# BLS-GAN: A Deep Layer Separation Framework for Eliminating Bone Overlap in Conventional Radiographs

arXiv: https://arxiv.org/abs/2409.07304 · HTML: https://mlsanity.com/paper/2409.07304/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 11 Sep 2024.

## Builds on (most cited first, 5 of 5)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --](https://mlsanity.com/paper/2301.03362/) (2023)
- [Amodal Completion via Progressive Mixed Context Diffusion](https://mlsanity.com/paper/2312.15540/) (2023)
- [GAN-based disentanglement learning for chest X-ray rib suppression](https://mlsanity.com/paper/2110.09134/) (2021)
- [Decompose X-ray Images for Bone and Soft Tissue](https://mlsanity.com/paper/2007.14510/) (2020)

## Built on by (most cited first, 3 of 3)

- [RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis](https://mlsanity.com/paper/2507.05193/) (2025)
- [Layer Separation: Adjustable Joint Space Width Images Synthesis in Conventional Radiography](https://mlsanity.com/paper/2502.01972/) (2025)
- [RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis](https://mlsanity.com/paper/2605.05616/) (2026)

## Abstract (arXiv)

Conventional radiography is the widely used imaging technology in diagnosing, monitoring, and prognosticating musculoskeletal (MSK) diseases because of its easy availability, versatility, and cost-effectiveness. In conventional radiographs, bone overlaps are prevalent, and can impede the accurate assessment of bone characteristics by radiologists or algorithms, posing significant challenges to conventional and computer-aided diagnoses. This work initiated the study of a challenging scenario - bone layer separation in conventional radiographs, in which separate overlapped bone regions enable the independent assessment of the bone characteristics of each bone layer and lay the groundwork for MSK disease diagnosis and its automation. This work proposed a Bone Layer Separation GAN (BLS-GAN) framework that can produce high-quality bone layer images with reasonable bone characteristics and texture. This framework introduced a reconstructor based on conventional radiography imaging principles, which achieved efficient reconstruction and mitigates the recurrent calculations and training instability issues caused by soft tissue in the overlapped regions. Additionally, pre-training with synthetic images was implemented to enhance the stability of both the training process and the results. The generated images passed the visual Turing test, and improved performance in downstream tasks. This work affirms the feasibility of extracting bone layer images from conventional radiographs, which holds promise for leveraging bone layer separation technology to facilitate more comprehensive analytical research in MSK diagnosis, monitoring, and prognosis. Code and dataset: https://github.com/pokeblow/BLS-GAN.git.