Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders

• URL: http://arxiv.org/abs/2212.07050v3
• Date: Fri, 11 Oct 2024 08:19:58 GMT
• Title: Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders
• Authors: Jongseong Jang, Daeun Kyung, Seung Hwan Kim, Honglak Lee, Kyunghoon Bae, Edward Choi,
• Abstract summary: We propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models.
• Score: 50.689585476660554
• License:
• Abstract: Deep neural networks are increasingly used in medical imaging for tasks such as pathological classification, but they face challenges due to the scarcity of high-quality, expert-labeled training data. Recent efforts have utilized pre-trained contrastive image-text models like CLIP, adapting them for medical use by fine-tuning the model with chest X-ray images and corresponding reports for zero-shot pathology classification, thus eliminating the need for pathology-specific annotations. However, most studies continue to use the same contrastive learning objectives as in the general domain, overlooking the multi-labeled nature of medical image-report pairs. In this paper, we propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. We aim to improve the performance of zero-shot pathology classification without relying on external knowledge. Our method can be applied to any pre-trained contrastive image-text encoder and easily transferred to out-of-domain datasets without further training, as it does not use external data. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models, with an average macro AUROC increase of 4.3%. Additionally, our method outperforms the state-of-the-art and marginally surpasses board-certified radiologists in zero-shot classification for the five competition pathologies in the CheXpert dataset.

Related papers

• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• RadTex: Learning Efficient Radiograph Representations from Text Reports [7.090896766922791]
  We build a data-efficient learning framework that utilizes radiology reports to improve medical image classification performance with limited labeled data. Our model achieves higher classification performance than ImageNet-supervised pretraining when labeled training data is limited.
  arXiv  Detail & Related papers  (2022-08-05T15:06:26Z)
• Application of Transfer Learning and Ensemble Learning in Image-level Classification for Breast Histopathology [9.037868656840736]
  In Computer-Aided Diagnosis (CAD), traditional classification models mostly use a single network to extract features. This paper proposes a deep ensemble model based on image-level labels for the binary classification of benign and malignant lesions. Result: In the ensemble network model with accuracy as the weight, the image-level binary classification achieves an accuracy of $98.90%$.
  arXiv  Detail & Related papers  (2022-04-18T13:31:53Z)
• A Deep Learning Technique using a Sequence of Follow Up X-Rays for Disease classification [3.3345134768053635]
  The ability to predict lung and heart based diseases using deep learning techniques is central to many researchers. We present a hypothesis that X-rays of patients included with the follow up history of their most recent three chest X-ray images would perform better in disease classification.
  arXiv  Detail & Related papers  (2022-03-28T19:58:47Z)
• Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning [7.535751594024775]
  Retinopathy represents a group of retinal diseases that, if not treated timely, can cause severe visual impairments or even blindness. This paper presents a novel incremental cross-domain adaptation instrument that allows any deep classification model to progressively learn abnormal retinal pathologies. The proposed framework, evaluated on six public datasets, outperforms the state-of-the-art competitors by achieving an overall accuracy and F1 score of 0.9826 and 0.9846, respectively.
  arXiv  Detail & Related papers  (2021-10-18T13:45:21Z)
• Malignancy Prediction and Lesion Identification from Clinical Dermatological Images [65.1629311281062]
  We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images. We first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy.
  arXiv  Detail & Related papers  (2021-04-02T20:52:05Z)
• 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)
• Multi-label Thoracic Disease Image Classification with Cross-Attention Networks [65.37531731899837]
  We propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images. We also design a new loss function that beyond cross-entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class.
  arXiv  Detail & Related papers  (2020-07-21T14:37:00Z)
• Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model [71.80319052891817]
  We present a relation-driven semi-supervised framework for medical image classification. It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
  arXiv  Detail & Related papers  (2020-05-15T06:57:54Z)

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.