Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction

Abstract

Pancreatic ductal adenocarcinoma (PDAC) is the third most common cause of cancer death in the United States. Predicting tumors like PDACs (including both classification and segmentation) from medical images by deep learning is becoming a growing trend, but usually a large number of annotated data are required for training, which is very labor-intensive and time-consuming. In this paper, we consider a partially supervised setting, where cheap imagelevel annotations are provided for all the training data, and the costly per-voxel annotations are only available for a subset of them. We propose an Inductive Attention Guidance Network (IAG-Net) to jointly learn a global image-level classifier for normal/PDAC classification and a local voxellevel classifier for semi-supervised PDAC segmentation. We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semisupervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier. Experimental results show that our IAG-Net boosts PDAC segmentation accuracy by more than 5% compared with the state-of-the-arts.

Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

“…Previous studies have employed deep CNNs for automatic PDAC detection on CT scans [ 12 , 13 , 14 , 15 , 16 , 17 ], but only two studies validated their models on an external test set [ 15 , 16 ], with one using the publicly available pancreas dataset. Liu and Wu et al [ 15 ] developed a 2D, patch-based deep learning model using the VGG architecture to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue.…”

“…Recently, deep learning models have started to be investigated for automatic PDAC diagnosis [ 12 , 13 , 14 , 15 , 16 , 17 ]. However, most studies perform only binary classification of the input image as cancerous or not cancerous, without simultaneous lesion localization.…”

Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging

“…Only three articles stratified the results based on tumour size, reporting model performance for the subgroup of lesions with sizes smaller than 2 cm [ 35 , 36 , 37 ]. Two papers (Alves et al (2022) and Wang et al (2021)) reported the results for both lesion detection and localization, and only one paper proposed a fully automatic approach (Alves et al (2022)) [ 35 , 38 ]. The study by Liu et al (2020) was the only one comparing AI performance to radiologists based on the analysis of radiology reports, but no reader study was conducted [ 37 ].…”

“…Eleven articles addressed AI for automated PDAC detection (Table 1). Only three articles stratified the results based on tumour size, reporting model performance for the subgroup of lesions with sizes smaller than 2 cm [35][36][37] 2022)) [35,38]. The study by Liu et al (2020) was the only one comparing AI performance to radiologists based on the analysis of radiology reports, but no reader study was conducted [37].…”

Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

“…In this study, the state-of-the-art, self-configuring framework for medical segmenta- CT scans [12][13][14][15][16][17], but only two studies validated their models on an external test set 218 [15,16], with one using the publicly available pancreas dataset. Liu and Wu, et al More recently, Si, et al [16]…”