Role of AI and Histopathological Images in Detecting Prostate Cancer: A Survey

Ayyad, Sarah M.; Shehata, Mohamed; Shalaby, Ahmed; El-Ghar, Mohamed Abou; Ghazal, Mohammed; El-Melegy, Moumen T.; Abdel-Hamid, Nahla B.; Labib, Labib M.; Ali, Hesham; El-Baz, Ayman

doi:10.3390/s21082586

Cited by 45 publications

(20 citation statements)

References 106 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, automated artificial intelligence algorithms can be utilized to distinguish abnormal characteristics based on a specific symptom. In agreement with other related studies [30,31,32], artificial intelligence has shown dramatic growth in environmental monitoring and medical health applications, mainly in enhancing histopathology imagery, which can provide a breeding ground for developing bioinformatics applications in various fields.…”

Section: Discussionsupporting

confidence: 87%

Bioinformatics Research Through Image Processing of Histopathological Response to Stonefish Venom

Wahsha¹,

Wahsheh²,

Hayek³

et al. 2021

IJACSA

View full text Add to dashboard Cite

The present study utilizes coastal and environmental engineering to investigate the histopathological effects of Synanceia verrucosa venom on Albino BALB/c mice. S. verrucosa is the most hazardous venomous marine fish that belong to the family Synanceiidae, generally known as the "Reef Stonefish". Crude venom was collected from venom glands of the dorsal spines of stonefish samples taken from the Jordanian coastline of the Gulf of Aqaba, Red Sea. The mice were given intramuscular injections of the venom. Consequently, the research evaluated the acute toxicity and influence on selected serum biomarker enzymes, as well as possible histological alterations of the soleus skeletal muscles. The mice 24 h LD 50 was 0.107 µg toxin/kg mouse body weight. After the treatment using venom sublethal dose, the serum biomarkers, including Lactate dehydrogenase (LDH) and Alanine aminotransferase (ALT), were significantly improved (P≤0.05). In addition, Lipid Peroxidation (LPO) contents were significantly increased (P≤0.05) after venom treatment. Moreover, we combined routine medical procedures and artificial intelligence-assisted image analysis for a rapid qualitative and quantitative diagnosis of stonefish injury, based on the histophotography of mice tissue samples during the observation period (1, 2, and 3 hours respectively). The novelty of our method is that we could detect severe and mild damage with an accuracy of 93% and 91%, respectively. The most histological abnormalities in muscles were the great variety in diameters, content, and widespread among randomly distributed muscle fibres. In addition, loss of the tissue's striated appearance was noticed in toxin-treated groups compared with the control group. Consequently, our findings indicate the Stonefish's harmful influences that may endanger human life and highlight the need for appropriate measures to be considered. This, in turn, can ensure beach safety in the Gulf of Aqaba.

show abstract

Section: Discussionsupporting

confidence: 87%

Bioinformatics Research Through Image Processing of Histopathological Response to Stonefish Venom

Wahsha¹,

Wahsheh²,

Hayek³

et al. 2021

IJACSA

View full text Add to dashboard Cite

show abstract

“…Observation of biodegradable implants requires an accurate localization of the implant and its borders, especially because of the constant changes over time. There lies the challenge of unclear border areas and artefacts, where individual judgement of the operator doing the analysis can affect the resulting data [ 89 ]. The use of machine learning, such as deep neural networks [ 90 , 91 ], has a potential to improve the speed and accuracy of image analysis, reducing the effect of human error and differences in individual judgements.…”

Section: Discussionmentioning

confidence: 99%

In Vivo Imaging of Biodegradable Implants and Related Tissue Biomarkers

et al. 2021

View full text Add to dashboard Cite

Non-invasive longitudinal imaging of osseointegration of bone implants is essential to ensure a comprehensive, physical and biochemical understanding of the processes related to a successful implant integration and its long-term clinical outcome. This study critically reviews the present imaging techniques that may play a role to assess the initial stability, bone quality and quantity, associated tissue remodelling dependent on implanted material, implantation site (surrounding tissues and placement depth), and biomarkers that may be targeted. An updated list of biodegradable implant materials that have been reported in the literature, from metal, polymer and ceramic categories, is provided with reference to the use of specific imaging modalities (computed tomography, positron emission tomography, ultrasound, photoacoustic and magnetic resonance imaging) suitable for longitudinal and non-invasive imaging in humans. The advantages and disadvantages of the single imaging modality are discussed with a special focus on preclinical imaging for biodegradable implant research. Indeed, the investigation of a new implant commonly requires histological examination, which is invasive and does not allow longitudinal studies, thus requiring a large number of animals for preclinical testing. For this reason, an update of the multimodal and multi-parametric imaging capabilities will be here presented with a specific focus on modern biomaterial research.

show abstract

“…With the development of CNN models, most of the histopathological image classification models [24], [25] are originated from the popular classification backbones from the natural image classification. However, histopathological image classification faces different challenges, such as extremely large image resolution, deficiency of labels and multiscale information integration [26]. WSI-Net [27] model was proposed to add an additional classification branch to discard the normal tissue in order to save computational resources.…”

Section: A Histopathological Image Classificationmentioning

confidence: 99%

PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learning

Lin¹,

Han²,

Pan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Histopathological tissue classification is a fundamental task in pathomics cancer research. Precisely differentiating different tissue types is a benefit for the downstream researches, like cancer diagnosis, prognosis and etc. Existing works mostly leverage the popular classification backbones in computer vision to achieve histopathological tissue classification. In this paper, we proposed a super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), for any well-trained classification backbone to further improve the classification performance without a re-training burden. We mimic how pathologists observe pathology slides in different magnifications and construct an image pyramid for the input image in order to obtain the pyramidal contextual information. For each level in the pyramid, we extract the multi-scale deep-broad features by our proposed Deep-Broad block (DB-block). We equipped PDBL in three popular classification backbones, ShuffLeNetV2, EfficientNetb0, and ResNet50 to evaluate the effectiveness and efficiency of our proposed module on two datasets (Kather Multiclass Dataset and the LC25000 Dataset). Experimental results demonstrate the proposed PDBL can steadily improve the tissue-level classification performance for any CNN backbones, especially for the lightweight models when given a small among of training samples (less than 10%), which greatly saves the computational time and annotation efforts.

show abstract

Role of AI and Histopathological Images in Detecting Prostate Cancer: A Survey

Cited by 45 publications

References 106 publications

Bioinformatics Research Through Image Processing of Histopathological Response to Stonefish Venom

Bioinformatics Research Through Image Processing of Histopathological Response to Stonefish Venom

In Vivo Imaging of Biodegradable Implants and Related Tissue Biomarkers

PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learning

Contact Info

Product

Resources

About