Metaphase finding with deep convolutional neural networks

A Circular Box-Based Deep Learning Model for the Identification of Signet Ring Cells from Histopathological Images

Signet ring cell (SRC) carcinoma is a particularly serious type of cancer that is a leading cause of death all over the world. SRC carcinoma has a more deceptive onset than other carcinomas and is mostly encountered in its later stages. Thus, the recognition of SRCs at their initial stages is a challenge because of different variants and sizes and illumination changes. The recognition process of SRCs at their early stages is costly because of the requirement for medical experts. A timely diagnosis is important because the level of the disease determines the severity, cure, and survival rate of victims. To tackle the current challenges, a deep learning (DL)-based methodology is proposed in this paper, i.e., custom CircleNet with ResNet-34 for SRC recognition and classification. We chose this method because of the circular shapes of SRCs and achieved better performance due to the CircleNet method. We utilized a challenging dataset for experimentation and performed augmentation to increase the dataset samples. The experiments were conducted using 35,000 images and attained 96.40% accuracy. We performed a comparative analysis and confirmed that our method outperforms the other methods.

An improved deep convolutional neural network architecture for chromosome abnormality detection using hybrid optimization model

Chromosomes are thread-like structures located in the cell nucleus that contains the human body blueprint. Chromosome analysis is also known as karyotyping is the test taken to detect the abnormalities identified in the human chromosome. The two types of widely known chromosome abnormalities are structural and numerical abnormalities. Manual karyotyping is complex, time-consuming, and error-prone. To overcome these complexities, automated chromosome karyotype architecture is proposed using the deep convolutional neural network (DCNN) architecture. Training the DCNN architecture from scratch needs a huge dataset and to overcome this problem a generative adversarial networks is used to create adversarial samples that resemble the images in the actual dataset. The time-consuming hyperparameter tuning in the DCNN architecture is overcome using the hybrid moth-flame optimization integrated with the hill-climbing strategy (HMFOHC). The HMFOHC algorithm is mainly utilized in this article to minimize the huge number of parameters associated with the DCNN architecture. The efficiency of the proposed methodology is evaluated using two datasets namely the BioImLab chromosome dataset and hospital dataset. The proposed HMFOHC optimized DCNN architecture is mainly utilized for multiclass classification where it differentiates five numerical chromosome abnormalities, namely Trisomy 13, Trisomy 18, Trisomy 21, Trisomy XXY syndrome, and Monosomy X. The proposed model offers an accuracy, F1-score, and kappa coefficient value of 98.65%, 98.86%, and 0.9894, respectively. The results obtained show that the proposed model achieves higher classification accuracy when compared with the different state-of-art techniques such as deep learning, random forest, and CNN. The inference time of the proposed methodology is 12.5 s which is relatively lower than the state-of-art techniques. The proposed approach can help cytogenetics forensic experts make better decisions and save time by automating manual karyotyping.

Classification of analyzable metaphase images using transfer learning and fine tuning

Chromosomes are bodies that contain human genetic information. Chromosomal disorders can cause structural and functional disorders in individuals. Detecting the metaphase stages of the cells accurately is a crucial step to detect possible defects in chromosomes. Thus, it is vital at this stage to identify the identical chromosome of each chromosome, to perform the pairing process, and to identify problems arising from this process. In this study, it was investigated whether the analyzable metaphase images can be analyzed by using the transfer learning and fine tuning approaches of deep learning models. The weights of VGG16 and InceptionV3 models trained with ImageNet data set were transferred to this problem and the classification process was carried out. True positive ratio values are 99%(± 0.9) and 99%(± 0.9) for VGG and Inception networks, respectively. The classification performances obtained depending on the changing training set ratios are presented comparatively in figures. F-measure, precision, and recall values obtained for the VGG and Inception networks were observed as 99%(± 1.0) and 99%(± 1.0), respectively. F-measure, precision, and recall values of VGG and Inceptionv3 networks are also presented with respect to the ratio of training size. The obtained results have compared with the state-of-the-art methods in the literature and supported with the tables and graphics. The training phase was also accelerated by using transfer learning and fine tuning methods. Transfer learning and fine tuning processes have almost similar performance as the models used in the literature and trained from scratch in metaphase Graphical Abstract The Flowchart of the proposed system for classifying metaphase candidates detection.