Literature DB >> 35018121

Deep Learning for the Automatic Diagnosis and Analysis of Bone Metastasis on Bone Scintigrams.

Simin Liu1, Ming Feng2, Tingting Qiao1, Haidong Cai1, Kele Xu3, Xiaqing Yu1, Wen Jiang1, Zhongwei Lv1, Yin Wang2, Dan Li1.   

Abstract

OBJECTIVE: To develop an approach for automatically analyzing bone metastases (BMs) on bone scintigrams based on deep learning technology.
METHODS: This research included a bone scan classification model, a regional segmentation model, an assessment model for tumor burden and a diagnostic report generation model. Two hundred eighty patients with BMs and 341 patients with non-BMs were involved. Eighty percent of cases were randomly extracted from two groups as training set. Remaining cases were as testing set. A deep residual convolutional neural network with different structures was used to determine whether metastatic bone lesions existed, regions of lesions were automatically segmented. Bone scan tumor burden index (BSTBI) was calculated; finally, diagnostic report could be automatically generated. The sensitivity, specificity and accuracy of classification model were compared with three physicians with different clinical experience. The Dice coefficient evaluated the effect of segmentation model and compared to the result of nnU-Net model. The correlation between BSTBI and blood alkaline phosphatase (ALP) level was analyzed to verify the efficiency of BSTBI. The performance of report generation model was evaluated by the accuracy of interpretation of report.
RESULTS: In testing set, the sensitivity, specificity and accuracy of classification model were 92.59%, 85.51% and 88.62%, respectively. The accuracy showed no statistical difference with moderately and experienced physicians and obviously outperformed the inexperienced. The Dice coefficient of BMs area was 0.7387 in segmentation stage. Based on the whole model frame, our segmentation model outperformed the nnU-Net. BSTBI value changed as the BMs changed. There was a positive correlation between BSTBI and ALP level. The accuracy of report generation model was 78.05%.
CONCLUSION: Deep learning based on automatic analysis frameworks for BMs can accurately identify BMs, preliminarily realize a fully automatic analysis process from raw data to report generation. BSTBI can be used as a quantitative evaluation indicator to assess the effect of therapy on BMs in different patients or in the same patient before and after treatment.
© 2022 Liu et al.

Entities:  

Keywords:  automatic report generation; bone metastases; bone scintigraphy; deep learning; tumor burden

Year:  2022        PMID: 35018121      PMCID: PMC8740774          DOI: 10.2147/CMAR.S340114

Source DB:  PubMed          Journal:  Cancer Manag Res        ISSN: 1179-1322            Impact factor:   3.989


  25 in total

1.  Computer-assisted interpretation of planar whole-body bone scans.

Authors:  May Sadik; Iman Hamadeh; Pierre Nordblom; Madis Suurkula; Peter Höglund; Mattias Ohlsson; Lars Edenbrandt
Journal:  J Nucl Med       Date:  2008-11-07       Impact factor: 10.057

2.  Phase II study of helical tomotherapy for oligometastatic colorectal cancer.

Authors:  B Engels; H Everaert; T Gevaert; M Duchateau; B Neyns; A Sermeus; K Tournel; D Verellen; G Storme; M De Ridder
Journal:  Ann Oncol       Date:  2010-08-04       Impact factor: 32.976

3.  [Predictive factors for skeletal-related events in lung cancer].

Authors:  A Villemain; B Ribeiro Baptista; N Paillot; M Soudant; O Menard; Y Martinet; A Tiotiu
Journal:  Rev Mal Respir       Date:  2019-12-18       Impact factor: 0.622

4.  Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network.

Authors:  Fangzhou Liao; Ming Liang; Zhe Li; Xiaolin Hu; Sen Song
Journal:  IEEE Trans Neural Netw Learn Syst       Date:  2019-02-14       Impact factor: 10.451

5.  Evaluation of a computer-assisted diagnosis system, BONENAVI version 2, for bone scintigraphy in cancer patients in a routine clinical setting.

Authors:  Mitsuru Koizumi; Kei Wagatsuma; Noriaki Miyaji; Taisuke Murata; Kenta Miwa; Tomohiro Takiguchi; Tomoko Makino; Masamichi Koyama
Journal:  Ann Nucl Med       Date:  2014-10-19       Impact factor: 2.668

6.  Investigation of computer-aided diagnosis system for bone scans: a retrospective analysis in 406 patients.

Authors:  Osamu Tokuda; Yuko Harada; Yona Ohishi; Naofumi Matsunaga; Lars Edenbrandt
Journal:  Ann Nucl Med       Date:  2014-02-27       Impact factor: 2.668

7.  The flare phenomenon on radionuclide bone scan in metastatic prostate cancer.

Authors:  J J Pollen; K F Witztum; W L Ashburn
Journal:  AJR Am J Roentgenol       Date:  1984-04       Impact factor: 3.959

8.  H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes.

Authors:  Xiaomeng Li; Hao Chen; Xiaojuan Qi; Qi Dou; Chi-Wing Fu; Pheng-Ann Heng
Journal:  IEEE Trans Med Imaging       Date:  2018-06-11       Impact factor: 10.048

9.  nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation.

Authors:  Fabian Isensee; Paul F Jaeger; Simon A A Kohl; Jens Petersen; Klaus H Maier-Hein
Journal:  Nat Methods       Date:  2020-12-07       Impact factor: 28.547

Review 10.  Percentage of the positive area of bone metastasis is an independent predictor of disease death in advanced prostate cancer.

Authors:  M Noguchi; H Kikuchi; M Ishibashi; S Noda
Journal:  Br J Cancer       Date:  2003-01-27       Impact factor: 7.640

View more
  1 in total

1.  Detection of developmental dysplasia of the hip in X-ray images using deep transfer learning.

Authors:  Mohammad Fraiwan; Noran Al-Kofahi; Ali Ibnian; Omar Hanatleh
Journal:  BMC Med Inform Decis Mak       Date:  2022-08-13       Impact factor: 3.298

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.