Analysing TB severity levels with an enhanced deep residual learning– depth-resnet

Gao, Xiaohong W., James-Reynolds, Carl and Currie, Edward (2018) Analysing TB severity levels with an enhanced deep residual learning– depth-resnet. In: ImageCLEF ImageCLEFtuberculosis competition, 10-14 Sept 2018, Avignon, France.

[img]
Preview
PDF - Published version (with publisher's formatting)
Download (956kB) | Preview

Abstract

This work responds to the Competition of Tuberculosis Task organised by imageCLEF 2018. While Task #3 appears to be challenging, the experience was very enjoyable. If time had been permitted, it was certain that more accurate results could have been achieved. The authors submitted 2 runs. Based on the given training datasets with severity levels of 1 to 5, an enhanced deep residual learning architecture, depthResNet, is developed and applied to train the datasets to classify 5 categories. The datasets are pre-processed with each volume being segmented into twenty- 128×128×depth blocks with ~64 pixel overlaps. While each block has been predicted with a severity level, assembling all constituent block scores together to give an overall label for the concerned volume tends to be more challenging. Since the probability of high severity is not provided from the training datasets, which bears little resemblance to the classification probability, the submission of probability for the first run was manually assigned as 0.9, 0.7, 0.5, 0.3, and 0.1 to severity levels of 1 to 5 respectively. After the deadline was extended, the model was re-trained with frame numbers increased from 1 to 8, which takes much longer to train. In addition, a new measure was introduced to calculate the overall probability of high severity based on the block scores. As a result, with regard to classification accuracy, the 2nd submitted run achieved place 14 over a total of 36 submissions, a significant
improvement from position of 35 from the first run.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Paper published in: CLEF 2018 Working Notes: Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum, Avignon, France, September 10-14, 2018. Edited by Linda Cappellato, Nicola Ferro, Jian-Yun Nie, Laure Soulier.
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 24811
Useful Links:
Depositing User: Xiaohong Gao
Date Deposited: 21 Aug 2018 08:49
Last Modified: 06 Apr 2019 07:22
URI: https://eprints.mdx.ac.uk/id/eprint/24811

Actions (login required)

Edit Item Edit Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year