ABSTRACT
Background: Melanoma is one of the deadliest skin cancers that originate from melanocytes due to sun exposure, causing mutations. Early detection boosts the cure rate to 90%, but misclassification drops survival to 15-20%. Clinical variations challenge dermatologists in distinguishing benign nevi and melanomas. Current diagnostic methods, including visual analysis and dermoscopy, have limitations, emphasizing the need for Artificial Intelligence understanding in dermatology. Objectives: In this paper, we aim to explore dermoscopic structures for the classification of melanoma lesions. The training of AI models faces a challenge known as brittleness, where small changes in input images impact the classification. A study explored AI vulnerability in discerning melanoma from benign lesions using features of size, color, and shape. Tests with artificial and natural variations revealed a notable decline in accuracy, emphasizing the necessity for additional information, such as dermoscopic structures. Methodology: The study utilizes datasets with clinically marked dermoscopic images examined by expert clinicians. Transformers and CNN-based models are employed to classify these images based on dermoscopic structures. Classification results are validated using feature visualization. To assess model susceptibility to image variations, classifiers are evaluated on test sets with original, duplicated, and digitally modified images. Additionally, testing is done on ISIC 2016 images. The study focuses on three dermoscopic structures crucial for melanoma detection: Blue-white veil, dots/globules, and streaks. Results: In evaluating model performance, adding convolutions to Vision Transformers proves highly effective for achieving up to 98% accuracy. CNN architectures like VGG-16 and DenseNet-121 reach 50-60% accuracy, performing best with features other than dermoscopic structures. Vision Transformers without convolutions exhibit reduced accuracy on diverse test sets, revealing their brittleness. OpenAI Clip, a pre-trained model, consistently performs well across various test sets. To address brittleness, a mitigation method involving extensive data augmentation during training and 23 transformed duplicates during test time, sustains accuracy. Conclusions: This paper proposes a melanoma classification scheme utilizing three dermoscopic structures across Ph2 and Derm7pt datasets. The study addresses AI susceptibility to image variations. Despite a small dataset, future work suggests collecting more annotated datasets and automatic computation of dermoscopic structural features.
ABSTRACT
Background: Carbon tetrachloride (CCl 4 ) is extensively used in various industries and induces oxidative stress in humans. Unfortunately, it is one of the neglected potent male reproductive toxicants. Objective: The present research reports the testicular histopathology of CCl 4 and ameliorations by four medicinal fruit pulp extracts (FPEs) in mice. Materials and Methods: Sixty male albino mice were divided into six groups (10/group) as per the following: 1. Vehicle control (Vc); 2. CCl 4 (C); 3-6. CCl 4 +Basella alba (CBa), CCl 4 +Solanum nigrum (CSn), CCl 4 +Ficus carica (CFc) and CCl 4 +Grewia asiatica (CGa). Except for the control group, CCl 4 (0.1 mL of 0.2 mL kg - 1 ) was given to the animals in corn oil. The four plant extracts (0.1 mL each) were respectively given to the relevant FPE group animals for the next five consecutive days, while the animals in the Vc and CCl 4 groups received water instead of FPE. Results: The CCl 4 exposure led to various histometric and histological alterations (loss of interstitial tissue and various dislodged tailless spermatids with enlarged heads) that were recovered in all except Solanum nigrum FPE mice post-treatment. The micrometric data of testicular sections also indicated significant decline in the number of spermatogonia, while the cross-sectional area of the sperm heads remained significantly higher in the CSn and C groups. Conclusion: Except for Solanum nigrum,the three FPEs, especially Ficus carica,showed rehabilitative properties against CCl 4 exposure-related modifications in testicular histopathologies.
ABSTRACT
To study the ameliorative capacity of Syzygium cumini fruit Pulp Extract (SPE) on cryopreserved bovine semen, three ejaculates each of three fertile bulls (total nine samples) were collected. Each sample was mixed with semen dilution medium in 1:2 ratios, centrifuged, and 50% of the supernatant was discarded. The remaining sample was mixed with semen cryopreservation extender (SCE) in 1:4 ratios. Three aliquots (0.3 mL) of each extended semen sample were further diluted with (1) 0.7 mL SCE (SCE group), (2) 0.7 mL SCE containing SPE equivalent to 7 ppm total antioxidants (SPE7 group), and (3) 0.7 mL SCE equivalent to 14 ppm antioxidants (SPE14 group). For each aliquot, semen quality was analyzed in situ as well as after cryopreservation. Results show significant improvement in sperm membrane integrity, motility, and fertilizability in SPE7 (63.5% ± 2.04%, 56.22% ± 1.7%, 51.1%, respectively) and SPE14 (68% ± 1.12%, 63.67% ± 1.06%, 57.7%, respectively) than the SCE group (62.33% ± 1.22%, 54.9% ± 1.34%, 48.8%, respectively). Similarly, significant improvement in the mean percent number of progressively motile sperm at the expense of the mean percent twitching, shaking, and whirling spermatozoa, both before and after cryopreservation, were observed in SPE7 (72 ± 1.06, 61.2 ± 1.2) and SPE14 (78.89 ± 1.12, 67 ± 1.32) groups to that of the SCE (59.6 ± 0.97, 52.3 ± 3.5). In addition, the mean percent of progressively motile spermatozoa showing 20 µm/s or above velocity, before and after cryopreservation, were significantly higher in SPE7 (58.9 ± 4.7, 43.6 ± 1.5) and SPE14 (66.9 ± 0.8, 51.3 ± 0.8) groups than that of the SCE (42.3 ± 3.1, 30 ± 2.4). These findings indicate that SPE can significantly improve various quality parameters of the cryopreserved bovine semen.
