Efficient Scopeformer: Towards Scalable and Rich Feature Extraction for Intracranial Hemorrhage Detection

by   Yassine Barhoumi, et al.

The quality and richness of feature maps extracted by convolution neural networks (CNNs) and vision Transformers (ViTs) directly relate to the robust model performance. In medical computer vision, these information-rich features are crucial for detecting rare cases within large datasets. This work presents the "Scopeformer," a novel multi-CNN-ViT model for intracranial hemorrhage classification in computed tomography (CT) images. The Scopeformer architecture is scalable and modular, which allows utilizing various CNN architectures as the backbone with diversified output features and pre-training strategies. We propose effective feature projection methods to reduce redundancies among CNN-generated features and to control the input size of ViTs. Extensive experiments with various Scopeformer models show that the model performance is proportional to the number of convolutional blocks employed in the feature extractor. Using multiple strategies, including diversifying the pre-training paradigms for CNNs, different pre-training datasets, and style transfer techniques, we demonstrate an overall improvement in the model performance at various computational budgets. Later, we propose smaller compute-efficient Scopeformer versions with three different types of input and output ViT configurations. Efficient Scopeformers use four different pre-trained CNN architectures as feature extractors to increase feature richness. Our best Efficient Scopeformer model achieved an accuracy of 96.94% and a weighted logarithmic loss of 0.083 with an eight times reduction in the number of trainable parameters compared to the base Scopeformer. Another version of the Efficient Scopeformer model further reduced the parameter space by almost 17 times with negligible performance reduction. Hybrid CNNs and ViTs might provide the desired feature richness for developing accurate medical computer vision models


page 1

page 3

page 4

page 5

page 6

page 8

page 9

page 10


Scopeformer: n-CNN-ViT Hybrid Model for Intracranial Hemorrhage Classification

We propose a feature generator backbone composed of an ensemble of convo...

An Acceleration Method Based on Deep Learning and Multilinear Feature Space

Computer vision plays a crucial role in Advanced Assistance Systems. Mos...

Towards efficient feature sharing in MIMO architectures

Multi-input multi-output architectures propose to train multiple subnetw...

LegoNet: Alternating Model Blocks for Medical Image Segmentation

Since the emergence of convolutional neural networks (CNNs), and later v...

Optimizing Vision Transformers for Medical Image Segmentation and Few-Shot Domain Adaptation

The adaptation of transformers to computer vision is not straightforward...

Memory Efficient Adaptive Attention For Multiple Domain Learning

Training CNNs from scratch on new domains typically demands large number...

CT Image Harmonization for Enhancing Radiomics Studies

While remarkable advances have been made in Computed Tomography (CT), ca...

Please sign up or login with your details

Forgot password? Click here to reset