXiv  Detail & Related papers  (2022-11-24T02:55:20Z)
• Improving Classification Model Performance on Chest X-Rays through Lung Segmentation [63.45024974079371]
  We propose a deep learning approach to enhance abnormal chest x-ray (CXR) identification performance through segmentations. Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets.
  arXiv  Detail & Related papers  (2022-02-22T15:24:06Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• Deep learning-based COVID-19 pneumonia classification using chest CT images: model generalizability [54.86482395312936]
  Deep learning (DL) classification models were trained to identify COVID-19-positive patients on 3D computed tomography (CT) datasets from different countries. We trained nine identical DL-based classification models by using combinations of the datasets with a 72% train, 8% validation, and 20% test data split. The models trained on multiple datasets and evaluated on a test set from one of the datasets used for training performed better.
  arXiv  Detail & Related papers  (2021-02-18T21:14:52Z)
• Brain Tumor Segmentation and Survival Prediction using Automatic Hard mining in 3D CNN Architecture [0.30098583327398537]
  We utilize 3-D fully convolutional neural networks (CNN) to segment gliomas and its constituents from multimodal Magnetic Resonance Images (MRI) The architecture uses dense connectivity patterns to reduce the number of weights and residual connections and is 0.448 with weights obtained from training this model with BraTS 2018 dataset. Hard mining is done during training to train for the difficult cases of segmentation tasks by increasing the dice similarity coefficient (DSC) threshold to choose the hard cases as epoch increases.
  arXiv  Detail & Related papers  (2021-01-05T14:34:16Z)
• Chest x-ray automated triage: a semiologic approach designed for clinical implementation, exploiting different types of labels through a combination of four Deep Learning architectures [83.48996461770017]
  This work presents a Deep Learning method based on the late fusion of different convolutional architectures. We built four training datasets combining images from public chest x-ray datasets and our institutional archive. We trained four different Deep Learning architectures and combined their outputs with a late fusion strategy, obtaining a unified tool.
  arXiv  Detail & Related papers  (2020-12-23T14:38:35Z)
• A new semi-supervised self-training method for lung cancer prediction [0.28734453162509355]
  There are only relatively few methods that simultaneously detect and classify nodules from computed tomography (CT) scans. This study presents a complete end-to-end scheme to detect and classify lung nodules using the state-of-the-art Self-training with Noisy Student method.
  arXiv  Detail & Related papers  (2020-12-17T09:53:51Z)

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.