MultiCheXNet: A Multi-Task Learning Deep Network For Pneumonia-like Diseases Diagnosis From X-ray Scans

TL;DR

MultiCheXNet is a multi-task deep learning model that simultaneously diagnoses, segments, and localizes pneumonia-like diseases from X-ray images, improving efficiency and performance through shared features and transfer learning.

Contribution

It introduces a multi-task learning architecture for pneumonia-like diseases that combines diagnosis, segmentation, and localization in a single model, with transfer learning for unseen diseases.

Findings

Outperforms baseline models on multiple tasks

Speeds up inference compared to separate models

Effective transfer learning to COVID-19 dataset

Abstract

We present MultiCheXNet, an end-to-end Multi-task learning model, that is able to take advantage of different X-rays data sets of Pneumonia-like diseases in one neural architecture, performing three tasks at the same time; diagnosis, segmentation and localization. The common encoder in our architecture can capture useful common features present in the different tasks. The common encoder has another advantage of efficient computations, which speeds up the inference time compared to separate models. The specialized decoders heads can then capture the task-specific features. We employ teacher forcing to address the issue of negative samples that hurt the segmentation and localization performance. Finally,we employ transfer learning to fine tune the classifier on unseen pneumonia-like diseases. The MTL architecture can be trained on joint or dis-joint labeled data sets. The training of the architecture follows a carefully designed protocol, that pre trains different sub-models on specialized datasets, before being integrated in the joint MTL model. Our experimental setup involves variety of data sets, where the baseline performance of the 3 tasks is compared to the MTL architecture performance. Moreover, we evaluate the transfer learning mode to COVID-19 data set,both from individual classifier model, and from MTL architecture classification head.