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

Basu, Soumen; Gupta, Mona; Rana, Pratyaksha; Gupta, Pankaj; Arora, Chetan

doi:10.1109/cvpr52688.2022.02022

Cited by 20 publications

(7 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Basu et al. reported a unique model for detecting gallbladder cancer (GBC) using ultrasound images that consists of two stages: detecting the gallbladder and classifying GBCs 24 . Applying such a method and focusing on regions of interest may improve our results.…”

Section: Discussionmentioning

confidence: 98%

Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning

Nakamura,

Fukuda,

Matsuda

et al. 2024

DEN Open

View full text Add to dashboard Cite

ObjectivesLocalized autoimmune pancreatitis is difficult to differentiate from pancreatic ductal adenocarcinoma on endoscopic ultrasound images. In recent years, deep learning methods have improved the diagnosis of diseases. Hence, we developed a special cross‐validation framework to search for effective methodologies of deep learning in distinguishing autoimmune pancreatitis from pancreatic ductal adenocarcinoma on endoscopic ultrasound images.MethodsData from 24 patients diagnosed with localized autoimmune pancreatitis (8751 images) and 61 patients diagnosed with pancreatic ductal adenocarcinoma (20,584 images) were collected from 2016 to 2022. We applied transfer learning to a convolutional neural network called ResNet152, together with our innovative imaging method contributing to data augmentation and temporal data process. We divided patients into five groups according to different factors for 5‐fold cross‐validation, where the ordered and balanced datasets were created for the performance evaluations.ResultsResNet152 surpassed the endoscopists in all evaluation metrics with almost all datasets. Interestingly, when the dataset is balanced according to the factor of the endoscopists’ diagnostic accuracy, the area under the receiver operating characteristic curve and accuracy were highest at 0.85 and 0.80, respectively.ConclusionsIt is deduced that image features useful for ResNet152 correlate with those used by endoscopists for their diagnoses. This finding may contribute to sample‐efficient dataset preparation to train convolutional neural networks for endoscopic ultrasonography‐imaging diagnosis.

show abstract

Section: Discussionmentioning

confidence: 98%

Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning

Nakamura,

Fukuda,

Matsuda

et al. 2024

DEN Open

View full text Add to dashboard Cite

show abstract

“…It adapts to the easier target domains first, then moves on to the more difficult ones. A curriculum based on human visual acuity [26] lessens the texture biases in models for gallbladder cancer. Most recently, the Curriculum By Smoothing (CBS) [18] employs the Gaussian filter of feature maps from a higher variance to lower across the training epochs.…”

Section: Related Workmentioning

confidence: 99%

Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding

Islam

Glocker

et al. 2024

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic vision. Most recent works focus on designing curricula based on difficulty levels in input samples or smoothing the feature maps. However, smoothing labels to control the learning utility in a curriculum manner is still unexplored. In this work, we design a paced curriculum by label smoothing (P-CBLS) using paced learning with uniform label smoothing (ULS) for classification tasks and fuse uniform and spatially varying label smoothing (SVLS) for semantic segmentation tasks in a curriculum manner. In ULS and SVLS, a bigger smoothing factor value enforces a heavy smoothing penalty in the true label and limits learning less information. Therefore, we design the curriculum by label smoothing (CBLS). We set a bigger smoothing value at the beginning of training and gradually decreased it to zero to control the model learning utility from lower to higher. We also designed a confidenceaware pacing function and combined it with our CBLS to investigate the benefits of various curricula. The proposed techniques are validated on four robotic surgery datasets of multiclass, multi-label classification, captioning, and segmentation tasks. We also investigate the robustness of our method by corrupting validation data into different severity levels. Our extensive analysis shows that the proposed method improves prediction accuracy and robustness. The code is publicly available at https://github.com/XuMengyaAmy/P-CBLS.

show abstract

“…The formal CL concept is first proposed by Bengio et al [7] with experiments on supervised visual and language learning [8][9][10][11][12]. After them, many methods are proposed to pursue generalization improvement or convergence speedup with the spirit of training from a sequence of easy-to-hard data.…”

Section: Related Work 21 Curriculum Learning (Cl)mentioning

confidence: 99%

Mixed-order self-paced curriculum learning for universal lesion detection

Li¹,

Huang²,

Zhou³

2023

Preprint

View full text Add to dashboard Cite

Self-paced curriculum learning (SCL) has demonstrated its great potential in computer vision, natural language processing, etc. During training, it implements easy-to-hard sampling based on online estimation of data difficulty. Most SCL methods commonly adopt a loss-based strategy of estimating data difficulty and deweight the 'hard' samples in the early training stage. While achieving success in a variety of applications, SCL stills confront two challenges in a medical image analysis task, such as universal lesion detection, featuring insufficient and highly class-imbalanced data: (i) the loss-based difficulty measurer is inaccurate; ii) the hard samples are under-utilized from a deweighting mechanism. To overcome these challenges, in this paper we propose a novel mixed-order self-paced curriculum learning (Mo-SCL) method. We integrate both uncertainty and loss to better estimate difficulty online and mix both hard and easy samples in the same mini-batch to appropriately alleviate the problem of under-utilization of hard samples. We provide a theoretical investigation of our method in the context of stochastic gradient descent optimization and extensive experiments based on the DeepLesion benchmark dataset for universal lesion detection (ULD). When applied for two state-of-the-art ULD methods, the proposed mixed-order SCL method can provide a free boost to lesion detection accuracy without extra special network designs.

show abstract

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

Cited by 20 publications

References 78 publications

Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning

Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning

Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding

Mixed-order self-paced curriculum learning for universal lesion detection

Contact Info

Product

Resources

About