Kidney Tumor Classification on CT images using Self-supervised Learning

One of the most common diseases affecting society around the world is kidney tumor. The risk of kidney disease increases due to reasons such as consumption of ready-made food and bad habits. Early diagnosis of kidney tumors is essential for effective treatment, reducing side effects, and reducing the number of deaths. With the development of computer-aided diagnostic methods, the need for accurate renal tumor classification is also increasing. Because traditional methods based on manual detection are time-consuming, boring, and costly, high-accuracy tests can be performed faster and at a lower cost with deep learning (DL) methods in kidney tumor detection (KTD). Among the current challenges regarding artificial intelligence-assisted KTD, obtaining more precise programming information and the capacity to group with high accuracy make clinical determination more vital and bring it to an important point for current treatment in KTD prediction. This encourages us to propose a more effective DL model that can effectively assist specialist physicians in the diagnosis of kidney tumors. In this way, the workload of radiologists can be alleviated and errors in clinical diagnoses that may occur due to the complex structure of the kidney can be prevented. A large amount of data is needed during the training of the developed methods. Although various studies have been conducted to reduce the amount of data with feature selection techniques, these techniques provide little improvement in the classification accuracy rate. In this paper, a masked autoencoder (MAE) is proposed for KTD, which can produce effective results on datasets containing some samples and can be directly fine-tuned and pre-trained. Self-supervised learning (SSL) is achieved through self-distillation (SD), which can be reintroduced into the configuration loss calculation using masked patches. The SD loss on the decoder and encoder outputs' latent representation is calculated operating SSLSD-KTD. The encoder obtains local attention, while the decoder transfers its global attention to calculate losses. The SSLSD-KTD method reached 98.04 % classification accuracy on the KAUH-kidney dataset, including 8400 samples, and 82.14 % on the CT-kidney dataset, containing 840 samples. By adding more external information to the SSLSD-KTD method with transfer learning, accuracy results of 99.82 % and 95.24 % were obtained on the same datasets. Experimental results have shown that the SSLSD-KTD method can effectively extract kidney tumor features with limited data and can be an aid or even an alternative for radiologists in decision-making in the diagnosis of the disease.

Interpretable features fusion with precision MRI images deep hashing for brain tumor detection

BACKGROUND AND OBJECTIVE

Brain tumor is a deadly disease that can affect people of all ages. Radiologists play a critical role in the early diagnosis and treatment of the 14,000 persons diagnosed with brain tumors on average each year. The best method for tumor detection with computer-aided diagnosis systems (CADs) is Magnetic Resonance Imaging (MRI). However, manual evaluation using conventional approaches may result in a number of inaccuracies due to the complicated tissue properties of a large number of images. Therefore a precision medical image hashing approach is proposed that combines interpretability and feature fusion using MRI images of brain tumors, to address the issue of medical image retrieval.

METHODS

A precision hashing method combining interpretability and feature fusion is proposed to recover the problem of low image resolutions in brain tumor detection on the Brain-Tumor-MRI (BT-MRI) dataset. First, the dataset is pre-trained with the DenseNet201 network using the Comparison-to-Learn method. Then, a global network is created that generates the salience map to yield a mask crop with local region discrimination. Finally, the local network features inputs and public features expressing the local discriminant regions are concatenated for the pooling layer. A hash layer is added between the fully connected layer and the classification layer of the backbone network to generate high-quality hash codes. The final result is obtained by calculating the hash codes with the similarity metric.

RESULTS

Experimental results with the BT-MRI dataset showed that the proposed method can effectively identify tumor regions and more accurate hash codes can be generated by using the three loss functions in feature fusion. It has been demonstrated that the accuracy of medical image retrieval is effectively increased when our method is compared with existing image retrieval approaches.

CONCLUSIONS

Our method has demonstrated that the accuracy of medical image retrieval can be effectively increased and potentially applied to CADs.

Interpretable pap-smear image retrieval for cervical cancer detection with rotation invariance mask generation deep hashing

Cervical cancer is a common disease in women, affecting their lives negatively and often resulting in death. Pap-smear tests are preferred by doctors as the primary tool in the early diagnosis and treatment of the disease. Physicians can be facilitated in the detection of five different categories of cervical cancer and similar cellular disease cases with the Pap-smear image retrieval technology. In this study, an algorithm for retrieval of cervical cancer images using hash coding with a Convolutional Neural Network (CNN) has been implemented. A sensitive deep hashing method combining interpretable mask generation and rotation invariance is proposed for cervical cancer detection. The distinctive features of cervical cancer cells with complex morphological features are focused on with the proposed hybrid dilated convolution spatial attention module and insignificant features are eliminated. Moreover, the loss function of Cauchy rotation invariance in terms of cervical cancer cell target is presented. In this way, the differences in the input samples are revealed, allowing the CNN to learn from different angles and achieve certain rotation invariance. The versatility and performance of the proposed method, as well as the efficiency of the loss function, have been tested on the SIPaKMeD and Mendeley LBC datasets consisting of cervical cancer images. In the experimental results obtained, it is shown that the proposed spatial attention module and rotational invariance deep hashing network generate high performance in cervical cancer image retrieval problems.