eprintid: 16700
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/67/00
datestamp: 2023-12-19 03:23:13
lastmod: 2023-12-19 03:23:13
status_changed: 2023-12-19 03:06:44
type: article
metadata_visibility: show
creators_name: Gajbhiye, G.O.
creators_name: Nandedkar, A.V.
creators_name: Faye, I.
title: Translating medical image to radiological report: Adaptive multilevel multi-attention approach
ispublished: pub
keywords: Application programs; Convolutional neural networks; Diagnosis; Embeddings; Long short-term memory; Medical imaging; Natural language processing systems; Radiation; Semantics; Signal encoding; Translation (languages), Attention mechanisms; Embeddings; Encoder-decoder; Multilevel multi-attention mechanism; Multilevels; Radiology report generation; Radiology reports; Radiology-trained word embedding; Report generation; Residual attention module, Radiology, accuracy; Article; convolutional neural network; diagnostic imaging; human; medical terminology; multiple malformation syndrome; qualitative analysis; recall; thorax radiography; training; algorithm; radiography; semantics; software, Algorithms; Humans; Neural Networks, Computer; Radiography; Semantics; Software
note: cited By 1
abstract: Background and Objective: Medical imaging techniques are widely employed in disease diagnosis and treatment. A readily available medical report can be a useful tool in assisting an expert for investigating the patient's health. A radiologist can benefit from an automatic medical image to radiological report translation system while preparing a final report. Previous attempts on automatic medical report generation task includes image captioning algorithms without taking domain-specific visual and textual contents into account, thus arises the question about credibility of generated report. Methods: In this work, a novel Adaptive Multilevel Multi-Attention (AMLMA) approach is proposed by offering domain-specific visual-textual knowledge to generate a thorough and believable radiological report for any view of a human chest X-ray image. The proposed approach leverages the encoder-decoder framework incorporated with multiple adaptive attention mechanisms. The potential of a convolutional neural network (CNN) with residual attention module (RAM) is demonstrated as a strong visual encoder for multi-label abnormality detection. The multilevel visual features (local and global) are extracted from proposed visual encoder to retrieve regional-level and abstract-level radiology-based semantic information. The Word2Vec and FastText word embeddings are trained on medical reports to acquire radiological knowledge and further used as textual encoders, feeding as input to Bi-directional Long Short Term Memory (Bi-LSTM) network to learn the co-relationship between medical terminologies in radiological reports. The AMLMA employs a weighted multilevel association of adaptive visual-semantic attention and visual-based linguistic attention mechanisms. This association of adaptive attention is exploited as a decoder and produces significant improvements in the report generation task. Results: The proposed approach is evaluated on a publicly available Indiana University chest X-ray (IU-CXR) dataset. The CNN with RAM shows the significant improvement in recall (0.4423), precision (0.1803) and F1-score (0.2551) for prediction of multiple abnormalities in X-ray image. The results of language generation metrics for proposed variants were acquired using the COCO-caption evaluation Application Program Interface (API). The trained embeddings with AMLMA model generates the convincing radiology report and outperform state-of-the-art (SOTA) approaches with high evaluation metrics scores for Bleu-4 (0.172), Meteor (0.247), RougeL (0.376) and CIDEr (0.381). In addition, a new �Unique Index� (UI) statistic is introduced to highlight the model's ability for generating unique reports. Conclusion: The overall architecture aids to the understanding of various X-ray image views and generating the relevant normal and abnormal radiography statements. The proposed model is emphasized on multi-level visual-textual knowledge with adaptive attention mechanism to balance visual and linguistic information for the generation of admissible radiology report. © 2022 Elsevier B.V.
date: 2022
publisher: Elsevier Ireland Ltd
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85129770805&doi=10.1016%2fj.cmpb.2022.106853&partnerID=40&md5=9da9b11e6d480c3e0979bc75b4590804
id_number: 10.1016/j.cmpb.2022.106853
full_text_status: none
publication: Computer Methods and Programs in Biomedicine
volume: 221
refereed: TRUE
issn: 01692607
citation:   Gajbhiye, G.O. and Nandedkar, A.V. and Faye, I.  (2022) Translating medical image to radiological report: Adaptive multilevel multi-attention approach.  Computer Methods and Programs in Biomedicine, 221.   ISSN 01692607