Dr. Md Belayat Hossain Profile

Dr. Md Belayat Hossain

at Univ of Pittsburgh

SPIE Involvement:

Author

Publications (5)

Proceedings Article | 3 April 2024 Presentation + Paper

Developing an image-domain transformation technique for adapting deep learning algorithms: preliminary work using simulated tomosynthesis of breast patches

Md Belayat Hossain, Bruno Barufaldi, Andrew D. Maidment, Robert Nishikawa, Juhun Lee

Proceedings Volume 12927, 129271O (2024) https://doi.org/10.1117/12.3007467

KEYWORDS: Digital breast tomosynthesis, Image quality, Breast, Artificial intelligence, Deep learning, Algorithm development, Imaging systems

Read Abstract +

When image data changes due to routine imaging machine updates, the performance of previously-trained deep learning (DL)-algorithms can be degraded. To mitigate the potential for performance degradation, we introduced an image-domain transfer approach by using a conditional Generative Adversarial Network (CGAN) that can transform the images acquired after the update to match previous images. Some studies have proposed domain adaptation (DA) method for DL algorithms from the old system to the new system. However, we sought to investigate the suitability of the DA method for transferring images from the current system to that of the previous system to adapt existing DL-algorithm in the current system. We validated our domain transfer approach using 1,000 DBT patch volumes (500 lesions; 500 normal) with two distinct image qualities under a virtual clinical trial framework. We curated two DBT image sets of breast patches with two distinct image qualities using different image reconstruction settings (simulating two different systems; e.g., previous and current). We then divided our data into training, validation, and testing set with a ratio of 0.8:0.1:0.1. Using the training set, we developed two CGANs (normal and lesion) for image-domain transformation from current to previous systems. We fine-tuned a DenseNet121 network as a reference classifier for classifying lesions vs. normal DBT patch volumes using the training set from the previous system. We evaluated our domain-transfer method by testing the reference model on the test sets in three qualities: a) previous (S_P), b) current (S_C), and c) domain-transferred images (DT_C2P). The performance of the reference model with an AUC of 1.0 on the previous images, was degraded to an AUC of 0.88 (S_C vs S_P: p < 0.005) on the current images, but restored its performance to an AUC of 0.97 on the DT-images (S_C vs DT_C2P: p < 0.005). This result demonstrated that our domain transfer approach effectively restores the reference model’s original performance on images with current quality.

Proceedings Article | 1 April 2024 Poster + Paper

Representation of complex mammary parenchyma texture in tomosynthesis using simplex noise simulations

Bruno Barufaldi, Chloe Choi, Joao P. Teixeira, Magnus Dustler, Raphael Englander, Thaís do Rêgo, Yuri Malheiros, Telmo Silva Filho, Belayat Hossain, Juhun Lee, Andrew D. Maidment

Proceedings Volume 12925, 1292548 (2024) https://doi.org/10.1117/12.3006839

KEYWORDS: Breast, Simulations, Quantum noise, Anatomy, Tissues, Breast density, Digital breast tomosynthesis, Adipose tissue, X-rays, Breast cancer

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Developing a task-oriented deep convolutional neural network application towards estimating near-term breast cancer risk: preliminary work

Md Belayat Hossain, Juhun Lee

Proceedings Volume 12465, 124650J (2023) https://doi.org/10.1117/12.2654196

KEYWORDS: Breast cancer, Mathematical optimization, Performance modeling, Data modeling, Breast, Mammography, Image segmentation, Deep convolutional neural networks, Statistical modeling

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Improving lesion detection algorithm in digital breast tomosynthesis leveraging ensemble cross-validation models with multi-depth levels

Belayat Hossain, Robert Nishikawa, Juhun Lee

Proceedings Volume 12033, 120330D (2022) https://doi.org/10.1117/12.2611007

KEYWORDS: Digital breast tomosynthesis, Detection and tracking algorithms, Performance modeling, Breast, Image segmentation, Algorithm development, Data modeling, Cancer

Read Abstract +

Proceedings Article | 16 March 2020 Paper

A deep learning approach for surgical instruments detection in orthopaedic surgery using transfer learning

Belayat Hossain, Shoichi Nishio, Hiranaka Takafunio, Syoji Kobashi

Proceedings Volume 11315, 113151M (2020) https://doi.org/10.1117/12.2550670

KEYWORDS: Surgery, Video, Navigation systems, Detection and tracking algorithms, Image classification, Databases, Laparoscopy, Machine learning

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years