MedSkip: Medical Report Generation Using Skip Connections and Integrated Attention

2021 ◽  
Author(s):  
Esha Pahwa ◽  
Dwij Mehta ◽  
Sanjeet Kapadia ◽  
Devansh Jain ◽  
Achleshwar Luthra
Keyword(s):  
Medical Report ◽  
Report Generation

From medical image to automatic medical report generation

2015 ◽  
Vol 59 (2/3) ◽  
pp. 2:1-2:7 ◽  
Author(s):  
P. Kisilev ◽  
E. Walach ◽  
E. Barkan ◽  
B. Ophir ◽  
S. Alpert ◽  
...  
Keyword(s):  
Medical Image ◽  
Medical Report ◽  
Report Generation

AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation

2021 ◽  
pp. 72-82
Author(s):  
Di You ◽  
Fenglin Liu ◽  
Shen Ge ◽  
Xiaoxia Xie ◽  
Jing Zhang ◽  
...  
Keyword(s):  
Medical Report ◽  
Report Generation

scholarly journals Unifying neural learning and symbolic reasoning for spinal medical report generation

2021 ◽  
Vol 67 ◽  
pp. 101872
Author(s):  
Zhongyi Han ◽  
Benzheng Wei ◽  
Xiaoming Xi ◽  
Bo Chen ◽  
Yilong Yin ◽  
...  
Keyword(s):  
Medical Report ◽  
Report Generation ◽  
Symbolic Reasoning ◽  
Neural Learning

scholarly journals DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation

2021 ◽  
Author(s):  
Jia-Hong Huang ◽  
C.-H. Huck Yang ◽  
Fangyu Liu ◽  
Meng Tian ◽  
Yi-Chieh Liu ◽  
...  
Keyword(s):  
Retinal Images ◽  
Medical Report ◽  
Report Generation

scholarly journals Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation

2021 ◽  
Author(s):  
Xingyi Yang ◽  
Muchao Ye ◽  
Quanzeng You ◽  
Fenglong Ma
Keyword(s):  
Medical Report ◽  
Report Generation

scholarly journals Disease Classification with E-Report Generation, Authentication and Encryption

2021 ◽  
Vol 9 (VI) ◽  
pp. 2717-2721
Author(s):  
Ashish Kurane
Keyword(s):  
Automatic Generation ◽  
Disease Classification ◽  
Privacy Rights ◽  
Medical Field ◽  
Medical Report ◽  
Report Generation ◽  
Death Rates ◽  
The World ◽  
Classification Of Diseases

The assortment of data analysis on the origin of diseases and consequences of mortality is essential to keep track of death rates caused due to diseases. Thus, the classification of diseases is very crucial. Cancer is one of the huge and major diseases of concern in the world. Machine learning is extensively implemented in the medical field in the anticipation of medical errors and early revelation of diseases. Along with the implementation of technology in medical field there is need for authentication to safeguard the privacy rights of patient’s health information. Thus, in this paper, revelation of disease using CNN (Convolutional Neural Networks) algorithm is achieved along with authentication and automatic generation of e-medical report which is further encrypted using RSA (Rivest, Shamir, Adleman) algorithm to overcome the breach of information while being shared from one hospital to another.

scholarly journals Competence-based Multimodal Curriculum Learning for Medical Report Generation

2021 ◽  
Author(s):  
Fenglin Liu ◽  
Shen Ge ◽  
Xian Wu
Keyword(s):  
Medical Report ◽  
Report Generation

scholarly journals Knowledge-Driven Encode, Retrieve, Paraphrase for Medical Image Report Generation

2019 ◽  
Vol 33 ◽  
pp. 6666-6673 ◽  
Author(s):  
Christy Y. Li ◽  
Xiaodan Liang ◽  
Zhiting Hu ◽  
Eric P. Xing
Keyword(s):  
Domain Knowledge ◽  
Medical Knowledge ◽  
Disease Classification ◽  
Visual Features ◽  
Medical Report ◽  
Report Generation ◽  
Unit Graph ◽  
Modern Learning ◽  
High Level ◽  
Multiple Domains

Generating long and semantic-coherent reports to describe medical images poses great challenges towards bridging visual and linguistic modalities, incorporating medical domain knowledge, and generating realistic and accurate descriptions. We propose a novel Knowledge-driven Encode, Retrieve, Paraphrase (KERP) approach which reconciles traditional knowledge- and retrieval-based methods with modern learning-based methods for accurate and robust medical report generation. Specifically, KERP decomposes medical report generation into explicit medical abnormality graph learning and subsequent natural language modeling. KERP first employs an Encode module that transforms visual features into a structured abnormality graph by incorporating prior medical knowledge; then a Retrieve module that retrieves text templates based on the detected abnormalities; and lastly, a Paraphrase module that rewrites the templates according to specific cases. The core of KERP is a proposed generic implementation unit—Graph Transformer (GTR) that dynamically transforms high-level semantics between graph-structured data of multiple domains such as knowledge graphs, images and sequences. Experiments show that the proposed approach generates structured and robust reports supported with accurate abnormality description and explainable attentive regions, achieving the state-of-the-art results on two medical report benchmarks, with the best medical abnormality and disease classification accuracy and improved human evaluation performance.

Sign in / Sign up

Export Citation Format

Share Document