Self-Supervised Learning with Limited Labeled Data for Prostate Cancer Detection in High Frequency Ultrasound

Wilson, Paul F. R.; Mahdi, Gilany,; Jamzad, Amoon; Fooladgar, Fahimeh; To, Minh Nguyen Nhat; Wodlinger, Brian; Abolmaesumi, Purang; Mousavi, Parvin

doi:10.48550/arxiv.2211.00527

Cited by 1 publication

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This reduction in the number of parameters mitigates overfitting and is associated with an increase in performance. 2 We pre-train each model described above for 100 epochs using VICReg, then finetune them by loading the self-supervised weights and training the model with an additional MLP classifier attached. We train the model to detect cancer in individual ROIs, then match each ROI to their corresponding core.…”

Section: Roi-scale Finetuningmentioning

confidence: 99%

Benchmarking image transformers for prostate cancer detection from ultrasound data

Harmanani,

Wilson,

Fooladgar

et al. 2024

Medical Imaging 2024: Image-Guided Procedures, Robotic Interventions, and Modeling

View full text Add to dashboard Cite

PURPOSE:Deep learning methods for classifying prostate cancer (PCa) in ultrasound images typically employ convolutional neural networks (CNN) to detect cancer in small regions of interest (ROI) along a needle trace region. However, this approach suffers from weak labelling, since the ground-truth histopathology labels do not describe the properties of individual ROIs. Recently, multi-scale approaches have sought to mitigate this issue by combining the context awareness of transformers with a convolutional feature extractor to detect cancer from multiple ROIs using multiple-instance learning (MIL). In this work, we present a detailed study of several image transformer architectures for both ROI-scale and multi-scale classification, and a comparison of the performance of CNNs and transformers for ultrasound-based prostate cancer classification. We also design a novel multi-objective learning strategy that combines both ROI and core predictions to further mitigate label noise. METHODS: We use a dataset of 6607 prostate biopsy cores extracted from 693 patients at 5 distinct clinical centers. We evaluate 3 image transformers on ROI-scale cancer classification, then use the strongest model to tune a multi-scale classifier with MIL, wherein another transformer is fine-tuned on top of the existing model's features. We train our MIL models using our novel multi-objective learning strategy and compare our results to existing baselines. RESULTS: We find that for both ROI-scale and multi-scale PCa detection, image transformer backbones lag behind their CNN counterparts. This deficit in performance is even more noticeable for larger models. When using multi-objective learning, we are able to improve the performance of MIL models, with a 77.9% AUROC, a sensitivity of 75.9%, and a specificity of 66.3%, a considerable improvement over the baseline. CONCLUSION: We conclude that convolutional networks are better suited for modelling sparse datasets of prostate ultrasounds, producing more robust features than their transformer counterparts in PCa detection. Multi-scale methods remain the best architecture for this task, with multi-objective learning presenting an effective way to improve performance.

show abstract

Section: Roi-scale Finetuningmentioning

confidence: 99%