# Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning

arXiv: https://arxiv.org/abs/2204.11433 · HTML: https://mlsanity.com/paper/2204.11433/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 62 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images](https://mlsanity.com/paper/2004.14133/) (2020)
- [The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation](https://mlsanity.com/paper/2007.11978/) (2020)
- [Global Second-order Pooling Convolutional Networks](https://mlsanity.com/paper/1811.12006/) (2018)
- [Detecting and classifying lesions in mammograms with Deep Learning](https://mlsanity.com/paper/1707.08401/) (2017)
- [Is Second-order Information Helpful for Large-scale Visual Recognition?](https://mlsanity.com/paper/1703.08050/) (2017)
- [CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection](https://mlsanity.com/paper/2003.09119/) (2020)
- [Non-linear Convolution Filters for CNN-based Learning](https://mlsanity.com/paper/1708.07038/) (2017)
- [On the Texture Bias for Few-Shot CNN Segmentation](https://mlsanity.com/paper/2003.04052/) (2020)
- [Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographs](https://mlsanity.com/paper/1807.07532/) (2018)
- [Deep Learning Ensembles for Melanoma Recognition in Dermoscopy Images](https://mlsanity.com/paper/1610.04662/) (2016)
- [Automatic CNN-based detection of cardiac MR motion artefacts using k-space data augmentation and curriculum learning](https://mlsanity.com/paper/1810.12185/) (2018)
- [CASED: Curriculum Adaptive Sampling for Extreme Data Imbalance](https://mlsanity.com/paper/1807.10819/) (2018)
- [Fetal Ultrasound Image Segmentation for Measuring Biometric Parameters Using Multi-Task Deep Learning](https://mlsanity.com/paper/1909.00273/) (2019)
- [Confident Head Circumference Measurement from Ultrasound with Real-time Feedback for Sonographers](https://mlsanity.com/paper/1908.02582/) (2019)

## Built on by (most cited first, 16 of 16)

- [Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining](https://mlsanity.com/paper/2207.13148/) (2022)
- [RadFormer: Transformers with Global-Local Attention for Interpretable and Accurate Gallbladder Cancer Detection](https://mlsanity.com/paper/2211.04793/) (2022)
- [FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders](https://mlsanity.com/paper/2403.08848/) (2024)
- [SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendation](https://mlsanity.com/paper/2309.05675/) (2023)
- [Revisiting Data Augmentation for Ultrasound Images](https://mlsanity.com/paper/2501.13193/) (2025)
- [Gall Bladder Cancer Detection from US Images with Only Image Level Labels](https://mlsanity.com/paper/2309.05261/) (2023)
- [Focus on Texture: Rethinking Pre-training in Masked Autoencoders for Medical Image Classification](https://mlsanity.com/paper/2507.10869/) (2025)
- [Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding](https://mlsanity.com/paper/2212.11511/) (2022)
- [Gallbladder Cancer Detection in Ultrasound Images based on YOLO and Faster R-CNN](https://mlsanity.com/paper/2404.15129/) (2024)
- [LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Image](https://mlsanity.com/paper/2412.00374/) (2024)
- [CortiNet: A Physics-Perception Hybrid Cortical-Inspired Dual-Stream Network for Gallbladder Disease Diagnosis from Ultrasound](https://mlsanity.com/paper/2602.01000/) (2026)
- [Mixed-order self-paced curriculum learning for universal lesion detection](https://mlsanity.com/paper/2302.04677/) (2023)
- [Enhancing Signed Graph Neural Networks through Curriculum-Based Training](https://mlsanity.com/paper/2310.11083/) (2023)
- [Dual-Channel Reliable Breast Ultrasound Image Classification Based on Explainable Attribution and Uncertainty Quantification](https://mlsanity.com/paper/2401.03664/) (2024)
- [Assessing Risk of Stealing Proprietary Models for Medical Imaging Tasks](https://mlsanity.com/paper/2506.19464/) (2025)
- [UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound](https://mlsanity.com/paper/2609.28610/) (2026)

## Abstract (arXiv)

We explore the potential of CNN-based models for gallbladder cancer (GBC) detection from ultrasound (USG) images as no prior study is known. USG is the most common diagnostic modality for GB diseases due to its low cost and accessibility. However, USG images are challenging to analyze due to low image quality, noise, and varying viewpoints due to the handheld nature of the sensor. Our exhaustive study of state-of-the-art (SOTA) image classification techniques for the problem reveals that they often fail to learn the salient GB region due to the presence of shadows in the USG images. SOTA object detection techniques also achieve low accuracy because of spurious textures due to noise or adjacent organs. We propose GBCNet to tackle the challenges in our problem. GBCNet first extracts the regions of interest (ROIs) by detecting the GB (and not the cancer), and then uses a new multi-scale, second-order pooling architecture specializing in classifying GBC. To effectively handle spurious textures, we propose a curriculum inspired by human visual acuity, which reduces the texture biases in GBCNet. Experimental results demonstrate that GBCNet significantly outperforms SOTA CNN models, as well as the expert radiologists. Our technical innovations are generic to other USG image analysis tasks as well. Hence, as a validation, we also show the efficacy of GBCNet in detecting breast cancer from USG images. Project page with source code, trained models, and data is available at https://gbc-iitd.github.io/gbcnet