Bone Marrow Cytomorphology Cell Detection using InceptionResNetV2
- URL: http://arxiv.org/abs/2305.05430v1
- Date: Tue, 9 May 2023 13:18:35 GMT
- Title: Bone Marrow Cytomorphology Cell Detection using InceptionResNetV2
- Authors: Raisa Fairooz Meem, Khandaker Tabin Hasan
- Abstract summary: This paper presents a novel transfer learning model for Bone Marrow Cell Detection.
The proposed model achieved 96.19% accuracy which can be used in the future for analysis of other medical images in this domain.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Critical clinical decision points in haematology are influenced by the
requirement of bone marrow cytology for a haematological diagnosis. Bone marrow
cytology, however, is restricted to reference facilities with expertise, and
linked to inter-observer variability which requires a long time to process that
could result in a delayed or inaccurate diagnosis, leaving an unmet need for
cutting-edge supporting technologies. This paper presents a novel transfer
learning model for Bone Marrow Cell Detection to provide a solution to all the
difficulties faced for the task along with considerable accuracy. The proposed
model achieved 96.19\% accuracy which can be used in the future for analysis of
other medical images in this domain.
Related papers
- Low-Resolution Chest X-ray Classification via Knowledge Distillation and Multi-task Learning [46.75992018094998]
This research addresses the challenges of diagnosing chest X-rays (CXRs) at low resolutions.
High-resolution CXR imaging is crucial for identifying small but critical anomalies, such as nodules or opacities.
This paper presents the Multilevel Collaborative Attention Knowledge (MLCAK) method.
arXiv Detail & Related papers (2024-05-22T06:10:54Z) - Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRI [55.78588835407174]
We propose a method that reformulates the generation task of diffusion models as a patch-based estimation of healthy brain anatomy.
We evaluate our approach on data of tumors and multiple sclerosis lesions and demonstrate a relative improvement of 25.1% compared to existing baselines.
arXiv Detail & Related papers (2023-03-07T09:40:22Z) - Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial
Hemorrhage Etiology based on CT Scan [40.51754649947294]
The deep learning model was developed with 1868 eligible NCCT scans with non-traumatic ICH collected between January 2011 and April 2018.
The model's diagnostic performance was compared with clinicians's performance.
The clinicians achieve significant improvements in the sensitivity, specificity, and accuracy of diagnoses of certain hemorrhage etiologies with proposed system augmentation.
arXiv Detail & Related papers (2023-02-02T08:45:17Z) - Beyond Labels: Visual Representations for Bone Marrow Cell Morphology
Recognition [3.4352862428120123]
We improve on the state-of-the-art methodologies of bone marrow cell recognition by deviating from sole reliance on labeled data.
Our experiments demonstrate significant performance improvements in conducting different bone marrow cell recognition tasks.
arXiv Detail & Related papers (2022-05-19T22:05:46Z) - Breast Cancer Induced Bone Osteolysis Prediction Using Temporal
Variational Auto-Encoders [65.95959936242993]
We develop a deep learning framework that can accurately predict and visualize the progression of osteolytic bone lesions.
It will assist in planning and evaluating treatment strategies to prevent skeletal related events (SREs) in breast cancer patients.
arXiv Detail & Related papers (2022-03-20T21:00:10Z) - Bone Marrow Cell Recognition: Training Deep Object Detection with A New
Loss Function [10.34651590388805]
This paper proposes a bone marrow cell detection algorithm based on the YOLOv5 network, trained by minimizing a novel loss function.
The proposed novel loss function considers the similarity between bone marrow cell classes, increases the penalty for prediction errors between dissimilar classes, and reduces the penalty for prediction errors between similar classes.
The results show that the proposed loss function effectively improves the algorithm's performance, and the proposed bone marrow cell detection algorithm has achieved better performance than other cell detection algorithms.
arXiv Detail & Related papers (2021-10-25T05:17:04Z) - Primary Tumor and Inter-Organ Augmentations for Supervised Lymph Node
Colon Adenocarcinoma Metastasis Detection [8.69535649683089]
scarcity of labeled data is a major bottleneck for developing deep learning-based models for histopathology applications.
This work explores alternatives on how to augment the training data for colon carcinoma metastasis detection when there is limited or no representation of the target domain.
arXiv Detail & Related papers (2021-09-17T17:31:25Z) - Learned super resolution ultrasound for improved breast lesion
characterization [52.77024349608834]
Super resolution ultrasound localization microscopy enables imaging of the microvasculature at the capillary level.
In this work we use a deep neural network architecture that makes effective use of signal structure to address these challenges.
By leveraging our trained network, the microvasculature structure is recovered in a short time, without prior PSF knowledge, and without requiring separability of the UCAs.
arXiv Detail & Related papers (2021-07-12T09:04:20Z) - Histogram of Cell Types: Deep Learning for Automated Bone Marrow
Cytology [3.8385120184415418]
Histogram of Cell Types (HCT) is a novel representation of bone marrow cell class probability distribution.
HCT has potential to revolutionize hematopathology diagnostic, leading to more cost-effective, accurate diagnosis and opening the door to precision medicine.
arXiv Detail & Related papers (2021-07-05T21:55:00Z) - An Attention-based Weakly Supervised framework for Spitzoid Melanocytic
Lesion Diagnosis in WSI [1.0948946179065253]
Melanoma is an aggressive neoplasm responsible for the majority of deaths from skin cancer.
The gold standard for its diagnosis and prognosis is the analysis of skin biopsies.
We propose a novel end-to-end weakly-supervised deep learning model, based on inductive transfer learning with an improved convolutional neural network (CNN)
The framework is composed of a source model in charge of finding the tumor patch-level patterns, and a target model focuses on the specific diagnosis of a biopsy.
arXiv Detail & Related papers (2021-04-20T10:18:57Z) - Spectral-Spatial Recurrent-Convolutional Networks for In-Vivo
Hyperspectral Tumor Type Classification [49.32653090178743]
We demonstrate the feasibility of in-vivo tumor type classification using hyperspectral imaging and deep learning.
Our best model achieves an AUC of 76.3%, significantly outperforming previous conventional and deep learning methods.
arXiv Detail & Related papers (2020-07-02T12:00:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.